{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1108,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":1108,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"70d852529f2b","filters":{"topic":"Machine Learning in Materials Science"}},"results":[{"id":"W2529996553","doi":"10.1021/acscentsci.7b00572","title":"Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules","year":2018,"lang":"en","type":"article","venue":"ACS Central Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3038,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto; University of New Brunswick","funders":"Basic Energy Sciences; Division of Graduate Education; Samsung; Samsung Advanced Institute of Technology; Fundación Rafael del Pino; Division of Information and Intelligent Systems; Alfred P. Sloan Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Representation (politics); Encoder; Set (abstract data type); Simple (philosophy); Chemical space; Continuous modelling; Chemical process; Continuous optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.05420585370622166,"gpt":0.3376089030363909,"spread":0.2834030493301692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001677129,0.0001446863,0.0002528226,0.00009357565,0.0002767413,0.0002370693,0.002323819,0.00004395222,0.0004869914],"category_scores_gemma":[0.00184167,0.0001230541,0.00002160874,0.0009042523,0.002562292,0.001043474,0.0007827824,0.00006743096,0.00008405287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008351343,"about_ca_system_score_gemma":0.0003389971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003021774,"about_ca_topic_score_gemma":0.000003382367,"domain_scores_codex":[0.9970469,0.0001942039,0.0004203869,0.0007465496,0.0009071279,0.0006848703],"domain_scores_gemma":[0.9981977,0.0001291045,0.0003352868,0.000950603,0.0002208305,0.0001665259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001166651,0.00002969676,0.0009759854,0.00001105845,0.000001183188,0.000003204392,0.0004746514,0.001717209,0.9956501,0.0001934039,0.0000785435,0.00085335],"study_design_scores_gemma":[0.00009471917,0.00004418008,0.00238168,0.00003092643,0.000007347185,0.00001857447,0.00004544692,0.3758908,0.6211976,0.0001775011,0.000009278513,0.0001019758],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9397487,0.000009294175,0.05906855,0.0000647773,0.0005872319,0.0002425314,0.0000150745,0.00009512616,0.0001687021],"genre_scores_gemma":[0.8111387,0.000001333717,0.1886916,0.00004907631,0.00009832657,0.000002320625,0.000003201239,0.000007990241,0.000007494245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3744525,"threshold_uncertainty_score":0.9440872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2778051509","doi":"10.1063/1.5019779","title":"SchNet – A deep learning architecture for molecules and materials","year":2018,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; H2020 Marie Skłodowska-Curie Actions; Bundesministerium für Bildung und Forschung; National Research Foundation; Deutsche Forschungsgemeinschaft; H2020 European Research Council; Ministry of Science, ICT and Future Planning; European Commission","keywords":"Deep learning; Chemical space; Computer science; Artificial intelligence; Ab initio; Molecular dynamics; Architecture; Space (punctuation); Quantum; Physics; Quantum mechanics; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.008686035346267636,"gpt":0.2588891007118113,"spread":0.2502030653655436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001249249,0.0001214961,0.0002436387,0.00001872002,0.0001417809,0.0001113852,0.0004453543,0.00004278509,0.00008470159],"category_scores_gemma":[0.0004885567,0.00007239875,0.00003910606,0.00007421564,0.0004624052,0.0001179267,0.0001275911,0.0001648985,0.00001539637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001378905,"about_ca_system_score_gemma":0.00002426495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004689064,"about_ca_topic_score_gemma":2.082059e-7,"domain_scores_codex":[0.9989324,0.0001647046,0.0002972301,0.0001172603,0.0002580675,0.0002303568],"domain_scores_gemma":[0.9989267,0.0002976895,0.0003929775,0.0001405748,0.0001736443,0.00006839904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001789962,0.0000129201,0.000007950381,0.00002483547,0.000004904709,5.552217e-7,0.0005365271,0.0003344488,0.9971293,0.0004601019,0.0001225908,0.001186933],"study_design_scores_gemma":[0.0002441853,0.0002279544,0.00003306712,0.00003887902,0.00003091422,0.00007783015,0.00003429309,0.0007050584,0.9766477,0.02119724,0.0006686003,0.0000942183],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9360005,0.00005745016,0.0631128,0.0003853485,0.0002569916,0.00008732908,0.000004116155,0.00001809984,0.0000773987],"genre_scores_gemma":[0.9743172,0.000007247886,0.02431516,0.0001758388,0.001149248,0.000001992396,8.446962e-7,0.00001625726,0.00001624533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03879763,"threshold_uncertainty_score":0.2952335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883583109","doi":"10.1126/science.aat2663","title":"Inverse molecular design using machine learning: Generative models for matter engineering","year":2018,"lang":"en","type":"review","venue":"Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2061,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"","keywords":"Generative grammar; Context (archaeology); Computer science; Variety (cybernetics); Pace; Artificial intelligence; Generative Design; Biochemical engineering; Machine learning; Engineering; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.09115376563814767,"gpt":0.3404637727868817,"spread":0.249310007148734,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005257504,0.0007220972,0.001288401,0.0005749909,0.0008040631,0.0008703932,0.00244922,0.0002254629,0.0004500113],"category_scores_gemma":[0.0009180335,0.0005928064,0.0002699526,0.001197958,0.001075058,0.0009319513,0.0007220216,0.0003778288,0.0006396221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004018104,"about_ca_system_score_gemma":0.001074444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004157612,"about_ca_topic_score_gemma":0.000001338025,"domain_scores_codex":[0.994892,0.0004379625,0.0008016242,0.001708719,0.0009466384,0.001213077],"domain_scores_gemma":[0.9975643,0.0002843112,0.0006946264,0.0008387584,0.0003190225,0.0002990214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000196326,0.00005840335,0.000003556736,0.007090742,0.00002886674,0.00003309859,0.0006831686,0.6400794,0.3454008,0.0007464722,0.0002878432,0.005568074],"study_design_scores_gemma":[0.0001306554,0.0001314587,1.779158e-7,0.002238498,0.0001364661,0.00009395756,0.000006834294,0.8453982,0.01221945,0.000412392,0.1382825,0.0009494282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002992038,0.441157,0.5553216,0.00001352231,0.001578082,0.001320503,0.00004947781,0.000180764,0.00007984537],"genre_scores_gemma":[0.00005884087,0.2288945,0.7692665,0.0001805274,0.0005012206,0.0003246233,0.00002387863,0.0002092257,0.0005407484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3331813,"threshold_uncertainty_score":0.9996523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2527189750","doi":"10.1038/ncomms13890","title":"Quantum-chemical insights from deep tensor neural networks","year":2017,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1492,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; National Research Foundation; National Science Foundation","keywords":"Chemical space; Observable; Computer science; Quantum; Quantum chemical; Tensor (intrinsic definition); Artificial neural network; Molecule; Deep learning; Artificial intelligence; Statistical physics; Physics; Quantum mechanics; Bioinformatics; Mathematics; Biology; Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.02172796084790833,"gpt":0.3136766616852384,"spread":0.29194870083733,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0003068362,0.0001842175,0.0002374538,0.00004152639,0.00162574,0.0006981266,0.006141674,0.000325591,0.0002712189],"category_scores_gemma":[0.001466149,0.0001552619,0.0000662577,0.00008164118,0.0007331869,0.0004446998,0.00172927,0.001018982,0.0002193965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004070829,"about_ca_system_score_gemma":0.00002813011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003253829,"about_ca_topic_score_gemma":0.000363065,"domain_scores_codex":[0.9984266,0.0002946896,0.0002976336,0.0003957297,0.0002931648,0.0002922448],"domain_scores_gemma":[0.9936907,0.0004769574,0.0003559116,0.005200257,0.0001507329,0.0001254667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004307584,0.0001698038,0.00901365,0.000006595968,0.00001353213,0.000008645929,0.0005164426,0.002407438,0.9452059,0.03890642,0.002306624,0.001401855],"study_design_scores_gemma":[0.0004532733,0.00003048194,0.08278098,0.00004380224,0.00004136565,0.00001353263,0.00005583199,0.8813819,0.01458173,0.004742274,0.01534438,0.0005304597],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9833831,0.002950862,0.001943877,0.005930231,0.001841642,0.0002287704,0.00003072383,0.0002813029,0.003409449],"genre_scores_gemma":[0.9754995,0.00006353916,0.02344359,0.0005849309,0.0002584639,0.00002975003,0.00005865829,0.00002127902,0.00004027149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9306242,"threshold_uncertainty_score":0.999674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2337082154","doi":"10.1038/nphys4035","title":"Machine learning phases of matter","year":2017,"lang":"en","type":"article","venue":"Nature Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1474,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Perimeter Institute","funders":"","keywords":"Physics; Artificial neural network; Locality; Artificial intelligence; Convolutional neural network; Monte Carlo method; Statistical physics; Coulomb; Machine learning; Computer science; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.01020908638589513,"gpt":0.297600411901716,"spread":0.2873913255158209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004252833,0.0001466825,0.0002397493,0.00002293117,0.0004526307,0.0002172579,0.0009337626,0.0001105576,0.001501522],"category_scores_gemma":[0.0003699814,0.0001190546,0.00005985256,0.00004848796,0.0002638938,0.0003821687,0.0002680582,0.0004255076,0.0003628055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001326145,"about_ca_system_score_gemma":0.00002609562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001272169,"about_ca_topic_score_gemma":0.00000356356,"domain_scores_codex":[0.9988267,0.00007753505,0.0001871262,0.0002971979,0.0003638054,0.0002476339],"domain_scores_gemma":[0.9986665,0.00007140543,0.0004434236,0.0006733512,0.00009537287,0.00004990246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002450357,0.00004998274,0.03074479,0.00004525926,0.000003783058,0.000003761575,0.0001186712,0.0009458505,0.9639744,0.002476902,0.0005820526,0.001030089],"study_design_scores_gemma":[0.0004786562,0.00008540373,0.02427674,0.00007785139,0.00002214161,0.000008581244,0.000009993642,0.004539419,0.956858,0.005229652,0.008103527,0.0003100563],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750415,0.0002070513,0.001995411,0.0005606289,0.001365585,0.0001275276,0.00004084506,0.00009759259,0.02056387],"genre_scores_gemma":[0.9935225,0.000006320357,0.004931959,0.000174193,0.000298186,0.000003880375,0.000006743246,0.00001817625,0.00103805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01952582,"threshold_uncertainty_score":0.9994112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1531674615","doi":"10.1021/acs.jpclett.5b00831","title":"Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space","year":2015,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry Letters","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":856,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Argonne National Laboratory; Natural Sciences and Engineering Research Council of Canada; Office of Science; Einstein Stiftung Berlin; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; U.S. Department of Energy; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; European Research Council; National Science Foundation","keywords":"Polarizability; Chemical space; Quantum nonlocality; Statistical physics; Representation (politics); Pairwise comparison; Molecule; Simple (philosophy); Density functional theory; Chemical bond; Space (punctuation); Computational chemistry; Chemistry; Chemical physics; Physics; Computer science; Quantum mechanics; Artificial intelligence; Quantum; Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.01239871839238937,"gpt":0.2447266328606346,"spread":0.2323279144682452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001535016,0.0001504947,0.0003389236,0.00002597068,0.00004989864,0.00004949516,0.0004699418,0.00003988716,0.00002894155],"category_scores_gemma":[0.0006430097,0.00009685233,0.00006277687,0.0001504056,0.0004399823,0.0001872169,0.0001790858,0.000417335,0.000004213063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000567792,"about_ca_system_score_gemma":0.00006036787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007852917,"about_ca_topic_score_gemma":1.585951e-7,"domain_scores_codex":[0.9983576,0.0002947278,0.0004316678,0.0001593369,0.0005267792,0.0002298685],"domain_scores_gemma":[0.9989806,0.0001090223,0.0004704619,0.0001978479,0.0001098615,0.00013218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001311721,0.00006822111,0.0001927644,0.00006751608,0.000007835363,0.00001225414,0.0006362771,0.03893311,0.9598974,0.00001533083,0.00002571256,0.00001237564],"study_design_scores_gemma":[0.0004194517,0.00004946859,0.0001625164,0.00008975676,0.00003544442,0.00008578594,0.0001226691,0.05702414,0.9417754,0.0001079698,0.00002717074,0.0001002298],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926021,0.00008015858,0.00505469,0.00204231,0.00005938753,0.00006993608,0.000004919882,0.0000142698,0.00007220378],"genre_scores_gemma":[0.9991874,0.000005282557,0.0005471978,0.0000774682,0.0001561936,0.000001757484,9.109064e-7,0.00001156238,0.00001227601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01812203,"threshold_uncertainty_score":0.3949524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3023042104","doi":"10.1039/d0cs00098a","title":"QSAR without borders","year":2020,"lang":"en","type":"review","venue":"Chemical Society Reviews","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":852,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto; Vancouver Biotech (Canada); Toronto Public Health","funders":"Army