{"meta":{"query_hash":"b9f047f5d007","filters":{"venue":"Proceedings of the Python in Science Conferences"},"cohort_total":13,"direct_labels_cover":0,"predictions_cover":13,"exported":13,"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/b9f047f5d007","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+Python+in+Science+Conferences"},"results":[{"id":"W2112364454","doi":"10.25080/majora-14bd3278-006","title":"Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn","year":2014,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":298,"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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Preprocessor; Machine learning; Benchmarking; Classifier (UML); Support vector machine; Pattern recognition (psychology); Data mining; Deep learning","score_opus":0.024583413551202186,"score_gpt":0.27673620596396115,"score_spread":0.25215279241275895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112364454","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005988665,0.00062455743,0.30399084,0.00027161883,0.00034520245,0.00042927457,0.004883424,0.6777152,0.005751205],"genre_scores_gemma":[0.09153431,0.00071198127,0.64146864,0.0016017929,0.00026677002,0.005479333,0.030791694,0.21639295,0.011752515],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963265,0.0011039624,0.0004969759,0.0008148384,0.00095207803,0.0003056406],"domain_scores_gemma":[0.9911089,0.004711919,0.00042154107,0.0021610686,0.0011922774,0.00040427304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056645344,0.005132728,0.0024872606,0.003883565,0.0010804079,0.0038494328,0.007976645,0.0043113725,0.05109996],"category_scores_gemma":[0.031290114,0.0028470166,0.0032138175,0.0027719433,0.0011287669,0.005325556,0.005578367,0.007904643,0.058811054],"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":[0.0012039911,0.00080009626,0.006309112,0.0022552435,0.00078737916,0.00044217275,0.0005048895,0.038826197,0.0071142325,0.009392462,0.4976523,0.43471196],"study_design_scores_gemma":[0.0012996986,0.00028354867,0.0030890089,0.0005765711,0.00021600045,0.00044930543,0.00022387144,0.7489264,0.0359644,0.07540168,0.13318026,0.00038921295],"about_ca_topic_score_codex":0.0025405383,"about_ca_topic_score_gemma":0.0055108448,"teacher_disagreement_score":0.05109996,"about_ca_system_score_codex":0.0017202434,"about_ca_system_score_gemma":0.002878956,"threshold_uncertainty_score":0.17094636},"labels":[],"label_agreement":null},{"id":"W2475602767","doi":"10.25080/majora-8b375195-004","title":"SkData: Data Sets and Algorithm Evaluation Protocols in Python","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"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":"Rowland Institute at Harvard; National Science Foundation","keywords":"Python (programming language); Computer science; Upload; Parsing; Benchmark (surveying); Scripting language; Algorithm; Set (abstract data type); Data mining; Data set; Programming language; Theoretical computer science; Information retrieval; Artificial intelligence; World Wide Web","score_opus":0.08828722234852654,"score_gpt":0.36836448869067395,"score_spread":0.2800772663421474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475602767","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003690532,0.0001359772,0.2932478,0.00078142306,0.0002013315,0.0011146573,0.054793067,0.63740724,0.008627973],"genre_scores_gemma":[0.08195586,0.00044820926,0.40539944,0.002436567,0.00017315269,0.013612778,0.21682714,0.26558045,0.013566364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867578,0.002868147,0.0026386373,0.0018022709,0.005111709,0.0008212921],"domain_scores_gemma":[0.97536904,0.008780937,0.0012487698,0.009666024,0.004108401,0.0008268447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012043165,0.0028030016,0.0018367996,0.0033722026,0.0017983958,0.0057011666,0.0073866127,0.0015497959,0.039321225],"category_scores_gemma":[0.045066953,0.0031384695,0.0023949326,0.0036965706,0.0027014345,0.011069059,0.009613873,0.006929241,0.03459