{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":36,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":36,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"bd4927a0c0a5","filters":{"venue":"Proceedings of the ACM on software engineering."}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03864211965604995,"gpt":0.2956780983054859,"spread":0.2570359786494359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008599681,0.000259615,0.0002175311,0.0003167557,0.0001192699,0.0003143913,0.00254526,0.0002352793,0.000003881813],"category_scores_gemma":[0.01296562,0.0002220886,0.0001736476,0.0009865756,0.00002707287,0.0004660059,0.0003935065,0.0005386418,0.00001334792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002386038,"about_ca_system_score_gemma":0.00009464208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003298545,"about_ca_topic_score_gemma":6.106878e-7,"domain_scores_codex":[0.9979225,0.000006327022,0.0003847815,0.0005935379,0.0006674491,0.0004254233],"domain_scores_gemma":[0.9975293,0.001054314,0.00009984226,0.0008922251,0.0003288394,0.00009551825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001115108,0.0005969439,0.009687219,0.007389142,0.0005422951,0.000006943785,0.002483192,0.0788905,0.5526459,0.2832226,0.02306916,0.04135454],"study_design_scores_gemma":[0.0003070275,0.0002869369,0.002875742,0.001080704,0.00003348808,0.000007242508,0.000005417576,0.549941,0.4341579,0.006088183,0.004739659,0.0004767287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03672688,0.0002661669,0.9588242,0.001171299,0.00125983,0.0006028322,0.00001169203,0.001133522,0.000003584977],"genre_scores_gemma":[0.5343672,0.000003947498,0.4649608,0.00009698335,0.0002496477,0.0002193616,0.000004476969,0.00005385274,0.00004373034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4976403,"threshold_uncertainty_score":0.9953486,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Code (set theory); Scale (ratio); Programming language; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.03305225606870409,"gpt":0.3336914157279161,"spread":0.300639159659212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00237663,0.0003336124,0.0003138194,0.0004383324,0.0001531856,0.0003357174,0.002346367,0.0001561023,0.00001096867],"category_scores_gemma":[0.0166826,0.0002742603,0.0001385492,0.001288173,0.00005999302,0.0005159121,0.002427064,0.000583661,0.00001076702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003396593,"about_ca_system_score_gemma":0.0000790669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008301429,"about_ca_topic_score_gemma":0.000001712784,"domain_scores_codex":[0.9973919,0.00002928687,0.0003767174,0.0007191793,0.0009884275,0.0004944491],"domain_scores_gemma":[0.9970219,0.00147976,0.0000910207,0.0008599635,0.0003730807,0.0001742669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008696741,0.0002242327,0.1148592,0.005965244,0.0008011685,0.00002305057,0.004897834,0.01447015,0.19129,0.01069668,0.09615499,0.5605305],"study_design_scores_gemma":[0.0006662304,0.0002160255,0.1859627,0.001856717,0.0001296256,0.0001886333,0.00002036611,0.5986962,0.1950799,0.001505308,0.01477106,0.0009072429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.729858,0.002880026,0.2573054,0.002791657,0.002856607,0.000805959,0.00001231323,0.003440643,0.00004931101],"genre_scores_gemma":[0.565814,0.00001919927,0.4334661,0.00007239023,0.0001291885,0.0001457988,0.000001721287,0.0000988727,0.000252832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.584226,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01965321696918847,"gpt":0.2719746363440795,"spread":0.2523214193748911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003372408,0.0002932521,0.0002528787,0.0002136043,0.00009525081,0.0002961067,0.002630468,0.0001316031,0.000008111674],"category_scores_gemma":[0.004571851,0.0002369588,0.0001955604,0.002085688,0.0000533887,0.0006992497,0.0006944199,0.0004464349,0.00001365799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189719,"about_ca_system_score_gemma":0.00005792701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001362649,"about_ca_topic_score_gemma":4.294557e-7,"domain_scores_codex":[0.9976717,0.00001010049,0.0003604126,0.0006098864,0.0008517644,0.0004961767],"domain_scores_gemma":[0.9981083,0.00058485,0.0000852731,0.000848885,0.0002906769,0.00008199164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002979195,0.00006018113,0.00839452,0.0008115292,0.0001078778,0.000006793614,0.000818921,0.9470956,0.003962809,0.006555757,0.02141223,0.01074404],"study_design_scores_gemma":[0.0005114209,0.0002287078,0.01310969,0.0009866707,0.00003773435,0.0000168764,0.00001038251,0.7987227,0.1757245,0.005049581,0.004928341,0.0006734072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.116564,0.0003324738,0.8774338,0.001712516,0.001491793,0.0004147782,0.000008302581,0.002000302,0.00004202874],"genre_scores_gemma":[0.8770798,0.00001316128,0.1220467,0.0003536016,0.0002732688,0.0001021829,0.000005451684,0.0000716506,0.00005420131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7605158,"threshold_uncertainty_score":0.9662898,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Invariant (physics); Computer security; Business; Computer science; Mathematics; Mathematical physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01155423335082128,"gpt":0.2314169403181839,"spread":0.2198627069673626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005070938,0.0001460344,0.0001719382,0.0001331434,0.00009679439,0.00009761976,0.001943895,0.0001138163,5.706247e-7],"category_scores_gemma":[0.002146163,0.0001128605,0.0001029801,0.0004726983,0.00002845518,0.0001788938,0.0005924145,0.0002523637,0.000003216633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005699599,"about_ca_system_score_gemma":0.00002693654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003686179,"about_ca_topic_score_gemma":2.530672e-7,"domain_scores_codex":[0.999111,0.00000256429,0.0001720545,0.0003455428,0.0001423929,0.0002264258],"domain_scores_gemma":[0.9987534,0.0005862127,0.00005487173,0.0004561173,0.0001113256,0.00003807038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000017211,0.00007052687,0.001476819,0.001472794,0.0001143672,0.000001557441,0.0004297816,0.0006654087,0.01799325,0.9667375,0.0008051776,0.01021561],"study_design_scores_gemma":[0.0009006768,0.0002872619,0.02195821,0.002520353,0.00008629558,0.00009948556,0.00002522795,0.2513121,0.5620305,0.1379287,0.02197997,0.0008712331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4549284,0.0006492134,0.5390121,0.002035982,0.000701742,0.0009223444,0.00001098207,0.001690761,0.00004849081],"genre_scores_gemma":[0.9174248,0.000005320217,0.08221553,0.00004112283,0.00004301499,0.0002406073,3.509041e-7,0.00001942206,0.000009834534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8288088,"threshold_uncertainty_score":0.4602319,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00800568433846788,"gpt":0.2089088547174961,"spread":0.2009031703790282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002345763,0.00009569502,0.0001103577,0.0002396517,0.00004339164,0.00003424868,0.0009122883,0.00005178755,8.93768e-7],"category_scores_gemma":[0.0007983778,0.00007314536,0.00003282861,0.0006994802,0.000006595974,0.0003993611,0.0003016699,0.0001885808,0.000001154058