{
  "schema_version": "1.0",
  "title": "SOS+CD publication catalog",
  "url": "https://scienceofscience.org/publications/",
  "updated": "2026-09-07T23:57:57.998602+00:00",
  "record_count": 70,
  "first_year": 2008,
  "topics": {"integrity":{"label":"Research integrity","short_label":"Integrity","description":"Trustworthy research: figure and journal quality, citation practices, review bias, reproducibility, and responsible AI.","aliases":["integrity","research integrity","scientific integrity"],"count":18},"discovery":{"label":"Peer review & discovery","short_label":"Discovery","description":"Scientific peer review, research recommendation, and computational tools for finding and interpreting scholarly information.","aliases":["discovery","computational discovery","peer review and discovery","peer review and computational discovery"],"count":24},"ecosystem":{"label":"Science of science","short_label":"Ecosystem","description":"How careers, collaboration, funding, recognition, and scholarly infrastructure shape science.","aliases":["science of science","ecosystem","research ecosystem","scientometrics","bibliometrics","science"],"count":33},"foundations":{"label":"Cognition & methods","short_label":"Methods","description":"Foundational work in learning, decision-making, neuroscience, human–computer interaction, and computational methods.","aliases":["cognition and methods","cognition","foundations","methods"],"count":25}},
  "tags": {"ai-bias":{"label":"AI bias & explainability","aliases":["ai bias","perception bias","explainable ai","comparative explanations","algorithmic bias"],"count":2},"citation-analysis":{"label":"Citation analysis","aliases":["citations","citation networks","citation impact","h index"],"count":10},"citation-practices":{"label":"Citation practices","aliases":["citation worthiness","citation worthiness detection","citation missingness","missing citations"],"count":1},"dataset-discovery":{"label":"Dataset discovery & reuse","aliases":["dataset discovery","data discovery","dataset reuse","data reuse","dataset credit"],"count":5},"decision-making":{"label":"Decision-making","aliases":["decision making","uncertainty","bayesian","bandit","exploration"],"count":12},"diversity":{"label":"Diversity & inclusion","aliases":["diversity","inclusion","gender","inequality","disparities","equity"],"count":8},"figure-accessibility":{"label":"Figure accessibility","aliases":["figure readability","color blindness","colour blindness","figure explainability"],"count":1},"figure-integrity":{"label":"Figure integrity","aliases":["scientific figure integrity"],"count":5},"graphical-integrity":{"label":"Graphical integrity","aliases":["misleading graphs","misleading charts","proportional ink","graphical integrity"],"count":2},"human-computer-interaction":{"label":"Human–computer interaction","aliases":["human computer interaction","hci","robotics","mobile computing"],"count":3},"image-forensics":{"label":"Image reuse & forensics","aliases":["image integrity","figure reuse","image reuse","image duplication","image manipulation","image tampering","image forensics"],"count":3},"interdisciplinarity":{"label":"Interdisciplinarity","aliases":["interdisciplinarity","interdisciplinary","interdisciplinary engagement"],"count":2},"language-models":{"label":"Language models","aliases":["llm","llms","large language models","generative ai"],"count":4},"mentorship":{"label":"Mentorship","aliases":["mentorship","mentoring","mentors"],"count":3},"metadata-quality":{"label":"Metadata quality","aliases":["reference missingness","missing references","openalex","bibliometric data quality"],"count":1},"multimodal-learning":{"label":"Multimodal learning","aliases":["multimodal","multi modal","contrastive learning","image text retrieval"],"count":3},"neuroscience":{"label":"Neuroscience & motor learning","aliases":["neuroscience","motor learning","chunking","motor control","neuroprostheses","fes"],"count":4},"peer-review":{"label":"Peer review","aliases":["peer review","peerreview","review","reviewers","scientific review"],"count":5},"perception":{"label":"Perception & psychophysics","aliases":["perception","psychophysics","vision","haptics"],"count":3},"questionable-journals":{"label":"Questionable journals","aliases":["predatory journals","blacklisted journals","journal blacklisting","predatory publishing"],"count":3},"recommender-systems":{"label":"Recommender systems","aliases":["recommendation","recommendations","recommender","recommendation systems"],"count":6},"reinforcement-learning":{"label":"Reinforcement learning","aliases":["reinforcement learning","rl","grpo"],"count":9},"reproducibility":{"label":"Reproducibility & resource longevity","aliases":["reproducibility","reproducible research","resource longevity","link rot","dead science","resource decay"],"count":3},"funding":{"label":"Research funding","aliases":["funding","grants","grant recommendation","science policy","energy research"],"count":5},"research-recommendation":{"label":"Research recommendation","aliases":["scientific recommendation","literature recommendation","literature discovery","research directions"],"count":4},"responsible-ai":{"label":"Responsible AI","aliases":["ai ethics","responsible ai","research misconduct","responsible conduct of research"],"count":2},"review-bias":{"label":"Review bias","aliases":["peer review bias","reviewer bias","author suggested reviewers"],"count":2},"scholarly-data":{"label":"Scholarly data & tools","aliases":["scholarly data","scholarly tools","scholarly metadata","pubmed","author disambiguation","name disambiguation"],"count":11},"careers":{"label":"Scientific careers & recognition","aliases":["scientific careers","academic careers","scientific success","recognition","awards"],"count":6},"statistical-methods":{"label":"Statistical methods & software","aliases":["statistical methods","statistical software","generalized linear models","elastic net","pyglmnet"],"count":7},"collaboration":{"label":"Teams & collaboration","aliases":["collaboration","scientific teams","team science","teamwork","leadership","coauthorship"],"count":7},"text-mining":{"label":"Text mining & NLP","aliases":["text mining","nlp","natural language processing","knowledge extraction","information extraction","paraphrase","paraphrases"],"count":14}},
  "publications": [{
    "id": "acuna2008bayesian",
    "title": "Bayesian modeling of human sequential decision-making on the multi-armed bandit problem",
    "alternate_title": "",
    "authors": [{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"},{"name":"Paul Schrater","given":"Paul","family":"Schrater"}],
    "year": "2008",
    "publication_date": "2008",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 30th annual conference of the cognitive science society",
    "doi": "",
    "source_url": "https://core.ac.uk/download/pdf/22874996.pdf",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2008bayesian.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2008structure",
    "title": "Structure learning in human sequential decision-making",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Paul Schrater","given":"Paul","family":"Schrater"}],
    "year": "2008",
    "publication_date": "2008",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 21st International Conference on Neural Information Processing Systems",
    "doi": "",
    "source_url": "https://dl.acm.org/doi/abs/10.5555/2981780.2981781",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2008structure.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2009improving",
    "title": "Improving bayesian reinforcement learning using transition abstraction",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Paul Schrater","given":"Paul","family":"Schrater"}],
    "year": "2009",
    "publication_date": "2009",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the ICML/UAI/COLT Workshop on Abstraction in Reinforcement Learning",
    "doi": "",
    "source_url": "https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.147.5877&rep=rep1&type=pdf",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2009improving.bib",
    "topics": ["foundations"],
    "tags": ["reinforcement-learning","decision-making"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2010people",
    "title": "People efficiently explore the solution space of the computationally intractable traveling salesman problem to find near-optimal tours",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Víctor Parada","given":"Víctor","family":"Parada"}],
    "year": "2010",
    "publication_date": "2010",
    "format": "article",
    "status": "",
    "venue": "PloS ONE",
    "doi": "",
    "source_url": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0011685",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2010people.bib",
    "topics": ["foundations"],
    "tags": ["decision-making"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2010structure",
    "title": "Structure learning in human sequential decision-making",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Paul Schrater","given":"Paul","family":"Schrater"}],
    "year": "2010",
    "publication_date": "2010-12-02",
    "format": "article",
    "status": "",
    "venue": "PLoS computational biology",
    "doi": "10.1371/journal.pcbi.1001003",
    "source_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1001003",
    "page_url": "https://scienceofscience.org/publications/structure-learning/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2010structure.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": "Behavior that looks inefficient under a fixed model can make sense when a person is also learning how the environment works. This study connects human choices in sequential reward tasks with Bayesian models that learn both rewards and the structure that generates them.",
    "abstract": "Studies of sequential decision-making in humans frequently find suboptimal performance relative to an ideal actor that has perfect knowledge of the model of how rewards and events are generated in the environment. Rather than being suboptimal, we argue that the learning problem humans face is more complex, in that it also involves learning the structure of reward generation in the environment. We formulate the problem of structure learning in sequential decision tasks using Bayesian reinforcement learning, and show that learning the generative model for rewards qualitatively changes the behavior of an optimal learning agent. To test whether people exhibit structure learning, we performed experiments involving a mixture of one-armed and two-armed bandit reward models, where structure learning produces many of the qualitative behaviors deemed suboptimal in previous studies. Our results demonstrate humans can perform structure learning in a near-optimal manner.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/structure-learning/paper.pdf"}]
  },{
    "id": "acuna2011rational",
