{"meta":{"query_hash":"e15010af2e4e","filters":{"venue":"Journal of Chemical Information and Computer Sciences"},"cohort_total":16,"direct_labels_cover":0,"predictions_cover":16,"exported":16,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e15010af2e4e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Chemical+Information+and+Computer+Sciences"},"results":[{"id":"W1971603507","doi":"10.1021/ci034270n","title":"Virtual Screening for SARS-CoV Protease Based on KZ7088 Pharmacophore Points","year":2004,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université du Québec à Montréal","funders":"","keywords":"Pharmacophore; Druggability; Computational biology; Drug discovery; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Virtual screening; Computer science; Docking (animal); Stereochemistry; Coronavirus disease 2019 (COVID-19); Chemistry; Combinatorial chemistry; Biology; Medicine; Biochemistry","score_opus":0.04136344539949326,"score_gpt":0.3359164211876713,"score_spread":0.294552975788178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971603507","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17707905,0.000009282765,0.81975883,0.0026402865,0.0002789903,0.00013469292,0.000002252743,0.000020105887,0.000076516735],"genre_scores_gemma":[0.4876938,0.0000013603744,0.50792503,0.0042603845,0.00011192764,0.000003951756,0.0000012370111,0.0000019073186,3.7977185e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852085,0.00004265618,0.0005162519,0.00013663525,0.0006012547,0.00018238042],"domain_scores_gemma":[0.9988922,0.00026812477,0.00038997774,0.000093926814,0.00024843332,0.00010731997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011183772,0.00012455715,0.0001730064,0.00027560248,0.00013230661,0.00047660532,0.0006691728,0.000038079947,0.0000011415009],"category_scores_gemma":[0.000100748126,0.00009644224,0.00010576712,0.00038636717,0.00012068478,0.0027129939,0.000114688584,0.00015009263,0.0000029591208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021640307,0.00020150958,0.000045449142,0.00005595057,0.000029282057,0.0000066974185,0.0012044861,0.39071387,0.0052507906,0.059228007,0.0018091451,0.5412384],"study_design_scores_gemma":[0.0014646718,0.00048666244,0.00013432397,0.00009324327,0.000004223219,0.000057248155,0.00001035711,0.92847747,0.063180424,0.0048995297,0.0010599562,0.00013188238],"about_ca_topic_score_codex":0.0000013200837,"about_ca_topic_score_gemma":3.8136346e-8,"teacher_disagreement_score":0.5411065,"about_ca_system_score_codex":0.000042514246,"about_ca_system_score_gemma":0.00027830008,"threshold_uncertainty_score":0.4595916},"labels":[],"label_agreement":null},{"id":"W1989259957","doi":"10.1021/ci020269x","title":"Path-Space Ratio as a Molecular Shape Descriptor of Polymer Conformation","year":2002,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Force Microscopy Techniques and Applications","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"Natural Sciences and Engineering Research Council of Canada; Uppsala Universitet","keywords":"Dimensionless quantity; Writhe; Quantum entanglement; Chain (unit); Topology (electrical circuits); Polymer; Knot (papermaking); Measure (data warehouse); Path (computing); Path length; Configuration space; Space (punctuation); Mathematics; Work (physics); Statistical physics; Computer science; Physics; Materials science; Geometry; Combinatorics; Data mining; Twist; Thermodynamics; Quantum mechanics","score_opus":0.008917623527431041,"score_gpt":0.2393814679755682,"score_spread":0.23046384444813717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989259957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77503735,0.00009940073,0.22056404,0.00059684156,0.00004520845,0.00007032829,0.0000037666994,0.000007783529,0.003575259],"genre_scores_gemma":[0.99076617,0.000009610213,0.008931501,0.0002445904,0.00003413228,0.000001642653,0.0000020410857,0.0000010616425,0.000009269106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993855,0.0000058776827,0.0003485584,0.00003320609,0.00015516137,0.00007169906],"domain_scores_gemma":[0.9994458,0.000012498746,0.0003382177,0.000043786364,0.000110367924,0.00004931229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000106092186,0.000055251432,0.000098616736,0.00006243253,0.00004561448,0.00007170049,0.00013179294,0.000019495275,0.00013359217],"category_scores_gemma":[0.0000019591105,0.00004247853,0.000048030048,0.00013114854,0.000099412886,0.0008443327,0.00002799945,0.00006366856,0.0000054047587],