{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T14:08:16Z","timestamp":1791986896916,"version":"4.4.0"},"reference-count":57,"publisher":"American Chemical Society (ACS)","issue":"14","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministerstvo ?kolstv?, Ml?de?e a Telov?chovy","award":["MSMT-355\/2025-16"],"award-info":[{"award-number":["MSMT-355\/2025-16"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Public leaderboards such as the Therapeutics Data Commons (TDC) ADMET benchmark are widely treated as a ranking of state-of-the-art models. However, a high leaderboard position is only meaningful if the corresponding model can actually be reproduced and deployed by an independent researcher. In this work, we audit whether the top-ranked TDC ADMET models meet that bar. We assessed the top-ranked models of all 22 TDC ADMET leaderboards from the perspective of an end user with access only to the publicly released artifacts of each model\u2500its publication, code repository, and installation instructions. For every end point, the top three models were screened with a unified protocol including an execution environment reproducibility check, a data-leakage assessment, verification of the hyperparameter-optimization procedure, and a reevaluation against the current leaderboard. Only three models (CaliciBoost, MapLight, and MapLight + GNN) passed all stages and reproduced their reported performance. The remaining models failed because of unavailable code, nonreproducible environments, runtime incompatibilities, or methodological flaws. We traced direct or indirect data leakage in the MiniMol, GradientBoost, and XGBoost models, and used deliberately overfitted variants of our own Mol2Vec-based models to show that tuning on the public test set\u2500whether accidental or intentional\u2500can substantially inflate both metrics and leaderboard rank. These results indicate that current TDC leaderboard positions cannot be read as a direct measure of model quality and practical applicability and emphasize the urgent need for better public ADMET benchmarks based on the hidden test sets, strict data set versioning and model submission with standardized inference environments.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00819","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:53:57Z","timestamp":1783043637000},"page":"8045-8058","source":"Crossref","is-referenced-by-count":4,"title":["An End-User Audit of Reproducibility, Data Leakage,\nand Overfitting of the Top-Ranked ADMET Prediction Models in TDC Leaderboards"],"prefix":"10.1021","volume":"66","author":[{"given":"Ihor","family":"Koleiev","sequence":"first","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]},{"name":"Institute of Physics of the National Academy of Sciences of Ukraine , , 46 Nauky Ave. , ,","place":["Kyiv, Ukraine, 03038"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"Stratiichuk","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]},{"name":"Taras Shevchenko Kyiv National University , , 64 Volodymyrska Str. , ,","place":["Kyiv, Ukraine, 01601"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazar","family":"Shevchuk","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykola","family":"Melnychenko","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Nyporko","sequence":"additional","affiliation":[{"name":"Taras Shevchenko Kyiv National University , 64 Volodymyrska Str. , ,","place":["Kyiv, Ukraine, 01601"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniil","family":"Todoryshyn","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladyslav","family":"Husak","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]},{"name":"The University of Trento , , Via Sommarive 9 , Povo, ,","place":["Trento, Italy, 38123"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5103-0635","authenticated-orcid":true,"given":"Sergii","family":"Starosyla","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6748-8931","authenticated-orcid":true,"given":"Semen","family":"Yesylevskyy","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]},{"name":"Institute of Physics of the National Academy of Sciences of Ukraine , , 46 Nauky Ave. , ,","place":["Kyiv, Ukraine, 03038"]},{"name":"Institute of Organic Chemistry and Biochemistry, Czech Academy of Sciences , ,","place":["Prague 