992],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017878136,0.0006505305,0.00485898,0.001852832,0.00028533785,0.0003061882,0.0010631292,0.01586829,0.005545378,0.03811789,0.7944457,0.13521785],"study_design_scores_gemma":[0.0009805107,0.0002506562,0.005718524,0.0005899467,0.00012150206,0.00050590286,0.00043404574,0.16757675,0.06547202,0.18152478,0.57625955,0.0005658076],"about_ca_topic_score_codex":0.00541607,"about_ca_topic_score_gemma":0.0047393753,"teacher_disagreement_score":0.039321225,"about_ca_system_score_codex":0.0030862277,"about_ca_system_score_gemma":0.006665038,"threshold_uncertainty_score":0.13154256},"labels":[],"label_agreement":null},{"id":"W2510475640","doi":"10.25080/majora-629e541a-00e","title":"MDAnalysis: A Python Package for the Rapid Analysis of Molecular Dynamics Simulations","year":2016,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2121,"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":"Biotechnology and Biological Sciences Research Council; Max-Planck-Gesellschaft; Arizona State University; Partnership for Advanced Computing in Europe AISBL; Canadian Institutes of Health Research; Leverhulme Trust; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust","keywords":"Python (programming language); Computer science; Modular design; Interoperability; Scripting language; Visualization; User interface; USable; Graphical user interface; Software; Programming language; Software engineering; Computational science; World Wide Web; Data mining","score_opus":0.01098305574029947,"score_gpt":0.2701563874052264,"score_spread":0.25917333166492695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510475640","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005726458,0.0010249491,0.5340997,0.0008625728,0.0006913552,0.0005888286,0.05639677,0.3870653,0.013544126],"genre_scores_gemma":[0.04901943,0.0024150878,0.6542134,0.0015235937,0.00035922005,0.0041643046,0.09142412,0.18141165,0.015469103],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985079,0.00029894945,0.00015342087,0.00025372865,0.0005986729,0.00018716701],"domain_scores_gemma":[0.9982211,0.0005796285,0.00016509111,0.00031374805,0.0004965249,0.00022394459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024130314,0.0017770334,0.0023948767,0.0014756634,0.0012932357,0.0025596446,0.005070834,0.0011065375,0.055872146],"category_scores_gemma":[0.0062467977,0.0014644406,0.0023450092,0.0014498271,0.0007599769,0.002870951,0.0040702014,0.0057637347,0.028145578],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071501936,0.00024602268,0.0025846902,0.0032511423,0.0007789109,0.0005189363,0.0006078172,0.034583468,0.02051612,0.042247042,0.776143,0.11780779],"study_design_scores_gemma":[0.0004285157,0.00013004855,0.002752297,0.00037710767,0.00016418885,0.0003421996,0.00008383683,0.27891365,0.021199603,0.048200596,0.6470506,0.00035731768],"about_ca_topic_score_codex":0.0038805963,"about_ca_topic_score_gemma":0.0036532434,"teacher_disagreement_score":0.055872146,"about_ca_system_score_codex":0.00089482573,"about_ca_system_score_gemma":0.0035314234,"threshold_uncertainty_score":0.18691093},"labels":[],"label_agreement":null},{"id":"W2885899215","doi":"10.25080/majora-4af1f417-002","title":"Equity, Scalability, and Sustainability of Data Science Infrastructure","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Liberal arts education; Equity (law); Higher education; Big data; Business; Public relations; Scalability; Knowledge management; Public administration; Political science; Computer science; Economic