{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Fangwen Mu","is_ca":false},{"name":"Lin Shi","is_ca":false},{"name":"Song Wang","is_ca":true},{"name":"Zhuohao Yu","is_ca":false},{"name":"Binquan Zhang","is_ca":false},{"name":"ChenXue Wang","is_ca":false},{"name":"Shichao Liu","is_ca":false},{"name":"Qing Wang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006709022,0.002595332,0.0008013883,0.002339753,0.0008374864,0.002088094,0.004376793,0.002429598,0.008730297],"category_scores_gemma":[0.03096388,0.001738982,0.002457153,0.0009517119,0.002165008,0.00384207,0.004982915,0.004555638,0.004555242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001476967,"about_ca_system_score_gemma":0.003922198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005099506,"about_ca_topic_score_gemma":0.007589884,"domain_scores_codex":[0.9939719,0.002490896,0.0005322197,0.00100287,0.001672058,0.0003300187],"domain_scores_gemma":[0.9860563,0.007746659,0.001207017,0.003137078,0.001398855,0.0004541219],"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":[0.0008521608,0.001001727,0.004929382,0.003006551,0.0002532481,0.001640172,0.004990538,0.07796579,0.06808623,0.07060592,0.08247399,0.6841943],"study_design_scores_gemma":[0.0004310609,0.0005191974,0.001237891,0.0004503567,0.0001206607,0.001111568,0.0005765189,0.7162777,0.06127133,0.05199287,0.1657359,0.0002749793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003305926,0.0001313153,0.9238024,0.0003486057,0.00005880304,0.0005660151,0.000439071,0.06945139,0.001896429],"genre_scores_gemma":[0.03692972,0.0001377959,0.9513541,0.0003752043,0.00002676338,0.0006471363,0.001902515,0.006736129,0.001890543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008730297,"threshold_uncertainty_score":0.03548115,"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","authors":[{"name":"Vijayaraghavan Murali","is_ca":false},{"name":"Chandra Maddila","is_ca":false},{"name":"Imad Ahmad","is_ca":false},{"name":"Michael Bolin","is_ca":false},{"name":"Daniel Cheng","is_ca":false},{"name":"Negar Ghorbani","is_ca":false},{"name":"Renuka Fernandez","is_ca":false},{"name":"Nachiappan Nagappan","is_ca":false},{"name":"Peter C. Rigby","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02933411,0.001918782,0.0007821088,0.001645065,0.0009150905,0.002164564,0.003863279,0.002145552,0.002949158],"category_scores_gemma":[0.1036975,0.0008998648,0.001222399,0.001085485,0.001917675,0.002918343,0.003911733,0.003461362,0.00139948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635361,"about_ca_system_score_gemma":0.002205478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007079716,"about_ca_topic_score_gemma":0.008663188,"domain_scores_codex":[0.985292,0.009986321,0.0009595599,0.001471517,0.00184859,0.0004419814],"domain_scores_gemma":[0.8608415,0.113594,0.002022776,0.01395802,0.007760521,0.001823297],"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":[0.004555324,0.005040111,0.0458971,0.003934852,0.001111779,0.0006486617,0.007724445,0.2429437,0.02244703,0.01624433,0.0344701,0.6149826],"study_design_scores_gemma":[0.001243272,0.001438909,0.006654484,0.000372305,0.0002223843,0.0001537621,0.001214042,0.9453399,0.0132947,0.01354026,0.01639692,0.0001290181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5437647,0.003271266,0.3832335,0.0024563,0.0007062853,0.003122563,0.002345388,0.04594987,0.01515006],"genre_scores_gemma":[0.5328169,0.0003961342,0.4541804,0.0007545791,0.000083789,0.002540886,0.003033073,0.003882476,0.002311745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02933411,"threshold_uncertainty_score":0.1551355,"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","authors":[{"name":"Md Nakhla Rafi","is_ca":true},{"name":"Dong Jae Kim","is_ca":false},{"name":"An Ran Chen","is_ca":true},{"name":"Tse-Hsun Chen","is_ca":true},{"name":"Shaowei Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000358182,0.0009941454,0.0005757029,0.001574002,0.0002441497,0.000738513,0.001426921,0.0008909735,0.001881679],"category_scores_gemma":[0.002698154,0.0003532387,0.0007145124,0.001113825,0.0005011826,0.001808749,0.0007954661,0.001195436,0.0005065162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088934,"about_ca_system_score_gemma":0.0009045497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01094477,"about_ca_topic_score_gemma":0.01219986,"domain_scores_codex":[0.9996983,0.00006373087,0.00001635747,0.0001000417,0.00008833451,0.00003336265],"domain_scores_gemma":[0.9991837,0.0003149828,0.0001162982,0.0001457746,0.0002074038,0.00003188877],"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":[0.00007591449,0.00007724834,0.0010233,0.00008907075,0.00003879311,0.00007632711,0.00005341414,0.8097898,0.006228343,0.007675292,0.002531371,0.1723411],"study_design_scores_gemma":[0.000002409139,0.000007245558,0.00007042162,0.000002368108,0.000003707812,0.000006163662,0.000003391206,0.9966917,0.0007004166,0.002266984,0.0002432986,0.000001866515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0301303,0.0001958221,0.9642248,0.0002886255,0.00003428583,0.00004516851,0.0003105649,0.00358698,0.001183401],"genre_scores_gemma":[0.5419931,0.0003822606,0.4504933,0.0003043704,0.00004348388,0.0002128326,0.00234037,0.0004211197,0.003809165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01094477,"threshold_uncertainty_score":0.02176213,"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","authors":[{"name":"Zhiyang Chen","is_ca":true},{"name":"Ye Liu","is_ca":false},{"name":"Sidi Mohamed Beillahi","is_ca":true},{"name":"Yi Li","is_ca":false},{"name":"Fan Long","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004384642,0.0007089887,0.0004673309,0.004213819,0.0003316793,0.001513896,0.001042866,0.0005759057,0.001105277],"category_scores_gemma":[0.02847464,0.0004094334,0.000569133,0.001410002,0.001666416,0.002978964,0.001642618,0.001132976,0.000246657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000842882,"about_ca_system_score_gemma":0.001352143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002657651,"about_ca_topic_score_gemma":0.003793636,"domain_scores_codex":[0.9958547,0.001054703,0.0003607656,0.0005603801,0.001763463,0.0004058638],"domain_scores_gemma":[0.9701201,0.01869764,0.003562542,0.005362539,0.001848072,0.0004091991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001001885,0.0004681304,0.2577993,0.0006841977,0.0002837809,0.0006804995,0.001648381,0.1794134,0.08766296,0.0182186,0.002757621,0.4493813],"study_design_scores_gemma":[0.00004570802,0.0004633456,0.02756362,0.00006544257,0.00008944025,0.0004291609,0.0003722699,0.8812168,0.07695832,0.00998186,0.002732059,0.00008203759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8164986,0.0006109762,0.1675347,0.0002461428,0.00003566038,0.0001359639,0.0007584468,0.01150343,0.002676022],"genre_scores_gemma":[0.9525822,0.0001047035,0.0463036,0.00002345762,0.000007058572,0.00003019755,0.0005191939,0.0002044895,0.0002251939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004384642,"threshold_uncertainty_score":0.02318847,"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","authors":[{"name":"Md Afif Al Mamun","is_ca":true},{"name":"Jie M. Zhang","is_ca":false},{"name":"Gias