6, Czech Republic, CZ-166 10"]},{"name":"Palacky\u0301 University Olomouc , , 17. Listopadu 12 , ,","place":["Olomouc, Czech Republic, 771 46"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8604-377X","authenticated-orcid":true,"given":"Alan","family":"Nafiiev","sequence":"additional","affiliation":[{"name":"Receptor.AI Inc. , 20-22 Wenlock Road , ,","place":["London, U.K., N1 7GU"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"2026072709090290700_cit1","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","article-title":"Innovation in the pharmaceutical\nindustry: New estimates of R&D costs","volume":"47","author":"DiMasi","year":"2016","journal-title":"J.\nHealth Econ"},{"issue":"9","key":"2026072709090290700_cit2","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1001\/jama.2020.1166","article-title":"Estimated Research and Development\nInvestment Needed to Bring a New Medicine to Market, 2009\u22122018","volume":"323","author":"Wouters","year":"2020","journal-title":"JAMA"},{"key":"2026072709090290700_cit3","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.2174\/15680266113139990033","article-title":"In Silico ADMET Prediction: Recent\nAdvances, Current Challenges and Future Trends","volume":"13","author":"Cheng","year":"2013","journal-title":"Curr. Top. Med. Chem."},{"issue":"8","key":"2026072709090290700_cit4","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1038\/nrd1470","article-title":"Can the pharmaceutical\nindustry reduce attrition rates?","volume":"3","author":"Kola","year":"2004","journal-title":"Nat. Rev.\nDrug Discovery"},{"issue":"7","key":"2026072709090290700_cit5","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1038\/nrd4609","article-title":"An analysis of the attrition of drug candidates from\nfour major pharmaceutical companies","volume":"14","author":"Waring","year":"2015","journal-title":"Nat. Rev.\nDrug Discovery"},{"issue":"5","key":"2026072709090290700_cit6","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/j.drudis.2019.03.015","article-title":"ADMET modeling approaches in drug\ndiscovery","volume":"24","author":"Ferreira","year":"2019","journal-title":"Drug Discovery Today"},{"issue":"1","key":"2026072709090290700_cit7","doi-asserted-by":"publisher","first-page":"42717","DOI":"10.1038\/srep42717","article-title":"SwissADME: a free web tool to evaluate\npharmacokinetics, drug-likeness and medicinal chemistry friendliness\nof small molecules","volume":"7","author":"Daina","year":"2017","journal-title":"Sci. Rep"},{"issue":"22\u221223","key":"2026072709090290700_cit8","doi-asserted-by":"publisher","first-page":"5545","DOI":"10.1093\/bioinformatics\/btaa1005","article-title":"DeepPurpose:\na deep learning library for drug\u2212target interaction prediction","volume":"36","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"issue":"1","key":"2026072709090290700_cit9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0169-409X(96)00423-1","article-title":"Experimental and\ncomputational approaches to estimate solubility and permeability in\ndrug discovery and development settings","volume":"23","author":"Lipinski","year":"1997","journal-title":"Adv.\nDrug Delivery Rev"},{"issue":"6","key":"2026072709090290700_cit10","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications\nof machine learning in drug discovery\nand development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat. Rev. Drug Discovery"},{"issue":"1","key":"2026072709090290700_cit11","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s13321-022-00599-3","article-title":"Transformer-based molecular\noptimization beyond matched molecular pairs","volume":"14","author":"He","year":"2022","journal-title":"J. Cheminf"},{"issue":"11","key":"2026072709090290700_cit12","doi-asserted-by":"publisher","first-page":"104487","DOI":"10.1016\/j.drudis.2025.104487","article-title":"Bridging data\nand drug development: Machine learning approaches for next-generation\nADMET prediction","volume":"30","author":"Fan","year":"2025","journal-title":"Drug Discovery Today"},{"key":"2026072709090290700_cit13","doi-asserted-by":"publisher","first-page":"100223","DOI":"10.1016\/j.medidd.2025.100223","article-title":"Revolutionizing\npharmacology: AI-powered approaches\nin molecular modeling and ADMET prediction","volume":"28","author":"Pathan","year":"2025","journal-title":"Med. Drug Discovery"},{"issue":"6","key":"2026072709090290700_cit14","doi-asserted-by":"publisher","first-page":"bbab159","DOI":"10.1093\/bib\/bbab159","article-title":"Utilizing graph machine learning within drug discovery and development","volume":"22","author":"Gaudelet","year":"2021","journal-title":"Briefings Bioinf."