Research Office; National Center for Advancing Translational Sciences; National Science Foundation; National Institutes of Health; National Cancer Institute; Horizon 2020 Framework Programme; U.S. Department of Defense","keywords":"Quantitative structure–activity relationship; Computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05423082091036748,"gpt":0.3766802286927348,"spread":0.3224494077823674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018849,0.000900247,0.004421347,0.00001826215,0.0001758678,0.0002845538,0.00207121,0.0005518859,0.002767888],"category_scores_gemma":[0.001122886,0.0006281991,0.002062408,0.0006127399,0.000455794,0.0001603413,0.0007053709,0.0009183519,0.009551176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002532894,"about_ca_system_score_gemma":0.0003227705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001075721,"about_ca_topic_score_gemma":1.715877e-7,"domain_scores_codex":[0.9950833,0.0005819248,0.001589489,0.001418312,0.0005678637,0.0007591231],"domain_scores_gemma":[0.9972169,0.0002081272,0.00116044,0.0009739108,0.00004916702,0.0003914769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001776755,0.00003809023,0.000001062086,0.04437632,0.00002765444,0.000004592246,0.0001672486,3.87208e-7,0.01219913,0.00005525031,0.06791326,0.8752152],"study_design_scores_gemma":[0.00007561349,0.00001513674,2.730223e-8,0.007055686,0.0003521819,0.00002788482,0.000004001882,0.00003718658,0.0003301679,0.00003192202,0.9913913,0.0006788675],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004327205,0.9960718,0.0003829723,0.0001750553,0.0006663424,0.001390892,0.00004133412,0.0003058974,0.0009613758],"genre_scores_gemma":[2.300823e-7,0.9694421,0.02815909,0.0007583521,0.0008122147,0.0003102777,0.00008160783,0.0001045601,0.0003315405],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9234781,"threshold_uncertainty_score":0.9996169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799915630","doi":"10.1038/s41578-018-0005-z","title":"Accelerating the discovery of materials for clean energy in the era of smart automation","year":2018,"lang":"en","type":"review","venue":"Nature Reviews Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":777,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Basic Energy Sciences; Division of Chemistry; Canadian Institute for Advanced Research; Office of Science; Division of Materials Research; U.S. Department of Energy; National Science Foundation","keywords":"Software deployment; Pace; Automation; Robotics; Computer science; Throughput; Artificial intelligence; Manufacturing engineering; Systems engineering; Nanotechnology; Risk analysis (engineering); Robot; Engineering; Telecommunications; Software engineering; Mechanical engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.04270453845116713,"gpt":0.3586417426277798,"spread":0.3159372041766126,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02239127,0.0007933604,0.004248597,0.0001820808,0.000237892,0.0006737902,0.003142608,0.0007768823,0.0005444621],"category_scores_gemma":[0.003789221,0.0003787438,0.0005040246,0.0006465582,0.0004307352,0.000515107,0.0004048416,0.0004177591,0.00005114046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001117825,"about_ca_system_score_gemma":0.0003443818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002099056,"about_ca_topic_score_gemma":0.00006799337,"domain_scores_codex":[0.9881597,0.005409046,0.004034651,0.0008693283,0.0009086569,0.0006186321],"domain_scores_gemma":[0.9909257,0.001511378,0.0055513,0.001691574,0.000281567,0.00003842729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000195157,0.0002921663,0.000001976657,0.1635011,0.00009641378,0.000005737866,0.001105955,0.000009713073,0.5031438,0.02256893,0.01160553,0.2974735],"study_design_scores_gemma":[0.0001930162,0.0001896017,0.00001258752,0.02556014,0.0003943597,0.00003983882,0.00002442556,0.000004074759,0.1636172,0.0005216062,0.8089416,0.000501503],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005502603,0.9841728,0.0002642265,0.0001132113,0.004411626,0.004395906,0.0009714832,0.00004662282,0.0001215515],"genre_scores_gemma":[0.002458185,0.9916769,0.002835121,0.0002320698,0.00119455,0.001236649,0.0002115406,0.00009383856,0.00006114774],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7973361,"threshold_uncertainty_score":0.9998664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810294304","doi":"10.1103/physrevmaterials.2.083802","title":"SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates","year":2018,"lang":"en","type":"article","venue":"Physical Review Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":755,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Office of Naval Research; Horizon 2020; Banting and Best Diabetes Centre, University of Toronto; Alexander von Humboldt-Stiftung; U.S. Department of Defense","keywords":"Curse of dimensionality; Binary number; Independence (probability theory); Property (philosophy); Key (lock); Operator (biology)","retraction":null,"screen_n_in":null,"score":{"opus":0.05378401772252962,"gpt":0.398152528856355,"spread":0.3443685111338254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037939,0.0002878614,0.001019813,0.00005513152,0.0002520679,0.0002062819,0.0006804188,0.0000457235,0.0004078517],"category_scores_gemma":[0.001067695,0.0001914401,0.0001035233,0.0002428395,0.0003902907,0.0003591678,0.0003005912,0.00008251992,0.0001319037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004700134,"about_ca_system_score_gemma":0.00007319097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007466684,"about_ca_topic_score_gemma":0.00006774987,"domain_scores_codex":[0.9963045,0.001294686,0.0008268426,0.0006090913,0.0004651266,0.0004997171],"domain_scores_gemma":[0.9977106,0.0006335297,0.0005619493,0.0006577771,0.0003340714,0.0001020474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001077365,0.0001150201,0.0000318344,0.001137272,0.000005198347,0.000001622921,0.0002324199,0.00003595937,0.9973093,0.0005165014,0.0001460908,0.0003610113],"study_design_scores_gemma":[0.0002827456,0.0001885614,0.0006877964,0.002083441,0.00006860217,0.000008556289,0.00002152054,0.005709428,0.9878005,0.002734866,0.0001763274,0.000237665],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941241,0.000431597,0.002963115,0.0003104204,0.0009342831,0.001045329,0.0001272733,0.00004332275,0.00002061666],"genre_scores_gemma":[0.9664975,0.00005340575,0.03225109,0.0006059283,0.0004641719,0.00005725365,0.00002524506,0.00003229083,0.00001316217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02928798,"threshold_uncertainty_score":0.7806699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1877361684","doi":"10.1002/smj.2294","title":"The double‐edged sword of recombination in breakthrough innovation","year":2014,"lang":"en","type":"article","venue":"Strategic Management Journal","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":745,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"SWORD; Novelty; Creativity; Value (mathematics); Realization (probability); Recombination; Computer science; Domain (mathematical analysis); Product (mathematics); Mathematics; Psychology; World Wide Web; Machine learning; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02301411220781436,"gpt":0.2850340469758742,"spread":0.2620199347680598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005740063,0.0001118912,0.0001480371,0.00020158,0.0002849076,0.0003624342,0.0005750848,0.00003536203,0.0003484139],"category_scores_gemma":[0.00005026568,0.00007770162,0.00002590799,0.0006402257,0.000117974,0.0002332686,0.00008883762,0.00018004,0.00004665488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005800203,"about_ca_system_score_gemma":0.0000296049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003426075,"about_ca_topic_score_gemma":0.00002388842,"domain_scores_codex":[0.9981071,0.0002955217,0.0006575992,0.0001933037,0.0004646504,0.0002818556],"domain_scores_gemma":[0.9989632,0.00007594618,0.0005426856,0.0002465058,0.0001442157,0.00002740676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008626319,0.00004785372,0.000530216,0.00004920745,0.000005209767,0.000004419517,0.000120601,0.001320853,0.05163264,0.9436694,0.00009002176,0.002443248],"study_design_scores_gemma":[0.00208019,0.0002171303,0.009149591,0.0001365411,0.00001527472,0.00003591774,0.0008299699,0.006118757,0.008978934,0.9707738,0.001429831,0.0002341342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8520241,0.00001668729,0.001685394,0.000837135,0.001234586,0.0001820543,4.145654e-7,0.0000241269,0.1439954],"genre_scores_gemma":[0.9964954,0.00004349119,0.002752913,0.00005014056,0.00009153795,0.000009668813,0.000001761482,0.000007738015,0.0005473673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1444712,"threshold_uncertainty_score":0.3814888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045928028","doi":"10.5445/ir/1000128111","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","year":2020,"lang":"en","type":"article","venue":"Repository KITopen (Karlsruhe Institute of Technology)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":726,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto; Vector Institute","funders":"Office of Naval Research; Tata Steel; Austrian Science Fund; European Commission","keywords":"Computer science; String (physics); Representation (politics); Intuition; Theoretical computer science; Generative model; Artificial intelligence; Generative grammar; Machine learning; Cognitive science; Physics; Theoretical physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02080048192199228,"gpt":0.2598707362992504,"spread":0.2390702543772581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004928787,0.0003551233,0.000621899,0.0003089143,0.0003552221,0.0002345091,0.001691902,0.0003292823,0.00008886599],"category_scores_gemma":[0.0006916034,0.0003527599,0.0001158152,0.001076636,0.0003934961,0.0009276057,0.0008542067,0.0004421846,0.0001030128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001360417,"about_ca_system_score_gemma":0.0003004271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002265585,"about_ca_topic_score_gemma":0.00000586959,"domain_scores_codex":[0.9967385,0.0001210395,0.0009330715,0.0009961035,0.0006822897,0.0005290132],"domain_scores_gemma":[0.9978824,0.00003943219,0.0007308415,0.000924669,0.0002446891,0.0001779776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004174675,0.00005340108,0.001507253,0.0001573017,0.00002772029,0.000198565,0.0003905699,0.01716144,0.9763092,0.003462943,0.0001452184,0.000544609],"study_design_scores_gemma":[0.0004929365,0.000200017,0.0003555075,0.0001343794,0.00006701292,0.0001206928,0.000255486,0.005141864,0.989603,0.0002104457,0.003036636,0.0003819906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827669,0.0001373853,0.009337416,0.001109691,0.001226661,0.0005608493,0.000005585558,0.001174713,0.003680808],"genre_scores_gemma":[0.8991983,0.00001463848,0.1003748,0.00009862767,0.0001458447,0.00004246489,0.000005209933,0.00003430226,0.00008580588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09103741,"threshold_uncertainty_score":0.9998924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4280501092","doi":"10.1016/j.apsusc.2022.153681","title":"Accessing the robustness of adventitious carbon for charge referencing (correction) purposes in XPS analysis: Insights from a multi-user facility data review","year":2022,"lang":"en","type":"article","venue":"Applied Surface Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":675,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"X-ray photoelectron spectroscopy; Auger; Robustness (evolution); Consistency (knowledge bases); Carbon fibers; Computer science; Binding energy; Charge (physics); Materials science; Analytical Chemistry (journal); Chemistry; Physics; Atomic physics; Algorithm; Nuclear magnetic resonance; Environmental chemistry; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04993315604445316,"gpt":0.311870156590728,"spread":0.2619370005462748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006393,0.0002242294,0.0005699677,0.0001952723,0.001026224,0.0002140206,0.003827156,0.00003511038,0.0004347838],"category_scores_gemma":[0.0007180147,0.000172603,0.00005919654,0.003494352,0.0006048825,0.0005937981,0.001835556,0.0002661155,0.000008449123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001848173,"about_ca_system_score_gemma":0.0004419459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002840017,"about_ca_topic_score_gemma":0.0009798432,"domain_scores_codex":[0.9959305,0.0003943968,0.000748301,0.00130975,0.001118447,0.0004986131],"domain_scores_gemma":[0.9970196,0.0003898131,0.0006215667,0.001736834,0.0001551243,0.00007704427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004019868,0.000121067,0.002365547,0.000156677,0.00001351656,0.00000132691,0.0008403527,0.2655615,0.7302735,0.0001192778,0.00007505636,0.0004319459],"study_design_scores_gemma":[0.0009568101,0.00007756059,0.02268559,0.000358331,0.0003516739,0.000006356943,0.002072903,0.8386565,0.1319061,0.0002059464,0.001798094,0.0009241403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885759,0.001114996,0.007462672,0.0001581729,0.001126233,0.001030542,0.0002819701,0.00007205263,0.0001774964],"genre_scores_gemma":[0.9932974,0.00007005866,0.006134305,0.0001388459,0.0000223057,0.0001627146,0.0000793263,0.00001014517,0.00008488465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5983675,"threshold_uncertainty_score":0.7892993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903010511","doi":"10.1002/aic.16489","title":"The promise of artificial intelligence in chemical engineering: Is it here, finally?","year":2018,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":637,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Engineering; Artificial intelligence; Computer