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007704931,"about_ca_system_score_gemma":0.00002016248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001483219,"about_ca_topic_score_gemma":0.000009156996,"domain_scores_codex":[0.9992983,0.000002920567,0.0001578305,0.0002095511,0.0001873912,0.0001440128],"domain_scores_gemma":[0.9994018,0.00005874653,0.00006502929,0.000365574,0.00009236373,0.00001647049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003888557,0.0002125209,0.01937726,0.0004122273,0.00009680699,0.000002345696,0.004469331,0.599224,0.008829392,0.3446894,0.000165616,0.02248222],"study_design_scores_gemma":[0.0004130699,0.00003208543,0.01438171,0.0002458688,0.00001268524,0.000003027385,0.00004000212,0.9647879,0.01565256,0.004211365,0.00008794199,0.0001317691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2859885,0.00006599667,0.7129685,0.0003804779,0.00009912989,0.0001488211,7.859352e-7,0.0001723813,0.0001754253],"genre_scores_gemma":[0.8660687,0.000001405243,0.1336897,0.00004641654,0.0000100873,0.00002610524,2.067285e-7,0.00000704162,0.0001503352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5800802,"threshold_uncertainty_score":0.2982781,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01315232630338241,"gpt":0.2774240932908377,"spread":0.2642717669874553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008098101,0.0002534977,0.0002964902,0.0001624521,0.0001124191,0.0002045209,0.003072938,0.00007178909,0.000004028885],"category_scores_gemma":[0.01625851,0.0001471998,0.0001365948,0.00142843,0.0001014173,0.0004423972,0.001106576,0.0006458196,0.000008558858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001027989,"about_ca_system_score_gemma":0.00009954267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001046298,"about_ca_topic_score_gemma":3.407343e-7,"domain_scores_codex":[0.9982295,0.00001062781,0.0003605625,0.0004343548,0.0006217792,0.0003431991],"domain_scores_gemma":[0.9967979,0.001700936,0.0001802723,0.0007565554,0.0004935979,0.00007077146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002261332,0.0005144976,0.3348988,0.140386,0.001672386,0.00004498147,0.01303138,0.1901091,0.0444808,0.07874799,0.02305408,0.172834],"study_design_scores_gemma":[0.001421326,0.001555452,0.1787711,0.05703035,0.0003685741,0.000247469,0.00009107517,0.6117726,0.1061053,0.0006571054,0.03951287,0.002466807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4102978,0.04786804,0.5322793,0.002083475,0.001730587,0.002169824,0.00003915747,0.003341269,0.0001905495],"genre_scores_gemma":[0.9890178,0.00016698,0.01033333,0.00002163548,0.00009376583,0.00006905632,0.000001323662,0.00005696795,0.0002391026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.57872,"threshold_uncertainty_score":0.9920279,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01965023609466952,"gpt":0.2678380185332676,"spread":0.248187782438598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008278,0.0003363309,0.0002747134,0.0003322778,0.0001519387,0.0005372515,0.003229404,0.0001400511,0.00000908375],"category_scores_gemma":[0.002141984,0.0002422394,0.0002193672,0.0008456045,0.00003338783,0.0007291116,0.001515433,0.0006588467,0.0000164669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001537746,"about_ca_system_score_gemma":0.00004558481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001007269,"about_ca_topic_score_gemma":6.434004e-7,"domain_scores_codex":[0.997432,0.000008590702,0.0003657264,0.0006663015,0.0008686239,0.0006587916],"domain_scores_gemma":[0.9983423,0.0003008071,0.00008118109,0.000927799,0.000208789,0.0001391019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007326598,0.001389173,0.07600979,0.01467724,0.001977617,0.0002105711,0.04138445,0.160623,0.2651814,0.2173081,0.1307551,0.09041028],"study_design_scores_gemma":[0.00116297,0.0005230195,0.00708634,0.003010675,0.00009922574,0.00009254235,0.0002615474,0.9355762,0.02916498,0.00561501,0.01555103,0.001856449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6104708,0.001684403,0.3773559,0.001750228,0.001875131,0.001156893,0.00004904931,0.005585536,0.00007207042],"genre_scores_gemma":[0.8310743,0.00001166389,0.1677874,0.00009784244,0.0002555148,0.0001374012,0.000005875439,0.0001138837,0.000516105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7749532,"threshold_uncertainty_score":0.9878235,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009439507259860338,"gpt":0.2265177608086981,"spread":0.2170782535488378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004358444,0.0002346056,0.0002659056,0.0001661503,0.00009758412,0.0001457691,0.001595415,0.0001333091,0.000003205674],"category_scores_gemma":[0.002028061,0.0001608377,0.0001322708,0.0005537814,0.00004861235,0.000631685,0.0007606488,0.0003682027,0.00001270863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008668735,"about_ca_system_score_gemma":0.00003725265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008970777,"about_ca_topic_score_gemma":4.743145e-7,"domain_scores_codex":[0.9984381,0.000004351766,0.0003661028,0.0004872209,0.0004315002,0.0002727107],"domain_scores_gemma":[0.9987736,0.00024759,0.00008685184,0.0006509208,0.000157888,0.00008313355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005659201,0.0001473786,0.8439011,0.007275922,0.0002606649,0.00001059549,0.002258293,0.00109832,0.002456807,0.03685208,0.02035125,0.08533101],"study_design_scores_gemma":[0.003468497,0.002048707,0.5299287,0.01209689,0.0003421648,0.001022501,0.0003644809,0.1909952,0.06247326,0.02331318,0.1702669,0.003679531],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8975648,0.003408414,0.08652608,0.002187717,0.005637605,0.001036245,0.00004710175,0.003448514,0.0001435226],"genre_scores_gemma":[0.9835694,0.00006490818,0.01584566,0.00008515114,0.0001451298,0.00004601099,6.025514e-7,0.0000288397,0.0002143264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3139724,"threshold_uncertainty_score":0.6558772,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0743767049240331,"gpt":0.3572547891152694,"spread":0.2828780841912363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001017638,0.0000870471,0.0001230207,0.0001074266,0.0001129054,0.0001593411,0.0003468877,0.0000518246,0.00003623241],"category_scores_gemma":[0.01247635,0.00005660425,0.00003894368,0.000628521,0.00005314911,0.0004928744,0.0002157698,0.0003308739,0.000001985804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002150518,"about_ca_system_score_gemma":0.00008890413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005900293,"about_ca_topic_score_gemma":0.00002658768,"domain_scores_codex":[0.9992168,0.00000903263,0.0002014555,0.0001729293,0.0002513514,0.000148453],"domain_scores_gemma":[0.9993905,0.0003029267,0.00006384426,0.0001393052,0.00005731957,0.00004610714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007808614,0.0002898181,0.1028956,0.01410881,0.000130795,0.00000461772,0.1332453,0.00009661167,0.001961448,0.6513003,0.0673493,0.02853927],"study_design_scores_gemma":[0.0006900618,0.0001969912,0.03714732,0.04264146,0.0001800469,0.00002156948,0.03627914,0.0005679653,0.001340259,0.06000003,0.819499,0.001436172],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4512877,0.03730436,0.002664647,0.4636086,0.007049419,0.00348144,0.00007850154,0.001691447,0.0328338],"genre_scores_gemma":[0.9975072,0.0009017