    "title": "Rational Bayesian Analysis of Sequential Decision-Making Under Uncertainty In Humans and Machines",
    "alternate_title": "",
    "authors": [{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"}],
    "year": "2011",
    "publication_date": "2011",
    "format": "phdthesis",
    "status": "",
    "venue": "University of Minnesota",
    "doi": "",
    "source_url": "https://dl.acm.org/doi/book/10.5555/2521677",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2011rational.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "avraham2012toward",
    "title": "Toward perceiving robots as humans: Three handshake models face the turing-like handshake test",
    "alternate_title": "",
    "authors": [{"name":"Guy Avraham","given":"Guy","family":"Avraham"},{"name":"Ilana Nisky","given":"Ilana","family":"Nisky"},{"name":"Hugo L Fernandes","given":"Hugo L","family":"Fernandes"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"},{"name":"Gerald E Loeb","given":"Gerald E","family":"Loeb"},{"name":"Amir Karniel","given":"Amir","family":"Karniel"}],
    "year": "2012",
    "publication_date": "2012",
    "format": "article",
    "status": "",
    "venue": "IEEE Transactions on Haptics",
    "doi": "",
    "source_url": "https://ieeexplore.ieee.org/abstract/document/6185551",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/avraham2012toward.bib",
    "topics": ["foundations"],
    "tags": ["human-computer-interaction","perception"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2012predicting",
    "title": "Predicting scientific success",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Stefano Allesina","given":"Stefano","family":"Allesina"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"}],
    "year": "2012",
    "publication_date": "2012",
    "format": "article",
    "status": "",
    "venue": "Nature",
    "doi": "",
    "source_url": "https://www.nature.com/articles/489201a",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2012predicting.bib",
    "topics": ["ecosystem"],
    "tags": ["careers","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2013future",
    "title": "The future h-index is an excellent way to predict scientistsˈ future impact",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Orion Penner","given":"Orion","family":"Penner"},{"name":"Colin G Orton","given":"Colin G","family":"Orton"}],
    "year": "2013",
    "publication_date": "2013",
    "format": "article",
    "status": "",
    "venue": "Medical Physics",
    "doi": "",
    "source_url": "https://aapm.onlinelibrary.wiley.com/doi/pdfdirect/10.1118/1.4816659",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2013future.bib",
    "topics": ["ecosystem"],
    "tags": ["careers","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2014multifaceted",
    "title": "Multifaceted aspects of chunking enable robust algorithms",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Nicholas F Wymbs","given":"Nicholas F","family":"Wymbs"},{"name":"Chelsea A Reynolds","given":"Chelsea A","family":"Reynolds"},{"name":"Nathalie Picard","given":"Nathalie","family":"Picard"},{"name":"Robert S Turner","given":"Robert S","family":"Turner"},{"name":"Peter L Strick","given":"Peter L","family":"Strick"},{"name":"Scott T Grafton","given":"Scott T","family":"Grafton"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"}],
    "year": "2014",
    "publication_date": "2014",
    "format": "article",
    "status": "",
    "venue": "Journal of neurophysiology",
    "doi": "",
    "source_url": "https://journals.physiology.org/doi/full/10.1152/jn.00028.2014",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2014multifaceted.bib",
    "topics": ["foundations"],
    "tags": ["neuroscience","decision-making"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2015using",
    "title": "Using psychophysics to ask if the brain samples or maximizes",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Max Berniker","given":"Max","family":"Berniker"},{"name":"Hugo L Fernandes","given":"Hugo L","family":"Fernandes"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"}],
    "year": "2015",
    "publication_date": "2015",
    "format": "article",
    "status": "",
    "venue": "Journal of vision",
    "doi": "",
    "source_url": "https://jov.arvojournals.org/article.aspx?articleid=2213288",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2015using.bib",
    "topics": ["foundations"],
    "tags": ["perception","decision-making"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "ramkumar2016chunking",
    "title": "Chunking as the result of an efficiency computation trade-off",
    "alternate_title": "",
    "authors": [{"name":"Pavan Ramkumar","given":"Pavan","family":"Ramkumar"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Max Berniker","given":"Max","family":"Berniker"},{"name":"Scott T Grafton","given":"Scott T","family":"Grafton"},{"name":"Robert S Turner","given":"Robert S","family":"Turner"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"}],
    "year": "2016",
    "publication_date": "2016",
    "format": "article",
    "status": "",
    "venue": "Nature communications",
    "doi": "",
    "source_url": "https://www.nature.com/articles/ncomms12176",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/ramkumar2016chunking.bib",
    "topics": ["foundations"],
    "tags": ["neuroscience","decision-making"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "ethier2016adaptive",
    "title": "Adaptive neuron-to-EMG decoder training for FES neuroprostheses",
    "alternate_title": "",
    "authors": [{"name":"Christian Ethier","given":"Christian","family":"Ethier"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"Sara A Solla","given":"Sara A","family":"Solla"},{"name":"Lee E Miller","given":"Lee E","family":"Miller"}],
    "year": "2016",
    "publication_date": "2016",
    "format": "article",
    "status": "",
    "venue": "Journal of neural engineering",
    "doi": "",
    "source_url": "https://iopscience.iop.org/article/10.1088/1741-2560/13/4/046009",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/ethier2016adaptive.bib",
    "topics": ["foundations"],
    "tags": ["neuroscience","statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "achakulvisut2016science",
    "title": "Science Concierge: A fast content-based recommendation system for scientific publications",
    "alternate_title": "",
    "authors": [{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Tulakan Ruangrong","given":"Tulakan","family":"Ruangrong"},{"name":"Konrad Kording","given":"Konrad","family":"Kording"}],
    "year": "2016",
    "publication_date": "2016",
    "format": "article",
    "status": "",
    "venue": "PloS ONE",
    "doi": "",
    "source_url": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0158423",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/achakulvisut2016science.bib",
    "topics": ["discovery"],
    "tags": ["research-recommendation","recommender-systems","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "shema2017show",
    "title": "Show Me Your App Usage and I Will Tell Who Your Close Friends Are: Predicting User’s Context from Simple Cellphone Activity",
    "alternate_title": "",
    "authors": [{"name":"Alain Shema","given":"Alain","family":"Shema"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2017",
    "publication_date": "2017",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems",
    "doi": "",
    "source_url": "https://dl.acm.org/doi/abs/10.1145/3027063.3053275",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/shema2017show.bib",
    "topics": ["foundations"],
    "tags": ["human-computer-interaction"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2018bioscience",
    "title": "Bioscience-scale automated detection of figure element reuse",
    "alternate_title": "",
    "authors": [{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Paul S Brookes","given":"Paul S","family":"Brookes"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"}],
    "year": "2018",
    "publication_date": "2018",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "BioRxiv",
    "doi": "",
    "source_url": "https://www.biorxiv.org/content/10.1101/269415v3",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2018bioscience.bib",
    "topics": ["integrity"],
    "tags": ["figure-integrity","image-forensics"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "teplitskiy2018sociology",
    "title": "The sociology of scientific validity: How professional networks shape judgement in peer review",
    "alternate_title": "",
    "authors": [{"name":"Misha Teplitskiy","given":"Misha","family":"Teplitskiy"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"Aı̈da Elamrani-Raoult","given":"Aı̈da","family":"Elamrani-Raoult"},{"name":"Konrad Körding","given":"Konrad","family":"Körding"},{"name":"James Evans","given":"James","family":"Evans"}],
    "year": "2018",
    "publication_date": "2018",
    "format": "article",
    "status": "",
    "venue": "Research Policy",
    "doi": "",
    "source_url": "https://www.sciencedirect.com/science/article/pii/S0048733318301598",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/teplitskiy2018sociology.bib",
    "topics": ["integrity","discovery","ecosystem"],
    "tags": ["peer-review","review-bias","collaboration"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "lienard2018intellectual",
    "title": "Intellectual synthesis in mentorship determines success in academic careers",
    "alternate_title": "",
    "authors": [{"name":"Jean F Liénard","given":"Jean F","family":"Liénard"},{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Stephen V David","given":"Stephen V","family":"David"}],
    "year": "2018",
    "publication_date": "2018-11-27",
    "format": "article",
    "status": "",
    "venue": "Nature communications",
    "doi": "10.1038/s41467-018-07034-y",
    "source_url": "https://www.nature.com/articles/s41467-018-07034-y",
    "page_url": "https://scienceofscience.org/publications/intellectual-synthesis-mentorship/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/lienard2018intellectual.bib",
    "topics": ["ecosystem"],
    "tags": ["mentorship","careers","interdisciplinarity"],
    "summary": "This observational study examines how graduate and postdoctoral mentorship relate to later academic careers. It asks whether combining ideas from mentors with different expertise predicts a trainee's subsequent success.",