science; Biochemical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02419514576406581,"gpt":0.2976703468166069,"spread":0.2734752010525411,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002605057,0.0001259596,0.0001806426,0.00006633464,0.0001551665,0.0002019796,0.0008336264,0.00006529834,0.001251685],"category_scores_gemma":[0.001108305,0.00008525535,0.00004918845,0.0002615027,0.0003235199,0.0001677593,0.0001391094,0.0003006782,0.0002416577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000475993,"about_ca_system_score_gemma":0.0001219322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002530328,"about_ca_topic_score_gemma":0.00000860559,"domain_scores_codex":[0.9982662,0.0001053381,0.0006215795,0.0002006327,0.0004251351,0.0003811564],"domain_scores_gemma":[0.999034,0.0001852,0.0002674557,0.0002630349,0.0001586779,0.00009161561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007257361,0.00003709073,0.0003181321,0.00001110454,0.00000246818,0.000007177835,0.0008846335,0.0004015506,0.9943628,0.0007313813,0.0006942883,0.002476847],"study_design_scores_gemma":[0.00007786573,0.0001541874,0.0008096861,0.00008864979,0.000005995886,0.0001272094,0.0001590389,0.02516018,0.9682664,0.002985023,0.002012844,0.0001529713],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907008,0.00005525574,0.005983711,0.001893379,0.0008602598,0.00009167266,0.000002056112,0.00001661716,0.0003962631],"genre_scores_gemma":[0.9836503,0.00001698893,0.01555808,0.0001596753,0.0004731868,0.000004511794,1.616089e-7,0.00001180997,0.000125236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0260964,"threshold_uncertainty_score":0.9996613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3009321976","doi":"10.1088/2632-2153/aba947","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":596,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research","keywords":"String (physics); Intuition; Representation (politics); Interpretation (philosophy); Task (project management); Generative model","retraction":null,"screen_n_in":null,"score":{"opus":0.01531151723872452,"gpt":0.2579600195144782,"spread":0.2426485022757537,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001796434,0.0003005696,0.0003919695,0.0005498074,0.0009817964,0.0005268979,0.001239057,0.0001608817,0.0002162975],"category_scores_gemma":[0.00375578,0.0002796632,0.00003384711,0.003021535,0.0009133753,0.0006911394,0.001009144,0.0007077724,0.0001367542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009405947,"about_ca_system_score_gemma":0.0002579745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001653371,"about_ca_topic_score_gemma":0.000007297108,"domain_scores_codex":[0.9964004,0.0001621525,0.0004517807,0.001264905,0.0009155364,0.0008052511],"domain_scores_gemma":[0.9985799,0.00009609911,0.0003304093,0.000429699,0.0003123744,0.000251582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001516132,0.00001997589,0.009794565,0.00004676914,0.000004438455,0.00004423847,0.001006426,0.007683584,0.9725487,0.006041454,0.00001803635,0.00277669],"study_design_scores_gemma":[0.0008285468,0.0006498785,0.001259949,0.00005838949,0.00004053882,0.0001709502,0.001145747,0.3550394,0.6363599,0.001340522,0.002394377,0.0007118171],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827929,0.0001602432,0.009107267,0.004950691,0.0001857841,0.0002738212,0.00000270652,0.001540617,0.0009859506],"genre_scores_gemma":[0.9644852,0.00002624067,0.0349891,0.0003502428,0.00005375462,0.00002079056,0.000003146204,0.00002696415,0.00004459679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3473558,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3164295949","doi":"10.1038/s41563-020-0777-6","title":"Machine-learned potentials for next-generation matter simulations","year":2021,"lang":"en","type":"review","venue":"Nature Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":565,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Horizon 2020 Framework Programme; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Commission","keywords":"Computer science; Bridging (networking); Computation; Field (mathematics); Computational model; Process (computing); Artificial intelligence; Machine learning; Nanotechnology; Computational science; Data science; Algorithm; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.07454285314483818,"gpt":0.3810042985753219,"spread":0.3064614454304838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002328307,0.001013014,0.003209545,0.0003503324,0.0005875565,0.002570292,0.001328496,0.001741798,0.02721874],"category_scores_gemma":[0.001327876,0.0008209903,0.0005616543,0.0004407626,0.0001379816,0.0005468606,0.000457842,0.0005849399,0.001781236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839959,"about_ca_system_score_gemma":0.0004230542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005765327,"about_ca_topic_score_gemma":0.00001195699,"domain_scores_codex":[0.9931589,0.001650816,0.001834171,0.001717093,0.0007374894,0.0009015089],"domain_scores_gemma":[0.9960513,0.0005975635,0.001443639,0.001341825,0.0003833153,0.0001823237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003375256,0.0001635366,0.00000131774,0.01927543,0.0001361257,0.00003254531,0.0000856695,0.0005223989,0.8893051,0.003307496,0.02163964,0.065497],"study_design_scores_gemma":[0.0002654093,0.0000454572,0.000001348406,0.002797792,0.0006485148,0.00007905092,0.000003438017,0.0001456344,0.02220373,0.0002365123,0.9726012,0.0009719399],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003860882,0.979519,0.00137017,0.0002293528,0.01159585,0.002469901,0.003972956,0.000266476,0.000190184],"genre_scores_gemma":[0.001033762,0.9578276,0.02279152,0.0008566769,0.005072341,0.0007701441,0.008202818,0.0003874519,0.00305763],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9509615,"threshold_uncertainty_score":0.9995542,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318486595","doi":"10.1038/s44160-022-00231-0","title":"The rise of self-driving labs in chemical and materials sciences","year":2023,"lang":"en","type":"article","venue":"Nature Synthesis","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":506,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Division of Chemical, Bioengineering, Environmental, and Transport Systems; Camille and Henry Dreyfus Foundation; National Science Foundation","keywords":"Pace; Computer science; Modular design; Automation; Status quo; Robotics; Implementation; Field (mathematics); Data science; Artificial intelligence; Sustainability; Engineering management; Systems engineering; Robot; Software engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.005897296889927839,"gpt":0.2682118815063124,"spread":0.2623145846163845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004749193,0.0001317756,0.0002460437,0.0001365322,0.0002540514,0.0001999996,0.0006821284,0.0001559458,0.0001474902],"category_scores_gemma":[0.003431194,0.00008448964,0.0000242878,0.0006293729,0.0005374611,0.0001584856,0.000308171,0.0001615714,0.00006972269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002295848,"about_ca_system_score_gemma":0.00005241631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004799771,"about_ca_topic_score_gemma":0.00001284956,"domain_scores_codex":[0.9981385,0.0003266001,0.0003229474,0.0003796055,0.0004462104,0.0003860844],"domain_scores_gemma":[0.9978788,0.001619137,0.0001614956,0.0002564156,0.00003839115,0.00004568902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009862176,0.000009857016,0.002137978,0.00003689677,0.00000162422,0.00000354043,0.0001711695,0.00003024305,0.9953355,0.001518208,0.0001585373,0.0005865783],"study_design_scores_gemma":[0.0000593927,0.00001401215,0.01594333,0.00008517387,0.000006364238,0.000006586073,0.0001007932,0.0007659161,0.9811779,0.000983048,0.0007400204,0.0001174771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975781,0.0001958151,0.000003105277,0.0009647185,0.0004816645,0.0001228371,0.00001247143,0.0001414563,0.0004998554],"genre_scores_gemma":[0.9956899,0.00008577896,0.004058698,0.00002386734,0.00006662012,0.00002634363,2.878209e-7,0.00001092654,0.00003753623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01415762,"threshold_uncertainty_score":0.4107707,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120951562","doi":"10.1021/acs.chemrev.1c00021","title":"Physics-Inspired Structural Representations for Molecules and Materials","year":2021,"lang":"en","type":"article","venue":"Chemical Reviews","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":491,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Set (abstract data type); Lead (geology); Cartesian coordinate system; Molecule; Current (fluid)","retraction":null,"screen_n_in":null,"score":{"opus":0.03355690780603994,"gpt":0.3408957769731631,"spread":0.3073388691671232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004457487,0.0001443428,0.0003744384,0.00000968164,0.0001145937,0.00020018,0.00020908,0.00004598266,0.0006344377],"category_scores_gemma":[0.001754245,0.0001160678,0.00005951583,0.0001034454,0.0001403245,0.00014338,0.0001584958,0.00004530602,0.00008681354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001837088,"about_ca_system_score_gemma":0.00003416216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009662583,"about_ca_topic_score_gemma":7.287646e-7,"domain_scores_codex":[0.9986445,0.0001189872,0.000393273,0.0004619908,0.0001379885,0.0002432119],"domain_scores_gemma":[0.9991898,0.0001301092,0.0001633301,0.0003477776,0.00008046046,0.00008855703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006062258,0.000006487282,0.00001925226,0.0001623746,0.000001271953,0.000001535678,0.00006006404,0.000004778643,0.9953055,0.002040023,0.000694907,0.00169777],"study_design_scores_gemma":[0.000162456,0.000008767607,0.0001312057,0.00005958028,0.00001662583,0.0000169344,0.000007976904,0.0002111809,0.9853251,0.005090699,0.008826878,0.000142587],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892931,0.001703771,0.007183469,0.0004728673,0.0004626652,0.0004453495,0.00006698206,0.00006829079,0.0003035243],"genre_scores_gemma":[0.6391278,0.0008303691,0.3561507,0.001325511,0.0009892759,0.0004871548,0.0002298017,0.0000600193,0.0007993594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3501653,"threshold_uncertainty_score":0.6946648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3143460494","doi":"10.1016/j.matt.2021.02.015","title":"Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery","year":2021,"lang":"en","type":"article","venue":"Matter","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":490,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Air Force Research Laboratory; National Science Foundation; Chemical Sciences, Geosciences, and Biosciences Division; Army Research Office; Basic Energy Sciences; U.S. Department of Energy; International Institute for Nanotechnology, Northwestern University; Minnesota Supercomputing Institute, University of Minnesota; Quest High Performance Computing; University of Minnesota; National Defense Science and Engineering Graduate; Office of Naval Research; Northwestern University","keywords":"Chemical space; Modular design; Computer science; Quantum chemical; Metal-organic framework; Quantum; Task (project management); Nanotechnology; Artificial intelligence; Materials science; Machine learning; Molecule; Physics; Chemistry; Drug discovery; Systems engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02327710158536039,"gpt":0.2575777627077148,"spread":0.2343006611223544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001082634,0.0002376097,0.0004456402,0.00003871374,0.0002295747,0.0005664807,0.0006188906,0.0001665389,0.007240013],"category_scores_gemma":[0.0007360022,0.0001475456,0.00009051834,0.0002059282,0.0002676985,0.0003691538,0.0003888813,0.0002960472,0.0003306452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002809102,"about_ca_system_score_gemma":0.00007989498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008123979,"about_ca_topic_score_gemma":0.000004256357,"domain_scores_codex":[0.9977419,0.0004326424,0.000555279,0.000482026,0.0003546619,0.0004335394],"domain_scores_gemma":[0.9987681,0.0002055232,0.0002872846,0.0005087816,0.000184191,0.00004612818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007415921,0.00004427143,0.0005705968,0.0001570535,0.00001309311,0.000002867613,0.0003163794,0.0002304905,0.9978149,0.0004079344,0.0003481091,0.00002017869],"study_design_scores_gemma":[0.0002213852,0.00003421574,0.0004658749,0.00009550504,0.00003647681,0.00002932899,0.00008891028,0.001080735,0.9962021,0.000580684,0.0009578703,0.000206988],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920232,0.0002730453,0.003931913,0.002397955,0.0008572809,0.0002960906,0.00004879828,0.00007812217,0.00009356824],"genre_scores_gemma":[0.9952159,0.000008911881,0.00203458,0.001042572,0.0001694761,0.00007513062,0.00002997772,0.00004746834,0.001376019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006909368,"threshold_uncertainty_score":0.9936675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766362701","doi":"10.1021/acs.chemmater.7b03500","title":"Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning","year":2017,"lang":"en","type":"article","venue":"Chemistry of Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":475,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Basic Energy Sciences; Division of Materials Research; Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Massachusetts Institute of Technology; U.S. Department of Energy; National Science Foundation","keywords":"Bottleneck; Computer science; Transformative learning; Compiler; Heuristic; Throughput; Nanotechnology; Artificial intelligence; Machine learning; Materials science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01231112383633575,"gpt":0.2511678201876742,"spread":0.2388566963513384,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00155494,0.0004086551,0.000752749,0.0000713453,0.001949532,0.002895031,0.001229132,0.0002857008,0.006554544],"category_scores_gemma":[0.001957017,0.0003561651,0.00005503964,0.0000780418,0.0009693081,0.000939602,0.00114696,0.0001642854,0.0001380484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004132353,"about_ca_system_score_gemma":0.00005257854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005315324,"about_ca_topic_score_gemma":0.000005990166,"domain_scores_codex":[0.9969411,0.0002954278,0.0007752199,0.0009798836,0.000583477,0.0004248515],"domain_scores_gemma":[0.996808,0.000238486,0.001371043,0.001230504,0.000186045,0.0001659469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001232993,0.0000432888,0.0001672245,0.0003868091,0.0000108443,0.0000187455,0.0004490355,0.00002047693,0.998396,0.00002428052,0.0000435253,0.0003164598],"study_design_scores_gemma":[0.0002701952,0.00002095574,0.002901569,0.0004402442,0.00004122821,0.00003936718,0.00002847645,0.00006670645,0.9938534,0.001042659,0.0009270343,0.0003681867],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996021,0.00038156,0.0001230046,0.000147854,0.002010539,0.000185682,0.0004726099,0.0001323993,0.0005253403],"genre_scores_gemma":[0.9954324,0.00005810046,0.003069765,0.00001355418,0.0004468694,0.00003875978,0.000125271,0.00004482083,0.0007703944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006416495,"threshold_uncertainty_score":0.999889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3128426563","doi":"10.1021/acs.accounts.0c00785","title":"Data-Driven