},{"issue":"3","key":"2026072709090290700_cit15","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular\ncontrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat. Mach. Intell"},{"issue":"2","key":"2026072709090290700_cit16","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.trechm.2020.12.004","article-title":"Metrics for\nBenchmarking and Uncertainty\nQuantification: Quality, Applicability, and Best Practices for Machine\nLearning in Chemistry","volume":"3","author":"Vishwakarma","year":"2021","journal-title":"Trends Chem"},{"issue":"6","key":"2026072709090290700_cit17","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1038\/s41570-022-00391-9","article-title":"Evaluation\nguidelines for machine\nlearning tools in the chemical sciences","volume":"6","author":"Bender","year":"2022","journal-title":"Nat.\nRev. Chem"},{"issue":"6","key":"2026072709090290700_cit18","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1038\/s41557-021-00716-z","article-title":"Best practices in machine\nlearning for chemistry","volume":"13","author":"Artrith","year":"2021","journal-title":"Nat. Chem"},{"issue":"8","key":"2026072709090290700_cit19","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing\nLearned Molecular Representations for Property\nPrediction","volume":"59","author":"Yang","year":"2019","journal-title":"J. Chem. Inf. Model"},{"issue":"1","key":"2026072709090290700_cit20","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-022-00630-7","article-title":"Machine intelligence-driven framework for optimized\nhit selection in virtual screening","volume":"14","author":"Kumar","year":"2022","journal-title":"J. Cheminf"},{"key":"2026072709090290700_cit21","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1039\/D2DD00004K","article-title":"Limitations Of Machine Learning Models\nWhen Predicting Compounds With Completely New Chemistries: possible\nImprovements Applied To The Discovery Of New Non-Fullerene Acceptors","volume":"1","author":"Zhao","year":"2022","journal-title":"Digital Discovery"},{"issue":"2","key":"2026072709090290700_cit22","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine\nlearning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci"},{"issue":"1","key":"2026072709090290700_cit23","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1038\/s41597-024-03793-0","article-title":"PharmaBench: Enhancing\nADMET benchmarks with large\nlanguage models","volume":"11","author":"Niu","year":"2024","journal-title":"Sci. Data"},{"key":"2026072709090290700_cit24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.09548","article-title":"Therapeutics Data Commons: Machine Learning\nDatasets and Tasks for\nDrug Discovery and Development","author":"Huang","year":"2021","journal-title":"arXiv"},{"issue":"10","key":"2026072709090290700_cit25","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1038\/s41589-022-01131-2","article-title":"Artificial\nintelligence foundation for therapeutic science","volume":"18","author":"Huang","year":"2022","journal-title":"Nat. Chem. Biol"},{"key":"2026072709090290700_cit26","doi-asserted-by":"publisher","DOI":"10.1101\/2024.06.12.598655","article-title":"TDC-2: Multimodal\nFoundation for Therapeutic\nScience","author":"Velez-Arce","year":"2024","journal-title":"bioRxiv"},{"issue":"9","key":"2026072709090290700_cit27","doi-asserted-by":"publisher","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis\nin machine-learning-based\nscience","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"issue":"11","key":"2026072709090290700_cit28","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s10462-025-11326-3","article-title":"Don\u2019t push the button! Exploring\ndata leakage risks in machine learning and transfer learning","volume":"58","author":"Apicella","year":"2025","journal-title":"Artif. Intell. Rev"},{"key":"2026072709090290700_cit29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.12580","article-title":"Model