{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3468,"total_is_capped":false,"direct_labels_cover":10,"predictions_cover":3468,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"180aa56179b7","filters":{"topic":"Software Engineering Research"}},"results":[{"id":"W4238014149","doi":"10.1002/(issn)1097-024x","title":"Software: Practice and Experience","year":2006,"lang":"en","type":"paratext","venue":"Software Practice and Experience","topic":"Software Engineering Research","field":"Computer Science","cited_by":1222,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Software engineering; Computer science; Coding (social sciences); Software; Software development; World Wide Web; Data science; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01775938229433564,"gpt":0.3186743183254481,"spread":0.3009149360311125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001065391,0.001059602,0.0008890435,0.0004596104,0.0008260795,0.002173641,0.002380593,0.0007572164,0.0001718208],"category_scores_gemma":[0.0297497,0.001082168,0.0001290318,0.001304458,0.0007426676,0.007866909,0.002363822,0.00186723,0.001099012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002403057,"about_ca_system_score_gemma":0.0006179874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199809,"about_ca_topic_score_gemma":0.000008252614,"domain_scores_codex":[0.992669,0.0004449032,0.0008778806,0.002646273,0.001846607,0.001515349],"domain_scores_gemma":[0.9831273,0.01242138,0.0007025293,0.002182262,0.0008924191,0.0006741085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005091348,0.001355337,0.003306032,0.001763421,0.0004748566,0.003022152,0.09837023,0.0004680287,0.0004068577,0.002362908,0.637437,0.250524],"study_design_scores_gemma":[0.0005340006,0.0002979043,0.0004820054,0.0002957202,0.00005433372,0.001745595,0.001929152,0.0002253302,0.0004299922,0.0001008709,0.9923744,0.00153069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005632037,0.04749209,0.9286602,0.003130559,0.005697714,0.001439856,0.00007471096,0.00169472,0.006178169],"genre_scores_gemma":[0.02500012,0.01837288,0.9008733,0.00573868,0.001695665,0.001806066,0.000138004,0.0003912469,0.04598403],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3549374,"threshold_uncertainty_score":0.9996787,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W397180395","doi":"10.1007/978-1-84800-044-5_11","title":"Selecting Empirical Methods for Software Engineering Research","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":1135,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; National Research Council Canada; University of Toronto","funders":"","keywords":"Empirical research; Computer science; Variety (cybernetics); Data science; Software engineering; Software; Management science; Method engineering; Systems engineering; Engineering; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2458908885786854,"gpt":0.4898852247386108,"spread":0.2439943361599254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00766504,0.0004486704,0.000514753,0.001501139,0.0002308699,0.0003287687,0.00211117,0.0006926823,0.00009056141],"category_scores_gemma":[0.01041284,0.0004529557,0.0002645167,0.000455002,0.00006222677,0.0002162665,0.001079687,0.002068063,0.0001317463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005271032,"about_ca_system_score_gemma":0.0003831912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008385593,"about_ca_topic_score_gemma":0.000002595517,"domain_scores_codex":[0.9958805,0.00005524487,0.0005015642,0.001137246,0.001077842,0.001347535],"domain_scores_gemma":[0.9750503,0.02235379,0.00006167553,0.001206116,0.0009657766,0.0003623026],"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":[0.00002068616,0.0000366536,0.0002032515,0.0007480963,0.0002835625,0.0001009226,0.000449084,0.0007258672,0.0001830985,0.3641641,0.02728331,0.6058013],"study_design_scores_gemma":[0.000296106,0.0002776222,0.0001028816,0.0002623736,0.00001157539,0.0000764376,0.000003140205,0.0531478,0.001605607,0.01155755,0.9316732,0.0009857671],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003303576,0.0007173737,0.9720299,0.0001341684,0.0006082591,0.0007119859,0.000002996174,0.00156233,0.02422966],"genre_scores_gemma":[0.00002345094,0.00001710418,0.7964956,0.00005439599,0.0004610905,0.00006473403,0.00000650903,0.0001413716,0.2027358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9043898,"threshold_uncertainty_score":0.9997922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101832700","doi":"10.1016/j.scico.2009.02.007","title":"Comparison and evaluation of code clone detection techniques and tools: A qualitative approach","year":2009,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Engineering Research","field":"Computer Science","cited_by":1002,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; clone (Java method); Schema (genetic algorithms); Taxonomy (biology); Set (abstract data type); Source code; Context (archaeology); Data mining; Software engineering; Artificial intelligence; Programming language; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.09302423369983133,"gpt":0.4135048661088837,"spread":0.3204806324090523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004972385,0.00009790443,0.0002001876,0.0003392632,0.0001026397,0.0002337554,0.0004616484,0.00003727739,1.428887e-7],"category_scores_gemma":[0.0002609769,0.00009196169,0.00002038176,0.001056434,0.0004029382,0.001032707,0.0001999039,0.0001097819,1.157391e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004903035,"about_ca_system_score_gemma":0.00009469848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001275059,"about_ca_topic_score_gemma":6.857364e-7,"domain_scores_codex":[0.9980125,0.0001277662,0.000273592,0.000385245,0.0009648362,0.0002360292],"domain_scores_gemma":[0.9987363,0.0002577118,0.0001371256,0.0002713394,0.0005210676,0.00007647544],"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":[0.000003270738,0.00005933625,0.0002674476,0.00002708434,0.000003255732,2.059415e-7,0.005686155,0.0002050135,0.005428057,0.001581539,0.000001177803,0.9867374],"study_design_scores_gemma":[0.0003366147,0.0009253997,0.01883152,0.00008600739,0.000009553592,0.00002774069,0.0004368784,0.8906057,0.08668336,0.001843371,0.00004134693,0.0001724339],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4190185,0.0001753012,0.5803558,0.0000333016,0.00003144916,0.000278983,2.22866e-7,0.00008225728,0.00002421618],"genre_scores_gemma":[0.5965331,0.000002459613,0.4034371,0.000002149898,0.00001225399,0.0000104739,2.596381e-7,0.000001795787,4.467144e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9865651,"threshold_uncertainty_score":0.3750089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079317829","doi":"10.1145/1134285.1134336","title":"Who should fix this bug?","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":921,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Open source; Computer science; Eclipse; Software engineering; Debugging; Software bug; Process (computing); Open-source software development; World Wide Web; Classifier (UML); Usability; Data science; Artificial intelligence; Programming language; Software; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02326066540004923,"gpt":0.2700901157109861,"spread":0.2468294503109369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001534306,0.00006605262,0.00006566422,0.0000795851,0.00003857676,0.0001219643,0.0006684659,0.00003867503,0.0002285619],"category_scores_gemma":[0.00009161748,0.00005620761,0.00002956454,0.0003254174,0.00001504958,0.0001979582,0.000196525,0.0001093199,0.0005148196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000299465,"about_ca_system_score_gemma":0.00002664548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002706742,"about_ca_topic_score_gemma":0.0000101504,"domain_scores_codex":[0.9991518,0.00001085901,0.0000827469,0.0002037793,0.0003045477,0.0002462782],"domain_scores_gemma":[0.999212,0.0002456713,0.000007737834,0.0004444332,0.00004132352,0.00004887363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001671758,0.00007915019,0.04849217,0.0000240962,0.0000121969,0.0000764843,0.0001543326,0.001547441,0.001216079,0.1997482,0.7231864,0.02546177],"study_design_scores_gemma":[0.0007373476,0.0001595023,0.3513412,0.00003982119,0.000003673954,0.00005684788,0.000006169126,0.206912,0.03791119,0.01124216,0.3906828,0.00090728],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01579178,0.0001334069,0.9368457,0.001690241,0.000232991,0.00007905643,4.797873e-7,0.0010338,0.04419254],"genre_scores_gemma":[0.8721907,0.000003836036,0.06994259,0.0003063655,0.0001847443,0.00001315984,0.000001095249,0.00001422208,0.05734335],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8669031,"threshold_uncertainty_score":0.6617137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132887549","doi":"10.1145/1368088.1368114","title":"A comparative analysis of the efficiency of change metrics and static code attributes for defect prediction","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":704,"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; Eclipse; Data mining; Naive Bayes classifier; Java; Machine learning; Set (abstract data type); Software bug; Artificial intelligence; Decision tree; Code (set theory); Process (computing); Source code; Software; Predictive power; Programming language; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.1447397305931119,"gpt":0.3278859026072174,"spread":0.1831461720141055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002907091,0.00005035499,0.0001924347,0.0003509806,0.00005077687,0.000007417659,0.0002761057,0.0000181436,0.000001654135],"category_scores_gemma":[0.0004613264,0.00003325213,0.00008381526,0.003004347,0.0000699008,0.000091129,0.00009854978,0.00003656341,1.545131e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001911153,"about_ca_system_score_gemma":0.00002655363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004273521,"about_ca_topic_score_gemma":0.0000117572,"domain_scores_codex":[0.9993165,0.00003317787,0.0001408784,0.0001370814,0.000261864,0.0001104843],"domain_scores_gemma":[0.9978479,0.001672247,0.00005628816,0.000237753,0.000159059,0.00002678308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001588391,0.000257691,0.9665141,0.0001731814,0.001032958,9.181355e-7,0.01113748,0.01312972,0.001235741,0.004441781,0.0007411416,0.001319456],"study_design_scores_gemma":[0.0001357657,0.0001232845,0.3818128,0.000005300536,0.00006392607,0.000001033474,0.00001972235,0.6109011,0.006860109,0.00002563598,0.00002007463,0.00003130497],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4580427,0.0001368985,0.5415286,0.00002846555,0.0000227603,0.0001794281,0.00003278904,0.0000205521,0.000007863421],"genre_scores_gemma":[0.9894051,0.00001766137,0.01051784,0.000007116336,0.000003949974,0.00002588114,0.000001897902,0.000001538532,0.00001902646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5977713,"threshold_uncertainty_score":0.1443489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147386665","doi":"10.1109/tse.2012.70","title":"A large-scale empirical study of just-in-time quality assurance","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":699,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; Polytechnique Montréal","funders":"","keywords":"Computer science; Software quality assurance; Quality assurance; Source lines of code; Quality (philosophy); Software quality; Code review; Scale (ratio); Software; Empirical research; Software quality analyst; Software bug; Data science; Software engineering; Software development; Operations management; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03357803100855729,"gpt":0.3186450643686469,"spread":0.2850670333600896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001012411,0.0002524311,0.0003892574,0.0004684996,0.00006686229,0.0000421339,0.0007570104,0.0001184865,0.00003177331],"category_scores_gemma":[0.0002268539,0.0002722981,0.0001150616,0.0012466,0.00001543389,0.0005652808,0.00001343388,0.0005516079,0.00006862677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001618104,"about_ca_system_score_gemma":0.00004563351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002314978,"about_ca_topic_score_gemma":0.00001388559,"domain_scores_codex":[0.9975502,0.00009868422,0.00047877,0.0004006882,0.0007518968,0.0007197341],"domain_scores_gemma":[0.9973338,0.001505229,0.00005054292,0.0008143466,0.0000762674,0.0002198507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00005005165,0.006012518,0.3428673,0.0003028623,0.0001500655,0.00002677662,0.01719011,0.6293525,0.001325534,0.00002662956,0.0001577823,0.002537933],"study_design_scores_gemma":[0.003371616,0.0006152564,0.9062577,0.0002398083,0.00003534183,0.00003427537,0.0004306241,0.07069996,0.01653085,0.00000615331,0.0005715288,0.001206884],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4709621,0.00003521477,0.528027,0.000009744618,0.0003797666,0.000185237,0.000006736391,0.0003913671,0.000002827599],"genre_scores_gemma":[0.9703541,0.000003844004,0.02937187,0.00001717336,0.00004497297,0.00009999869,5.231033e-7,0.00003759837,0.00006989297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5633904,"threshold_uncertainty_score":0.9999729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158744032","doi":"10.1109/icse.2009.5070510","title":"Predicting faults using the complexity of code