Uddin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004440343,0.001629003,0.0009697395,0.001602469,0.0005243564,0.001914111,0.001774262,0.001527613,0.001041329],"category_scores_gemma":[0.02785358,0.000586184,0.001437133,0.0008889667,0.001061565,0.003592783,0.00309998,0.001948031,0.0009720192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009038101,"about_ca_system_score_gemma":0.001050172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004968088,"about_ca_topic_score_gemma":0.007165468,"domain_scores_codex":[0.9957956,0.001646061,0.0003460269,0.001034442,0.001001494,0.0001762769],"domain_scores_gemma":[0.9839357,0.01138654,0.001241786,0.002166385,0.001018391,0.000251211],"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":[0.001295752,0.0004617297,0.03873779,0.00141619,0.001056921,0.002796693,0.001949632,0.2775883,0.03925931,0.006633818,0.02174796,0.607056],"study_design_scores_gemma":[0.00004082602,0.0001039912,0.001659157,0.00003574269,0.00006977429,0.0004904126,0.0002246524,0.9760089,0.00959558,0.009499172,0.002234491,0.00003731053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2107225,0.002920418,0.7291935,0.001382689,0.0001659639,0.0002710044,0.002028531,0.05079232,0.002523038],"genre_scores_gemma":[0.8225754,0.0004025807,0.170176,0.0009175448,0.00007748167,0.000142934,0.003407765,0.000859108,0.001441369],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004968088,"threshold_uncertainty_score":0.02348304,"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","authors":[{"name":"Oussama Ben Sghaier","is_ca":true},{"name":"Houari Sahraoui","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005159675,0.002470593,0.001672955,0.001907115,0.0008182088,0.001709602,0.003367693,0.002824067,0.00236571],"category_scores_gemma":[0.02558921,0.0007266336,0.001224848,0.001075203,0.0009384231,0.004269854,0.003131546,0.004149023,0.001845647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001955242,"about_ca_system_score_gemma":0.003066886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007547219,"about_ca_topic_score_gemma":0.01272766,"domain_scores_codex":[0.9955831,0.001512805,0.0002755578,0.001565814,0.0007542328,0.0003084509],"domain_scores_gemma":[0.9782507,0.01180626,0.00153018,0.00292512,0.004623816,0.0008640044],"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":[0.0008641625,0.001025524,0.00734001,0.0008170148,0.0002262129,0.0002686762,0.0006103847,0.1064522,0.02308233,0.001472967,0.02162093,0.8362196],"study_design_scores_gemma":[0.00009363012,0.0004002453,0.001384846,0.00004594806,0.0000744547,0.0001102891,0.00009769373,0.9759151,0.01554587,0.002893822,0.003390454,0.00004756882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2945325,0.006119653,0.6512368,0.002197416,0.001041046,0.0008699957,0.001280678,0.0360985,0.006623368],"genre_scores_gemma":[0.76029,0.0007936453,0.2196056,0.001519648,0.0003421916,0.0005174946,0.005151483,0.0009187917,0.01086116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007547219,"threshold_uncertainty_score":0.0272873,"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","authors":[{"name":"Bonan Kou","is_ca":false},{"name":"S. Chen","is_ca":false},{"name":"Zhijie Wang","is_ca":true},{"name":"Lei Ma","is_ca":true},{"name":"Tianyi Zhang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005873315,0.000687982,0.0006284129,0.001012107,0.000537013,0.002671429,0.001231242,0.001536306,0.002746627],"category_scores_gemma":[0.07296127,0.000704008,0.0005386031,0.0006570037,0.001772331,0.005601228,0.001913059,0.001732226,0.001232841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007546004,"about_ca_system_score_gemma":0.0009158074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002903264,"about_ca_topic_score_gemma":0.003819678,"domain_scores_codex":[0.9936491,0.002878122,0.0001901709,0.001467203,0.001347884,0.0004676751],"domain_scores_gemma":[0.9576057,0.02762619,0.003808086,0.007168941,0.002585041,0.001205947],"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":[0.001526958,0.0005054955,0.227238,0.001074846,0.0004929402,0.001433561,0.04129446,0.01489269,0.1157985,0.02094825,0.01558417,0.5592101],"study_design_scores_gemma":[0.0004631724,0.001647838,0.2861018,0.0004891637,0.0006633696,0.004270142,0.0231482,0.3503791,0.07297616,0.1463075,0.1130025,0.0005509808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7016768,0.001054618,0.2643784,0.005417522,0.0002140778,0.0001745179,0.0002560351,0.00656134,0.02026657],"genre_scores_gemma":[0.9665791,0.0002117057,0.02844609,0.001517268,0.00005028462,0.00006760749,0.0002258159,0.0009728273,0.001929218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005873315,"threshold_uncertainty_score":0.03106141,"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","authors":[{"name":"Gengyi Sun","is_ca":true},{"name":"Sarra Habchi","is_ca":true},{"name":"Shane McIntosh","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00233761,0.003151045,0.001361547,0.003886178,0.0005673679,0.001303645,0.002214018,0.001479564,0.002294623],"category_scores_gemma":[0.00963312,0.0006563119,0.001331041,0.001809003,0.0004722805,0.002364597,0.002685329,0.002538539,0.00246469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007128267,"about_ca_system_score_gemma":0.001249261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009681338,"about_ca_topic_score_gemma":0.02482225,"domain_scores_codex":[0.9979724,0.0003930323,0.0001299895,0.0007831351,0.0005285892,0.0001928158],"domain_scores_gemma":[0.9963061,0.001816214,0.0003931037,0.0006202715,0.0006065415,0.0002577607],"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":[0.00118445,0.001041168,0.1463705,0.0009513492,0.0004885858,0.001005724,0.0005459022,0.1795894,0.01046273,0.002043838,0.0602705,0.596046],"study_design_scores_gemma":[0.00007276554,0.0003203155,0.0152886,0.00009471029,0.0001309635,0.0003624283,0.0001175308,0.9592164,0.006976148,0.005309447,0.01204362,0.00006718086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.416254,0.01129079,0.4261541,0.002047785,0.000699811,0.0007571366,0.02575885,0.1063181,0.01071933],"genre_scores_gemma":[0.7723374,0.0008757224,0.1896885,0.0004484473,0.0001975658,0.0003906957,0.02992588,0.001209595,0.004926195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009681338,"threshold_uncertainty_score":0.01924998,"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","authors":[{"name":"Md Shamimur Rahman","is_ca":true},{"name":"Zadia Codabux","is_ca":true},{"name":"Chanchal K. Roy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06602757,0.0008981579,0.0009118636,0.007814402,0.02280953,0.02762034,0.003413602,0.008254616,0.004857671],"category_scores_gemma":[0.2938707,0.001333139,0.0008449077,0.003221797,0.06190302,0.04517166,0.02987917,0.009419537,0.00122374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01344986,"about_ca_system_score_gemma":0.01837597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005137568,"about_ca_topic_score_gemma":0.005652096,"domain_scores_codex":[0.8090104,0.1565334,0.004543663,0.006608651,0.01625612,0.007047772],"domain_scores_gemma":[0.5189419,0.389716,0.04563428,0.0120598,0.02002173,0.01362634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002834967,0.00002002193,0.003494631,0.0001425181,0.00001278975,0.0006089741,0.9421662,0.00004554345,0.00028853,0.03865084,0.002500229,0.01204143],"study_design_scores_gemma":[0.00003517006,0.00006597431,0.002969235,0.0008156509,0.00003165283,0.0008426611,0.7872438,0.0004906665,0.0005456571,0.08985628,0.1170315,0.00007174453],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5786625,0.009310001,0.03488177,0.2079481,0.001577964,0.0002670118,0.00004882222,0.0003080314,0.1669958],"genre_scores_gemma":[0.987363,0.001400961,0.001913261,0.005373882,0.0003634663,0.0001254473,0.00002001394,0.000139007,0.00330088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06602757,"threshold_uncertainty_score":0.3491914,"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","authors":[{"name":"Xu