{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":371,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":371,"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":"1f0d90f13f76","filters":{"venue":"Empirical Software Engineering"}},"results":[{"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":"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":"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":"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":"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":"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":"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":"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":"W2518473846","doi":"10.1007/s10664-016-9451-7","title":"Naming the pain in requirements engineering","year":2016,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":271,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Queen's University; Eesti Teadusagentuur; Queen's University Belfast","keywords":"Relevance (law); Dependency (UML); Context (archaeology); Status quo; Empirical research; Computer science; Management science; Requirements engineering; Complement (music); Data science; Criticality; Engineering ethics; Knowledge management; Risk analysis (engineering); Engineering; Software; Epistemology; Artificial intelligence; Political science; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.02583063276581971,"gpt":0.2732133516125181,"spread":0.2473827188466984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00142966,0.0002589348,0.0002059674,0.0001894998,0.00006024302,0.0001198645,0.00105171,0.0001090047,0.00001632771],"category_scores_gemma":[0.004909373,0.0001638041,0.00008539291,0.0007033683,0.00001417006,0.0007453635,0.0003223338,0.0002913293,0.00002596037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000188418,"about_ca_system_score_gemma":0.00002850088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001385808,"about_ca_topic_score_gemma":0.000001576902,"domain_scores_codex":[0.9982755,0.00006024534,0.0003500111,0.0004085825,0.0003356064,0.0005700957],"domain_scores_gemma":[0.9967273,0.002406348,0.00005803654,0.0006459894,0.00004389108,0.000118396],"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":[0.00003008433,0.0002969261,0.2496774,0.0003773208,0.0002235531,0.0006673874,0.00207145,0.0779789,0.008314798,0.01314657,0.01275267,0.634463],"study_design_scores_gemma":[0.001514946,0.0004376111,0.1442563,0.001562126,0.00002287492,0.0001565774,0.00001691035,0.2968566,0.005338704,0.00132967,0.5459978,0.002509947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0209153,0.0002687703,0.9744332,0.00202674,0.0004423364,0.0001615563,0.000001110979,0.001737608,0.00001333955],"genre_scores_gemma":[0.7261434,0.0000415074,0.2728988,0.0004739101,0.0001925738,0.000119919,8.96035e-7,0.00005702051,0.0000720274],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.705228,"threshold_uncertainty_score":0.6679735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1914969610","doi":"10.1007/s10664-015-9393-5","title":"An in-depth study of the promises and perils of mining GitHub","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":270,"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":"","keywords":"Computer science; Software; Point (geometry); Data science; World Wide Web; Set (abstract data type); Event (particle physics); Empirical research; The Internet; Quality (philosophy)","retraction":null,"screen_n_in":null,"score":{"opus":0.05189227763191294,"gpt":0.3137880090306686,"spread":0.2618957313987556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004735464,0.0001410605,0.000253621,0.0001657319,0.00002122254,0.00003696737,0.0007526951,0.0000545548,0.000001130059],"category_scores_gemma":[0.002513944,0.0001094988,0.00003061939,0.0007739405,0.00003414457,0.0002666894,0.0003715519,0.0001893747,5.066326e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694804,"about_ca_system_score_gemma":0.00009241549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003816221,"about_ca_topic_score_gemma":0.0000123733,"domain_scores_codex":[0.9986364,0.00005753996,0.0002921181,0.0002878273,0.0004642531,0.0002618857],"domain_scores_gemma":[0.9985228,0.0006166723,0.00004922277,0.0005647362,0.00009146906,0.0001551564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004781138,0.000158065,0.9664018,0.00004411503,0.00001081245,0.00000711446,0.007090937,0.02469545,0.0002057069,0.0000108308,0.00002826904,0.001342189],"study_design_scores_gemma":[0.0005898576,0.0003766384,0.9794933,0.00006407967,0.000003803036,0.000008968999,0.0003049112,0.01791116,0.001010315,0.00001504148,0.00007484831,0.0001470959],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569069,0.0001901046,0.04231337,0.00003113473,0.0001476757,0.0002486652,7.576984e-7,0.0001565177,0.000004916678],"genre_scores_gemma":[0.9810405,0.000001154906,0.01888078,0.00000702895,0.00002543505,0.00002119375,1.906598e-7,0.0000175597,0.000006089214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0241337,"threshold_uncertainty_score":0.4465233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011992028","doi":"10.1007/s10664-019-09796-5","title":"An exploratory study of smart contracts in the Ethereum blockchain platform","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":241,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Microsoft","keywords":"Blockchain; Smart contract; Computer science; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.03360663077197832,"gpt":0.2675809242198514,"spread":0.233974293447873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003590197,0.0001208883,0.0001838765,0.00006577007,0.00004801225,0.00002527954,0.001040513,0.00009815457,0.000002813012],"category_scores_gemma":[0.0001917293,0.00009498734,0.00002984965,0.0006933764,0.00002068453,0.00009803758,0.0001216598,0.0003847595,0.000004596657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000187502,"about_ca_system_score_gemma":0.00002233125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001331131,"about_ca_topic_score_gemma":0.0000409866,"domain_scores_codex":[0.999027,0.000041584,0.0002523242,0.0002822917,0.000195491,0.0002013503],"domain_scores_gemma":[0.9990709,0.0002587416,0.00004699935,0.000517589,0.00002914558,0.00007664689],"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":[0.00008363806,0.007605324,0.439775,0.0001870696,0.0001988945,0.0003676722,0.3651937,0.1148296,0.002530867,0.02780002,0.001604772,0.03982342],"study_design_scores_gemma":[0.002932456,0.003229318,0.1846875,0.00004960935,0.00002862941,0.00002594456,0.007807211,0.7858666,0.002866615,0.002396354,0.009005351,0.001104406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7949066,0.00006522352,0.2035072,0.0009444395,0.00003111213,0.0002419271,9.624584e-7,0.0002975048,0.000005017997],"genre_scores_gemma":[0.994951,0.00000109676,0.004437496,0.0004967001,0.00002953476,0.00007463584,5.17526e-7,0.000008733611,3.464717e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.671037,"threshold_uncertainty_score":0.3873471,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031459347","doi":"10.1007/s10664-010-9152-6","title":"Using grounded theory to study the experience of software development","year":2011,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":236,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Grounded theory; Computer science; Context (archaeology); Software; Management science; Development theory; Qualitative research; Engineering; Sociology; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.1170929886314408,"gpt":0.3288625697848295,"spread":0.2117695811533887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007511282,0.0002640863,0.0002562543,0.000148992,0.0001556122,0.00006870282,0.001449658,0.00007216864,0.00003490341],"category_scores_gemma":[0.001206664,0.0002017595,0.00007262918,0.0008093377,0.00002579409,0.0004189389,0.0006597943,0.0002483167,0.00001031373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008136939,"about_ca_system_score_gemma":0.00006052926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005347087,"about_ca_topic_score_gemma":0.000001799961,"domain_scores_codex":[0.9982731,0.00007900089,0.0004229841,0.0004185965,0.0004110894,0.0003952034],"domain_scores_gemma":[0.9981063,0.0007534274,0.00009733394,0.0007943503,0.00009142062,0.0001571949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001544194,0.002019734,0.4149331,0.0002099874,0.000765454,0.0002889532,0.3761599,0.02264424,0.0006525455,0.006713697,0.0003527348,0.1751053],"study_design_scores_gemma":[0.001042997,0.001180999,0.9132613,0.0003161496,0.0001200764,0.0001602317,0.001820709,0.01105406,0.04517988,0.003239885,0.01969292,0.002930795],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2997518,0.00007931393,0.6988178,0.00001191563,0.0002513737,0.000275928,4.829866e-7,0.000802318,0.000008996391],"genre_scores_gemma":[0.4815196,7.828978e-7,0.518301,0.00007210313,0.00002257461,0.00005614834,2.051679e-7,0.00001920235,0.000008507656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4983282,"threshold_uncertainty_score":0.8227513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288079797","doi":"10.1007/s10664-020-09875-y","title":"Pandemic programming","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":234,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"New York Institute of Technology; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Oulun Yliopisto; Dalhousie University; University of Adelaide","keywords":"Structural equation modeling; Productivity; Confirmatory factor analysis; Notice; Pandemic; Psychology; Applied psychology; Preparedness; Human factors and ergonomics; Poison control; Computer science; Coronavirus disease 2019 (COVID-19); Medicine; Environmental health; Political science; Economics; Management; Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.1644432876958341,"gpt":0.4689126539423454,"spread":0.3044693662465113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003014689,0.0001191034,0.0001920809,0.00004159394,0.0002840702,0.000006240776,0.0001501397,0.0001515976,0.0004495989],"category_scores_gemma":[0.003445209,0.0001064894,0.00005519183,0.0003894952,0.00001347399,0.00007747,0.000107046,0.0009308369,0.0009392321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001232532,"about_ca_system_score_gemma":0.0002254532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000181271,"about_ca_topic_score_gemma":0.000002285853,"domain_scores_codex":[0.9983725,0.00008126631,0.0003520275,0.0002350125,0.0003060182,0.0006531872],"domain_scores_gemma":[0.9978056,0.001368723,0.00003877912,0.0001161578,0.00008423669,0.0005864819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004094437,0.00001048398,0.9811835,0.0003669524,0.000007386144,0.000006919882,0.0006556424,0.0003518433,0.00001778081,0.00004168698,0.003299897,0.01401694],"study_design_scores_gemma":[0.0004329698,0.00009409067,0.5324752,0.00006878919,0.000003872986,0.000001054207,0.00005820863,0.003725724,0.000003702248,0.00001673337,0.4629595,0.0001601037],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6869334,0.0008008236,0.2896228,0.01433982,0.001194234,0.002429527,0.00003772272,0.003572609,0.001069052],"genre_scores_gemma":[0.9738311,0.00002650856,0.01917845,0.00478512,0.001539825,0.0003315965,0.00004281739,0.00005783553,0.0002067819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4596596,"threshold_uncertainty_score":0.9998387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109156518","doi":"10.1007/s10664-013-9258-8","title":"Bug