{"meta":{"query_hash":"bd4927a0c0a5","filters":{"venue":"Proceedings of the ACM on software engineering."},"cohort_total":36,"direct_labels_cover":0,"predictions_cover":36,"exported":36,"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/bd4927a0c0a5","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+ACM+on+software+engineering."},"results":[{"id":"W4394906543","doi":"10.1145/3660806","title":"An Empirical Study on Code Review Activity Prediction and Its Impact in Practice","year":2024,"lang":"en","type":"preprint","venue":"Proceedings of the ACM on software engineering.","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"Ubisoft (Canada); Queen's University","funders":"Mitacs","keywords":"Code (set theory); Computer science; Programming language","score_opus":0.10133249139045217,"score_gpt":0.44118744781838515,"score_spread":0.33985495642793295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394906543","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":[0.9933117,0.0011812701,0.00009601632,0.002050617,0.0014700288,0.0013677005,0.0001707597,0.00023690192,0.000115020186],"genre_scores_gemma":[0.9982786,0.00015637426,0.0010890561,0.00015963026,0.00011498991,0.00006636334,0.0000034399193,0.0000321726,0.00009934509],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99566823,0.000064936605,0.00068718515,0.0013809493,0.0019323571,0.00026631152],"domain_scores_gemma":[0.9959208,0.0012979489,0.0004604891,0.0017726932,0.00042097268,0.0001271051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008386633,0.00035690167,0.000578652,0.00056658796,0.00006792581,0.0005250692,0.0031266056,0.00013058285,0.000008647277],"category_scores_gemma":[0.07241864,0.00022355329,0.00016357964,0.0012474922,0.000027420945,0.00031882612,0.0058305315,0.0011620081,0.000024942874],"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":[0.0013176348,0.008665771,0.2650301,0.011977464,0.0012788915,0.00006284791,0.01133781,0.08790443,0.0007404943,0.00059331756,0.48518217,0.1259091],"study_design_scores_gemma":[0.00094282435,0.0022812868,0.8507248,0.016649654,0.00071918574,0.00003874425,0.0009088219,0.10998308,0.0005482754,0.0040389276,0.011966543,0.0011978389],"about_ca_topic_score_codex":0.000020822683,"about_ca_topic_score_gemma":0.0000018472475,"teacher_disagreement_score":0.58569473,"about_ca_system_score_codex":0.00018043934,"about_ca_system_score_gemma":0.00006955301,"threshold_uncertainty_score":0.93539476},"labels":[],"label_agreement":null},{"id":"W4400434361","doi":"10.1145/3715773","title":"An Adaptive Language-Agnostic Pruning Method for Greener Language Models for Code","year":2025,"lang":"en","type":"preprint","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University","funders":"Agencia Estatal de Investigación; Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Knut och Alice Wallenbergs Stiftelse","keywords":"Pruning; Computer science; Code (set theory); Artificial intelligence; Language model; Natural language processing; Programming language; Biology; Botany","score_opus":0.02915474167711867,"score_gpt":0.31616635034274054,"score_spread":0.28701160866562186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400434361","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":[0.014095112,0.0005284932,0.9801694,0.0003012695,0.00088669074,0.0022129146,0.000483106,0.0013055797,0.000017445855],"genre_scores_gemma":[0.084481895,0.000008840306,0.9132159,0.000109711094,0.00026775908,0.001407035,0.000023535671,0.00011692298,0.0003684541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686193,0.000016123839,0.00051965733,0.0011710367,0.0006790388,0.0007522317],"domain_scores_gemma":[0.99261594,0.0040347204,0.00030668807,0.0020590657,0.0008049726,0.00017861935],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012083788,0.0006269237,0.00074391405,0.0005525728,0.00012864236,0.00022419402,0.008581235,0.00043063294,0.0000014330617],"category_scores_gemma":[0.020266479,0.0005472543,0.00044086747,0.0005814467,0.000037953057,0.00038535628,0.0038788742,0.00091839005,9.3647776e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016098857,0.00017518534,0.0003923733,0.0044448758,0.00041849626,0.0000027923008,0.005568552,0.95097387,0.0031211595,0.017507477,0.004233153,0.0130011],"study_design_scores_gemma":[0.00063297607,0.0003405755,0.00041392824,0.0015074344,0.00009889139,0.0000059276863,0.00009579077,0.9586285,0.032243688,0.0050436356,0.00027664902,0.0007120154],"about_ca_topic_score_codex":0.000060391554,"about_ca_topic_score_gemma":0.0000027972023,"teacher_disagreement_score":0.07038678,"about_ca_system_score_codex":0.00025660437,"about_ca_system_score_gemma":0.00022515282,"threshold_uncertainty_score":0.9996979},"labels":[],"label_agreement":null},{"id":"W4400581753","doi":"10.1145/3660823","title":"Dependency-Induced Waste in Continuous Integration: An Empirical Study of Unused Dependencies in the npm Ecosystem","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"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":"Dependency (UML); Computer science; Context (archaeology); Reuse; JSON; Dependency theory (database theory); Code reuse; Resource (disambiguation); Dependency graph; Database; Software; Software engineering; Functional dependency; Relational database; Operating system; Engineering","score_opus":0.029745562251328024,"score_gpt":0.28998160021238495,"score_spread":0.26023603796105693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400581753","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":[0.99577045,0.000119298165,0.002323915,0.0002616503,0.00042701862,0.000757891,0.0000032598916,0.0003228146,0.000013712211],"genre_scores_gemma":[0.99586654,0.0000024590913,0.0038689456,0.00001757952,0.000062597726,0.00013393622,4.462883e-7,0.000034260924,0.000013217429],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974391,0.000041039966,0.00057978474,0.00052354496,0.0010272656,0.00038930384],"domain_scores_gemma":[0.99737656,0.0012906931,0.00009112925,0.000981535,0.00019733219,0.0000627413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015753955,0.000274997,0.00038546053,0.00063450105,0.00003899146,0.0002042929,0.0048578572,0.00012319275,0.0000020588425],"category_scores_gemma":[0.0063917064,0.00017886031,0.000096878575,0.0022122308,0.000018750306,0.00057160575,0.00075145386,0.0007712991,0.0000037292643],"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":[0.00013745796,0.0025431807,0.83326805,0.002234164,0.00023451472,0.00019121147,0.09397201,0.024041364,0.021924451,0.0060008774,0.0010794282,0.014373279],"study_design_scores_gemma":[0.0029844025,0.004365116,0.713203,0.0039561205,0.00006688914,0.00023876509,0.01294796,0.171465,0.08743548,0.0015895133,0.00022150055,0.0015262516],"about_ca_topic_score_codex":0.00006530012,"about_ca_topic_score_gemma":0.00008046247,"teacher_disagreement_score":0.14742362,"about_ca_system_score_codex":0.00015879159,"about_ca_system_score_gemma":0.000092016424,"threshold_uncertainty_score":0.90271884},"labels":[],"label_agreement":null},{"id":"W4400581925","doi":"10.1145/3660813","title":"Revealing Software Development Work Patterns with PR-Issue Graph Topologies","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"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":"Network topology; Computer science; Graph; Software development; Software; Software engineering; Theoretical computer science; Programming language; Operating system","score_opus":0.014321233758022994,"score_gpt":0.23332791828836394,"score_spread":0.21900668453034094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400581925","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":[0.66031957,0.0012616857,0.32833374,0.0017412216,0.0017172978,0.0007814397,0.000010963935,0.0058080754,0.000026006055],"genre_scores_gemma":[0.5442484,0.000025682895,0.4547435,0.000101041835,0.00017592001,0.0001696428,0.0000020103516,0.00010687563,0.0004268992],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972762,0.000006103715,0.00038865028,0.00071694975,0.00093821966,0.00067391124],"domain_scores_gemma":[0.9975247,0.0009807566,0.00008871385,0.0010044589,0.0002568797,0.00014451315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050583633,0.0004225972,0.00034425315,0.00044696077,0.00013220192,0.00035665891,0.0043604397,0.00014058588,0.000011630737],"category_scores_gemma":[0.005688294,0.00029499608,0.00013422128,0.0018016237,0.00006177131,0.0004710642,0.001720137,0.0006647103,0.00003242059],"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":[0.00018894945,0.0004370728,0.7310418,0.012718624,0.0015866483,0.00018553299,0.013493837,0.039509155,0.0017920142,0.011293043,0.057570294,0.13018304],"study_design_scores_gemma":[0.001840404,0.001419511,0.5630815,0.025555022,0.00017350398,0.0004307362,0.00034852812,0.0037032175,0.27893028,0.0024632183,0.11660322,0.0054508345],"about_ca_topic_score_codex":0.0000075897487,"about_ca_topic_score_gemma":5.21574e-7,"teacher_disagreement_score":0.27713826,"about_ca_system_score_codex":0.00018589238,"about_ca_system_score_gemma":0.00011844445,"threshold_uncertainty_score":0.99995023},"labels":[],"label_agreement":null},{"id":"W4400581939","doi":"10.1145/3660812","title":"A Weak Supervision-Based Approach to Improve Chatbots for Code Repositories","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"AI in Service Interactions","field":"Computer Science","cited_by":2,"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 Calgary; Concordia University","funders":"","keywords":"Computer science; Code (set theory); Programming language; World Wide Web; Software