{"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":"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":[0.92285174,0.000021996444,0.05064991,0.0076362253,0.0005931001,0.0006038392,0.0000017917183,0.000162175,0.017479198],"genre_scores_gemma":[0.9755748,0.000004943371,0.024048705,0.0001409146,0.00003248458,0.000047397654,6.8302126e-7,0.0000042125953,0.00014588238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822706,0.000027187107,0.00039110673,0.00049783074,0.0005466033,0.00031022626],"domain_scores_gemma":[0.99853337,0.00022971406,0.0003929795,0.00029518083,0.0004678353,0.00008091439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027662013,0.00012823957,0.00019897713,0.00024801676,0.00034630435,0.0005214636,0.0023982555,0.00005091596,0.000011758244],"category_scores_gemma":[0.0036705579,0.00008663438,0.000053160868,0.0010689647,0.0005671994,0.0011606831,0.00024164753,0.00015609906,0.000008355416],"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":[0.0000093535555,0.000070112554,0.028859515,0.00012740272,0.000003856459,2.7128364e-8,0.0035152542,0.000079274185,0.047381338,0.7142948,0.00020294708,0.20545615],"study_design_scores_gemma":[0.0004114364,0.00021172047,0.08197734,0.00016268896,0.000009170723,0.0000065885783,0.00081455114,0.8525357,0.026130227,0.0320619,0.005417144,0.00026153558],"about_ca_topic_score_codex":0.000056320372,"about_ca_topic_score_gemma":0.000007758607,"teacher_disagreement_score":0.85245645,"about_ca_system_score_codex":0.00003361907,"about_ca_system_score_gemma":0.00025761462,"threshold_uncertainty_score":0.50284857},"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":"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":[0.9401301,0.00015949257,0.010589862,0.015530917,0.00053195097,0.019473664,0.00003120963,0.0001735315,0.013379275],"genre_scores_gemma":[0.9719181,0.000014748678,0.02697645,0.000042773492,0.000014917652,0.0010063673,0.0000039750166,0.0000029646008,0.000019691712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772644,0.000042399213,0.0003938225,0.00071116077,0.0008542337,0.0002719186],"domain_scores_gemma":[0.9985355,0.00007950728,0.00032851467,0.0005684296,0.00042666408,0.000061369414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005335463,0.0001165277,0.00015970219,0.00028147543,0.0001399571,0.0006830572,0.003919029,0.000044654902,0.000011889194],"category_scores_gemma":[0.0016275094,0.00007965659,0.000010498296,0.0015152865,0.00046827464,0.004205823,0.0015524654,0.00020158583,0.000006009427],"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":[0.0000027553751,0.00007844544,0.1982958,0.000059343893,0.0000015823825,9.7713084e-8,0.0018071297,0.000010351099,0.007377317,0.018208612,0.00030064615,0.7738579],"study_design_scores_gemma":[0.00021496211,0.00003357032,0.3685924,0.00015650522,0.000001946725,0.000004121652,0.00035000787,0.61509097,0.0014355166,0.013619043,0.00039630034,0.00010465797],"about_ca_topic_score_codex":0.0006747979,"about_ca_topic_score_gemma":0.00005403582,"teacher_disagreement_score":0.7737532,"about_ca_system_score_codex":0.000045077613,"about_ca_system_score_gemma":0.00037951005,"threshold_uncertainty_score":0.7282597},"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":"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":[0.9750019,0.00017724663,0.023035284,0.00081745937,0.00006561737,0.00030442345,0.00008646224,0.000004388348,0.0005072368],"genre_scores_gemma":[0.9988851,0.0000615403,0.0009136631,0.000038914954,0.000015613086,0.000025627633,0.000003922488,0.000005116686,0.000050507308],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880815,0.000010447081,0.00033987252,0.0003208331,0.00030589153,0.00021478874],"domain_scores_gemma":[0.99869925,0.00008110517,0.00035568888,0.00027409388,0.0005560401,0.0000338416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007235241,0.000115514595,0.00022272652,0.00022088725,0.00012474274,0.000036416946,0.0010190887,0.00006990814,0.000008279605],"category_scores_gemma":[0.00095858617,0.000055638055,0.00020525283,0.0015212034,0.0008919306,0.000019597563,0.00020674783,