characteristics in open source software","year":2013,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":232,"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":"National Science Foundation","keywords":"Software bug; Computer science; Concurrency; Security bug; Software regression; Linux kernel; Operating system; Software; Source code; Software engineering; Software system; Software security assurance; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.02582870811887423,"gpt":0.2819716111627644,"spread":0.2561429030438902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004858199,0.0003897502,0.0004994574,0.0003815921,0.0000901938,0.0008689212,0.00314325,0.0002048454,0.0001660376],"category_scores_gemma":[0.006162914,0.0003989054,0.00009619017,0.001344114,0.00003196756,0.001360994,0.002119899,0.0007605121,0.0007149973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002995658,"about_ca_system_score_gemma":0.0001229571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001980788,"about_ca_topic_score_gemma":0.000003122634,"domain_scores_codex":[0.9969934,0.00005312229,0.0005558701,0.0007850696,0.0005668098,0.001045762],"domain_scores_gemma":[0.9964252,0.001887919,0.0000666293,0.001051982,0.000138518,0.0004298216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003443895,0.0001159523,0.9631999,0.00009513162,0.00002517549,0.00008195092,0.0004775984,0.006006156,0.0001115332,0.00007429805,0.004765609,0.02504322],"study_design_scores_gemma":[0.0004979551,0.0000682349,0.9485061,0.0001327189,0.000002803936,0.00003641551,0.00000728441,0.03037778,0.000193819,0.0001702504,0.01932382,0.0006828372],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2726126,0.0001004197,0.7243778,0.000414839,0.0004336024,0.0005183171,0.000003044668,0.001522565,0.00001683284],"genre_scores_gemma":[0.7652481,0.00001109985,0.2329011,0.0004393636,0.0002221014,0.0004181196,0.00001436936,0.0001227135,0.0006230417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4926355,"threshold_uncertainty_score":0.9998463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1174118978","doi":"10.1007/s10664-015-9388-2","title":"Fresh apps: an empirical study of frequently-updated mobile apps in the Google play store","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":201,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Mobile apps; Computer science; World Wide Web; App store; Internet privacy","retraction":null,"screen_n_in":null,"score":{"opus":0.04990175293114012,"gpt":0.3499705564766025,"spread":0.3000688035454623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001981325,0.0001965524,0.0003405254,0.0001126734,0.0001423619,0.0001039551,0.0006222925,0.0001838754,0.00003770749],"category_scores_gemma":[0.003329144,0.000159477,0.00007273137,0.0009417017,0.000124934,0.0002901248,0.00007990459,0.0004014532,0.00001613121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002033127,"about_ca_system_score_gemma":0.0001792534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001134548,"about_ca_topic_score_gemma":0.001052722,"domain_scores_codex":[0.9973941,0.0004830782,0.0004023846,0.0003236624,0.0009002916,0.0004964554],"domain_scores_gemma":[0.9983602,0.0008291262,0.00007786727,0.0003004083,0.0001110973,0.0003213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004285315,0.001638409,0.7476487,0.0000174131,0.00003763933,0.00005919478,0.2303734,0.004101986,0.000005646836,0.00006687397,0.01279338,0.003214531],"study_design_scores_gemma":[0.003548012,0.002487743,0.3609434,0.0001854161,0.00008899039,0.000005823897,0.3214779,0.0009646017,0.00002580087,0.0008759728,0.307912,0.001484302],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996354,0.0001821118,0.0003053317,0.0001635718,0.0004240498,0.0005834021,0.00001129782,0.0002805479,0.001695675],"genre_scores_gemma":[0.9989067,0.000004257292,0.000386101,0.0001193068,0.0003561082,0.0001047191,0.00001759039,0.00002774949,0.00007745355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3867053,"threshold_uncertainty_score":0.6503283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2612705982","doi":"10.1007/s10664-017-9522-4","title":"Identifying self-admitted technical debt in open source projects using text mining","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Concordia University","funders":"Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Technical debt; Computer science; Classifier (UML); Source code; Code review; Baseline (sea); Open source; Artificial intelligence; F1 score; Machine learning; Data mining; Natural language processing; Software; Software quality; Software development; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07815053665037296,"gpt":0.3568263279761991,"spread":0.2786757913258261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001092554,0.0004008083,0.0005087902,0.0004819765,0.0004576864,0.002019179,0.005158322,0.0002621862,0.0000125523],"category_scores_gemma":[0.007963097,0.0004276124,0.0001167774,0.0008401823,0.00004643335,0.001843286,0.004464046,0.0008085683,0.0000406439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005513057,"about_ca_system_score_gemma":0.0002476913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001741777,"about_ca_topic_score_gemma":0.00001583222,"domain_scores_codex":[0.9966274,0.00006131829,0.0005212922,0.0009986634,0.0006878369,0.001103501],"domain_scores_gemma":[0.9963688,0.001237933,0.0001414895,0.001813742,0.00009576895,0.0003422138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001046591,0.0001593137,0.9702091,0.000176375,0.00005006883,0.0004077705,0.001309973,0.01984857,0.001588212,0.0001091726,0.0003957234,0.005735232],"study_design_scores_gemma":[0.001035742,0.0000718739,0.7463515,0.0005730992,0.00001217171,0.0001746964,0.00002599675,0.2472291,0.001214608,0.00007214633,0.002286248,0.0009527431],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4400647,0.00009959622,0.5575956,0.0001305056,0.0003604548,0.0004045475,8.095723e-7,0.00130687,0.00003695014],"genre_scores_gemma":[0.6484872,0.000003676615,0.3511574,0.00004542707,0.0001163442,0.0000661286,0.000001245709,0.00006922843,0.0000533685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2273805,"threshold_uncertainty_score":0.9998176,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991867644","doi":"10.1007/s10664-015-9375-7","title":"Analyzing and automatically labelling the types of user issues that are raised in mobile app reviews","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"App store; Computer science; World Wide Web; Download; Internet privacy; Mobile apps; Mobile device; Analytics; Notice; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.05224016304009076,"gpt":0.3190022140689671,"spread":0.2667620510288763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001170562,0.0001997656,0.0004114475,0.0001856222,0.00003515461,0.00009705221,0.0006658933,0.00008780358,0.000006310668],"category_scores_gemma":[0.003888967,0.0001468129,0.00006150576,0.0008552639,0.00004147855,0.0002726501,0.0003394883,0.0003326852,0.00001628811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007326922,"about_ca_system_score_gemma":0.00004101483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001358957,"about_ca_topic_score_gemma":0.000002331447,"domain_scores_codex":[0.9984935,0.00006663286,0.000363211,0.0003258917,0.0003718229,0.0003789444],"domain_scores_gemma":[0.9976998,0.001462949,0.00007170482,0.000513136,0.00007704385,0.0001753777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008667386,0.00008764648,0.8681135,0.0005288202,0.00005258004,0.0000481574,0.003370517,0.1150562,0.0001667048,0.0002308908,0.002288599,0.01004777],"study_design_scores_gemma":[0.001367344,0.0002518017,0.5650966,0.001523841,0.0000295573,0.0000458683,0.0001299552,0.3343301,0.001941337,0.000435739,0.09367935,0.001168482],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3242166,0.01530905,0.6590646,0.0003372069,0.0001803387,0.0003807817,0.000001286312,0.000503575,0.000006593834],"genre_scores_gemma":[0.8334458,0.0004142507,0.1657062,0.00007416616,0.0001037615,0.0001228668,0.000001657666,0.0000463116,0.00008497946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5092292,"threshold_uncertainty_score":0.5986856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604794021","doi":"10.1007/s10664-017-9514-4","title":"What do developers search for on the web?","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of British Columbia","funders":"Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China; Baidu","keywords":"Computer science; Debugging; World Wide Web; Reuse; Software bug; Software; Search engine optimization; Application programming interface; Information retrieval; Software engineering; Search engine; Data science; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06330645191543763,"gpt":0.3294800053743171,"spread":0.2661735534588795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009093169,0.00025326,0.0002105196,0.0001378254,0.0006276443,0.002000733,0.003000235,0.0001172762,0.00002012475],"category_scores_gemma":[0.006646141,0.0001861554,0.0001345945,0.0002424114,0.00006187339,0.0008738113,0.0006733935,0.0004844986,0.000125606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000160157,"about_ca_system_score_gemma":0.0001346013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004227658,"about_ca_topic_score_gemma":6.997392e-7,"domain_scores_codex":[0.9978727,0.0000273502,0.0002024945,0.0005397423,0.0006126438,0.0007450482],"domain_scores_gemma":[0.9938225,0.004124071,0.00003828916,0.001652024,0.0001414963,0.0002216771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001288657,0.0004668476,0.3896727,0.0008008007,0.0007053026,0.0003482092,0.007045595,0.1540725,0.001389637,0.04551778,0.08367986,0.3161719],"study_design_scores_gemma":[0.001914046,0.0005409784,0.475586,0.001020646,0.00001855874,0.00005823089,0.0001240804,0.2068776,0.0132842,0.0006471526,0.297749,0.00217954],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1979769,0.0003232148,0.7896345,0.008382531,0.002070848,0.0005717629,0.000004841186,0.001000431,0.00003501315],"genre_scores_gemma":[0.9486738,0.00008883079,0.04969626,0.0004417942,0.0003831241,0.0002583623,0.000002348181,0.00007585793,0.000379583],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.750697,"threshold_uncertainty_score":0.9990353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1549553848","doi":"10.1023/a:1009815306478","title":"Replicated