    "abstract": "As academic careers become more competitive, junior scientists need to understand the value that mentorship brings to their success in academia. Previous research has found that, unsurprisingly, successful mentors tend to train successful students. But what characteristics of this relationship predict success, and how? We analyzed an open-access database of 18,856 researchers who have undergone both graduate and postdoctoral training, compiled across several fields of biomedical science with an emphasis on neuroscience. Our results show that postdoctoral mentors were more instrumental to trainees’ success compared to graduate mentors. Trainees’ success in academia was also predicted by the degree of intellectual synthesis between their graduate and postdoctoral mentors. Researchers were more likely to succeed if they trained under mentors with disparate expertise and integrated that expertise into their own work. This pattern has held up over at least 40 years, despite fluctuations in the number of students and availability of independent research positions.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/intellectual-synthesis-mentorship/paper.pdf"}]
  },{
    "id": "lee2019limiting",
    "title": "Limiting motor skill knowledge via incidental training protects against choking under pressure",
    "alternate_title": "",
    "authors": [{"name":"Taraz G Lee","given":"Taraz G","family":"Lee"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Konrad P Kording","given":"Konrad P","family":"Kording"},{"name":"Scott T Grafton","given":"Scott T","family":"Grafton"}],
    "year": "2019",
    "publication_date": "2019",
    "format": "article",
    "status": "",
    "venue": "Psychonomic bulletin & review",
    "doi": "",
    "source_url": "https://link.springer.com/article/10.3758/s13423-018-1486-x",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/lee2019limiting.bib",
    "topics": ["foundations"],
    "tags": ["neuroscience"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "zeng2019dead",
    "title": "Dead science: Most resources linked in biomedical articles disappear in eight years",
    "alternate_title": "",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Alain Shema","given":"Alain","family":"Shema"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2019",
    "publication_date": "2019",
    "format": "inproceedings",
    "status": "",
    "venue": "International Conference on Information",
    "doi": "",
    "source_url": "https://link.springer.com/chapter/10.1007/978-3-030-15742-5_16",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zeng2019dead.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["reproducibility","dataset-discovery"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "zeng2020finding",
    "title": "Finding datasets in publications: the Syracuse University approach",
    "alternate_title": "Dataset Mention Extraction in Scientific Articles Using Bi-LSTM-CRF Model",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "incollection",
    "status": "",
    "venue": "Rich Search and Discovery for Research Datasets",
    "doi": "10.5281/zenodo.4402304",
    "source_url": "https://surface.syr.edu/cgi/viewcontent.cgi?article=1194&context=istpub",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zeng2020finding.bib",
    "topics": ["discovery"],
    "tags": ["dataset-discovery","text-mining","scholarly-data"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "preprint", "url": "https://arxiv.org/abs/2405.13135"}]
  },{
    "id": "liang2020artificial",
    "title": "Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models",
    "alternate_title": "",
    "authors": [{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency",
    "doi": "",
    "source_url": "https://dl.acm.org/doi/abs/10.1145/3351095.3375623",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/liang2020artificial.bib",
    "topics": ["foundations"],
    "tags": ["ai-bias","perception"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/LiamLiang/Bias_AI"}]
  },{
    "id": "zeng2020assigning",
    "title": "Assigning credit to scientific datasets using article citation networks",
    "alternate_title": "",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Longfeng Wu","given":"Longfeng","family":"Wu"},{"name":"Sarah Bratt","given":"Sarah","family":"Bratt"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "article",
    "status": "",
    "venue": "Journal of Informetrics",
    "doi": "",
    "source_url": "https://www.sciencedirect.com/science/article/pii/S1751157719301841",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zeng2020assigning.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["dataset-discovery","citation-analysis","scholarly-data"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "achakulvisut2020pubmed",
    "title": "Pubmed parser: a python parser for pubmed open-access XML subset and MEDLINE XML dataset XML dataset",
    "alternate_title": "",
    "authors": [{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"},{"name":"Konrad Kording","given":"Konrad","family":"Kording"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "article",
    "status": "",
    "venue": "Journal of Open Source Software",
    "doi": "",
    "source_url": "https://joss.theoj.org/papers/10.21105/joss.01979",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/achakulvisut2020pubmed.bib",
    "topics": ["discovery"],
    "tags": ["scholarly-data","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/titipata/pubmed_parser"}]
  },{
    "id": "jas2020pyglmnet",
    "title": "Pyglmnet: Python implementation of elastic-net regularized generalized linear models",
    "alternate_title": "",
    "authors": [{"name":"Mainak Jas","given":"Mainak","family":"Jas"},{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Aid Idrizović","given":"Aid","family":"Idrizović"},{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"},{"name":"Matthew Antalek","given":"Matthew","family":"Antalek"},{"name":"Vinicius Marques","given":"Vinicius","family":"Marques"},{"name":"Tommy Odland","given":"Tommy","family":"Odland"},{"name":"Ravi Prakash Garg","given":"Ravi Prakash","family":"Garg"},{"name":"Mayank Agrawal","given":"Mayank","family":"Agrawal"},{"name":"Yu Umegaki","given":"Yu","family":"Umegaki"},{"name":"others","given":"","family":"others"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "article",
    "status": "",
    "venue": "Journal of Open Source Software",
    "doi": "",
    "source_url": "https://joss.theoj.org/papers/10.21105/joss.01959",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/jas2020pyglmnet.bib",
    "topics": ["foundations"],
    "tags": ["statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/glm-tools/pyglmnet"}]
  },{
    "id": "zeng2020modeling",
    "title": "Modeling citation worthiness by using attention-based bidirectional long short-term memory networks and interpretable models",
    "alternate_title": "",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "article",
    "status": "",
    "venue": "Scientometrics",
    "doi": "",
    "source_url": "https://link.springer.com/article/10.1007/s11192-020-03421-9",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zeng2020modeling.bib",
    "topics": ["integrity","discovery"],
    "tags": ["citation-practices","text-mining","scholarly-data"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/sciosci/cite-worthiness"},{"type": "demo", "url": "https://cite-worthiness.scienceofscience.org"}]
  },{
    "id": "zhuangacuna2020",
    "title": "An Automatic Misleading Graph Detection Tool",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "inproceedings",
    "status": "",
    "venue": "International Conference on Computational Social Science",
    "doi": "",
    "source_url": "",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhuangacuna2020.bib",
    "topics": ["integrity"],
    "tags": ["figure-integrity","graphical-integrity"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "liangacuna2020",
    "title": "Are author, affiliation, and citation networks predictive of a journal getting blacklisted?",
    "alternate_title": "",
    "authors": [{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "inproceedings",
    "status": "",
    "venue": "International Conference on Computational Social Science",
    "doi": "",
    "source_url": "https://zenodo.org/record/4403394/files/ic2s2_Liang.pdf",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/liangacuna2020.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["questionable-journals","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "liang2020don",
    "title": "Don’t judge a journal by its cover?: Appearance of a Journal’s website as predictor of blacklisted Open-Access status",
    "alternate_title": "",
    "authors": [{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the Association for Information Science and Technology",
    "doi": "",
    "source_url": "https://zenodo.org/record/4403155/files/Liang_L%20AM20.pdf",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/liang2020don.bib",
    "topics": ["integrity"],
    "tags": ["questionable-journals"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "zengacuna2020",
    "title": "Large-scale author name disambiguation using approximate network structures",
    "alternate_title": "",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020-07-17",
    "format": "inproceedings",
    "status": "",
    "venue": "International Conference on Computational Social Science",
    "doi": "10.5281/zenodo.4403705",
    "source_url": "https://scienceofscience.org/assets/pdf/ic2s2-author_name_disambiguation_zeng_and_acuna.pdf",
    "page_url": "https://scienceofscience.org/publications/ic2s2-author-name-disambiguation.html",
    "bibtex_url": "https://scienceofscience.org/publications/citations/zengacuna2020.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["scholarly-data","citation-analysis"],
    "summary": "Names alone are unreliable identifiers: different people can share a name, and one person's name can appear in several forms. This work investigates a scalable approach to author-name disambiguation using approximate network structures.",
    "abstract": "Properly identifying the author of a scientific article is an important task for giving credit, tracking progress, and identifying ideas’ lineages. Usually, publications and citations do not provide unique identifiers to authors but only the raw string character representation of their name and affiliation. The fundamental problem is that an author might change the string representations due to changing in name spelling (e.g., removing accents), journal limitations (e.g., only allow first letter of first name), or simply two people having the same name. Several researchers have proposed methods to solve this problem, but most methods do not scale well and are not open to the community. In this work, we develop a scalable method that we make publicly available to disambiguate large-scale publications",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/ic2s2-author-name-disambiguation.pdf"}]
  },{
    "id": "zeng2020gotfunding",
    "title": "GotFunding: A grant recommendation system based on scientific articles",
    "alternate_title": "",
    "authors": [{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the Association for Information Science and Technology",
    "doi": "",