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020311198,0.00019154395,0.0008602782,0.00006956199,0.000058665766,4.2005752e-7,0.0047375164,0.00017043702,0.2801373,0.45776975,0.01603754,0.2399467],"study_design_scores_gemma":[0.0003315088,0.00017272675,0.00003090983,0.00005573987,0.000011001869,0.000019428198,0.00021119873,0.17150848,0.82058084,0.0013050582,0.005663536,0.00010958468],"about_ca_topic_score_codex":0.000005514137,"about_ca_topic_score_gemma":5.056692e-9,"teacher_disagreement_score":0.54044354,"about_ca_system_score_codex":0.000005277604,"about_ca_system_score_gemma":0.000020228686,"threshold_uncertainty_score":0.17322242},"labels":[],"label_agreement":null},{"id":"W1997807661","doi":"10.1021/ci000112+","title":"Metric and Multidimensional Scaling:  Efficient Tools for Clustering Molecular Conformations","year":2001,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Multidimensional scaling; Cluster analysis; Scaling; Metric (unit); Hierarchical clustering; Cluster (spacecraft); Computer science; Group (periodic table); Process (computing); Data mining; Mathematics; Artificial intelligence; Machine learning; Chemistry; Engineering; Geometry","score_opus":0.03105088405611471,"score_gpt":0.3074839465348506,"score_spread":0.2764330624787359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997807661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32711545,0.00007527364,0.67184025,0.00062698737,0.00016419802,0.000071180904,9.1806356e-7,0.00001050231,0.00009524363],"genre_scores_gemma":[0.5615683,0.000013752494,0.43771777,0.0006578072,0.00003731772,0.0000019244515,0.0000012043928,0.0000011704296,7.3971376e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987817,0.000030329496,0.00053376576,0.0000965871,0.000408739,0.00014889796],"domain_scores_gemma":[0.99860203,0.0005923536,0.00031629205,0.00006850889,0.00029882003,0.00012201701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000980302,0.00009242674,0.0001570091,0.00032228162,0.00013250244,0.00062091154,0.00031098994,0.000033988294,0.0000012176826],"category_scores_gemma":[0.00017547037,0.00007289476,0.00006125084,0.00045796885,0.0001076352,0.002807578,0.00021762255,0.00008464296,9.819181e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029172854,0.000053162643,0.00006890788,0.00004431299,0.000026768861,0.0000028605364,0.0013210359,0.3601969,0.0012676856,0.10527608,0.00016633897,0.5315468],"study_design_scores_gemma":[0.00048782217,0.000085537344,0.00052979885,0.000029251303,0.000005025683,0.00033226516,0.0000378276,0.9935136,0.0022501878,0.0010392305,0.0015932571,0.0000962113],"about_ca_topic_score_codex":7.737828e-7,"about_ca_topic_score_gemma":3.3617734e-8,"teacher_disagreement_score":0.6333167,"about_ca_system_score_codex":0.000022934779,"about_ca_system_score_gemma":0.00009405754,"threshold_uncertainty_score":0.5987464},"labels":[],"label_agreement":null},{"id":"W2006569277","doi":"10.1021/ci034125+","title":"Design of Diverse and Focused Combinatorial Libraries Using an Alternating Algorithm","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Diversity (politics); Reagent; Computer science; Computation; Chemical space; Space (punctuation); Algorithm; Combinatorial chemistry; Chemistry; Organic chemistry; Drug discovery; Sociology","score_opus":0.02312346725678098,"score_gpt":0.2447039158447606,"score_spread":0.2215804485879796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006569277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83935606,0.00008711596,0.16044621,0.0000136806,0.000054662614,0.0000149022735,6.201747e-7,9.3259246e-7,0.000025805564],"genre_scores_gemma":[0.8941407,0.000034355784,0.10569505,0.000058907648,0.00006870326,1.11225624e-7,8.0095157e-7,0.0000010007325,3.284767e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994958,0.000026193482,0.00023979541,0.00004962257,0.00012773016,0.00006087063],"domain_scores_gemma":[0.9996028,0.000021520033,0.00021516033,0.00003220792,0.00007079427,0.000057510322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027459092,0.000048772163,0.00010470025,0.00003667748,0.00004264497,0.00008057128,0.000089287554,0.00003619501,0.0000026290368],"category_scores_gemma":[0.000037766953,0.000036274516,0.000028477074,0.00006341317,0.00012953918,0.00009115269,0.000039589657,0.000033692093,4.032592e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005691179,0.00012364259,0.0015701124,0.000032463664,0.000091811235,0.0000011274738,0.00054261874,0.0013653527,0.8287991,0.0017430886,0.000119651166,0.16555409],"study_design_scores_gemma":[0.0004819938,0.0002243992,0.000029052411,0.000020217189,0.000017736656,0.00003818858,0.00009060992,0.101422034,0.8965142,0.0007311369,0.00034640124,0.00008405721],"about_ca_topic_score_codex":0.0000018593324,"about_ca_topic_score_gemma":1.41342875e-8,"teacher_disagreement_score":0.16547003,"about_ca_system_score_codex":0.0000025517447,"about_ca_system_score_gemma":0.000035393932,"threshold_uncertainty_score":0.14792319},"labels":[],"label_agreement":null},{"id":"W2016219846","doi":"10.1021/ci0001536","title":"A