Yang","is_ca":true},{"name":"Shaowei Wang","is_ca":true},{"name":"Jiayuan Zhou","is_ca":true},{"name":"Wenhan Zhu","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005310628,0.003987368,0.002365205,0.00276934,0.0009540166,0.002512401,0.00328479,0.003991501,0.004511975],"category_scores_gemma":[0.01365912,0.001232172,0.003011136,0.001245838,0.001488747,0.009675007,0.005180401,0.00538598,0.005707867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248832,"about_ca_system_score_gemma":0.001846194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004856099,"about_ca_topic_score_gemma":0.01003023,"domain_scores_codex":[0.995644,0.001140169,0.0002438214,0.001431249,0.001018901,0.0005218375],"domain_scores_gemma":[0.9948208,0.002048858,0.0003503031,0.001662679,0.000766433,0.0003508123],"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":[0.0009883525,0.0006475639,0.02145188,0.0007731168,0.001016319,0.0005903561,0.0003671245,0.0931206,0.01545807,0.008363274,0.07641772,0.7808056],"study_design_scores_gemma":[0.00008788864,0.0004056105,0.002707162,0.0002301424,0.0002404575,0.001273477,0.0002185164,0.9068868,0.02095887,0.03650761,0.03032805,0.0001555353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08654629,0.009282838,0.8327342,0.005954359,0.001049066,0.0003132099,0.002279264,0.05105182,0.010789],"genre_scores_gemma":[0.526357,0.002495515,0.4408609,0.005691069,0.0003505616,0.0002578227,0.006337742,0.002831576,0.01481772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005310628,"threshold_uncertainty_score":0.02808559,"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","authors":[{"name":"Zhijie Wang","is_ca":true},{"name":"Zhehua Zhou","is_ca":true},{"name":"Jiayang Song","is_ca":true},{"name":"Yuheng Huang","is_ca":false},{"name":"Zhan Shu","is_ca":true},{"name":"Lei Ma","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003202415,0.001674858,0.0006235217,0.000867647,0.0005213654,0.0009809466,0.003414438,0.002177025,0.003036358],"category_scores_gemma":[0.013307,0.0007530313,0.001365145,0.0003395785,0.001572145,0.00190759,0.001931716,0.002147024,0.0006799424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00190229,"about_ca_system_score_gemma":0.001669172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01230621,"about_ca_topic_score_gemma":0.01243409,"domain_scores_codex":[0.9983253,0.0005734492,0.0001157777,0.0004069807,0.0004446495,0.0001338779],"domain_scores_gemma":[0.9915685,0.006456992,0.0004107166,0.0008390776,0.000481562,0.0002431029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007334704,0.0008501097,0.005736214,0.0006167298,0.0002056875,0.0001915491,0.0002624578,0.8998533,0.01245523,0.005071458,0.004045818,0.06997789],"study_design_scores_gemma":[0.00004961224,0.0002820326,0.0005378685,0.00001974922,0.000014182,0.00003475682,0.00002699867,0.9930728,0.004365382,0.001000293,0.0005819615,0.00001429495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6558537,0.0009764071,0.3155743,0.0006797121,0.0003432333,0.001207726,0.001987693,0.01643031,0.006946956],"genre_scores_gemma":[0.8313949,0.0002398218,0.1629666,0.0002470521,0.00002649137,0.0006390127,0.002486316,0.0006298784,0.001369996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01230621,"threshold_uncertainty_score":0.02446914,"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","authors":[{"name":"Nimmi Rashinika Weeraddana","is_ca":true},{"name":"Mahmoud Alfadel","is_ca":true},{"name":"Shane McIntosh","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01171605,0.0006501609,0.0006282326,0.005044703,0.001417561,0.002853375,0.002490155,0.001251654,0.00156724],"category_scores_gemma":[0.088709,0.0006617882,0.0007560916,0.008664466,0.001785715,0.006918644,0.003775374,0.002594372,0.0008296089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001498201,"about_ca_system_score_gemma":0.001835341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008248563,"about_ca_topic_score_gemma":0.008294825,"domain_scores_codex":[0.9890295,0.003273567,0.001127859,0.001821201,0.003807715,0.0009401053],"domain_scores_gemma":[0.8472636,0.08836684,0.03421008,0.0128083,0.01297954,0.004371649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001998883,0.0005073154,0.9575647,0.000275096,0.0001215753,0.0005483513,0.004235549,0.001932406,0.0004901989,0.001034956,0.003437645,0.02965235],"study_design_scores_gemma":[0.00003013971,0.000344571,0.9494114,0.0002844155,0.0001202578,0.001207632,0.01200086,0.02017725,0.001005603,0.002638163,0.01269627,0.00008333485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954235,0.0004376005,0.001374637,0.0002246359,0.00001066565,0.0000354946,0.001085871,0.00009767838,0.001309918],"genre_scores_gemma":[0.9881016,0.0004392335,0.004022889,0.0001802375,0.00002673236,0.0001065126,0.006213979,0.0001551239,0.0007537696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01171605,"threshold_uncertainty_score":0.06196117,"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","authors":[{"name":"Huaien Zhang","is_ca":false},{"name":"Yu Pei","is_ca":false},{"name":"Shuyun Liang","is_ca":false},{"name":"Shin Hwei Tan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004572764,0.001154198,0.0006672054,0.004685577,0.0006171915,0.00169176,0.001418407,0.001409862,0.000752366],"category_scores_gemma":[0.03499101,0.0006691461,0.000757088,0.001657995,0.001422308,0.003790471,0.001320717,0.001052522,0.0001990294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001179266,"about_ca_system_score_gemma":0.001651439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003707778,"about_ca_topic_score_gemma":0.004932108,"domain_scores_codex":[0.9916937,0.00253628,0.0006545408,0.001343127,0.003118526,0.0006538118],"domain_scores_gemma":[0.9542338,0.02915878,0.006627103,0.004783086,0.004848645,0.0003487281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008111766,0.0007609235,0.3331147,0.001132387,0.0002583624,0.004228123,0.0125037,0.04721941,0.1347222,0.0183922,0.003101259,0.4437557],"study_design_scores_gemma":[0.00008216942,0.0006735618,0.1125452,0.0004573537,0.0005780004,0.003179444,0.003413914,0.6718457,0.174018,0.02255343,0.01045698,0.0001961569],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6221396,0.000567366,0.3670848,0.0004096175,0.00004502899,0.000178592,0.000329288,0.007297831,0.001947991],"genre_scores_gemma":[0.8962969,0.0001688756,0.1022392,0.0000771854,0.00002116793,0.00007430744,0.0003603895,0.000341832,0.0004201682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004685577,"threshold_uncertainty_score":0.02418339,"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","authors":[{"name":"Xu Yang","is_ca":true},{"name":"Wenhan Zhu","is_ca":true},{"name":"Michael Pacheco","is_ca":true},{"name":"Jiayuan Zhou","is_ca":true},{"name":"Shaowei Wang","is_ca":true},{"name":"Xing Hu","is_ca":false},{"name":"Kui