engineering; Database","score_opus":0.012757721096490286,"score_gpt":0.24273440712088265,"score_spread":0.22997668602439236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400581939","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":[0.022494832,0.00015651292,0.96275836,0.0069149183,0.0045057493,0.001128374,0.000053525175,0.001701496,0.00028625104],"genre_scores_gemma":[0.37204945,0.0000013969565,0.6262173,0.00034035867,0.00034228535,0.0004560883,0.0000017436957,0.000061008297,0.0005303696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986077,0.00000195899,0.00026868287,0.000501881,0.0003416293,0.00027813477],"domain_scores_gemma":[0.9983687,0.00041152776,0.00006063113,0.00075759686,0.00031010993,0.00009147619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022356289,0.00020908692,0.00019193004,0.0001795071,0.000095506795,0.00029812337,0.0029111726,0.0000802656,0.000001075729],"category_scores_gemma":[0.0023173338,0.00014306068,0.00016961487,0.00067655975,0.000015476158,0.00041433572,0.0007398153,0.00021511826,0.0000089887035],"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":[0.00035558533,0.0013268926,0.0034283572,0.0140834255,0.0008384454,0.0000055358432,0.016005086,0.061846018,0.3237393,0.34854826,0.19583154,0.03399159],"study_design_scores_gemma":[0.00039667156,0.00055748323,0.00081637065,0.0013262613,0.000060290866,0.000032831427,0.00015194398,0.65805775,0.24043772,0.0023885553,0.09502115,0.00075296673],"about_ca_topic_score_codex":0.000009265966,"about_ca_topic_score_gemma":3.0624642e-7,"teacher_disagreement_score":0.59621173,"about_ca_system_score_codex":0.00010563075,"about_ca_system_score_gemma":0.000055115564,"threshold_uncertainty_score":0.5833845},"labels":[],"label_agreement":null},{"id":"W4400582230","doi":"10.1145/3660810","title":"ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Consistency (knowledge bases); Computer science; Fidelity; Code (set theory); Natural language generation; Natural language; Artificial intelligence; Programming language","score_opus":0.03864211965604995,"score_gpt":0.2956780983054859,"score_spread":0.25703597864943595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582230","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":[0.036726877,0.00026616687,0.9588242,0.0011712991,0.0012598304,0.00060283224,0.000011692031,0.0011335224,0.000003584977],"genre_scores_gemma":[0.5343672,0.0000039474976,0.46496078,0.00009698335,0.00024964768,0.00021936164,0.000004476969,0.00005385274,0.000043730342],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979225,0.0000063270218,0.00038478145,0.0005935379,0.0006674491,0.00042542326],"domain_scores_gemma":[0.99752927,0.0010543144,0.00009984226,0.0008922251,0.00032883938,0.000095518255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00085996813,0.000259615,0.00021753111,0.00031675573,0.00011926995,0.00031439128,0.0025452604,0.00023527925,0.0000038818134],"category_scores_gemma":[0.012965621,0.00022208864,0.00017364761,0.0009865756,0.000027072874,0.0004660059,0.0003935065,0.00053864176,0.000013347916],"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":[0.000111510846,0.0005969439,0.009687219,0.0073891417,0.0005422951,0.0000069437847,0.002483192,0.0788905,0.5526459,0.28322262,0.023069164,0.04135454],"study_design_scores_gemma":[0.00030702745,0.00028693688,0.0028757423,0.001080704,0.000033488075,0.0000072425078,0.0000054175757,0.549941,0.43415788,0.006088183,0.0047396594,0.00047672872],"about_ca_topic_score_codex":0.000003298545,"about_ca_topic_score_gemma":6.1068783e-7,"teacher_disagreement_score":0.49764034,"about_ca_system_score_codex":0.00023860375,"about_ca_system_score_gemma":0.00009464208,"threshold_uncertainty_score":0.9953486},"labels":[],"label_agreement":null},{"id":"W4400582353","doi":"10.1145/3660809","title":"Mining Action Rules for Defect Reduction Planning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Commit; Computer science; Counterfactual thinking; Reduction (mathematics); Precision and recall; Code (set theory); Action (physics); Recall; Compiler; Software; Baseline (sea); Machine learning; Software bug; Artificial intelligence; Software engineering; Programming language; Database; Set (abstract data type)","score_opus":0.03604877384191616,"score_gpt":0.29302717810681783,"score_spread":0.25697840426490165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582353","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":[0.7944744,0.0008306714,0.19882233,0.00050023536,0.0025582993,0.00046942825,0.0000070131696,0.0023139687,0.000023624192],"genre_scores_gemma":[0.7606502,0.000008020535,0.23857749,0.000013238638,0.00034813068,0.00014586211,0.0000017457304,0.00006310101,0.00019216725],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985873,0.0000028513066,0.00022076671,0.00042945764,0.00040716722,0.00035243251],"domain_scores_gemma":[0.9983896,0.0008546669,0.000057383924,0.00047407523,0.0001570162,0.000067272485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047036144,0.00020301744,0.00017526466,0.00034314586,0.00009389409,0.00023199746,0.0017984511,0.000098245444,0.0000016560605],"category_scores_gemma":[0.008045177,0.00016579304,0.00020517211,0.0006736175,0.000022505825,0.0005215806,0.000489644,0.00028377736,0.0000075448515],"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":[0.00035678476,0.000409229,0.043443765,0.01937412,0.0018071408,0.000023462067,0.013748444,0.1682593,0.24055137,0.09262162,0.20201118,0.2173936],"study_design_scores_gemma":[0.0013537449,0.0012882273,0.052955564,0.007649121,0.00018137736,0.00048419347,0.0002872847,0.29400843,0.5829883,0.007508895,0.049051873,0.002242986],"about_ca_topic_score_codex":0.0000021562616,"about_ca_topic_score_gemma":2.8973146e-8,"teacher_disagreement_score":0.34243694,"about_ca_system_score_codex":0.00014080599,"about_ca_system_score_gemma":0.0000423584,"threshold_uncertainty_score":0.9631409},"labels":[],"label_agreement":null},{"id":"W4400582376","doi":"10.1145/3660807","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"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":"Programmer; Interpretability; Computer science; Code (set theory); Programming language; Code generation; Artificial intelligence; Computer security","score_opus":0.01965023609466952,"score_gpt":0.26783801853326755,"score_spread":0.24818778243859804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582376","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":[0.6104708,0.0016844032,0.37735593,0.0017502283,0.0018751314,0.0011568925,0.000049049315,0.005585536,0.00007207042],"genre_scores_gemma":[0.8310743,0.00001166389,0.16778743,0.00009784244,0.00025551475,0.00013740125,0.0000058754395,0.0001138837,0.000516105],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997432,0.000008590702,0.00036572645,0.00066630146,0.0008686239,0.00065879157],"domain_scores_gemma":[0.99834234,0.0003008071,0.00008118109,0.00092779903,0.00020878902,0.00013910193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008278,0.00033633088,0.0002747134,0.00033227782,0.00015193867,0.0005372515,0.003229404,0.00014005108,0.00000908375],"category_scores_gemma":[0.0021419844,0.00024223937,0.0002193672,0.0008456045,0.00003338783,0.0007291116,0.0015154328,0.0006588467,0.0000164669],"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":[0.00007326598,0.001389173,0.07600979,0.014677241,0.001977617,0.00021057112,0.04138445,0.16062303,0.2651814,0.21730806,0.13075513,0.09041028],"study_design_scores_gemma":[0.0011629695,0.0005230195,0.00708634,0.0030106748,0.00009922574,0.00009254235,0.0002615474,0.9355762,0.029164985,0.0056150104,0.01555103,0.0018564486],"about_ca_topic_score_codex":0.000010072692,"about_ca_topic_score_gemma":6.434004e-7,"teacher_disagreement_score":0.7749532,"about_ca_system_score_codex":0.00015377458,"about_ca_system_score_gemma":0.00004558481,"threshold_uncertainty_score":0.9878235},"labels":[],"label_agreement":null},{"id":"W4400582478","doi":"10.1145/3660793","title":"Towards Better Graph Neural Network-Based Fault Localization through Enhanced Code Representation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"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 Manitoba; University of Alberta; Concordia University","funders":"","keywords":"Computer science; Debugging; Graph; Scalability; Inference; Software; Theoretical computer science; Leverage (statistics); Autoencoder; Artificial neural network; Software quality; Artificial intelligence; Data mining; Programming language; Software development","score_opus":0.019653216969188467,"score_gpt":0.27197463634407953,"score_spread":0.25232141937489105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582478","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":[0.11656399,0.00033247378,0.87743384,0.0017125163,0.001491793,0.00041477816,0.000008302581,0.0020003018,0.000042028736],"genre_scores_gemma":[0.8770798,0.0000131612815,0.12204669,0.0003536016,0.00027326884,0.00010218287,0.0000054516836,0.000071650604,0.000054201308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767166,0.000010100488,0.0003604126,0.00060988637,0.0008517644,0.0004961767],"domain_scores_gemma":[0.9981083,0.00058485,0.0000852731,0.000848885,0.0002906769,0.00008199164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003372408,0.00029325215,0.00025287867,0.00021360435,0.00009525081,0.00029610674,0.0026304678,0.00013160313,0.000008111674],"category_scores_gemma":[0.004571851,0.00023695876,0.00019556038,0.0020856876,0.000053388703,0.0006992497,0.0006944199,0.00044643492,0.000013657988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029791947,0.00006018113,0.00839452,0.00081152923,0.00010787778,0.0000067936144,0.00081892096,0.9470956,0.0039628088,0.006555757,0.021412233,0.010744041],"study_design_scores_gemma":[0.00051142095,0.00022870781,0.013109688,0.0009866707,0.000037734353,0.000016876396,0.000010382511,0.7987227,0.17572454,0.005049581,0.004928341,0.00067340716],"about_ca_topic_score_codex":0.000013626493,"about_ca_topic_score_gemma":4.2945572e-7,"teacher_disagreement_score":0.7605158,"about_ca_system_score_codex":0.000118971904,"about_ca_system_score_gemma":0.00005792701,"threshold_uncertainty_score":0.96628976},"labels":[],"label_agreement":null},{"id":"W4400582740","doi":"10.1145/3643759","title":"Understanding