growth; Economics","score_opus":0.15186823782974673,"score_gpt":0.4464732322396021,"score_spread":0.2946049944098554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885899215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8102276,0.0028658893,0.016600363,0.042144228,0.0001352145,0.00017539576,0.0018984763,0.00027467628,0.12567818],"genre_scores_gemma":[0.9974668,0.00024295891,0.00084747636,0.0003630913,0.000031438354,0.000018631352,0.00020371734,0.000016476675,0.0008095013],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98595715,0.0021890823,0.0005489022,0.0012783132,0.005924948,0.0041016378],"domain_scores_gemma":[0.943513,0.013589604,0.00954784,0.004428182,0.019928468,0.008992817],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.014175757,0.00021747682,0.0003409258,0.0046192175,0.0029944086,0.0076064887,0.001661579,0.0007458626,0.003934467],"category_scores_gemma":[0.056823526,0.00025954845,0.00035217058,0.00616443,0.0065042265,0.008064856,0.0070479903,0.0017747789,0.00023084016],"study_design_candidate":"theoretical_or_conceptual","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":[0.000109890985,0.00011537078,0.6731599,0.00015190968,0.00012242974,0.00021048493,0.003680998,0.0077918065,0.00092790194,0.1884161,0.008212108,0.11710098],"study_design_scores_gemma":[0.00004904843,0.00018130147,0.74104667,0.0005840311,0.00009924397,0.00034589766,0.015821569,0.013998033,0.002355599,0.14471728,0.08069053,0.000110867746],"about_ca_topic_score_codex":0.26117063,"about_ca_topic_score_gemma":0.29012355,"teacher_disagreement_score":0.9983384,"about_ca_system_score_codex":0.022383802,"about_ca_system_score_gemma":0.03200109,"threshold_uncertainty_score":0.5193009},"labels":[],"label_agreement":null},{"id":"W4289139873","doi":"10.25080/majora-212e5952-018","title":"Phylogeography: Analysis of genetic and climatic data of SARS-CoV-2","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Python (programming language); Computer science; Phylogeography; Coronavirus disease 2019 (COVID-19); Programming language; Biology; Phylogenetic tree; Genetics","score_opus":0.053555973776493446,"score_gpt":0.30708019623717614,"score_spread":0.2535242224606827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289139873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85678095,0.0005160659,0.0989813,0.0010555225,0.000055164986,0.0000678548,0.029642733,0.006017006,0.0068833246],"genre_scores_gemma":[0.8996293,0.00029786752,0.06797222,0.00014700805,0.000029699062,0.000089616966,0.029426564,0.0012263441,0.0011812445],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952555,0.00014657853,0.000029665542,0.0001425862,0.00008295116,0.000072651164],"domain_scores_gemma":[0.999201,0.00037889523,0.00016528313,0.00009230263,0.00008355525,0.00007898677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013885531,0.00029010663,0.00043984648,0.0023636355,0.0007039674,0.00082810083,0.0004266536,0.00031014267,0.0042644725],"category_scores_gemma":[0.0032173756,0.0002827928,0.0009020207,0.0031620283,0.0003374786,0.00079486595,0.0010757687,0.0006704822,0.000855813],"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":[0.0009213019,0.00023245515,0.7502876,0.0005720275,0.0008851936,0.0012507612,0.0025576446,0.049486104,0.03443455,0.006623322,0.020651387,0.13209768],"study_design_scores_gemma":[0.000072138595,0.000096161624,0.7525906,0.00009997225,0.00018953152,0.0012383241,0.0010610768,0.19387957,0.007343355,0.008667221,0.034641553,0.00012053689],"about_ca_topic_score_codex":0.0053007407,"about_ca_topic_score_gemma":0.0046590245,"teacher_disagreement_score":0.0053007407,"about_ca_system_score_codex":0.0003376258,"about_ca_system_score_gemma":0.0007106568,"threshold_uncertainty_score":0.014266074},"labels":[],"label_agreement":null},{"id":"W4300096145","doi":"10.25080/majora-14bd3278-011","title":"Proceedings of the 13th Python in Science Conference","year":2014,"lang":"en","type":"paratext","venue":"Proceedings of the Python in Science Conferences","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":58,"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":"Pennsylvania State University; University of Edinburgh; University of Pennsylvania","keywords":"Python (programming language); Computer science; Programming