914,0.001065881,0.0002293367,0.0000552327,0.00001852344,5.14653e-7,0.00001300198,0.0002085914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7521497,"threshold_uncertainty_score":0.995842,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008965197819905181,"gpt":0.2428457572716993,"spread":0.2338805594517941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006319942,0.0002242334,0.0003274065,0.0001541003,0.0001173136,0.0000610629,0.002385683,0.0001443399,0.000001806557],"category_scores_gemma":[0.01123955,0.0001734431,0.0001636461,0.0006260306,0.00004536677,0.0003044647,0.0009454452,0.0003491605,5.143564e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001278178,"about_ca_system_score_gemma":0.00002623578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001642501,"about_ca_topic_score_gemma":0.000001331475,"domain_scores_codex":[0.9984818,0.00001040062,0.0004060857,0.0004552167,0.0003465676,0.0002999899],"domain_scores_gemma":[0.9981262,0.0006425279,0.0002537738,0.0006631604,0.0002664887,0.00004784955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004572228,0.00045375,0.02149784,0.003030056,0.0004698931,4.187419e-7,0.003641606,0.04927856,0.7814587,0.01616769,0.002572766,0.1209715],"study_design_scores_gemma":[0.0004016797,0.00008615879,0.002766999,0.0003893642,0.00003419392,7.362049e-7,0.0000241849,0.01558004,0.9770063,0.001979068,0.001447841,0.0002834846],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2398011,0.00007050284,0.7575458,0.0007924061,0.001043674,0.0003639059,0.000003960476,0.0003462073,0.00003249044],"genre_scores_gemma":[0.8544341,0.00000288318,0.1451733,0.0001292329,0.00006474061,0.00005243121,5.765787e-7,0.00002040538,0.0001223298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.614633,"threshold_uncertainty_score":0.9970892,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04418603467234083,"gpt":0.3291355321729803,"spread":0.2849494975006395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003341027,0.0001247346,0.0001299166,0.0001314843,0.0001473327,0.00009102109,0.0008393736,0.00005126733,3.247624e-7],"category_scores_gemma":[0.00822916,0.0001060837,0.00004052634,0.0004803903,0.00001329015,0.0002913797,0.000457003,0.0001536534,6.639933e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005007517,"about_ca_system_score_gemma":0.00001861114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003381345,"about_ca_topic_score_gemma":2.483131e-7,"domain_scores_codex":[0.9991795,0.000003616388,0.0002052473,0.0002874393,0.0001733008,0.0001508748],"domain_scores_gemma":[0.9986064,0.0006514203,0.0001412502,0.0003530825,0.0002192228,0.0000285647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008842745,0.00003466045,0.008937951,0.0003947369,0.0000215305,3.942682e-8,0.0003803559,0.8999712,0.02028123,0.01993934,0.0001073667,0.04992276],"study_design_scores_gemma":[0.0001737395,0.00005467214,0.05086802,0.0002057838,0.0000143989,0.000002353357,0.00000928476,0.9389523,0.002071254,0.007552226,0.000006464294,0.00008953584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3871718,0.00005767231,0.6110937,0.0007001637,0.0001314121,0.0004582741,7.020895e-7,0.0003414967,0.00004478878],"genre_scores_gemma":[0.5890462,5.454526e-7,0.4108059,0.00003364549,0.00001758397,0.0000572376,4.038546e-7,0.000009129562,0.00002933257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2018744,"threshold_uncertainty_score":0.9851667,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02974556225132802,"gpt":0.2899816002123849,"spread":0.2602360379610569,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001575395,0.000274997,0.0003854605,0.000634501,0.00003899146,0.0002042929,0.004857857,0.0001231927,0.000002058842],"category_scores_gemma":[0.006391706,0.0001788603,0.00009687858,0.002212231,0.00001875031,0.0005716057,0.0007514539,0.0007712991,0.000003729264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001587916,"about_ca_system_score_gemma":0.00009201642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006530012,"about_ca_topic_score_gemma":0.00008046247,"domain_scores_codex":[0.9974391,0.00004103997,0.0005797847,0.000523545,0.001027266,0.0003893038],"domain_scores_gemma":[0.9973766,0.001290693,0.00009112925,0.0009815349,0.0001973322,0.0000627413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000137458,0.002543181,0.833268,0.002234164,0.0002345147,0.0001912115,0.09397201,0.02404136,0.02192445,0.006000877,0.001079428,0.01437328],"study_design_scores_gemma":[0.002984402,0.004365116,0.713203,0.00395612,0.00006688914,0.0002387651,0.01294796,0.171465,0.08743548,0.001589513,0.0002215006,0.001526252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957705,0.0001192982,0.002323915,0.0002616503,0.0004270186,0.000757891,0.000003259892,0.0003228146,0.00001371221],"genre_scores_gemma":[0.9958665,0.000002459091,0.003868946,0.00001757952,0.00006259773,0.0001339362,4.462883e-7,0.00003426092,0.00001321743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1474236,"threshold_uncertainty_score":0.9027188,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05424952230509408,"gpt":0.2565203950209407,"spread":0.2022708727158466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003672547,0.0001466332,0.0001740842,0.0002653476,0.00006155152,0.00008257161,0.0009067489,0.00005312228,5.534051e-7],"category_scores_gemma":[0.005813382,0.0001151618,0.00006311793,0.0007721891,0.00003022231,0.0002651973,0.0003989326,0.0001895135,4.946142e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007372833,"about_ca_system_score_gemma":0.00002770887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001338501,"about_ca_topic_score_gemma":2.055154e-7,"domain_scores_codex":[0.9990235,0.000003716636,0.0002429716,0.0002707667,0.00028279,0.0001762746],"domain_scores_gemma":[0.9986883,0.0007393034,0.0001120515,0.0003133069,0.0001027513,0.0000442235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001464138,0.0004489607,0.2388211,0.02830784,0.001336419,0.00004867412,0.04969174,0.01273125,0.1848417,0.2829949,0.03413437,0.1664966],"study_design_scores_gemma":[0.000681524,0.0009246173,0.02359963,0.008466234,0.0001483067,0.0001380691,0.0002965741,0.5341299,0.2542319,0.1759917,0.0001344755,0.001257008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7125371,0.0001610537,0.2813063,0.0003756789,0.0003241859,0.0002021911,0.00000375659,0.005049613,0.00004021057],"genre_scores_gemma":[0.8197222,0.000003666968,0.1802067,0.00002132091,0.00001625201,0.000007503574,1.433525e-7,0.00001679797,0.000005424748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5213987,"threshold_uncertainty_score":0.6959581,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03821973506433667,"gpt":0.2594014123250999,"spread":0.2211816772607632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001169016,0.000260717,0.0002720043,0.0001773874,0.0001497701,0.00007471188,0.001558459,0.0001261053,0.000005066332],"category_scores_gemma":[0.01486755,0.0002220643,0.00009966573,0.0004178585,0.00006376025,0.0003522431,0.0009327996,0.000360566,0.000002231002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005979523,"about_ca_system_score_gemma":0.00005437074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001657457,"about_ca_topic_score_gemma":0.000001963015,"domain_scores_codex":[0.9982727,0.00001092635,0.0003785292,0.0005808233,0.000