Similarity Mitigates\nTest Set\nOveruse","author":"Mania","year":"2019","journal-title":"arXiv"},{"key":"2026072709090290700_cit30","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1039\/D4FD00091A","article-title":"Are we fitting data\nor noise? Analysing\nthe predictive power of commonly used datasets in drug-, materials-,\nand molecular-discovery","volume":"256","author":"Crusius","year":"2025","journal-title":"Faraday Discuss"},{"issue":"4","key":"2026072709090290700_cit31","doi-asserted-by":"publisher","first-page":"101185","DOI":"10.1016\/j.patter.2025.101185","article-title":"Unraveling overoptimism and publication\nbias in ML-driven science","volume":"6","author":"Saidi","year":"2025","journal-title":"Patterns"},{"issue":"18","key":"2026072709090290700_cit32","doi-asserted-by":"publisher","first-page":"9398","DOI":"10.1021\/acs.jcim.5c01609","article-title":"Practically\nSignificant Method Comparison Protocols for Machine Learning in Small\nMolecule Drug Discovery","volume":"65","author":"Ash","year":"2025","journal-title":"J. Chem. Inf. Model"},{"issue":"1","key":"2026072709090290700_cit33","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1186\/s13321-024-00931-z","article-title":"Comprehensive benchmarking of computational tools for\npredicting toxicokinetic and physicochemical properties of chemicals","volume":"16","author":"Gadaleta","year":"2024","journal-title":"J. Cheminf"},{"issue":"2","key":"2026072709090290700_cit34","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.drudis.2020.12.009","article-title":"Artificial intelligence\nin drug discovery:\nwhat is realistic, what are illusions? Part 1: Ways to make an impact,\nand why we are not there yet","volume":"26","author":"Bender","year":"2021","journal-title":"Drug Discovery\nToday"},{"issue":"16","key":"2026072709090290700_cit35","doi-asserted-by":"publisher","first-page":"8651","DOI":"10.1021\/acs.jmedchem.0c01077","article-title":"Artificial Intelligence in Drug Discovery:\nInto the Great Wide Open","volume":"63","author":"Bajorath","year":"2020","journal-title":"J. Med. Chem"},{"issue":"6","key":"2026072709090290700_cit36","doi-asserted-by":"publisher","first-page":"2697","DOI":"10.1021\/acs.jcim.9b00975","article-title":"Evaluating\nScalable Uncertainty Estimation Methods for Deep Learning-Based Molecular\nProperty Prediction","volume":"60","author":"Scalia","year":"2020","journal-title":"J. Chem. Inf. Model"},{"issue":"1","key":"2026072709090290700_cit37","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s13321-025-01041-0","article-title":"Benchmarking ML in ADMET\npredictions: the practical impact of feature representations in ligand-based\nmodels","volume":"17","author":"Kamuntavic\u030cius","year":"2025","journal-title":"J. Cheminf"},{"key":"2026072709090290700_cit38","unstructured":"Kamuntavic\u030cius, G.; Paquet, T.; Bastas, O.; S\u030calkauskas, D.; Prat, A.; Aty, H. A.; et al., lightgbm.LGBMRegressor2026https:\/\/lightgbm.readthedocs.io\/en\/latest\/pythonapi\/lightgbm.LGBMRegressor.html Accessed 20 February 2026."},{"key":"2026072709090290700_cit39","unstructured":"Kamuntavic\u030cius, G.; Paquet, T.; Bastas, O.; S\u030calkauskas, D.; Prat, A.; Aty, H. A.; et al., lightgbm.LGBMClassifier2026https:\/\/lightgbm.readthedocs.io\/en\/latest\/pythonapi\/lightgbm.LGBMClassifier.html Accessed 20 February 2026."},{"key":"2026072709090290700_cit40","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: A Next-generation Hyperparameter\nOptimization Framework","volume-title":"KDD\u201919:\nProceedings of the 25th ACM SIGKDD International Conference on Knowledge\nDiscovery & Data Mining","author":"Akiba","year":"2019"},{"key":"2026072709090290700_cit41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.11127","article-title":"Tree-Structured\nParzen Estimator: Understanding Its Algorithm Components and Their\nRoles for Better Empirical Performance","author":"Watanabe","year":"2025","journal-title":"arXiv"},{"key":"2026072709090290700_cit42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.00174","article-title":"ADMET property\nprediction through combinations of molecular fingerprints","author":"Notwell","year":"2023","journal-title":"arXiv"},{"issue":"1","key":"2026072709090290700_cit43","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1186\/s13321-025-01137-7","article-title":"CaliciBoost: Performance-driven\nevaluation of molecular representations\nfor caco-2 permeability prediction","volume":"17","author":"Le","year":"2025","journal-title":"J. Cheminf"},{"key":"2026072709090290700_cit44","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-dh70x","article-title":"Enhancing ADMET\nProperty Models Performance\nthrough Combinatorial Fusion Analysis","author":"Jiang","year":"2023","journal-title":"ChemRxiv"},{"key":"2026072709090290700_cit45","unstructured":"GitHub.