    "source_url": "https://asistdl.onlinelibrary.wiley.com/doi/full/10.1002/pra2.323",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zeng2020gotfunding.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["funding","research-recommendation","recommender-systems","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "10.1145/3461702.3462616",
    "title": "Are AI Ethics Conferences Different and More Diverse Compared to Traditional Computer Science Conferences?",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"}],
    "year": "2021",
    "publication_date": "2021",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society",
    "doi": "10.1145/3461702.3462616",
    "source_url": "https://dl.acm.org/doi/pdf/10.1145/3461702.3462616",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/10-1145-3461702-3462616.bib",
    "topics": ["ecosystem"],
    "tags": ["diversity","responsible-ai"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/sciosci/demographicx"}]
  },{
    "id": "acunaiconference2022",
    "title": "Predicting the usage of scientific datasets based on article, author, institution, and journal bibliometrics",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Zijun Yi","given":"Zijun","family":"Yi"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Han Zhuang","given":"Han","family":"Zhuang"}],
    "year": "2022",
    "publication_date": "2022",
    "format": "inproceedings",
    "status": "",
    "venue": "International Conference on Information",
    "doi": "10.1007/978-3-030-96957-8_5",
    "source_url": "https://link.springer.com/chapter/10.1007/978-3-030-96957-8_5",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acunaiconference2022.bib",
    "topics": ["ecosystem"],
    "tags": ["dataset-discovery","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "zhuangacuna2021",
    "title": "Graphical integrity issues in open access publications: detection and patterns of proportional ink violations",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Tzu-Yang Huang","given":"Tzu-Yang","family":"Huang"},{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"}],
    "year": "2021",
    "publication_date": "2021-12-13",
    "format": "article",
    "status": "",
    "venue": "PloS Computational Biology",
    "doi": "10.1371/journal.pcbi.1009650",
    "source_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009650",
    "page_url": "https://scienceofscience.org/publications/graphical-integrity/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhuangacuna2021.bib",
    "topics": ["integrity"],
    "tags": ["figure-integrity","graphical-integrity"],
    "summary": "This study examines violations of the proportional ink principle: the amount of visual ink representing a value should agree with that value. It develops an automated method for detecting these inconsistencies in scientific bar charts.",
    "abstract": "Academic graphs are essential for communicating complex scientific ideas and results. To ensure that these graphs truthfully reflect underlying data and relationships, visualization researchers have proposed several principles to guide the graph creation process. However, the extent of violations of these principles in academic publications is unknown. In this work, we develop a deep learning-based method to accurately measure violations of the proportional ink principle (AUC = 0.917), which states that the size of shaded areas in graphs should be consistent with their corresponding quantities. We apply our method to analyze a large sample of bar charts contained in 300K figures from open access publications. Our results estimate that 5% of bar charts contain proportional ink violations. Further analysis reveals that these graphical integrity issues are significantly more prevalent in some research fields, such as psychology and computer science, and some regions of the globe. Additionally, we find no temporal and seniority trends in violations. Finally, apart from openly releasing our large annotated dataset and method, we discuss how computational research integrity could be part of peer-review and the publication processes.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/graphical-integrity/paper.pdf"},{"type": "code", "url": "https://github.com/sciosci/graph_check"}]
  },{
    "id": "acuna2022",
    "title": "Author-suggested reviewers rate manuscripts much more favorably: A cross-sectional analysis of the neuroscience section of PLOS ONE",
    "alternate_title": "",
    "authors": [{"name":"D E Acuna","given":"D E","family":"Acuna"},{"name":"M Teplitskiy","given":"M","family":"Teplitskiy"},{"name":"J. Evans","given":"J.","family":"Evans"},{"name":"K. Kording","given":"K.","family":"Kording"}],
    "year": "2022",
    "publication_date": "2022-12-12",
    "format": "article",
    "status": "",
    "venue": "PLOS ONE",
    "doi": "10.1371/journal.pone.0273994",
    "source_url": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0273994",
    "page_url": "https://scienceofscience.org/publications/author-suggested-reviewers/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2022.bib",
    "topics": ["integrity","discovery","ecosystem"],
    "tags": ["peer-review","review-bias"],
    "summary": "This study examines the association between author-suggested reviewers and peer-review outcomes. It uses records from the neuroscience section of PLOS ONE to compare reviewer invitations, evaluations, and acceptance outcomes.",
    "abstract": "Peer review is an important part of science, aimed at providing expert and objective assessment of a manuscript. Because of many factors, including time constraints, unique expertise needs, and deference, many journals ask authors to suggest peer reviewers for their own manuscript. Previous researchers have found differing effects about this practice that might be inconclusive due to sample sizes. In this article, we analyze the association between author-suggested reviewers and review invitation, review scores, acceptance rates, and subjective review quality using a large dataset of close to 8K manuscripts from 46K authors and 21K reviewers from the journal PLOS ONE’s Neuroscience section. We found that all-author-suggested review panels increase the chances of acceptance by 20 percent points vs all-editor-suggested panels while agreeing to review less often. While PLOS ONE has since ended the practice of asking for suggested reviewers, many others still use them and perhaps should consider the results presented here.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/author-suggested-reviewers/paper.pdf"}]
  },{
    "id": "keacuna2022",
    "title": "A dataset of mentorship in bioscience with semantic and demographic estimations",
    "alternate_title": "",
    "authors": [{"name":"Q. Ke","given":"Q.","family":"Ke"},{"name":"L. Liang","given":"L.","family":"Liang"},{"name":"Y. Ding","given":"Y.","family":"Ding"},{"name":"S V David","given":"S V","family":"David"},{"name":"D E Acuna","given":"D E","family":"Acuna"}],
    "year": "2022",
    "publication_date": "2022-08-02",
    "format": "article",
    "status": "",
    "venue": "Scientific Data",
    "doi": "10.1038/s41597-022-01578-x",
    "source_url": "https://www.nature.com/articles/s41597-022-01578-x",
    "page_url": "https://scienceofscience.org/publications/mentorship-dataset/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/keacuna2022.bib",
    "topics": ["ecosystem"],
    "tags": ["mentorship","scholarly-data","diversity"],
    "summary": "This data descriptor introduces a resource linking academic mentorship relationships to publication records, research representations, and demographic estimates. It is designed to support analysis of mentorship and scientific careers.",
    "abstract": "Mentorship in science is crucial for topic choice, career decisions, and the success of mentees and mentors. Typically, researchers who study mentorship use article co-authorship and doctoral dissertation datasets. However, available datasets of this type focus on narrow selections of fields and miss out on early career and non-publication-related interactions. Here, we describe Mentorship, a crowdsourced dataset of 743176 mentorship relationships among 738989 scientists primarily in biosciences that avoids these shortcomings. Our dataset enriches the Academic Family Tree project by adding publication data from the Microsoft Academic Graph and “semantic” representations of research using deep learning content analysis. Because gender and race have become critical dimensions when analyzing mentorship and disparities in science, we also provide estimations of these factors. We perform extensive validations of the profile–publication matching, semantic content, and demographic inferences, which mostly cover neuroscience and biomedical sciences. We anticipate this dataset will spur the study of mentorship in science and deepen our understanding of its role in scientists’ career outcomes.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/mentorship-dataset/paper.pdf"},{"type": "dataset", "url": "https://zenodo.org/record/4917086"}]
  },{
    "id": "zhuang2023computational",
    "title": "A computational analysis of accessibility, readability, and explainability of figures in open access publications",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Tzu-Yang Huang","given":"Tzu-Yang","family":"Huang"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2023",
    "publication_date": "2023",
    "format": "article",
    "status": "",
    "venue": "EPJ Data Science",
    "doi": "",
    "source_url": "https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-023-00380-y",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhuang2023computational.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["figure-accessibility"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "10.1162/qss_a_00332",
    "title": "Incorporating costs and benefits to the evaluation of uncertain research results: applications to cancer research funding",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "article",
    "status": "",
    "venue": "Quantitative Science Studies",
    "doi": "10.1162/qss_a_00332",
    "source_url": "https://doi.org/10.1162/qss_a_00332",
    "page_url": "https://scienceofscience.org/publications/research-costs-benefits/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/10-1162-qss-a-00332.bib",
    "topics": ["ecosystem","foundations"],
    "tags": ["funding","decision-making"],
    "summary": "A study's chance of being correct is only one part of deciding whether a research program is worth pursuing. This paper develops a decision-theoretic framework that makes potential costs and benefits explicit.",