0.000044943597,8.5103444e-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":[0.000032191998,0.000017521357,0.040066436,0.000014869303,0.00015995796,2.4134483e-8,0.00015602069,0.00046823386,0.94320583,0.009833684,0.0000055901005,0.0060396236],"study_design_scores_gemma":[0.00036243894,0.00014357026,0.031777058,0.000059152262,0.00064736005,0.0000010051201,0.0007821811,0.047783796,0.9088828,0.009202196,0.00015312864,0.00020529132],"about_ca_topic_score_codex":0.000037695674,"about_ca_topic_score_gemma":0.00019034951,"teacher_disagreement_score":0.047315564,"about_ca_system_score_codex":0.000026042317,"about_ca_system_score_gemma":0.00022584134,"threshold_uncertainty_score":0.32863554},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98164576,0.000020926089,0.0003350398,0.0014975175,0.0006359949,0.0003248326,0.000022909622,0.00001569963,0.015501316],"genre_scores_gemma":[0.9978185,0.000004637426,0.0020519996,0.000028855611,0.000033561384,0.000002172806,2.2403728e-7,0.0000020888617,0.000057924637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992808,0.000032870917,0.0009942694,0.0016626727,0.003956676,0.00054553646],"domain_scores_gemma":[0.9883655,0.0006843479,0.0011024815,0.0025161766,0.0071024746,0.00022906516],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.047787227,0.00014838393,0.00032884043,0.0008304149,0.00062336936,0.001097783,0.014791764,0.000039947612,0.000053361444],"category_scores_gemma":[0.044145662,0.00008644266,0.000033452157,0.009171771,0.025970457,0.0035265938,0.022834485,0.00015447944,0.000002237449],"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":[0.000023311171,0.00006826262,0.79547584,0.000063318395,0.0000019398515,8.354898e-8,0.002557181,0.000012107861,0.005816972,0.06574957,0.00069185044,0.12953955],"study_design_scores_gemma":[0.0001484771,0.00009279933,0.6063226,0.000077192606,0.000006809285,0.0000036478673,0.008401885,0.022598885,0.010237216,0.351082,0.00089569204,0.00013284133],"about_ca_topic_score_codex":0.000261333,"about_ca_topic_score_gemma":0.000093877126,"teacher_disagreement_score":0.28533244,"about_ca_system_score_codex":0.00009753052,"about_ca_system_score_gemma":0.0017644247,"threshold_uncertainty_score":0.99993914},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99843353,0.0007695191,0.0000071705613,0.00006115548,0.00004736737,0.00010808228,0.000076873795,5.3823453e-7,0.0004957778],"genre_scores_gemma":[0.9988912,0.0002596969,0.0008083006,0.000019842257,0.000005062976,0.000008915299,0.000001999348,0.0000022821655,0.0000026978262],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989813,0.000010863863,0.00031487385,0.00030549118,0.000252146,0.00013531755],"domain_scores_gemma":[0.99924374,0.00001628334,0.00032790474,0.00023814569,0.00016004038,0.000013893055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075758266,0.00007538182,0.00022453292,0.00022264976,0.000097433534,0.00001145559,0.0011532648,0.000017942386,0.000002583594],"category_scores_gemma":[0.0001416408,0.000057406683,0.000053397885,0.0011699686,0.00092146435,0.000002787735,0.0015092461,0.000043194126,1.4760037e-8],"study_design_candidate":"observational","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":[0.000007649767,0.000019905638,0.41985607,0.000019622015,0.00004769716,1.1874694e-8,0.00022854932,0.000034549525,0.5791962,0.00020587086,0.000007111212,0.0003767709],"study_design_scores_gemma":[0.00013933229,0.00018023937,0.6683489,0.000012352618,0.0001723357,0.0000015082923,0.0019227834,0.0021897855,0.32568163,0.0011048524,0.00015021143,0.000096053984],"about_ca_topic_score_codex":0.00015698992,"about_ca_topic_score_gemma":0.000057918005,"teacher_disagreement_score":0.25351456,"about_ca_system_score_codex":0.0000033458282,"about_ca_system_score_gemma":0.000095870986,"threshold_uncertainty_score":0.33951738},"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":"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":[0.6222017,0.00020614798,0.0023311435,0.0070760963,0.0035837311,0.0027542666,0.000055418306,0.00008652989,0.361705],"genre_scores_gemma":[0.99482334,0.000073788404,