Liu","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002622185,0.002051324,0.0006531539,0.003086383,0.0005843059,0.001535895,0.002047346,0.001624485,0.002722497],"category_scores_gemma":[0.01246049,0.0007147497,0.001765421,0.001042673,0.000717176,0.003531368,0.002437567,0.003296476,0.001783106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542458,"about_ca_system_score_gemma":0.002514772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01303483,"about_ca_topic_score_gemma":0.02700873,"domain_scores_codex":[0.997197,0.0008561843,0.0002620358,0.0008798506,0.0006101724,0.0001946991],"domain_scores_gemma":[0.9921863,0.005177228,0.000526986,0.001017938,0.000851364,0.0002401932],"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":[0.0006594124,0.0007115697,0.03622313,0.001098205,0.0002674294,0.0007885565,0.001348558,0.07894886,0.0324242,0.003741959,0.01673226,0.8270559],"study_design_scores_gemma":[0.00005313532,0.0001559919,0.004192709,0.00007858465,0.00009801596,0.0002520168,0.0003200603,0.9633134,0.01716241,0.007351804,0.006948345,0.00007357218],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830833,0.002906818,0.7010432,0.00188078,0.0002629302,0.0004772064,0.005141542,0.1016603,0.003543777],"genre_scores_gemma":[0.5136851,0.0003959756,0.4736831,0.0005234348,0.00005220999,0.000258339,0.008393742,0.0009807955,0.002027283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01303483,"threshold_uncertainty_score":0.02591789,"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","authors":[{"name":"Junkai Chen","is_ca":false},{"name":"Zhenhao Li","is_ca":true},{"name":"Qiheng Mao","is_ca":false},{"name":"Xing Hu","is_ca":false},{"name":"Kui Liu","is_ca":false},{"name":"Xin Xia","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1905473,0.0008006697,0.0008658379,0.008477343,0.00247516,0.008369639,0.002198256,0.003209493,0.002563265],"category_scores_gemma":[0.6664146,0.0009525642,0.0008508506,0.003416712,0.003051926,0.01079276,0.005454425,0.003398732,0.002207048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007260213,"about_ca_system_score_gemma":0.0107979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003834169,"about_ca_topic_score_gemma":0.004547938,"domain_scores_codex":[0.7449617,0.1468888,0.02111676,0.01123113,0.07154385,0.004257803],"domain_scores_gemma":[0.1561655,0.5341199,0.06310776,0.02018238,0.2196111,0.006813353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001404561,0.00045555,0.1496185,0.007530111,0.0002384557,0.001158409,0.1760799,0.004122589,0.0352952,0.01355615,0.04315835,0.5673823],"study_design_scores_gemma":[0.0007760562,0.00337038,0.2746892,0.01690425,0.0007961949,0.00423579,0.1892473,0.07326375,0.05308099,0.0470354,0.3348754,0.001725379],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7414639,0.004835037,0.1850963,0.02830827,0.0008119354,0.002774519,0.001031387,0.004377065,0.03130161],"genre_scores_gemma":[0.9110454,0.001364499,0.07729882,0.003758001,0.0002561965,0.001374098,0.001033237,0.0007037598,0.003165913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1905473,"threshold_uncertainty_score":0.9981993,"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","authors":[{"name":"Mohayeminul Islam","is_ca":true},{"name":"Ajay Kumar Jha","is_ca":false},{"name":"Ildar Akhmetov","is_ca":false},{"name":"Sarah Nadi","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037398,0.0009335357,0.0004504528,0.006785265,0.001766666,0.001437217,0.001659569,0.0008087526,0.001404865],"category_scores_gemma":[0.03325842,0.0007269117,0.000814471,0.007560704,0.001461097,0.003716834,0.003577852,0.00164071,0.00102841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002264278,"about_ca_system_score_gemma":0.00287679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009194119,"about_ca_topic_score_gemma":0.01939045,"domain_scores_codex":[0.9924935,0.001132235,0.0008106896,0.001671825,0.003221868,0.0006700605],"domain_scores_gemma":[0.9588422,0.01206528,0.01229245,0.00755219,0.008251534,0.00099642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007320521,0.0003569493,0.5347706,0.002500174,0.0001665225,0.002393225,0.01639627,0.008929322,0.03542762,0.00901311,0.03737014,0.3519439],"study_design_scores_gemma":[0.00006160542,0.000353856,0.6374365,0.0008199576,0.0002149217,0.004001486,0.006891799,0.06066654,0.06164294,0.008505732,0.2190332,0.0003715271],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8917039,0.001242747,0.06233282,0.0007097376,0.0001588065,0.0004931267,0.01355885,0.01849193,0.01130806],"genre_scores_gemma":[0.7822109,0.001197242,0.1519442,0.0008138504,0.00009081863,0.001440787,0.0470232,0.005546059,0.009732964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009194119,"threshold_uncertainty_score":0.01977819,"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","authors":[{"name":"Roozbeh Aghili","is_ca":true},{"name":"Heng Li","is_ca":true},{"name":"Foutse Khomh","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06805147,0.0009700778,0.001814078,0.005517486,0.004466236,0.01795575,0.003481667,0.004170741,0.001985722],"category_scores_gemma":[0.2549001,0.0009920477,0.001512507,0.008291818,0.009983061,0.0367525,0.007122133,0.006076673,0.001402994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004048408,"about_ca_system_score_gemma":0.01463811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005782754,"about_ca_topic_score_gemma":0.004517729,"domain_scores_codex":[0.8911175,0.06561345,0.01158444,0.006970143,0.02160419,0.003110188],"domain_scores_gemma":[0.6355125,0.2083025,0.03072031,0.0818717,0.04093167,0.00266141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005956238,0.0003888538,0.08581156,0.0053353,0.00032225,0.001110846,0.0365793,0.009216866,0.005820565,0.3037823,0.05163791,0.4993985],"study_design_scores_gemma":[0.0001108999,0.0002242429,0.02795163,0.01232043,0.000350294,0.001856887,0.05669162,0.01798371,0.01360462,0.464801,0.4037194,0.000385294],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1462523,0.02576927,0.5130436,0.2582791,0.002038426,0.002055793,0.009764718,0.003161173,0.03963563],"genre_scores_gemma":[0.7234229,0.02198504,0.2146043,0.02108455,0.001747768,0.002243602,0.009352604,0.001084166,0.004474954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06805147,"threshold_uncertainty_score":0.3598949,"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","authors":[{"name":"Lipeng He","is_ca":true},{"name":"Tian-Yu Tu","is_ca":false},{"name":"Jian Liu","is_ca":false},{"name":"Kui Ren","is_ca":false},{"name":"Chun Chen","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002248029,0.001114868,0.001012978,0.001728668,0.0006536474,0.001479549,0.001413154,0.001359464,0.001625248],"category_scores_gemma":[0.00898841,0.0004272047,0.0007353798,0.0006860171,0.001444298,0.004329004,0.002559088,0.001898787,0.0007998877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006748035,"about_ca_system_score_gemma":0.001601441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001765347,"about_ca_topic_score_gemma":0.002668342,"domain_scores_codex":[0.9981287,0.0005338275,0.0001166349,0.0003803953,0.0006399565,0.0002005748],"domain_scores_gemma":[0.9948428,0.002049137,0.001117151,0.001319314,0.0004311728,0.0002403996],"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":[0.0009790785,0.0005507726,0.06005504,0.0003766639,0.0001809164,0.000560443,0.0005820195,0.3309473,0.02752233,0.02560046,0.01473007,0.5379148],"study_design_scores_gemma":[0.00003064099,0.0001784845,0.00211615,0.00003109216,0.00002090959,0.0002935207,0.00008559258,0.9677633,0.009076159,0.01737196,0.003000543,0.00003167632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2490775,0.001441017,0.723272,0.001409248,0.0001216814,0.0004555799,0.0008426518,0.01746783,0.005912605],"genre_scores_gemma":[0.888467,0.0002991529,0.1072934,0.0003517079,0.00004935564,0.00009531713,0.0009404108,0.0002046775,0.002298967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002248029,"threshold_uncertainty_score":0.01188886,"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","authors":[{"name":"Renzhi Wang","is_ca":true},{"name":"Mingfei Cheng","is_ca":false},{"name":"Xiaofei Xie","is_ca":false},{"name":"Yuan Zhou","is_ca":false},{"name":"Lei