    "abstract": "Abstract Correctness is a key aspiration of the scientific process, yet recent studies suggest that many high-profile findings may be difficult to replicate or require considerable evidence for verification. Proposals to fix these issues typically ask for tighter statistical controls (e.g., stricter p-value thresholds or higher statistical power). However, these approaches often overlook the importance of contemplating research outcomes’ potential costs and benefits. Here, we develop a framework grounded in Bayesian decision theory that seamlessly integrates cost-benefit analysis into evaluating research programs with potentially uncertain results. We derive minimally acceptable prestudy odds and positive predictive values for cost and benefit levels. We show that tolerance to inaccurate results changes dramatically due to uncertainties posed by research. We also show that reducing uncertainties (e.g., by recruiting more subjects) may have limited effects on the expected benefit of continuing specific research programs. We apply our framework to several types of cancer research and their funding. Our analysis shows that highly exploratory research designs are easily justifiable due to their potential benefits, even when probabilistic models suggest otherwise. We discuss how the cost and benefit of research could and should always be part of the toolkit used by scientists, institutions, or funding agencies.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://direct.mit.edu/qss/article-pdf/5/4/1047/2482654/qss_a_00332.pdf"}]
  },{
    "id": "novoa2024science",
    "title": "Science Needs You: Mobilizing for Diversity in Award Recognition",
    "alternate_title": "",
    "authors": [{"name":"Elizabeth Novoa-Monsalve","given":"Elizabeth","family":"Novoa-Monsalve"},{"name":"David Patterson","given":"David","family":"Patterson"},{"name":"Stephanie Ludi","given":"Stephanie","family":"Ludi"},{"name":"Daniel E Acuna","given":"Daniel E","family":"Acuna"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "article",
    "status": "",
    "venue": "Communications of the ACM",
    "doi": "",
    "source_url": "https://dl.acm.org/doi/10.1145/3651150",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/novoa2024science.bib",
    "topics": ["ecosystem"],
    "tags": ["diversity","careers"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "taechoyotin2024misti",
    "title": "MISTI: Metadata-Informed Scientific Text and Image Representation through Contrastive Learning",
    "alternate_title": "",
    "authors": [{"name":"Pawin Taechoyotin","given":"Pawin","family":"Taechoyotin"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",
    "doi": "10.18653/v1/2024.sdp-1.15",
    "source_url": "https://aclanthology.org/2024.sdp-1.15/",
    "page_url": "https://scienceofscience.org/publications/misti/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/taechoyotin2024misti.bib",
    "topics": ["discovery"],
    "tags": ["multimodal-learning","text-mining","scholarly-data"],
    "summary": "MISTI learns joint representations of scientific figures, captions, and publication metadata. The study tests whether contextual information such as titles, sections, and concepts improves retrieval beyond the image-caption pair alone.",
    "abstract": "In scientific publications, automatic representations of figures and their captions can be used in NLP, computer vision, and information retrieval tasks. Contrastive learning has proven effective for creating such joint representations for natural scenes, but its application to scientific imagery and descriptions remains under-explored. Recent open-access publication datasets provide an opportunity to understand the effectiveness of this technique as well as evaluate the usefulness of additional metadata, which are available only in the scientific context. Here, we introduce MISTI, a novel model that uses contrastive learning to simultaneously learn the representation of figures, captions, and metadata, such as a paper’s title, sections, and curated concepts from the PubMed Open Access Subset. We evaluate our model on multiple information retrieval tasks, showing substantial improvements over baseline models. Notably, incorporating metadata doubled retrieval performance, achieving a Recall@1 of 30% on a 70K-item caption retrieval task. We qualitatively explore how metadata can be used to strategically retrieve distinctive representations of the same concept but for different sections, such as introduction and results. Additionally, we show that our model seamlessly handles out-of-domain tasks related to image segmentation. We share our dataset and methods (https://github.com/Khempawin/scientific-image-caption-pair/tree/section-attr) and outline future research directions.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/misti/paper.pdf"},{"type": "code", "url": "https://github.com/Khempawin/scientific-image-caption-pair/tree/section-attr"}]
  },{
    "id": "XU2024103542",
    "title": "The impact of heterogeneous shared leadership in scientific teams",
    "alternate_title": "Shared Leadership in Scientific Teams: Heterogeneity vs. Homogeneity",
    "authors": [{"name":"Huimin Xu","given":"Huimin","family":"Xu"},{"name":"Meijun Liu","given":"Meijun","family":"Liu"},{"name":"Yi Bu","given":"Yi","family":"Bu"},{"name":"Shujing Sun","given":"Shujing","family":"Sun"},{"name":"Yi Zhang","given":"Yi","family":"Zhang"},{"name":"Chenwei Zhang","given":"Chenwei","family":"Zhang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Steven Gray","given":"Steven","family":"Gray"},{"name":"Eric Meyer","given":"Eric","family":"Meyer"},{"name":"Ying Ding","given":"Ying","family":"Ding"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "article",
    "status": "",
    "venue": "Information Processing & Management",
    "doi": "10.1016/j.ipm.2023.103542",
    "source_url": "https://www.sciencedirect.com/science/article/pii/S0306457323002790",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/xu2024103542.bib",
    "topics": ["ecosystem"],
    "tags": ["collaboration","diversity"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "leto2024first",
    "title": "A First Step towards Measuring Interdisciplinary Engagement in Scientific Publications: A Case Study on NLP+ CSS Research",
    "alternate_title": "",
    "authors": [{"name":"Alexandria Leto","given":"Alexandria","family":"Leto"},{"name":"Shamik Roy","given":"Shamik","family":"Roy"},{"name":"Alexander Hoyle","given":"Alexander","family":"Hoyle"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"María Leonor Pacheco","given":"María Leonor","family":"Pacheco"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+ CSS 2024)",
    "doi": "",
    "source_url": "https://aclanthology.org/2024.nlpcss-1.11/",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/leto2024first.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["interdisciplinarity","citation-analysis","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "Bibal2024",
    "title": "RecSOI: recommending research directions using statements of ignorance",
    "alternate_title": "",
    "authors": [{"name":"Adrien Bibal","given":"Adrien","family":"Bibal"},{"name":"Nourah M. Salem","given":"Nourah M.","family":"Salem"},{"name":"Rémi Cardon","given":"Rémi","family":"Cardon"},{"name":"Elizabeth K. White","given":"Elizabeth K.","family":"White"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Robin Burke","given":"Robin","family":"Burke"},{"name":"Lawrence E. Hunter","given":"Lawrence E.","family":"Hunter"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "article",
    "status": "",
    "venue": "Journal of Biomedical Semantics",
    "doi": "10.1186/s13326-024-00304-3",
    "source_url": "https://doi.org/10.1186/s13326-024-00304-3",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/bibal2024.bib",
    "topics": ["discovery"],
    "tags": ["research-recommendation","recommender-systems","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "taechoyotin2024mamorx",
    "title": "MAMORX: Multi-agent Multi-modal Scientific Review Generation with External Knowledge",
    "alternate_title": "",
    "authors": [{"name":"Pawin Taechoyotin","given":"Pawin","family":"Taechoyotin"},{"name":"Guanchao Wang","given":"Guanchao","family":"Wang"},{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Bradley Sides","given":"Bradley","family":"Sides"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "inproceedings",
    "status": "",
    "venue": "NeurIPS 2024 Workshop on Foundation Models for Science: Progress, Opportunities, and Challenges",
    "doi": "",
    "source_url": "https://openreview.net/forum?id=frvkE8rCfX",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/taechoyotin2024mamorx.bib",
    "topics": ["discovery"],
    "tags": ["peer-review","language-models","multimodal-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "code", "url": "https://github.com/sciosci/mamorx-review-system"},{"type": "demo", "url": "https://rev0.ai"}]
  },{
    "id": "varasteh2024comparative",
    "title": "Comparative Explanations for Recommendation: Research Directions",
    "alternate_title": "",
    "authors": [{"name":"Meysam Varasteh","given":"Meysam","family":"Varasteh"},{"name":"Elizabeth McKinnie","given":"Elizabeth","family":"McKinnie"},{"name":"Amanda Aird","given":"Amanda","family":"Aird"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Robin Burke","given":"Robin","family":"Burke"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "inproceedings",
    "status": "",
    "venue": "Proceedings of the 11th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2024), co-located with RecSys 2024",
    "doi": "",
    "source_url": "https://ceur-ws.org/Vol-3815/paper1.pdf",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/varasteh2024comparative.bib",
    "topics": ["discovery","foundations"],
    "tags": ["recommender-systems","ai-bias","human-computer-interaction"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "zhou2022paraphrase",
    "title": "Paraphrase Identification with Deep Learning: A Review of Datasets and Methods",
    "alternate_title": "",
    "authors": [{"name":"Chao Zhou","given":"Chao","family":"Zhou"},{"name":"Cheng Qiu","given":"Cheng","family":"Qiu"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2025",
    "publication_date": "2025",
    "format": "article",
    "status": "",
    "venue": "IEEE Access",
    "doi": "10.1109/ACCESS.2025.3556899",
    "source_url": "https://doi.org/10.1109/ACCESS.2025.3556899",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhou2022paraphrase.bib",
    "topics": ["discovery","foundations"],
    "tags": ["text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2022predicting",
    "title": "Predicting the longevity of resources shared in scientific publications",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Jian Jian","given":"Jian","family":"Jian"},{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Han Zhuang","given":"Han","family":"Zhuang"}],
    "year": "2025",
    "publication_date": "2025-05-22",
    "format": "article",
    "status": "",
    "venue": "Humanities and Social Sciences Communications",
    "doi": "10.1057/s41599-025-04716-z",
    "source_url": "https://doi.org/10.1057/s41599-025-04716-z",