Linear Algorithm for the Hyper-Wiener Index of Chemical Trees","year":2001,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Wiener index; Computation; Index (typography); Algorithm; Computational complexity theory; Mathematics; Tree (set theory); Computer science; Combinatorics; Graph","score_opus":0.025968441968558558,"score_gpt":0.3009394019409087,"score_spread":0.2749709599723501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016219846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12140901,0.00010433611,0.87660205,0.0014591813,0.00025746238,0.000070250084,0.0000013969172,0.0000092832215,0.00008703869],"genre_scores_gemma":[0.41475967,0.000039479026,0.58395916,0.00095596554,0.00027498833,0.000003366744,9.099268e-7,0.0000021725496,0.0000042865454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986395,0.000030399173,0.0005788986,0.000094886964,0.000508107,0.00014818215],"domain_scores_gemma":[0.99837464,0.0006847896,0.00041660885,0.000111593494,0.000332254,0.000080121055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097334204,0.00009442441,0.0001873517,0.00014978435,0.00007081314,0.00019601367,0.0008732267,0.000043405962,0.0000032744379],"category_scores_gemma":[0.000076749915,0.000057281693,0.0001111683,0.00048777412,0.00023474444,0.0018794389,0.00020207601,0.00011812062,8.001534e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016209586,0.000044430028,0.00017103908,0.000009710222,0.000020309024,4.358388e-7,0.0005661186,0.008102009,0.0006416345,0.005949979,0.000630497,0.9838476],"study_design_scores_gemma":[0.0004073107,0.00010806314,0.0004343445,0.000022383216,0.0000061579535,0.0001836789,0.000025673804,0.98415244,0.007612877,0.002694832,0.0042743157,0.00007794339],"about_ca_topic_score_codex":0.000002531839,"about_ca_topic_score_gemma":7.8521445e-8,"teacher_disagreement_score":0.98376966,"about_ca_system_score_codex":0.000016448232,"about_ca_system_score_gemma":0.00013934278,"threshold_uncertainty_score":0.23358797},"labels":[],"label_agreement":null},{"id":"W2049151260","doi":"10.1021/ci030006i","title":"BHB:  A Simple Knowledge-Based Scoring Function to Improve the Efficiency of Database Screening","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Simple (philosophy); Function (biology); Computer science; Information retrieval; Data mining","score_opus":0.011226192337527618,"score_gpt":0.264050326589317,"score_spread":0.25282413425178935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049151260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53585017,0.00005458785,0.46349755,0.000075879805,0.00010841361,0.00004707688,0.0000012061537,0.0000019858182,0.0003631071],"genre_scores_gemma":[0.9713797,0.0000040523887,0.028036207,0.0005102811,0.00006198869,7.9880715e-7,0.0000032481128,0.0000013680119,0.0000023580858],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999299,0.000025853526,0.00035673444,0.000049035385,0.00017372007,0.00009565665],"domain_scores_gemma":[0.9993926,0.00003541625,0.000275525,0.000087361484,0.00015019302,0.000058869184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007701953,0.00006152558,0.00008502426,0.000069961425,0.00007606988,0.00006534848,0.00018834864,0.00002913734,0.0000033897318],"category_scores_gemma":[0.00017568159,0.00003890611,0.000040189963,0.00017055866,0.00009325718,0.000051329083,0.00006599829,0.00008533917,9.858334e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044971608,0.0002804775,0.009586702,0.000529272,0.00011821159,7.498942e-7,0.0032343871,0.05796894,0.5875191,0.0060199113,0.008723673,0.32556885],"study_design_scores_gemma":[0.0010907763,0.00148524,0.0006410944,0.000110871806,0.000024409002,0.000063361105,0.00028012277,0.29593584,0.6580409,0.00007204072,0.042034432,0.0002209003],"about_ca_topic_score_codex":0.0000011786609,"about_ca_topic_score_gemma":1.9491786e-7,"teacher_disagreement_score":0.4355295,"about_ca_system_score_codex":0.000004247327,"about_ca_system_score_gemma":0.00008164295,"threshold_uncertainty_score":0.15865451},"labels":[],"label_agreement":null},{"id":"W2077018271","doi":"10.1021/ci0200671","title":"Fuzzy