363326,0.0003936534],"domain_scores_gemma":[0.9978257,0.0009249301,0.0001225442,0.0006358834,0.0004050233,0.00008595295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002242733,0.0009679581,0.3475939,0.007215146,0.0005646824,0.000001013904,0.008290502,0.0006627293,0.06918216,0.005547332,0.02634017,0.5334101],"study_design_scores_gemma":[0.001858456,0.0004221822,0.1915146,0.001179509,0.00006577527,0.00001953657,0.00009750067,0.03535504,0.612747,0.004950703,0.1504802,0.001309497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6530005,0.0005167407,0.3424791,0.001036393,0.000981458,0.001101237,0.000008475135,0.0008571199,0.00001904691],"genre_scores_gemma":[0.8904627,0.000007439665,0.1083474,0.0001427684,0.00005040183,0.0006049421,0.000001477169,0.00003761493,0.0003452743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5435649,"threshold_uncertainty_score":0.9934306,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05825794102582445,"gpt":0.2989452171374843,"spread":0.2406872761116598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003644031,0.000211028,0.0002475111,0.0003104084,0.0001492209,0.00009674543,0.002791298,0.00006898784,0.000006649617],"category_scores_gemma":[0.01606757,0.0001769717,0.0001251327,0.001319524,0.00003505575,0.0003163391,0.0008307652,0.000431859,0.00002249624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003777571,"about_ca_system_score_gemma":0.00005134543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002163768,"about_ca_topic_score_gemma":1.538805e-7,"domain_scores_codex":[0.9984232,0.000008602727,0.0002947471,0.0003656556,0.0005897477,0.0003180184],"domain_scores_gemma":[0.9975795,0.001149271,0.000125146,0.0008776379,0.0001933415,0.00007506645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008661977,0.0006276143,0.01923393,0.006811015,0.0005085839,0.000006840331,0.001347372,0.007498514,0.001527616,0.3941097,0.5661851,0.002057077],"study_design_scores_gemma":[0.0126021,0.00475749,0.1957001,0.1769481,0.000842144,0.000205561,0.002023199,0.06857101,0.1783443,0.06142887,0.2895896,0.008987596],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06549843,0.005820915,0.8247625,0.08133817,0.005878367,0.005160604,0.00007719643,0.0071741,0.004289763],"genre_scores_gemma":[0.8965919,0.0005202756,0.0990971,0.002688963,0.00008699454,0.0002537169,0.000004135033,0.00008028391,0.0006766102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8310935,"threshold_uncertainty_score":0.9922205,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Python (programming language); Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04678773520401621,"gpt":0.2944841030300863,"spread":0.2476963678260701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001069,0.0001332222,0.0001525245,0.0003705735,0.00009807192,0.0008898011,0.002855757,0.00003833182,0.00008035429],"category_scores_gemma":[0.01163085,0.00008299986,0.0001456895,0.001542812,0.00003366462,0.000669364,0.001513592,0.0001740776,0.0001481685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001757759,"about_ca_system_score_gemma":0.0000221914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001749984,"about_ca_topic_score_gemma":1.083361e-7,"domain_scores_codex":[0.9980926,0.000004504804,0.0003803616,0.0004868136,0.0008416121,0.0001941389],"domain_scores_gemma":[0.9982171,0.00064613,0.00009602682,0.0008923702,0.00008671416,0.00006167428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001456728,0.00006278123,0.009309497,0.0001935038,0.00005584253,0.000003105517,0.001193241,0.0008023338,0.006448881,0.02032319,0.9105045,0.05108857],"study_design_scores_gemma":[0.0001106673,0.00006053866,0.0390943,0.0006674487,0.00002945025,0.00001199691,0.0002034449,0.02089703,0.01894224,0.007696266,0.9119629,0.0003237192],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.972585,0.0005565292,0.003964748,0.01185696,0.00646444,0.0004125543,0.0001044456,0.001809004,0.002246309],"genre_scores_gemma":[0.9665345,0.000008569732,0.02541763,0.0002982289,0.0003052738,0.00001759451,0.00000553455,0.00004137449,0.007371292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05076485,"threshold_uncertainty_score":0.9966946,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01804381769544553,"gpt":0.2513165258656156,"spread":0.2332727081701701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001064882,0.0003431202,0.0004687283,0.0003806002,0.0001555612,0.0002525007,0.004498183,0.0002241095,0.000003671033],"category_scores_gemma":[0.01234031,0.0002535658,0.0002000719,0.001694764,0.00005794855,0.001323094,0.002141835,0.0007307274,0.000005452261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099344,"about_ca_system_score_gemma":0.0001111899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002485175,"about_ca_topic_score_gemma":0.000001120855,"domain_scores_codex":[0.9977186,0.00001536873,0.0006053094,0.0006332349,0.0005212837,0.0005061991],"domain_scores_gemma":[0.997616,0.0004984665,0.0002282051,0.001303582,0.0002845961,0.00006917786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000361378,0.001187356,0.7846048,0.0129149,0.0004063678,0.00001296082,0.01247989,0.01533841,0.006129023,0.01017256,0.01630945,0.1400829],"study_design_scores_gemma":[0.01190875,0.001388561,0.4190789,0.03502314,0.0001927352,0.0001495422,0.001881806,0.04590895,0.3806573,0.02860608,0.06967791,0.005526336],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9364184,0.0009953958,0.04877483,0.007182294,0.002774548,0.002032044,0.000004309474,0.001732503,0.00008571518],"genre_scores_gemma":[0.8398452,0.00007237424,0.158287,0.001069717,0.0001027707,0.0003164757,9.268008e-7,0.0000473094,0.0002581523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3745283,"threshold_uncertainty_score":0.9999917,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005683394962144602,"gpt":0.2175159818541883,"spread":0.2118325868920437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003137972,0.0001623835,0.0002043501,0.0001589559,0.000134802,0.00004699087,0.002952957,0.0001566706,0.000001559248],"category_scores_gemma":[0.002199876,0.0001377712,0.0001063522,0.000680963,0.00004634655,0.0001546138,0.001190702,0.0003626265,0.000004300247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005557789,"about_ca_system_score_gemma":0.00003616752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007944622,"about_ca_topic_score_gemma":6.392202e-7,"domain_scores_codex":[0.9989306,0.000002777783,0.0002727518,0.0003422509,0.0001857396,0.0002659345],"domain_scores_gemma":[0.998749,0.000179857,0.000146261,0.0007243184,0.0001647013,0.00003583413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005454895,0.0005688653,0.03544559,0.0007714923,0.0003465092,0.000002200052,0.0008886644,0.003556125,0.02668519,0.8619467,0.008272897,0.06146123],"study_design_scores_gemma":[0.003312068,0.0002950798,0.04611555,0.001798888,0.0001854515,0.00005127464,0.00009716743,0.1697613,0.5980831,0.1393781,0.03933589,0.001586114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5874726,0.0003640179,0.4052383,0.003340648,0.0009145123,0.0007051082,0.000004014376,0.001423673,0.0005371361],"genre_scores_gemma":[0.890887,0.000005270803,0.1087786,0.0001497344,0.00003783951,0.00004459537,3.230474e-7,0.00001048078,0.0000861778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7225686,"threshold_uncertainty_score