Strategies for Accelerated Materials Design","year":2021,"lang":"en","type":"article","venue":"Accounts of Chemical Research","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":472,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research; Defense Advanced Research Projects Agency; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Nanotechnology; Data science; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.2920212880198274,"gpt":0.4658191087606581,"spread":0.1737978207408307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005507558,0.0001713775,0.0004084868,0.00009398322,0.0001530068,0.0007442583,0.002376298,0.0001536287,0.003833336],"category_scores_gemma":[0.005369367,0.0001503517,0.00003231728,0.0004638339,0.0005242592,0.000913583,0.001318522,0.0002015453,0.0002148121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000621029,"about_ca_system_score_gemma":0.001131954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000106173,"about_ca_topic_score_gemma":0.000004384868,"domain_scores_codex":[0.9961625,0.0005205756,0.0005460599,0.000821443,0.001185247,0.0007641332],"domain_scores_gemma":[0.995526,0.001538186,0.0001548265,0.001290153,0.001367034,0.0001238504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001658031,0.00008135619,0.00001231539,0.0001454668,0.000007099653,0.000008585921,0.00007595654,0.000207648,0.9907286,0.001498554,0.006918358,0.0001503267],"study_design_scores_gemma":[0.0003446598,0.00005522415,0.00004612874,0.0000580108,0.000007481854,0.000007887348,0.0001472987,0.002288505,0.9897923,0.005210809,0.001885427,0.0001562375],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928489,0.00007205056,0.004513066,0.0005510106,0.0003260906,0.000451922,0.000618872,0.00006839249,0.0005496393],"genre_scores_gemma":[0.9496906,0.00001711375,0.04954193,0.00006210092,0.0002199216,0.00007799765,0.0002077389,0.00003081739,0.0001517584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04502887,"threshold_uncertainty_score":0.9970773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2726670313","doi":"10.48550/arxiv.1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":470,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; National Research Foundation; European Commission","keywords":"Computer science; Potential energy surface; Quantum; Grid; Convolutional neural network; Discretization; Deep learning; Chemical space; Filter (signal processing); Invariant (physics); Benchmark (surveying); Quantum dynamics; Differentiable function; Artificial intelligence; Theoretical computer science; Statistical physics; Molecule; Physics; Quantum mechanics; Chemistry; Mathematics; Computer vision; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.1020130245770991,"gpt":0.2450478718179639,"spread":0.1430348472408648,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001007907,0.000441073,0.000600156,0.0001500254,0.001081051,0.0005729139,0.001892582,0.0002674841,0.0006822891],"category_scores_gemma":[0.0003451684,0.0004848993,0.0002986123,0.0001105214,0.000372848,0.000568401,0.001481715,0.0006212653,0.0002517017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002081505,"about_ca_system_score_gemma":0.0002585856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000606471,"about_ca_topic_score_gemma":0.0001071921,"domain_scores_codex":[0.9970243,0.0002564635,0.0004044379,0.001392643,0.0001632379,0.0007589045],"domain_scores_gemma":[0.9972605,0.0002409433,0.0007048086,0.00122113,0.0003753877,0.0001972093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001781959,0.00004380456,0.00129917,0.00007931141,0.00002393603,0.00002859488,0.00006352003,0.9668782,0.005342638,0.02477831,0.001262668,0.00002164314],"study_design_scores_gemma":[0.0004421816,0.0000574426,0.0002594155,0.0001851969,0.00009305361,0.00001154077,0.00004384136,0.9637803,0.0001423621,0.03325966,0.001210527,0.0005144847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6817077,0.00004315172,0.3117716,0.0001893126,0.0047639,0.0005286676,0.0001926215,0.000238007,0.0005650375],"genre_scores_gemma":[0.9915218,0.00001959312,0.005123211,0.0001125789,0.0008798479,0.00001243473,0.00009222955,0.00004598075,0.002192344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3098141,"threshold_uncertainty_score":0.9997603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388870365","doi":"10.1021/acs.jpcb.3c06662","title":"OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials","year":2023,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry B","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":469,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; Horizon 2020 Framework Programme; EMD Serono; National Institutes of Health; National Institute of General Medical Sciences; Ministerio de Ciencia e Innovación; Agencia Estatal de Investigación; XtalPi; Vir Biotechnology; Relay Therapeutics; Parker Institute for Cancer Immunotherapy; Entasis Therapeutics; Chan Zuckerberg Initiative; New York University; Cycle for Survival; Merck KGaA; Engineering and Physical Sciences Research Council; York University; AstraZeneca; Memorial Sloan-Kettering Cancer Center; Damon Runyon Cancer Research Foundation; National Science Foundation","keywords":"Computer science; Molecular dynamics; CUDA; Interface (matter); Artificial intelligence; Computational science; Machine learning; Parallel computing; Chemistry; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.007211110089778363,"gpt":0.2635682370907619,"spread":0.2563571270009836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001285624,0.000134732,0.0002341618,0.0000235002,0.0001728121,0.0001035717,0.0006035495,0.00003096126,0.000210841],"category_scores_gemma":[0.000347371,0.00007784381,0.00006436123,0.0002971429,0.0001500616,0.0001743126,0.0001391538,0.0003104312,0.00009211286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005773958,"about_ca_system_score_gemma":0.00006767301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513106,"about_ca_topic_score_gemma":5.708691e-7,"domain_scores_codex":[0.9985668,0.000189997,0.0002656742,0.0001303972,0.0006096718,0.0002374807],"domain_scores_gemma":[0.9988332,0.0002953971,0.000437861,0.0002074573,0.0001466999,0.00007940061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004652382,0.00001362809,0.00003862024,0.00001565295,0.000004165285,0.00001431594,0.0001324438,0.4647996,0.5348426,0.00001670405,0.000005106722,0.00007069583],"study_design_scores_gemma":[0.0002030593,0.00009767762,0.0001860209,0.00003813102,0.0000361767,0.0000450204,0.00007013348,0.5253718,0.4733967,0.0003840906,0.00007524519,0.0000958925],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891298,0.00001421526,0.009887789,0.0003841772,0.0000582475,0.00005351424,0.000004959437,0.00005346282,0.0004138586],"genre_scores_gemma":[0.9990312,0.000002630302,0.000342317,0.00002666705,0.0002037875,9.294826e-7,0.000005214586,0.0000189822,0.0003682457],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06144587,"threshold_uncertainty_score":0.3174379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306698380","doi":"10.1038/s41578-022-00490-5","title":"Machine learning for a sustainable energy future","year":2022,"lang":"en","type":"review","venue":"Nature Reviews Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":468,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Basic Energy Sciences; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Office of Science; Connaught Fund; Defense Advanced Research Projects Agency; Ministry of Colleges and Universities; National Research Foundation; University of Toronto; National Research Foundation Singapore; Energy Market Authority of Singapore; Canadian Institute for Advanced Research; U.S. Department of Energy","keywords":"Renewable energy; Computer science; Photovoltaics; Energy engineering; Energy management; Workflow; Fossil fuel; Energy storage; Efficient energy use; Systems engineering; Energy (signal processing); Risk analysis (engineering); Environmental economics; Photovoltaic system; Engineering; Business; Database; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02452425542512801,"gpt":0.3365971440426327,"spread":0.3120728886175048,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.01001102,0.001541569,0.006447959,0.0005108108,0.001261223,0.001102154,0.002898298,0.001377094,0.02815221],"category_scores_gemma":[0.003066597,0.001129476,0.001119666,0.0009613134,0.0001386048,0.0004742482,0.001315104,0.001522413,0.0004498732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005731609,"about_ca_system_score_gemma":0.0005468889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048105,"about_ca_topic_score_gemma":0.00000499272,"domain_scores_codex":[0.9888645,0.003920612,0.002622606,0.002029604,0.0008894511,0.001673252],"domain_scores_gemma":[0.9939284,0.0008050437,0.003319612,0.00150021,0.0001820303,0.0002647222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008461368,0.0001386509,2.353637e-7,0.1560782,0.00007775579,0.0001333204,0.00008439102,0.00001914121,0.003434482,0.02620677,0.02353594,0.7902065],"study_design_scores_gemma":[0.0002149687,0.0001784213,5.449029e-8,0.003096211,0.0006037982,0.0001723665,0.00001801093,0.000005587238,0.0003603321,0.0003518855,0.9938211,0.001177209],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000020774,0.9880245,0.0002238309,0.00005948125,0.006186038,0.003651035,0.000377168,0.0004118845,0.001064039],"genre_scores_gemma":[0.000001189529,0.9749118,0.003018314,0.000331835,0.003555084,0.004955591,0.001749925,0.0003168336,0.0111594],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9702852,"threshold_uncertainty_score":0.9999348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888436131","doi":"10.1021/acscentsci.8b00307","title":"Phoenics: A Bayesian Optimizer for Chemistry","year":2018,"lang":"en","type":"article","venue":"ACS Central Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":384,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"Division of Chemistry; Harvard University","keywords":"Computer science; Computation; Probabilistic logic; Bayesian probability; Bayesian optimization; Set (abstract data type); Kernel (algebra); Sampling (signal processing); Mathematical optimization; Machine learning; Artificial intelligence; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.00845738216555129,"gpt":0.270516171670086,"spread":0.2620587895045347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001853736,0.0001966968,0.0001969995,0.00004780619,0.0008644677,0.0004965912,0.001776138,0.00006407365,0.002555409],"category_scores_gemma":[0.001047195,0.0001653928,0.00005143023,0.0005708156,0.002356724,0.0006881102,0.0003083882,0.00008718736,0.0002912937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001387241,"about_ca_system_score_gemma":0.0003680065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005457449,"about_ca_topic_score_gemma":0.000005423522,"domain_scores_codex":[0.9968262,0.00003693569,0.0003052954,0.0008506392,0.0006817954,0.001299187],"domain_scores_gemma":[0.9985585,0.00008422551,0.0001655993,0.0005774629,0.0002645357,0.0003497286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002924987,0.00002398083,0.000289044,0.0000153858,6.971753e-7,0.000001290498,0.0003942597,0.0002866548,0.9973006,0.0005137195,0.0006527131,0.0004923752],"study_design_scores_gemma":[0.0002962367,0.00009111747,0.001286392,0.00002200287,0.000005348096,0.00001997004,0.0000662431,0.02005269,0.9713209,0.0007848697,0.005776519,0.0002776768],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499491,0.00001746992,0.04094777,0.0005974353,0.001855488,0.0003620123,0.00002579828,0.0002184682,0.006026404],"genre_scores_gemma":[0.933672,0.000002964176,0.06467906,0.0003953044,0.0005529288,0.00003095099,0.000002320495,0.00001574907,0.0006487472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0259797,"threshold_uncertainty_score":0.9983564,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068222694","doi":"10.1063/1.2196882","title":"Elucidating the hard/soft acid/base principle: A perspective based on half-reactions","year":2006,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":371,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"HSAB theory; Chemistry; Electron transfer; Base (topology); Chemical reaction; Reagent; Computational chemistry; Reactivity (psychology); Chemical physics; Organic chemistry; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01414932762796733,"gpt":0.2780104737206882,"spread":0.2638611460927209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001822044,0.0001650653,0.000215993,0.00002515483,0.000289469,0.0001397325,0.0008306463,0.00004004451,0.0001955189],"category_scores_gemma":[0.0008158308,0.00008604227,0.0001159689,0.0002383776,0.0003389574,0.0002118412,0.0000888318,0.0004941959,0.00007408208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001567205,"about_ca_system_score_gemma":0.0001261326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167646,"about_ca_topic_score_gemma":9.527973e-7,"domain_scores_codex":[0.9981223,0.0003038271,0.0004197516,0.0001632477,0.0007130483,0.0002777859],"domain_scores_gemma":[0.9978424,0.0007435048,0.000658111,0.0004117583,0.0002815337,0.00006272869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007244883,0.0001064669,0.00002844262,0.000007355821,0.000003756594,0.000002656501,0.0001750988,0.02707984,0.9688156,0.003202696,0.0004381776,0.00006750793],"study_design_scores_gemma":[0.0002892666,0.0000718277,0.0002592983,0.00006107343,0.00004449606,0.00003979894,0.000110343,0.01536645,0.9713366,0.01183526,0.000463754,0.0001218423],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.970989,0.0000299,0.02144486,0.004790599,0.0003898416,0.0001354323,0.000006353785,0.00004284469,0.002171127],"genre_scores_gemma":[0.9946181,8.890603e-7,0.003805909,0.0004258104,0.001061267,0.000003319466,8.233411e-7,0.00001773715,0.00006614594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02362906,"threshold_uncertainty_score":0.3508702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979285519","doi":"10.1016/j.matt.2019.08.017","title":"Inverse Design of Solid-State Materials via a Continuous Representation","year":2019,"lang":"en","type":"article","venue":"Matter","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":370,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"Korea