\n          \n          Advancing ADMET prediction:\nA hybrid machine\nlearning framework (Partex ADMETrix). https:\/\/github.com\/partex-nv-opensource\/tdc-submission\/blob\/main\/src\/ics-admet-prediction-tdc-versiontwo\/report\/Advancing\u00a0ADMET\u00a0Prediction\u00a0A\u00a0Hybrid\u00a0Machine\u00a0Learning\u00a0Framework\u00a0(Partex\u00a0ADMETrix).pdf Accessed 20 February 2026."},{"key":"2026072709090290700_cit46","unstructured":"GitHub.\n          \n          SimGCN_for_TDC_Benchmarks. https:\/\/github.com\/KatanaGraph\/SimGCN-TDC\/blob\/main\/Report_SimGCN_for_TDC_Benchmarks.pdf Accessed 20 February 2026."},{"key":"2026072709090290700_cit47","doi-asserted-by":"publisher","DOI":"10.1101\/2022.12.13.520154","article-title":"First fully-automated\nAI\/ML virtual screening cascade implemented at a drug discovery centre\nin Africa","author":"Turon","year":"2022","journal-title":"bioRxiv"},{"issue":"1","key":"2026072709090290700_cit48","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13321-020-00456-1","article-title":"An open\nsource chemical structure curation\npipeline using RDKit","volume":"12","author":"Bento","year":"2020","journal-title":"J. Cheminf"},{"key":"2026072709090290700_cit49","unstructured":"We Need Better Benchmarks for Machine Learning\nin Drug Discovery\n          2026\n          https:\/\/practicalcheminformatics.blogspot.com\/2023\/08\/we-need-better-benchmarks-for-machine.html Accessed 7 May 2026."},{"key":"2026072709090290700_cit50","first-page":"1006","article-title":"The Ladder: A Reliable Leaderboard\nfor Machine Learning Competitions","volume-title":"Proceedings\nof the 32nd International Conference on Machine Learning","author":"Blum","year":"2015"},{"key":"2026072709090290700_cit51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.07048","article-title":"Leakage and the\nReproducibility Crisis in ML-based Science [Internet]","author":"Kapoor","year":"2022","journal-title":"arXiv"},{"key":"2026072709090290700_cit52","unstructured":"DREAM Challenges.\n          \n          2026\n          https:\/\/dreamchallenges.org\/ Accessed 20 February 2026."},{"key":"2026072709090290700_cit53","unstructured":"Mobley, D. L.\n          \n          The SAMPL challenges\n          SAMPL\n          https:\/\/samplchallenges.org\/\/ Accessed 20 February 2026."},{"issue":"7","key":"2026072709090290700_cit54","doi-asserted-by":"publisher","first-page":"100543","DOI":"10.1016\/j.patter.2022.100543","article-title":"Codabench: Flexible, easy-to-use, and reproducible\nmeta-benchmark platform","volume":"3","author":"Xu","year":"2022","journal-title":"Patterns"},{"key":"2026072709090290700_cit55","unstructured":"MoleculeNet.\n          \n          Pande Group. https:\/\/moleculenet.org\/ Accessed\n20 February 2026."},{"key":"2026072709090290700_cit56","unstructured":"mindrank-ai\/PharmaBench\n          MindRank Technologies; 2026https:\/\/github.com\/mindrank-ai\/PharmaBench Accessed 20 February 2026."},{"key":"2026072709090290700_cit57","unstructured":"OpenADMET.\n          \n          OMSF. https:\/\/openadmet.org\/ Accessed\n20 February 2026."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00819","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8045\/65518305\/acs.jcim.6c00819.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8045\/65518305\/acs.jcim.6c00819.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:24:23Z","timestamp":1785158663000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/14\/8045\/5184746\/An-End-User-Audit-of-Reproducibility-Data-Leakage"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":57,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7,2]]},"published-print":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00819","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}