Ma","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001273779,0.001298076,0.0003340116,0.0009163119,0.000254231,0.0005513009,0.002340639,0.0009545211,0.003346474],"category_scores_gemma":[0.005496521,0.0004354911,0.0006335419,0.0002877341,0.0008383387,0.001353927,0.0009855236,0.0009440428,0.0005986017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005487496,"about_ca_system_score_gemma":0.0008548227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002484838,"about_ca_topic_score_gemma":0.003154759,"domain_scores_codex":[0.9988719,0.0002942861,0.00006594134,0.0001859362,0.000471233,0.0001106924],"domain_scores_gemma":[0.9969541,0.001777802,0.0003064942,0.0004991258,0.0003663077,0.00009614779],"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":[0.0008613794,0.00049857,0.02393115,0.001033803,0.0002234109,0.001503538,0.0008412727,0.3320419,0.1653492,0.01371714,0.01612977,0.4438688],"study_design_scores_gemma":[0.0001239604,0.0007011437,0.003036974,0.0000635082,0.00006045945,0.0006703407,0.00007748,0.8558918,0.1193086,0.006602414,0.01339579,0.00006758596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1865883,0.0006387783,0.7360482,0.0003783498,0.0001423335,0.0006797118,0.0009830919,0.06771174,0.006829457],"genre_scores_gemma":[0.7055929,0.0001829682,0.2878298,0.0002809165,0.00002523804,0.0003492333,0.001227184,0.00191971,0.002592062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003346474,"threshold_uncertainty_score":0.01119506,"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","authors":[{"name":"Yingjie Fu","is_ca":false},{"name":"Bozhou Li","is_ca":false},{"name":"Linyi Li","is_ca":true},{"name":"Wentao Zhang","is_ca":false},{"name":"Tao Xie","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0106398,0.001395787,0.0008974175,0.001340981,0.0005595933,0.002291641,0.002423454,0.001558181,0.003706945],"category_scores_gemma":[0.07462703,0.0004931991,0.001055517,0.001093288,0.00128266,0.004128648,0.002586553,0.002170048,0.001450717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001466617,"about_ca_system_score_gemma":0.00235127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004488434,"about_ca_topic_score_gemma":0.005330537,"domain_scores_codex":[0.9839138,0.008508175,0.0007676229,0.001453467,0.004884723,0.0004721425],"domain_scores_gemma":[0.9319447,0.0454809,0.002142277,0.01044764,0.008788329,0.001196193],"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":[0.003286815,0.002274633,0.02494879,0.003034739,0.0004879333,0.0005993812,0.002728818,0.2093764,0.03705904,0.01642852,0.03163591,0.6681389],"study_design_scores_gemma":[0.0004802959,0.002503114,0.008158939,0.0004516304,0.0002104257,0.0004314078,0.001215738,0.8979132,0.04633655,0.010257,0.0318669,0.0001747384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6797331,0.003220061,0.266373,0.002674025,0.0004121914,0.0008985984,0.002134926,0.02459657,0.0199575],"genre_scores_gemma":[0.6968561,0.0006539879,0.2905954,0.0005145909,0.00004288229,0.0004022537,0.005660266,0.002079155,0.003195341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0106398,"threshold_uncertainty_score":0.05626935,"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","authors":[{"name":"Cleidson R. B. de Souza","is_ca":false},{"name":"E. Ma","is_ca":true},{"name":"Jesse Wong","is_ca":true},{"name":"Dongwook Yoon","is_ca":true},{"name":"Ivan Beschastnikh","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003906001,0.0004911391,0.000326037,0.009624139,0.001412854,0.003447283,0.001089097,0.0009801278,0.002034848],"category_scores_gemma":[0.0292859,0.0005487078,0.0006162883,0.008820276,0.001227955,0.00735253,0.002836299,0.001047575,0.0005609393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001172803,"about_ca_system_score_gemma":0.001357789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003086518,"about_ca_topic_score_gemma":0.008144623,"domain_scores_codex":[0.9957026,0.002100476,0.0003433088,0.0006534826,0.0009875011,0.0002126153],"domain_scores_gemma":[0.9531955,0.03408312,0.004771584,0.004176746,0.002971628,0.0008015468],"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":[0.00047901,0.0004552617,0.2787185,0.002439094,0.0002905239,0.003972716,0.1534164,0.03542673,0.0180539,0.123645,0.01475481,0.368348],"study_design_scores_gemma":[0.0001144702,0.0003453872,0.1402012,0.001169973,0.0003233595,0.004348526,0.1229541,0.2589418,0.02058906,0.2795079,0.1711908,0.0003134527],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5402408,0.0008971902,0.4341388,0.002007354,0.00006654034,0.0006896952,0.003614846,0.002750587,0.01559417],"genre_scores_gemma":[0.7426009,0.0005767702,0.2498387,0.0001050776,0.00002184569,0.0004666448,0.003344386,0.0004139714,0.002631785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009624139,"threshold_uncertainty_score":0.02065712,"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","authors":[{"name":"Farbod Farhour","is_ca":true},{"name":"Ahmad Abdellatif","is_ca":true},{"name":"E. M. E. Mansour","is_ca":true},{"name":"Emad Shihab","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005951964,0.002241269,0.001852654,0.002539399,0.001925004,0.001305198,0.00330826,0.002062535,0.002597165],"category_scores_gemma":[0.01931144,0.0006568888,0.001128234,0.001267552,0.001501823,0.004213799,0.003905081,0.003041507,0.002243655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001611161,"about_ca_system_score_gemma":0.00369931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01337112,"about_ca_topic_score_gemma":0.02575223,"domain_scores_codex":[0.993958,0.002402441,0.0003454361,0.001910447,0.0009784345,0.0004051698],"domain_scores_gemma":[0.9861813,0.006004495,0.001058105,0.002385841,0.003466714,0.0009036016],"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":[0.002633137,0.002284456,0.02770492,0.001551584,0.0002138965,0.0007028525,0.004212964,0.03771846,0.06564067,0.005367343,0.04209976,0.8098699],"study_design_scores_gemma":[0.0001605401,0.0008997137,0.006641254,0.0001301238,0.0001340419,0.0003339988,0.0008356958,0.9467472,0.02172362,0.00613516,0.01617622,0.00008236658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1807995,0.001943636,0.758029,0.00118289,0.0003271156,0.000926141,0.00137443,0.05034285,0.005074461],"genre_scores_gemma":[0.6117705,0.0002887081,0.3687249,0.0008354835,0.0001993638,0.0008544615,0.006954678,0.001231168,0.009140789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01337112,"threshold_uncertainty_score":0.03147739,"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","authors":[{"name":"Doriane Olewicki","is_ca":true},{"name":"Sarra Habchi","is_ca":true},{"name":"Bram Adams","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02070612,0.0006478004,0.0005608971,0.003449069,0.0006440534,0.002219124,0.001195101,0.001178944,0.001205381],"category_scores_gemma":[0.1995223,0.0003550304,0.0006120332,0.003494607,0.001049318,0.003352669,0.001100038,0.001625656,0.0009612975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290062,"about_ca_system_score_gemma":0.001148935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004130891,"about_ca_topic_score_gemma":0.003996646,"domain_scores_codex":[0.9793782,0.009441298,0.001944935,0.004036426,0.004567663,0.0006315237],"domain_scores_gemma":[0.514272,0.3970731,0.04684094,0.01119122,0.02639301,0.004229721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007159905,0.000677531,0.9178482,0.0008262271,0.0001977063,0.0002200951,0.003894828,0.003172912,0.0009901599,0.0002392796,0.004897445,0.06631968],"study_design_scores_gemma":[0.00007425958,0.00156115,0.9334898,0.0003260328,0.0001602689,0.0007986818,0.00341571,0.04991519,0.002342713,0.0005415631,0.00727146,0.000103167],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931004,0.001237461,0.002518507,0.0003614609,0.00003307489,0.0001189127,0.001230029,0.0002162461,0.001183974],"genre_scores_gemma":[0.9951351,0.0002650223,0.002153003,0.00005118604,0.00003581926,0.00009275146,0.001822666,0.00004073678,0.0004036828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02070612,"threshold_uncertainty_score":0.1095057,"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)","authors":[{"name":"Khouloud