":0.5618148,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01694061228693788,"gpt":0.2359343562073011,"spread":0.2189937439203632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004636242,0.0002633602,0.0003221756,0.0002867322,0.0001704137,0.0001908744,0.003315284,0.0001165137,2.104182e-7],"category_scores_gemma":[0.03071458,0.0002167859,0.0001263467,0.001030539,0.00002952619,0.0002110647,0.001027429,0.0002324453,0.000001079991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381674,"about_ca_system_score_gemma":0.00006917946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002567314,"about_ca_topic_score_gemma":1.302651e-7,"domain_scores_codex":[0.9985223,0.000004930591,0.0003701276,0.0004607684,0.0002632618,0.0003785629],"domain_scores_gemma":[0.9968408,0.001453773,0.0002249032,0.0008919362,0.0005292993,0.00005931651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008711891,0.0007168301,0.3279377,0.007613173,0.0006751289,0.000005445713,0.001384235,0.07471208,0.02810377,0.1411619,0.3258212,0.09178142],"study_design_scores_gemma":[0.000463924,0.0002371258,0.01768414,0.002675305,0.0000434567,0.00002356578,0.000004524562,0.9423926,0.01812052,0.01567956,0.002084384,0.0005909101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1327577,0.0004229309,0.8084993,0.0006602372,0.002442535,0.001538644,0.00001439627,0.05332772,0.000336457],"genre_scores_gemma":[0.4541093,6.388225e-7,0.5454134,0.00005654002,0.00006418373,0.0001725528,4.276997e-7,0.00002725267,0.0001557943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8676805,"threshold_uncertainty_score":0.9774501,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03728653452721785,"gpt":0.2970827131643091,"spread":0.2597961786370912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001670828,0.0001495477,0.0001265205,0.000114238,0.0001749838,0.0001180673,0.002068869,0.00005969264,0.000003278227],"category_scores_gemma":[0.005430353,0.0000874509,0.00005477722,0.0006053236,0.00003533925,0.0002025471,0.0002941588,0.0002251554,0.000002976113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001213845,"about_ca_system_score_gemma":0.0001039861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000936921,"about_ca_topic_score_gemma":0.000003904341,"domain_scores_codex":[0.9984741,0.00002145925,0.0002088227,0.0002558232,0.0008197862,0.0002199874],"domain_scores_gemma":[0.9976984,0.0007950236,0.00009421659,0.0008240567,0.0005600543,0.0000282925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001280448,0.0004833721,0.005905446,0.0005372062,0.0002585542,9.450579e-7,0.006495096,0.7683342,0.00667116,0.1584479,0.03070466,0.02203338],"study_design_scores_gemma":[0.0003684688,0.00009088223,0.004046275,0.000159626,0.00001673583,6.674866e-7,0.0000234779,0.9609544,0.03222112,0.0006862665,0.001317196,0.0001148327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8017045,0.0006660337,0.1907818,0.002473331,0.001174522,0.002139442,0.00005223846,0.0006200733,0.000388083],"genre_scores_gemma":[0.9931406,0.000004119664,0.006373598,0.0001451951,0.00006024957,0.0001540499,0.000003619267,0.00001916941,0.00009933393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1926202,"threshold_uncertainty_score":0.6501032,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01432123375802299,"gpt":0.2333279182883639,"spread":0.2190066845303409,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005058363,0.0004225972,0.0003442531,0.0004469608,0.0001322019,0.0003566589,0.00436044,0.0001405859,0.00001163074],"category_scores_gemma":[0.005688294,0.0002949961,0.0001342213,0.001801624,0.00006177131,0.0004710642,0.001720137,0.0006647103,0.00003242059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001858924,"about_ca_system_score_gemma":0.0001184444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007589749,"about_ca_topic_score_gemma":5.21574e-7,"domain_scores_codex":[0.9972762,0.000006103715,0.0003886503,0.0007169498,0.0009382197,0.0006739112],"domain_scores_gemma":[0.9975247,0.0009807566,0.00008871385,0.001004459,0.0002568797,0.0001445131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001889494,0.0004370728,0.7310418,0.01271862,0.001586648,0.000185533,0.01349384,0.03950915,0.001792014,0.01129304,0.05757029,0.130183],"study_design_scores_gemma":[0.001840404,0.001419511,0.5630815,0.02555502,0.000173504,0.0004307362,0.0003485281,0.003703217,0.2789303,0.002463218,0.1166032,0.005450835],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6603196,0.001261686,0.3283337,0.001741222,0.001717298,0.0007814397,0.00001096393,0.005808075,0.00002600606],"genre_scores_gemma":[0.5442484,0.0000256829,0.4547435,0.0001010418,0.00017592,0.0001696428,0.000002010352,0.0001068756,0.0004268992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2771383,"threshold_uncertainty_score":0.9999502,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01275772109649029,"gpt":0.2427344071208827,"spread":0.2299766860243924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002235629,0.0002090869,0.00019193,0.0001795071,0.0000955068,0.0002981234,0.002911173,0.0000802656,0.000001075729],"category_scores_gemma":[0.002317334,0.0001430607,0.0001696149,0.0006765597,0.00001547616,0.0004143357,0.0007398153,0.0002151183,0.000008988703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056308,"about_ca_system_score_gemma":0.00005511556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009265966,"about_ca_topic_score_gemma":3.062464e-7,"domain_scores_codex":[0.9986077,0.00000195899,0.0002686829,0.000501881,0.0003416293,0.0002781348],"domain_scores_gemma":[0.9983687,0.0004115278,0.00006063113,0.0007575969,0.0003101099,0.00009147619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003555853,0.001326893,0.003428357,0.01408343,0.0008384454,0.000005535843,0.01600509,0.06184602,0.3237393,0.3485483,0.1958315,0.03399159],"study_design_scores_gemma":[0.0003966716,0.0005574832,0.0008163707,0.001326261,0.00006029087,0.00003283143,0.000151944,0.6580577,0.2404377,0.002388555,0.09502115,0.0007529667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02249483,0.0001565129,0.9627584,0.006914918,0.004505749,0.001128374,0.00005352517,0.001701496,0.000286251],"genre_scores_gemma":[0.3720495,0.000001396956,0.6262173,0.0003403587,0.0003422853,0.0004560883,0.000001743696,0.0000610083,0.0005303696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5962117,"threshold_uncertainty_score":0.5833845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ubisoft (Canada); Queen's University","funders":"Mitacs","keywords":"Code (set