    "page_url": "https://scienceofscience.org/publications/predicting-the-longevity-of-resources-shared-in-scientific-publications.html",
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2022predicting.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["reproducibility","dataset-discovery"],
    "summary": "Code and data links can stop working long after a paper is published. This study examines which features of a resource, its host, and its associated publication help explain and predict its availability over time.",
    "abstract": "Research has shown that most resources shared in articles (e.g., URLs to code or data) are not kept up to date and mostly disappear from the web after some years (Zeng et al., 2019). Little is known about the factors that differentiate and predict the longevity of these resources. This article explores a range of explanatory features related to the publication venue, authors, references, and where the resource is shared. We analyze an extensive repository of publications and, through web archival services, reconstruct how they looked at different time points. We discover that the most important factors are related to where and how the resource is shared, while surprisingly little consideration is given to the author’s reputation or prestige of the journal. By examining the places where long-lasting resources are shared, we suggest that it is critical to educate researchers on modern sharing technologies. Finally, we discuss implications for reproducibility and acknowledge scientific datasets as first-class citizens of science.",
    "abstract_license": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/predicting-the-longevity-of-resources-shared-in-scientific-publications.pdf"},{"type": "preprint", "url": "https://arxiv.org/abs/2203.12800"},{"type": "code", "url": "https://github.com/sciosci/predicting_resource_longevity/"}]
  },{
    "id": "zhuang2025estimating",
    "title": "Estimating the predictability of questionable open-access journals",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2025",
    "publication_date": "2025-08-27",
    "format": "article",
    "status": "",
    "venue": "Science Advances",
    "doi": "10.1126/sciadv.adt2792",
    "source_url": "https://doi.org/10.1126/sciadv.adt2792",
    "page_url": "https://scienceofscience.org/publications/questionable-journals/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhuang2025estimating.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["questionable-journals"],
    "summary": "This study evaluates whether journal websites and publication metadata can support large-scale screening for questionable open-access journals. It treats automated predictions as a way to focus expert investigation.",
    "abstract": "Questionable journals threaten global research integrity, yet manual vetting can be slow and inflexible. Here, we explore the potential of artificial intelligence (AI) to systematically identify such venues by analyzing website design, content, and publication metadata. Evaluated against extensive human-annotated datasets, our method achieves practical accuracy and uncovers previously overlooked indicators of journal legitimacy. By adjusting the decision threshold, our method can prioritize either comprehensive screening or precise, low-noise identification. At a balanced threshold, we flag over 1000 suspect journals, which collectively publish hundreds of thousands of articles, receive millions of citations, acknowledge funding from major agencies, and attract authors from developing countries. Error analysis reveals challenges involving discontinued titles, book series misclassified as journals, and small society outlets with limited online presence, which are issues addressable with improved data quality. Our findings demonstrate AI’s potential for scalable integrity checks, while also highlighting the need to pair automated triage with expert review.",
    "abstract_license": "https://creativecommons.org/licenses/by-nc/4.0/",
    "resources": [{"type": "pdf", "url": "https://www.science.org/doi/pdf/10.1126/sciadv.adt2792"}]
  },{
    "id": "zhou2026widespread",
    "title": "Widespread reference missingness disparities in open scholarly metadata",
    "alternate_title": "",
    "authors": [{"name":"Huaxia Zhou","given":"Huaxia","family":"Zhou"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2026",
    "publication_date": "2026",
    "format": "article",
    "status": "",
    "venue": "Quantitative Science Studies",
    "doi": "10.1162/qss.a.400",
    "source_url": "https://doi.org/10.1162/qss.a.400",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhou2026widespread.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["metadata-quality","scholarly-data","citation-analysis","diversity"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "xu2026beyond",
    "title": "Beyond a number game: Flat team structures improve inclusion and performance in diverse scientific teams",
    "alternate_title": "Beyond a Number Game: Flat Structures Foster Minority Inclusion in Diverse Scientific Teams",
    "authors": [{"name":"Huimin Xu","given":"Huimin","family":"Xu"},{"name":"Shujing Sun","given":"Shujing","family":"Sun"},{"name":"Meijun Liu","given":"Meijun","family":"Liu"},{"name":"Chenwei Zhang","given":"Chenwei","family":"Zhang"},{"name":"Yi Bu","given":"Yi","family":"Bu"},{"name":"Yi Zhang","given":"Yi","family":"Zhang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Eric Meyer","given":"Eric","family":"Meyer"},{"name":"Ying Ding","given":"Ying","family":"Ding"}],
    "year": "2026",
    "publication_date": "2026",
    "format": "article",
    "status": "",
    "venue": "Journal of the Association for Information Science and Technology",
    "doi": "10.1002/asi.70083",
    "source_url": "https://doi.org/10.1002/asi.70083",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/xu2026beyond.bib",
    "topics": ["ecosystem"],
    "tags": ["collaboration","diversity"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "preprint", "url": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4751297"}]
  },{
    "id": "kusumegi2026dissecting",
    "title": "Dissecting the gender divide: authorship and acknowledgment in scientific publications",
    "alternate_title": "",
    "authors": [{"name":"Keigo Kusumegi","given":"Keigo","family":"Kusumegi"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Yukie Sano","given":"Yukie","family":"Sano"}],
    "year": "2026",
    "publication_date": "2026",
    "format": "article",
    "status": "",
    "venue": "Scientometrics",
    "doi": "10.1007/s11192-026-05712-z",
    "source_url": "https://doi.org/10.1007/s11192-026-05712-z",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/kusumegi2026dissecting.bib",
    "topics": ["ecosystem"],
    "tags": ["diversity","collaboration","careers"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "meguimtsop2026sciintbench",
    "title": "SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing",
    "alternate_title": "",
    "authors": [{"name":"Almene De Meran Meguimtsop","given":"Almene De Meran","family":"Meguimtsop"},{"name":"Maria Leonor Pacheco","given":"Maria Leonor","family":"Pacheco"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2026",
    "publication_date": "2026-05-28",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv preprint arXiv:2605.29468",
    "doi": "10.48550/arXiv.2605.29468",
    "source_url": "https://arxiv.org/abs/2605.29468",
    "page_url": "https://scienceofscience.org/publications/sciintbench/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/meguimtsop2026sciintbench.bib",
    "topics": ["integrity","discovery"],
    "tags": ["responsible-ai","language-models"],
    "summary": "SciIntBench evaluates how language models respond to scientific requests framed as explicit misconduct, covert misconduct, or legitimate work. It measures both refusal of problematic requests and helpfulness on benign ones.",
    "abstract": "Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchmark of 810 prompts across ten RCR categories and three scientific domains. Each scenario appears as an Overt Adversarial, Covert Adversarial, and Benign version, allowing us to jointly measure framing-sensitive refusal of misconduct and helpfulness on legitimate requests. We evaluate 16 commercial and open-weight LLMs from six providers (2024--2026), producing 12,960 responses. We find that scientific integrity alignment is strongly framing-sensitive: models refuse explicit misconduct far more reliably than covert violations, especially failing when misconduct is presented as a pressure-driven shortcut. Refusals vary by RCR category, with weaker boundaries around transparency, plagiarism, and fabrication.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/sciintbench/paper.pdf"}]
  },{
    "id": "taechoyotin2026remctx",
    "title": "REM-CTX: Automated Peer Review via Reinforcement Learning with Auxiliary Context",
    "alternate_title": "",
    "authors": [{"name":"Pawin Taechoyotin","given":"Pawin","family":"Taechoyotin"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2026",
    "publication_date": "2026-03-31",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv preprint arXiv:2604.00248",
    "doi": "10.48550/arXiv.2604.00248",
    "source_url": "https://arxiv.org/abs/2604.00248",
    "page_url": "https://scienceofscience.org/publications/rem-ctx/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/taechoyotin2026remctx.bib",
    "topics": ["discovery"],
    "tags": ["peer-review","language-models","reinforcement-learning","multimodal-learning"],
    "summary": "REM-CTX extends review generation beyond manuscript text. It trains a language model to use auxiliary context and tests whether explicit correspondence rewards improve the grounding of generated reviews.",
    "abstract": "Most automated peer review systems rely on textual manuscript content alone, leaving visual elements such as figures and external scholarly signals underutilized. We introduce REM-CTX, a reinforcement-learning system that incorporates auxiliary context into the review generation process via correspondence-aware reward functions. REM-CTX trains an 8B-parameter language model with Group Relative Policy Optimization (GRPO) and combines a multi-aspect quality reward with two correspondence rewards that explicitly encourage alignment with auxiliary context. Experiments on manuscripts across Computer, Biological, and Physical Sciences show that REM-CTX achieves the highest overall review quality among six baselines, outperforming other systems with substantially larger commercial models, and surpassing the next-best RL baseline across both quality and contextual grounding metrics. Ablation studies confirm that the two correspondence rewards are complementary: each selectively improves its targeted correspondence reward while preserving all quality dimensions, and the full model outperforms all partial variants. Analysis of training dynamics reveals that the criticism aspect is negatively correlated with other metrics during training, suggesting that future studies should group multi-dimension rewards for review generation.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://arxiv.org/pdf/2604.00248"}]