language","score_opus":0.02687334716002674,"score_gpt":0.2880246484455867,"score_spread":0.2611513012855599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300096145","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036436613,0.0038154267,0.53184056,0.03039921,0.034581926,0.0011853233,0.015446128,0.06808076,0.31100702],"genre_scores_gemma":[0.03228936,0.0065148063,0.22538303,0.007986867,0.0091059655,0.0023378874,0.062228587,0.0585264,0.5956271],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99441695,0.0016002672,0.00040603962,0.00064731174,0.0024904804,0.00043898658],"domain_scores_gemma":[0.9931206,0.0014400225,0.00013996816,0.0015088312,0.0019402816,0.0018502751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010053882,0.0017036663,0.0013449768,0.0012628608,0.0017612728,0.0074128625,0.0040464224,0.0016178748,0.23706193],"category_scores_gemma":[0.014210504,0.000990273,0.0015715873,0.0012046725,0.0015427954,0.007932694,0.0065417066,0.0068767886,0.13713342],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006925989,0.00007835923,0.00013163626,0.00014943992,0.000019063042,0.00004171199,0.000078290504,0.0006976081,0.0006091456,0.022088341,0.91054314,0.06549402],"study_design_scores_gemma":[0.000023786468,0.000017627379,0.00028660113,0.00008907842,0.0000071621826,0.00006753393,0.000024190145,0.003985287,0.0010190865,0.01868949,0.9757691,0.000021011232],"about_ca_topic_score_codex":0.0021886535,"about_ca_topic_score_gemma":0.0027743343,"teacher_disagreement_score":0.23706193,"about_ca_system_score_codex":0.0019654676,"about_ca_system_score_gemma":0.005750525,"threshold_uncertainty_score":0.7930512},"labels":[],"label_agreement":null},{"id":"W4300922358","doi":"10.25080/majora-8b375195-011","title":"Proceedings of the 12th Python in Science Conference","year":2013,"lang":"en","type":"paratext","venue":"Proceedings of the Python in Science Conferences","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"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":"National Science Foundation","keywords":"Python (programming language); Computer science; Programming language","score_opus":0.02890822528707918,"score_gpt":0.2860082458534352,"score_spread":0.257100020566356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300922358","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004414637,0.0049229823,0.43244192,0.022361523,0.036326867,0.0008104787,0.017014887,0.13928996,0.34241673],"genre_scores_gemma":[0.029624725,0.0069387383,0.15643783,0.004787432,0.006746039,0.0013470401,0.0570617,0.06702666,0.6700299],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967668,0.00075472554,0.0002337119,0.0004793573,0.0014107904,0.0003546072],"domain_scores_gemma":[0.995774,0.0005738685,0.000095681564,0.0011329702,0.001225238,0.0011981889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059422995,0.0014412015,0.0012450923,0.001262615,0.0015912047,0.0058602607,0.0031400002,0.0012187173,0.24573493],"category_scores_gemma":[0.008357438,0.00076301594,0.0015817959,0.0013162538,0.0015583022,0.0066470928,0.006197179,0.0049132463,0.1443602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010237925,0.000058658614,0.00019245566,0.00023177752,0.000025169782,0.00008020122,0.00011073954,0.00067693955,0.0013919516,0.029235562,0.88414323,0.08375084],"study_design_scores_gemma":[0.00001603021,0.000013017103,0.0002318091,0.000046151,0.0000063750026,0.000068201356,0.000018564007,0.0021040027,0.0010511194,0.008239185,0.9881887,0.0000168557],"about_ca_topic_score_codex":0.003293618,"about_ca_topic_score_gemma":0.003959719,"teacher_disagreement_score":0.24573493,"about_ca_system_score_codex":0.002093969,"about_ca_system_score_gemma":0.005059319,"threshold_uncertainty_score":0.82206523},"labels":[],"label_agreement":null},{"id":"W4385894309","doi":"10.25080/gerudo-f2bc6f59-00f","title":"aPhyloGeo-Covid: A Web Interface for Reproducible Phylogeographic Analysis of SARS-CoV-2 Variation using Neo4j and Snakemake","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Computer science; Phylogeography; Data science; Coronavirus disease 2019 (COVID-19); Context (archaeology); Workflow; Phylogenetic tree; Database; Geography; Biology; Infectious disease (medical