changes","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":697,"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":"","keywords":"Computer science; Code (set theory); Source code; Process (computing); Software; Product metric; Product (mathematics); Software bug; Reliability engineering; Programming language; Mathematics; Engineering; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.1164617127977515,"gpt":0.329170741102404,"spread":0.2127090283046524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291145,0.00005197576,0.00007195387,0.00004619731,0.00006541673,0.0000273713,0.0006522551,0.00001933296,0.000006262565],"category_scores_gemma":[0.0002061952,0.00003468847,0.00001864133,0.0002896252,0.00006281628,0.00009197395,0.0001328262,0.0000881307,0.000001934154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001923063,"about_ca_system_score_gemma":0.00002041738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000678787,"about_ca_topic_score_gemma":0.00002018001,"domain_scores_codex":[0.9993272,0.00002453349,0.0000824934,0.0001283692,0.0002604175,0.0001769206],"domain_scores_gemma":[0.9992805,0.000234169,0.00002641517,0.0003656436,0.00006024813,0.00003304056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003653484,0.0004799559,0.2246416,0.0001968664,0.0001424901,0.00005395701,0.0148944,0.04671738,0.1059376,0.3909384,0.002516778,0.213444],"study_design_scores_gemma":[0.0001586757,0.0001039559,0.118188,0.00003144137,0.000002054478,0.00002662882,0.00004259718,0.8614579,0.01716857,0.002558805,0.0001580312,0.0001034189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3637964,0.00005016679,0.6329863,0.002281182,0.00009580031,0.0001049638,0.000001446185,0.0002351621,0.0004486321],"genre_scores_gemma":[0.9473111,0.00000152108,0.05251336,0.00009313103,0.00003652812,8.011929e-7,1.82904e-7,0.000002362618,0.00004102875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8147405,"threshold_uncertainty_score":0.1414555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2360967250","doi":"10.1145/2884781.2884804","title":"Automatically learning semantic features for defect prediction","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":692,"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","keywords":"Computer science; Software bug; Focus (optics); ENCODE; Machine learning; Code (set theory); Artificial intelligence; Software; Software engineering; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01051924701454742,"gpt":0.2535673509846479,"spread":0.2430481039701005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000326925,0.00006303542,0.0000670068,0.00007888087,0.00006345475,0.0000751193,0.0003217389,0.00003965156,0.00001668448],"category_scores_gemma":[0.001859733,0.00003835024,0.00005640797,0.0001344264,0.00001434933,0.0002151073,0.00009204545,0.00006235942,0.00006586353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003524547,"about_ca_system_score_gemma":0.00002906645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002421863,"about_ca_topic_score_gemma":9.201623e-7,"domain_scores_codex":[0.9992512,0.00002342905,0.00008487861,0.0002080024,0.0001990085,0.0002334086],"domain_scores_gemma":[0.998128,0.001502732,0.00001275943,0.0002329664,0.00006148891,0.00006203202],"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":[0.00002490814,0.0001074377,0.08008159,0.0002857783,0.0001674244,0.00001771981,0.0006210024,0.001738514,0.03759814,0.1567738,0.03579654,0.6867871],"study_design_scores_gemma":[0.001919432,0.001054149,0.5221991,0.0002849618,0.00001854651,0.00009713774,0.00001274492,0.4279944,0.0222663,0.009588992,0.01399326,0.0005709878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01675,0.00002253927,0.9806471,0.000760862,0.0001654384,0.0001512095,5.387766e-7,0.001204987,0.0002973021],"genre_scores_gemma":[0.9109014,0.00000308242,0.08544143,0.0000243836,0.00006017871,0.00004311742,4.09138e-7,0.000009468731,0.003516483],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8952057,"threshold_uncertainty_score":0.2226409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056894403","doi":"10.1007/s10664-012-9231-y","title":"What are developers talking about? An analysis of topics and trends in Stack Overflow","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":613,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; World Wide Web; Topic model; Popularity; Data science; Leverage (statistics); Android (operating system); Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03051975966812,"gpt":0.3086728286717767,"spread":0.2781530690036567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000458567,0.000210369,0.0004046834,0.00109529,0.00003457412,0.0001547563,0.0004711421,0.0001231246,0.00002544593],"category_scores_gemma":[0.000766394,0.0002137244,0.00008826797,0.003052292,0.00002474907,0.001645961,0.0002745709,0.0002798129,0.000001825701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001580795,"about_ca_system_score_gemma":0.00001908834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002887784,"about_ca_topic_score_gemma":0.00001842755,"domain_scores_codex":[0.9982768,0.00003708535,0.0003198783,0.0003618928,0.0004098033,0.0005945],"domain_scores_gemma":[0.9985987,0.0005140968,0.00005279211,0.0004914957,0.00005690057,0.0002860132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001967484,0.00004744007,0.9412918,0.00003633161,0.00008597357,0.000009748611,0.001762562,0.03190639,0.00002476729,0.00006435311,0.0000211205,0.02474753],"study_design_scores_gemma":[0.0001341392,0.00002245787,0.9266498,0.00005539847,0.0000231342,0.000003411829,0.00004917225,0.07192862,0.0001544005,0.000003354076,0.0007443918,0.0002317335],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8032327,0.001040182,0.1950268,0.00008378682,0.0003303704,0.00004576622,0.000002603448,0.0002352747,0.000002435391],"genre_scores_gemma":[0.9597165,0.00004380989,0.04004228,0.00004437635,0.00007817997,0.00001177434,0.000008252698,0.00002223369,0.0000325804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1564838,"threshold_uncertainty_score":0.8715428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160517961","doi":"10.1145/1453101.1453146","title":"What makes a good bug report?","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":603,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Victoria","funders":"","keywords":"Eclipse; Computer science; Software bug; Software engineering; Software development; Quality (philosophy); Software; World Wide Web; Data science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02898726885447551,"gpt":0.2706047792222137,"spread":0.2416175103677382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001723376,0.00006575707,0.00007287884,0.00007485099,0.0000590565,0.0001498424,0.000535675,0.00002961296,0.00004490051],"category_scores_gemma":[0.0002744307,0.00005641221,0.00003326643,0.000320431,0.00002532577,0.000769479,0.0001970895,0.00009182806,0.0002398676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002407832,"about_ca_system_score_gemma":0.00006159647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002189164,"about_ca_topic_score_gemma":0.000002145341,"domain_scores_codex":[0.9990501,0.00001154939,0.0001143264,0.0002533599,0.0003391915,0.0002314281],"domain_scores_gemma":[0.9989579,0.0002150026,0.00001592415,0.0006652825,0.00005831412,0.00008756942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001472091,0.0007045485,0.4158189,0.0001405595,0.0002111373,0.05742322,0.008880138,0.001985591,0.004297319,0.1042109,0.2256653,0.1806477],"study_design_scores_gemma":[0.001226674,0.0003615644,0.6333318,0.0001324857,0.000005295517,0.02719155,0.000161751,0.0418519,0.03678714,0.003965304,0.2534595,0.00152498],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1703897,0.0004332023,0.8191385,0.002315438,0.001336222,0.0001340917,1.23427e-7,0.001449487,0.004803224],"genre_scores_gemma":[0.9039453,0.00009479791,0.07052867,0.0001674527,0.00009405325,0.00001729849,8.322561e-7,0.00001136555,0.0251402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7486098,"threshold_uncertainty_score":0.3083093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135198476","doi":"10.1145/1368088.1368161","title":"Predicting defects using network analysis on dependency graphs","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":575,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Dependency (UML); Dependency graph; Graph; Face (sociological concept); Software; Code (set theory); Theoretical computer science; Software engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02803036766470379,"gpt":0.2665311234336598,"spread":0.238500755768956,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002894217,0.0001078801,0.0001496919,0.0003654485,0.0002237812,0.00005874043,0.0005841927,0.00004849784,0.00002245936],"category_scores_gemma":[0.0002509041,0.00009838249,0.0001287468,0.003119956,0.0000201478,0.0002099056,0.0001849449,0.0001775064,0.00002675989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004949027,"about_ca_system_score_gemma":0.00004937096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001122084,"about_ca_topic_score_gemma":0.00001847384,"domain_scores_codex":[0.9985471,0.00004552344,0.0001414026,0.0003560315,0.0004880819,0.0004218113],"domain_scores_gemma":[0.9986292,0.0005996543,0.00002906582,0.0005658232,0.00005711416,0.0001192117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001074803,0.00001466515,0.7501611,0.000002580671,0.0000933229,0.00005912965,0.00008108073,0.2469509,0.00003325976,0.002018885,0.00009903087,0.0004850164],"study_design_scores_gemma":[0.00009985148,0.00004933502,0.2984136,0.00001047076,0.00002511986,0.00002874157,0.000002387013,0.7003577,0.0003404155,0.0005016361,0.00001854643,0.0001522093],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.534081,0.00004582335,0.464921,0.000008879398,0.000111215,0.00004406949,1.23876e-7,0.0003313541,0.0004564453],"genre_scores_gemma":[0.9398189,0.000007621244,0.05995698,0.00004938714,0.00006580932,0.000003752305,5.594284e-7,0.000008331908,0.00008863018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4534068,"threshold_uncertainty_score":0.4011922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2511803001","doi":"10.1145/2970276.2970326","title":"Deep learning code fragments for code clone detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":569,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Singapore Management University; University of Saskatchewan; National Science Foundation","keywords":"Computer science; Identifier; clone (Java method); Java; False positive paradox; Source code; Software maintenance; Code (set theory); Artificial intelligence; Software; Program comprehension; Point (geometry); Static program analysis; Software system; Programming language; Machine learning; Data mining; Software development; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01918773439204367,"gpt":0.2735869598500928,"spread":0.2543992254580492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002889742,0.00007162669,0.00007380657,0.00008533346,0.00009117868,0.00005992032,0.0003906092,0.00004397217,0.00002568955],"category_scores_gemma":[0.0007378277,0.00005072792,0.00003401527,0.0001602314,0.00001389902,0.0002492349,0.0001295457,0.00007312693,0.0001306571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007706306,"about_ca_system_score_gemma":0.00001402489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007604408,"about_ca_topic_score_gemma":0.00001476827,"domain_scores_codex":[0.9991219,0.00002146639,0.00009862486,0.0002586434,0.0002152993,0.0002840638],"domain_scores_gemma":[0.9988295,0.0007399838,0.00002051527,0.0002560747,0.00007770983,0.00007622769],"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":[0.00001973109,0.00004134783,0.01024927,0.00002967814,0.00003576504,0.000005111876,0.0001853511,0.001750454,0.07639933,0.002751288,0.0005758628,0.9079568],"study_design_scores_gemma":[0.002336407,0.0006501107,0.03597401,0.00006700534,0.000006327019,0.00002478487,0.0000182339,0.6173334,0.2837122,0.002345665,0.05696028,0.0005715747],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03093538,0.00002475025,0.9677275,0.000276729,0.0002563536,0.0001396139,5.864228e-7,0.0005418207,0.00009724929],"genre_scores_gemma":[0.9297835,0.000008940287,0.06727229,0.00003103531,0.00006055972,0.00005855663,3.550407e-7,0.00001288027,0.002771853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9073852,"threshold_uncertainty_score":0.2068624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2474835145","doi":"10.1109/tse.2016.2584050","title":"An Empirical Comparison of Model Validation Techniques for Defect Prediction Models","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":566,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Japan Society for the Promotion of Science; Japan Society for the Promotion of Science London; Compute Canada","keywords":"Computer science; Variance (accounting); Context (archaeology); Cross-validation; Model validation; Sample (material); Data mining; Predictive modelling; Software