theory); Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1013324913904522,"gpt":0.4411874478183851,"spread":0.339854956427933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008386633,0.0003569017,0.000578652,0.000566588,0.00006792581,0.0005250692,0.003126606,0.0001305828,0.000008647277],"category_scores_gemma":[0.07241864,0.0002235533,0.0001635796,0.001247492,0.00002742095,0.0003188261,0.005830531,0.001162008,0.00002494287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804393,"about_ca_system_score_gemma":0.00006955301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002082268,"about_ca_topic_score_gemma":0.000001847248,"domain_scores_codex":[0.9956682,0.0000649366,0.0006871852,0.001380949,0.001932357,0.0002663115],"domain_scores_gemma":[0.9959208,0.001297949,0.0004604891,0.001772693,0.0004209727,0.0001271051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001317635,0.008665771,0.2650301,0.01197746,0.001278891,0.00006284791,0.01133781,0.08790443,0.0007404943,0.0005933176,0.4851822,0.1259091],"study_design_scores_gemma":[0.0009428244,0.002281287,0.8507248,0.01664965,0.0007191857,0.00003874425,0.0009088219,0.1099831,0.0005482754,0.004038928,0.01196654,0.001197839],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933117,0.00118127,0.00009601632,0.002050617,0.001470029,0.001367701,0.0001707597,0.0002369019,0.0001150202],"genre_scores_gemma":[0.9982786,0.0001563743,0.001089056,0.0001596303,0.0001149899,0.00006636334,0.000003439919,0.0000321726,0.00009934509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5856947,"threshold_uncertainty_score":0.9353948,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03604877384191616,"gpt":0.2930271781068178,"spread":0.2569784042649016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004703614,0.0002030174,0.0001752647,0.0003431459,0.00009389409,0.0002319975,0.001798451,0.00009824544,0.00000165606],"category_scores_gemma":[0.008045177,0.000165793,0.0002051721,0.0006736175,0.00002250582,0.0005215806,0.000489644,0.0002837774,0.000007544852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140806,"about_ca_system_score_gemma":0.0000423584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002156262,"about_ca_topic_score_gemma":2.897315e-8,"domain_scores_codex":[0.9985873,0.000002851307,0.0002207667,0.0004294576,0.0004071672,0.0003524325],"domain_scores_gemma":[0.9983896,0.0008546669,0.00005738392,0.0004740752,0.0001570162,0.00006727249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003567848,0.000409229,0.04344377,0.01937412,0.001807141,0.00002346207,0.01374844,0.1682593,0.2405514,0.09262162,0.2020112,0.2173936],"study_design_scores_gemma":[0.001353745,0.001288227,0.05295556,0.007649121,0.0001813774,0.0004841935,0.0002872847,0.2940084,0.5829883,0.007508895,0.04905187,0.002242986],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7944744,0.0008306714,0.1988223,0.0005002354,0.002558299,0.0004694283,0.00000701317,0.002313969,0.00002362419],"genre_scores_gemma":[0.7606502,0.000008020535,0.2385775,0.00001323864,0.0003481307,0.0001458621,0.00000174573,0.00006310101,0.0001921673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3424369,"threshold_uncertainty_score":0.9631409,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01056494758060279,"gpt":0.232949269598238,"spread":0.2223843220176352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006999117,0.0002678172,0.000304255,0.000200715,0.0001934546,0.0001057574,0.002578036,0.0001773468,0.000003673044],"category_scores_gemma":[0.001543404,0.0002016656,0.0002081763,0.001062542,0.00005934306,0.0003690622,0.0008301795,0.0003769938,0.00000884695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002033572,"about_ca_system_score_gemma":0.00008664463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003249786,"about_ca_topic_score_gemma":0.000004345973,"domain_scores_codex":[0.9982846,0.00001081775,0.0004292343,0.0004768244,0.0004270341,0.000371476],"domain_scores_gemma":[0.9982176,0.0002886547,0.0001956004,0.001014296,0.0002171382,0.0000666889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003157552,0.0008555728,0.7367319,0.008007373,0.0005128801,0.000004294453,0.002190741,0.1640495,0.004330539,0.03520628,0.00990606,0.03788913],"study_design_scores_gemma":[0.001415369,0.0003619788,0.774841,0.001582493,0.00008001058,0.00001358303,0.00004093252,0.08240513,0.1288451,0.004439272,0.004960058,0.001015092],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7640775,0.00008985312,0.2310026,0.0009985976,0.002594907,0.0004010533,0.000003702004,0.0007090922,0.000122668],"genre_scores_gemma":[0.9816473,0.000002404783,0.01780017,0.0003209391,0.0001357898,0.00004191617,5.229709e-7,0.00001576156,0.00003519153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2175698,"threshold_uncertainty_score":0.8223686,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02323148773819599,"gpt":0.3041548689782159,"spread":0.2809233812400199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005131148,0.0003347759,0.0003292701,0.0004681294,0.0001153317,0.0001813753,0.005695214,0.0001152236,0.000003464042],"category_scores_gemma":[0.01049133,0.0002643983,0.0001312385,0.001220412,0.00002396727,0.0003710778,0.001423199,0.0006745425,0.00001199198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002032186,"about_ca_system_score_gemma":0.00005875786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001340218,"about_ca_topic_score_gemma":4.000788e-7,"domain_scores_codex":[0.9975932,0.00001362295,0.0003578551,0.0006913269,0.0008422546,0.0005016932],"domain_scores_gemma":[0.9968832,0.0008139032,0.00008992697,0.001810247,0.0002478208,0.0001549372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003287762,0.0005602563,0.9892676,0.0001760389,0.00007751488,0.000006279091,0.0007952459,0.003339478,0.001101275,0.0008456444,0.001551882,0.002245931],"study_design_scores_gemma":[0.0005459065,0.0006530733,0.9749548,0.0003995698,0.00001576347,0.000003944385,0.00007039126,0.003335895,0.01883558,0.0001710456,0.0006729848,0.0003410402],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981299,0.00002535492,0.01586134,0.000455371,0.0007095963,0.0004891031,0.000004707586,0.001121724,0.00003384435],"genre_scores_gemma":[0.9891634,0.000002712782,0.01038253,0.0001271746,0.00008846037,0.00007816971,5.026009e-7,0.00004374748,0.000113302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0177343,"threshold_uncertainty_score":0.9999808,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Ransomware; Backup; Computer science; Computer security; Encryption; Malware; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.006109823960931409,"gpt":0.2282517523318598,"spread":0.2221419283709284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002706787,0.0001808772,0.0002625081,0.0002284473,0.0000688952,0.00003449338,0.00222735,0.00008961802,5.514653e-7],"category_scores_gemma":[0.001590766,0.0001510443,0.000150432,0.0008153443,0.00002904196,0.0003460918,0.0009103774,0.0002058185,0.000001362085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192347,"about_ca_system_score_gemma":0.00002238212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002244122,"about_ca_topic_score_gemma":1.233937e-7,"domain_scores_codex":[0.9988107,0.000005015047,0.0003888224,0.0003048567,0.0002873634,0.0002032131],"domain_scores_gemma":[0.9986105,0.0001213614,0.0002743775,0.0006597498,0.0003019417,0.00003208219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002619502,0.0007029361,0.06304976,0.03231584,0.0006943253,0.000006528801,0.002820109,0.03407988,0.3052652,0.2874572,0.008251932,0.2650944],"study_design_scores_gemma":[0.0006588065,0.0001475426,0.01142059,0.005790369,0.00004201695,0.00001242707,0.0001216306,0.02191929,0.9547126,0.00181964,0.002860488,0.0004945837],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1891264,0.0001270105,0.8076087,0.0001523989,0.0006017147,0.000510805,0.000007077139,0.001539971,0.0003259616],"genre_scores_gemma":[0.7708974,0.000008268624,0.2288343,0.00003244844,0.00002445,0.00004904149,4.91763e-7,0.00001716605,0.0001363924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6494474,"threshold_uncertainty_score":0.6159