and Detecting Annotation-Induced Faults of Static Analyzers","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"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","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence","score_opus":0.05424952230509408,"score_gpt":0.25652039502094065,"score_spread":0.20227087271584657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582740","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":[0.71253705,0.00016105373,0.2813063,0.00037567885,0.00032418594,0.00020219108,0.0000037565899,0.0050496133,0.000040210565],"genre_scores_gemma":[0.81972224,0.0000036669683,0.18020669,0.000021320913,0.000016252006,0.0000075035737,1.4335247e-7,0.000016797969,0.0000054247475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990235,0.0000037166355,0.00024297155,0.0002707667,0.00028279005,0.00017627455],"domain_scores_gemma":[0.99868834,0.00073930336,0.00011205148,0.0003133069,0.000102751255,0.000044223503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036725475,0.00014663323,0.00017408421,0.0002653476,0.000061551524,0.000082571605,0.0009067489,0.00005312228,5.5340513e-7],"category_scores_gemma":[0.005813382,0.00011516182,0.00006311793,0.0007721891,0.000030222312,0.00026519733,0.00039893264,0.00018951348,4.946142e-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":[0.00014641382,0.0004489607,0.23882113,0.028307844,0.0013364188,0.000048674123,0.049691744,0.012731254,0.18484172,0.2829949,0.03413437,0.16649657],"study_design_scores_gemma":[0.00068152405,0.0009246173,0.023599628,0.008466234,0.00014830672,0.00013806908,0.00029657412,0.5341299,0.25423193,0.1759917,0.00013447549,0.0012570078],"about_ca_topic_score_codex":0.000013385014,"about_ca_topic_score_gemma":2.0551543e-7,"teacher_disagreement_score":0.52139866,"about_ca_system_score_codex":0.00007372833,"about_ca_system_score_gemma":0.000027708871,"threshold_uncertainty_score":0.69595814},"labels":[],"label_agreement":null},{"id":"W4400582781","doi":"10.1145/3643775","title":"Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","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":"Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Code (set theory); Distillation; Artificial intelligence; Machine learning; Programming language; Engineering; Chemistry; Chromatography","score_opus":0.013152326303382412,"score_gpt":0.2774240932908377,"score_spread":0.2642717669874553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582781","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":[0.4102978,0.047868043,0.5322793,0.002083475,0.001730587,0.0021698235,0.00003915747,0.0033412685,0.00019054953],"genre_scores_gemma":[0.98901784,0.00016697998,0.010333331,0.000021635482,0.000093765826,0.000069056325,0.0000013236622,0.00005696795,0.00023910256],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982295,0.000010627809,0.00036056252,0.00043435476,0.00062177924,0.0003431991],"domain_scores_gemma":[0.99679786,0.0017009362,0.00018027227,0.0007565554,0.0004935979,0.000070771464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00080981007,0.00025349768,0.00029649024,0.00016245212,0.00011241909,0.00020452087,0.0030729382,0.000071789094,0.000004028885],"category_scores_gemma":[0.016258514,0.00014719975,0.00013659477,0.0014284304,0.000101417325,0.00044239717,0.0011065761,0.0006458196,0.000008558858],"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":[0.00022613321,0.0005144976,0.33489877,0.14038596,0.001672386,0.000044981465,0.013031376,0.19010907,0.0444808,0.07874799,0.023054078,0.17283396],"study_design_scores_gemma":[0.0014213256,0.001555452,0.17877112,0.05703035,0.00036857405,0.00024746897,0.00009107517,0.6117726,0.106105275,0.00065710535,0.039512865,0.0024668067],"about_ca_topic_score_codex":0.000010462984,"about_ca_topic_score_gemma":3.4073426e-7,"teacher_disagreement_score":0.57872003,"about_ca_system_score_codex":0.000102798884,"about_ca_system_score_gemma":0.00009954267,"threshold_uncertainty_score":0.99202794},"labels":[],"label_agreement":null},{"id":"W4400582900","doi":"10.1145/3643774","title":"AI-Assisted Code Authoring at Scale: Fine-Tuning, Deploying, and Mixed Methods Evaluation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","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":"Concordia University","funders":"","keywords":"Computer science; Code (set theory); Scale (ratio); Programming language; Geography; Cartography","score_opus":0.033052256068704086,"score_gpt":0.3336914157279161,"score_spread":0.300639159659212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582900","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":[0.72985804,0.0028800261,0.25730544,0.002791657,0.0028566066,0.000805959,0.000012313234,0.003440643,0.000049311006],"genre_scores_gemma":[0.56581396,0.00001919927,0.43346608,0.000072390234,0.00012918847,0.00014579883,0.0000017212867,0.000098872704,0.00025283205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739194,0.000029286868,0.00037671745,0.00071917934,0.0009884275,0.0004944491],"domain_scores_gemma":[0.9970219,0.0014797597,0.0000910207,0.0008599635,0.00037308072,0.00017426693],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023766295,0.00033361238,0.00031381936,0.00043833238,0.0001531856,0.00033571743,0.0023463666,0.0001561023,0.000010968669],"category_scores_gemma":[0.016682604,0.00027426032,0.00013854924,0.0012881728,0.00005999302,0.0005159121,0.0024270643,0.000583661,0.000010767024],"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":[0.00008696741,0.00022423275,0.114859186,0.005965244,0.0008011685,0.000023050567,0.004897834,0.014470154,0.19128998,0.010696683,0.09615499,0.56053054],"study_design_scores_gemma":[0.0006662304,0.00021602548,0.18596266,0.0018567168,0.00012962555,0.00018863335,0.000020366106,0.5986962,0.19507994,0.0015053084,0.014771065,0.0009072429],"about_ca_topic_score_codex":0.000008301429,"about_ca_topic_score_gemma":0.000001712784,"teacher_disagreement_score":0.584226,"about_ca_system_score_codex":0.0003396593,"about_ca_system_score_gemma":0.0000790669,"threshold_uncertainty_score":0.999971},"labels":[],"label_agreement":null},{"id":"W4400582940","doi":"10.1145/3660786","title":"Demystifying Invariant Effectiveness for Securing Smart Contracts","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":15,"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 Toronto","funders":"","keywords":"Invariant (physics); Computer security; Business; Computer science; Mathematics; Mathematical physics","score_opus":0.011554233350821282,"score_gpt":0.23141694031818386,"score_spread":0.21986270696736257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582940","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":[0.45492843,0.00064921344,0.5390121,0.0020359815,0.00070174196,0.0009223444,0.000010982074,0.001690761,0.00004849081],"genre_scores_gemma":[0.9174248,0.000005320217,0.082215525,0.000041122832,0.00004301499,0.0002406073,3.5090414e-7,0.000019422063,0.0000098345345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999111,0.0000025642903,0.00017205445,0.00034554282,0.00014239289,0.00022642582],"domain_scores_gemma":[0.9987534,0.00058621273,0.000054871725,0.00045611727,0.00011132561,0.000038070382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005070938,0.0001460344,0.00017193817,0.00013314342,0.00009679439,0.00009761976,0.0019438954,0.00011381631,5.706247e-7],"category_scores_gemma":[0.0021461628,0.00011286054,0.000102980135,0.00047269833,0.000028455182,0.00017889378,0.0005924145,0.0002523637,0.0000032166329],"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":[0.000017211003,0.00007052687,0.001476819,0.0014727935,0.000114367176,0.000001557441,0.00042978162,0.00066540873,0.017993245,0.9667375,0.0008051776,0.010215609],"study_design_scores_gemma":[0.00090067677,0.0002872619,0.02195821,0.0025203528,0.00008629558,0.00009948556,0.000025227946,0.25131208,0.5620305,0.13792871,0.021979973,0.0008712331],"about_ca_topic_score_codex":0.0000036861786,"about_ca_topic_score_gemma":2.530672e-7,"teacher_disagreement_score":0.8288088,"about_ca_system_score_codex":0.000056995992,"about_ca_system_score_gemma":0.000026936541,"threshold_uncertainty_score":0.46023193},"labels":[],"label_agreement":null},{"id":"W4400582991","doi":"10.1145/3643771","title":"RavenBuild: Context, Relevance, and Dependency Aware Build Outcome Prediction","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada); University of Waterloo","funders":"","keywords":"Relevance (law); Dependency (UML); Outcome (game theory); Context (archaeology); Computer science; Data science; Artificial intelligence; History; Political