bug; Software; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05422237551678902,"gpt":0.3303165094466313,"spread":0.2760941339298422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212065,0.0002042513,0.0002466572,0.0004190811,0.00008337912,0.00004312172,0.0004915613,0.0001532788,0.000002969512],"category_scores_gemma":[0.0001035692,0.0001782765,0.0001656938,0.0003574999,0.00002276338,0.0009693491,0.000003723997,0.0001737507,0.000002650515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001685106,"about_ca_system_score_gemma":0.00006566503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003028263,"about_ca_topic_score_gemma":6.254527e-7,"domain_scores_codex":[0.9984806,0.00002520264,0.0003582603,0.0004250034,0.0003868086,0.0003241243],"domain_scores_gemma":[0.9981589,0.0008458697,0.0000532902,0.0006226194,0.0001861913,0.0001331503],"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":[0.00001689331,0.0001314405,0.0003223868,0.00005110861,0.00002859238,2.914992e-7,0.0002106711,0.955961,0.01061431,0.0001580717,0.00005540389,0.03244981],"study_design_scores_gemma":[0.0002099715,0.0002504718,0.0001038202,0.00007659016,0.00001146334,0.000002492684,0.000002023153,0.7427968,0.2561853,0.0001876273,0.00002553545,0.0001478868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02838135,0.00001809275,0.9689415,0.00003086786,0.0002841988,0.0003858494,0.00006864707,0.001887654,0.000001916634],"genre_scores_gemma":[0.6654122,0.000005783577,0.3343129,0.000004862213,0.0000252649,0.0001907291,0.000002072479,0.00003141115,0.0000148123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6370308,"threshold_uncertainty_score":0.7269905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156833313","doi":"10.1145/1368088.1368151","title":"An approach to detecting duplicate bug reports using natural language and execution information","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":544,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Eclipse; Software bug; Natural language; Security bug; Open source; Information retrieval; Natural language processing; Programming language; Software; Information security; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.018405413256578,"gpt":0.2639931120956284,"spread":0.2455876988390504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002488884,0.00006186896,0.00005724174,0.0001449602,0.0001166543,0.0001121835,0.0001491523,0.00002769319,5.578729e-7],"category_scores_gemma":[0.0002050789,0.00005669791,0.00001057566,0.0003303216,0.00001081102,0.001272634,0.0001158909,0.0000958044,0.000003582147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004425009,"about_ca_system_score_gemma":0.00002119034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001576611,"about_ca_topic_score_gemma":6.854319e-7,"domain_scores_codex":[0.9993237,0.00001247589,0.0001288503,0.0001652812,0.0002005264,0.0001692173],"domain_scores_gemma":[0.9994828,0.00003801937,0.00002906825,0.0003106919,0.0000530589,0.00008635505],"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":[0.00004016091,0.0002370627,0.1508957,0.0003371957,0.00006492489,0.0004411375,0.1042659,0.07989147,0.2043815,0.002742796,0.0006535749,0.4560486],"study_design_scores_gemma":[0.00007831302,0.00002660249,0.07938124,0.000006613232,9.234465e-7,0.001335873,0.0001627463,0.9095296,0.009251462,0.00001322672,0.00005546892,0.0001579554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5320555,0.00001512623,0.4675219,0.000009109294,0.0000425202,0.00007054261,5.486109e-8,0.0001925743,0.00009268],"genre_scores_gemma":[0.8328769,4.835031e-7,0.1670359,0.00003973225,0.00002029182,0.000005441841,0.000001674438,0.00000312386,0.0000164777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8296381,"threshold_uncertainty_score":0.2312074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165739648","doi":"10.1109/icpc.2008.41","title":"NICAD: Accurate Detection of Near-Miss Intentional Clones Using Flexible Pretty-Printing and Code Normalization","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":519,"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":"","keywords":"Computer science; Parsing; Normalization (sociology); Agile software development; Programming language; Precision and recall; Transformation (genetics); Source code; Disk formatting; Code generation; Rule-based machine translation; Compiler; Code (set theory); Artificial intelligence; Natural language processing; Software engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0470208530369328,"gpt":0.2932180374607296,"spread":0.2461971844237968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002351163,0.00006842682,0.00008547276,0.0001032326,0.0001459767,0.00006152417,0.0002093176,0.00004093793,0.000008233827],"category_scores_gemma":[0.0003521015,0.00006771601,0.00002403556,0.0003990736,0.00005972873,0.0005105855,0.0002209949,0.00008610725,0.000003181754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002850665,"about_ca_system_score_gemma":0.00005041818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007199284,"about_ca_topic_score_gemma":0.00000580246,"domain_scores_codex":[0.9991986,0.0000272713,0.0001819997,0.0001934629,0.0002410618,0.0001576142],"domain_scores_gemma":[0.999384,0.0001575644,0.00005572764,0.0001837812,0.0001708079,0.00004806789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000530678,0.0001608406,0.3947738,0.0003570957,0.0001024658,0.00002416681,0.002096783,0.145448,0.4092188,0.01162524,0.00009366904,0.03604604],"study_design_scores_gemma":[0.0001503938,0.00002924936,0.1076363,0.0000233427,0.000001872423,0.00008760639,0.000008245008,0.7870974,0.1046754,0.0001091684,0.00009419821,0.00008679045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4690014,0.00003019637,0.5307119,0.00001958062,0.00006262719,0.00004583492,3.444597e-7,0.00009855458,0.00002949983],"genre_scores_gemma":[0.9376103,0.00001476434,0.0622311,0.000009419958,0.00001908166,0.000002938147,7.466028e-7,0.000006436282,0.0001052222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6416494,"threshold_uncertainty_score":0.2761379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034628356","doi":"10.1007/s10664-005-1290-x","title":"Studying Software Engineers: Data Collection Techniques for Software Field Studies","year":2005,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":491,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Software engineering; Field (mathematics); Software; Task (project management); Data science; Taxonomy (biology); Data collection; Systems engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09495362100580118,"gpt":0.3624809855118468,"spread":0.2675273645060456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001120744,0.0006254537,0.0006877778,0.0005966342,0.0003645115,0.0003147979,0.002870119,0.0003181894,0.00001617054],"category_scores_gemma":[0.03039933,0.0006388391,0.0002005074,0.001482663,0.00004296835,0.001603572,0.001751624,0.0007454109,0.00003728066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005884301,"about_ca_system_score_gemma":0.0001784873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001300843,"about_ca_topic_score_gemma":0.000007728564,"domain_scores_codex":[0.9958319,0.00005064993,0.0007152,0.00137236,0.0008338888,0.001195997],"domain_scores_gemma":[0.9884626,0.008550148,0.0001089953,0.002107579,0.0004253346,0.000345306],"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":[0.000123513,0.00078127,0.1111489,0.002418979,0.0016529,0.0001507447,0.005861739,0.0866128,0.0004373786,0.0003508585,0.3012945,0.4891664],"study_design_scores_gemma":[0.004134439,0.002374853,0.0212676,0.001853094,0.0002861102,0.0003572001,0.0003035083,0.4064521,0.03374139,0.0009596472,0.5214475,0.00682248],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008946556,0.002692835,0.977892,0.001236345,0.0009701925,0.0009746229,0.00003087679,0.007253943,0.00000267603],"genre_scores_gemma":[0.04270151,0.0001297553,0.9548208,0.0004926078,0.000837132,0.0005770689,0.00005776165,0.0001509824,0.0002323669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4823439,"threshold_uncertainty_score":0.9996063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998265754","doi":"10.1109/ms.2006.105","title":"How are Java software developers using the Eclipse IDE?","year":2006,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":407,"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":"Eclipse; Java; Computer science; Popularity; Software development; Development environment; Software engineering; Software; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02894594475689117,"gpt":0.2534921181635719,"spread":0.2245461734066807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004829549,0.0003818272,0.0003069684,0.0002296438,0.0007486974,0.0007390251,0.002333274,0.0001769375,0.00001661401],"category_scores_gemma":[0.001661498,0.000298358,0.0001660215,0.001250977,0.0001561741,0.0008140589,0.0005910716,0.0005256809,0.00009366807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002780461,"about_ca_system_score_gemma":0.0002827343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001490971,"about_ca_topic_score_gemma":0.00005893809,"domain_scores_codex":[0.9969213,0.0001140526,0.0002996325,0.0007493135,0.0009734904,0.0009422384],"domain_scores_gemma":[0.9966933,0.001193435,0.0001424007,0.001441066,0.0003607938,0.0001690298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004700674,0.0004797539,0.6296266,0.0006598765,0.0003743366,0.00178019,0.003941686,0.1016715,0.002183248,0.005813221,0.167042,0.08638061],"study_design_scores_gemma":[0.006013264,0.0004970818,0.5048421,0.001805575,0.0002168221,0.002213665,0.001293064,0.0553546,0.04199174,0.03765535,0.3381618,0.009954949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1246214,0.0004999089,0.8705213,0.001100863,0.00158636,0.0003224401,0.00001650703,0.001307136,0.00002409799],"genre_scores_gemma":[0.6281807,0.00001334698,0.3673468,0.0004519454,0.001744935,0.00005749088,0.000009570935,0.0001201406,0.002075038],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5035593,"threshold_uncertainty_score":0.9999468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W180288257","doi":"","title":"Automatic bug triage using text categorization.","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":404,"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":"Triage; Categorization; Computer science; Open source; Machine learning; Software bug; Supervised learning; Natural language processing; Artificial intelligence; Data science; Software engineering; Software; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02661114984628477,"gpt":0.2801050682765093,"spread":0.2534939184302246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001842567,0.00007143795,0.00007785758,0.0001304893,0.00006395668,0.0001481783,0.0005033648,0.00003139395,0.00006348111],"category_scores_gemma":[0.0003134242,0.0000635739,0.00002492669,0.0006440166,0.00001382768,0.0003477591,0.000131583,0.00007337533,0.0001871139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000125803,"about_ca_system_score_gemma":0.0001360725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000917217,"about_ca_topic_score_gemma":0.000001601569,"domain_scores_codex":[0.9991937,0.00001491647,0.0001223476,0.0001857975,0.0002636954,0.0002195033],"domain_scores_gemma":[0.9993206,0.0001536532,0.00001732029,0.0003873531,0.00004721262,0.00007386736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003514238,0.0003824286,0.009513766,0.0002040531,0.00009487269,0.0002424779,0.003517332,0.3519435,0.01472434,0.5150582,0.001443123,0.1028725],"study_design_scores_gemma":[0.0009445797,0.00005487912,0.01312559,0.00003197338,0.000003601783,0.00005806982,0.00001614215,0.9653599,0.01106084,0.008677384,0.0003600705,0.0003069483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1219746,0.00002757139,0.8765524,0.0002362851,0.0001850872,0.00009220665,1.273961e-7,0.000650268,0.0002814689],"genre_scores_gemma":[0.8078328,0.000001074584,0.1918952,0.00004750192,0.00003337139,0.000004212794,4.58566e-7,0.000007725516,0.0001777012],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6858582,"threshold_uncertainty_score":0.2592468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100925270","doi":"10.1007/s10664-011-9171-y","title":"An exploratory study of the impact of antipatterns on class change- and fault-proneness","year":2011,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":394,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Odds; Computer science; Machine learning; Logistic regression","retraction":null,"screen_n_in":null,"score":{"opus":0.1070401985481799,"gpt":0.3282979284401009,"spread":0.221257729891921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000284374,0.0002122619,0.0002803308,0.000187967,0.0000421935,0.00002440149,0.0009705887,0.00007704553,0.000006882579],"category_scores_gemma":[0.000401657,0.0001496581,0.00008254809,0.0005998008,0.00004612625,0.0003481458,0.0003538275,0.0002687895,0.000001975961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006161538,"about_ca_system_score_gemma":0.00003682563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001103162,"about_ca_topic_score_gemma":0.000004510009,"domain_scores_codex":[0.9985618,0.00007420866,0.0002583697,0.000359866,0.0004232224,0.0003225206],"domain_scores_gemma":[0.9984074,0.0003675955,0.00006838126,0.0009133114,0.00008901172,0.0001543295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001163257,0.0004589539,0.9817401,0.00004953308,0.00004563514,0.00001023065,0.009926309,0.005829439,0.0003553885,0.00001644193,0.00002096232,0.001535354],"study_design_scores_gemma":[0.0003183622,0.0009442537,0.9862735,0.00005901608,0.000004980512,0.000004123006,0.00006518595,0.009982081,0.002163913,0.00001140057,0.000006430147,0.00016677],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9257967,0.00005190442,0.07339596,0.000009180326,0.0001884223,0.000324949,0.000004722265,0.0002264314,0.000001730905],"genre_scores_gemma":[0.9983754,0.000002594599,0.001480396,0.00001230353,0.00004668774,0.00005057643,4.660528e-7,0.00002978172,0.000001795797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0725787,"threshold_uncertainty_score":0.610288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156448859","doi":"10.1109/ms.2009.161","title":"Recommendation