  },{
    "id": "popp2026government",
    "title": "Government Funding and the Direction of Academic Energy Research",
    "alternate_title": "",
    "authors": [{"name":"David Popp","given":"David","family":"Popp"},{"name":"Myriam Gregoire-Zawilski","given":"Myriam","family":"Gregoire-Zawilski"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2026",
    "publication_date": "2026",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "NBER Working Paper No. 34856",
    "doi": "10.3386/w34856",
    "source_url": "https://doi.org/10.3386/w34856",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/popp2026government.bib",
    "topics": ["ecosystem"],
    "tags": ["funding"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "taechoyotin2025remor",
    "title": "REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning",
    "alternate_title": "",
    "authors": [{"name":"Pawin Taechoyotin","given":"Pawin","family":"Taechoyotin"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2025",
    "publication_date": "2025-05-16",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv preprint arXiv:2505.11718",
    "doi": "10.48550/arXiv.2505.11718",
    "source_url": "https://arxiv.org/abs/2505.11718",
    "page_url": "https://scienceofscience.org/publications/remor/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/taechoyotin2025remor.bib",
    "topics": ["discovery"],
    "tags": ["peer-review","language-models","reinforcement-learning"],
    "summary": "REMOR studies review generation with a reasoning language model and rewards for multiple aspects of review quality. It compares different reward designs and examines how training changes the feedback produced.",
    "abstract": "AI-based peer review systems tend to produce shallow and overpraising suggestions compared to human feedback. Here, we evaluate how well a reasoning LLM trained with multi-objective reinforcement learning (REMOR) can overcome these limitations. We start by designing a multi-aspect reward function that aligns with human evaluation of reviews. The aspects are related to the review itself (e.g., criticisms, novelty) and the relationship between the review and the manuscript (i.e., relevance). First, we perform supervised fine-tuning of DeepSeek-R1-Distill-Qwen-7B using LoRA on PeerRT, a new dataset of high-quality top AI conference reviews enriched with reasoning traces. We then apply Group Relative Policy Optimization (GRPO) to train two models: REMOR-H (with the human-aligned reward) and REMOR-U (with a uniform reward). Interestingly, the human-aligned reward penalizes aspects typically associated with strong reviews, leading REMOR-U to produce qualitatively more substantive feedback. Our results show that REMOR-U and REMOR-H achieve more than twice the average rewards of human reviews, non-reasoning state-of-the-art agentic multi-modal AI review systems, and general commercial LLM baselines. We found that while the best AI and human reviews are comparable in quality, REMOR avoids the long tail of low-quality human reviews. We discuss how reasoning is key to achieving these improvements and release the Human-aligned Peer Review Reward (HPRR) function, the Peer Review Reasoning-enriched Traces (PeerRT) dataset, and the REMOR models, which we believe can help spur progress in the area.",
    "abstract_license": "https://creativecommons.org/licenses/by/4.0/",
    "resources": [{"type": "pdf", "url": "https://scienceofscience.org/publications/remor/paper.pdf"}]
  },{
    "id": "liang2024complementary",
    "title": "The complementary contributions of academia and industry to AI research",
    "alternate_title": "",
    "authors": [{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"},{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"James Zou","given":"James","family":"Zou"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2024",
    "publication_date": "2024",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv preprint arXiv:2401.10268",
    "doi": "",
    "source_url": "https://arxiv.org/abs/2401.10268",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/liang2024complementary.bib",
    "topics": ["ecosystem"],
    "tags": ["collaboration"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "lancichinetti2015topic",
    "title": "High-Reproducibility and High-Accuracy Method for Automated Topic Classification",
    "alternate_title": "",
    "authors": [{"name":"Andrea Lancichinetti","given":"Andrea","family":"Lancichinetti"},{"name":"M. Irmak Sirer","given":"M. Irmak","family":"Sirer"},{"name":"Jane X. Wang","given":"Jane X.","family":"Wang"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"Konrad Körding","given":"Konrad","family":"Körding"},{"name":"Luís A. Nunes Amaral","given":"Luís A.","family":"Nunes Amaral"}],
    "year": "2015",
    "publication_date": "2015",
    "format": "article",
    "status": "",
    "venue": "Physical Review X",
    "doi": "10.1103/PhysRevX.5.011007",
    "source_url": "https://doi.org/10.1103/PhysRevX.5.011007",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/lancichinetti2015topic.bib",
    "topics": ["discovery","foundations"],
    "tags": ["text-mining","statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "achakulvisut2019claim",
    "title": "Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning",
    "alternate_title": "",
    "authors": [{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Chandra Bhagavatula","given":"Chandra","family":"Bhagavatula"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"Konrad Kording","given":"Konrad","family":"Kording"}],
    "year": "2019",
    "publication_date": "2019",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv:1907.00962",
    "doi": "10.48550/arXiv.1907.00962",
    "source_url": "https://arxiv.org/abs/1907.00962",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/achakulvisut2019claim.bib",
    "topics": ["discovery","foundations"],
    "tags": ["text-mining","scholarly-data"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "liu2022team",
    "title": "Team formation and team impact: The balance between team freshness and repeat collaboration",
    "alternate_title": "",
    "authors": [{"name":"Meijun Liu","given":"Meijun","family":"Liu"},{"name":"Ajay Jaiswal","given":"Ajay","family":"Jaiswal"},{"name":"Yi Bu","given":"Yi","family":"Bu"},{"name":"Chao Min","given":"Chao","family":"Min"},{"name":"Sijie Yang","given":"Sijie","family":"Yang"},{"name":"Zhibo Liu","given":"Zhibo","family":"Liu"},{"name":"Daniel Acuña","given":"Daniel","family":"Acuña"},{"name":"Ying Ding","given":"Ying","family":"Ding"}],
    "year": "2022",
    "publication_date": "2022",
    "format": "article",
    "status": "",
    "venue": "Journal of Informetrics",
    "doi": "10.1016/j.joi.2022.101337",
    "source_url": "https://doi.org/10.1016/j.joi.2022.101337",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/liu2022team.bib",
    "topics": ["ecosystem"],
    "tags": ["collaboration","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "achakulvisut2020neuromatch",
    "title": "neuromatch: Algorithms to match scientists",
    "alternate_title": "",
    "authors": [{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Tulakan Ruangrong","given":"Tulakan","family":"Ruangrong"},{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"},{"name":"Brad Wyble","given":"Brad","family":"Wyble"},{"name":"Dan Goodman","given":"Dan","family":"Goodman"},{"name":"Konrad Kording","given":"Konrad","family":"Kording"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "webarticle",
    "status": "Web article",
    "venue": "eLife Labs",
    "doi": "",
    "source_url": "https://elifesciences.org/labs/5ed408f4/neuromatch-algorithms-to-match-scientists",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/achakulvisut2020neuromatch.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["recommender-systems","collaboration","careers","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "xiang2020tampering",
    "title": "Scientific Image Tampering Detection Based On Noise Inconsistencies: A Method And Datasets",
    "alternate_title": "",
    "authors": [{"name":"Ziyue Xiang","given":"Ziyue","family":"Xiang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020-01-21",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv:2001.07799",
    "doi": "10.48550/arXiv.2001.07799",
    "source_url": "https://arxiv.org/abs/2001.07799",
    "page_url": "https://scienceofscience.org/publications/scientific-image-tampering/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/xiang2020tampering.bib",
    "topics": ["integrity","foundations"],
    "tags": ["figure-integrity","image-forensics"],
    "summary": "Scientific images have different properties from everyday photographs. This preprint develops a detector tailored to scientific imagery and tests whether inconsistencies in image noise can reveal manipulated regions.",
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "pdf", "url": "https://arxiv.org/pdf/2001.07799"}]
  },{
    "id": "zhuang2019novelty",
    "title": "The effect of novelty on the future impact of scientific grants",
    "alternate_title": "",
    "authors": [{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"}],
    "year": "2019",
    "publication_date": "2019",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv:1911.02712",
    "doi": "10.48550/arXiv.1911.02712",
    "source_url": "https://arxiv.org/abs/1911.02712",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/zhuang2019novelty.bib",
    "topics": ["ecosystem"],
    "tags": ["funding","citation-analysis"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2020mentorshipcommentary",
    "title": "Some considerations for studying gender, mentorship, and scientific impact: commentary on AlShebli, Makovi, and Rahwan (2020)",
    "alternate_title": "",
    "authors": [{"name":"Daniel Ernesto Acuna","given":"Daniel Ernesto","family":"Acuna"}],
    "year": "2020",
    "publication_date": "2020",
    "format": "preprint",
    "status": "Archived preprint",
    "venue": "OSF Preprints",
    "doi": "10.31219/osf.io/ybfk6",
    "source_url": "https://scholar.archive.org/work/qk62l25nhjcnzck3fhcxdogl2u/access/wayback/https://files.osf.io/v1/resources/ybfk6/providers/osfstorage/5fe01fca149e75061b032ad0?action=download&direct&version=3",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2020mentorshipcommentary.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["mentorship","diversity","statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "abatayo2026credibility",
    "title": "Assessments of Credibility in the Social and Behavioral Sciences",
    "alternate_title": "",