Case Studies for Investigating Quality Factors in Object-Oriented Designs","year":2001,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Carleton University","funders":"","keywords":"Computer science; Cohesion (chemistry); Software engineering; Quality (philosophy); Software quality; Set (abstract data type); Software; Data science; Data mining; Programming language; Software development","retraction":null,"screen_n_in":null,"score":{"opus":0.1714365202462394,"gpt":0.4017966966694224,"spread":0.230360176423183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009119512,0.0003459275,0.0004776801,0.000364631,0.0001485135,0.00009232421,0.0005686528,0.0001502384,0.000003406196],"category_scores_gemma":[0.02926534,0.0003351158,0.0001259639,0.001895583,0.00004890042,0.0004132745,0.0003348523,0.0004527067,0.000006748259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004273322,"about_ca_system_score_gemma":0.00008439602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001045115,"about_ca_topic_score_gemma":0.00001798882,"domain_scores_codex":[0.9972526,0.00008446789,0.0006259132,0.0007796744,0.00040371,0.000853573],"domain_scores_gemma":[0.9915082,0.007170237,0.00007874339,0.0007350448,0.0002076808,0.0003000463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001012997,0.00009263487,0.9558115,0.000241034,0.00009073354,0.0009205661,0.003281343,0.03620536,0.0009832871,0.0004024138,0.0004672862,0.00149368],"study_design_scores_gemma":[0.003257109,0.0005775087,0.7842523,0.0005509747,0.00003321289,0.001668767,0.0005345563,0.1849953,0.0122075,0.001012854,0.007923006,0.002986839],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5189525,0.0001819261,0.479303,0.0001031461,0.0002066668,0.0002790871,0.00000312522,0.000969233,0.000001338161],"genre_scores_gemma":[0.8692024,0.000009449936,0.1303331,0.00007308872,0.0000812809,0.0002041461,0.000007590294,0.00004896575,0.00003994328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3502499,"threshold_uncertainty_score":0.9999101,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176989815","doi":"10.1007/s10664-021-10066-6","title":"Test case selection and prioritization using machine learning: a systematic literature review","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":158,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Mitacs; Huawei Technologies; Canada Research Chairs","keywords":"Regression testing; Computer science; Machine learning; Prioritization; Artificial intelligence; Feature selection; Process (computing); Software; Test case; Test (biology); Software engineering; Regression analysis; Software development; Engineering; Management science; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.01946948849480299,"gpt":0.2850008970086635,"spread":0.2655314085138605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004174968,0.0002271536,0.0003640238,0.000156809,0.0001411841,0.0002971124,0.0001805412,0.0001094517,0.000006860845],"category_scores_gemma":[0.01528034,0.0002232213,0.0000673894,0.001847882,0.000007971352,0.0004038884,0.0002258184,0.0005301324,0.000005628417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001518758,"about_ca_system_score_gemma":0.0000702051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004709431,"about_ca_topic_score_gemma":0.000001945197,"domain_scores_codex":[0.9984246,0.0001000638,0.000332643,0.0004576697,0.0003399796,0.0003450238],"domain_scores_gemma":[0.9975602,0.001629056,0.00005547016,0.0003049836,0.0002595853,0.0001907105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004342449,0.0003031302,0.4333583,0.4577288,0.0002658562,0.02434745,0.001914266,0.07470246,0.004283279,0.0002973358,0.0005284228,0.00226644],"study_design_scores_gemma":[0.0003038077,0.00008468128,0.003182532,0.04389936,0.00006338166,0.03765606,0.000005007431,0.912616,0.000741136,0.00001398902,0.000829468,0.0006046354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02534554,0.1020702,0.8708385,0.0001737702,0.0001777622,0.0003307455,0.000002990254,0.001059249,0.000001243963],"genre_scores_gemma":[0.525873,0.01030735,0.4621122,0.0005257826,0.0004159788,0.0001559303,0.00005051575,0.0001890332,0.0003701526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8379135,"threshold_uncertainty_score":0.9930144,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144641356","doi":"10.1007/s10664-006-7552-4","title":"A flexible method for software effort estimation by analogy","year":2006,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":156,"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":"Analogy; Data mining; Computer science; Similarity (geometry); Quality (philosophy); Feature (linguistics); Adaptation (eye); Estimation; Machine learning; Artificial intelligence; Engineering; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0171820834262038,"gpt":0.3118333456040533,"spread":0.2946512621778495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005944044,0.0003611593,0.0003949986,0.0003156797,0.0001483906,0.0002073679,0.0009191816,0.00022044,0.00001717652],"category_scores_gemma":[0.002665786,0.0003781943,0.000188314,0.0009994789,0.00002252279,0.0004772973,0.0002450797,0.0003355072,0.00004321653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002613706,"about_ca_system_score_gemma":0.00009024113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007066281,"about_ca_topic_score_gemma":0.000001792835,"domain_scores_codex":[0.9973494,0.00002872452,0.0004523614,0.0007366197,0.0005286978,0.0009041929],"domain_scores_gemma":[0.9959953,0.002898419,0.00006635638,0.0006592117,0.0001514919,0.0002292066],"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":[0.00002196012,0.0002280701,0.08731848,0.0004484233,0.0001053974,0.00003666354,0.0001587399,0.7535529,0.001086753,0.002067244,0.1099029,0.04507253],"study_design_scores_gemma":[0.001153618,0.000259517,0.05936804,0.00008169223,0.00002631572,0.00007418278,0.000001898409,0.8433763,0.009967305,0.00268742,0.08186958,0.001134138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006412457,0.0004110316,0.9886331,0.0003163653,0.0004572037,0.000441242,0.00002487047,0.003294779,0.000008959392],"genre_scores_gemma":[0.03624903,0.000002114746,0.9625425,0.0001377647,0.0002100511,0.0002906281,0.00009353313,0.00008158017,0.000392829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08982342,"threshold_uncertainty_score":0.999867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045837563","doi":"10.1007/s10664-012-9219-7","title":"Static test case prioritization using topic models","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":156,"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":"Test suite; Computer science; Code coverage; Test case; Source code; Black box; Test Management Approach; Programming language; White-box testing; Test (biology); Test data; Operating system; Software; Software development; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06432137932201937,"gpt":0.3036697114581389,"spread":0.2393483321361196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002420302,0.0001730436,0.0001598542,0.0001191105,0.0001122495,0.00009755384,0.0002551256,0.00008151158,0.000003972741],"category_scores_gemma":[0.001400123,0.0001739218,0.0000486347,0.0004492367,0.00001219212,0.0007973905,0.0001690105,0.0001706461,0.000008227141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260916,"about_ca_system_score_gemma":0.00003353302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003682193,"about_ca_topic_score_gemma":2.968668e-7,"domain_scores_codex":[0.9988658,0.00002193053,0.0002247727,0.0002323451,0.0002037142,0.0004514626],"domain_scores_gemma":[0.9985216,0.0008052508,0.00004636206,0.0003727608,0.00005943031,0.0001945704],"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":[0.000002932833,0.0005641402,0.7631552,0.0004284631,0.00005890921,0.001289744,0.005828251,0.1719298,0.0002808286,0.003240478,0.009944203,0.04327707],"study_design_scores_gemma":[0.0001116512,0.00003663657,0.003398017,0.00007515762,0.00001100808,0.001471306,0.000002664606,0.9907523,0.000249052,0.002996732,0.0005388826,0.0003565747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07237958,0.0001909417,0.9180328,0.00006440358,0.0002831485,0.00009874723,0.000001736448,0.008934137,0.00001452531],"genre_scores_gemma":[0.5370809,0.000001168149,0.4626541,0.0001249468,0.0001053682,0.000007784058,0.000001127405,0.00001541916,0.000009191915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8188225,"threshold_uncertainty_score":0.7092326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2586191823","doi":"10.1007/s10664-017-9499-z","title":"Reengineering legacy applications into software product lines: a systematic mapping","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Austrian Science Fund; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Business process reengineering; Code refactoring; Computer science; Software product line; Software engineering; Process (computing); Process management; Product (mathematics); Reuse; Software; Data science; Software development; Systems engineering; Engineering; Manufacturing engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05418621084206881,"gpt":0.3191469998959,"spread":0.2649607890538312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009862885,0.0006476646,0.0009262433,0.0003815525,0.0007665456,0.0009617576,0.0034726,0.0001968908,0.000004503358],"category_scores_gemma":[0.01785276,0.0006395876,0.0002537704,0.0006209207,0.00008112571,0.002275034,0.001256718,0.0006985113,0.00008508932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003056428,"about_ca_system_score_gemma":0.00009325794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001405936,"about_ca_topic_score_gemma":0.000001514273,"domain_scores_codex":[0.9964864,0.0000748533,0.0008338866,0.001114012,0.000579456,0.0009114126],"domain_scores_gemma":[0.9939376,0.001678226,0.000341417,0.003476234,0.0002232074,0.0003433719],"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":[0.00001343249,0.0002007699,0.01480456,0.03662596,0.0004712238,0.0002406112,0.002970825,0.9133236,0.00200266,0.003187585,0.0005686952,0.02559007],"study_design_scores_gemma":[0.008037717,0.001158664,0.1871625,0.05076468,0.0007023229,0.002224816,0.0006970083,0.5378996,0.02302592,0.04369814,0.117232,0.02739661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002261311,0.001576374,0.9879867,0.0003985906,0.001103273,0.001031772,0.000003093326,0.00562409,0.000014768],"genre_scores_gemma":[0.07439999,0.00003042447,0.9238667,0.00007246322,0.0005203854,0.0008550936,0.000006096431,0.0001127142,0.0001360626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3754241,"threshold_uncertainty_score":0.9996055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039052699","doi":"10.1007/s10664-012-9228-6","title":"Studying