Systems for Software Engineering","year":2009,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; McGill University","funders":"","keywords":"Software engineering; Social software engineering; Software development; Computer science; Software construction; Personal software process; Software peer review; Reuse; Software system; Package development process; Software Engineering Process Group; Software; World Wide Web; Engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0223554942090374,"gpt":0.2680150422771015,"spread":0.2456595480680641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004228257,0.0002223695,0.0002279918,0.000243589,0.0002085238,0.000223031,0.0008405683,0.0001241632,0.00000887911],"category_scores_gemma":[0.002261437,0.0002361915,0.0001031487,0.0004833827,0.000009292222,0.0005690261,0.00008067908,0.0002076218,0.00004378562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001676243,"about_ca_system_score_gemma":0.00007185662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008764517,"about_ca_topic_score_gemma":3.69206e-7,"domain_scores_codex":[0.9983233,0.00002346213,0.000280716,0.0004989894,0.0003049866,0.0005685936],"domain_scores_gemma":[0.9977285,0.00121105,0.00006163126,0.0006110787,0.0002146666,0.0001730878],"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":[0.00007399092,0.000500999,0.01698781,0.001248047,0.0002556759,0.00009885598,0.002628765,0.2214426,0.002735198,0.01208012,0.09564146,0.6463065],"study_design_scores_gemma":[0.004353928,0.00192288,0.05094457,0.0006786183,0.00005383707,0.0002867436,0.0000440722,0.5940745,0.01009523,0.002780429,0.3310032,0.003761978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007137032,0.0002020141,0.9876107,0.0003093876,0.001932669,0.0004982421,0.00001832054,0.002283287,0.000008360501],"genre_scores_gemma":[0.4918202,0.00003384956,0.5064412,0.0002879312,0.0006857439,0.0002626835,0.00005395783,0.0000694721,0.0003450152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6425445,"threshold_uncertainty_score":0.9631612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169952536","doi":"10.1145/1062455.1062491","title":"Using structural context to recommend source code examples","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":385,"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":"Computer science; Programming language; Source code; Eclipse; Coding (social sciences); Code (set theory); Context (archaeology); Code review; Class (philosophy); Code generation; Task (project management); Software engineering; Static program analysis; Artificial intelligence; Software development; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.0811007841125726,"gpt":0.3297570460288722,"spread":0.2486562619162996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001774464,0.000094141,0.00009678565,0.0001082617,0.00007856613,0.0001657444,0.0006922795,0.00002913676,0.000131116],"category_scores_gemma":[0.0002091917,0.00008445371,0.00002640269,0.0002666854,0.00001337887,0.0002781191,0.0003359625,0.0001038983,0.0001303754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009925746,"about_ca_system_score_gemma":0.00003039577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001591656,"about_ca_topic_score_gemma":0.00008655745,"domain_scores_codex":[0.9990358,0.000024692,0.0001243053,0.0002622771,0.0002241611,0.0003287938],"domain_scores_gemma":[0.9990123,0.0003559038,0.00001375428,0.0004100651,0.00005053844,0.0001574272],"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":[0.000007553392,0.00001943406,0.01193096,0.00001345703,0.00002883084,0.000008354957,0.002644361,0.04042789,0.005865498,0.01072459,0.01242594,0.9159032],"study_design_scores_gemma":[0.0004642661,0.00008141009,0.01401159,0.00002824841,0.000002449228,0.00008354172,0.000104563,0.7303424,0.01761867,0.0002439576,0.236504,0.0005148687],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3137368,0.00003251712,0.6842949,0.001309058,0.0001136274,0.00007743701,8.554847e-7,0.0002855902,0.0001492189],"genre_scores_gemma":[0.6801855,4.084861e-7,0.3185208,0.0005537685,0.0000862111,0.000002568064,3.143633e-7,0.000008229482,0.0006422186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153882,"threshold_uncertainty_score":0.3443922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008107570","doi":"10.1109/ms.2009.193","title":"What Makes APIs Hard to Learn? Answers from Developers","year":2009,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":383,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Microsoft Research","keywords":"Application programming interface; Computer science; Learnability; Usability; Reuse; Software engineering; World Wide Web; Interface (matter); Software development; Software; Human–computer interaction; Programming language; Engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02359606906170304,"gpt":0.2671319431312975,"spread":0.2435358740695944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002261652,0.00023468,0.0002250142,0.0002286206,0.0001967199,0.0005640943,0.001551468,0.000109587,0.00004527237],"category_scores_gemma":[0.0007982427,0.0002368603,0.00008151129,0.0008252973,0.00002832283,0.001071235,0.0001863052,0.0002832975,0.0008028707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001522563,"about_ca_system_score_gemma":0.0001366813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005859098,"about_ca_topic_score_gemma":0.00001115864,"domain_scores_codex":[0.9978012,0.00004474743,0.0002071585,0.0006844742,0.0006473949,0.0006150661],"domain_scores_gemma":[0.9980652,0.0004936466,0.00002904989,0.0009159946,0.0001514826,0.0003445726],"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":[0.00003352319,0.0001149391,0.01654685,0.00002704266,0.00008595494,0.0004168325,0.01201674,0.008402513,0.00472396,0.0002077375,0.05040086,0.9070231],"study_design_scores_gemma":[0.002593303,0.001354436,0.6875997,0.001174125,0.00003615927,0.0001112441,0.0008986187,0.005000618,0.07443912,0.006393832,0.2159556,0.004443257],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3279537,0.0004525589,0.6646526,0.003071147,0.002128365,0.0002496508,0.000007701981,0.001461066,0.00002324226],"genre_scores_gemma":[0.5841487,0.00008355041,0.4101463,0.003393826,0.0003025577,0.0000367194,0.00001063983,0.00004714706,0.001830571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9025798,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106013472","doi":"10.1109/wcre.2002.1173068","title":"Java quality assurance by detecting code smells","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":380,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Code smell; Code refactoring; Computer science; Static program analysis; Software quality; Software engineering; KPI-driven code analysis; Code review; Software visualization; Code (set theory); Program comprehension; Software inspection; Source code; Software; Java; Programming language; Software development; Software system; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.02990889963983731,"gpt":0.3101992349853636,"spread":0.2802903353455263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001045874,0.00009084701,0.0001068952,0.00004291231,0.00007176618,0.0001229918,0.0005907899,0.00004341039,0.00004976121],"category_scores_gemma":[0.002383287,0.00008565612,0.00003340615,0.0004021116,0.00001776758,0.0002309473,0.00008108581,0.0001633916,0.0001687758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004746554,"about_ca_system_score_gemma":0.00005072652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005784435,"about_ca_topic_score_gemma":0.0000117504,"domain_scores_codex":[0.9987068,0.000112152,0.000165488,0.0003174976,0.0003509172,0.0003471374],"domain_scores_gemma":[0.9978372,0.001415226,0.00002701256,0.0005527667,0.00006507387,0.0001027007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001249368,0.0004700441,0.3294775,0.000355189,0.0001548791,0.0000844777,0.002132037,0.004603047,0.1785152,0.2059609,0.1219121,0.1563221],"study_design_scores_gemma":[0.001244191,0.0001556183,0.05819993,0.00005361098,0.000003407458,0.0000588361,0.00007514825,0.02951779,0.7992938,0.004805366,0.105247,0.001345299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06964217,0.0001444306,0.9253586,0.0002134395,0.0002204148,0.00007548886,0.000001225443,0.0004889874,0.003855232],"genre_scores_gemma":[0.9135633,0.00000440552,0.08457635,0.00009764529,0.00001198447,0.000007427885,2.118706e-7,0.000008523634,0.001730117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8439212,"threshold_uncertainty_score":0.3492956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112533109","doi":"10.1145/1101908.1101919","title":"UMLDiff","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":369,"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; Correctness; Software evolution; Java; Robustness (evolution); Object-oriented design; Software system; Software; Software engineering; Software maintenance; Software design; Software development; Structural pattern; Programming language; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.01435277878923805,"gpt":0.2629028471432182,"spread":0.2485500683539801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007865969,0.00002736975,0.00002481507,0.00003865148,0.00001503228,0.00004442501,0.0004258547,0.00001165577,0.00008763386],"category_scores_gemma":[0.00007500446,0.00002310687,0.00001166435,0.0001396987,0.000005007837,0.0001751668,0.0001081636,0.00004347302,0.0009391028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001736824,"about_ca_system_score_gemma":0.00001229985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000329889,"about_ca_topic_score_gemma":0.000001069663,"domain_scores_codex":[0.9996092,0.000003941406,0.00003605877,0.00009682285,0.0001277664,0.0001262156],"domain_scores_gemma":[0.9995691,0.0001081467,0.000002677017,0.0002606107,0.00001477278,0.00004475089],"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":[6.257441e-7,0.00005502755,0.007850761,0.000005584272,0.000008400951,0.00001303976,0.0002944286,0.001491413,0.001277721,0.220188,0.0469417,0.7218733],"study_design_scores_gemma":[0.0003971145,0.00005821185,0.09912149,0.000006381908,7.076468e-7,0.00004059213,0.000004318209,0.3250128,0.02636993,0.001346514,0.5472953,0.0003466663],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01635273,0.00003841358,0.9726949,0.001913329,0.0000698868,0.00002420966,3.701516e-8,0.0005540359,0.008352445],"genre_scores_gemma":[0.7935094,0.000001428614,0.2026624,0.0001779032,0.00006166309,0.00000273401,5.608832e-8,0.00000240799,0.003581958],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7771567,"threshold_uncertainty_score":0.9998388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090432523","doi":"10.1007/s10664-008-9076-6","title":"“Cloning considered harmful” considered harmful: patterns of cloning in software","year":2008,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":363,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cloning (programming); Source code; Computer science; Software engineering; Code (set theory); Software system; Software; clone (Java method); Maintainability; Web application; Codebase; Programming language; World Wide Web; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.044662327963924,"gpt":0.2815639292607685,"spread":0.2369016012968445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063403,0.0005862429,0.0008906313,0.0008212666,0.0001637641,0.0001073126,0.001304384,0.0003110822,0.00009247373],"category_scores_gemma":[0.01122249,0.0006485433,0.0002502568,0.00146781,0.0001048461,0.0007002025,0.0008272546,0.00112495,0.00005015781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003241661,"about_ca_system_score_gemma":0.0003391605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001731418,"about_ca_topic_score_gemma":0.00001634555,"domain_scores_codex":[0.995464,0.0001149783,0.001037949,0.001016343,0.001036025,0.001330708],"domain_scores_gemma":[0.9931839,0.004786635,0.0001704528,0.001111533,0.00028943,0.0004580265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000134123,0.0001138282,0.9472035,0.000254443,0.00006843892,0.0009116988,0.001610781,0.04721961,0.000600313,0.00008519979,0.0008399313,0.001078797],"study_design_scores_gemma":[0.002237117,0.0002040457,0.9482715,0.0007903987,0.00001633014,0.0006366497,0.00004592921,0.02974329,0.01474748,0.0001725155,0.001720953,0.001413768],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4914618,0.0004283489,0.5060543,0.0001819808,0.0004281427,0.0002550912,0.00001286842,0.00117063,0.000006899595],"genre_scores_gemma":[0.8596228,0.00003718934,0.1398272,0.0001534572,0.0001124139,0.00007262189,0.00001269367,0.00009975988,0.00006179701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3681611,"threshold_uncertainty_score":0.9995966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991613282","doi":"10.1007/s10664-010-9150-8","title":"A field study of API learning