408,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01895505048035933,"gpt":0.2946897396904545,"spread":0.2757346892100952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003432928,0.0002102608,0.0002061518,0.0003025095,0.0001350327,0.0001669491,0.003441374,0.0001058718,0.000001394426],"category_scores_gemma":[0.007989948,0.0001713928,0.0001837646,0.001306472,0.00004215079,0.0004015932,0.000533277,0.0002416038,0.000003660863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199922,"about_ca_system_score_gemma":0.00008387859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003830884,"about_ca_topic_score_gemma":2.158746e-7,"domain_scores_codex":[0.9985519,0.000002833096,0.0003061983,0.0003431409,0.0004004074,0.0003955109],"domain_scores_gemma":[0.9982463,0.0003846003,0.00008100236,0.0007390422,0.0004738746,0.00007520436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007526583,0.001127891,0.01319052,0.003063519,0.0002999183,5.040295e-7,0.001364675,0.005959195,0.002506872,0.1229915,0.02759247,0.8218277],"study_design_scores_gemma":[0.004300125,0.002296645,0.2860336,0.001898392,0.0002069417,0.00002084682,0.0001723164,0.2313979,0.1869912,0.0157472,0.2689019,0.002032923],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1806684,0.0002369457,0.7960631,0.005402125,0.001609351,0.007965228,0.00005199503,0.007654848,0.0003479662],"genre_scores_gemma":[0.4193683,0.00001156229,0.5783073,0.00006678321,0.0000537938,0.001999367,0.000004764119,0.00003051395,0.0001577169],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8197947,"threshold_uncertainty_score":0.956529,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02915474167711867,"gpt":0.3161663503427405,"spread":0.2870116086656219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001208379,0.0006269237,0.000743914,0.0005525728,0.0001286424,0.000224194,0.008581235,0.0004306329,0.000001433062],"category_scores_gemma":[0.02026648,0.0005472543,0.0004408675,0.0005814467,0.00003795306,0.0003853563,0.003878874,0.0009183901,9.364778e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002566044,"about_ca_system_score_gemma":0.0002251528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006039155,"about_ca_topic_score_gemma":0.000002797202,"domain_scores_codex":[0.9968619,0.00001612384,0.0005196573,0.001171037,0.0006790388,0.0007522317],"domain_scores_gemma":[0.9926159,0.00403472,0.0003066881,0.002059066,0.0008049726,0.0001786193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001609886,0.0001751853,0.0003923733,0.004444876,0.0004184963,0.000002792301,0.005568552,0.9509739,0.00312116,0.01750748,0.004233153,0.0130011],"study_design_scores_gemma":[0.0006329761,0.0003405755,0.0004139282,0.001507434,0.00009889139,0.000005927686,0.00009579077,0.9586285,0.03224369,0.005043636,0.000276649,0.0007120154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01409511,0.0005284932,0.9801694,0.0003012695,0.0008866907,0.002212915,0.000483106,0.00130558,0.00001744585],"genre_scores_gemma":[0.08448189,0.000008840306,0.9132159,0.0001097111,0.0002677591,0.001407035,0.00002353567,0.000116923,0.0003684541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07038678,"threshold_uncertainty_score":0.9996979,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0138911653291388,"gpt":0.297761580012134,"spread":0.2838704146829952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006074032,0.0002540926,0.0005056435,0.0009748475,0.00006790309,0.00009165994,0.005575232,0.00008831058,0.000005598266],"category_scores_gemma":[0.01073514,0.0002016374,0.0001839418,0.004464231,0.00004246697,0.0003306935,0.001297374,0.0003873263,0.000001739844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000807718,"about_ca_system_score_gemma":0.00006020475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110128,"about_ca_topic_score_gemma":0.000001013267,"domain_scores_codex":[0.9977868,0.00001654569,0.0004712938,0.0005270116,0.000826635,0.0003716904],"domain_scores_gemma":[0.9966791,0.001058672,0.0001625072,0.00153039,0.0004652351,0.0001041019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003943681,0.0008406437,0.9417418,0.0003460299,0.0007825406,0.000001839448,0.004136174,0.04694258,0.002346176,0.0004163746,0.001557714,0.0008486959],"study_design_scores_gemma":[0.0008161418,0.0008439996,0.8840759,0.0001513494,0.0002572831,0.000001622953,0.0001930318,0.09323194,0.01948226,0.000426725,0.000178925,0.0003407694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9571946,0.00003111297,0.04148457,0.0002578566,0.0001829989,0.0003762047,0.000004200335,0.0004577234,0.00001069254],"genre_scores_gemma":[0.9678928,0.000001875103,0.03190617,0.00004057954,0.00001620852,0.00005305267,8.411228e-7,0.0000222875,0.00006617692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05766583,"threshold_uncertainty_score":0.9998051,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05208794963468529,"gpt":0.2627753376960894,"spread":0.2106873880614041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002826743,0.0001450051,0.0001683054,0.0003315633,0.00008346063,0.00009827772,0.001324862,0.00006849306,3.674826e-7],"category_scores_gemma":[0.005764493,0.0001221018,0.00003889127,0.0009019843,0.00002856516,0.0002472767,0.0008549483,0.0002382269,5.137527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008864116,"about_ca_system_score_gemma":0.00002722162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001116515,"about_ca_topic_score_gemma":7.725355e-7,"domain_scores_codex":[0.9991672,0.000003648098,0.0002055411,0.0002565745,0.0001567722,0.0002102595],"domain_scores_gemma":[0.9989876,0.0004183603,0.00008183287,0.0004065417,0.00007031894,0.00003536468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001462881,0.0001233397,0.8459496,0.0005216215,0.00004285828,0.000002683647,0.0007570027,0.0002573219,0.007576813,0.1358705,0.005826236,0.00305732],"study_design_scores_gemma":[0.0005587831,0.000130042,0.7854823,0.003359353,0.00002103145,0.00002619776,0.00003221078,0.02356692,0.01654953,0.1691465,0.0005938642,0.0005333024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8708465,0.0001652486,0.1163605,0.003683979,0.0004753258,0.0004390221,0.0000031739,0.007546982,0.0004792975],"genre_scores_gemma":[0.8889307,0.000007371475,0.1108032,0.0001560571,0.00001140276,0.00002149921,1.690648e-7,0.00001125917,0.00005833878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06046741,"threshold_uncertainty_score":0.6901053,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01723503358432096,"gpt":0.2818270580510308,"spread":0.2645920244667099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007450132,0.00031295,0.0003756256,0.0004510444,0.0001048053,0.000156774,0.003480715,0.0001396196,0.000003492653],"category_scores_gemma":[0.02186193,0.0002850567,0.000110767,0.001610135,0.00003470236,0.0003799441,0.001463847,0.0005008294,0.000006777636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965053,"about_ca_system_score_gemma":0.0001624267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001737667,"about_ca_topic_score_gemma":0.000003658268,"domain_scores_codex":[0.9979707,0.000007471716,0.0004330966,0.0005828876,0.0003720379,0.0006337888],"domain_scores_gemma":[0.9965248,0.00202112,0.0001067808,0.0008319468,0.0004259704,0.00008935059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003421704,0.0009615664