Clustering as a Means of Selecting Representative Conformers and Molecular Alignments","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Outlier; Cluster analysis; Data mining; Fuzzy clustering; Fuzzy logic; Computer science; Entropy (arrow of time); Single-linkage clustering; Cluster (spacecraft); Mathematics; Artificial intelligence; Pattern recognition (psychology); CURE data clustering algorithm; Physics","score_opus":0.018076261927230396,"score_gpt":0.30713325410694986,"score_spread":0.2890569921797195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077018271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43334696,0.00004613698,0.56438994,0.00017002107,0.00010345319,0.00004007186,2.5055476e-7,0.0000050045232,0.0018981793],"genre_scores_gemma":[0.7699076,0.000012633819,0.2296965,0.00037113586,0.00000961085,4.5965513e-7,1.6054737e-7,9.660392e-7,9.683205e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987942,0.000077025165,0.00048591985,0.00009196951,0.0004316466,0.00011923113],"domain_scores_gemma":[0.99900526,0.00021656872,0.00044695052,0.000060773895,0.00018009797,0.00009036487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094152417,0.00007954906,0.00015934736,0.00016186705,0.00006054978,0.00021293614,0.00027131883,0.000025223835,0.0000015033108],"category_scores_gemma":[0.00013223673,0.00006482104,0.000041041498,0.0003306151,0.00014213566,0.002228637,0.00014009711,0.00008825118,5.0060635e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008196891,0.00014928794,0.0022906489,0.00024555964,0.00024660034,0.000020664289,0.03267871,0.12489874,0.025608446,0.51085174,0.0005570752,0.30237052],"study_design_scores_gemma":[0.0010640742,0.00042790847,0.00052634574,0.00013337971,0.000013880173,0.00092743675,0.0007109023,0.826113,0.1378973,0.031437885,0.00050558336,0.00024233198],"about_ca_topic_score_codex":0.000004097623,"about_ca_topic_score_gemma":6.6602524e-8,"teacher_disagreement_score":0.70121425,"about_ca_system_score_codex":0.00001790005,"about_ca_system_score_gemma":0.000118683776,"threshold_uncertainty_score":0.26433253},"labels":[],"label_agreement":null},{"id":"W2077046074","doi":"10.1021/ci034147w","title":"Inductive Electronegativity Scale. Iterative Calculation of Inductive Partial Charges","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Electronegativity; Inductive effect; Scale (ratio); Computer science; Statistical physics; Physics; Chemistry; Quantum mechanics; Organic chemistry","score_opus":0.011942963552214034,"score_gpt":0.2607042645147699,"score_spread":0.2487613009625559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077046074","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95062345,0.000016850645,0.04847806,0.00016308407,0.0003517694,0.0000659417,0.0000018110893,0.000007983146,0.00029104637],"genre_scores_gemma":[0.96299917,0.000003999728,0.036811624,0.000104983636,0.00007516524,0.0000012699021,4.6383565e-7,0.0000014583433,0.0000018938948],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984829,0.00017155687,0.0005763423,0.000110520974,0.00048940646,0.0001692736],"domain_scores_gemma":[0.9986098,0.00010686774,0.00082389696,0.0000634557,0.00031682118,0.00007916749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014825086,0.00010160302,0.00023567278,0.00013557801,0.00010787629,0.00018642657,0.00022665744,0.0000518458,0.000056022403],"category_scores_gemma":[0.00020163458,0.00007243373,0.000040750627,0.00028512537,0.0004932497,0.0025759812,0.00005104385,0.00014012364,0.000004898905],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053362048,0.000066911176,0.0036659709,0.000031268428,0.000008909187,5.406582e-7,0.0065688444,0.0016651162,0.972326,0.0103563145,0.00012686854,0.0051298896],"study_design_scores_gemma":[0.00029534198,0.00030588414,0.0023943933,0.000041628573,0.0000071619106,0.00005454328,0.00011869248,0.015415837,0.9795657,0.0013966563,0.00028987217,0.00011432323],"about_ca_topic_score_codex":0.000008198781,"about_ca_topic_score_gemma":2.493624e-7,"teacher_disagreement_score":0.013750722,"about_ca_system_score_codex":0.00002950083,"about_ca_system_score_gemma":0.00012700917,"threshold_uncertainty_score":0.29537618},"labels":[],"label_agreement":null},{"id":"W2086798344","doi":"10.1021/ci0000474","title":"Benchmarking of Model Core Potentials:  Application to the Halogen Complexes of Group 4 Metals","year":2000,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Advanced