0.0030317565,0.00013362379,0.00009847296,0.00012784087,8.827e-7,0.000016734197,0.0016935362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993299,0.000021357102,0.0014180329,0.0015883641,0.0027783087,0.000894946],"domain_scores_gemma":[0.9932354,0.00023629205,0.0022364089,0.00063922134,0.0034777443,0.00017491652],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.004351675,0.0005077984,0.0007960367,0.0010637689,0.0006031038,0.0010364978,0.015417087,0.00019198454,0.000035686746],"category_scores_gemma":[0.00083323114,0.0003345535,0.00019893292,0.011022269,0.005907235,0.0017279125,0.0035491127,0.0008783516,0.000042558837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012511305,0.0002136423,0.009853371,0.00037628078,0.0000080165155,8.0700794e-8,0.0044188905,0.00026667884,0.053955548,0.92175674,0.0034339435,0.0057042763],"study_design_scores_gemma":[0.0013960348,0.00039819806,0.15627769,0.006771726,0.000057602778,0.000040172774,0.0024135008,0.12805997,0.2586822,0.42185107,0.021561857,0.0024899945],"about_ca_topic_score_codex":0.00042744793,"about_ca_topic_score_gemma":0.00005301259,"teacher_disagreement_score":0.4999057,"about_ca_system_score_codex":0.00025963996,"about_ca_system_score_gemma":0.00434803,"threshold_uncertainty_score":0.99991065},"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":"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":[0.67811954,0.0002301246,0.0008490281,0.0057670344,0.002846388,0.002907963,0.000048984355,0.000069825364,0.30916113],"genre_scores_gemma":[0.99377465,0.00010746757,0.003069121,0.00011464672,0.00008303336,0.00020601314,8.5160633e-7,0.000016862135,0.0026273585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933093,0.000015767306,0.0014272222,0.0015672172,0.0027557148,0.0009247317],"domain_scores_gemma":[0.9928891,0.00020257296,0.0021716012,0.0006218887,0.0039316225,0.00018321355],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0030898652,0.0005161352,0.0007624719,0.0010721245,0.000589641,0.0012538276,0.015446347,0.00019440553,0.00008514565],"category_scores_gemma":[0.0006715763,0.00033522336,0.00019417662,0.011312805,0.0059453673,0.0024652977,0.003798496,0.00089651387,0.00007025334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010459062,0.00028885732,0.010030624,0.00039758277,0.000010364274,1.0261793e-7,0.00558139,0.00021530436,0.09908366,0.8711379,0.0065035853,0.0067401286],"study_design_scores_gemma":[0.0011828764,0.00032443882,0.17230473,0.0058954363,0.000048425147,0.000036233487,0.0034293819,0.09173671,0.30577442,0.40478414,0.012160548,0.0023226435],"about_ca_topic_score_codex":0.0006565302,"about_ca_topic_score_gemma":0.000040614297,"teacher_disagreement_score":0.4663538,"about_ca_system_score_codex":0.0002682628,"about_ca_system_score_gemma":0.004511381,"threshold_uncertainty_score":0.99991},"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":"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":[0.9989356,0.00025973385,0.0001043781,0.0001801486,0.00010076318,0.0002396883,0.000028011793,0.0000030502113,0.0001486567],"genre_scores_gemma":[0.99894446,0.00017766157,0.0008003147,0.000024022926,0.000018906507,0.000020335538,0.0000012192096,0.0000042637416,0.000008787356],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988402,0.000007902679,0.0002973162,0.00048123545,0.00016467416,0.00020865568],"domain_scores_gemma":[0.99914193,0.000028160106,0.000284894,0.00016343106,0.0003603672,0.000021232752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013384568,0.00010423834,0.00023303591,0.00041803368,0.00012892058,0.000037905495,0.00040587113,0.000052730673,4.979767e-7],"category_scores_gemma":[0.000600446,0.0000792036,0.00009035278,0.0021530553,0.0006052383,0.00000506721,0.00030478038,0.00003727833,5.713213e-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":[0.00001951839,0.000011362649,0.17565861,0.000035962963,0.00006105054,1.0620401e-8,0.0005668431,0.0001922497,0.8228493,0.0004078057,0.000008099035,0.00018919936],"study_design_scores_gemma":[0.00020475105,0.00012797724,0.21968813,0.000029530462,0.00014060055,9.798767e-7,0.0010314552