,0.5372317,0.009145144,0.0005048105,0.000007985138,0.00859932,0.08701733,0.2032818,0.02815873,0.1020873,0.02266208],"study_design_scores_gemma":[0.00322919,0.0005368048,0.07127476,0.006846765,0.00005165596,0.0000140931,0.0001550731,0.1879383,0.6941187,0.002429142,0.03149749,0.001907993],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7036215,0.001018782,0.291643,0.0005169148,0.001585866,0.0007578067,0.0000174301,0.0007510412,0.0000876227],"genre_scores_gemma":[0.9539075,0.00002157916,0.04533779,0.00007974736,0.00006482063,0.00008047897,0.000001883672,0.00004766276,0.0004584809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4908369,"threshold_uncertainty_score":0.9999602,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04127833120726755,"gpt":0.2794976332482037,"spread":0.2382193020409362,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002515129,0.0001599248,0.0002320326,0.00007178172,0.000103999,0.00008172318,0.0005153813,0.00009500582,0.000001521296],"category_scores_gemma":[0.00228011,0.0001487821,0.00007591161,0.0004130173,0.00003583888,0.0001797302,0.000107228,0.0001476797,3.709396e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008784474,"about_ca_system_score_gemma":0.00002707487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007337958,"about_ca_topic_score_gemma":3.301049e-7,"domain_scores_codex":[0.9991871,0.000001981744,0.0003405957,0.0001585312,0.0001401426,0.0001716085],"domain_scores_gemma":[0.9990988,0.0002204614,0.0001006574,0.0002260929,0.0003285738,0.00002538471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001968911,0.00006646834,0.01179239,0.003559083,0.00009601139,1.473968e-7,0.0001062298,0.09983768,0.8307676,0.002928355,0.005513684,0.04531266],"study_design_scores_gemma":[0.0001850508,0.00002743407,0.004206126,0.000815869,0.00002175782,0.000001217293,0.00001649473,0.2304831,0.7626671,0.0002414796,0.001178279,0.0001561706],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9302683,0.0003541961,0.06469292,0.0003803038,0.0005548616,0.0009954894,0.00003423081,0.001489101,0.001230558],"genre_scores_gemma":[0.7124808,0.000005181173,0.2872811,0.00002928608,0.0000473717,0.00003393269,0.000002862074,0.00002848033,0.00009100765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2225882,"threshold_uncertainty_score":0.6067159,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01559207690885851,"gpt":0.2795375657167719,"spread":0.2639454888079134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005855435,0.000179677,0.0003754006,0.0009983554,0.00005494878,0.0001277678,0.003110672,0.00009883785,0.000003879977],"category_scores_gemma":[0.01428562,0.000155629,0.00008454786,0.0039838,0.00003847214,0.0004873547,0.002128704,0.0002449393,9.596638e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001146182,"about_ca_system_score_gemma":0.00009467097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005475786,"about_ca_topic_score_gemma":0.000004357475,"domain_scores_codex":[0.9985901,0.000007943509,0.0003866651,0.0003917281,0.0003824815,0.000241152],"domain_scores_gemma":[0.9979066,0.001023696,0.0001323793,0.0005837315,0.0003037729,0.00004984919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003890138,0.0001183023,0.9125593,0.0004625998,0.0005672689,0.000001220911,0.0007693784,0.06876693,0.004182348,0.003887684,0.001713241,0.006932816],"study_design_scores_gemma":[0.0003455824,0.00003310815,0.8890204,0.0002809034,0.00005578197,0.000002728487,0.0000197644,0.09503122,0.01423993,0.0002217907,0.0005674718,0.0001812611],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.877677,0.0001717351,0.1201808,0.0005078993,0.0001884772,0.0005213725,0.000008416808,0.0007189682,0.00002535286],"genre_scores_gemma":[0.7796457,0.00001287531,0.219959,0.00005111657,0.000009758817,0.00006307533,0.000002852376,0.00002011716,0.000235469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09977826,"threshold_uncertainty_score":0.9940175,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; 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","retraction":null,"screen_n_in":null,"score":{"opus":0.03286994685591208,"gpt":0.3322889776632466,"spread":0.2994190308073345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002563891,0.0001001653,0.0001702996,0.000243671,0.00002788195,0.00008793456,0.00442262,0.00004034429,0.000001543378],"category_scores_gemma":[0.002580767,0.00007969215,0.00001842815,0.001337926,0.00001931805,0.0008103819,0.001838714,0.00008485994,5.090839e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001477769,"about_ca_system_score_gemma":0.00003968494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007603647,"about_ca_topic_score_gemma":0.000001943466,"domain_scores_codex":[0.9990647,0.000007028771,0.0002908694,0.0002757916,0.0002537803,0.0001078383],"domain_scores_gemma":[0.9986694,0.00008002779,0.0001042728,0.001007875,0.0001120523,0.00002637348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003383907,0.002371673,0.8529526,0.0004913586,0.00008270719,9.085116e-7,0.004528481,0.005086831,0.0007886529,0.1145426,0.01661021,0.002510146],"study_design_scores_gemma":[0.001354219,0.0004734658,0.2377609,0.0005068631,0.00004519745,0.000001386253,0.0007373658,0.7404631,0.01157828,0.002746781,0.003931174,0.0004011638],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8183854,0.00005584659,0.1798452,0.0005591118,0.0003112844,0.0004135672,0.00002334664,0.0003412404,0.00006496721],"genre_scores_gemma":[0.9801118,0.000004631104,0.01963841,0.0001571729,0.00001491818,0.000005230766,0.000009766314,0.000009870613,0.00004816744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7353763,"threshold_uncertainty_score":0.8218403,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006555163432256633,"gpt":0.2317463961842824,"spread":0.2251912327520258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001801239,0.0001100746,0.0001282188,0.0001803353,0.00007776883,0.00004549604,0.001089784,0.00009863202,3.89418e-7],"category_scores_gemma":[0.0005003985,0.00009370641,0.00002226817,0.0007897673,0.00003529967,0.0001629101,0.0003945638,0.0001894897,6.248056e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002185793,"about_ca_system_score_gemma":0.00001461848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003809376,"about_ca_topic_score_gemma":0.000001171477,"domain_scores_codex":[0.9992833,0.000002674979,0.0002151863,0.0002865272,0.00008617374,0.0001261818],"domain_scores_gemma":[0.9993854,0.00009421144,0.00004375894,0.0003527199,0.00009925389,0.00002470052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000005652208,0.0001562015,0.01429333,0.0005177885,0.00002930999,1.115535e-7,0.001036357,0.00008867094,0.007275049,0.9701829,0.0004735251,0.005941109],"study_design_scores_gemma":[0.001128423,0.00007228234,0.3923762,0.0004622682,0.0000512085,0.00001142428,0.0001098515,0.3320861,0.1534138,0.1147579,0.00485999,0.000670556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645209,0.0006230563,0.03155857,0.001840428,0.00005402638,0.0006458964,0.00000859433,0.0007159717,0.00003257471],"genre_scores_gemma":[0.9954758,0.00007348859,0.0041793,0.00003081496,0.000004277676,0.000219639,7.339472e-7,0.000004843841,0.0000111437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8554251,"threshold_uncertainty_score":0.3821236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}