Chemical Physics Studies","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudopotential; Halogen; Valence electron; Electronegativity; Bond length; Core electron; Chemistry; Atom (system on chip); Metal; Computational chemistry; Crystallography; Materials science; Electron; Atomic physics; Physics; Quantum mechanics; Alkyl; Organic chemistry","score_opus":0.01992898776159973,"score_gpt":0.2690186908565783,"score_spread":0.24908970309497858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086798344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59465164,0.000029842126,0.40427527,0.0001497227,0.000019368335,0.000056258916,0.000006491076,0.0000017868691,0.0008096286],"genre_scores_gemma":[0.9804588,0.0000055432392,0.01934063,0.00010323926,0.000085172884,0.0000015581231,0.0000026935795,9.725939e-7,0.0000013842637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992479,0.0000058233377,0.0004139378,0.000045703884,0.00021235298,0.00007426763],"domain_scores_gemma":[0.999405,0.000050058257,0.0003361544,0.000056137265,0.000117018186,0.00003562622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016963141,0.000058537167,0.0001662849,0.00003127973,0.000053841428,0.00002248056,0.0002160203,0.000010686263,0.000010861273],"category_scores_gemma":[0.000002253511,0.000036576697,0.000060199858,0.00014719009,0.00015042587,0.00041968244,0.000057119767,0.00005549107,8.139623e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053477925,0.00013635543,0.00078412035,0.000050852326,0.00012357453,4.1420297e-8,0.0028607624,0.2255133,0.11220829,0.043162152,0.0012648632,0.6138422],"study_design_scores_gemma":[0.00056489656,0.0002014601,0.0005454372,0.00010238085,0.00005839126,0.0000053286494,0.00032506307,0.69784176,0.19295195,0.105447255,0.0017410481,0.00021505146],"about_ca_topic_score_codex":0.0000049239998,"about_ca_topic_score_gemma":6.087206e-8,"teacher_disagreement_score":0.61362714,"about_ca_system_score_codex":0.000004510193,"about_ca_system_score_gemma":0.000013365202,"threshold_uncertainty_score":0.14915545},"labels":[],"label_agreement":null},{"id":"W2089365195","doi":"10.1021/ci000055k","title":"Applying the Concept of Partially Ordered Sets on the Ranking of Near-Shore Sediments by a Battery of Tests","year":2001,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"History and advancements in chemistry","field":"Chemistry","cited_by":173,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ranking (information retrieval); Data mining; Sorting; Computer science; sort; Representation (politics); Enumeration; Comparability; Pairwise comparison; Visualization; Mathematics; Information retrieval; Algorithm; Artificial intelligence; Discrete mathematics; Combinatorics","score_opus":0.019079145671169934,"score_gpt":0.2616621171374997,"score_spread":0.24258297146632976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089365195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970107,0.00008288374,0.001241315,0.0003719833,0.00006429747,0.000044518056,0.0000052838923,0.000002499621,0.0011765118],"genre_scores_gemma":[0.9987916,0.000015219091,0.00070648256,0.00044370198,0.00003181482,0.000002407346,0.0000016937192,0.0000012111628,0.00000592168],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998938,0.000010660304,0.00052926346,0.000045693545,0.0003915829,0.00008479286],"domain_scores_gemma":[0.9988999,0.00017711679,0.00070236844,0.00008435787,0.00010513648,0.000031165022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003040367,0.00006790441,0.00014620583,0.000015885982,0.00007477542,0.000029749759,0.00032274637,0.000034135046,0.000065058375],"category_scores_gemma":[0.00004091789,0.000037855843,0.000048162612,0.00011062984,0.00043297542,0.00030431137,0.000048507238,0.00012704355,2.4464202e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030028156,0.0003736972,0.0057879025,0.00042201445,0.00018343257,0.0000027393153,0.010546511,0.0061458508,0.7943751,0.00038806893,0.01118107,0.1702933],"study_design_scores_gemma":[0.0005793555,0.00006960236,0.000034765977,0.00030659995,0.000014156854,0.000033606477,0.00039571337,0.009971152,0.9740958,0.00010922435,0.014313452,0.000076537515],"about_ca_topic_score_codex":7.2596384e-7,"about_ca_topic_score_gemma":3.679289e-8,"teacher_disagreement_score":0.1797207,"about_ca_system_score_codex":0.000011853426,"about_ca_system_score_gemma":0.00005075042,"threshold_uncertainty_score":0.1595316},"labels":[],"label_agreement":null},{"id":"W2107015503","doi":"10.1021/ci025526c","title":"A