Institute of Energy Technology Evaluation and Planning; Office of Science; Korea Institute of Science and Technology Information; Natural Resources Canada; National Research Foundation of Korea; U.S. Department of Energy","keywords":"Representation (politics); Generative grammar; Computer science; Generative Design; Space (punctuation); Chemical space; Inverse; Artificial intelligence; Materials science; Mathematics; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01388422208033181,"gpt":0.2728444738720601,"spread":0.2589602517917283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00106845,0.0001619587,0.0003666196,0.00009103196,0.00004634968,0.0001006135,0.0004018473,0.00005363868,0.02521502],"category_scores_gemma":[0.00006628064,0.0001398843,0.00003584183,0.0001288809,0.0001233153,0.0003173634,0.0001593441,0.00005474151,0.01336522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002449466,"about_ca_system_score_gemma":0.00002723707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002588156,"about_ca_topic_score_gemma":0.000002173586,"domain_scores_codex":[0.9980314,0.0004102394,0.0004820553,0.0004074255,0.0003397102,0.0003291194],"domain_scores_gemma":[0.9988816,0.0001095491,0.0003437751,0.0005242735,0.00008585118,0.00005495584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007798494,0.00002264629,0.005831777,0.00006173536,0.000003372057,0.000004615605,0.0004314291,0.005218695,0.9855755,0.00001227887,0.002725182,0.00003480423],"study_design_scores_gemma":[0.0003336055,0.00008148135,0.009047067,0.00003720109,0.000008363491,0.00001667318,0.00002801334,0.001603633,0.9877452,0.0007243794,0.000194735,0.0001796025],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748145,0.000003702858,0.02281108,0.0002393784,0.00108945,0.0004549147,0.00003196895,0.00007371953,0.0004812664],"genre_scores_gemma":[0.9840773,0.000001270026,0.01221743,0.000637532,0.00004387607,0.00002507739,0.000006712057,0.00002713524,0.002963649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0118498,"threshold_uncertainty_score":0.987403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011392421","doi":"10.1126/sciadv.aaz0510","title":"Computationally aided, entropy-driven synthesis of highly efficient and durable multi-elemental alloy catalysts","year":2020,"lang":"en","type":"article","venue":"Science Advances","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":348,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Light Source (Canada); Dalhousie University","funders":"University of Pittsburgh; Division of Materials Research; Center for Research Computing, University of Pittsburgh; U.S. Department of Energy; National Institutes of Health; National Science Foundation","keywords":"Alloy; Catalysis; Materials science; Computer science; Nanotechnology; Chemistry; Composite material; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01082329942644769,"gpt":0.2686163609030912,"spread":0.2577930614766435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009618804,0.0001823615,0.0002990304,0.0001099606,0.000417786,0.0001793794,0.0009113913,0.00002502603,0.0001609416],"category_scores_gemma":[0.001016544,0.000152501,0.00003558426,0.0006264152,0.00169868,0.0007758948,0.0003636481,0.00007237846,0.0001040399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004812166,"about_ca_system_score_gemma":0.0001756124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006727583,"about_ca_topic_score_gemma":0.00001130229,"domain_scores_codex":[0.9973041,0.00009654929,0.000434844,0.0007433704,0.0009683016,0.0004528453],"domain_scores_gemma":[0.9988222,0.0002295397,0.0003340837,0.0002146754,0.0001645902,0.0002349629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002111852,0.00003907413,0.002306459,0.00005571338,0.000001515563,0.000003704601,0.0006841692,0.08650468,0.9094515,0.0004123363,0.00001410542,0.0005055621],"study_design_scores_gemma":[0.0002966378,0.0001177764,0.007139799,0.00005113537,0.00001133887,0.000009772803,0.0005058708,0.08887029,0.9024625,0.0000540126,0.0002578632,0.0002230324],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947584,0.0001609232,0.003368185,0.0009147486,0.0003015811,0.0002277486,0.0000498847,0.00008611075,0.0001324616],"genre_scores_gemma":[0.924788,0.00001099408,0.07493661,0.0001805451,0.00004056718,0.00001534922,0.000002352921,0.000008968144,0.00001659721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07156842,"threshold_uncertainty_score":0.6258856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2886177874","doi":"10.1088/1361-6463/aad926","title":"The 2019 materials by design roadmap","year":2018,"lang":"en","type":"article","venue":"Journal of Physics D Applied Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":343,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Basic Energy Sciences; Office of Naval Research; Engineering and Physical Sciences Research Council; U.S. Department of Energy; U.S. Department of Defense","keywords":"Characterization (materials science); Systems engineering; Computer science; Renewable energy; Nanotechnology; Materials informatics; Engineering; Materials science; Health informatics; Health care","retraction":null,"screen_n_in":null,"score":{"opus":0.01329086361960884,"gpt":0.2580309013493508,"spread":0.244740037729742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00246763,0.000283801,0.0004504328,0.00001946922,0.0006221535,0.0005991352,0.001342665,0.00006887558,0.0002188043],"category_scores_gemma":[0.00007538756,0.0001853128,0.00009458191,0.000266923,0.0006315057,0.0003860128,0.0001880424,0.000236039,0.0008050135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000685673,"about_ca_system_score_gemma":0.0001708534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001443718,"about_ca_topic_score_gemma":2.875021e-7,"domain_scores_codex":[0.997316,0.0002812799,0.0007281161,0.0002864403,0.0008574332,0.0005307415],"domain_scores_gemma":[0.9973251,0.0003714637,0.001312993,0.0004815143,0.0003729855,0.0001359206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001326005,0.00007321228,0.000003736252,0.000007184541,0.00001448158,0.00000120633,0.0002567542,0.001502559,0.9548358,0.01170094,0.02908309,0.002388436],"study_design_scores_gemma":[0.0003427508,0.0002174999,0.00003280908,0.0000218438,0.00002975972,0.00001012119,0.00003227065,0.0002644413,0.9558832,0.03904752,0.003896848,0.0002209242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6567388,0.0001038808,0.336202,0.0003530723,0.004246164,0.0004461097,0.00006502322,0.00008417016,0.001760798],"genre_scores_gemma":[0.9814771,0.00002929717,0.0132535,0.0002692413,0.00464115,0.000009796629,0.000004040468,0.00005358171,0.0002622455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3247383,"threshold_uncertainty_score":0.999973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4300537282","doi":"10.48550/arxiv.1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling\\n quantum interactions","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":342,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; National Research Foundation; European Commission","keywords":"Computer science; Potential energy surface; Convolutional neural network; Quantum; Grid; Discretization; Chemical space; Deep learning; Filter (signal processing); Invariant (physics); Quantum dynamics; Artificial intelligence; Benchmark (surveying); Theoretical computer science; Statistical physics; Algorithm; Molecule; Physics; Quantum mechanics; Chemistry; Mathematics; Computer vision; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.09864835142768193,"gpt":0.2445056205225259,"spread":0.145857269094844,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001009581,0.0004666138,0.0006298685,0.0001538756,0.001035877,0.0005720103,0.002063822,0.0002885418,0.0007907859],"category_scores_gemma":[0.0003654093,0.0005094503,0.0003213429,0.0001150968,0.0004310413,0.0005554508,0.00155711,0.0006440178,0.0002986922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002098968,"about_ca_system_score_gemma":0.0002808621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006104175,"about_ca_topic_score_gemma":0.0001152628,"domain_scores_codex":[0.9969004,0.0002698811,0.0004192001,0.001458984,0.0001707755,0.0007807229],"domain_scores_gemma":[0.9970751,0.0002406752,0.0007347856,0.001329427,0.0004072075,0.0002128351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002109669,0.00005421052,0.001369082,0.00008229694,0.00002664136,0.00003102589,0.00006467815,0.9620152,0.004561261,0.02945678,0.002105469,0.0000223462],"study_design_scores_gemma":[0.0004775725,0.00006973175,0.0002972026,0.0001718851,0.0001002559,0.00001213881,0.00003975416,0.9583475,0.0001433097,0.03801686,0.001781721,0.000542057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7038069,0.00004668889,0.2886585,0.0002364041,0.005449913,0.0005948588,0.00023454,0.0002669528,0.0007052231],"genre_scores_gemma":[0.9912643,0.00002091602,0.004633145,0.0001289234,0.0008965979,0.00001414727,0.0001024433,0.00004850848,0.002890981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2874574,"threshold_uncertainty_score":0.9997357,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2805504266","doi":"10.1038/s41467-018-05169-6","title":"Insightful classification of crystal structures using deep learning","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":340,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Waterloo","funders":"Horizon 2020; European Commission","keywords":"Deep learning; Artificial neural network; Construct (python library); Pattern recognition (psychology); Crystal structure; Identification (biology); Deep neural networks; Lattice (music)","retraction":null,"screen_n_in":null,"score":{"opus":0.03610897137876738,"gpt":0.3432417308081047,"spread":0.3071327594293373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006772766,0.0001249749,0.0001743073,0.0001287392,0.0006321177,0.00009227055,0.001606028,0.0002019907,0.0004780365],"category_scores_gemma":[0.0008977549,0.0001128718,0.00004063566,0.0004101384,0.000810037,0.0002554209,0.0004781625,0.0005424097,0.00005033952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005307102,"about_ca_system_score_gemma":0.00006944984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007131761,"about_ca_topic_score_gemma":0.0001905197,"domain_scores_codex":[0.998412,0.0004747752,0.0003478801,0.0002517842,0.0003101279,0.0002034822],"domain_scores_gemma":[0.997534,0.0002227968,0.0003817055,0.001397839,0.0004094747,0.00005422157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009046491,0.00002388283,0.003941774,0.000008899568,0.0000028804,1.069029e-7,0.0006128383,0.0003972381,0.9756141,0.01899508,0.00004933191,0.0003448066],"study_design_scores_gemma":[0.0005820548,0.0002888315,0.2690003,0.0001181059,0.00008566417,0.0000577428,0.001020895,0.2588466,0.4229417,0.004878666,0.04141084,0.0007685267],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877675,0.0006963104,0.005773503,0.0003483981,0.0005270811,0.0001537611,0.000008756823,0.0001363385,0.004588314],"genre_scores_gemma":[0.9018958,0.00002026183,0.09783689,0.0000659385,0.0001121177,0.000005723798,0.00001765514,0.00001501487,0.00003056776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5526724,"threshold_uncertainty_score":0.5234165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3180230246","doi":"10.1145/3404835.3463238","title":"Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":328,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Python (programming language); Computer science; Information retrieval; Scripting language; Ranking (information retrieval); Relevance (law); Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07509590162092218,"gpt":0.3699382741183271,"spread":0.2948423724974049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003999939,0.0001099808,0.0001674735,0.0001251356,0.0004387323,0.0007129094,0.0002096306,0.0000543123,0.0007258991],"category_scores_gemma":[0.004445798,0.00008853821,0.00002031685,0.0005870999,0.0002390889,0.001157405,0.0002339328,0.0001264079,0.0001466186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003834233,"about_ca_system_score_gemma":0.0002527562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817631,"about_ca_topic_score_gemma":0.00006721326,"domain_scores_codex":[0.9978577,0.0002680319,0.0003237732,0.000581202,0.0005731303,0.0003961609],"domain_scores_gemma":[0.9978204,0.0003997255,0.0001035262,0.0007649151,0.0008028022,0.0001086823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004925441,0.0000466356,0.002329497,0.0001530949,0.000005310691,0.00001558212,0.001516199,0.001596376,0.9802655,0.008888422,0.004175745,0.0005150838],"study_design_scores_gemma":[0.0009848892,0.0004114766,0.01305356,0.00006398771,0.00001636365,0.0002359805,0.001549993,0.005113152,0.9519573,0.002972253,0.02332643,0.0003145855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813969,0.00002913627,0.01064666,0.002497767,0.00027608,0.0005086744,0.00001987216,0.0001560455,0.004468837],"genre_scores_gemma":[0.7949194,0.00002981129,0.1977341,0.0003209636,0.0001862575,0.0001077546,0.00004697994,0.00002634916,0.006628355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1870874,"threshold_uncertainty_score":0.7948086,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2884258597","doi":"10.1021/acsnano.8b04726","title":"How To Optimize Materials and Devices <i>via</i> Design of Experiments and Machine Learning: Demonstration Using Organic Photovoltaics","year":2018,"lang":"en","type":"article","venue":"ACS Nano","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":315,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; National Institute for Nanotechnology; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Alberta Innovates - Technology Futures","keywords":"Interconnectivity; Variable (mathematics); Computer science; Design of experiments; Multivariable calculus; Process (computing); Photovoltaics; Photovoltaic system; Artificial intelligence; Machine learning; Engineering; Control