re-opened bugs in open source software","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":138,"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":"Software bug; Eclipse; Software regression; Dimension (graph theory); Open source; Rework; Computer science; Software; Software quality; Software engineering; Engineering; Software development; Operating system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05923128895567467,"gpt":0.3226179125427767,"spread":0.263386623587102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001575528,0.0004546347,0.0005448512,0.0004765209,0.0001504359,0.0005261892,0.003348088,0.000216305,0.00007423441],"category_scores_gemma":[0.007043353,0.0004695106,0.0001195914,0.001917792,0.00002987507,0.002203802,0.003153432,0.0008676458,0.0002372252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004766681,"about_ca_system_score_gemma":0.0001131353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001135156,"about_ca_topic_score_gemma":0.000007333398,"domain_scores_codex":[0.9961358,0.0001042174,0.0005643766,0.0007711113,0.0007919224,0.00163253],"domain_scores_gemma":[0.9953523,0.002679419,0.00007004588,0.001196406,0.00008384399,0.000617984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008732182,0.0001900597,0.9630119,0.00007576028,0.00003443673,0.00004617012,0.001833956,0.02364812,0.00006682758,0.00008920165,0.00181411,0.009180743],"study_design_scores_gemma":[0.001402912,0.0001256324,0.9322138,0.0002711807,0.00001077724,0.0000607441,0.00007071214,0.01288677,0.0008795312,0.00008484584,0.05059392,0.001399201],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2231411,0.0006899379,0.7728356,0.0002564741,0.0007323587,0.0005313292,0.00000221536,0.001773745,0.00003724133],"genre_scores_gemma":[0.7904896,0.00000865811,0.208342,0.0002780212,0.000278902,0.0001960787,0.000006064134,0.0001106943,0.0002900158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5673485,"threshold_uncertainty_score":0.9997756,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3185088259","doi":"10.1007/s10664-021-09992-2","title":"Perceived diversity in software engineering: a systematic literature review","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"","keywords":"Diversity (politics); Gender diversity; Diversity training; Cultural diversity; Knowledge management; Computer science; Psychology; Engineering; Political science; Management","retraction":null,"screen_n_in":null,"score":{"opus":0.02310516610456684,"gpt":0.2595688079767733,"spread":0.2364636418722064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004931504,0.0004093244,0.000774449,0.0003008847,0.0001543759,0.000264932,0.001158425,0.0002007119,0.00003709001],"category_scores_gemma":[0.008309484,0.0004178934,0.0002246945,0.003878955,0.00001502901,0.0007676223,0.001478614,0.0007481943,0.00007901601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003199359,"about_ca_system_score_gemma":0.0001186073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004672394,"about_ca_topic_score_gemma":0.000003122134,"domain_scores_codex":[0.997235,0.0001013775,0.0006975649,0.0007373219,0.0006143326,0.0006144254],"domain_scores_gemma":[0.9973913,0.000849722,0.0001064369,0.001064971,0.0003583793,0.0002292113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001218251,0.001159608,0.4548781,0.4312982,0.0006836665,0.01114393,0.01676629,0.05829002,0.0004712042,0.004900039,0.01828294,0.002113869],"study_design_scores_gemma":[0.002396779,0.0001792738,0.5358446,0.390354,0.0002610283,0.002164002,0.00008616557,0.0478363,0.0003074612,0.0003178801,0.0153197,0.004932828],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01985221,0.03209257,0.9433278,0.00119953,0.0007437178,0.0007805031,0.00001688669,0.001969018,0.00001774927],"genre_scores_gemma":[0.1990599,0.003003058,0.7901362,0.006007524,0.000345243,0.0003953378,0.0001402592,0.0001944231,0.0007180438],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1792077,"threshold_uncertainty_score":0.9998273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810627707","doi":"10.1007/s10664-018-9634-5","title":"How do developers utilize source code from stack overflow?","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":129,"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; Source code; Copying; Codebase; Code reuse; Reuse; Code review; Programming language; Code (set theory); Stack (abstract data type); Software engineering; World Wide Web; Operating system; Static program analysis; Software; Software development; Engineering; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.03258012208955109,"gpt":0.277064878376598,"spread":0.244484756287047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003199541,0.0004252122,0.0003726921,0.0002409109,0.0001669266,0.0007049958,0.001717785,0.0002244889,0.00008680674],"category_scores_gemma":[0.005428929,0.0004215513,0.0001370669,0.001171028,0.0000905628,0.0006846879,0.000814611,0.0005694607,0.0002980692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002966901,"about_ca_system_score_gemma":0.0001462112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003343114,"about_ca_topic_score_gemma":0.000004781396,"domain_scores_codex":[0.996817,0.00004482729,0.0003032953,0.0009373755,0.0008838316,0.001013654],"domain_scores_gemma":[0.9960664,0.002017374,0.00005008433,0.00116927,0.0002096768,0.0004872282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007454663,0.0002812817,0.8146433,0.0002178202,0.0005738541,0.0003787119,0.007042255,0.02010233,0.002528992,0.0007146338,0.05505002,0.09839229],"study_design_scores_gemma":[0.001216825,0.0002488083,0.3761968,0.0002012606,0.00001965729,0.00004228227,0.00004578226,0.09937797,0.008040308,0.0002328552,0.5126422,0.00173531],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2313363,0.0003178067,0.7645723,0.0005482037,0.0008406875,0.0001449637,0.00001332016,0.002206826,0.00001968306],"genre_scores_gemma":[0.7509447,0.000009914106,0.2473895,0.0002378718,0.0007234977,0.00003582635,0.000009809204,0.00009447217,0.0005544642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5196084,"threshold_uncertainty_score":0.9998236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1497968089","doi":"10.1023/a:1024424811345","title":"Fault Prediction Modeling for Software Quality Estimation: Comparing Commonly Used Techniques","year":2003,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Software quality; Software; Artificial neural network; Approximation error; Reliability engineering; Data mining; Artificial intelligence; Machine learning; Algorithm; Software development; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07721747522635733,"gpt":0.3501777772525694,"spread":0.2729603020262121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00140083,0.0002906085,0.0004805184,0.0002253725,0.0003116049,0.0002764199,0.0006873557,0.0002012792,0.000008864174],"category_scores_gemma":[0.005380118,0.000292858,0.0002656979,0.0008240814,0.00003255575,0.0006636013,0.0001687635,0.0004158302,0.00001126196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562927,"about_ca_system_score_gemma":0.0001121793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002957987,"about_ca_topic_score_gemma":0.000004850769,"domain_scores_codex":[0.997311,0.000130758,0.0006674411,0.0006625305,0.000638091,0.0005901718],"domain_scores_gemma":[0.9972937,0.001359376,0.0000840328,0.0007361227,0.0002821524,0.0002446934],"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":[0.00001064787,0.0001672034,0.09468009,0.0003084925,0.00008055412,0.000003888579,0.0003951948,0.8871707,0.00007651346,0.002342355,0.0003664099,0.01439798],"study_design_scores_gemma":[0.0003061675,0.00006204323,0.001832844,0.00007526464,0.00001441691,0.000008300578,0.00001089933,0.9912236,0.001157902,0.002270302,0.002696077,0.0003421484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05314642,0.0001534791,0.9435468,0.0001609792,0.0001758099,0.0004006998,0.00001065437,0.002389677,0.00001547486],"genre_scores_gemma":[0.4940997,0.000005026055,0.5055825,0.00005551093,0.00005706008,0.0001340235,0.00002253186,0.0000240018,0.00001971609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4409533,"threshold_uncertainty_score":0.9999524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2543971965","doi":"10.1007/s10664-016-9452-6","title":"Review participation in modern code review","year":2016,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Software quality; Code review; Android (operating system); Open source software; Computer science; Process (computing); Source code; Open source; Software; Best practice; Quality (philosophy); Set (abstract data type); Data science; Software development; Political science; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.04737496011315095,"gpt":0.3480544134304684,"spread":0.3006794533173175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007575117,0.000221119,0.000380194,0.0001409669,0.00002521954,0.00002879646,0.0007753494,0.0000718062,0.00004309817],"category_scores_gemma":[0.008980447,0.0001651537,0.00009599431,0.0009652405,0.00001559101,0.0004580875,0.0002620545,0.0002296708,0.0001528657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002298746,"about_ca_system_score_gemma":0.00006247404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003395321,"about_ca_topic_score_gemma":0.000001785536,"domain_scores_codex":[0.997958,0.00006174019,0.0004625464,0.0004915178,0.0004379514,0.0005882306],"domain_scores_gemma":[0.9974568,0.001446121,0.00004587159,0.0007488307,0.00008275956,0.0002195396],"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":[0.000008134658,0.0003414052,0.3234422,0.02336106,0.00007970197,0.0002644088,0.000269605,0.005514902,0.0007857035,0.0005496573,0.08005099,0.5653322],"study_design_scores_gemma":[0.001841209,0.0002573348,0.5077471,0.1553996,0.00005826318,0.0001135589,7.699803e-7,0.04145813,0.001184474,0.0009348129,0.2882996,0.002705204],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003701405,0.09283011,0.8979808,0.003976741,0.0001939727,0.000369559,0.000003013796,0.0009351831,0.00000923275],"genre_scores_gemma":[0.5990868,0.2116793,0.1704314,0.01548916,0.0004989639,0.001893965,0.00001954613,0.0003040716,0.0005967795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7275494,"threshold_uncertainty_score":0.9993674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075269190","doi":"10.1007/s10664-014-9350-8","title":"Linguistic antipatterns: what they are and how developers perceive them","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Lexicon; Documentation; Source code; Cognitive dissonance; Computer science; Open source; Code (set theory); Empirical research; Affect (linguistics); Code review; Data science; Linguistics; Psychology; Artificial intelligence; Software