Oueslati","is_ca":true},{"name":"Gabriel Laberge","is_ca":true},{"name":"Maxime Lamothe","is_ca":true},{"name":"Foutse Khomh","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00248963,0.001779192,0.0009589106,0.003823457,0.0007189459,0.001324581,0.001812453,0.001356769,0.00186069],"category_scores_gemma":[0.01483726,0.000628332,0.0020836,0.001446749,0.000891896,0.001558167,0.001134968,0.001616119,0.0007103562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001224173,"about_ca_system_score_gemma":0.003765405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032147,"about_ca_topic_score_gemma":0.01794616,"domain_scores_codex":[0.996785,0.0008246491,0.000295607,0.0008252639,0.00107621,0.0001932515],"domain_scores_gemma":[0.9869556,0.009423043,0.001098933,0.0009850197,0.001331744,0.0002057131],"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":[0.0004092722,0.0007352392,0.04425475,0.001145422,0.0003545457,0.001875243,0.0008452783,0.3775247,0.01381049,0.009574661,0.01025083,0.5392195],"study_design_scores_gemma":[0.00005022698,0.0001267524,0.002225915,0.00008988295,0.0001142215,0.0002583449,0.0001957259,0.9729674,0.007828868,0.01238572,0.003722615,0.00003426463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1165589,0.001020969,0.8617915,0.001432709,0.0001131847,0.0006972683,0.003513296,0.01190358,0.002968551],"genre_scores_gemma":[0.5108278,0.0003682417,0.479359,0.0003423096,0.00003868619,0.0005673634,0.006789538,0.000388411,0.001318645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032147,"threshold_uncertainty_score":0.02052277,"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","authors":[{"name":"Jiongchi Yu","is_ca":false},{"name":"Xiaofei Xie","is_ca":false},{"name":"Qiang Hu","is_ca":false},{"name":"Ziming Zhao","is_ca":false},{"name":"Yun Lin","is_ca":false},{"name":"Lei Ma","is_ca":true},{"name":"Ruitao Feng","is_ca":false},{"name":"Frank Liauw","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002634072,0.002665178,0.001159045,0.003319465,0.0008881235,0.001615534,0.003031,0.001542414,0.001205498],"category_scores_gemma":[0.007795872,0.0004004013,0.00111195,0.002329947,0.001150779,0.00254777,0.001913921,0.001945943,0.001324951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00177346,"about_ca_system_score_gemma":0.001888521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01692883,"about_ca_topic_score_gemma":0.01848605,"domain_scores_codex":[0.9968932,0.0004766553,0.0003449534,0.0009801558,0.0008828715,0.0004221149],"domain_scores_gemma":[0.9964618,0.0009592849,0.0003816461,0.0008567582,0.0009525624,0.0003879798],"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":[0.004222825,0.003952868,0.1259791,0.002661347,0.001189946,0.001053286,0.0005007572,0.3375867,0.01862217,0.004351208,0.1532878,0.3465918],"study_design_scores_gemma":[0.0002478261,0.000881858,0.02397524,0.00006933073,0.00006466557,0.0004690237,0.0002406323,0.9503839,0.01142337,0.001696821,0.01046339,0.00008401052],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8364463,0.006699526,0.05632481,0.001867175,0.002205693,0.001179109,0.03106352,0.05599587,0.008217947],"genre_scores_gemma":[0.8864237,0.0008609109,0.04521307,0.0005502438,0.0002052773,0.0002682903,0.06394218,0.0005053142,0.002030939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01692883,"threshold_uncertainty_score":0.03366059,"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","authors":[{"name":"Shayan Noei","is_ca":true},{"name":"Heng Li","is_ca":true},{"name":"Ying Zou","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01319158,0.000385818,0.0003242744,0.002713337,0.0007145263,0.001951965,0.001124836,0.0007648472,0.001337474],"category_scores_gemma":[0.1194781,0.0005055139,0.0004401279,0.003421723,0.001237098,0.002800369,0.001271755,0.001544331,0.0004182291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001145561,"about_ca_system_score_gemma":0.0011218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00249332,"about_ca_topic_score_gemma":0.003696985,"domain_scores_codex":[0.9879704,0.003681946,0.001689359,0.001948643,0.004063808,0.0006457414],"domain_scores_gemma":[0.6550581,0.2011007,0.09564765,0.01192302,0.03135919,0.004911321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002143703,0.0002498754,0.9615933,0.0002169123,0.00007980589,0.0002567625,0.008212707,0.0005025575,0.00147057,0.0003558344,0.0005192449,0.02632806],"study_design_scores_gemma":[0.0000158905,0.0003380632,0.9877395,0.0000741941,0.00003080399,0.000313406,0.006525125,0.002152203,0.0006351253,0.00026513,0.001880628,0.00002982727],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966027,0.000233511,0.001634719,0.0001375307,0.00000674994,0.0000699609,0.0002518673,0.0000383194,0.00102451],"genre_scores_gemma":[0.9970715,0.0001469436,0.00178758,0.00004363466,0.000007413488,0.00009229391,0.0003842934,0.00003041197,0.0004359071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01319158,"threshold_uncertainty_score":0.06976455,"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","authors":[{"name":"Yiwei Thomas Hou","is_ca":false},{"name":"Lihua Guo","is_ca":false},{"name":"Chijin Zhou","is_ca":false},{"name":"Quan Zhang","is_ca":false},{"name":"Wenhuan Liu","is_ca":false},{"name":"C. P. Sun","is_ca":true},{"name":"Yu Jiang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001172467,0.001135846,0.0007757872,0.001891567,0.000663511,0.0008306207,0.0008666542,0.0009640473,0.0007391809],"category_scores_gemma":[0.007263238,0.0002782176,0.0004302582,0.0004067138,0.0005536036,0.001805171,0.001332959,0.0007997554,0.001104732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002713082,"about_ca_system_score_gemma":0.0004820064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007508326,"about_ca_topic_score_gemma":0.001313016,"domain_scores_codex":[0.9981354,0.0003368343,0.0001029682,0.0003940151,0.0007984911,0.0002322581],"domain_scores_gemma":[0.9955662,0.001065014,0.00105694,0.001337799,0.0007871494,0.0001869651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007871025,0.0006230848,0.0738163,0.0003787925,0.0002191248,0.0009196192,0.0007925273,0.02076963,0.1258353,0.001840631,0.0107792,0.7632387],"study_design_scores_gemma":[0.0000610797,0.002667498,0.0638459,0.0001538092,0.0002192912,0.005008939,0.0008576065,0.5714704,0.3354663,0.00294342,0.01714797,0.0001577935],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.827668,0.001697151,0.1480779,0.0003930316,0.0002175938,0.0002067405,0.0002568201,0.01625079,0.005232038],"genre_scores_gemma":[0.9581792,0.0001886116,0.03947859,0.0001447097,0.00003156853,0.00002771846,0.000362876,0.000145385,0.001441324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001891567,"threshold_uncertainty_score":0.006200671,"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","authors":[{"name":"Haibo Wang","is_ca":true},{"name":"Zezhong Xing","is_ca":false},{"name":"C. P. Sun","is_ca":true},{"name":"Zheng Wang","is_ca":false},{"name":"Shin