science; Mathematics","score_opus":0.009439507259860338,"score_gpt":0.22651776080869815,"score_spread":0.2170782535488378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582991","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":[0.89756477,0.003408414,0.08652608,0.002187717,0.0056376047,0.0010362453,0.000047101752,0.0034485136,0.00014352264],"genre_scores_gemma":[0.9835694,0.00006490818,0.015845664,0.00008515114,0.00014512979,0.00004601099,6.0255144e-7,0.0000288397,0.0002143264],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984381,0.0000043517657,0.00036610282,0.0004872209,0.00043150017,0.00027271075],"domain_scores_gemma":[0.99877363,0.00024759004,0.00008685184,0.0006509208,0.00015788803,0.00008313355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043584444,0.00023460564,0.00026590563,0.00016615035,0.00009758412,0.0001457691,0.0015954146,0.00013330912,0.0000032056744],"category_scores_gemma":[0.0020280613,0.00016083772,0.00013227083,0.0005537814,0.00004861235,0.00063168496,0.0007606488,0.00036820266,0.000012708631],"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":[0.000056592005,0.00014737858,0.8439011,0.007275922,0.0002606649,0.000010595487,0.0022582926,0.0010983195,0.0024568068,0.03685208,0.02035125,0.08533101],"study_design_scores_gemma":[0.0034684972,0.002048707,0.5299287,0.012096887,0.00034216483,0.0010225013,0.00036448092,0.19099517,0.062473264,0.023313183,0.17026691,0.0036795307],"about_ca_topic_score_codex":0.000008970777,"about_ca_topic_score_gemma":4.7431453e-7,"teacher_disagreement_score":0.31397238,"about_ca_system_score_codex":0.00008668735,"about_ca_system_score_gemma":0.000037252652,"threshold_uncertainty_score":0.6558772},"labels":[],"label_agreement":null},{"id":"W4400583026","doi":"10.1145/3660780","title":"Do Words Have Power? Understanding and Fostering Civility in Code Review Discussion","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Legal Education and Practice Innovations","field":"Social Sciences","cited_by":7,"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 Saskatchewan","funders":"","keywords":"Civility; Power (physics); Code (set theory); Sociology; Political science; Psychology; Computer science; Programming language; Law; Politics","score_opus":0.0743767049240331,"score_gpt":0.3572547891152694,"score_spread":0.28287808419123633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400583026","genre_codex":"commentary","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":[0.45128775,0.03730436,0.0026646466,0.46360862,0.0070494195,0.00348144,0.00007850154,0.001691447,0.0328338],"genre_scores_gemma":[0.99750715,0.0009017914,0.0010658812,0.00022933671,0.000055232704,0.000018523442,5.1465304e-7,0.000013001978,0.00020859145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992168,0.00000903263,0.00020145554,0.0001729293,0.0002513514,0.000148453],"domain_scores_gemma":[0.9993905,0.00030292667,0.00006384426,0.0001393052,0.00005731957,0.00004610714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010176377,0.000087047105,0.0001230207,0.00010742656,0.000112905385,0.00015934107,0.0003468877,0.0000518246,0.000036232406],"category_scores_gemma":[0.012476346,0.00005660425,0.000038943675,0.00062852097,0.000053149113,0.00049287436,0.00021576976,0.0003308739,0.0000019858037],"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":[0.00007808614,0.0002898181,0.10289557,0.014108812,0.00013079497,0.00000461772,0.13324533,0.00009661167,0.0019614482,0.6513003,0.0673493,0.02853927],"study_design_scores_gemma":[0.0006900618,0.0001969912,0.03714732,0.04264146,0.00018004689,0.00002156948,0.03627914,0.00056796527,0.0013402586,0.060000032,0.81949896,0.0014361722],"about_ca_topic_score_codex":0.00005900293,"about_ca_topic_score_gemma":0.000026587675,"teacher_disagreement_score":0.7521497,"about_ca_system_score_codex":0.00021505181,"about_ca_system_score_gemma":0.000088904126,"threshold_uncertainty_score":0.995842},"labels":[],"label_agreement":null},{"id":"W4400583149","doi":"10.1145/3643731","title":"Characterizing Python Library Migrations","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"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","score_opus":0.04678773520401621,"score_gpt":0.2944841030300863,"score_spread":0.2476963678260701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400583149","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":[0.972585,0.0005565292,0.003964748,0.011856964,0.0064644404,0.0004125543,0.0001044456,0.0018090043,0.002246309],"genre_scores_gemma":[0.9665345,0.000008569732,0.02541763,0.00029822893,0.00030527383,0.000017594508,0.0000055345504,0.000041374493,0.0073712915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980926,0.0000045048037,0.00038036157,0.00048681357,0.00084161205,0.00019413893],"domain_scores_gemma":[0.9982171,0.00064613,0.00009602682,0.0008923702,0.00008671416,0.00006167428],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010690002,0.00013322219,0.0001525245,0.00037057349,0.00009807192,0.0008898011,0.0028557568,0.00003833182,0.00008035429],"category_scores_gemma":[0.01163085,0.00008299986,0.00014568945,0.0015428115,0.000033664615,0.000669364,0.0015135917,0.0001740776,0.00014816853],"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":[0.000014567276,0.00006278123,0.009309497,0.00019350382,0.000055842534,0.0000031055174,0.0011932406,0.00080233376,0.006448881,0.020323193,0.91050446,0.051088568],"study_design_scores_gemma":[0.00011066726,0.00006053866,0.039094295,0.00066744874,0.000029450246,0.000011996912,0.00020344488,0.020897035,0.018942237,0.0076962663,0.9119629,0.00032371923],"about_ca_topic_score_codex":0.0000017499843,"about_ca_topic_score_gemma":1.0833611e-7,"teacher_disagreement_score":0.050764848,"about_ca_system_score_codex":0.000017577588,"about_ca_system_score_gemma":0.000022191402,"threshold_uncertainty_score":0.9966946},"labels":[],"label_agreement":null},{"id":"W4411449683","doi":"10.1145/3729343","title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"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":"Computer science; Robustness (evolution); Artificial intelligence; Software deployment; Machine learning; Generative grammar; Human–computer interaction; Software engineering","score_opus":0.04418603467234083,"score_gpt":0.3291355321729803,"score_spread":0.28494949750063947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449683","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":[0.3871718,0.000057672307,0.6110937,0.0007001637,0.00013141213,0.00045827407,7.020895e-7,0.00034149666,0.00004478878],"genre_scores_gemma":[0.58904624,5.4545256e-7,0.41080588,0.000033645487,0.000017583965,0.000057237598,4.0385464e-7,0.000009129562,0.000029332574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917954,0.0000036163876,0.00020524728,0.00028743927,0.00017330084,0.00015087484],"domain_scores_gemma":[0.99860644,0.0006514203,0.00014125025,0.00035308246,0.0002192228,0.000028564698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033410275,0.0001247346,0.00012991665,0.00013148425,0.00014733266,0.000091021095,0.0008393736,0.000051267325,3.247624e-7],"category_scores_gemma":[0.00822916,0.00010608372,0.000040526338,0.00048039033,0.0000132901505,0.0002913797,0.00045700296,0.00015365338,6.639933e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008842745,0.000034660447,0.008937951,0.00039473694,0.000021530504,3.942682e-8,0.00038035586,0.8999712,0.02028123,0.019939335,0.00010736671,0.049922757],"study_design_scores_gemma":[0.00017373954,0.00005467214,0.050868023,0.0002057838,0.0000143988955,0.0000023533569,0.00000928476,0.93895227,0.002071254,0.0075522256,0.0000064642936,0.00008953584],"about_ca_topic_score_codex":0.000033813452,"about_ca_topic_score_gemma":2.4831306e-7,"teacher_disagreement_score":0.20187442,"about_ca_system_score_codex":0.000050075174,"about_ca_system_score_gemma":0.000018611143,"threshold_uncertainty_score":0.9851667},"labels":[],"label_agreement":null},{"id":"W4411449687","doi":"10.1145/3715730","title":"Towards Diverse Program Transformations for Program Simplification","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"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; Concordia University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Program comprehension; Computer science; Source lines of code; Program transformation; Maintainability; Program slicing; Programming language; Heuristics; Software engineering; Set (abstract data type); Code (set theory); Static program analysis; Program analysis; Software; Source code; Software maintenance; Software quality; Software system; Software development; Operating system","score_opus":0.01895505048035933,"score_gpt":0.29468973969045453,"score_spread":0.2757346892100952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449687","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":[0.18066841,0.00023694574,0.7960631,0.0054021254,0.001609351,0.007965228,0.000051995034,0.007654848,0.00034796615],"genre_scores_gemma":[0.41936827,0.000011562289,0.5783073,0.000066783214,0.000053793803,0.0019993666,0.0000047641192,0.000030513953,0.00015771686],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985519,0.000002833096,0.00030619826,0.00034314088,0.00040040744,0.00039551087],"domain_scores_gemma":[0.99824625,0.0003846003,0.00008100236,0.0007390422,0.00047387456,0.000075204356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003432928,0.0002102608,0.00020615179,0.00030250952,0.00013503272,0.00016694906,0.003441374,0.00010587177,0.0000013944264],"category_scores_gemma":[0.007989948,0.00017139278,0.00018376463,0.0013064725,0.000042150787,0.0004015932,0.000533277,0.00024160376,0.0000036608626],"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":[0.00007526583,0.001127891,0.013190517,0.0030635193,0.00029991835,5.0402946e-7,0.0013646755,0.005959195,0.0025068722,0.122991525,0.027592473,0.82182765],"study_design_scores_gemma":[0.0043001254,0.0022966447,0.2860336,0.0018983925,0.00020694167,0.000020846817,0.00017231642,0.23139785,0.18699124,0.015747195,0.26890194,0.0020329226],"about_ca_topic_score_codex":0.000003830884,"about_ca_topic_score_gemma":2.1587462e-7,"teacher_disagreement_score":0.8197947,"about_ca_system_score_codex":0.00011999216,"about_ca_system_score_gemma":0.000083878585,"threshold_uncertainty_score":0.956529},"labels":[],"label_agreement":null},{"id":"W4411449706","doi":"10.1145/3715738","title":"Code