Survey and New Results on Computer Enumeration of Polyhex and Fusene Hydrocarbons","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Enumeration; Adjacency list; Constructive; Boundary (topology); Computer science; Enantiomer; Graph; Combinatorics; Code (set theory); Source code; Orientation (vector space); Algorithm; Mathematics; Process (computing); Theoretical computer science; Chemistry; Stereochemistry; Geometry","score_opus":0.03795253731339658,"score_gpt":0.29302839116795626,"score_spread":0.25507585385455966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107015503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4869952,0.000098032935,0.51183724,0.00060545903,0.00019735523,0.00004539173,0.0000015987749,0.0000072488774,0.0002124874],"genre_scores_gemma":[0.84174156,0.000033891214,0.15764013,0.00052761176,0.000051752668,2.1763648e-7,0.0000011969826,0.0000013010806,0.0000023596601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998617,0.00014364901,0.00059056404,0.00013200744,0.00040106638,0.00011572664],"domain_scores_gemma":[0.9986339,0.00058222795,0.00043071507,0.00009034516,0.00011339078,0.00014941161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014908733,0.00010373193,0.00019943602,0.00021619255,0.00006681689,0.00031882126,0.00023780766,0.000041419364,6.017835e-7],"category_scores_gemma":[0.00014014046,0.0000807778,0.000030815292,0.0003382461,0.00014362247,0.0016187191,0.00010804478,0.000112258895,5.044661e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019974426,0.00018615779,0.0033642016,0.00007030558,0.000083066334,0.0000048889,0.008027397,0.015247898,0.0015298057,0.14100675,0.0037688892,0.8265109],"study_design_scores_gemma":[0.0015611231,0.00076743844,0.029098826,0.0000910183,0.0000066972925,0.00026729383,0.00002206065,0.9519647,0.007776366,0.007231199,0.0009920757,0.000221255],"about_ca_topic_score_codex":0.000011791187,"about_ca_topic_score_gemma":7.842769e-7,"teacher_disagreement_score":0.93671674,"about_ca_system_score_codex":0.000012201086,"about_ca_system_score_gemma":0.00016169748,"threshold_uncertainty_score":0.3294023},"labels":[],"label_agreement":null},{"id":"W2126662293","doi":"10.1021/ci0200467","title":"Property Distributions:  Differences between Drugs, Natural Products, and Molecules from Combinatorial Chemistry","year":2002,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":921,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Molecule; Heteroatom; Combinatorial chemistry; Chemical space; Combinatorial synthesis; Chemistry; Ring (chemistry); Drug discovery; Organic chemistry","score_opus":0.019150483928312312,"score_gpt":0.2456147566528213,"score_spread":0.22646427272450897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126662293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8451368,0.00061888515,0.14969897,0.0036847687,0.00054870854,0.00007872152,0.000008263727,0.000030434654,0.00019443808],"genre_scores_gemma":[0.9344443,0.00005000381,0.06508324,0.00014287388,0.00026881238,0.0000011797647,0.0000044763847,0.0000012898797,0.0000038419375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998623,0.00006105763,0.0004915631,0.0001605928,0.00051318656,0.0001506104],"domain_scores_gemma":[0.99895823,0.00026450295,0.00034059165,0.00010093736,0.0002283064,0.000107433436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042088953,0.00012578488,0.00021669672,0.00006687135,0.00013450686,0.00068217394,0.0006047681,0.00004611415,0.0000041484927],"category_scores_gemma":[0.000121260215,0.00007887363,0.00004116449,0.00032660904,0.000273034,0.0028782554,0.00029057957,0.00020258866,0.0000018759283],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032811495,0.00023095404,0.0050437916,0.00016148142,0.00014277226,0.0000070884366,0.0058086542,0.0002427456,0.0034450204,0.02964548,0.0055743284,0.9496649],"study_design_scores_gemma":[0.0013120115,0.00019617024,0.012822028,0.00016156543,0.000027089236,0.00014180085,0.000082750936,0.93060106,0.025094338,0.025633905,0.003449244,0.00047803624],"about_ca_topic_score_codex":0.00000506055,"about_ca_topic_score_gemma":1.9384084e-8,"teacher_disagreement_score":0.94918686,"about_ca_system_score_codex":0.000025068575,"about_ca_system_score_gemma":0.00006223924,"threshold_uncertainty_score":0.6578219},"labels":[],"label_agreement":null},{"id":"W2129893339","doi":"10.1021/ci034143r","title":"Spline-Fitting with a Genetic Algorithm:  A Method for Developing Classification Structure−Activity Relationships","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Dalhousie