development; Static program analysis; Social psychology; Software; Programming language; Communication; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.064961403368231,"gpt":0.2848505495581046,"spread":0.2198891461898736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004484697,0.0003229485,0.0003130209,0.0001681998,0.00008009019,0.0008416695,0.0008287748,0.0001366741,0.000005302434],"category_scores_gemma":[0.007570803,0.0002954523,0.0000630758,0.0004363619,0.00003614657,0.0008455758,0.0005467701,0.0004447637,0.00006794325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001912182,"about_ca_system_score_gemma":0.0001003665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001149325,"about_ca_topic_score_gemma":0.00000219138,"domain_scores_codex":[0.9979285,0.00004294113,0.0001723868,0.0006045542,0.0006051355,0.0006464616],"domain_scores_gemma":[0.9975135,0.001125397,0.00004318007,0.0005571034,0.0002214547,0.0005393163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001053653,0.00006630292,0.9622895,0.0002107424,0.0001038666,0.0004901807,0.01360811,0.00808102,0.00006107798,0.0001971815,0.002504496,0.01237699],"study_design_scores_gemma":[0.001543851,0.0002246876,0.8843107,0.0009086065,0.00002709928,0.0004744604,0.0007034718,0.06907811,0.0005806216,0.0005137062,0.03949031,0.002144403],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3894947,0.0009100485,0.6054888,0.001511573,0.001001353,0.0001744025,0.000002530405,0.00140259,0.0000139572],"genre_scores_gemma":[0.9357632,0.00006807387,0.06354639,0.0001983837,0.0002396449,0.00003050233,0.000002894054,0.00005460566,0.00009624722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5462685,"threshold_uncertainty_score":0.9999498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1909497710","doi":"10.1007/s10664-015-9396-2","title":"Towards building a universal defect prediction model with rank transformed predictors","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"University of Victoria","keywords":"Computer science; Software; Rank (graph theory); Workflow; Predictive modelling; Context (archaeology); Eclipse; Data mining; Software development; Obstacle; Software bug; Software engineering; Machine learning; Database; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02760184776548904,"gpt":0.2626829102734268,"spread":0.2350810625079377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004967626,0.0003470849,0.0003204588,0.0003532679,0.00008379864,0.0001488829,0.0008487701,0.0001723722,0.000004977282],"category_scores_gemma":[0.001311992,0.0003100125,0.0001347005,0.001145198,0.00004109129,0.0008990088,0.0001849057,0.0005304886,0.00001668784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005593395,"about_ca_system_score_gemma":0.0004254069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000223817,"about_ca_topic_score_gemma":0.000001645501,"domain_scores_codex":[0.997327,0.00003301994,0.0002783145,0.0006072115,0.0009985345,0.0007559236],"domain_scores_gemma":[0.9981569,0.0004277504,0.00003445291,0.000548059,0.000176637,0.000656223],"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":[0.00003941064,0.00004898979,0.04396766,0.00006089411,0.00009547183,0.00006731994,0.001214663,0.951546,0.0001250585,0.0003217549,0.0009971692,0.001515624],"study_design_scores_gemma":[0.001483678,0.000378046,0.0161956,0.000106886,0.00002944782,0.00008541723,0.00001483686,0.9768612,0.0008202167,0.0001529429,0.003359995,0.0005117554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2012297,0.00008754126,0.7953404,0.0001335339,0.0002904476,0.0002370241,0.000009530021,0.00263372,0.00003806324],"genre_scores_gemma":[0.7468565,0.000004900095,0.2528227,0.00003269863,0.0001165235,0.00004811522,0.000007085848,0.00005784303,0.0000536394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5456268,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026170849","doi":"10.1007/s10664-014-9338-4","title":"On rapid releases and software testing: a case study and a semi-systematic literature review","year":2014,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Context (archaeology); Test suite; Systematic review; Scope (computer science); Software engineering; Software; Software bug; Software testing; Test case; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02742795834347492,"gpt":0.2857589749436667,"spread":0.2583310166001918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001026332,0.000448234,0.0006997797,0.0002873302,0.0001689825,0.0003624868,0.0004812675,0.0001213308,0.000003618791],"category_scores_gemma":[0.03957811,0.0003768664,0.00007158864,0.001287038,0.0000298482,0.0003317526,0.0004650722,0.0006187606,0.00001179168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007153599,"about_ca_system_score_gemma":0.00003296275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001006421,"about_ca_topic_score_gemma":0.000001105087,"domain_scores_codex":[0.9973565,0.0002009169,0.0004872451,0.00083498,0.0005679707,0.0005523801],"domain_scores_gemma":[0.9886906,0.009689499,0.00008116692,0.0009313963,0.0001627888,0.0004445104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0000361614,0.001500013,0.4140809,0.4414271,0.0006947088,0.03331838,0.01018986,0.007679637,0.00006732767,0.0003842,0.009574081,0.08104759],"study_design_scores_gemma":[0.00710534,0.01025711,0.1406277,0.4322082,0.0006936993,0.08891694,0.0002438861,0.3066022,0.0001221626,0.0006346379,0.004396993,0.008191195],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4149471,0.05834781,0.5212908,0.0002618277,0.0003054635,0.001920301,0.000006372933,0.002915283,0.000005069072],"genre_scores_gemma":[0.9220911,0.0007407668,0.0756472,0.0007801689,0.0001703249,0.0003960948,0.000003629399,0.0001136979,0.00005700815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.507144,"threshold_uncertainty_score":0.9998683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2531425405","doi":"10.1007/s10664-016-9456-2","title":"Which log level should developers choose for a new logging statement?","year":2016,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Queen's University","funders":"","keywords":"Statement (logic); Logging; Computer science; Brier score; Leverage (statistics); Login; Database; Data mining; Information retrieval; Operating system; Machine learning; Forestry","retraction":null,"screen_n_in":null,"score":{"opus":0.07458787435700132,"gpt":0.3073065049729828,"spread":0.2327186306159815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005527308,0.0002907008,0.0003124899,0.0001335893,0.0001279203,0.00009892006,0.000759066,0.0001554996,0.00002463068],"category_scores_gemma":[0.001082004,0.0001949214,0.0001198051,0.0004988045,0.00001760144,0.0006798557,0.0002495991,0.0001501892,0.00009000645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002889838,"about_ca_system_score_gemma":0.0002895386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002194171,"about_ca_topic_score_gemma":0.000007582728,"domain_scores_codex":[0.9978303,0.00002127673,0.0004844096,0.0006138583,0.0003499492,0.0007002497],"domain_scores_gemma":[0.998212,0.0006708302,0.0000760552,0.000577123,0.0001513834,0.0003126105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001047864,0.0002287915,0.4984455,0.0009798551,0.0004048624,0.00002482805,0.003163178,0.0110518,0.001578905,0.001145894,0.07487842,0.4079932],"study_design_scores_gemma":[0.006227609,0.0006402509,0.3924212,0.001184454,0.00006857841,0.00008662456,0.00004686266,0.03617467,0.009502307,0.002350592,0.5479562,0.00334067],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03281292,0.0001143563,0.961664,0.002996464,0.0009742887,0.0003604526,0.00001111354,0.001048559,0.00001783728],"genre_scores_gemma":[0.6175734,0.00002065504,0.3805265,0.0004665479,0.00040614,0.0001237726,0.000005380797,0.00005415153,0.0008233834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5847605,"threshold_uncertainty_score":0.7948663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2055777130","doi":"10.1007/s10664-015-9366-8","title":"Investigating technical and non-technical factors influencing modern code review","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Code review; Process (computing); Code (set theory); Key (lock); Source code; Variety (cybernetics); Empirical research; Software engineering; Component (thermodynamics); Data science; Static program analysis; Software development; Computer security; Software; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05327895845453611,"gpt":0.31370679174594,"spread":0.2604278332914039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009029174,0.0003898318,0.0005226991,0.0002046596,0.00008899043,0.000166509,0.001057727,0.0002260956,0.000003323041],"category_scores_gemma":[0.01450765,0.0003631996,0.0001019764,0.001049521,0.00007610304,0.0005873565,0.001090991,0.0009250625,0.00002134644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003597514,"about_ca_system_score_gemma":0.0001909089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001348582,"about_ca_topic_score_gemma":0.000001935864,"domain_scores_codex":[0.9971033,0.0000458668,0.0005249556,0.000730612,0.0008499883,0.0007452173],"domain_scores_gemma":[0.9966091,0.001448683,0.00006931763,0.0007963785,0.0001569978,0.0009195241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003172075,0.00009396079,0.9602281,0.001663873,0.00004995832,0.000123563,0.00102507,0.01916204,0.003812124,0.0002129249,0.009914507,0.00371066],"study_design_scores_gemma":[0.001396087,0.0004912129,0.8487226,0.005364517,0.00006240759,0.0005570401,0.00002057271,0.1297252,0.002058181,0.001274311,0.007605402,0.002722468],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2304231,0.003761867,0.7625388,0.0004603912,0.0001847047,0.0003338523,0.000003142399,0.002277186,0.00001697025],"genre_scores_gemma":[0.7795002,0.0001122947,0.2196942,0.0004489622,0.00009736359,0.00006090251,0.000005574281,0.00006694008,0.00001348013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5490772,"threshold_uncertainty_score":0.999882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386982649","doi":"10.1007/s10664-023-10380-1","title":"Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code?","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":101,"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; Vulnerability (computing); Code (set theory); Process (computing); Computer security; Perspective (graphical); Secure coding; Software; Software engineering; Software security assurance; Artificial intelligence; Operating system; Information security; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03474644801521013,"gpt":0.3154596742478399,"spread":0.2807132262326297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009188286,0.0004059611,0.0004711092,0.0007471671,0.0001750933,0.0002190436,0.001279467,0.0001956342,0.0002225075],"category_scores_gemma":[0.008167374,0.000430545,0.0001448494,0.002466303,0.00005658425,0.0005053682,0.001192301,0.00076359,0.001956843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007065113,"about_ca_system_score_gemma":0.0001548969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001605245,"about_ca_topic_score_gemma":0.00002222623,"domain_scores_codex":[0.996208,0.00006611568,0.0005365604,0.001044475,0.0009449642,0.001199955],"domain_scores_gemma":[0.9952915,0.00308552,0.00004562262,0.001117683,0.0001024623,0.0003571924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002797455,0.000132539,0.702413,0.0004167305,0.00009869167,0.0006664553,0.01066577,0.2427232,0.0009366137,0.001139554,0.03754087,0.003238657],"study_design_scores_gemma":[0.001648072,0.0006143534,0.7704953,0.0004618157,0.00001341314,0.000128142,0.0001028208,0.1269248,0.009269198,0.001748921,0.08645829,0.002134904],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9011679,0.0002737354,0.09115834,0.002091942,0.0009352678,0.0003150715,0.00001017983,0.003976048,0.00007155703],"genre_scores_gemma":[0.9809093,0.00004022772,0.01469587,0.0005557049,0.0003761377,0.0001934432,0.00001850408,0.0001296648,0.00308117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1157984,"threshold_uncertainty_score":0.9998146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914582798","doi":"10.1007/s10664-018-9679-5","title":"The impact of feature reduction techniques on defect prediction models","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of Alberta","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Reduction (mathematics); Feature (linguistics); Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01584160135086377,"gpt":0.2569401352835333,"spread":0.2410985339326695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002374576,0.0001840588,0.0002037163,0.0001180731,0.00005930673,0.00003411161,0.0000928402,0.0002332192,0.00001004465],"category_scores_gemma":[0.00009053442,0.0001244991,0.0002559493,0.0003268671,0.000009070191,0.0001484613,0.00001505055,0.0003854626,0.00001858393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002398551,"about_ca_system_score_gemma":0.00001472298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001875091,"about_ca_topic_score_gemma":2.195277e-7,"domain_scores_codex":[0.9991366,0.00002296052,0.0002359898,0.0001603407,0.0002181227,0.0002259411],"domain_scores_gemma":[0.9994196,0.0001565247,0.00004057798,0.0002723955,0.00005105494,0.0000598707],"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":[0.00003950558,0.00001132726,0.001638452,0.00003721294,0.00008112747,5.741479e-7,0.00007398389,0.9787868,0.006662637,0.00001789259,0.005707563,0.006942984],"study_design_scores_gemma":[0.001408559,0.00280703,0.04219403,0.0009730902,0.00007965819,0.000164298,0.00009634214,0.8145137,0.1108816,0.0004520755,0.02514074,0.001288882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9525787,0.0002728411,0.0435232,0.00001191192,0.001389451,0.000494054,0.00002188538,0.001215069,0.0004929265],"genre_scores_gemma":[0.9991565,0.0000230945,0.000321502,0.000001716533,0.0003174478,0.00003017338,0.000006696374,0.00004476499,0.00009812917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.164273,"threshold_uncertainty_score":0.5076928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786424616","doi":"10.1007/s10664-018-9595-8","title":"Studying software logging using topic models","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Queen's University","funders":"","keywords":"Logging; Computer science; Software; Software engineering; Operating system; Forestry; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.0777747160628274,"gpt":0.316326678815803,"spread":0.2385519627529755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005118187,0.0004213418,0.0004009803,0.0004252509,0.0003034539,0.0003154789,0.001483752,0.0001913534,0.00003722779],"category_scores_gemma":[0.002446872,0.0004387199,0.0001524643,0.001202165,0.00007043553,0.001069792,0.0009817422,0.0005723861,0.00009964524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003814306,"about_ca_system_score_gemma":0.0001347002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003529906,"about_ca_topic_score_gemma":0.000001385979,"domain_scores_codex":[0.9966944,0.00004930447,0.0004461033,0.0008622523,0.0008008252,0.001147103],"domain_scores_gemma":[0.9970499,0.001229239,0.00006312567,0.001051951,0.0002182456,0.0003875779],"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":[0.00001816253,0.0002471808,0.3876337,0.0004344902,0.0002789513,0.0003879578,0.004282119,0.5720215,0.001223374,0.001269387,0.002238177,0.02996494],"study_design_scores_gemma":[0.0006742692,0.0002097795,0.05016086,0.0002530462,0.00002132933,0.000138673,0.00002156024,0.938502,0.001756057,0.001162614,0.005808719,0.001291105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2634501,0.0002543853,0.7326838,0.00007650625,0.0008702963,0.0001803098,0.000001845776,0.002465553,0.00001714111],"genre_scores_gemma":[0.6252622,0.000003638049,0.3738894,0.0001509087,0.0005382026,0.00002249014,0.000001820078,0.0000676023,0.00006372027],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3664804,"threshold_uncertainty_score":0.9998065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3159076496","doi":"10.1007/s10664-020-09910-y","title":"Promises and challenges of microservices: an exploratory study","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Microservices; Computer science; Software deployment; Scalability; Reuse; Best practice; Software development; Process (computing); Software engineering; Code reuse; Software; Knowledge management; Engineering; Cloud computing; Database; Management","retraction":null,"screen_n_in":null,"score":{"opus":0.04185144518438682,"gpt":0.2711256357909792,"spread":0.2292741906065924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003010401,0.0001457053,0.000260227,0.00005355816,0.00005057303,0.00004729784,0.0003136905,0.00006757558,0.000003654732],"category_scores_gemma":[0.0001722668,0.0001271289,0.00003923872,0.0002637566,0.00001782321,0.0005065735,0.0002732749,0.0001121832,0.000003634318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002170244,"about_ca_system_score_gemma":0.00006446295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004523838,"about_ca_topic_score_gemma":0.00001476153,"domain_scores_codex":[0.998859,0.00006325552,0.0002609225,0.0004125688,0.0002067246,0.0001975225],"domain_scores_gemma":[0.9989775,0.000167386,0.00004540926,0.0005593191,0.0001280776,0.0001222817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001369417,0.001508856,0.9178703,0.002244088,0.000135326,0.0001314889,0.0437936,0.001795881,0.001320084,0.0002493465,0.00005020234,0.03088713],"study_design_scores_gemma":[0.00131675,0.0008328237,0.973226,0.0002772186,0.0000303947,0.00007447336,0.003317734,0.007072204,0.008656147,0.0001953808,0.004191013,0.0008098825],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638233,0.00443941,0.03084561,0.0001389863,0.000236822,0.0001542126,0.000001347482,0.0003545736,0.000005762047],"genre_scores_gemma":[0.9826474,0.0001371628,0.01707187,0.00003908793,0.00005695205,0.00002882977,9.937503e-7,0.00001284844,0.000004872305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05535568,"threshold_uncertainty_score":0.5184167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979991500","doi":"10.1007/s10664-012-9224-x","title":"Configuring latent Dirichlet allocation based feature location","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":92,"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":"U.S. Department of Education; National Science Foundation","keywords":"Latent Dirichlet allocation; Computer science; Feature (linguistics); Source code; Heuristics; Context (archaeology); Java; Artificial intelligence; Topic model; Code (set theory); Measure (data warehouse); Data mining; Natural language processing; Information retrieval; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0249021583454907,"gpt":0.2743756658225636,"spread":0.2494735074770729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005053923,0.0002736067,0.0002118883,0.0002573355,0.00009735407,0.000142456,0.000673337,0.0001727861,0.00002197549],"category_scores_gemma":[0.002307262,0.0002750617,0.00008370567,0.001130686,0.00001770855,0.0007202154,0.0001742096,0.0004503653,0.0001625018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002960885,"about_ca_system_score_gemma":0.00007692727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007759668,"about_ca_topic_score_gemma":3.133222e-7,"domain_scores_codex":[0.9979314,0.0000396586,0.0002351536,0.000390513,0.0005963015,0.0008069666],"domain_scores_gemma":[0.9977708,0.0009816218,0.00004497102,0.0006541631,0.000156033,0.0003924497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007558645,0.0002056426,0.7764213,0.0002812369,0.00005845044,0.00001751643,0.0006431837,0.2078303,0.001196544,0.0007707287,0.006344035,0.006223564],"study_design_scores_gemma":[0.0003851537,0.00004752734,0.826615,0.0001086006,0.00001040649,0.00002264896,0.000002868268,0.141282,0.005751718,0.00001408421,0.02517003,0.0005900068],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05946279,0.0007589292,0.9360986,0.0008566431,0.0007749467,0.0002041057,0.000001443571,0.001826974,0.0000155916],"genre_scores_gemma":[0.9014249,0.000003736944,0.09778346,0.0002189673,0.0003326907,0.00007093789,0.00001698243,0.00004479039,0.0001035071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8419622,"threshold_uncertainty_score":0.9999701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1024906986","doi":"10.1007/s10664-015-9387-3","title":"A contextual approach towards more accurate duplicate bug report detection and ranking","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":90,"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":"Computer science; Data deduplication; Software bug; Android (operating system); Software; Ranking (information retrieval); Context (archaeology); Data science; Software engineering; Data mining; World Wide Web; Information retrieval; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05477320630831465,"gpt":0.3061968965378645,"spread":0.2514236902295499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008912401,0.0003223351,0.0003470919,0.0002500158,0.00009526451,0.0002795768,0.0006283331,0.0001741639,0.000002051962],"category_scores_gemma":[0.005311671,0.0003100477,0.00008355189,0.0008644225,0.00004947561,0.0005899671,0.0005696282,0.0005350605,0.00001697916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002241492,"about_ca_system_score_gemma":0.000120056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147979,"about_ca_topic_score_gemma":7.393114e-7,"domain_scores_codex":[0.9974777,0.00003774341,0.0003906593,0.000756218,0.0007017214,0.000635954],"domain_scores_gemma":[0.9980202,0.0004887518,0.00007024991,0.000699261,0.0001954299,0.0005261325],"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":[0.0002070368,0.0006498655,0.3816082,0.001176672,0.0007486867,0.004422944,0.01739177,0.3535842,0.004590458,0.0007169185,0.006172817,0.2287305],"study_design_scores_gemma":[0.001988021,0.0002583706,0.2692412,0.000104033,0.00002935068,0.003389636,0.00008641437,0.6979429,0.003702894,0.0002270546,0.02147916,0.001551035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2246357,0.0003406931,0.7725818,0.0002193795,0.0003469143,0.0002142841,0.00000143495,0.001632297,0.00002757875],"genre_scores_gemma":[0.9243937,0.000005600996,0.07508279,0.00007607759,0.0001985213,0.0001005238,0.000005834961,0.0000507888,0.0000861686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6997581,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3030475425","doi":"10.1007/s10664-020-09858-z","title":"The