Change Intention, Development Artifact, and History Vulnerability: Putting Them Together for Vulnerability Fix Detection by LLM","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Computer science; Vulnerability (computing); Artifact (error); Commit; Context (archaeology); Leverage (statistics); Computer security; Vulnerability assessment; Data science; Artificial intelligence; Database; Psychology","score_opus":0.038219735064336666,"score_gpt":0.2594014123250999,"score_spread":0.2211816772607632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449706","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":[0.6530005,0.0005167407,0.34247905,0.0010363925,0.000981458,0.0011012373,0.000008475135,0.00085711986,0.000019046907],"genre_scores_gemma":[0.8904627,0.0000074396653,0.10834736,0.00014276842,0.000050401828,0.00060494215,0.0000014771691,0.00003761493,0.00034527428],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982727,0.0000109263465,0.00037852916,0.0005808233,0.00036332602,0.00039365338],"domain_scores_gemma":[0.9978257,0.0009249301,0.0001225442,0.00063588336,0.00040502328,0.00008595295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011690158,0.000260717,0.0002720043,0.00017738741,0.00014977013,0.000074711876,0.0015584595,0.00012610531,0.000005066332],"category_scores_gemma":[0.01486755,0.00022206428,0.000099665725,0.00041785854,0.00006376025,0.0003522431,0.0009327996,0.00036056602,0.000002231002],"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":[0.00022427335,0.00096795807,0.34759393,0.0072151455,0.0005646824,0.0000010139037,0.008290502,0.00066272926,0.06918216,0.0055473316,0.026340172,0.5334101],"study_design_scores_gemma":[0.0018584558,0.0004221822,0.19151464,0.0011795089,0.00006577527,0.00001953657,0.00009750067,0.035355043,0.612747,0.004950703,0.15048015,0.001309497],"about_ca_topic_score_codex":0.000016574573,"about_ca_topic_score_gemma":0.000001963015,"teacher_disagreement_score":0.54356486,"about_ca_system_score_codex":0.00059795234,"about_ca_system_score_gemma":0.000054370736,"threshold_uncertainty_score":0.9934306},"labels":[],"label_agreement":null},{"id":"W4411449748","doi":"10.1145/3715735","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Calgary","funders":"","keywords":"Recall; Computer science; Margin (machine learning); Cognitive psychology; Psychology; Artificial intelligence; Machine learning","score_opus":0.00800568433846788,"score_gpt":0.20890885471749607,"score_spread":0.2009031703790282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449748","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":[0.2859885,0.00006599667,0.71296847,0.00038047793,0.00009912989,0.00014882107,7.8593524e-7,0.0001723813,0.0001754253],"genre_scores_gemma":[0.86606866,0.000001405243,0.13368972,0.000046416542,0.000010087296,0.000026105236,2.0672849e-7,0.0000070416204,0.00015033523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992983,0.0000029205673,0.00015783051,0.0002095511,0.00018739115,0.00014401275],"domain_scores_gemma":[0.9994018,0.00005874653,0.000065029286,0.00036557403,0.000092363734,0.000016470487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023457635,0.00009569502,0.000110357665,0.00023965171,0.00004339164,0.00003424868,0.0009122883,0.000051787545,8.93768e-7],"category_scores_gemma":[0.0007983778,0.00007314536,0.00003282861,0.0006994802,0.0000065959744,0.0003993611,0.0003016699,0.00018858085,0.0000011540582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038885573,0.00021252094,0.019377256,0.00041222732,0.000096806994,0.0000023456964,0.004469331,0.599224,0.0088293925,0.3446894,0.00016561603,0.022482222],"study_design_scores_gemma":[0.0004130699,0.00003208543,0.01438171,0.00024586878,0.000012685245,0.0000030273845,0.00004000212,0.9647879,0.01565256,0.004211365,0.00008794199,0.00013176915],"about_ca_topic_score_codex":0.000014832188,"about_ca_topic_score_gemma":0.000009156996,"teacher_disagreement_score":0.5800802,"about_ca_system_score_codex":0.00007704931,"about_ca_system_score_gemma":0.000020162477,"threshold_uncertainty_score":0.29827812},"labels":[],"label_agreement":null},{"id":"W4411449758","doi":"10.1145/3715734","title":"An Empirical Study on Release-Wise Refactoring Patterns","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Code refactoring; Computer science; Cohesion (chemistry); Quality (philosophy); Software deployment; Java; Code (set theory); Software evolution; Software engineering; Software; Programming language; Software system","score_opus":0.023231487738195986,"score_gpt":0.30415486897821586,"score_spread":0.28092338124001986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449758","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":[0.981299,0.000025354915,0.015861344,0.00045537096,0.00070959626,0.0004891031,0.0000047075864,0.0011217238,0.000033844346],"genre_scores_gemma":[0.9891634,0.000002712782,0.010382534,0.00012717462,0.000088460365,0.00007816971,5.0260087e-7,0.00004374748,0.00011330197],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975932,0.00001362295,0.00035785508,0.00069132686,0.00084225455,0.00050169317],"domain_scores_gemma":[0.99688315,0.0008139032,0.000089926965,0.0018102467,0.00024782083,0.00015493717],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005131148,0.00033477586,0.00032927011,0.0004681294,0.00011533172,0.00018137526,0.0056952145,0.00011522361,0.0000034640425],"category_scores_gemma":[0.010491327,0.0002643983,0.00013123846,0.001220412,0.000023967266,0.00037107783,0.0014231991,0.0006745425,0.000011991978],"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":[0.000032877622,0.0005602563,0.9892676,0.0001760389,0.00007751488,0.0000062790914,0.0007952459,0.0033394776,0.0011012749,0.0008456444,0.0015518817,0.0022459314],"study_design_scores_gemma":[0.00054590654,0.0006530733,0.9749548,0.0003995698,0.00001576347,0.000003944385,0.00007039126,0.0033358952,0.018835576,0.00017104557,0.00067298475,0.00034104017],"about_ca_topic_score_codex":0.0000134021775,"about_ca_topic_score_gemma":4.0007885e-7,"teacher_disagreement_score":0.0177343,"about_ca_system_score_codex":0.00020321865,"about_ca_system_score_gemma":0.00005875786,"threshold_uncertainty_score":0.9999808},"labels":[],"label_agreement":null},{"id":"W4411449759","doi":"10.1145/3715736","title":"One-for-All Does Not Work! Enhancing Vulnerability Detection by Mixture-of-Experts (MoE)","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Vulnerability (computing); Computer science; Task (project management); Artificial intelligence; Baseline (sea); Deep learning; Machine learning; Code (set theory); Computer security; Engineering; Biology","score_opus":0.008965197819905181,"score_gpt":0.24284575727169933,"score_spread":0.23388055945179415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449759","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":[0.23980106,0.000070502836,0.75754577,0.0007924061,0.001043674,0.00036390586,0.000003960476,0.00034620732,0.000032490443],"genre_scores_gemma":[0.8544341,0.0000028831798,0.14517334,0.00012923287,0.000064740605,0.000052431213,5.765787e-7,0.00002040538,0.00012232977],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848175,0.000010400625,0.00040608572,0.00045521668,0.00034656763,0.00029998994],"domain_scores_gemma":[0.9981262,0.00064252794,0.00025377376,0.0006631604,0.0002664887,0.000047849546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006319942,0.00022423336,0.00032740645,0.00015410031,0.00011731363,0.0000610629,0.0023856834,0.00014433988,0.0000018065572],"category_scores_gemma":[0.011239552,0.00017344308,0.00016364605,0.00062603055,0.000045366774,0.00030446475,0.00094544515,0.0003491605,5.1435643e-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":[0.00045722284,0.00045375,0.02149784,0.0030300557,0.00046989307,4.1874193e-7,0.003641606,0.04927856,0.7814587,0.016167693,0.0025727658,0.1209715],"study_design_scores_gemma":[0.00040167975,0.00008615879,0.0027669992,0.00038936423,0.000034193916,7.3620487e-7,0.000024184905,0.015580039,0.97700626,0.0019790677,0.0014478408,0.00028348464],"about_ca_topic_score_codex":0.000016425007,"about_ca_topic_score_gemma":0.0000013314755,"teacher_disagreement_score":0.61463296,"about_ca_system_score_codex":0.00012781782,"about_ca_system_score_gemma":0.000026235779,"threshold_uncertainty_score":0.9970892},"labels":[],"label_agreement":null},{"id":"W4411449762","doi":"10.1145/3729346","title":"CAShift: Benchmarking Log-Based Cloud Attack Detection under Normality Shift","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":2,"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":"Cloud computing; Computer science; Normality; Benchmarking; Data mining; Construct (python library); Paradigm shift; Anomaly detection; Statistics; Mathematics; Operating