University","funders":"","keywords":"Artificial intelligence; Test set; Categorical variable; Stability (learning theory); Mathematics; Molecular descriptor; Set (abstract data type); Training set; Pattern recognition (psychology); Quantitative structure–activity relationship; Computer science; Machine learning","score_opus":0.05268222656046128,"score_gpt":0.3256682158601837,"score_spread":0.2729859892997224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129893339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08301152,0.00003025527,0.91595757,0.0006624757,0.00015818236,0.000109194676,0.000001214908,0.0000149531625,0.000054617612],"genre_scores_gemma":[0.20006686,0.0000027106996,0.7996711,0.00020741795,0.000046455814,0.0000024312903,6.356996e-7,0.0000017337625,6.093224e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869746,0.00015394813,0.00046687177,0.00014035238,0.00039097713,0.0001504093],"domain_scores_gemma":[0.9981473,0.00072372507,0.0005758003,0.00009141455,0.0003840852,0.00007767992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014926076,0.00010754057,0.00016751088,0.00020806304,0.00020059833,0.00042471173,0.0003524056,0.000046588153,6.70042e-7],"category_scores_gemma":[0.00018421034,0.00007926162,0.000045260796,0.0005319672,0.00007292885,0.002453055,0.000053543376,0.00016577094,3.970589e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017544808,0.000025925165,0.00034071898,0.00004506734,0.000034295168,0.0000010526053,0.0011584125,0.02533227,0.0008641912,0.1447858,0.00008604466,0.82730865],"study_design_scores_gemma":[0.0003832958,0.00010278942,0.0034934662,0.000035587316,0.000008909983,0.00035802016,0.00003786145,0.9717554,0.005934133,0.017120974,0.0006435886,0.00012597757],"about_ca_topic_score_codex":9.584103e-7,"about_ca_topic_score_gemma":2.1589878e-7,"teacher_disagreement_score":0.9464231,"about_ca_system_score_codex":0.000045468387,"about_ca_system_score_gemma":0.00036414675,"threshold_uncertainty_score":0.40955052},"labels":[],"label_agreement":null},{"id":"W2204875011","doi":"10.1021/ci034157x","title":"Use of Electron Density Critical Points as Chemical Function-Based Reduced Representations of Pharmacological Ligands","year":2004,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Fonds De La Recherche Scientifique - FNRS","keywords":"Pharmacophore; Representation (politics); Similarity (geometry); Resolution (logic); Molecule; Set (abstract data type); Function (biology); Electron density; Critical point (mathematics); Topology (electrical circuits); Order (exchange); Computer science; Electron; Computational chemistry; Biological system; Mathematics; Chemical physics; Chemistry; Physics; Artificial intelligence; Image (mathematics); Combinatorics; Stereochemistry; Quantum mechanics; Biology; Geometry; Organic chemistry","score_opus":0.03739974045223304,"score_gpt":0.3456817049560347,"score_spread":0.30828196450380163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204875011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6069574,0.000013684057,0.3913494,0.0014336237,0.00015656013,0.000040964216,9.2732546e-7,0.000009859781,0.00003763995],"genre_scores_gemma":[0.84048325,0.0000051800776,0.15879974,0.0006603644,0.000047493937,9.44522e-7,0.0000013519067,0.0000012708111,4.1506715e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998164,0.000059929273,0.00080347864,0.00013949274,0.0006704564,0.00016264692],"domain_scores_gemma":[0.9978792,0.00078984495,0.00047193293,0.00010709979,0.00060805713,0.00014386851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006783559,0.00010742363,0.00025408613,0.00022886714,0.000064374406,0.00016326342,0.00045823722,0.00006326795,0.0000064538904],"category_scores_gemma":[0.0004639109,0.000085848405,0.0001213165,0.00058159075,0.000406109,0.002484045,0.00015173432,0.00019060624,0.0000020769385],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006341658,0.0011344114,0.0007885011,0.00014607044,0.00018215454,0.00001417184,0.0019517,0.1886178,0.4830669,0.28871667,0.0012431913,0.033504285],"study_design_scores_gemma":[0.0006448725,0.00042598665,0.0014007495,0.00005476999,0.000026505519,0.00012425467,0.000011747533,0.19167747,0.79012066,0.015361889,0.000042889424,0.00010819717],"about_ca_topic_score_codex":0.0000056115296,"about_ca_topic_score_gemma":4.478824e-8,"teacher_disagreement_score":0.30705377,"about_ca_system_score_codex":0.000042553074,"about_ca_system_score_gemma":0.00044209763,"threshold_uncertainty_score":0.35007963},"labels":[],"label_agreement":null},{"id":"W2217493032","doi":"10.1021/ci034177z","title":"Statistically