{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Anton Barua","is_ca":true},{"name":"Stephen W. Thomas","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.003743622,0.0002208513,0.0002537383,0.008621708,0.001108391,0.002134667,0.0005184539,0.0007278773,0.001172877],"category_scores_gemma":[0.0415329,0.0003245859,0.0002920487,0.008282863,0.0008052008,0.004389322,0.001333264,0.00109744,0.0002735356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001606732,"about_ca_system_score_gemma":0.002409521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009625689,"about_ca_topic_score_gemma":0.01325964,"domain_scores_codex":[0.9971895,0.0008733026,0.0003495735,0.0003361222,0.000933444,0.0003180685],"domain_scores_gemma":[0.9128747,0.05638798,0.01573795,0.001174787,0.0107283,0.003096273],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003237839,0.0001300269,0.8414324,0.0004008762,0.00005525841,0.0004096781,0.06532566,0.0002245986,0.003242983,0.001455506,0.002676999,0.08432224],"study_design_scores_gemma":[0.00001104225,0.0001061596,0.9496954,0.0002150056,0.00007424177,0.0004698056,0.03900119,0.001376371,0.001168107,0.000705514,0.007146041,0.00003119017],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995082,0.0009148988,0.000580288,0.0008720514,0.00001657954,0.00001798398,0.0004552006,0.00003546379,0.002025537],"genre_scores_gemma":[0.9957578,0.001210555,0.001022472,0.0001719724,0.00007407573,0.00003332168,0.0008562059,0.00005220499,0.000821484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9962564,"threshold_uncertainty_score":0.0197984,"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","authors":[{"name":"Timothy C. Lethbridge","is_ca":true},{"name":"Susan Elliott Sim","is_ca":false},{"name":"Janice Singer","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04516862,0.002017278,0.002443867,0.0230501,0.003368275,0.003143301,0.003178183,0.001830939,0.006484781],"category_scores_gemma":[0.1973267,0.001381583,0.001861835,0.02267465,0.002129896,0.004202681,0.004220237,0.003355481,0.003877834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002664489,"about_ca_system_score_gemma":0.007651343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004315421,"about_ca_topic_score_gemma":0.006830576,"domain_scores_codex":[0.9390138,0.03005608,0.0122241,0.004485982,0.01254618,0.001673969],"domain_scores_gemma":[0.6642607,0.1935533,0.01935323,0.04939711,0.06974211,0.003693576],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001150881,0.00425472,0.1341568,0.008167575,0.0003675188,0.0004672872,0.02112395,0.003741004,0.01989563,0.01786618,0.06240759,0.7264008],"study_design_scores_gemma":[0.002050253,0.004395655,0.4272557,0.004208195,0.001552314,0.001077604,0.04573526,0.03036018,0.08405102,0.05901596,0.3393857,0.0009121765],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.141126,0.001498775,0.6978443,0.001499437,0.0003938586,0.08746344,0.04623595,0.003067297,0.02087083],"genre_scores_gemma":[0.1300793,0.00124823,0.6530349,0.0007559146,0.0002620172,0.1863822,0.023061,0.0006456068,0.004530814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9548314,"threshold_uncertainty_score":0.2388774,"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","authors":[{"name":"Foutse Khomh","is_ca":true},{"name":"Massimiliano Di Penta","is_ca":false},{"name":"Yann‐Gaël Guéhéneuc","is_ca":true},{"name":"Giuliano Antoniol","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00513228,0.0003351865,0.0002938944,0.0008750966,0.0005571765,0.0007952459,0.001108225,0.000743105,0.004539121],"category_scores_gemma":[0.0632035,0.0002767399,0.0005090167,0.001090895,0.0009453421,0.001544321,0.0008688805,0.001416259,0.0004109067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005745796,"about_ca_system_score_gemma":0.00080931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002293995,"about_ca_topic_score_gemma":0.003459563,"domain_scores_codex":[0.9959962,0.002564714,0.0001871258,0.0004160717,0.000590083,0.0002457783],"domain_scores_gemma":[0.692534,0.2725572,0.0200635,0.007399546,0.003953846,0.003491831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003505899,0.007942014,0.952508,0.0001244649,0.0003368397,0.0003836619,0.002837749,0.001829351,0.00545247,0.0009466428,0.0003715011,0.02376125],"study_design_scores_gemma":[0.0001354891,0.004281832,0.9864547,0.00001087479,0.0001302777,0.0001904713,0.001618015,0.004502993,0.001746507,0.0004994943,0.0004092376,0.0000200329],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9993175,0.00001251784,0.0002176416,0.00002515864,0.00000105606,0.00001313998,0.00008861933,0.000006691472,0.0003176451],"genre_scores_gemma":[0.9992266,0.000009990315,0.0003808255,0.00001395565,0.000002872399,0.00002380534,0.0000962269,0.00000447281,0.0002413623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00513228,"threshold_uncertainty_score":0.02714241,"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","authors":[{"name":"Cory Kapser","is_ca":true},{"name":"Michael