engineering; Mathematics; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03409122818066906,"gpt":0.2711255650264505,"spread":0.2370343368457815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001093262,0.0002096151,0.000320545,0.00009792775,0.0002923734,0.0004061691,0.0002602072,0.00008559338,0.000263174],"category_scores_gemma":[0.0003664741,0.0001844908,0.00001085687,0.0002053854,0.0002966348,0.000439616,0.000264293,0.00005294389,0.00001662659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002608299,"about_ca_system_score_gemma":0.00004719188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002025005,"about_ca_topic_score_gemma":0.00001066679,"domain_scores_codex":[0.9982965,0.0003290611,0.0003209459,0.0004578648,0.0002851666,0.0003104337],"domain_scores_gemma":[0.9991267,0.0001021509,0.0002892171,0.0002347625,0.0001299904,0.0001172233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007060436,0.00001708326,0.001144057,0.00003285763,0.00000391224,0.00000145578,0.000538284,0.0001774715,0.9978756,0.0000230057,0.00001344131,0.0001022197],"study_design_scores_gemma":[0.0002796919,0.0003424374,0.0003002902,0.00004812338,0.00001882437,0.00003812992,0.00007800283,0.003597415,0.9948988,0.0000674719,0.0001314119,0.0001994056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9243419,0.0001115168,0.07471769,0.00008765898,0.0003165813,0.0003346395,0.000009156428,0.00005984502,0.00002103381],"genre_scores_gemma":[0.8706487,0.00001716821,0.1290212,0.0001080737,0.00008145387,0.000009223696,0.000002704931,0.00002345695,0.00008805104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05430348,"threshold_uncertainty_score":0.7523316,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3115677442","doi":"10.1063/5.0021106","title":"Data-driven materials research enabled by natural language processing and information extraction","year":2020,"lang":"en","type":"article","venue":"Applied Physics Reviews","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":294,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Xerox (Canada)","funders":"Lawrence Livermore National Laboratory; Office of Naval Research; ISIS Neutron and Muon Source; Royal Academy of Engineering; Laboratory Directed Research and Development; U.S. Department of Energy; Science and Technology Facilities Council; National Nuclear Security Administration; National Science Foundation","keywords":"Computer science; Data science; Information extraction; Variety (cybernetics); Field (mathematics); Domain (mathematical analysis); Data processing; Natural language; Natural (archaeology); Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.0655541559999387,"gpt":0.374987713412994,"spread":0.3094335574130553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002287652,0.0001726709,0.0003550581,0.00002805375,0.0002810069,0.0006597,0.0006782403,0.00004919191,0.0002488579],"category_scores_gemma":[0.000345867,0.0001390463,0.00001374555,0.0003429918,0.0001418874,0.00216783,0.0004838873,0.0002329254,0.0008622559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002775145,"about_ca_system_score_gemma":0.00004409745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002638174,"about_ca_topic_score_gemma":9.234334e-7,"domain_scores_codex":[0.9979807,0.0003061378,0.000476073,0.0004403325,0.0004634467,0.0003332935],"domain_scores_gemma":[0.9989555,0.00009341938,0.0003360001,0.0004451273,0.00006740275,0.0001025888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001865414,0.000009166872,0.000002573007,0.0003358597,0.000001057826,4.047955e-7,0.0009208316,0.00004151963,0.9617804,0.0004403896,0.00462932,0.03181982],"study_design_scores_gemma":[0.00060089,0.00006647823,0.0001186094,0.0002432017,0.00003835321,0.00000748364,0.0004671619,0.02665593,0.657354,0.0003083459,0.3134718,0.0006677529],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651938,0.007186506,0.01535182,0.001385841,0.0007202056,0.003606834,0.0005201843,0.0005023625,0.005532424],"genre_scores_gemma":[0.990885,0.0003896951,0.006776352,0.0008133361,0.0004051494,0.0001007165,0.0005786795,0.00001989622,0.00003118566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3088425,"threshold_uncertainty_score":0.9999157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321085451","doi":"10.1021/acscatal.2c05426","title":"The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts","year":2023,"lang":"en","type":"article","venue":"ACS Catalysis","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":288,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; The Scarborough Hospital; University of Toronto","funders":"","keywords":"Benchmark (surveying); Baseline (sea); Computer science; Scaling; Range (aeronautics); Oxide; Set (abstract data type); Machine learning; Materials science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0375950222084821,"gpt":0.3100737398999703,"spread":0.2724787176914882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004359728,0.0002438178,0.000370013,0.0001312805,0.001198832,0.0009085053,0.002514002,0.00007147172,0.00005721353],"category_scores_gemma":[0.001058431,0.0001735633,0.00005348076,0.0006297447,0.0002978463,0.0006126757,0.001691057,0.0001108278,0.0005523721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004268092,"about_ca_system_score_gemma":0.00008117536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006787098,"about_ca_topic_score_gemma":0.0008676496,"domain_scores_codex":[0.9973986,0.0001795427,0.0004045761,0.0008677763,0.0004342251,0.0007152688],"domain_scores_gemma":[0.9974431,0.0008196419,0.0002444223,0.00127418,0.0000763583,0.0001422705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007269638,0.00003259298,0.0001496919,0.000115681,0.00005793232,0.00001221991,0.000467461,0.0001428601,0.9581422,0.002425219,0.03227479,0.006106673],"study_design_scores_gemma":[0.0009376269,0.0001982928,0.005054915,0.00004039378,0.0002698707,0.00006783586,0.001121123,0.002804181,0.5339656,0.003679452,0.4509276,0.0009330638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779755,0.003457661,0.0002784171,0.01327549,0.0006718739,0.001412688,0.002107377,0.0003936777,0.0004273328],"genre_scores_gemma":[0.9751221,0.006291002,0.002798503,0.0006299064,0.0003539054,0.001472782,0.01001352,0.0001274415,0.003190851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4241766,"threshold_uncertainty_score":0.9220568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306179830","doi":"10.1016/j.patter.2022.100588","title":"SELFIES and the future of molecular string representations","year":2022,"lang":"en","type":"review","venue":"Patterns","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":267,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"National Institute of General Medical Sciences; European Research Council; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; National Centre of Competence in Research Robotics; University of Toronto; Horizon 2020; Amazon Web Services; Universität Wien; Office of Science; Austrian Science Fund; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Consejo Nacional de Ciencia y Tecnología; National Science Foundation; Deutsche Forschungsgemeinschaft; Fundação de Amparo à Pesquisa do Estado de São Paulo; U.S. Department of Energy; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Cheminformatics; Computer science; String (physics); Artificial intelligence; Interpretability; Context (archaeology); Popularity; Representation (politics); Perspective (graphical); Data science; Cognitive science; Chemistry; Computational chemistry; Physics; Theoretical physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02486925247903319,"gpt":0.3301125758047184,"spread":0.3052433233256852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001124717,0.0001985754,0.0007386023,0.00007800089,0.0001908042,0.0001197535,0.0007198886,0.00005646863,0.002330702],"category_scores_gemma":[0.0001358643,0.0001225243,0.0001447468,0.0001717457,0.0001885694,0.00006546239,0.00059712,0.0002329431,0.00001833878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002187288,"about_ca_system_score_gemma":0.00006131861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001490278,"about_ca_topic_score_gemma":0.000007698321,"domain_scores_codex":[0.9977567,0.000860378,0.0004458947,0.0003773277,0.0003745743,0.0001851014],"domain_scores_gemma":[0.9984539,0.0004535643,0.0004836939,0.0005555746,0.0000185507,0.00003478446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003351972,0.00008827032,0.0004383088,0.04216727,0.0001487775,0.0001061894,0.00404444,0.0005349186,0.001976817,0.02384263,0.000591083,0.9260278],"study_design_scores_gemma":[0.0002405319,0.00002387769,0.00004266504,0.00106769,0.000303263,0.00008969293,0.0002583573,0.00003799014,0.0002071897,0.0003395916,0.9971101,0.0002790379],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002200361,0.9955239,0.000419598,0.0001041674,0.0008321166,0.0004623456,0.0001349635,0.00004172361,0.0002808729],"genre_scores_gemma":[0.0005717718,0.9985197,0.0004502006,0.00003539548,0.0001434463,0.0001427156,0.00002276009,0.00002403494,0.00009004601],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.996519,"threshold_uncertainty_score":0.9985813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041603413","doi":"10.1021/acscentsci.0c00426","title":"Generative Adversarial Networks for Crystal Structure Prediction","year":2020,"lang":"en","type":"article","venue":"ACS Central Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"National Research Foundation of Korea","keywords":"Generative grammar; Computer science; Chemical space; Representation (politics); Crystal structure prediction; Crystal (programming language); Ternary operation; Adversarial system; Generative model; Stability (learning theory); Generative adversarial network; Space (punctuation); Artificial intelligence; Machine learning; Deep learning; Crystal structure; Drug discovery; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01083802880132513,"gpt":0.2411311884319809,"spread":0.2302931596306558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006520956,0.0001933992,0.0001975046,0.00003926536,0.0007425994,0.0004576711,0.00102249,0.00007659086,0.0005537029],"category_scores_gemma":[0.0008264668,0.0001608999,0.00004535223,0.0005847132,0.0007539273,0.0009366789,0.0002353991,0.0001456816,0.00002216505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109881,"about_ca_system_score_gemma":0.0002642415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003108081,"about_ca_topic_score_gemma":0.000007273257,"domain_scores_codex":[0.9972359,0.00008251624,0.000297354,0.0008106668,0.0006678766,0.0009056642],"domain_scores_gemma":[0.9989782,0.00006906765,0.0001689116,0.000231913,0.0001521979,0.0003996992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006402718,0.000008000266,0.000709598,0.000008549614,0.000001166355,0.000001244381,0.0007705566,0.1007142,0.8955806,0.001054192,0.0008889873,0.00019879],"study_design_scores_gemma":[0.0007365621,0.0003883818,0.009006102,0.00001482061,0.00001542456,0.00001148904,0.0001393601,0.5279005,0.4574769,0.000588204,0.003348357,0.0003739102],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8372099,0.00002132432,0.1569781,0.001439389,0.003253349,0.0005414076,0.0001860723,0.0001975698,0.0001729073],"genre_scores_gemma":[0.9802102,0.000003152769,0.01736325,0.0009684071,0.001385172,0.0000139918,0.00001720725,0.00001290036,0.00002570721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4381037,"threshold_uncertainty_score":0.6561307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067050455","doi":"10.1063/1.2336223","title":"A random-sampling high dimensional model representation neural network for building potential energy surfaces","year":2006,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":259,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Representation (politics); Component (thermodynamics); Artificial neural network; Computer science; Mode (computer interface); Term (time); Potential energy; Quantum; Statistical physics; Energy (signal processing); Construct (python library); Algorithm; Applied mathematics; Mathematics; Artificial intelligence; Physics; Quantum mechanics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.016444030152513,"gpt":0.2742124467487915,"spread":0.2577684165962785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001087156,0.0001333668,0.0002808703,0.00001508929,0.0001821814,0.00009969659,0.0004347212,0.000042666,0.00001871862],"category_scores_gemma":[0.0001188286,0.0000876483,0.0001179817,0.0001159504,0.0001377352,0.000274716,0.00009917534,0.0001348448,0.000001343947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003188263,"about_ca_system_score_gemma":0.00004358638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009243345,"about_ca_topic_score_gemma":4.976785e-7,"domain_scores_codex":[0.9984416,0.000136372,0.0004847059,0.0001491092,0.0004946889,0.000293484],"domain_scores_gemma":[0.9985036,0.0005064695,0.000583839,0.0001568398,0.0001998656,0.00004939111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002617936,0.00001461813,0.000006640449,0.000003539725,0.00000252007,4.079186e-7,0.00001121232,0.5000162,0.4985703,0.0007056501,0.0003531432,0.00005396835],"study_design_scores_gemma":[0.0005294129,0.00002020973,0.00001919658,0.00001661656,0.00003410679,0.00001851549,0.000001886525,0.507033,0.417349,0.07490071,0.000006783577,0.00007055634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6780485,0.0000493183,0.3211799,0.0002410679,0.0004039129,0.00004979883,0.000004751374,0.00001387208,0.000008857656],"genre_scores_gemma":[0.9318985,0.000002010286,0.06621259,0.0001037732,0.001739732,0.000002400069,0.000005089838,0.00001559543,0.00002027726],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2549673,"threshold_uncertainty_score":0.3574194,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2558855463","doi":"10.1107/s2053273314085623","title":"SHELXT: Integrating space group determination and structure solution","year":2014,"lang":"en","type":"article","venue":"Acta Crystallographica Section A Foundations and Advances","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":249,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Group (periodic table); Space (punctuation); Superposition principle; Crystallography; Simple (philosophy); Atom (system on chip); Element (criminal law); Crystal structure; Isotropy; Physics; Chemistry; Computer science; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.005479377483220156,"gpt":0.2483983033882465,"spread":0.2429189259050263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005273168,0.0001578913,0.000151065,0.0001922612,0.0008249386,0.0004425087,0.0001094258,0.00007337682,0.0001648681],"category_scores_gemma":[0.0003498683,0.0001359987,0.0000240987,0.0003071244,0.0003288357,0.001139917,0.00007070717,0.0001342275,5.399548e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001772798,"about_ca_system_score_gemma":0.00001032203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008857416,"about_ca_topic_score_gemma":0.0005942272,"domain_scores_codex":[0.9987609,0.0001793836,0.0002335288,0.0004247818,0.0001906824,0.000210771],"domain_scores_gemma":[0.9993107,0.0001630108,0.000216675,0.0001552951,0.00007946088,0.00007486655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009242455,0.00001216908,0.00228455,0.00003551268,0.00000156068,1.702953e-7,0.0001713697,0.00008202317,0.9839736,0.00254159,0.000009326897,0.0108789],"study_design_scores_gemma":[0.001991474,0.001518563,0.1388707,0.0003588355,0.0001354628,0.0004427173,0.001670106,0.2534575,0.007921204,0.0609526,0.530772,0.001908961],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9122214,0.00008819067,0.08569083,0.0006324553,0.0005929671,0.000153563,0.000008248947,0.0001442708,0.0004680195],"genre_scores_gemma":[0.9673097,0.0001131492,0.0322656,0.00007554299,0.0001545637,0.0000171303,0.0000197207,0.0000107715,0.0000337936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9760524,"threshold_uncertainty_score":0.6344844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176386153","doi":"10.1038/s41524-021-00559-9","title":"Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon","year":2021,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":248,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Nuclear Security Administration; Sandia National Laboratories; Deutsche Forschungsgemeinschaft; U.S. Department of Energy","keywords":"Cluster expansion; Cluster (spacecraft); Atomic units; Silicon; Coupled cluster; Copper; Atom (system on chip); Computer science; Computational science; Scale (ratio); Statistical physics; Atomic physics; Materials science; Physics; Parallel computing; Quantum mechanics; Optoelectronics; Molecule; Metallurgy","retraction":null,"screen_n_in":null,"score":{"opus":0.006751412768742941,"gpt":0.2815870211184462,"spread":0.2748356083497033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006848521,0.0001159584,0.0001864225,0.00004217502,0.000186127,0.0001518058,0.0001352763,0.00003877527,0.0004120914],"category_scores_gemma":[0.00006193358,0.00008863353,0.00001560732,0.0001118188,0.00009917605,0.0001724961,0.0002984627,0.0000294393,0.0000394218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002844969,"about_ca_system_score_gemma":0.00008133448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001220319,"about_ca_topic_score_gemma":0.00002055638,"domain_scores_codex":[0.9986152,0.0002287366,0.0003707016,0.0003225695,0.0003078662,0.0001549192],"domain_scores_gemma":[0.9993252,0.0001024017,0.0001873354,0.0001837477,0.0001463025,0.00005503754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002226814,0.00001056933,0.00208663,0.00006158731,0.000002054805,2.555833e-7,0.0005749481,0.004286711,0.9904289,0.00178111,0.0001219293,0.0006230713],"study_design_scores_gemma":[0.0003516542,0.00003806376,0.1956692,0.00003312123,0.00001080462,0.00003543033,0.0001942574,0.002540451,0.7989117,0.001960258,0.0001410296,0.0001139748],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952872,0.00002172997,0.002638192,0.001198692,0.0003677191,0.0003711519,0.0000628452,0.00002400997,0.00002845783],"genre_scores_gemma":[0.9925346,0.000004356305,0.006780412,0.0005361558,0.00004745406,0.0000337761,0.00002613436,0.00001060079,0.00002646648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1935826,"threshold_uncertainty_score":0.4512112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792351009","doi":"10.1063/1.5003074","title":"Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy","year":2018,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":243,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Kriging; Energy spectrum; Artificial neural network; Gaussian process; Quality (philosophy); Regression; Gaussian; Energy (signal processing); Process (computing); Statistics; Regression analysis; Spectrum (functional analysis); Artificial intelligence; Pattern recognition (psychology); Statistical physics; Machine learning; Computer science; Biological system; Mathematics; Physics; Biology; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.05107494095692278,"gpt":0.3710061537636172,"spread":0.3199312128066944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001344517,0.0001340125,0.000370332,0.0000173374,0.0001887225,0.00008702136,0.0004856034,0.00003680649,0.00003514948],"category_scores_gemma":[0.0002634134,0.0000796243,0.00004995509,0.000139153,0.0003642281,0.0003708939,0.0001542397,0.0001545354,3.97242e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001435638,"about_ca_system_score_gemma":0.00004094129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004634507,"about_ca_topic_score_gemma":0.00000313574,"domain_scores_codex":[0.9981596,0.0003607847,0.0006064463,0.000177507,0.000490875,0.0002047273],"domain_scores_gemma":[0.9976238,0.0005659491,0.001252789,0.0001951756,0.0002970845,0.00006519636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001101148,0.000210411,0.0004321514,0.00002831704,0.00001421366,6.786926e-7,0.002461458,0.03267973,0.9627785,0.0001466096,0.00008317694,0.0000636195],"study_design_scores_gemma":[0.000775765,0.0005344141,0.001698024,0.00006606791,0.00004761467,0.00002239798,0.0006123966,0.2410488,0.7488156,0.006248655,0.000003041475,0.0001272519],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830633,0.00002133701,0.0161698,0.0003245233,0.0002441,0.000138838,0.000004422378,0.000008982933,0.00002471127],"genre_scores_gemma":[0.9980926,0.000001419832,0.001042068,0.00004268467,0.0008049865,0.000002309202,0.000001303384,0.000008165748,0.00000445651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2139629,"threshold_uncertainty_score":0.3246985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384154882","doi":"10.1126/science.abn3445","title":"The central role of density functional theory in the AI age","year":2023,"lang":"en","type":"review","venue":"Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Density functional theory; Context (archaeology); Relevance (law); Computer science; Transferability; Scalability; Artificial intelligence; Machine learning; Data science; Learning theory; Chemistry; Biology; Psychology; Cognitive psychology; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.0355435939069281,"gpt":0.335990011550217,"spread":0.3004464176432889,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01712428,0.0002702849,0.0006124106,0.0001858408,0.0008651836,0.0005528576,0.004026511,0.00009408158,0.0001906863],"category_scores_gemma":[0.002364167,0.0001294784,0.0001637269,0.002007699,0.003217154,0.00026393,0.0006527731,0.0004242044,0.0004656765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248044,"about_ca_system_score_gemma":0.001053955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001010794,"about_ca_topic_score_gemma":0.00008948234,"domain_scores_codex":[0.9950715,0.001214214,0.0006728034,0.0007002434,0.001510478,0.0008307489],"domain_scores_gemma":[0.9967857,0.001577041,0.0004708011,0.0009907978,0.00009650495,0.00007912618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007221859,0.0002360544,0.0003624558,0.005862412,0.00002460926,0.0001392599,0.005987464,0.001019435,0.04012508,0.2191055,0.00128497,0.7257805],"study_design_scores_gemma":[0.0001335875,0.00008723606,0.00707131,0.003220177,0.00009176875,0.0001314608,0.0007337274,0.0003214123,0.0008106873,0.03941713,0.9472908,0.0006906359],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005974883,0.985526,0.0002266326,0.000213393,0.004680763,0.001284865,0.0000508592,0.0001443086,0.001898347],"genre_scores_gemma":[0.004843157,0.9928555,0.0003337439,0.000229461,0.0004392807,0.0001568813,0.000009990998,0.00004602073,0.001085957],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9460059,"threshold_uncertainty_score":0.9994955,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071267590","doi":"10.1002/qua.24795","title":"Neural network‐based approaches for building high dimensional and quantum dynamics‐friendly potential energy surfaces","year":2014,"lang":"en","type":"article","venue":"International Journal of Quantum Chemistry","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":220,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bottleneck; Quantum; Computer science; Ab initio; Artificial neural network; Potential energy; Statistical physics; Function (biology); Multi-mode optical fiber; Reduction (mathematics); Biological system; Physics; Artificial intelligence; Quantum mechanics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01168171702476078,"gpt":0.2484356903704982,"spread":0.2367539733457374,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001309424,0.0002138412,0.0003170765,0.00005931269,0.0001579773,0.0002889631,0.0007783945,0.00009747016,0.0001396922],"category_scores_gemma":[0.0004068898,0.0001844496,0.0001168891,0.00006107493,0.0002231368,0.0002998314,0.00015912,0.0001675805,0.000001308012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007848101,"about_ca_system_score_gemma":0.00009687793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005385957,"about_ca_topic_score_gemma":0.000001970345,"domain_scores_codex":[0.9978645,0.0001050544,0.0006202261,0.0003308224,0.0007458559,0.0003335354],"domain_scores_gemma":[0.9982753,0.0002768278,0.0007812388,0.0001528278,0.0003688148,0.0001450031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002974364,0.00005477912,0.0003058875,0.00003509855,0.00002065589,0.00001516309,0.00001044223,0.4294018,0.5526665,0.01635566,0.0003563568,0.000480191],"study_design_scores_gemma":[0.0007515902,0.0001159151,0.0005688904,0.00007627449,0.00002717736,0.0002461419,0.00001473281,0.9344825,0.05386826,0.00914442,0.0005045512,0.0001996175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7853423,0.00009320864,0.2113341,0.001081175,0.002009969,0.00003434717,0.00003448451,0.00002402895,0.00004642548],"genre_scores_gemma":[0.9847605,0.000002875998,0.01377833,0.0002210095,0.001140023,0.000004762224,0.00002585705,0.000023487,0.00004314065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5050806,"threshold_uncertainty_score":0.7521638,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013352749","doi":"10.1088/1361-651x/ab7150","title":"Roadmap on multiscale materials modeling","year":2020,"lang":"en","type":"article","venue":"Modelling and Simulation in Materials Science and Engineering","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":203,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"H2020 European Research Council; Lawrence Livermore National Laboratory; FP7 Ideas: European Research Council; Basic Energy Sciences; Deutsche Forschungsgemeinschaft; Cleansky; Sandia National Laboratories; National Nuclear Security Administration; U.S. Department of Energy; European Commission; Comunidad de Madrid; Korea Institute of Materials Science; Engineering and Physical Sciences Research Council; Leverhulme Trust; Seventh Framework Programme; Division of Materials Sciences and Engineering; National Science Foundation","keywords":"Computer science; Management science; Field (mathematics); Multiscale modeling; Scale (ratio); Systems engineering; Data science; Nanotechnology; Biochemical engineering; Materials science; Engineering; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02873269238294067,"gpt":0.2535725967670546,"spread":0.2248399043841139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001979968,0.0002410439,0.0003390003,0.0001989668,0.0002725439,0.0006587433,0.0002764027,0.00007779412,0.000108481],"category_scores_gemma":[0.0003660821,0.0002228735,0.00001164529,0.0003279849,0.0001443895,0.0006684306,0.0001570414,0.00009894618,0.00003533169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004424442,"about_ca_system_score_gemma":0.00003661154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001026888,"about_ca_topic_score_gemma":5.42188e-7,"domain_scores_codex":[0.9977476,0.00005675226,0.0004960463,0.0007074971,0.0005089826,0.0004831168],"domain_scores_gemma":[0.9993505,0.00008752653,0.00008913421,0.0001819182,0.00008628151,0.0002046609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002040977,0.000004098478,0.00001818962,0.00003607431,2.907428e-7,0.000001546633,0.0004476534,0.5235976,0.4756362,0.0002013227,4.056621e-7,0.00003627544],"study_design_scores_gemma":[0.0002245733,0.00004767425,0.00009580693,0.00007845486,0.000002852863,0.000002161566,0.00003447742,0.8296801,0.1694774,0.0001112332,0.00002438694,0.0002208227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9116418,0.00003293931,0.08732323,0.0002258118,0.0004084656,0.000183555,0.00001224388,0.0001418529,0.00003011291],"genre_scores_gemma":[0.9883072,0.00002228831,0.01127956,0.0001940634,0.0001511341,0.00001461553,0.000002663507,0.00002346189,0.000005005544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3061588,"threshold_uncertainty_score":0.9088517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770164889","doi":"10.1038/s41524-017-0055-6","title":"Virtual screening of inorganic materials synthesis parameters with deep learning","year":2017,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":198,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; National Science Foundation","keywords":"Autoencoder; Computer science; Realizability; Chemical space; Space (punctuation); Artificial intelligence; Machine learning; Deep learning; Algorithm; Chemistry; Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.01598037952391024,"gpt":0.2593914036471683,"spread":0.243411024123258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002287939,0.0003934051,0.0008085188,0.0002214531,0.001019149,0.001239324,0.001317302,0.0001331208,0.004605289],"category_scores_gemma":[0.001732153,0.0003321388,0.00005657482,0.000129406,0.0007019747,0.0008033631,0.0004684611,0.0001184119,0.000330074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004842413,"about_ca_system_score_gemma":0.0001050119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003739099,"about_ca_topic_score_gemma":0.000007899044,"domain_scores_codex":[0.9962447,0.0006618825,0.0008952342,0.0007119254,0.0009282026,0.0005581087],"domain_scores_gemma":[0.996605,0.000662886,0.001600058,0.0006942944,0.0002990574,0.0001387283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002770495,0.00004152018,0.001247355,0.00007885885,0.00002566304,0.00001423968,0.0002313538,0.07339547,0.9218412,0.002141434,0.00001488135,0.0006909952],"study_design_scores_gemma":[0.0005494061,0.0002807337,0.03879309,0.0002502727,0.00005222101,0.00005733367,0.0001022991,0.001412238,0.95704,0.0009615468,0.000047013,0.0004538567],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736211,0.00001029741,0.02437879,0.000191983,0.0009447004,0.000314837,0.0001116364,0.0001693541,0.0002573396],"genre_scores_gemma":[0.9221823,0.000003682811,0.07735142,0.00005819366,0.0001641899,0.00005621753,0.00003525654,0.00006067712,0.00008811669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07198323,"threshold_uncertainty_score":0.999913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998860313","doi":"10.1021/jp055253z","title":"A