who, what, how of software engineering research: a socio-technical framework","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social software engineering; Software peer review; Software development; Empirical research; Beneficiary; Personal software process; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.08362109294565391,"gpt":0.3358897120986377,"spread":0.2522686191529838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001410943,0.0004259422,0.000514979,0.000180246,0.0003012629,0.0009224917,0.002546756,0.0004039641,0.00001167528],"category_scores_gemma":[0.02292538,0.0003561191,0.0002780344,0.001958709,0.0001107717,0.001451276,0.001193343,0.002024962,0.00002162034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001489808,"about_ca_system_score_gemma":0.0001168687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005986829,"about_ca_topic_score_gemma":4.51921e-7,"domain_scores_codex":[0.9964758,0.0001250881,0.0005225668,0.0007314382,0.001127786,0.001017386],"domain_scores_gemma":[0.988381,0.009636621,0.0001386965,0.001089355,0.0002767851,0.0004775634],"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":[0.000394916,0.0009604874,0.07907835,0.005299305,0.001776071,0.001362973,0.02450282,0.2441115,0.00552921,0.1478627,0.2555035,0.2336181],"study_design_scores_gemma":[0.0007955385,0.001333321,0.02281322,0.001899184,0.00007115351,0.0001494604,0.0002515636,0.1782068,0.005851515,0.004000217,0.7819127,0.002715291],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005063983,0.003128952,0.9764602,0.01092059,0.0007459611,0.0003450937,0.000004702694,0.003326115,0.000004379253],"genre_scores_gemma":[0.2583669,0.0006807803,0.739566,0.0004628254,0.0006086036,0.0001483802,0.00000385509,0.000124534,0.00003813852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5264092,"threshold_uncertainty_score":0.9998891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3018447383","doi":"10.1007/s10664-020-09819-6","title":"What do Programmers Discuss about Deep Learning Frameworks","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":89,"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":"Deep learning; Workflow; Computer science; Latent Dirichlet allocation; Leverage (statistics); Artificial intelligence; Topic model; Data science; Profiling (computer programming); World Wide Web; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01947834175930554,"gpt":0.2802885285859658,"spread":0.2608101868266603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003097114,0.0004030707,0.0003838659,0.0001546166,0.0001489394,0.001191498,0.001438423,0.000371329,0.00005509244],"category_scores_gemma":[0.006076903,0.0003808857,0.000197726,0.001592921,0.00004358851,0.001342746,0.0007361078,0.002270015,0.0002126407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001420194,"about_ca_system_score_gemma":0.00005166825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003252846,"about_ca_topic_score_gemma":2.797342e-7,"domain_scores_codex":[0.9968327,0.00005957509,0.0003779858,0.000868712,0.0008137688,0.001047253],"domain_scores_gemma":[0.9970175,0.00146406,0.00005607163,0.000557393,0.0001044448,0.0008005175],"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":[0.0000168306,0.00009720041,0.2440224,0.0003409267,0.0001515029,0.0003239774,0.007526493,0.4202347,0.0001280132,0.0003455917,0.001004272,0.325808],"study_design_scores_gemma":[0.001035619,0.0005742093,0.1271799,0.0006406055,0.00002869936,0.00006321001,0.0003089856,0.6802323,0.0007307198,0.0001704032,0.1867456,0.002289705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03251577,0.002891416,0.9568699,0.002685108,0.0009356673,0.0002666907,5.913986e-7,0.003827915,0.000006925092],"genre_scores_gemma":[0.8374745,0.0002291761,0.1605902,0.0007705453,0.0006138339,0.000122275,0.000009727327,0.0001315569,0.00005828019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8049586,"threshold_uncertainty_score":0.9998643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109942136","doi":"10.1007/s10664-008-9104-6","title":"A study of the non-linear adjustment for analogy based software cost estimation","year":2009,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Saskatchewan; University of Wisconsin-Madison","keywords":"Categorical variable; Analogy; Flexibility (engineering); Computer science; Software; Estimation; Artificial intelligence; Artificial neural network; Machine learning; Data mining; Statistics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0355013702707655,"gpt":0.320520460559485,"spread":0.2850190902887195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003776216,0.0002629807,0.0003335389,0.0002144845,0.0001100883,0.00004509681,0.001129702,0.0001076663,0.000004539816],"category_scores_gemma":[0.003808394,0.0002128364,0.0001558816,0.001038125,0.00001968137,0.0001969825,0.0001778394,0.0002906972,0.000005726821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001889138,"about_ca_system_score_gemma":0.000123359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001073517,"about_ca_topic_score_gemma":0.00000225417,"domain_scores_codex":[0.9979618,0.00004057123,0.0004156548,0.0004724407,0.0006003602,0.0005092159],"domain_scores_gemma":[0.9970002,0.001678965,0.00008733684,0.0008949732,0.0001825129,0.000156068],"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":[0.00001454208,0.0004730894,0.04563655,0.00007657426,0.00003597715,0.000007928908,0.0005080796,0.9369976,0.00008286043,0.00003774022,0.0007461756,0.01538287],"study_design_scores_gemma":[0.001141066,0.0006397379,0.437632,0.0000661989,0.00001847554,0.00000583159,0.000009491065,0.5587952,0.0009404534,0.00005366564,0.0004372114,0.0002606971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1756916,0.00004955016,0.8220226,0.0002367208,0.0003960722,0.001117723,0.00000639362,0.0004784297,0.00000100611],"genre_scores_gemma":[0.7837989,5.569163e-7,0.2157491,0.0001528352,0.00008356891,0.0001680569,0.00000549322,0.00002555967,0.00001589785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6081073,"threshold_uncertainty_score":0.8679218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2788314565","doi":"10.1007/s10664-018-9601-1","title":"App store mining is not enough for app improvement","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures","keywords":"App store; Computer science; Mobile apps; Smartphone app; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02549139422760458,"gpt":0.2673284083448976,"spread":0.241837014117293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002025678,0.0001680099,0.0001539665,0.00008028747,0.0001561207,0.0001281513,0.0004332547,0.00009730754,0.00001727217],"category_scores_gemma":[0.0002695507,0.0001654103,0.00009136083,0.0002884888,0.00001697276,0.0002639825,0.0001482353,0.000119087,0.00003672165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009785647,"about_ca_system_score_gemma":0.00002820875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001223596,"about_ca_topic_score_gemma":0.000001588617,"domain_scores_codex":[0.9987914,0.000006578483,0.00019612,0.0004053984,0.0002277199,0.0003728042],"domain_scores_gemma":[0.9991916,0.0002089946,0.00004565119,0.0003507295,0.00008125326,0.0001217793],"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":[0.0001310518,0.0003352782,0.01267989,0.0006119062,0.000342052,0.00002800393,0.02752668,0.005494665,0.02379232,0.001998923,0.1224897,0.8045695],"study_design_scores_gemma":[0.00103528,0.001316466,0.01022745,0.0001036304,0.00002589156,0.00001796729,0.00003143495,0.2745195,0.08418881,0.000349186,0.6272004,0.0009840395],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08635495,0.00004617598,0.910548,0.0005946341,0.001387161,0.0001704359,0.00000454143,0.0008697935,0.00002431784],"genre_scores_gemma":[0.7604935,0.000001456055,0.2367647,0.001262234,0.001113167,0.00007261984,0.000003024299,0.00003094546,0.0002584015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8035855,"threshold_uncertainty_score":0.6745236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981075560","doi":"10.1007/s10664-013-9274-8","title":"Studying the relationship between logging characteristics and the code quality of platform software","year":2013,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":83,"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; Software; Product metric; Process (computing); Relation (database); Source lines of code; Logging; Software quality; Code (set theory); Database; Quality (philosophy); Product (mathematics); Software development; Software engineering; Data mining; Operating system; Programming language; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.1071977212306796,"gpt":0.3313187722431654,"spread":0.2241210510124858,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001760415,0.0002551509,0.000431335,0.000126466,0.0002871379,0.0002491497,0.001142045,0.0001209084,0.000008937021],"category_scores_gemma":[0.02213654,0.0001609962,0.0001126971,0.0006061771,0.0001767715,0.0004763021,0.0007079215,0.0007497124,0.00002399946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008526451,"about_ca_system_score_gemma":0.00005096534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007780483,"about_ca_topic_score_gemma":0.000001181626,"domain_scores_codex":[0.9977289,0.0001204937,0.0006336099,0.0003722481,0.0006386825,0.0005060426],"domain_scores_gemma":[0.9680029,0.03073505,0.0001476888,0.0008201418,0.0001370685,0.0001571403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003514599,0.00001028615,0.9943889,0.0001062041,0.00003620528,0.000001243224,0.000999135,0.0006699344,0.000007713138,0.0009250654,0.0001330895,0.002718645],"study_design_scores_gemma":[0.0004365158,0.00002056346,0.9929479,0.0000580676,0.00001033907,0.000005931409,0.00002612812,0.005069331,0.00002945671,0.0009366482,0.0002561125,0.0002029697],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5031146,0.0001649547,0.4953339,0.000576482,0.0001318501,0.0003022061,0.000005694165,0.0003681398,0.00000209906],"genre_scores_gemma":[0.9742926,0.000006002819,0.02530414,0.0000858357,0.0001458638,0.000094034,0.000004935533,0.0000323484,0.00003421149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.471178,"threshold_uncertainty_score":0.9861004,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2920526824","doi":"10.1007/s10664-019-09695-9","title":"An