system","score_opus":0.010564947580602788,"score_gpt":0.23294926959823797,"score_spread":0.2223843220176352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449762","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":[0.76407754,0.00008985312,0.23100261,0.0009985976,0.002594907,0.0004010533,0.0000037020036,0.00070909224,0.000122668],"genre_scores_gemma":[0.9816473,0.0000024047827,0.017800173,0.00032093906,0.00013578979,0.00004191617,5.2297094e-7,0.000015761558,0.00003519153],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828464,0.000010817754,0.00042923426,0.0004768244,0.00042703407,0.00037147602],"domain_scores_gemma":[0.99821764,0.00028865467,0.00019560044,0.0010142964,0.0002171382,0.000066688895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069991173,0.00026781723,0.00030425497,0.000200715,0.00019345463,0.000105757375,0.0025780364,0.00017734682,0.0000036730441],"category_scores_gemma":[0.0015434036,0.00020166564,0.00020817634,0.001062542,0.000059343063,0.0003690622,0.00083017955,0.00037699382,0.00000884695],"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":[0.00031575517,0.0008555728,0.7367319,0.008007373,0.0005128801,0.0000042944525,0.0021907415,0.16404946,0.004330539,0.035206284,0.00990606,0.037889127],"study_design_scores_gemma":[0.001415369,0.00036197877,0.774841,0.0015824926,0.000080010584,0.000013583032,0.00004093252,0.08240513,0.12884507,0.004439272,0.0049600583,0.0010150917],"about_ca_topic_score_codex":0.000032497857,"about_ca_topic_score_gemma":0.0000043459727,"teacher_disagreement_score":0.21756978,"about_ca_system_score_codex":0.00020335718,"about_ca_system_score_gemma":0.00008664463,"threshold_uncertainty_score":0.82236856},"labels":[],"label_agreement":null},{"id":"W4411449776","doi":"10.1145/3715766","title":"Automated and Accurate Token Transfer Identification and Its Applications in Cryptocurrency Security","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Blockchain Technology Applications and Security","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 Guelph","funders":"","keywords":"Security token; Computer science; Computer security; Cryptocurrency; Exploit; Identification (biology); False positive paradox; Artificial intelligence","score_opus":0.006555163432256633,"score_gpt":0.23174639618428244,"score_spread":0.22519123275202582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449776","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":[0.9645209,0.00062305626,0.03155857,0.0018404279,0.000054026375,0.00064589636,0.00000859433,0.00071597175,0.00003257471],"genre_scores_gemma":[0.99547577,0.00007348859,0.0041793,0.00003081496,0.000004277676,0.00021963897,7.339472e-7,0.0000048438405,0.000011143698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99928325,0.0000026749788,0.00021518627,0.00028652715,0.000086173735,0.00012618175],"domain_scores_gemma":[0.99938536,0.00009421144,0.000043758944,0.0003527199,0.00009925389,0.000024700515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018012394,0.00011007459,0.00012821876,0.00018033531,0.000077768826,0.000045496043,0.0010897836,0.00009863202,3.89418e-7],"category_scores_gemma":[0.00050039846,0.00009370641,0.000022268174,0.0007897673,0.00003529967,0.00016291012,0.0003945638,0.0001894897,6.248056e-7],"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":[0.0000056522076,0.00015620154,0.014293332,0.0005177885,0.000029309986,1.1155349e-7,0.0010363566,0.00008867094,0.0072750486,0.9701829,0.00047352508,0.0059411093],"study_design_scores_gemma":[0.0011284227,0.00007228234,0.39237624,0.00046226822,0.000051208503,0.000011424283,0.00010985146,0.3320861,0.15341382,0.11475786,0.0048599895,0.00067055604],"about_ca_topic_score_codex":0.0000038093765,"about_ca_topic_score_gemma":0.0000011714774,"teacher_disagreement_score":0.85542506,"about_ca_system_score_codex":0.000021857926,"about_ca_system_score_gemma":0.000014618482,"threshold_uncertainty_score":0.38212365},"labels":[],"label_agreement":null},{"id":"W4411449886","doi":"10.1145/3729353","title":"LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":3,"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":"Adversarial system; Computer science; Database transaction; Focus (optics); Software deployment; Computer security; Artificial intelligence; Code (set theory); Semantics (computer science); State (computer science); Machine learning; Database; Programming language; Software engineering","score_opus":0.005683394962144602,"score_gpt":0.21751598185418827,"score_spread":0.21183258689204368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449886","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":[0.58747256,0.0003640179,0.40523833,0.003340648,0.00091451226,0.0007051082,0.0000040143764,0.0014236735,0.0005371361],"genre_scores_gemma":[0.89088696,0.000005270803,0.10877859,0.0001497344,0.000037839505,0.00004459537,3.230474e-7,0.0000104807805,0.0000861778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989306,0.000002777783,0.00027275181,0.00034225086,0.0001857396,0.00026593453],"domain_scores_gemma":[0.998749,0.00017985699,0.00014626097,0.0007243184,0.00016470125,0.000035834135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031379718,0.00016238351,0.00020435013,0.00015895593,0.00013480199,0.00004699087,0.0029529566,0.0001566706,0.0000015592476],"category_scores_gemma":[0.0021998764,0.00013777125,0.000106352156,0.000680963,0.000046346548,0.00015461381,0.0011907021,0.00036262645,0.0000043002474],"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":[0.000054548946,0.00056886533,0.035445586,0.00077149225,0.00034650922,0.0000022000524,0.0008886644,0.0035561253,0.026685191,0.8619467,0.0082728965,0.061461225],"study_design_scores_gemma":[0.0033120676,0.00029507984,0.046115547,0.0017988883,0.00018545146,0.000051274645,0.00009716743,0.16976131,0.5980831,0.13937815,0.03933589,0.0015861136],"about_ca_topic_score_codex":0.000007944622,"about_ca_topic_score_gemma":6.3922016e-7,"teacher_disagreement_score":0.7225686,"about_ca_system_score_codex":0.000055577886,"about_ca_system_score_gemma":0.00003616752,"threshold_uncertainty_score":0.56181484},"labels":[],"label_agreement":null},{"id":"W4411449952","doi":"10.1145/3715729","title":"An Empirical Study of Suppressed Static Analysis Warnings","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"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":"Spectrum analyzer; False positive paradox; Python (programming language); Computer science; Software; Static analysis; Scalability; Empirical research; False positives and false negatives; Code (set theory); Artificial intelligence; Programming language; Statistics; Telecommunications; Operating system; Mathematics","score_opus":0.0138911653291388,"score_gpt":0.29776158001213404,"score_spread":0.28387041468299523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449952","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":[0.9571946,0.000031112973,0.041484572,0.0002578566,0.00018299888,0.00037620467,0.0000042003353,0.00045772342,0.000010692544],"genre_scores_gemma":[0.9678928,0.0000018751026,0.031906173,0.00004057954,0.000016208522,0.00005305267,8.411228e-7,0.000022287499,0.00006617692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977868,0.000016545691,0.00047129378,0.0005270116,0.00082663505,0.0003716904],"domain_scores_gemma":[0.99667907,0.0010586722,0.00016250717,0.0015303898,0.00046523506,0.00010410191],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.00060740317,0.00025409256,0.0005056435,0.00097484747,0.00006790309,0.00009165994,0.0055752317,0.00008831058,0.000005598266],"category_scores_gemma":[0.010735139,0.0002016374,0.00018394177,0.0044642305,0.00004246697,0.00033069347,0.0012973743,0.00038732626,0.0000017398442],"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":[0.00003943681,0.00084064365,0.94174176,0.0003460299,0.0007825406,0.0000018394485,0.0041361745,0.046942584,0.0023461762,0.00041637465,0.0015577137,0.0008486959],"study_design_scores_gemma":[0.00081614184,0.0008439996,0.88407594,0.00015134945,0.00025728313,0.0000016229534,0.00019303175,0.09323194,0.019482257,0.00042672505,0.00017892501,0.00034076942],"about_ca_topic_score_codex":0.000031101285,"about_ca_topic_score_gemma":0.0000010132674,"teacher_disagreement_score":0.057665832,"about_ca_system_score_codex":0.0000807718,"about_ca_system_score_gemma":0.000060204755,"threshold_uncertainty_score":0.9998051},"labels":[],"label_agreement":null},{"id":"W4411450040","doi":"10.1145/3715741","title":"Understanding and Characterizing Mock Assertions in Unit Tests","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Assertion; Test (biology); Testability; Complement (music); Unit testing; Programming language; Control flow; Test case; Software engineering; Reliability engineering; Machine learning; Software","score_opus":0.05208794963468529,"score_gpt":0.26277533769608935,"score_spread":0.21068738806140405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450040","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":[0.87084645,0.00016524862,0.11636051,0.003683979,0.0004753258,0.00043902211,0.0000031739,0.007546982,0.0004792975],"genre_scores_gemma":[0.88893074,0.000007371475,0.11080316,0.00015605707,0.000011402755,0.000021499212,1.6906476e-7,0.000011259167,0.00005833878],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991672,0.0000036480976,0.0002055411,0.0002565745,0.00015677219,0.00021025952],"domain_scores_gemma":[0.99898756,0.0004183603,0.00008183287,0.00040654166,0.00007031894,0.000035364676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028267433,0.00014500513,0.00016830537,0.00033156332,0.000083460625,0.00009827772,0.0013248624,0.000068493064,3.6748258e-7],"category_scores_gemma":[0.005764493,0.00012210176,0.000038891274,0.00090198434,0.000028565162,0.00024727674,0.0008549483,0.00023822686,5.137527e-7],"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":[0.000014628813,0.00012333968,0.84594965,0.0005216215,0.00004285828,0.000002683647,0.00075700274,0.00025732187,0.0075768135,0.1358705,0.005826236,0.00305732],"study_design_scores_gemma":[0.00055878307,0.00013004204,0.7854823,0.0033593532,0.00002103145,0.000026197764,0.000032210777,0.02356692,0.016549528,0.16914651,0.00059386424,0.00053330243],"about_ca_topic_score_codex":0.000011165147,"about_ca_topic_score_gemma":7.725355e-7,"teacher_disagreement_score":0.060467407,"about_ca_system_score_codex":0.00008864116,"about_ca_system_score_gemma":0.000027221618,"threshold_uncertainty_score":0.6901053},"labels":[],"label_agreement":null},{"id":"W4411450091","doi":"10.1145/3715724","title":"CKTyper: Enhancing Type Inference for Java Code Snippets by Leveraging Crowdsourcing Knowledge in Stack Overflow","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"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":"Basic and Applied Basic Research Foundation of Guangdong Province","keywords":"Snippet; Computer science; Crowdsourcing; Context (archaeology); Code (set theory); Inference; Set (abstract data type); Information retrieval; Type inference; Java; Source code; World Wide Web; Artificial intelligence; Programming language","score_opus":0.017235033584320957,"score_gpt":0.2818270580510308,"score_spread":0.2645920244667099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450091","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":[0.7036215,0.0010187824,0.29164302,0.0005169148,0.0015858664,0.0007578067,0.000017430104,0.0007510412,0.0000876227],"genre_scores_gemma":[0.95390755,0.000021579162,0.045337792,0.00007974736,0.00006482063,0.000080478974,0.0000018836715,0.000047662765,0.0004584809],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979707,0.0000074717163,0.00043309663,0.00058288756,0.00037203787,0.00063378876],"domain_scores_gemma":[0.9965248,0.00202112,0.00010678079,0.0008319468,0.0004259704,0.00008935059],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007450132,0.00031295,0.00037562556,0.00045104444,0.00010480533,0.00015677403,0.0034807145,0.00013961956,0.0000034926534],"category_scores_gemma":[0.021861933,0.0002850567,0.000110766996,0.0016101347,0.000034702356,0.00037994413,0.0014638465,0.0005008294,0.000006777636],"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":[0.00034217042,0.0009615664,0.53723174,0.009145144,0.0005048105,0.000007985138,0.00859932,0.08701733,0.20328183,0.02815873,0.10208727,0.022662079],"study_design_scores_gemma":[0.0032291897,0.00053680484,0.071274765,0.006846765,0.000051655956,0.000014093096,0.00015507314,0.18793832,0.69411874,0.0024291421,0.03149749,0.0019079933],"about_ca_topic_score_codex":0.000017376675,"about_ca_topic_score_gemma":0.0000036582678,"teacher_disagreement_score":0.4908369,"about_ca_system_score_codex":0.00029650526,"about_ca_system_score_gemma":0.00016242666,"threshold_uncertainty_score":0.9999602},"labels":[],"label_agreement":null},{"id":"W4411450197","doi":"10.1145/3729363","title":"An Empirical Study of Bugs in Data Visualization Libraries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"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; Hong Kong University of Science and Technology","keywords":"Computer science; Visualization; Data science; Information retrieval; Root cause; Empirical research; Software bug; Key (lock); Data mining; Software; Programming language; Computer security","score_opus":0.03286994685591208,"score_gpt":0.33228897766324655,"score_spread":0.29941903080733445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450197","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":[0.8183854,0.000055846587,0.17984524,0.0005591118,0.00031128438,0.00041356718,0.000023346644,0.00034124037,0.00006496721],"genre_scores_gemma":[0.98011184,0.0000046311043,0.019638414,0.00015717288,0.000014918183,0.0000052307655,0.000009766314,0.000009870613,0.00004816744],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990647,0.0000070287706,0.00029086944,0.00027579156,0.00025378034,0.00010783826],"domain_scores_gemma":[0.9986694,0.00008002779,0.00010427282,0.0010078754,0.00011205229,0.000026373476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025638912,0.000100165285,0.00017029964,0.000243671,0.000027881946,0.00008793456,0.0044226204,0.000040344286,0.0000015433776],"category_scores_gemma":[0.0025807673,0.00007969215,0.000018428149,0.0013379258,0.000019318051,0.0008103819,0.0018387141,0.00008485994,5.090839e-7],"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":[0.000033839067,0.002371673,0.8529526,0.0004913586,0.00008270719,9.085116e-7,0.004528481,0.0050868313,0.00078865286,0.11454258,0.016610213,0.0025101462],"study_design_scores_gemma":[0.0013542187,0.00047346577,0.23776095,0.00050686306,0.00004519745,0.000001386253,0.0007373658,0.74046314,0.011578283,0.0027467806,0.003931174,0.0004011638],"about_ca_topic_score_codex":0.0000076036467,"about_ca_topic_score_gemma":0.0000019434665,"teacher_disagreement_score":0.7353763,"about_ca_system_score_codex":0.000014777693,"about_ca_system_score_gemma":0.00003968494,"threshold_uncertainty_score":0.8218403},"labels":[],"label_agreement":null},{"id":"W4411450220","doi":"10.1145/3715779","title":"Protecting Privacy in Software Logs: What Should Be Anonymized?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Identification (biology); Computer science; Information privacy; Personally identifiable information; Privacy policy; Information sensitivity; Data anonymization; Software; Privacy by Design; Data science; Identifier; Internet privacy; Computer security","score_opus":0.018043817695445535,"score_gpt":0.2513165258656156,"score_spread":0.23327270817017007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450220","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":[0.93641835,0.0009953958,0.048774835,0.0071822936,0.002774548,0.002032044,0.0000043094738,0.0017325027,0.00008571518],"genre_scores_gemma":[0.83984524,0.00007237424,0.15828705,0.0010697171,0.000102770675,0.00031647572,9.268008e-7,0.0000473094,0.00025815234],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99771863,0.000015368734,0.00060530944,0.0006332349,0.0005212837,0.0005061991],"domain_scores_gemma":[0.997616,0.0004984665,0.00022820513,0.0013035823,0.00028459614,0.00006917786],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010648818,0.00034312025,0.00046872828,0.00038060016,0.00015556117,0.00025250073,0.004498183,0.00022410955,0.0000036710328],"category_scores_gemma":[0.012340312,0.00025356578,0.0002000719,0.0016947635,0.000057948546,0.0013230939,0.0021418354,0.0007307274,0.0000054522607],"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":[0.00036137796,0.0011873556,0.7846048,0.0129149,0.00040636785,0.000012960816,0.012479886,0.015338407,0.006129023,0.010172564,0.016309448,0.14008291],"study_design_scores_gemma":[0.011908755,0.0013885605,0.41907892,0.035023138,0.00019273517,0.00014954219,0.0018818058,0.04590895,0.3806573,0.028606083,0.06967791,0.0055263364],"about_ca_topic_score_codex":0.000024851752,"about_ca_topic_score_gemma":0.0000011208548,"teacher_disagreement_score":0.37452826,"about_ca_system_score_codex":0.00020993444,"about_ca_system_score_gemma":0.00011118985,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W4411450398","doi":"10.1145/3729383","title":"Automated Extraction and Analysis of Developer's Rationale in Open Source Software","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","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":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Computer science; Software engineering; Software; Open source; Generalization; Open source software; Data science; Artificial intelligence; Programming language","score_opus":0.015592076908858506,"score_gpt":0.27953756571677185,"score_spread":0.26394548880791335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450398","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":[0.877677,0.0001717351,0.12018077,0.0005078993,0.00018847724,0.0005213725,0.000008416808,0.00071896816,0.000025352856],"genre_scores_gemma":[0.7796457,0.000012875307,0.21995904,0.000051116567,0.000009758817,0.00006307533,0.0000028523764,0.000020117157,0.00023546896],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99859005,0.0000079435085,0.00038666505,0.0003917281,0.00038248146,0.00024115203],"domain_scores_gemma":[0.99790657,0.0010236964,0.00013237931,0.00058373145,0.00030377292,0.000049849194],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005855435,0.000179677,0.00037540056,0.0009983554,0.000054948785,0.00012776777,0.0031106716,0.000098837845,0.000003879977],"category_scores_gemma":[0.014285616,0.00015562901,0.00008454786,0.0039838,0.00003847214,0.00048735473,0.0021287042,0.00024493926,9.596638e-7],"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":[0.000038901384,0.000118302334,0.91255933,0.00046259983,0.0005672689,0.0000012209113,0.00076937844,0.06876693,0.0041823476,0.003887684,0.0017132415,0.0069328165],"study_design_scores_gemma":[0.00034558238,0.000033108146,0.88902044,0.0002809034,0.00005578197,0.0000027284868,0.0000197644,0.09503122,0.014239928,0.00022179073,0.00056747184,0.00018126106],"about_ca_topic_score_codex":0.000054757857,"about_ca_topic_score_gemma":0.000004357475,"teacher_disagreement_score":0.099778265,"about_ca_system_score_codex":0.00011461819,"about_ca_system_score_gemma":0.00009467097,"threshold_uncertainty_score":0.9940175},"labels":[],"label_agreement":null},{"id":"W4411523015","doi":"10.1145/3728876","title":"MoDitector: Module-Directed Testing for Autonomous Driving Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"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":"Root cause; Computer science; Debugging; Reliability (semiconductor); Reliability engineering; Root cause analysis; Process (computing); Scenario testing; Embedded system; Engineering; Artificial