Nested Molecule-Independent Neural Network Approach for High-Quality Potential Fits","year":2005,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry A","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Mean squared error; Simple (philosophy); Artificial neural network; Function (biology); Basis (linear algebra); Chemistry; Surface (topology); Potential energy; Energy (signal processing); Algorithm; Square (algebra); Potential energy surface; Statistical physics; Molecule; Computer science; Mathematics; Physics; Artificial intelligence; Quantum mechanics; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01316314854971842,"gpt":0.2817688155195605,"spread":0.2686056669698421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001909624,0.0001884628,0.0003636112,0.000009831759,0.0002159371,0.0001160912,0.0009634985,0.00005979276,0.0001399238],"category_scores_gemma":[0.0002437687,0.0001193861,0.0001617271,0.0001243992,0.0001730492,0.0002033155,0.0001507146,0.0003117913,0.00001209915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005408816,"about_ca_system_score_gemma":0.00006531491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185348,"about_ca_topic_score_gemma":2.885893e-7,"domain_scores_codex":[0.9979785,0.000264993,0.0005004527,0.000206476,0.0006437164,0.0004058306],"domain_scores_gemma":[0.998472,0.0002329419,0.0006608415,0.0003127804,0.0001846032,0.0001367943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000187737,0.00009326403,0.000002889567,0.00003321192,0.000005823123,0.000001545854,0.00008838068,0.3857717,0.6134706,0.00006094193,0.0001921152,0.00009184046],"study_design_scores_gemma":[0.0008333967,0.0001442116,0.000585188,0.00002431632,0.00008290137,0.0001728821,0.00004936553,0.1656335,0.8313722,0.0007884902,0.00009303668,0.0002205771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965052,0.00003307695,0.03378118,0.0006106624,0.0001136144,0.0001382757,0.00001054634,0.0000284556,0.0002322035],"genre_scores_gemma":[0.9908091,0.000001011703,0.005413439,0.0001590103,0.003427793,0.000006616542,0.000003608465,0.00001680607,0.0001625441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2201382,"threshold_uncertainty_score":0.4868423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3015692433","doi":"10.1039/d0sc00445f","title":"Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex","year":2020,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; Toronto Metropolitan University; University of Toronto; Toronto Public Health","funders":"Natural Resources Canada; Horizon 2020 Framework Programme; Norges Forskningsråd; European Commission; Compute Canada","keywords":"Chemical space; Space (punctuation); Computer science; Chemistry; Materials science; Biochemistry; Drug discovery; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03534743907417005,"gpt":0.2820316854995478,"spread":0.2466842464253778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002583301,0.000219849,0.0002592086,0.0000659178,0.0003764519,0.00048609,0.002132258,0.00007009695,0.0005733876],"category_scores_gemma":[0.003376649,0.00015796,0.0000501072,0.001637721,0.001073826,0.0006246619,0.0005196428,0.0004761098,0.0002416001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578533,"about_ca_system_score_gemma":0.0001074188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001455049,"about_ca_topic_score_gemma":0.000001528745,"domain_scores_codex":[0.9966935,0.0002004366,0.0003665377,0.0008318038,0.00118281,0.0007249295],"domain_scores_gemma":[0.9988257,0.0003682608,0.0001807805,0.0003222411,0.0000666061,0.000236385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001958846,0.00002679844,0.001744965,0.00001657631,4.1659e-7,0.000003432315,0.001551663,0.0006219172,0.9949415,0.0008497133,0.00006181734,0.0001616459],"study_design_scores_gemma":[0.0002199914,0.00003253853,0.0008860869,0.00002190165,0.000002711877,0.000011836,0.00018381,0.05275233,0.944079,0.0003095722,0.001268029,0.00023222],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898614,0.0000134813,0.001586012,0.005954979,0.0001260384,0.0002094486,0.000002600414,0.0001524206,0.002093621],"genre_scores_gemma":[0.9945978,0.000001979715,0.004011407,0.001137021,0.0001999751,0.00001685251,0.000008346895,0.00001377179,0.00001285406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05213041,"threshold_uncertainty_score":0.644142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015541791","doi":"10.1063/1.2387950","title":"Using neural networks to represent potential surfaces as sums of products","year":2006,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential function; Artificial neural network; Product (mathematics); Representation (politics); Canonical normal form; Grid; Quantum; Computer science; Hartree; Applied mathematics; Mathematics; Mathematical optimization; Algorithm; Artificial intelligence; Quantum mechanics; Physics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.0176585223734998,"gpt":0.2790053328809624,"spread":0.2613468105074626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001133816,0.0001237523,0.0002816324,0.00002030604,0.00006503305,0.00006163019,0.0006823041,0.00003520327,0.0000489266],"category_scores_gemma":[0.0002215783,0.00007884242,0.00006562338,0.0002480362,0.0002138594,0.0001983634,0.0001996172,0.0001928578,0.000007736904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003079834,"about_ca_system_score_gemma":0.00005187008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002136519,"about_ca_topic_score_gemma":3.126884e-7,"domain_scores_codex":[0.9983038,0.0001878728,0.0005059872,0.0001448681,0.0005959241,0.0002614947],"domain_scores_gemma":[0.9986593,0.0001103493,0.0005916654,0.000293237,0.0002802301,0.00006523514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007873678,0.00002464052,0.00005708972,0.000007957827,0.000001881079,0.00000222543,0.00004618571,0.4170471,0.5824241,0.00004485677,0.0002319693,0.00003332243],"study_design_scores_gemma":[0.0001288767,0.00006172444,0.0001883316,0.00003116324,0.00003201369,0.00007849527,0.00001308347,0.0568301,0.9403411,0.002186869,0.00001928299,0.00008899568],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934858,0.00006562299,0.005131191,0.000524606,0.0006016279,0.00009284367,0.000001815241,0.00001118466,0.00008532935],"genre_scores_gemma":[0.9942251,0.000001806484,0.004528536,0.00006298353,0.001145456,2.872566e-7,5.192477e-7,0.00001272459,0.00002261601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3602169,"threshold_uncertainty_score":0.3215101,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416191329","doi":"10.1063/5.0297006","title":"A foundation model for atomistic materials chemistry","year":2025,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":187,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; Air Force Research Laboratory; Science and Technology Facilities Council; HORIZON EUROPE Framework Programme; Shanghai Jiao Tong University; Office of Science; Gauss Centre for Supercomputing; U.S. Naval Research Laboratory; Churchill College, University of Cambridge; Natural Sciences and Engineering Research Council of Canada; Grand Équipement National De Calcul Intensif; Commissariat à l'Énergie Atomique et aux Énergies Alternatives; Deutsche Forschungsgemeinschaft; John Fell Fund, University of Oxford; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Isaac Newton Trust; Alexander von Humboldt-Stiftung; Danmarks Grundforskningsfond; Stuttgart Center for Simulation Science, Universität Stuttgart; European Commission; HORIZON EUROPE European Research Council; Studienstiftung des Deutschen Volkes; Graphene Flagship; National Science Foundation; UK Research and Innovation; Centro Svizzero di Calcolo Scientifico; Vetenskapsrådet","keywords":"Leverage (statistics); Foundation (evidence); Ab initio; Transferability; Molecular dynamics; Underpinning; Force field (fiction); Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01469872653165858,"gpt":0.2907855304744932,"spread":0.2760868039428346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124786,0.0001098525,0.000238808,0.00001122086,0.00008874652,0.00009736362,0.0006283958,0.00004544452,0.000115417],"category_scores_gemma":[0.0005170348,0.00007216432,0.00006143476,0.00009551249,0.0001594424,0.0001488045,0.00009113082,0.0001059215,0.00001382232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006482355,"about_ca_system_score_gemma":0.0001639763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002628963,"about_ca_topic_score_gemma":3.626349e-8,"domain_scores_codex":[0.9989899,0.00005529695,0.0004245793,0.000105384,0.0002404643,0.0001843941],"domain_scores_gemma":[0.9988093,0.0003015956,0.0004147411,0.0002159508,0.0002194318,0.00003892588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001720509,0.00002923854,0.000001945006,0.00008804711,0.00000569554,1.680279e-7,0.00009785093,0.006908213,0.990534,0.001329716,0.0006505135,0.0001825394],"study_design_scores_gemma":[0.0002855746,0.00001104834,0.000003149049,0.00005504413,0.0000502804,0.000006899822,0.000007996451,0.04805437,0.8857059,0.06565676,0.00009667279,0.00006625462],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7494287,0.00001282005,0.2495173,0.0004010416,0.0002832645,0.00009853797,0.000007981523,0.00001448841,0.0002358188],"genre_scores_gemma":[0.991398,0.000003149509,0.007818461,0.000191295,0.000340533,0.000006128936,0.000002640717,0.000009533618,0.0002302566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2419692,"threshold_uncertainty_score":0.2942775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118102630","doi":"10.1016/j.cej.2021.129307","title":"Transfer learning for solvation free energies: From quantum chemistry to experiments","year":2021,"lang":"en","type":"article","venue":"Chemical Engineering Journal","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":185,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Office of Science; National Energy Research Scientific Computing Center; Defense Advanced Research Projects Agency; U.S. Department of Energy; McGill University; Belgian American Educational Foundation","keywords":"Solvation; Chemistry; Quantum chemistry; Quantum; Chemical physics; Quantum chemical; Computational chemistry; Statistical physics; Quantum mechanics; Physics; Organic chemistry; Supramolecular chemistry; Molecule","retraction":null,"screen_n_in":null,"score":{"opus":0.01100974234388593,"gpt":0.241517511667168,"spread":0.2305077693232821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003550294,0.000180845,0.000235417,0.00002938651,0.0001096654,0.0002823209,0.0004695488,0.00009849933,0.001150679],"category_scores_gemma":[0.001224477,0.0001814029,0.00008822566,0.0001285719,0.00002299134,0.0002246972,0.00008548405,0.0002792612,0.00002681398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009239736,"about_ca_system_score_gemma":0.00006931992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004384737,"about_ca_topic_score_gemma":5.2533e-8,"domain_scores_codex":[0.998545,0.00002285724,0.0003561353,0.0003438142,0.0003365808,0.0003956443],"domain_scores_gemma":[0.9992583,0.0001240702,0.00004946069,0.0002368634,0.0001333917,0.000197953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001899542,0.00001687396,0.000009017918,0.00002660492,0.000005502922,0.000008178708,0.0002774296,0.1611314,0.8380677,0.00005849866,0.0002465873,0.0001332672],"study_design_scores_gemma":[0.0004222888,0.0000176731,0.00001908245,0.0000883482,0.000009352288,0.00004013042,0.00006177695,0.04364702,0.951711,0.0001407689,0.003628842,0.0002137362],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6778107,0.00009246277,0.3211502,0.0002213833,0.0005624269,0.00003943592,0.000008247297,0.00008681936,0.00002824889],"genre_scores_gemma":[0.8319918,0.000008903491,0.1662444,0.000182188,0.00116623,0.000035257,0.0000310595,0.00005942548,0.0002807097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1549058,"threshold_uncertainty_score":0.9997624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213283694","doi":"10.1088/2516-1075/ac572f","title":"Roadmap on Machine learning in electronic structure","year":2022,"lang":"en","type":"article","venue":"Electronic Structure","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Ottawa; Queen's University","funders":"","keywords":"Field (mathematics); Computer science; Artificial intelligence; Data science; Paradigm shift; Informatics; Management science; Cognitive science; Epistemology; Engineering; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.00331492774217716,"gpt":0.2224145289110618,"spread":0.2190996011688846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001013212,0.0004654562,0.0004750867,0.0003327773,0.0008221563,0.0001593366,0.001339741,0.0001312041,0.02524898],"category_scores_gemma":[0.0002341357,0.0004311093,0.00008671797,0.000891678,0.0001055468,0.000191677,0.0004162661,0.002855864,0.00006600377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316083,"about_ca_system_score_gemma":0.000600494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000286382,"about_ca_topic_score_gemma":0.0006424855,"domain_scores_codex":[0.9945263,0.0009552873,0.0004763784,0.001076051,0.001039894,0.001926116],"domain_scores_gemma":[0.9987901,0.0001315071,0.0003112471,0.0006227527,0.00003436933,0.0001099636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001995096,0.00004115357,0.003624056,0.00002162501,0.00001030618,0.00002743007,0.0005923133,0.2386575,0.739651,0.01551504,0.0004814703,0.001178534],"study_design_scores_gemma":[0.006154085,0.00713752,0.03447597,0.00007336671,0.00008354106,0.001327608,0.0005379614,0.06208494,0.3860563,0.109051,0.3890751,0.003942621],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959946,0.0008905986,0.00007121103,0.0009792597,0.0008137705,0.0003954878,0.00009119109,0.0003052056,0.000458657],"genre_scores_gemma":[0.9973192,0.0000199852,0.0002447469,0.001081091,0.0002129397,0.00004294405,0.0001005988,0.00007362784,0.0009048293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3885936,"threshold_uncertainty_score":0.9998141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}