specialty)","score_opus":0.05797028395049003,"score_gpt":0.3319342107216462,"score_spread":0.27396392677115616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385894309","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015606755,0.00040809263,0.16230296,0.00047266943,0.00043392478,0.0005253841,0.12756802,0.683959,0.008723203],"genre_scores_gemma":[0.09850132,0.00081204646,0.3834136,0.0017883552,0.00021105006,0.0037177398,0.27444705,0.225134,0.011974889],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992372,0.000104179446,0.000088018685,0.00023114719,0.00024347579,0.000096044],"domain_scores_gemma":[0.9986249,0.00062060443,0.00013163732,0.00026928613,0.00018273067,0.00017082832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002551358,0.0021866674,0.001476776,0.0023694783,0.00088315184,0.0024157395,0.0026788255,0.0011336029,0.044540644],"category_scores_gemma":[0.0051057274,0.0014128045,0.0025568546,0.0013732322,0.00070199306,0.0032858162,0.0054432107,0.0024704929,0.017720854],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032801707,0.0004816481,0.024188248,0.0039650197,0.0010784533,0.0015148779,0.0020879374,0.009237194,0.036970746,0.013730892,0.7733051,0.13015977],"study_design_scores_gemma":[0.0016951335,0.00029907178,0.036232803,0.0010033267,0.00040361582,0.0013124517,0.00065566495,0.19938758,0.03870655,0.05923271,0.6602517,0.00081940787],"about_ca_topic_score_codex":0.0032054954,"about_ca_topic_score_gemma":0.0051432136,"teacher_disagreement_score":0.044540644,"about_ca_system_score_codex":0.00074461417,"about_ca_system_score_gemma":0.0017880771,"threshold_uncertainty_score":0.14900333},"labels":[],"label_agreement":null},{"id":"W4401946725","doi":"10.25080/xgyx8633","title":"unPython: Converting Python Numerical Programs into C","year":2008,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"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 Alberta","funders":"","keywords":"Python (programming language); Computer science; Programming language; Software engineering","score_opus":0.033090295547364194,"score_gpt":0.2770277039471624,"score_spread":0.24393740839979822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401946725","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029971988,0.0001290573,0.6277527,0.00018395926,0.00022650002,0.00034304455,0.010244634,0.33838457,0.019738447],"genre_scores_gemma":[0.0450938,0.00035011457,0.75795627,0.0007111181,0.00012152878,0.0015991103,0.028007323,0.13765973,0.028501075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981109,0.00023161047,0.00019345319,0.00034851974,0.0008502408,0.00026527463],"domain_scores_gemma":[0.9974306,0.0008281877,0.00016958191,0.00046786063,0.00093357096,0.00017011288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015013188,0.0013779234,0.00076797267,0.0015206945,0.0007929108,0.0017069101,0.0029049735,0.0007760988,0.058404602],"category_scores_gemma":[0.007442062,0.0010949179,0.0011295333,0.0013599051,0.0007562256,0.001639013,0.0023509234,0.0025978338,0.030856008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007581604,0.0002225969,0.00200143,0.0015558266,0.00016174343,0.0009291046,0.0006977937,0.023326509,0.028538967,0.042381104,0.59883106,0.3005957],"study_design_scores_gemma":[0.00028210922,0.0000764594,0.0024181902,0.00028748545,0.000044669123,0.0008024037,0.00012049591,0.15650012,0.07562577,0.04363967,0.7199733,0.00022931599],"about_ca_topic_score_codex":0.0034436076,"about_ca_topic_score_gemma":0.0036338936,"teacher_disagreement_score":0.058404602,"about_ca_system_score_codex":0.0008413791,"about_ca_system_score_gemma":0.0021827216,"threshold_uncertainty_score":0.19538283},"labels":[],"label_agreement":null},{"id":"W4403120212","doi":"10.25080/nkvc9349","title":"Continuous Tools for Scientific Publishing","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":4,"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":"Alberta Innovates; Alfred P. Sloan Foundation","keywords":"Computer science; Publishing; Scientific publishing; Political