Based Reduced Representation of Amino Acid Side Chains","year":2004,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Government of Ontario","keywords":"Side chain; Conformational isomerism; Dihedral angle; Atom (system on chip); Chemistry; Crystallography; Protein structure; Mathematics; Computer science; Molecule; Hydrogen bond","score_opus":0.009061677483396523,"score_gpt":0.2604846135330205,"score_spread":0.25142293604962396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2217493032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6634623,0.000027043807,0.3360812,0.00021238656,0.00005260067,0.000025852798,0.0000023871467,0.0000012644279,0.0001349743],"genre_scores_gemma":[0.93156433,0.000012934201,0.06798474,0.0003729604,0.000055380347,3.5622165e-7,0.000007642544,8.2019267e-7,8.540609e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994348,0.000009165527,0.0002870144,0.00004664806,0.00016040844,0.000061924206],"domain_scores_gemma":[0.9995303,0.000009221799,0.00023262756,0.000048472462,0.0001326326,0.000046718673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012806532,0.000045352695,0.00008415538,0.000046170535,0.000023754517,0.00003204921,0.000110585876,0.000039472394,0.0000012552807],"category_scores_gemma":[0.000055059954,0.000034207656,0.000033366927,0.000083492705,0.00013109902,0.000037010177,0.000029527117,0.0000425257,2.0661584e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008983349,0.000028760616,0.00022340735,0.000030892003,0.000017523009,0.0000010876689,0.00020322471,0.003704968,0.9468664,0.0039726994,0.0001509849,0.044710252],"study_design_scores_gemma":[0.0006070588,0.0003712607,0.0011303694,0.000023408551,0.0000060607663,0.000051601797,0.00002599761,0.010227268,0.98609495,0.0012305379,0.00016830782,0.000063198306],"about_ca_topic_score_codex":0.0000017645731,"about_ca_topic_score_gemma":2.306536e-7,"teacher_disagreement_score":0.26810202,"about_ca_system_score_codex":0.0000056788817,"about_ca_system_score_gemma":0.00010301996,"threshold_uncertainty_score":0.13949476},"labels":[],"label_agreement":null},{"id":"W2217739880","doi":"10.1021/ci025639w","title":"Development of Quantitative Structure−Activity Relationships and Classification Models for Anticonvulsant Activity of Hydantoin Analogues","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Dalhousie University","funders":"","keywords":"Quantitative structure–activity relationship; Hydantoin; Molecular descriptor; Test set; Principal component analysis; Mathematics; Artificial intelligence; Representation (politics); Metric (unit); Similarity (geometry); Pattern recognition (psychology); Biological system; Machine learning; Computer science; Chemistry; Biology","score_opus":0.1143413405236026,"score_gpt":0.33801232913562096,"score_spread":0.22367098861201834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2217739880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49193367,0.000023892193,0.50784826,0.00006433012,0.000048408285,0.000048993432,0.0000018349016,0.0000023484622,0.000028228256],"genre_scores_gemma":[0.57981646,0.0000052538944,0.42016065,0.000011846432,0.000003945439,5.8328044e-7,4.7686007e-7,6.423301e-7,1.476732e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988199,0.000115004514,0.00053786114,0.0001010332,0.00033496274,0.000091276605],"domain_scores_gemma":[0.9980616,0.00062462775,0.0008319002,0.00007241467,0.00035073495,0.000058744787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013855518,0.00008376913,0.00021967228,0.00021678318,0.000099332916,0.000090551795,0.0002243039,0.000039970964,3.8958885e-7],"category_scores_gemma":[0.00016609076,0.00006614175,0.000041046147,0.0003065217,0.0001846166,0.0029037027,0.000060782055,0.00009975746,6.8834744e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086382875,0.00014460558,0.00079563016,0.000206749,0.000066896784,1.9889949e-7,0.009046736,0.0229992,0.055407126,0.73349327,0.000034167075,0.17771907],"study_design_scores_gemma":[0.00030195637,0.000108965636,0.010429793,0.000041430136,0.0000063146877,0.00002163875,0.0000843474,0.8760577,0.087378174,0.025444541,0.00004293017,0.00008224916],"about_ca_topic_score_codex":9.596356e-7,"about_ca_topic_score_gemma":6.040952e-7,"teacher_disagreement_score":0.85305846,"about_ca_system_score_codex":0.00002200403,"about_ca_system_score_gemma":0.00026569568,"threshold_uncertainty_score":0.26971823},"labels":[],"label_agreement":null}]}