empirical study of the long duration of continuous integration builds","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":82,"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":"Duration (music); Computer science; Set (abstract data type); Empirical research; Software development; Cache; Software; Software engineering; Process management; Engineering; Statistics; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01694477932419394,"gpt":0.2973705753052279,"spread":0.280425795981034,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004725772,0.0001942511,0.0003262995,0.0001803148,0.00003991037,0.00005668537,0.001116576,0.0001132402,0.00001514307],"category_scores_gemma":[0.001536262,0.0001474092,0.0000979603,0.001048696,0.00002426989,0.0004284882,0.0002677703,0.0003617307,0.000009487519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009197221,"about_ca_system_score_gemma":0.00006817066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003744035,"about_ca_topic_score_gemma":0.000006948583,"domain_scores_codex":[0.9979908,0.00009961973,0.0005054274,0.0003893855,0.0007200167,0.000294764],"domain_scores_gemma":[0.9977026,0.0008527294,0.0001189817,0.001013509,0.0002091985,0.0001029907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006631778,0.0002795185,0.9615797,0.00004176248,0.00002366179,0.000003088157,0.001571316,0.03270349,0.002013381,0.00003172963,0.00006666603,0.001679079],"study_design_scores_gemma":[0.0004034713,0.0005050916,0.9385241,0.00005527132,0.000007447658,0.000007128902,0.00005644591,0.05427423,0.005923209,0.00001590691,0.00005983316,0.0001678586],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6099686,0.00002438615,0.3891019,0.00004963697,0.0003219886,0.0003246614,0.000001065559,0.00020485,0.000002899779],"genre_scores_gemma":[0.9910079,7.491404e-7,0.008839797,0.00002245738,0.00005046264,0.00002193018,0.00000222915,0.00002494539,0.00002957281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3810393,"threshold_uncertainty_score":0.6011171,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2738381526","doi":"10.1007/s10664-017-9533-1","title":"EnTagRec ++: An enhanced tag recommendation system for software information sites","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":81,"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":"Ask price; Computer science; Set (abstract data type); Software; Recall; Precision and recall; Information retrieval; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03528399466237,"gpt":0.3128422166076763,"spread":0.2775582219453063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006107065,0.0003138679,0.000311209,0.0002606985,0.0005628496,0.001095116,0.001623893,0.0001894706,0.00001638814],"category_scores_gemma":[0.006969332,0.0003258282,0.0001290255,0.0002216891,0.00002640965,0.004242302,0.0004144287,0.000303878,0.00008907227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003902942,"about_ca_system_score_gemma":0.00007887465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000210875,"about_ca_topic_score_gemma":0.000003072866,"domain_scores_codex":[0.9979745,0.00002903363,0.0004497951,0.0004760013,0.0004150785,0.0006556055],"domain_scores_gemma":[0.9969214,0.001081145,0.0001858584,0.001215704,0.0002780613,0.000317865],"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":[0.0001588865,0.0003991884,0.2749084,0.00383459,0.0003985956,0.00003780098,0.006033997,0.08503956,0.003614248,0.002993571,0.01139371,0.6111874],"study_design_scores_gemma":[0.003682793,0.0008931155,0.404102,0.0005587573,0.00004929203,0.00007787126,0.0001203898,0.4874371,0.03489672,0.0002987734,0.06505004,0.002833189],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08327109,0.00002071839,0.9123433,0.0002486821,0.001167247,0.0004753705,0.00002963524,0.002427513,0.00001649091],"genre_scores_gemma":[0.7310809,0.000003027509,0.2681233,0.0000694862,0.0002849614,0.000232725,0.0001317338,0.0000407226,0.0000330596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6478099,"threshold_uncertainty_score":0.9999418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2534933448","doi":"10.1007/s10664-016-9467-z","title":"Towards just-in-time suggestions for log changes","year":2016,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Queen's University","funders":"","keywords":"Commit; Computer science; Logging; Random forest; Set (abstract data type); Directory; Source code; Process (computing); Machine learning; Data mining; Data science; Database; Artificial intelligence; Programming language; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02384869600911503,"gpt":0.2737739051977656,"spread":0.2499252091886506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004092136,0.0001831552,0.0002484676,0.0001470214,0.00006190284,0.00004870311,0.0006153766,0.0001372052,0.00002199065],"category_scores_gemma":[0.0009549549,0.0001234875,0.00009225601,0.000392436,0.00002357982,0.0002777162,0.0001703143,0.00009867903,0.0001068823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001659008,"about_ca_system_score_gemma":0.00005990014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007614709,"about_ca_topic_score_gemma":0.000004301397,"domain_scores_codex":[0.9986228,0.00001913229,0.0002426679,0.0004073064,0.0002375854,0.0004705243],"domain_scores_gemma":[0.9986909,0.0006152492,0.00003674742,0.0004479264,0.00007240068,0.0001367755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000664752,0.0005713535,0.6466935,0.00100794,0.0001300009,0.00006771218,0.002483106,0.006869541,0.003266241,0.00228073,0.02594171,0.3106216],"study_design_scores_gemma":[0.00443765,0.0009126471,0.7040953,0.00135557,0.0000389395,0.00009052242,0.00001807307,0.04874685,0.009568935,0.002462514,0.2256741,0.002598902],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09583456,0.0001186871,0.8990081,0.003177446,0.0006659028,0.0003018029,0.00001164884,0.0008658486,0.0000159769],"genre_scores_gemma":[0.8765904,0.00002894694,0.1214589,0.0003847333,0.0005944898,0.0003634685,0.000005025533,0.00004372674,0.0005302912],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7807559,"threshold_uncertainty_score":0.5035675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969265968","doi":"10.1007/s10664-007-9054-4","title":"Analysis of attribute weighting heuristics for analogy-based software effort estimation method AQUA+","year":2007,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":77,"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":"Weighting; Heuristics; Data mining; Set (abstract data type); Computer science; Selection (genetic algorithm); Estimation; Exploit; A-weighting; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02959484286795332,"gpt":0.3421866429248011,"spread":0.3125918000568478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00232258,0.0003646889,0.0007332424,0.001393957,0.0001277949,0.00008787278,0.0009557701,0.0002442323,0.0000116319],"category_scores_gemma":[0.01110233,0.0003811111,0.0004580075,0.004172049,0.00003451433,0.0002578403,0.0002147508,0.0003749988,0.000005772122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002811164,"about_ca_system_score_gemma":0.0001279791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002005117,"about_ca_topic_score_gemma":0.000004909168,"domain_scores_codex":[0.9967753,0.00003512186,0.0008217567,0.0006957007,0.0007634934,0.0009086732],"domain_scores_gemma":[0.9879202,0.01033996,0.0001837069,0.0008329268,0.000398131,0.0003251389],"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":[0.00001255288,0.00005842688,0.2894761,0.0001957853,0.0003577727,0.00001816565,0.0001111231,0.7004454,0.0001163928,0.0001522931,0.0001534976,0.008902516],"study_design_scores_gemma":[0.0003617592,0.0001028426,0.2225802,0.00004785302,0.0001984567,0.000003994927,0.000002389844,0.7718169,0.003638672,0.00005998847,0.0008268434,0.0003600714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0549912,0.0001324139,0.9429393,0.0000735409,0.000337263,0.000329161,0.00004135465,0.001154139,0.000001572567],"genre_scores_gemma":[0.3023765,9.497716e-7,0.6973307,0.00005554195,0.00007078233,0.00003322344,0.00007889773,0.00004126346,0.00001208712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2473853,"threshold_uncertainty_score":0.9998641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3004570974","doi":"10.1007/s10664-019-09781-y","title":"How bugs are born: a model to identify how bugs are introduced in software components","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; University of Waterloo","funders":"H2020 Industrial Leadership; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Software bug; Software regression; Computer science; False positive paradox; Source lines of code; Software; Source code; Open source; Debugging; Software maintenance; Snapshot (computer storage); Code (set theory); Security bug; Data mining; Software development; Software quality; Programming language; Machine learning; Database; Operating system; Set (abstract data type); Software security assurance","retraction":null,"screen_n_in":null,"score":{"opus":0.06211628819800336,"gpt":0.2983208692382943,"spread":0.236204581040291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004371005,0.0007660761,0.0009336406,0.0006431398,0.0001411237,0.001011271,0.00266517,0.0003325434,0.000006869691],"category_scores_gemma":[0.01351179,0.0008349529,0.0002562053,0.002949003,0.00004051797,0.001148119,0.001698711,0.001367245,0.0001215157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005524658,"about_ca_system_score_gemma":0.0001221987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001697437,"about_ca_topic_score_gemma":0.000006936054,"domain_scores_codex":[0.9945916,0.00008934327,0.0005273791,0.001720893,0.001480073,0.001590737],"domain_scores_gemma":[0.9959326,0.001106275,0.0001425287,0.001270889,0.0002742854,0.001273462],"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":[0.00007407378,0.0002925231,0.3655783,0.0009722452,0.000155677,0.00104817,0.003595165,0.5887282,0.006323423,0.0000426643,0.0272344,0.00595525],"study_design_scores_gemma":[0.001400013,0.0001786758,0.5782471,0.0004889591,0.00001741664,0.00003571749,0.00007240051,0.4085321,0.002270009,0.0000810058,0.00687061,0.001805981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3051757,0.000235626,0.6740202,0.01735092,0.0004331913,0.000482423,0.00002905687,0.002272167,8.021084e-7],"genre_scores_gemma":[0.8617076,0.000008995316,0.1361791,0.001197873,0.0004453474,0.0001807591,0.00001866925,0.0001542697,0.0001073748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5565319,"threshold_uncertainty_score":0.9994102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}