science","score_opus":0.5985646921998998,"score_gpt":0.5403248105297374,"score_spread":0.058239881670162474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403120212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008975665,0.0032246318,0.7869526,0.02596989,0.006687166,0.0014204842,0.0016420576,0.043730397,0.12139708],"genre_scores_gemma":[0.118074454,0.0038714006,0.79002005,0.0026367155,0.0066759023,0.0032470438,0.0031108246,0.011853182,0.060510475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88473696,0.045904305,0.0129323015,0.008896731,0.045128204,0.002401493],"domain_scores_gemma":[0.4983371,0.18960005,0.023780763,0.21057692,0.06535658,0.012348619],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.08885011,0.0017795423,0.0013372061,0.015834218,0.00774269,0.04296493,0.00832602,0.0066886963,0.042453036],"category_scores_gemma":[0.29412583,0.0020781087,0.00223595,0.016239982,0.012711937,0.049644873,0.032991905,0.009711558,0.032848332],"study_design_candidate":"not_applicable","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":[0.000190593,0.00021045882,0.0024730081,0.0011119298,0.000074706164,0.00042387014,0.012636689,0.001743968,0.0029494592,0.3299985,0.10780952,0.5403773],"study_design_scores_gemma":[0.0000884755,0.000103346945,0.00093669095,0.00057562225,0.00003337249,0.00060656486,0.0017513782,0.0022029008,0.0027180347,0.17669562,0.81415486,0.00013313412],"about_ca_topic_score_codex":0.00094389886,"about_ca_topic_score_gemma":0.00083669956,"teacher_disagreement_score":0.9841658,"about_ca_system_score_codex":0.0046406146,"about_ca_system_score_gemma":0.012988102,"threshold_uncertainty_score":0.46988994},"labels":[],"label_agreement":null},{"id":"W4403120218","doi":"10.25080/kmxn4784","title":"How the Scientific Python ecosystem helps answer fundamental questions of the Universe","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Particle Physics","funders":"","keywords":"Python (programming language); Computer science; Universe; Data science; Ecosystem; Scientific discovery; Astronomy; Programming language; Physics; Ecology; Cognitive science; Psychology","score_opus":0.024946111644908883,"score_gpt":0.25938449094257776,"score_spread":0.23443837929766886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403120218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014195704,0.0011621091,0.8401602,0.038026504,0.0022240658,0.00026075574,0.0020900734,0.06274515,0.039135486],"genre_scores_gemma":[0.1888922,0.0041637355,0.71935874,0.01722935,0.0021280877,0.0007225065,0.0069284397,0.037971217,0.022605725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912832,0.003635798,0.0004483944,0.001081098,0.0027980267,0.00075358734],"domain_scores_gemma":[0.9800283,0.009069823,0.0007105417,0.00546431,0.002387367,0.0023395885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015678646,0.0012214483,0.0007632752,0.002173456,0.0028618413,0.00858711,0.002766054,0.0019657584,0.01191638],"category_scores_gemma":[0.045402184,0.0010103874,0.0018608714,0.0024144,0.005851844,0.025493592,0.015523516,0.008734879,0.009197443],"study_design_candidate":"not_applicable","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":[0.00068452465,0.0003516957,0.01163425,0.0012954576,0.00026697267,0.0010900028,0.008570986,0.009009789,0.018446868,0.39344937,0.28817946,0.26702064],"study_design_scores_gemma":[0.000089991365,0.000082287486,0.002151557,0.00030936688,0.00006339036,0.00072852423,0.0010618607,0.026185088,0.010087981,0.47717524,0.48183343,0.00023120633],"about_ca_topic_score_codex":0.0018604058,"about_ca_topic_score_gemma":0.0025148478,"teacher_disagreement_score":0.015678646,"about_ca_system_score_codex":0.00087026175,"about_ca_system_score_gemma":0.00581321,"threshold_uncertainty_score":0.08291757},"labels":[],"label_agreement":null},{"id":"W4403120414","doi":"10.25080/nvyf1037","title":"Ecological and Spatial Influences on the Genetics of Cumacea (Crustacea: Peracarida) in the Northern North Atlantic","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Marine Biology and