obstacles","year":2010,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":352,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"McGill University; Microsoft Research","keywords":"Documentation; Computer science; Programmer; Presentation (obstetrics); Field (mathematics); World Wide Web; Software engineering; Software documentation; Internal documentation; Multimedia; Software development; Software; Programming language; Software development process","retraction":null,"screen_n_in":null,"score":{"opus":0.01773343287783852,"gpt":0.2866929103016268,"spread":0.2689594774237883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003512855,0.0001981716,0.0002617275,0.0002391689,0.00007097625,0.00008278649,0.0009648062,0.0001208211,0.00003647532],"category_scores_gemma":[0.007420908,0.0001952388,0.00007719741,0.0007606883,0.0000148682,0.0002549164,0.0004359475,0.0010204,0.00002404539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000268347,"about_ca_system_score_gemma":0.0000413225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004167038,"about_ca_topic_score_gemma":0.00000651538,"domain_scores_codex":[0.9983115,0.00003002788,0.0003032062,0.000400881,0.0005209421,0.0004335063],"domain_scores_gemma":[0.9962434,0.002795334,0.00004697959,0.0006287479,0.0001000398,0.0001855069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000665156,0.0002824099,0.9691461,0.00006276706,0.00004848695,0.00005891176,0.001983739,0.01702657,0.002519492,0.000133475,0.0003380126,0.008393438],"study_design_scores_gemma":[0.001273187,0.001745624,0.9171814,0.00007218267,0.00001715762,0.00005230115,0.0001264128,0.05767582,0.009341124,0.00009826649,0.01146457,0.0009519694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6592954,0.00003368224,0.3392684,0.00005546124,0.0004116512,0.0001304024,2.73486e-7,0.0007940628,0.00001074999],"genre_scores_gemma":[0.9600763,0.000001360776,0.03967797,0.00002276893,0.000102199,0.00003087431,6.683302e-7,0.00002952015,0.00005830411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.300781,"threshold_uncertainty_score":0.8884056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110431240","doi":"10.1109/tse.2002.1019484","title":"Assessing the applicability of fault-proneness models across object-oriented software projects","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":351,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Universidade Federal do Rio Grande do Sul; National Science Foundation","keywords":"Computer science; Software metric; Software system; Software; Data mining; A priori and a posteriori; Multivariate adaptive regression splines; Software development; Java; Fault (geology); Software fault tolerance; Software engineering; Machine learning; Software quality; Regression analysis; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04020972332741948,"gpt":0.2891038020238414,"spread":0.2488940786964219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006207087,0.0004214686,0.0004105935,0.0002419396,0.0004571002,0.0003375206,0.001315054,0.0001972337,0.0000209044],"category_scores_gemma":[0.000365596,0.0003653459,0.0002395557,0.001731052,0.0001380733,0.001295111,0.00003034177,0.0008586696,0.00002444354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002448161,"about_ca_system_score_gemma":0.00008032899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004189188,"about_ca_topic_score_gemma":0.000003822946,"domain_scores_codex":[0.9968544,0.00007525433,0.0005341432,0.0007748829,0.0009133405,0.0008479563],"domain_scores_gemma":[0.9959784,0.001880219,0.0001004465,0.00158118,0.000274997,0.0001847687],"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":[0.000005311934,0.0002270567,0.0003991598,0.0002265991,0.00007011713,0.00001079059,0.002490186,0.9596111,0.000555894,0.00007936754,0.00003305487,0.03629142],"study_design_scores_gemma":[0.0006937815,0.0001294274,0.002409523,0.0002338379,0.00002382518,0.00005525962,0.00016013,0.9615999,0.03362281,0.00004857925,0.000326072,0.0006968224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1402246,0.0001606235,0.8566431,0.00003974823,0.0007181707,0.0005704947,0.00002560455,0.001611328,0.000006307781],"genre_scores_gemma":[0.9024865,0.00001764182,0.0969644,0.00002268458,0.0000475731,0.0003282915,0.000001377975,0.00006908979,0.00006246165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7622619,"threshold_uncertainty_score":0.9998798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108769867","doi":"10.1145/2597073.2597076","title":"The impact of code review coverage and code review participation on software quality: a case study of the qt, VTK, and ITK projects","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":351,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Code review; Software quality; Computer science; Software engineering; Team software process; Software; Code (set theory); Software inspection; Quality (philosophy); Software peer review; Process (computing); Software construction; Software quality assurance; Software development; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08101323997282231,"gpt":0.4072925866464281,"spread":0.3262793466736058,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002596513,0.0001238097,0.0003226988,0.00002916906,0.0001074856,0.00004523543,0.000374075,0.00002213901,0.000003274438],"category_scores_gemma":[0.005029332,0.00005980281,0.00005546072,0.0003871706,0.0000587432,0.0001120719,0.0002792141,0.0001300573,0.000001028458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002802163,"about_ca_system_score_gemma":0.00007175003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004411577,"about_ca_topic_score_gemma":0.0002271006,"domain_scores_codex":[0.9981646,0.0006038555,0.000380392,0.0002509413,0.0004122352,0.000187955],"domain_scores_gemma":[0.9965281,0.002159403,0.0001657829,0.0009216471,0.0001570551,0.00006801594],"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":[0.00008168347,0.001917659,0.4225819,0.03723211,0.0005442242,0.0001390869,0.009874316,0.0007655903,0.000180434,0.004817879,0.01517352,0.5066916],"study_design_scores_gemma":[0.004894458,0.009701778,0.8999974,0.03665926,0.0004141565,0.001149154,0.0003872072,0.03967116,0.001193953,0.0007238061,0.003758269,0.001449367],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9686019,0.01584672,0.01291322,0.0004840214,0.00004586067,0.002000885,0.000009055724,0.0000643926,0.00003392701],"genre_scores_gemma":[0.9922543,0.00709345,0.0003299233,0.0001897708,0.000007366412,0.00007255589,3.34913e-7,0.00000786673,0.00004449266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5052422,"threshold_uncertainty_score":0.6020944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120738100","doi":"10.1109/tse.2006.102","title":"Empirical Analysis of Object-Oriented Design Metrics for Predicting High and Low Severity Faults","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":349,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Larner College of Medicine, University of Vermont; University of Alberta","keywords":"Computer science; Fault (geology); Data mining; Software fault tolerance; Empirical research; Object-oriented programming; Machine learning; Reliability engineering; Logistic regression; Artificial intelligence; Fault tolerance; Distributed computing; Engineering; Statistics; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01827904818554282,"gpt":0.260653268209901,"spread":0.2423742200243582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004459208,0.0002373142,0.0003972336,0.001363578,0.0001217781,0.00005064592,0.0003354166,0.0001373614,0.000003890198],"category_scores_gemma":[0.0004043358,0.0002576902,0.0001874453,0.003636731,0.00002890473,0.0002865607,0.000007590305,0.0002798888,0.000001063095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001380088,"about_ca_system_score_gemma":0.00005571179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008378863,"about_ca_topic_score_gemma":0.00000641756,"domain_scores_codex":[0.9982151,0.00003531766,0.0003825156,0.0004892266,0.000460097,0.0004177406],"domain_scores_gemma":[0.9958394,0.003322417,0.00006311681,0.0004541487,0.0001962451,0.0001246642],"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":[0.00001698683,0.0001017084,0.005566444,0.0000898923,0.000308257,0.000004626811,0.0001325618,0.9905794,0.0003704826,0.00003658899,0.00002899182,0.002764005],"study_design_scores_gemma":[0.0004703211,0.0001395733,0.04257331,0.00004085741,0.0001863636,0.000005484882,0.000005383823,0.9349554,0.02130072,0.00001380419,0.00004192719,0.0002668654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1833293,0.00005301817,0.8153101,0.00001274283,0.0003400364,0.0002675075,0.00005506006,0.0006317287,5.339396e-7],"genre_scores_gemma":[0.716551,0.000005842536,0.2832935,0.000006417043,0.00002500205,0.00006883435,0.000004560975,0.00002402967,0.00002083184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5332218,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2559885217","doi":"10.1007/s10664-017-9512-6","title":"Curating GitHub for engineered software projects","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":345,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Software; Classifier (UML); Software engineering; Software development; Software bug; Software metric; Data mining; Machine learning; Data science; Software quality; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05729360034467611,"gpt":0.325474775312802,"spread":0.2681811749681259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006123101,0.0004914973,0.0004844389,0.0002859307,0.0008796388,0.001475019,0.002920731,0.0002454244,0.00001176359],"category_scores_gemma":[0.02884,0.0004977081,0.0002611137,0.0003506808,0.00007040808,0.001294285,0.0008799544,0.0005566725,0.00005527554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002201095,"about_ca_system_score_gemma":0.0002172112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001901792,"about_ca_topic_score_gemma":0.000002182232,"domain_scores_codex":[0.9967132,0.00002200553,0.0004611829,0.0009310645,0.0006578228,0.001214746],"domain_scores_gemma":[0.9944837,0.002630208,0.000146916,0.00205374,0.0002637099,0.0004217419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000761463,0.0004828598,0.7440752,0.002598347,0.0006419736,0.0004726692,0.004147796,0.1083505,0.002720934,0.003759247,0.02969963,0.1029747],"study_design_scores_gemma":[0.003512656,0.0006027888,0.5618833,0.0007463316,0.00005348927,0.000176656,0.00002400088,0.3276431,0.01127156,0.0008631485,0.08960683,0.003616147],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06263296,0.0002217873,0.9315885,0.0005180872,0.00130241,0.0006809021,0.00001783648,0.003022398,0.00001512463],"genre_scores_gemma":[0.4846145,0.000004651521,0.5140429,0.00008297493,0.0005319038,0.0003617467,0.00001175287,0.0001128066,0.0002368283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4219815,"threshold_uncertainty_score":0.9997475,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2367798545","doi":"10.1145/2884781.2884857","title":"Automated parameter optimization of classification techniques for defect prediction models","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":344,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Classifier (UML); Machine learning; Artificial intelligence; Random forest; Predictive modelling; Software bug; Decision tree; Software; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03975154568969916,"gpt":0.2891461855171243,"spread":0.2493946398274251,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000257479,0.00005306671,0.00006539369,0.0001298581,0.00002024928,0.00002247477,0.0002381271,0.00005572891,0.0000038614],"category_scores_gemma":[0.0003793845,0.00003588945,0.00004004321,0.0001928042,0.00001703102,0.000493885,0.00003778213,0.00001880155,0.000001655913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004876686,"about_ca_system_score_gemma":0.00002677225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003119842,"about_ca_topic_score_gemma":1.555198e-7,"domain_scores_codex":[0.999388,0.00001976864,0.0001465129,0.0001817259,0.0001495148,0.0001144154],"domain_scores_gemma":[0.9988785,0.0005649886,0.00003950585,0.0003042314,0.0001854589,0.00002729313],"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":[0.00007265652,0.0003088067,0.006789514,0.0002334644,0.0001382372,7.590652e-7,0.0003548501,0.3342766,0.124755,0.1435782,0.01298548,0.3765064],"study_design_scores_gemma":[0.0001084419,0.0000802977,0.0009741936,0.00002071871,0.000001961841,9.14549e-7,6.191631e-7,0.9606822,0.03669908,0.001351672,0.00003636851,0.0000435476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001893581,0.000006005664,0.9953596,0.0001647241,0.00005249564,0.0003136572,0.000004764956,0.002099149,0.0001060287],"genre_scores_gemma":[0.5420623,0.000005834042,0.4577642,0.000004803337,0.000007976663,0.0000925291,0.000002154739,0.000005228388,0.00005488135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6264056,"threshold_uncertainty_score":0.1463529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3152332785","doi":"10.1016/b978-0-12-411519-4.00006-9","title":"Latent Dirichlet Allocation","year":2015,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Software Engineering Research","field":"Computer Science","cited_by":344,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Documentation; Data science; Commit; Variety (cybernetics); Subject-matter