Hwei Tan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004671357,0.00200689,0.001174666,0.004999228,0.0009833543,0.001944411,0.002517527,0.001193202,0.001825495],"category_scores_gemma":[0.03185955,0.001290797,0.002924198,0.003388688,0.001506898,0.003607989,0.003822718,0.003033333,0.002038392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006948,"about_ca_system_score_gemma":0.002685869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002479093,"about_ca_topic_score_gemma":0.00617908,"domain_scores_codex":[0.9915176,0.002409146,0.0007811349,0.002094422,0.002809739,0.0003879951],"domain_scores_gemma":[0.9787411,0.009060334,0.001831923,0.006939915,0.003137769,0.0002889553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005956981,0.0007958873,0.03383257,0.001937583,0.0003955423,0.0009209248,0.002834933,0.04990559,0.08773897,0.01526195,0.02988851,0.7758919],"study_design_scores_gemma":[0.0003216516,0.0007008758,0.01446669,0.0005020737,0.0004694298,0.001939902,0.001024465,0.6992407,0.1364221,0.04941817,0.09531751,0.0001763973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07891822,0.0007444045,0.8396897,0.0006774698,0.00007683066,0.0005430279,0.001920579,0.07463872,0.002791066],"genre_scores_gemma":[0.1629332,0.0005369023,0.8156297,0.0004374955,0.00004907389,0.000443658,0.01166384,0.006643728,0.00166234],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004999228,"threshold_uncertainty_score":0.02470475,"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","authors":[{"name":"Mootez Saad","is_ca":true},{"name":"José Antonio Hernández López","is_ca":false},{"name":"Boqi Chen","is_ca":true},{"name":"Dániel Varró","is_ca":false},{"name":"Tushar Sharma","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007975062,0.0008001346,0.0005373412,0.00107966,0.0003937839,0.0007702113,0.001538736,0.0006336298,0.001976058],"category_scores_gemma":[0.003810895,0.0003994316,0.0009833388,0.0006369354,0.0005519286,0.001447208,0.001191185,0.001318392,0.001253583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005297766,"about_ca_system_score_gemma":0.001387517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003341905,"about_ca_topic_score_gemma":0.009192916,"domain_scores_codex":[0.9993107,0.0001363843,0.00004081957,0.0001599602,0.0002919869,0.00006009433],"domain_scores_gemma":[0.9984639,0.0007280737,0.0001390262,0.000291068,0.0003346867,0.00004329547],"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":[0.0003738739,0.0002345663,0.003853264,0.0003453953,0.0001170575,0.0005411748,0.0005718721,0.1462316,0.09092842,0.01695791,0.01290596,0.7269388],"study_design_scores_gemma":[0.00002170037,0.00007223363,0.0004543065,0.00001708269,0.00002433501,0.0001667365,0.00005378006,0.9662142,0.02136898,0.006397401,0.005191395,0.00001786314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02356315,0.0001869272,0.9668588,0.0001392007,0.00004302226,0.00007124526,0.0001966078,0.008108311,0.0008327282],"genre_scores_gemma":[0.2478322,0.0002408371,0.7416704,0.0003508778,0.00005716924,0.0002656317,0.001848395,0.002052319,0.00568213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003341905,"threshold_uncertainty_score":0.006644905,"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","authors":[{"name":"Huimin Hu","is_ca":false},{"name":"Yingying Wang","is_ca":true},{"name":"Julia Rubin","is_ca":true},{"name":"Michael Pradel","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01965829,0.0005311784,0.0003912555,0.003428265,0.001028882,0.001643682,0.001288583,0.0008818586,0.001390445],"category_scores_gemma":[0.1864453,0.0005836556,0.0003100416,0.002568746,0.001927084,0.003912123,0.0020741,0.002139419,0.0004201579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006959908,"about_ca_system_score_gemma":0.001232788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001950559,"about_ca_topic_score_gemma":0.002323758,"domain_scores_codex":[0.9807842,0.008362874,0.002045238,0.002349979,0.005663549,0.0007941647],"domain_scores_gemma":[0.6027452,0.2366589,0.09499525,0.0182035,0.04190523,0.005491954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003686884,0.0004543705,0.9053479,0.0004597038,0.0001019336,0.0006015427,0.03861083,0.000521938,0.002643862,0.0006614327,0.001712866,0.04851492],"study_design_scores_gemma":[0.00004510229,0.001123304,0.9454249,0.0003519808,0.00007777489,0.001252755,0.03082201,0.00671124,0.002559137,0.0009557027,0.01058241,0.00009365995],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968978,0.0001884824,0.001259206,0.0001713766,0.000009463416,0.00004659496,0.0001485798,0.00007441913,0.001204128],"genre_scores_gemma":[0.9976841,0.0001276276,0.001259637,0.00008177973,0.00001243646,0.00007731518,0.0002744886,0.00004030961,0.0004421594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01965829,"threshold_uncertainty_score":0.1039641,"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","authors":[{"name":"Hengcheng Zhu","is_ca":false},{"name":"Valerio Terragni","is_ca":false},{"name":"Lili Wei","is_ca":true},{"name":"Shing-Chi Cheung","is_ca":false},{"name":"Jiarong Wu","is_ca":false},{"name":"Yepang Liu","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01596562,0.001171021,0.000835544,0.004196637,0.0009501083,0.004669188,0.002749005,0.002727513,0.001338948],"category_scores_gemma":[0.1798463,0.001376141,0.001033503,0.001986195,0.005152537,0.01239184,0.003499215,0.002084877,0.0005199747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001558419,"about_ca_system_score_gemma":0.002327923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003050309,"about_ca_topic_score_gemma":0.002743011,"domain_scores_codex":[0.9722415,0.01272144,0.002793113,0.002828043,0.008027589,0.001388248],"domain_scores_gemma":[0.7189856,0.1955202,0.02952386,0.03528652,0.01867695,0.002006954],"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":[0.001001232,0.0006571236,0.1544165,0.001850223,0.0002765476,0.00582518,0.01834038,0.1426561,0.04087816,0.3354688,0.004641004,0.2939888],"study_design_scores_gemma":[0.0001066351,0.0007555234,0.01578574,0.00127814,0.000271384,0.003743777,0.002633297,0.5179235,0.0531892,0.3707064,0.03330152,0.0003047872],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1610315,0.0007137136,0.8311719,0.0005414739,0.00006836399,0.0003104279,0.0002785719,0.003071754,0.00281233],"genre_scores_gemma":[0.7063916,0.000319698,0.2900509,0.0003338907,0.0000673085,0.0004319506,0.0006862753,0.0007155598,0.00100287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01596562,"threshold_uncertainty_score":0.08443522,"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","authors":[{"name":"Anji Li","is_ca":false},{"name":"Neng Zhang","is_ca":false},{"name":"Ying Zou","is_ca":true},{"name":"Jian Wang","is_ca":false},{"name":"Zibin Zheng","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004473238,0.002796678,0.001295869,0.008696754,0.002110081,0.002123778,0.002953367,0.002679536,0.004101353],"category_scores_gemma":[0.03155835,0.0008197028,0.002352061,0.003447598,0.001615833,0.005551907,0.004983794,0.002849394,0.002916004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002053105,"about_ca_system_score_gemma":0.0037702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02632981,"about_ca_topic_score_gemma":0.05241246,"domain_scores_codex":[0.9931105,0.00145704,0.0004349757,0.002185591,0.002425434,0.0003864954],"domain_scores_gemma":[0.9862316,0.007161349,0.00119213,0.002803186,0.002125774,0.0004859848],"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":[0.001563999,0.0007611581,0.02792386,0.002811779,0.0004816199,0.003040181,0.005110279,0.05347438,0.04961157,0.01426974,0.08702515,0.7539263],"study_design_scores_gemma":[0.0002922559,0.0002604919,0.01573789,0.0004450931,0.0002902934,0.001008568,0.001974946,0.76394,0.05160142,0.05887957,0.1051063,0.0004632127],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08997626,0.00166789,0.80845,0.002548062,0.0008141303,0.001620858,0.02002621,0.06303087,0.01186573],"genre_scores_gemma":[0.3315767,0.0007257829,0.6144601,0.001685774,0.0004139683,0.001519361,0.03289322,0.004389375,0.01233584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02632981,"threshold_uncertainty_score":0.05235314,"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","authors":[{"name":"Dominik