intelligence","score_opus":0.016940612286937884,"score_gpt":0.23593435620730108,"score_spread":0.2189937439203632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523015","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":[0.13275772,0.0004229309,0.80849934,0.00066023716,0.0024425348,0.0015386444,0.000014396265,0.05332772,0.00033645696],"genre_scores_gemma":[0.45410925,6.3882254e-7,0.5454134,0.000056540022,0.000064183725,0.00017255283,4.2769975e-7,0.000027252667,0.00015579432],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852234,0.0000049305913,0.00037012761,0.0004607684,0.00026326178,0.0003785629],"domain_scores_gemma":[0.9968408,0.0014537734,0.00022490321,0.0008919362,0.0005292993,0.00005931651],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004636242,0.00026336024,0.00032217565,0.00028673222,0.0001704137,0.00019087442,0.003315284,0.00011651368,2.1041816e-7],"category_scores_gemma":[0.030714579,0.00021678592,0.00012634673,0.001030539,0.000029526185,0.00021106473,0.0010274294,0.0002324453,0.0000010799907],"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":[0.00008711891,0.00071683014,0.32793772,0.007613173,0.0006751289,0.000005445713,0.0013842353,0.074712075,0.028103767,0.14116189,0.3258212,0.091781415],"study_design_scores_gemma":[0.000463924,0.00023712576,0.017684143,0.0026753047,0.0000434567,0.00002356578,0.0000045245624,0.9423926,0.018120522,0.015679559,0.0020843842,0.0005909101],"about_ca_topic_score_codex":0.000025673138,"about_ca_topic_score_gemma":1.3026505e-7,"teacher_disagreement_score":0.8676805,"about_ca_system_score_codex":0.00013816742,"about_ca_system_score_gemma":0.000069179456,"threshold_uncertainty_score":0.97745013},"labels":[],"label_agreement":null},{"id":"W4411523021","doi":"10.1145/3728919","title":"Assessing Scene Generation Techniques for Testing COLREGS-Compliance of Autonomous Surface Vehicles","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Set (abstract data type); Computer science; Logical analysis; Functional requirement; Operations research; Artificial intelligence; Engineering; Software engineering","score_opus":0.04127833120726755,"score_gpt":0.2794976332482037,"score_spread":0.23821930204093617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523021","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":[0.93026835,0.00035419612,0.06469292,0.0003803038,0.00055486156,0.0009954894,0.000034230812,0.0014891013,0.0012305585],"genre_scores_gemma":[0.7124808,0.0000051811735,0.2872811,0.000029286082,0.000047371697,0.000033932687,0.0000028620739,0.000028480334,0.00009100765],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991871,0.0000019817442,0.00034059567,0.00015853124,0.00014014263,0.00017160845],"domain_scores_gemma":[0.99909884,0.00022046144,0.00010065743,0.00022609287,0.0003285738,0.000025384714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025151292,0.00015992476,0.00023203257,0.00007178172,0.000103998966,0.00008172318,0.00051538134,0.00009500582,0.000001521296],"category_scores_gemma":[0.0022801105,0.00014878214,0.00007591161,0.0004130173,0.000035838882,0.00017973021,0.00010722801,0.00014767972,3.7093963e-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":[0.000019689109,0.00006646834,0.011792385,0.0035590832,0.00009601139,1.4739676e-7,0.00010622976,0.099837676,0.83076763,0.0029283552,0.0055136844,0.045312658],"study_design_scores_gemma":[0.0001850508,0.00002743407,0.0042061256,0.00081586896,0.00002175782,0.0000012172934,0.000016494732,0.23048308,0.76266706,0.00024147957,0.0011782786,0.00015617059],"about_ca_topic_score_codex":0.0000073379583,"about_ca_topic_score_gemma":3.3010485e-7,"teacher_disagreement_score":0.22258818,"about_ca_system_score_codex":0.00008784474,"about_ca_system_score_gemma":0.000027074866,"threshold_uncertainty_score":0.6067159},"labels":[],"label_agreement":null},{"id":"W4411523084","doi":"10.1145/3728947","title":"The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Code (set theory); Computer science; Benchmark (surveying); Iterative and incremental development; Code generation; Process (computing); Natural language generation; Natural language; Programming language; Software engineering; Artificial intelligence; Computer security; Geography","score_opus":0.03728653452721785,"score_gpt":0.29708271316430906,"score_spread":0.2597961786370912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523084","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":[0.80170447,0.00066603365,0.19078182,0.0024733308,0.0011745222,0.0021394421,0.00005223846,0.00062007335,0.00038808296],"genre_scores_gemma":[0.99314064,0.000004119664,0.006373598,0.00014519512,0.00006024957,0.00015404986,0.0000036192673,0.000019169409,0.00009933393],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984741,0.00002145925,0.0002088227,0.0002558232,0.0008197862,0.00021998739],"domain_scores_gemma":[0.99769837,0.0007950236,0.00009421659,0.00082405674,0.00056005426,0.000028292498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016708282,0.0001495477,0.0001265205,0.000114237955,0.0001749838,0.00011806727,0.0020688688,0.00005969264,0.0000032782275],"category_scores_gemma":[0.005430353,0.0000874509,0.00005477722,0.0006053236,0.000035339253,0.00020254707,0.0002941588,0.00022515538,0.0000029761134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012804476,0.0004833721,0.0059054457,0.0005372062,0.00025855418,9.450579e-7,0.006495096,0.7683342,0.0066711605,0.1584479,0.03070466,0.02203338],"study_design_scores_gemma":[0.0003684688,0.000090882226,0.004046275,0.00015962603,0.000016735828,6.674866e-7,0.000023477902,0.9609544,0.032221116,0.0006862665,0.001317196,0.00011483267],"about_ca_topic_score_codex":0.00000936921,"about_ca_topic_score_gemma":0.0000039043407,"teacher_disagreement_score":0.19262023,"about_ca_system_score_codex":0.00012138452,"about_ca_system_score_gemma":0.000103986065,"threshold_uncertainty_score":0.6501032},"labels":[],"label_agreement":null},{"id":"W4411523089","doi":"10.1145/3728880","title":"Preventing Disruption of System Backup against Ransomware Attacks","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"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":"Ransomware; Backup; Computer science; Computer security; Encryption; Malware; Operating system","score_opus":0.006109823960931409,"score_gpt":0.22825175233185982,"score_spread":0.22214192837092842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523089","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":[0.18912637,0.0001270105,0.8076087,0.0001523989,0.00060171465,0.000510805,0.000007077139,0.0015399707,0.00032596156],"genre_scores_gemma":[0.77089745,0.000008268624,0.22883427,0.000032448443,0.000024449997,0.00004904149,4.9176305e-7,0.000017166049,0.00013639241],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988107,0.0000050150466,0.00038882243,0.00030485666,0.00028736336,0.00020321312],"domain_scores_gemma":[0.9986105,0.00012136144,0.00027437753,0.0006597498,0.00030194168,0.000032082193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027067875,0.00018087719,0.00026250805,0.00022844734,0.0000688952,0.000034493376,0.0022273497,0.00008961802,5.5146535e-7],"category_scores_gemma":[0.0015907664,0.00015104431,0.00015043204,0.00081534433,0.000029041956,0.0003460918,0.0009103774,0.00020581849,0.0000013620853],"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":[0.00026195016,0.00070293614,0.06304976,0.03231584,0.0006943253,0.000006528801,0.0028201095,0.03407988,0.30526516,0.28745723,0.008251932,0.26509437],"study_design_scores_gemma":[0.0006588065,0.00014754257,0.01142059,0.0057903687,0.000042016953,0.000012427068,0.000121630634,0.021919288,0.9547126,0.0018196402,0.0028604881,0.00049458374],"about_ca_topic_score_codex":0.0000022441222,"about_ca_topic_score_gemma":1.2339368e-7,"teacher_disagreement_score":0.64944744,"about_ca_system_score_codex":0.00011923466,"about_ca_system_score_gemma":0.000022382124,"threshold_uncertainty_score":0.6159408},"labels":[],"label_agreement":null},{"id":"W4411523132","doi":"10.1145/3728931","title":"Understanding Practitioners’ Expectations on Clear Code Review Comments","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"CLARITY; Computer science; Constructive; Relevance (law); Set (abstract data type); Code (set theory); Process (computing); Data science; Code review; Programming language; Software; Software quality; Political science; Software development","score_opus":0.058257941025824454,"score_gpt":0.2989452171374843,"score_spread":0.24068727611165983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523132","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":[0.06549843,0.005820915,0.82476246,0.08133817,0.0058783665,0.0051606037,0.000077196426,0.0071741,0.0042897626],"genre_scores_gemma":[0.8965919,0.00052027556,0.0990971,0.0026889634,0.00008699454,0.0002537169,0.000004135033,0.000080283906,0.00067661016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984232,0.000008602727,0.00029474706,0.00036565558,0.00058974774,0.00031801837],"domain_scores_gemma":[0.9975795,0.0011492708,0.000125146,0.00087763794,0.00019334155,0.00007506645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00036440312,0.00021102805,0.00024751114,0.00031040842,0.00014922094,0.000096745425,0.0027912979,0.000068987836,0.0000066496173],"category_scores_gemma":[0.016067568,0.00017697173,0.00012513273,0.0013195238,0.000035055753,0.0003163391,0.00083076523,0.00043185902,0.000022496235],"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":[0.00008661977,0.0006276143,0.01923393,0.0068110153,0.0005085839,0.0000068403306,0.001347372,0.0074985144,0.0015276159,0.3941097,0.5661851,0.0020570767],"study_design_scores_gemma":[0.012602105,0.0047574905,0.19570008,0.17694806,0.000842144,0.00020556097,0.0020231993,0.06857101,0.17834432,0.061428867,0.28958955,0.008987596],"about_ca_topic_score_codex":0.000002163768,"about_ca_topic_score_gemma":1.538805e-7,"teacher_disagreement_score":0.8310935,"about_ca_system_score_codex":0.0003777571,"about_ca_system_score_gemma":0.000051345425,"threshold_uncertainty_score":0.9922205},"labels":[],"label_agreement":null}]}