expert; Software; Interpretability; Set (abstract data type); Source code; Subject (documents); Information retrieval; World Wide Web; Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03667132724998003,"gpt":0.2673423774947125,"spread":0.2306710502447324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005009026,0.0003243898,0.0003169776,0.0002438669,0.00005238828,0.0001435201,0.001315766,0.0002600593,0.00004430265],"category_scores_gemma":[0.0001197543,0.000313827,0.0001189597,0.00003017987,0.00005522436,0.0001003882,0.0005676411,0.0005127331,0.001167245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568001,"about_ca_system_score_gemma":0.0002698924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.909227e-7,"about_ca_topic_score_gemma":0.000002136378,"domain_scores_codex":[0.9979052,0.00002026596,0.0002938158,0.0005695005,0.0008604082,0.0003508088],"domain_scores_gemma":[0.9979342,0.0001685707,0.00009884978,0.001254559,0.0003037817,0.000239995],"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":[0.000001337711,0.000003859541,0.000009732503,0.0000334458,0.00003858142,0.0000410887,0.0001247201,0.00002017575,0.000007602789,0.02948976,0.002250466,0.9679793],"study_design_scores_gemma":[0.0001269105,0.00004895515,0.00006200554,0.0001334041,0.00001130479,0.00001943221,2.465639e-7,0.000378393,0.00002354887,0.01350945,0.9853351,0.0003512563],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000007356432,0.001674088,0.005706906,0.0002001837,0.0007548411,0.0003951426,0.000005162255,0.0005451852,0.9907112],"genre_scores_gemma":[0.0007389092,0.00003389231,0.005088088,0.00009730164,0.0002709355,0.00003751524,0.00001317339,0.00006707464,0.9936531],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9830846,"threshold_uncertainty_score":0.9999314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121596715","doi":"10.1007/s10664-017-9521-5","title":"Do developers update their library dependencies?","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Japan Society for the Promotion of Science","keywords":"Reuse; Dependency (UML); Computer science; Workload; Exploit; Software; World Wide Web; Software engineering; Data science; Computer security; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03368879006535396,"gpt":0.2799169180110553,"spread":0.2462281279457014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003282568,0.0003475395,0.0003013491,0.0002087169,0.0004264691,0.001396064,0.003801505,0.0001689659,0.00008755517],"category_scores_gemma":[0.003653798,0.0003118059,0.0001342911,0.0003464165,0.00005692966,0.002070071,0.001852802,0.0005723782,0.0002911898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009624911,"about_ca_system_score_gemma":0.0001634188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005230858,"about_ca_topic_score_gemma":6.675353e-7,"domain_scores_codex":[0.997673,0.00002567617,0.0002827085,0.0006737908,0.0005228361,0.0008220308],"domain_scores_gemma":[0.9967326,0.00082472,0.00007309877,0.001905969,0.00006116453,0.0004024772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008786748,0.00006316094,0.939101,0.0001155174,0.000119152,0.0003765228,0.0006863118,0.007176957,0.0001515769,0.001650466,0.01260548,0.03794502],"study_design_scores_gemma":[0.0004168423,0.00004634686,0.8815826,0.0001100967,0.000004726224,0.00007426986,0.000007898125,0.01369245,0.003535341,0.0004270641,0.09923235,0.0008700054],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2166816,0.0004547078,0.777249,0.00135776,0.001010074,0.0001753763,0.000007910457,0.002903755,0.0001598308],"genre_scores_gemma":[0.8369367,0.00004444676,0.1621674,0.0002341511,0.0002366818,0.00004343117,0.000005261684,0.00007974629,0.00025218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6202551,"threshold_uncertainty_score":0.9999334,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1746353556","doi":"10.1007/978-1-84800-044-5_8","title":"Reporting Experiments in Software Engineering","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":330,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Guideline; Computer science; Presentation (obstetrics); Unification; Set (abstract data type); Software; Empirical research; Data science; Management science; Software engineering; Engineering; Medicine; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06714879045561481,"gpt":0.3130913835188216,"spread":0.2459425930632068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009267656,0.0003299874,0.000393486,0.0007444804,0.00002506633,0.0001070662,0.000911711,0.0002362294,0.0001208041],"category_scores_gemma":[0.002056113,0.0003548703,0.0001122568,0.0001294773,0.00001471948,0.000209065,0.0005944468,0.000684252,0.0001453459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003098725,"about_ca_system_score_gemma":0.0001000996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002811737,"about_ca_topic_score_gemma":0.000005548437,"domain_scores_codex":[0.9970909,0.000003279418,0.001060649,0.0006454012,0.0006685393,0.0005312178],"domain_scores_gemma":[0.9980172,0.0005060713,0.0003229081,0.0009260755,0.00007883452,0.0001489052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002178655,0.0001768644,0.04107955,0.001219413,0.0004401133,0.02082055,0.002438467,0.01114798,0.0007540169,0.7076203,0.00767312,0.2066079],"study_design_scores_gemma":[0.004040649,0.0006066618,0.05930086,0.009493534,0.00004506995,0.001831898,0.00004025932,0.08018302,0.02119959,0.01275885,0.7955218,0.01497785],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003631498,0.0008537705,0.8718175,0.00002340423,0.0009095623,0.0003635737,0.000001021969,0.001760953,0.1239071],"genre_scores_gemma":[0.009488651,0.00003756101,0.5074885,0.0001080451,0.0003202603,0.00003739369,0.00001128154,0.0002108289,0.4822975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7878487,"threshold_uncertainty_score":0.9998903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019257047","doi":"10.1007/s10664-015-9381-9","title":"An empirical study of the impact of modern code review practices on software quality","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Code review; Software quality; Computer science; Software engineering; Software quality analyst; Software inspection; Software peer review; Software quality management; Static program analysis; Software construction; Software quality assurance; Software development; Software; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.14670699522306,"gpt":0.4503907650299953,"spread":0.3036837698069353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002021862,0.0003918155,0.0007577915,0.0001860219,0.00006585287,0.00006617633,0.002367675,0.000143609,0.00001030565],"category_scores_gemma":[0.02787888,0.0002695756,0.0002910915,0.001553179,0.00005454552,0.0005753416,0.0005865789,0.0007254057,0.00001038788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003186311,"about_ca_system_score_gemma":0.0004109063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001791606,"about_ca_topic_score_gemma":0.000007992588,"domain_scores_codex":[0.9958455,0.0004630066,0.000833388,0.0006846376,0.001619661,0.0005538131],"domain_scores_gemma":[0.9936323,0.002751446,0.0004842771,0.002186828,0.0004841613,0.0004610076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002991689,0.001192056,0.8407615,0.0003871029,0.0001105674,0.00001267278,0.001644658,0.1516697,0.00005194043,0.000008303816,0.00186633,0.002265203],"study_design_scores_gemma":[0.000838186,0.001856668,0.9666544,0.0006076573,0.00003373014,0.00002032003,0.00003115201,0.02883939,0.0002485382,0.000120185,0.0002749773,0.0004747876],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7537063,0.001328314,0.2433815,0.0001650256,0.0002331085,0.0006276666,0.00001581059,0.0005368525,0.000005336927],"genre_scores_gemma":[0.9837691,0.00002661923,0.01590308,0.0001003233,0.00007771851,0.0000540689,0.000003376631,0.00005181229,0.00001390717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2300627,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171733741","doi":"10.5555/776816.776866","title":"Hipikat: recommending pertinent software development artifacts","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":320,"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":"Eclipse; Computer science; Task (project management); Context (archaeology); Open source; Software project management; Open source software; Software; Open-source software development; Software engineering; Software development; World Wide Web; Data science; Software construction; Engineering; Systems engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03155944281280614,"gpt":0.2593580953075713,"spread":0.2277986524947652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005105688,0.0001341893,0.0001085059,0.0001455466,0.0001304624,0.0001499694,0.0005574677,0.00004239546,0.0002236118],"category_scores_gemma":[0.001235551,0.0001196619,0.00003358872,0.0003771445,0.00001055765,0.0002630798,0.0001858177,0.000151109,0.0005512147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001593556,"about_ca_system_score_gemma":0.0001375673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004115022,"about_ca_topic_score_gemma":0.000002156866,"domain_scores_codex":[0.9985622,0.00004336625,0.0002041319,0.0003461446,0.0003648273,0.0004793834],"domain_scores_gemma":[0.9988547,0.0004138251,0.0000241495,0.0004594034,0.00006211401,0.0001858122],"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":[0.000007543063,0.0004766413,0.1913013,0.0001570712,0.0001458729,0.0001729648,0.005469577,0.001691329,0.002551902,0.0676204,0.0305554,0.69985],"study_design_scores_gemma":[0.0009422182,0.0001206662,0.07930957,0.0001133347,0.000004007621,0.0001301204,0.00009230861,0.004608227,0.2262401,0.001544651,0.6855368,0.001357953],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04565305,0.00006502577,0.9509187,0.0004206914,0.0004285483,0.0001160247,9.762169e-8,0.0008101598,0.001587679],"genre_scores_gemma":[0.477291,0.000002923117,0.5210785,0.0001874174,0.00001479526,0.00002627557,8.321956e-7,0.00001295048,0.00138525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6984921,"threshold_uncertainty_score":0.7084934,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4250023757","doi":"10.1109/icse.2015.91","title":"Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models","year":2015,"lang":"en","type":"article","venue":"2015 IEEE/ACM 37th IEEE International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":319,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Replicate; Machine learning; Predictive modelling; Artificial intelligence; Software bug; Software; Data mining; Multivariate adaptive regression splines; Multivariate statistics; Set (abstract data type); Variety (cybernetics); Support vector machine; Regression; Logistic regression; Regression analysis; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1198000391827528,"gpt":0.3409680431586617,"spread":0.2211680039759089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312997,0.0002407809,0.0002240296,0.0002966157,0.00006034155,0.0001018818,0.00208708,0.00009692758,0.000009683381],"category_scores_gemma":[0.002173821,0.0001573184,0.0001577583,0.0004169593,0.00006297287,0.0004979611,0.0001425533,0.0004621503,0.0000132088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003170451,"about_ca_system_score_gemma":0.0002246785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004507759,"about_ca_topic_score_gemma":2.735293e-7,"domain_scores_codex":[0.9978719,0.00007270344,0.000442996,0.0003349767,0.001001404,0.0002760631],"domain_scores_gemma":[0.9966825,0.001099281,0.0002314303,0.001016321,0.0008731777,0.00009725388],"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":[0.0001151903,0.0001117084,0.0275577,0.0001135927,0.0003121638,0.000004324661,0.001212682,0.9074306,0.01174616,0.03395075,0.002268325,0.01517677],"study_design_scores_gemma":[0.0001719534,0.0003256787,0.01578472,0.0004657571,0.00000679243,0.00001206082,0.00002291024,0.9639622,0.01866093,0.0003638548,0.00004924191,0.0001739028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.574836,0.00003720929,0.4231385,0.0003461652,0.0006645048,0.0003286738,0.0000315723,0.0003663841,0.0002509897],"genre_scores_gemma":[0.9914337,0.00004864248,0.008095773,0.00001509582,0.0002476297,0.00008565762,0.000007163043,0.00002589894,0.00004037111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4165978,"threshold_uncertainty_score":0.641526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138350998","doi":"10.1145/1518701.1518803","title":"A survey of software learnability","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":318,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Autodesk (Canada)","funders":"","keywords":"Learnability; Computer science; Usability; Protocol (science); Software; Think aloud protocol; Software engineering; Artificial intelligence; Human–computer interaction; Programming language; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03215782087970254,"gpt":0.2924752062013817,"spread":0.2603173853216792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000706976,0.00004952333,0.00009143848,0.00005628137,0.00001550754,0.00002391786,0.000622749,0.00002691976,0.00002599432],"category_scores_gemma":[0.003206443,0.00004293101,0.00002399104,0.0004759422,0.00001757717,0.0001376803,0.00008660741,0.00008031743,0.00002400825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001957093,"about_ca_system_score_gemma":0.00005959164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002126557,"about_ca_topic_score_gemma":0.00001315446,"domain_scores_codex":[0.9992645,0.00005364637,0.0001120421,0.0001730019,0.0002384764,0.0001583075],"domain_scores_gemma":[0.9985265,0.0007089273,0.00001522291,0.0005300679,0.0001630623,0.0000562641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004891759,0.0001253676,0.745637,0.00001575219,0.000006658267,0.000004644731,0.0001364054,0.0004458821,0.0002441704,0.003017576,0.001975376,0.2483863],"study_design_scores_gemma":[0.00005878354,0.00006951417,0.995666,0.000002439558,1.67855e-7,0.000001044195,4.210629e-7,0.002425914,0.001116178,0.0005508899,0.00006111374,0.00004756822],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1812411,0.00004478682,0.8179775,0.0001598228,0.00005069209,0.00005597733,8.224525e-7,0.0002880261,0.0001811598],"genre_scores_gemma":[0.9480085,0.000001104403,0.0517647,0.00003566268,0.000004431756,8.627439e-7,6.079929e-7,0.000001937481,0.0001822074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7667673,"threshold_uncertainty_score":0.3838643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097750323","doi":"10.1109/tse.2008.26","title":"Asking and Answering Questions during a Programming Change Task","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":314,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Vrije Universiteit Brussel; University of Washington","keywords":"Computer science; Programmer; Ask price; Task (project management); Key (lock); Programming language; Question answering; Code (set theory); Software engineering; World Wide Web; Data science; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02214495530722297,"gpt":0.2361953929923954,"spread":0.2140504376851724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001684933,0.0003188192,0.0002456314,0.0005959547,0.000476454,0.0001342078,0.0004364979,0.0001203197,0.000006072224],"category_scores_gemma":[0.0001247166,0.0003694942,0.00009899366,0.0008730812,0.00004773423,0.0009153475,0.00001575264,0.0005967357,0.0000211543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000167878,"about_ca_system_score_gemma":0.00003941776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004734652,"about_ca_topic_score_gemma":0.000003878177,"domain_scores_codex":[0.9980424,0.0000225666,0.0002655035,0.0005789819,0.0004246313,0.0006659066],"domain_scores_gemma":[0.9986588,0.0004080001,0.00003552579,0.0005555093,0.00007231702,0.00026982],"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":[0.00006483438,0.0008102647,0.02034251,0.001686479,0.0006017269,0.002216656,0.02004227,0.6406878,0.02052369,0.0007361962,0.00005517102,0.2922324],"study_design_scores_gemma":[0.005668439,0.001158581,0.3850387,0.00338573,0.0001400332,0.008640049,0.0001649245,0.4789286,0.1008888,0.00004939412,0.008939574,0.006997244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2368349,0.0002272335,0.7599913,0.00003588762,0.0005073411,0.0002616767,0.000004208654,0.002135511,0.00000192953],"genre_scores_gemma":[0.86613,0.0001137791,0.133228,0.00001803973,0.0001004772,0.0002908771,6.681451e-7,0.00006043636,0.00005770918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6292951,"threshold_uncertainty_score":0.9998757,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167809408","doi":"10.1109/wcre.1999.806964","title":"Experiments with clustering as a software remodularization method","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":311,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Cluster analysis; Computer science; Reverse engineering; Data mining; Domain (mathematical analysis); Software; Code (set theory); Source code; Software engineering; Theoretical computer science; Machine learning; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02114513403742583,"gpt":0.3051099445116784,"spread":0.2839648104742525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002955637,0.0001005411,0.00008685096,0.0001030363,0.00006597255,0.0001365293,0.0003752902,0.00003757535,0.00005153942],"category_scores_gemma":[0.0005169641,0.00008314168,0.00001814455,0.0004542589,0.000009455002,0.0003371588,0.0001103459,0.00008685204,0.00006073934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005594319,"about_ca_system_score_gemma":0.00006658874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002502757,"about_ca_topic_score_gemma":0.000001737413,"domain_scores_codex":[0.9989181,0.00006878415,0.00009415582,0.0003185838,0.0003485029,0.0002519314],"domain_scores_gemma":[0.9991204,0.0002033775,0.00001867659,0.0004920353,0.00007194216,0.00009356584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009875432,0.0007917543,0.105217,0.0003464909,0.0004631484,0.0009891425,0.01205755,0.1633535,0.04269819,0.3544243,0.002501864,0.3170583],"study_design_scores_gemma":[0.003665315,0.001044999,0.01374581,0.0002028982,0.00001520776,0.001289426,0.000228505,0.428956,0.5241222,0.005922048,0.01883243,0.001975137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004240517,0.00003039389,0.993438,0.00004599551,0.0001044868,0.0001303702,8.224077e-8,0.0005285055,0.001481645],"genre_scores_gemma":[0.1586393,9.498107e-7,0.8401676,0.00009035248,0.00000865828,0.00001985921,5.661903e-7,0.00001376451,0.001058964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4814241,"threshold_uncertainty_score":0.3390419,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2093400716","doi":"10.1007/s10664-015-9379-3","title":"What are mobile developers asking about? A large scale study using stack overflow","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":311,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Mobile device; World Wide Web; Mobile computing; Latent Dirichlet allocation; Context (archaeology); Software; Popularity; Mobile Web; Data science; Mobile technology; Software development; Topic model; Telecommunications; Artificial intelligence; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0514213064798872,"gpt":0.324397707768517,"spread":0.2729764012886298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001120452,0.0004744451,0.0005188186,0.0003925893,0.0001758964,0.0009113792,0.001375852,0.0001787237,0.00001810322],"category_scores_gemma":[0.002266109,0.0004836988,0.0001300408,0.001766982,0.00002694621,0.002017454,0.001122093,0.0006774085,0.0001010762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007542131,"about_ca_system_score_gemma":0.0002690263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002483247,"about_ca_topic_score_gemma":0.00000977492,"domain_scores_codex":[0.9959553,0.00009348449,0.0004887547,0.0009341817,0.001289963,0.001238339],"domain_scores_gemma":[0.997054,0.0007595181,0.0000878334,0.001064655,0.0003142186,0.0007197637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001157521,0.0004152484,0.7260981,0.00008403755,0.00009483498,0.0003131398,0.0100103,0.2600571,0.00004521414,0.000007871424,0.001063283,0.001799311],"study_design_scores_gemma":[0.003679944,0.0006789127,0.4629442,0.0008305109,0.00004796964,0.0001682167,0.004623929,0.4958116,0.0007100027,0.00005089685,0.02776353,0.002690286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5360192,0.0006604578,0.4604915,0.00003418926,0.00121448,0.0003928964,0.000003237804,0.001181495,0.000002550887],"genre_scores_gemma":[0.8961228,0.00001279881,0.1031221,0.0001315801,0.0002757363,0.0001310987,0.000004240126,0.0001100424,0.0000897048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3601035,"threshold_uncertainty_score":0.9997615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3144106047","doi":"10.1109/msr.2009.5069475","title":"The promises and perils of mining git","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":310,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Commit; Computer science; Decentralization; Semantics (computer science); Confusion; Focus (optics); Data science; Code (set theory); Source code; World Wide Web; Computer security; Database; Political science; Programming language; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01494064876810455,"gpt":0.2601414647745975,"spread":0.245200816006493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470501,0.00002638221,0.00003424337,0.00001881362,0.00003849299,0.00006317716,0.0002647524,0.000008726717,0.00000227478],"category_scores_gemma":[0.0002608804,0.00001595482,0.000007889086,0.00009697697,0.00002012888,0.00007909664,0.00005614763,0.00002572555,0.00000141931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003708349,"about_ca_system_score_gemma":0.000017224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001694373,"about_ca_topic_score_gemma":4.531244e-7,"domain_scores_codex":[0.9996695,0.00000654516,0.00004929966,0.00007391438,0.0001062137,0.00009451075],"domain_scores_gemma":[0.9993938,0.0003736797,0.000007674691,0.0001762429,0.00002378499,0.00002477957],"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":[0.000006671509,0.00003281811,0.01819186,0.00002015495,0.00001428336,0.000008017124,0.00261045,0.00007674452,0.006232417,0.05774597,0.003726967,0.9113336],"study_design_scores_gemma":[0.0004926135,0.0005531328,0.8915675,0.00005027327,0.00000253867,0.00004112322,0.0001876161,0.04713523,0.04470662,0.002981306,0.0120107,0.0002713871],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8951324,0.0006989634,0.09935653,0.001931924,0.00006193654,0.0001034127,1.036966e-7,0.000160991,0.002553729],"genre_scores_gemma":[0.9741148,0.00001412453,0.02535158,0.00002206724,0.000008765534,0.000001415157,1.56482e-8,0.00000108746,0.0004861908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9110622,"threshold_uncertainty_score":0.06506185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160506632","doi":"10.1109/wcre.2009.28","title":"An Exploratory Study of the Impact of Code Smells on Software Change-proneness","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":305,"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":"Code smell; Eclipse; Computer science; Software quality; Code (set theory); Relation (database); Software; Programming language; Software development; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.05944708631218296,"gpt":0.3358983610185198,"spread":0.2764512747063368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003359389,0.0001122678,0.0001667438,0.0001210959,0.0000364026,0.00002569379,0.001373322,0.00003489387,0.0000107264],"category_scores_gemma":[0.0001320059,0.00006817001,0.00006159875,0.0005643956,0.00002339104,0.0002931174,0.0001302243,0.0001180587,0.000005358501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005066639,"about_ca_system_score_gemma":0.00007123453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009816665,"about_ca_topic_score_gemma":0.00001792369,"domain_scores_codex":[0.9988088,0.0001015935,0.0001614577,0.0002382607,0.0004802527,0.0002096397],"domain_scores_gemma":[0.9983671,0.0001748265,0.0000546756,0.001205224,0.0001241768,0.00007399663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000132309,0.01130902,0.6817625,0.00009364292,0.0001937791,0.00003907201,0.06020515,0.05350743,0.01491157,0.002130258,0.001567492,0.1741478],"study_design_scores_gemma":[0.0004392559,0.003151456,0.9742181,0.00003227642,0.000002583007,0.000001265746,0.0002286202,0.006716382,0.01492206,0.0001543064,0.00000354588,0.000130106],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97189,0.00002295778,0.02741336,0.00003402444,0.00008408595,0.0003932489,0.000002870416,0.0001423142,0.0000171328],"genre_scores_gemma":[0.9984412,0.000001415257,0.001462061,0.00002854201,0.00002627122,0.00001497565,2.662825e-7,0.000007701371,0.00001760643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2924557,"threshold_uncertainty_score":0.2779892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148854374","doi":"10.1145/2491411.2491444","title":"Convergent contemporary software peer review practices","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":301,"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; Software peer review; Software review; Software; Android (operating system); Code review; World Wide Web; Software inspection; Software technical review; Data science; Software engineering; Software development; Software development process; Software quality; Software construction; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.07734132822184826,"gpt":0.3324186486525014,"spread":0.2550773204306531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007339169,0.0001132239,0.0001558947,0.00005761138,0.0000439453,0.0001913337,0.0009784769,0.00003727541,0.001171451],"category_scores_gemma":[0.007950782,0.00008900028,0.00005242083,0.000321151,0.00002162384,0.001235172,0.0003403527,0.0001747029,0.003548227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003067269,"about_ca_system_score_gemma":0.0001430214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002297452,"about_ca_topic_score_gemma":8.088587e-7,"domain_scores_codex":[0.9983392,0.00005968256,0.0002024277,0.0003102815,0.0008352388,0.000253159],"domain_scores_gemma":[0.9973579,0.0008690719,0.0001170706,0.0007659377,0.0007105579,0.0001794791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[3.29185e-7,0.00002843939,0.009296873,0.0002921486,0.00001732746,0.00001388986,0.0000408476,0.000002127472,0.00003301612,0.001201354,0.9795976,0.009476067],"study_design_scores_gemma":[0.0003224018,0.0001053687,0.03801963,0.0005236478,0.000005660004,0.00005418735,0.00001776765,0.003601457,0.0007203849,0.0007018693,0.9554268,0.0005008172],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002528886,0.03128718,0.8515209,0.09816664,0.001234002,0.001735886,0.000002201746,0.002708747,0.01081553],"genre_scores_gemma":[0.445815,0.003371824,0.4280386,0.01792956,0.0002928833,0.0008331041,0.00002700858,0.00008011414,0.1036119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4432861,"threshold_uncertainty_score":0.9997416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050187629","doi":"10.1145/1052898.1052912","title":"Mylar","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":296,"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":"AspectJ; Computer