,0.012223112,0.76350963,0.0027396106,0.00017963444,0.00012457387],"about_ca_topic_score_codex":0.00014511505,"about_ca_topic_score_gemma":0.00012204376,"teacher_disagreement_score":0.05933965,"about_ca_system_score_codex":0.0000071955537,"about_ca_system_score_gemma":0.00014544497,"threshold_uncertainty_score":0.32298294},"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":"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":[0.9533507,0.00006642274,0.027932193,0.0045084367,0.00042130458,0.0005328166,8.6383386e-7,0.00016628954,0.013020975],"genre_scores_gemma":[0.97727734,0.000012017948,0.02242377,0.00011944821,0.00004638488,0.00005883325,3.655571e-7,0.0000058489845,0.000055998225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975398,0.000014048838,0.0005071191,0.0006063827,0.0009348015,0.0003978348],"domain_scores_gemma":[0.9984196,0.00010765122,0.00038485555,0.0002779777,0.0006872303,0.00012267326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009089182,0.00017153233,0.0002387386,0.00020397604,0.0005509796,0.0002109438,0.0030330026,0.00004415552,0.000004996932],"category_scores_gemma":[0.0002102717,0.00012592315,0.000088731074,0.0035796198,0.0011533874,0.0010423975,0.00081844017,0.00021900868,0.000012306403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072155576,0.00022260915,0.12242476,0.00004124889,0.0000059566037,9.737071e-7,0.008082094,0.000117376905,0.017314633,0.8072296,0.00014784171,0.044405732],"study_design_scores_gemma":[0.00068623165,0.00025191274,0.19492102,0.00031828356,0.000011250565,0.00011356992,0.0012198365,0.26415026,0.07270857,0.4604743,0.0042877803,0.0008569443],"about_ca_topic_score_codex":0.00016474577,"about_ca_topic_score_gemma":0.0000074426657,"teacher_disagreement_score":0.34675524,"about_ca_system_score_codex":0.00006559401,"about_ca_system_score_gemma":0.00064249634,"threshold_uncertainty_score":0.5636124},"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":"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":[0.95938224,0.0006682796,0.00054831436,0.005859457,0.003561815,0.00065800035,0.00004283013,0.000044316923,0.029234739],"genre_scores_gemma":[0.9968843,0.000023124405,0.0012129785,0.000039879935,0.0000756743,0.000046638277,4.259425e-7,0.0000061432393,0.0017108467],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9874309,0.000023105178,0.0009970164,0.0012701623,0.0094229765,0.0008558515],"domain_scores_gemma":[0.9729596,0.009203928,0.0006744374,0.00073065714,0.015978824,0.00045257845],"candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.07567436,0.00015465115,0.00033348618,0.03125981,0.0006699399,0.073861726,0.009516142,0.00009285972,0.00009337363],"category_scores_gemma":[0.18802191,0.000083986495,0.00018885483,0.20063831,0.0028855624,0.010619545,0.0014946584,0.00033756593,0.000021931977],"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":[0.000022670622,0.000088083296,0.13474694,0.00008758603,0.000006980602,8.928404e-7,0.002174022,0.000013042915,0.060720555,0.32224068,0.01669471,0.46320382],"study_design_scores_gemma":[0.00055860763,0.00028068246,0.104762085,0.00053539156,0.000015236941,0.000018561997,0.014503649,0.06365052,0.11847948,0.5398842,0.15674601,0.0005655223],"about_ca_topic_score_codex":0.00006453407,"about_ca_topic_score_gemma":0.000023958082,"teacher_disagreement_score":0.46263832,"about_ca_system_score_codex":0.00012817176,"about_ca_system_score_gemma":0.0017067905,"threshold_uncertainty_score":0.99982804},"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":"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":[0.955045,0.00021591835,0.006220167,0.028564261,0.002532433,0.00079585885,0.000039956183,0.000090434456,0.0064959605],"genre_scores_gemma":[0.99862564,0.000008081784,0.0008446734,0.000030653755,0.000038677903,0.000027175296,2.7853153e-7,0.000004108181,0.00042070134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980745,0.000025810816,0.00028663946,0.00047731254,0.0008933554,0.00024240918],"domain_scores_gemma":[0.9986113,0.00017452883,0.00024250045,0.0003797233,0.0005428805,0.000049098104],