    "authors": [{"name":"Anna Lou Abatayo","given":"Anna Lou","family":"Abatayo"},{"name":"Titipat Achakulvisut","given":"Titipat","family":"Achakulvisut"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"Balazs Aczel","given":"Balazs","family":"Aczel"},{"name":"Laxmaan Balaji","given":"Laxmaan","family":"Balaji"},{"name":"Anita Bandrowski","given":"Anita","family":"Bandrowski"},{"name":"Daniel M Benjamin","given":"Daniel M","family":"Benjamin"},{"name":"Michael M Bishop","given":"Michael M","family":"Bishop"},{"name":"Gary L Brase","given":"Gary L","family":"Brase"},{"name":"Andrew W Brown","given":"Andrew W","family":"Brown"},{"name":"Martin Bush","given":"Martin","family":"Bush"},{"name":"James Caverlee","given":"James","family":"Caverlee"},{"name":"Tatiana Chakravorti","given":"Tatiana","family":"Chakravorti"},{"name":"Yiling Chen","given":"Yiling","family":"Chen"},{"name":"Macie Daley","given":"Macie","family":"Daley"},{"name":"Morteza Dehghani","given":"Morteza","family":"Dehghani"},{"name":"Mirka Dirzo","given":"Mirka","family":"Dirzo"},{"name":"Anna Dreber","given":"Anna","family":"Dreber"},{"name":"Peter Eckmann","given":"Peter","family":"Eckmann"},{"name":"Timothy M Errington","given":"Timothy M","family":"Errington"},{"name":"Qizhang Feng","given":"Qizhang","family":"Feng"},{"name":"Fiona Fidler","given":"Fiona","family":"Fidler"},{"name":"Samuel Field","given":"Samuel","family":"Field"},{"name":"Nicholas W Fox","given":"Nicholas W","family":"Fox"},{"name":"Robert D Fraleigh","given":"Robert D","family":"Fraleigh"},{"name":"Aaron Frank","given":"Aaron","family":"Frank"},{"name":"Hannah Fraser","given":"Hannah","family":"Fraser"},{"name":"James Gentile","given":"James","family":"Gentile"},{"name":"C L Giles","given":"C L","family":"Giles"},{"name":"Brandon Goldfedder","given":"Brandon","family":"Goldfedder"},{"name":"Phil Gooch","given":"Phil","family":"Gooch"},{"name":"Michael Gordon","given":"Michael","family":"Gordon"},{"name":"Elliot Gould","given":"Elliot","family":"Gould"},{"name":"Christopher Griffin","given":"Christopher","family":"Griffin"},{"name":"Timothy Gulden","given":"Timothy","family":"Gulden"},{"name":"Noah Haber","given":"Noah","family":"Haber"},{"name":"Krystal Hahn","given":"Krystal","family":"Hahn"},{"name":"Felix Holzmeister","given":"Felix","family":"Holzmeister"},{"name":"Xia B Hu","given":"Xia B","family":"Hu"},{"name":"Yuzhong Huang","given":"Yuzhong","family":"Huang"},{"name":"Magnus Johannesson","given":"Magnus","family":"Johannesson"},{"name":"Brendan Kennedy","given":"Brendan","family":"Kennedy"},{"name":"Melissa Kline Struhl","given":"Melissa","family":"Kline Struhl"},{"name":"Anthony Kwasnica","given":"Anthony","family":"Kwasnica"},{"name":"Dong-Ho Lee","given":"Dong-Ho","family":"Lee"},{"name":"Kristina Lerman","given":"Kristina","family":"Lerman"},{"name":"Yang Liu","given":"Yang","family":"Liu"},{"name":"Allegra Pearce","given":"Allegra","family":"Pearce"},{"name":"Isabella Mandema","given":"Isabella","family":"Mandema"},{"name":"Alexandru Marcoci","given":"Alexandru","family":"Marcoci"},{"name":"Brinna Mawhinney","given":"Brinna","family":"Mawhinney"},{"name":"Souad McIntosh","given":"Souad","family":"McIntosh"},{"name":"Michael Mclaughlin","given":"Michael","family":"Mclaughlin"},{"name":"Arjun Menon","given":"Arjun","family":"Menon"},{"name":"Olivia Miske","given":"Olivia","family":"Miske"},{"name":"Fallon Mody","given":"Fallon","family":"Mody"},{"name":"Fred Morstatter","given":"Fred","family":"Morstatter"},{"name":"Nishanth S Nakshatri","given":"Nishanth S","family":"Nakshatri"},{"name":"Brian A Nosek","given":"Brian A","family":"Nosek"},{"name":"Michele B Nuijten","given":"Michele B","family":"Nuijten"},{"name":"David Pennock","given":"David","family":"Pennock"},{"name":"Thomas Pfeiffer","given":"Thomas","family":"Pfeiffer"},{"name":"Darien Pipkin","given":"Darien","family":"Pipkin"},{"name":"Jay Pujara","given":"Jay","family":"Pujara"},{"name":"Sarah Rajtmajer","given":"Sarah","family":"Rajtmajer"},{"name":"Martijn Roelandse","given":"Martijn","family":"Roelandse"},{"name":"Adam Russell","given":"Adam","family":"Russell"},{"name":"Priya Silverstein","given":"Priya","family":"Silverstein"},{"name":"Vaibhav Singh","given":"Vaibhav","family":"Singh"},{"name":"Courtney K Soderberg","given":"Courtney K","family":"Soderberg"},{"name":"Anna M Squicciarini","given":"Anna M","family":"Squicciarini"},{"name":"Theresa Stankov","given":"Theresa","family":"Stankov"},{"name":"Jordan W Suchow","given":"Jordan W","family":"Suchow"},{"name":"Barnabas Szaszi","given":"Barnabas","family":"Szaszi"},{"name":"Louisa Tran","given":"Louisa","family":"Tran"},{"name":"Peter A Vesk","given":"Peter A","family":"Vesk"},{"name":"Tim Vines","given":"Tim","family":"Vines"},{"name":"Colby J Vorland","given":"Colby J","family":"Vorland"},{"name":"Juntao Wang","given":"Juntao","family":"Wang"},{"name":"Zhuoer Wang","given":"Zhuoer","family":"Wang"},{"name":"David P Wilkinson","given":"David P","family":"Wilkinson"},{"name":"Bonnie Wintle","given":"Bonnie","family":"Wintle"},{"name":"Jian Wu","given":"Jian","family":"Wu"}],
    "year": "2026",
    "publication_date": "2026",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "MetaArXiv",
    "doi": "",
    "source_url": "https://osf.io/preprints/metaarxiv/7u58q_v1",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/abatayo2026credibility.bib",
    "topics": ["integrity","ecosystem"],
    "tags": ["reproducibility","statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "dataset", "url": "https://osf.io/9fpyb/"}]
  },{
    "id": "acuna2021eileen",
    "title": "EILEEN: A recommendation system for scientific publications and grants",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Kartik Nagre","given":"Kartik","family":"Nagre"},{"name":"Priya Matnani","given":"Priya","family":"Matnani"}],
    "year": "2021",
    "publication_date": "2021",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv:2110.09663",
    "doi": "10.48550/arXiv.2110.09663",
    "source_url": "https://arxiv.org/abs/2110.09663",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2021eileen.bib",
    "topics": ["discovery","ecosystem"],
    "tags": ["research-recommendation","recommender-systems","funding","text-mining"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "bu2022workshop",
    "title": "International Workshop on Data-driven Science of Science",
    "alternate_title": "",
    "authors": [{"name":"Yi Bu","given":"Yi","family":"Bu"},{"name":"Meijun Liu","given":"Meijun","family":"Liu"},{"name":"Yujia Zhai","given":"Yujia","family":"Zhai"},{"name":"Ying Ding","given":"Ying","family":"Ding"},{"name":"Feng Xia","given":"Feng","family":"Xia"},{"name":"Daniel E. Acuña","given":"Daniel E.","family":"Acuña"},{"name":"Yi Zhang","given":"Yi","family":"Zhang"}],
    "year": "2022",
    "publication_date": "2022",
    "format": "inproceedings",
    "status": "Workshop announcement",
    "venue": "Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",
    "doi": "10.1145/3534678.3542891",
    "source_url": "https://doi.org/10.1145/3534678.3542891",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/bu2022workshop.bib",
    "topics": ["ecosystem","discovery"],
    "tags": ["scholarly-data"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2010aspiration",
    "title": "The rational control of aspiration in learning",
    "alternate_title": "",
    "authors": [{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"},{"name":"C. Shawn Green","given":"C. Shawn","family":"Green"},{"name":"Paul Schrater","given":"Paul","family":"Schrater"}],
    "year": "2010",
    "publication_date": "2010",
    "format": "inproceedings",
    "status": "Conference abstract",
    "venue": "Computational and Systems Neuroscience 2010",
    "doi": "10.3389/conf.fnins.2010.03.00169",
    "source_url": "https://www.frontiersin.org/10.3389/conf.fnins.2010.03.00169/event_abstract",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2010aspiration.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2020nullmodel",
    "title": "Estimating a Null Model of Scientific Image Reuse to Support Research Integrity Investigations",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Ziyue Xiang","given":"Ziyue","family":"Xiang"}],
    "year": "2020",
    "publication_date": "2020-02-22",
    "format": "preprint",
    "status": "Preprint / working paper",
    "venue": "arXiv:2003.00878",
    "doi": "10.48550/arXiv.2003.00878",
    "source_url": "https://arxiv.org/abs/2003.00878",
    "page_url": "https://scienceofscience.org/publications/image-reuse-null-model/",
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2020nullmodel.bib",
    "topics": ["integrity","foundations"],
    "tags": ["figure-integrity","image-forensics","statistical-methods"],
    "summary": "Image similarities need a reference point: a repeated pattern might be rare, or it might be common in scientific imagery. This preprint develops a statistical baseline for estimating how often a feature could occur by chance.",
    "abstract": null,
    "abstract_license": null,
    "resources": [{"type": "pdf", "url": "https://arxiv.org/pdf/2003.00878"}]
  },{
    "id": "schrater2009structure",
    "title": "Structure learning in sequential decision making",
    "alternate_title": "",
    "authors": [{"name":"Paul Schrater","given":"Paul","family":"Schrater"},{"name":"Daniel Acuna","given":"Daniel","family":"Acuna"}],
    "year": "2009",
    "publication_date": "2009",
    "format": "inproceedings",
    "status": "Conference abstract",
    "venue": "Journal of Vision: Vision Sciences Society Annual Meeting Abstracts",
    "doi": "",
    "source_url": "https://jov.arvojournals.org/article.aspx?articleid=2136291",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/schrater2009structure.bib",
    "topics": ["foundations"],
    "tags": ["decision-making","reinforcement-learning"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  },{
    "id": "acuna2021mlworkshop",
    "title": "Machine Learning and Artificial Intelligence for Science of Science and Computational Discovery: Principles, Applications, and Future Opportunities",
    "alternate_title": "",
    "authors": [{"name":"Daniel E. Acuna","given":"Daniel E.","family":"Acuna"},{"name":"Tong Zeng","given":"Tong","family":"Zeng"},{"name":"Han Zhuang","given":"Han","family":"Zhuang"},{"name":"Lizhen Liang","given":"Lizhen","family":"Liang"}],
    "year": "2021",
    "publication_date": "2021",
    "format": "inproceedings",
    "status": "Workshop description",
    "venue": "iConference 2021 workshop",
    "doi": "",
    "source_url": "https://scienceofscience.org/workshops/",
    "page_url": null,
    "bibtex_url": "https://scienceofscience.org/publications/citations/acuna2021mlworkshop.bib",
    "topics": ["discovery","ecosystem","foundations"],
    "tags": ["scholarly-data","text-mining","statistical-methods"],
    "summary": null,
    "abstract": null,
    "abstract_license": null,
    "resources": []
  }]
}