Frey","is_ca":false},{"name":"Ulf Kargén","is_ca":false},{"name":"Dániel Varró","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004041529,0.001047318,0.0003309522,0.001402133,0.0002494622,0.0005826653,0.001837782,0.001015857,0.0009421203],"category_scores_gemma":[0.02663684,0.0003469301,0.0006860799,0.0008708245,0.0005971987,0.001196101,0.001035316,0.0005837573,0.0002531559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000643165,"about_ca_system_score_gemma":0.0008082365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002262294,"about_ca_topic_score_gemma":0.0028475,"domain_scores_codex":[0.9950825,0.002449463,0.0003867228,0.0006743217,0.001162397,0.000244581],"domain_scores_gemma":[0.969354,0.02330057,0.002130251,0.002649432,0.002186199,0.0003796029],"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":[0.001398317,0.001709772,0.0448966,0.001104196,0.0003119921,0.0005655491,0.001233376,0.4893942,0.09030801,0.003189606,0.001902462,0.3639859],"study_design_scores_gemma":[0.0001708138,0.001687173,0.009125575,0.0000538517,0.0001044802,0.000406274,0.0003483829,0.9337009,0.05142971,0.001444626,0.001494443,0.00003375106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7581987,0.0003691014,0.2339542,0.0001699779,0.00003011112,0.000618798,0.0004446412,0.003939948,0.002274366],"genre_scores_gemma":[0.7940692,0.0001418712,0.2040523,0.00004700147,0.000007092804,0.0002098353,0.0009780793,0.0002044848,0.0002901583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004041529,"threshold_uncertainty_score":0.02137387,"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","authors":[{"name":"Mouna Dhaouadi","is_ca":true},{"name":"Bentley Oakes","is_ca":true},{"name":"Michalis Famelis","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01204773,0.00123389,0.0006590258,0.01056886,0.001668932,0.003757118,0.001542144,0.001627059,0.00140011],"category_scores_gemma":[0.05287255,0.001130895,0.001409272,0.003369209,0.00110865,0.005441541,0.003066278,0.002451709,0.0008733144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001538786,"about_ca_system_score_gemma":0.004692356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004370282,"about_ca_topic_score_gemma":0.01312671,"domain_scores_codex":[0.9879295,0.004918852,0.001064071,0.00108601,0.004616786,0.0003847305],"domain_scores_gemma":[0.9410493,0.03815739,0.006433772,0.005242905,0.00860747,0.0005091476],"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":[0.0002711086,0.0005134546,0.04245823,0.001518713,0.0001967125,0.002444146,0.01009898,0.02042503,0.04640547,0.03526662,0.0175826,0.8228189],"study_design_scores_gemma":[0.0001687259,0.0003478054,0.03390755,0.001193832,0.0003219292,0.001781833,0.006127339,0.6698895,0.09076859,0.1092824,0.08572871,0.0004818404],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1265777,0.0006704507,0.8495694,0.001835456,0.0001237525,0.0009961085,0.002986051,0.01309291,0.004148327],"genre_scores_gemma":[0.2689251,0.0003256857,0.7220737,0.0001869508,0.00005216657,0.0003411942,0.005399452,0.0008506667,0.001844931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01204773,"threshold_uncertainty_score":0.06371522,"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","authors":[{"name":"Weiqi Lu","is_ca":false},{"name":"Yongqiang Tian","is_ca":false},{"name":"Haoyang Ma","is_ca":false},{"name":"Zhenyang Xu","is_ca":true},{"name":"Shing-Chi Cheung","is_ca":false},{"name":"C. P. Sun","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01501504,0.001041518,0.0006899103,0.006897518,0.001267297,0.002408916,0.001741467,0.001313599,0.001796395],"category_scores_gemma":[0.1880314,0.0007779203,0.0006564741,0.004226132,0.00181404,0.005135497,0.002854814,0.001777893,0.0005551756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001796522,"about_ca_system_score_gemma":0.002084874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003884543,"about_ca_topic_score_gemma":0.00469175,"domain_scores_codex":[0.9771482,0.007505233,0.003092492,0.002500128,0.008599296,0.001154783],"domain_scores_gemma":[0.6959439,0.1987914,0.05381682,0.01163349,0.03641923,0.003395086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005974667,0.000832202,0.8071393,0.001807947,0.0001793295,0.00166191,0.02977246,0.001154591,0.003592044,0.001357961,0.006653103,0.1452517],"study_design_scores_gemma":[0.0001093992,0.002052093,0.895957,0.001890538,0.0003953773,0.004221385,0.0350241,0.0197158,0.01028041,0.002253154,0.02780365,0.0002971117],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902249,0.001033885,0.004973555,0.000459453,0.00003036603,0.0002329929,0.0007246211,0.0008679438,0.001452313],"genre_scores_gemma":[0.991015,0.0004716914,0.006120857,0.0002290662,0.00001974404,0.0001917494,0.001034719,0.0002112456,0.0007058327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01501504,"threshold_uncertainty_score":0.07940805,"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","authors":[{"name":"Shuwei Song","is_ca":false},{"name":"Ting Chen","is_ca":false},{"name":"Ao Qiao","is_ca":false},{"name":"Xiapu Luo","is_ca":false},{"name":"Leqing Wang","is_ca":false},{"name":"Zheyuan He","is_ca":false},{"name":"Ting Wang","is_ca":false},{"name":"Xiaodong Lin","is_ca":true},{"name":"Peng He","is_ca":false},{"name":"Wensheng Zhang","is_ca":false},{"name":"Xiaosong Zhang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002478441,0.0008302202,0.0008165525,0.002495996,0.0008825408,0.001865896,0.001387352,0.001456834,0.002359014],"category_scores_gemma":[0.01056137,0.0006779979,0.0003988188,0.002021705,0.001618185,0.004350273,0.001732637,0.00150345,0.001318824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184715,"about_ca_system_score_gemma":0.002206261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004214287,"about_ca_topic_score_gemma":0.003332086,"domain_scores_codex":[0.9966461,0.0009598567,0.0002107872,0.0007373819,0.001225864,0.0002199682],"domain_scores_gemma":[0.9895815,0.004295861,0.001518481,0.002973696,0.001353127,0.000277356],"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":[0.0005961123,0.0003913276,0.01754391,0.0003647616,0.00006853621,0.0004228468,0.0004526117,0.1176669,0.0454879,0.0288977,0.01019158,0.7779158],"study_design_scores_gemma":[0.00004112431,0.0001278183,0.002140618,0.00004816414,0.00001913526,0.0003983897,0.0001026217,0.9257131,0.03983193,0.02249,0.009018427,0.00006874723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06591935,0.00109134,0.9028373,0.0006228667,0.00009429987,0.0001725753,0.0003246189,0.02595513,0.002982548],"genre_scores_gemma":[0.6369744,0.0006773482,0.3582783,0.0001596468,0.00005681165,0.00008223194,0.0006494731,0.0006087672,0.002513091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004214287,"threshold_uncertainty_score":0.01310736,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}