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014639961,0.00012617646,0.00013452425,0.0002058425,0.0006978515,0.001445764,0.0036669157,0.00002876115,0.0000044473],"category_scores_gemma":[0.00012221621,0.000064688276,0.0001146012,0.0043566455,0.001522342,0.0010524329,0.0010689886,0.00019370334,0.0000041690787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010810517,0.00003458576,0.0019866081,0.000042406282,0.000004820196,7.90873e-8,0.002619463,0.00012356468,0.021804404,0.96899676,0.00028619394,0.004100027],"study_design_scores_gemma":[0.0002622279,0.000094302886,0.04926431,0.0013177248,0.000043305256,0.000036819856,0.008290106,0.3188776,0.07660284,0.51506823,0.029650295,0.0004922174],"about_ca_topic_score_codex":0.00006277946,"about_ca_topic_score_gemma":0.00007389037,"teacher_disagreement_score":0.45392853,"about_ca_system_score_codex":0.00007873255,"about_ca_system_score_gemma":0.0008232079,"threshold_uncertainty_score":0.9995908},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933248,0.00020707307,2.2393588e-7,0.002702686,0.00014165271,0.00026223395,0.000004473827,0.000005626637,0.0033511838],"genre_scores_gemma":[0.9996263,0.00022430524,0.000010362966,0.000089097404,0.000026734311,0.000005644793,6.0528413e-7,8.863688e-7,0.000016073845],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99867547,0.000061922496,0.00026665043,0.00028829367,0.00040601328,0.00030165966],"domain_scores_gemma":[0.9989144,0.00077283924,0.000090069814,0.00009101626,0.00009946031,0.000032193155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023549264,0.000102313905,0.00015413573,0.00014288322,0.00022896101,0.00012084406,0.001197383,0.00006680536,0.00015245318],"category_scores_gemma":[0.00065456657,0.00004122539,0.00003081231,0.00083631685,0.0025613026,0.00013372797,0.000112416914,0.00037720712,0.000006316975],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002074022,0.000014747498,0.99320805,0.000027547292,0.0000031691393,0.0000010993369,0.0013573419,0.000104677325,0.000050386523,0.0010511208,0.000010855484,0.004150257],"study_design_scores_gemma":[0.000048330094,0.00021980017,0.9828758,0.00003986755,0.000004559097,0.0000074971363,0.0016634305,0.012384807,0.00013324738,0.002479917,0.00008714646,0.00005557171],"about_ca_topic_score_codex":0.0027847781,"about_ca_topic_score_gemma":0.041187115,"teacher_disagreement_score":0.038402334,"about_ca_system_score_codex":0.0000051297957,"about_ca_system_score_gemma":0.00024848044,"threshold_uncertainty_score":0.9763087},"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":"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":[0.42761567,0.006766355,0.0430404,0.05595179,0.0057473183,0.0036584153,0.000004861223,0.00016322301,0.45705196],"genre_scores_gemma":[0.99373424,0.00047685203,0.0026406099,0.0013262689,0.000036491503,0.000028205222,4.5460773e-8,0.000003899779,0.001753373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600327,0.00003912804,0.0014350502,0.0006582251,0.0012148555,0.00064944156],"domain_scores_gemma":[0.9966897,0.00033502586,0.0012993333,0.0004126853,0.0011644746,0.00009882135],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0073620114,0.00032232612,0.0005259953,0.00048888376,0.0011612449,0.0030795997,0.0049404264,0.00008790746,0.000040662035],"category_scores_gemma":[0.0015096547,0.00017814725,0.000108286345,0.0027686001,0.0057982537,0.0036103395,0.0028347108,0.00041041395,0.000005316105],"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":[0.000025981948,0.000043885564,0.004287278,0.00073665986,0.0000142149975,8.939326e-8,0.03734371,0.000028556842,0.00019383266,0.92879623,0.00079629006,0.027733259],"study_design_scores_gemma":[0.0022435752,0.000098769386,0.0068964893,0.004565931,0.000063359184,0.000019718873,0.01156631,0.53565353,0.020927936,0.40899816,0.008371289,0.00059493975],"about_ca_topic_score_codex":0.0000733148,"about_ca_topic_score_gemma":0.000006206023,"teacher_disagreement_score":0.5661186,"about_ca_system_score_codex":0.00009784061,"about_ca_system_score_gemma":0.0013455155,"threshold_uncertainty_score":0.9979553},"labels":[],"label_agreement":null}]}