science; Programmer; Java; Programming language; Task (project management); Context (archaeology); Code (set theory); Software engineering; Software system; Software; Aspect-oriented programming; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01355061999694686,"gpt":0.2581420106157525,"spread":0.2445913906188057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008451782,0.00002502309,0.00002280663,0.00003605769,0.00001435231,0.00004171447,0.0004055066,0.00001108238,0.00008851497],"category_scores_gemma":[0.0000735047,0.00002133092,0.00001081978,0.0001364328,0.000004410262,0.0001787081,0.00009754328,0.00004120452,0.001020481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001550301,"about_ca_system_score_gemma":0.00001207209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000291751,"about_ca_topic_score_gemma":8.080454e-7,"domain_scores_codex":[0.9996326,0.00000389852,0.00003316255,0.00009055277,0.0001227597,0.0001170452],"domain_scores_gemma":[0.9995995,0.0000925036,0.000002353202,0.0002497428,0.00001476402,0.00004111377],"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":[6.646449e-7,0.00005713934,0.008079198,0.000006555552,0.00001042538,0.00001764241,0.0003424761,0.002182814,0.001863536,0.2499306,0.05734394,0.680165],"study_design_scores_gemma":[0.0002793476,0.00004762725,0.05833487,0.000004948356,5.340844e-7,0.00002801389,0.000003315551,0.2375472,0.02845844,0.0009951351,0.6740391,0.0002614541],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01269064,0.00004732029,0.9774222,0.0020088,0.00006179072,0.00002300946,3.450689e-8,0.0005223753,0.007223885],"genre_scores_gemma":[0.7822868,0.000001502547,0.2145763,0.0001762467,0.00005541439,0.000002365568,5.188695e-8,0.000002229174,0.002899087],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7695962,"threshold_uncertainty_score":0.9997573,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2344444819","doi":"10.1145/2902362","title":"On the naturalness of software","year":2016,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Software Engineering Research","field":"Computer Science","cited_by":291,"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":"Engineering and Physical Sciences Research Council","keywords":"Naturalness; Computer science; Natural language; Natural (archaeology); Software; Artificial intelligence; Program comprehension; Natural language processing; Simplicity; Code (set theory); Programming language; Linguistics; Software system; Set (abstract data type); Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.04508847840595311,"gpt":0.2959249936897846,"spread":0.2508365152838315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003452096,0.00004269497,0.00006022412,0.00003703463,0.0001042655,0.00001002071,0.05161377,0.00002134045,0.000005690026],"category_scores_gemma":[0.04583185,0.00001800623,0.00005103881,0.0003290903,0.0002122621,0.00007381228,0.01908865,0.0001167954,0.0000154871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002017001,"about_ca_system_score_gemma":0.00003806538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008948798,"about_ca_topic_score_gemma":0.000002154115,"domain_scores_codex":[0.999426,0.0001161817,0.0001108035,0.00007130391,0.0001931311,0.00008259522],"domain_scores_gemma":[0.9550121,0.00796813,0.00006731726,0.03680625,0.0001317748,0.00001438224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008321657,0.0002140248,0.01524445,0.00003514647,0.00008120677,1.658931e-7,0.001073319,0.0001215563,0.01054374,0.8517259,0.0656381,0.05531406],"study_design_scores_gemma":[0.0004370997,0.00007994209,0.2052699,0.0006054892,0.00001018193,0.000005956742,0.00003477083,0.0008393656,0.09066571,0.6937397,0.008085251,0.0002267015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3961796,0.00174235,0.06013939,0.539514,0.0005554305,0.0006871386,0.00002443685,0.0003215505,0.0008360541],"genre_scores_gemma":[0.9501413,0.00003257142,0.04961828,0.00005759013,0.000003404759,0.00001542861,1.464159e-7,0.000004018676,0.0001272242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5539617,"threshold_uncertainty_score":0.9888448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051204868","doi":"10.1109/icsm.2012.6405249","title":"What makes a good code example?: A study of programming Q&A in StackOverflow","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Documentation; Code (set theory); Answer set programming; Set (abstract data type); Questions and answers; World Wide Web; Programming language; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.07388383997217017,"gpt":0.3253173807742034,"spread":0.2514335408020332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006700165,0.0001139602,0.0001711948,0.0002115947,0.00002235419,0.0001704703,0.0005898015,0.00003612977,0.00001746273],"category_scores_gemma":[0.0001845351,0.00009752779,0.00002736888,0.0006815979,0.00001680053,0.001210942,0.0002636363,0.0001131646,0.00002666782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007332028,"about_ca_system_score_gemma":0.00003916902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005973955,"about_ca_topic_score_gemma":0.001074547,"domain_scores_codex":[0.9985573,0.00007171575,0.0002148895,0.000244734,0.0004153981,0.0004959343],"domain_scores_gemma":[0.9986253,0.000532216,0.00003152002,0.0006469066,0.00005285186,0.0001112222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009015851,0.001995421,0.8554186,0.00004297318,0.0000312298,0.00001041998,0.02575493,0.0003519108,0.0002707831,0.001802452,0.00006645975,0.1142458],"study_design_scores_gemma":[0.002903569,0.001300706,0.9569082,0.0001329767,0.000009136288,0.00002421708,0.006157798,0.007167984,0.001853139,0.0001019601,0.02275175,0.0006885728],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9188697,0.0001889009,0.07993363,0.00003467023,0.0002706854,0.0004632612,2.905526e-7,0.0001894143,0.00004944533],"genre_scores_gemma":[0.9615875,0.000009646003,0.03797317,0.000008011432,0.00003475392,0.0000669223,4.679148e-7,0.00001102935,0.0003084782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1135572,"threshold_uncertainty_score":0.3977068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153258502","doi":"10.1109/icre.2003.1232745","title":"Improving requirements tracing via information retrieval","year":2004,"lang":"en","type":"article","venue":"Journal of Lightwave Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University; National Aeronautics and Space Administration","keywords":"Tracing; Traceability; Computer science; Framing (construction); Focus (optics); Information retrieval; Data mining; Software engineering; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01136877547295464,"gpt":0.253957388270777,"spread":0.2425886127978223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006093599,0.00009616493,0.0001734202,0.001086711,0.00006360537,0.00008082215,0.000933696,0.0001540842,0.000003530856],"category_scores_gemma":[0.001078763,0.00008442492,0.00005896475,0.0009379298,0.0000399209,0.001685804,0.0002028384,0.0004916711,0.00003291079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002937898,"about_ca_system_score_gemma":0.000159365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000351316,"about_ca_topic_score_gemma":3.729178e-7,"domain_scores_codex":[0.9986568,0.00001142628,0.0004991575,0.0000966523,0.0004551341,0.0002808318],"domain_scores_gemma":[0.9988627,0.00007167298,0.0003415047,0.0003179898,0.000336224,0.00006992603],"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":[0.0001513562,0.0003511945,0.009076747,0.0002590751,0.0003030343,0.001080717,0.002955387,0.005117603,0.3858012,0.06063582,0.0006317665,0.5336361],"study_design_scores_gemma":[0.004176979,0.002196389,0.005597494,0.0003533944,0.00002758758,0.004247984,0.0001310253,0.005928112,0.9239933,0.0491875,0.003558783,0.0006014012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2078502,0.0001003959,0.7896293,0.001720047,0.000430158,0.0000597369,1.784171e-7,0.0001690717,0.00004084014],"genre_scores_gemma":[0.897687,0.000009589015,0.1021782,0.00004343467,0.00006868999,7.403212e-7,1.647058e-7,0.000005554264,0.000006641252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6898368,"threshold_uncertainty_score":0.3442748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118944299","doi":"10.1145/581339.581390","title":"Concern graphs","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":289,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Source code; Java; Scalability; Usability; Software engineering; Abstraction; Representation (politics); Graph; Software; Programming language; Source lines of code; Theoretical computer science; Human–computer interaction; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04323818430936585,"gpt":0.2629492601822788,"spread":0.219711075872913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005638632,0.00003549347,0.00003439956,0.00005052349,0.00002195435,0.00005572304,0.0004815065,0.00001511682,0.0003793257],"category_scores_gemma":[0.00008432532,0.00003049132,0.00001816622,0.000264149,0.00001343122,0.0001393927,0.00009498711,0.00005450241,0.0008430912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009500915,"about_ca_system_score_gemma":0.000002926044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008181766,"about_ca_topic_score_gemma":4.538892e-7,"domain_scores_codex":[0.9995214,0.000006529093,0.00004256251,0.0001228051,0.000158228,0.0001484592],"domain_scores_gemma":[0.9994723,0.0001518933,0.000004114051,0.0002962975,0.00002082813,0.0000545482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.810266e-7,0.00007963526,0.03534021,0.00001446656,0.00002365471,0.00008825254,0.0008395683,0.0002260299,0.0006637446,0.5541469,0.166501,0.2420761],"study_design_scores_gemma":[0.0009572863,0.0002233319,0.06658958,0.00001988516,0.000002270054,0.00009418797,0.00001628511,0.7286001,0.01006175,0.01346766,0.1791768,0.0007908405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0225041,0.0002993964,0.9451385,0.001226905,0.0003228822,0.00007130756,1.945812e-7,0.001257005,0.0291797],"genre_scores_gemma":[0.9726292,0.000009788459,0.02293291,0.0001308637,0.00001488436,0.000004044006,5.209162e-8,0.000003380725,0.00427485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9501251,"threshold_uncertainty_score":0.9999349,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004758929","doi":"10.1016/j.sysarc.2010.06.003","title":"Using complexity, coupling, and cohesion metrics as early indicators of vulnerabilities","year":2010,"lang":"en","type":"article","venue":"Journal of Systems Architecture","topic":"Software Engineering Research","field":"Computer Science","cited_by":289,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Cohesion (chemistry); Software security assurance; Software quality; Secure coding; Software metric; Software bug; Vulnerability (computing); Software; Data mining; Software evolution; Vulnerability management; Software development; Software engineering; Computer security; Software construction; Vulnerability assessment; Information security","retraction":null,"screen_n_in":null,"score":{"opus":0.02959389043743297,"gpt":0.2917865568671155,"spread":0.2621926664296825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00135862,0.0001251652,0.0003469684,0.001004656,0.00008095192,0.0001419173,0.0006819996,0.0001066929,0.000003258259],"category_scores_gemma":[0.001191092,0.00009519275,0.00007425342,0.0007095176,0.0001508831,0.0001814789,0.0002079007,0.0008564899,7.255487e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003517465,"about_ca_system_score_gemma":0.0001522708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001630313,"about_ca_topic_score_gemma":0.000004139103,"domain_scores_codex":[0.9983122,0.00005968632,0.0004776271,0.0001495839,0.0007928979,0.0002080224],"domain_scores_gemma":[0.9979267,0.0009082273,0.0004038519,0.000315362,0.000263185,0.0001826725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001125585,0.0002870925,0.7136748,0.002077384,0.0004191903,0.0002702512,0.01675263,0.07049615,0.1525652,0.02594047,0.0002057271,0.01719851],"study_design_scores_gemma":[0.005368698,0.005103991,0.685077,0.003187735,0.0001753976,0.01553681,0.001238761,0.195549,0.05707286,0.02164743,0.007895169,0.002147228],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.869228,0.0005879598,0.1293034,0.00005611529,0.0006741027,0.0001063127,0.000002207584,0.00002325046,0.00001862014],"genre_scores_gemma":[0.9727693,0.000007210619,0.02701593,0.000005142067,0.0001762504,7.629874e-7,1.055626e-7,0.00001244508,0.00001280836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1250528,"threshold_uncertainty_score":0.3881848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}