Ecology Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Ecology; Ecological genetics; Geography; Evolutionary biology; Biology; Demography; Sociology","score_opus":0.033640583455500965,"score_gpt":0.2697292356826447,"score_spread":0.2360886522271437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403120414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9998591,0.000029799343,0.000018542118,0.000004929082,5.1090296e-7,7.080702e-7,0.000015752017,5.6987517e-7,0.0000700615],"genre_scores_gemma":[0.9998165,0.000032563148,0.000050004855,0.0000070119236,0.0000020789626,0.0000017128941,0.000043978096,7.382645e-7,0.000045376015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998368,0.000039089467,0.000015078756,0.00005801496,0.000025357287,0.00002559324],"domain_scores_gemma":[0.99955565,0.00008227954,0.0001885137,0.000030106581,0.00004366285,0.00009979572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713522,0.0001231738,0.00016505097,0.00048811716,0.00028544935,0.00031561137,0.00013511421,0.0001790365,0.0005406103],"category_scores_gemma":[0.00066815544,0.00012792424,0.00016340657,0.00041193428,0.0004263643,0.00018045008,0.00035840026,0.00015151883,0.000056602337],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008571594,0.000020707857,0.97535,0.000016976797,0.000056589815,0.00009900519,0.0006915142,0.00019871327,0.019502455,0.000032923657,0.000024953968,0.0039203893],"study_design_scores_gemma":[7.174452e-7,0.000010637309,0.99972194,0.0000011378341,0.0000033352767,0.000016241553,0.00011746731,0.00006471306,0.00003145263,0.0000048244706,0.000026598638,8.3649684e-7],"about_ca_topic_score_codex":0.012256165,"about_ca_topic_score_gemma":0.036004905,"teacher_disagreement_score":0.012256165,"about_ca_system_score_codex":0.00033079737,"about_ca_system_score_gemma":0.00023221763,"threshold_uncertainty_score":0.024369657},"labels":[],"label_agreement":null},{"id":"W7092194480","doi":"10.25080/hwcj9957","title":"Jupyter Book 2 and the MyST Document Stack","year":2025,"lang":"","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":2,"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":"Alberta Innovates; National Cancer Institute; Alfred P. Sloan Foundation; National Institutes of Health; National Science Foundation","keywords":"Stack (abstract data type); Reuse; Scalability; Foundation (evidence); Publication","score_opus":0.011401672200601346,"score_gpt":0.26461652229463584,"score_spread":0.2532148500940345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092194480","genre_codex":"other","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020497069,0.0038617009,0.30993435,0.007091524,0.005587474,0.00046410065,0.033972777,0.29505455,0.34198377],"genre_scores_gemma":[0.010892442,0.0043991613,0.20710097,0.004008153,0.0017357463,0.0006305842,0.05840443,0.18412803,0.52870053],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983358,0.00014077366,0.00012432547,0.00018905374,0.0010463798,0.00016374317],"domain_scores_gemma":[0.99551904,0.0011037495,0.00018144058,0.0012398066,0.0012235729,0.0007323525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023214943,0.001283405,0.0010858735,0.0030370352,0.0021962444,0.010867694,0.0029649425,0.002332953,0.24888478],"category_scores_gemma":[0.009722542,0.001958501,0.0018463096,0.005055564,0.0013358697,0.016592976,0.006915778,0.0040689316,0.22732083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007590108,0.000028360078,0.00010545673,0.00021760454,0.000013333567,0.000095005555,0.0001626024,0.00030571545,0.001044068,0.03729854,0.89733136,0.06332202],"study_design_scores_gemma":[0.000017204069,0.000006327744,0.000120216464,0.00007436501,0.0000047680214,0.00011534014,0.000024154735,0.0005144182,0.00062651845,0.010055681,0.9884166,0.00002436834],"about_ca_topic_score_codex":0.0040113144,"about_ca_topic_score_gemma":0.00599812,"teacher_disagreement_score":0.24888478,"about_ca_system_score_codex":0.0017495936,"about_ca_system_score_gemma":0.0029317287,"threshold_uncertainty_score":0.83260256},"labels":[],"label_agreement":null}]}