W. Godfrey","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01225782,0.0003027364,0.000542597,0.003719789,0.00434082,0.004028709,0.001375041,0.002384484,0.003393452],"category_scores_gemma":[0.1295866,0.0004991386,0.0005137589,0.00789833,0.009417824,0.008244663,0.005129136,0.003829415,0.0003049181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001987997,"about_ca_system_score_gemma":0.003426615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005115161,"about_ca_topic_score_gemma":0.006250781,"domain_scores_codex":[0.9821985,0.009560371,0.001734217,0.001424484,0.003694473,0.001387967],"domain_scores_gemma":[0.7696085,0.1448309,0.04181017,0.02927056,0.0110505,0.003429307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007364828,0.0002218251,0.5626897,0.0005991604,0.0002431193,0.0007302896,0.1143361,0.001537587,0.005640766,0.2088166,0.005436368,0.09901208],"study_design_scores_gemma":[0.00008643669,0.0003346325,0.4884825,0.0008965287,0.000427115,0.004453923,0.1048057,0.008696132,0.007789778,0.3499233,0.03386217,0.0002418097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9471351,0.000611618,0.02840479,0.004382325,0.00005076014,0.00006767215,0.0002378686,0.0001614884,0.01894835],"genre_scores_gemma":[0.9948925,0.00008558745,0.004060058,0.0003064966,0.00001692208,0.00002073256,0.00008091426,0.00004895525,0.0004877856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01225782,"threshold_uncertainty_score":0.06482631,"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","authors":[{"name":"Martin P. Robillard","is_ca":true},{"name":"Robert DeLine","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003584597,0.0003962891,0.0003824444,0.002459405,0.002813437,0.001486426,0.001511501,0.001124988,0.007130457],"category_scores_gemma":[0.02690458,0.0004775941,0.0002909542,0.001810293,0.001635927,0.002756436,0.001628241,0.002297278,0.000967709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710871,"about_ca_system_score_gemma":0.003065803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006725766,"about_ca_topic_score_gemma":0.008847254,"domain_scores_codex":[0.9978828,0.0009200315,0.0001241086,0.0003202459,0.0004927359,0.0002601002],"domain_scores_gemma":[0.9486915,0.03441855,0.002916923,0.003033663,0.007387905,0.003551503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00615818,0.1196572,0.369503,0.00120444,0.00009226475,0.002900654,0.1345138,0.003056696,0.01808162,0.02563718,0.01644754,0.3027473],"study_design_scores_gemma":[0.001257576,0.03595973,0.53708,0.0008470285,0.0002208738,0.002551469,0.30098,0.01833008,0.02386355,0.02203592,0.05656299,0.0003107648],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914458,0.00006505309,0.001701812,0.0001856038,0.00001502878,0.000201397,0.000104598,0.00003871158,0.006242027],"genre_scores_gemma":[0.9928038,0.0001134372,0.001679601,0.0001119844,0.00001238104,0.0001848774,0.000179196,0.00001807419,0.004896523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007130457,"threshold_uncertainty_score":0.02385372,"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","authors":[{"name":"Nuthan Munaiah","is_ca":false},{"name":"Steven Kroh","is_ca":false},{"name":"Craig Cabrey","is_ca":false},{"name":"Meiyappan Nagappan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005722354,0.001572351,0.0007534124,0.006204288,0.00193514,0.003147876,0.001891491,0.001330189,0.01171539],"category_scores_gemma":[0.05672424,0.0009064901,0.001566149,0.00276721,0.001008918,0.004165006,0.008731061,0.002056815,0.008287753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009637127,"about_ca_system_score_gemma":0.004522694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004172427,"about_ca_topic_score_gemma":0.01070553,"domain_scores_codex":[0.99224,0.002226207,0.0004216188,0.0009854302,0.003583757,0.0005430517],"domain_scores_gemma":[0.9681357,0.00811609,0.002003833,0.01348971,0.007088271,0.001166333],"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":[0.0006327671,0.0004604532,0.02030483,0.002400512,0.0002289062,0.002096733,0.005882422,0.005422005,0.03039898,0.02430057,0.182771,0.7251008],"study_design_scores_gemma":[0.000294969,0.0008783297,0.0322842,0.002256264,0.0005327007,0.003878438,0.005613033,0.1172522,0.08057525,0.08575327,0.6703022,0.0003792718],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1867958,0.00200665,0.5090892,0.003538195,0.001292021,0.001622779,0.009279256,0.2114196,0.07495655],"genre_scores_gemma":[0.2968762,0.001337425,0.589691,0.0008908056,0.0002209033,0.00085102,0.02386589,0.04813353,0.03813322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01171539,"threshold_uncertainty_score":0.03919184,"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","authors":[{"name":"Raula Gaikovina Kula","is_ca":false},{"name":"Daniel M. Germán","is_ca":true},{"name":"Ali Ouni","is_ca":false},{"name":"Takashi Ishio","is_ca":false},{"name":"Katsuro Inoue","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01038443,0.0004406657,0.0004082184,0.00374617,0.001320141,0.003599494,0.00163209,0.001904035,0.009912373],"category_scores_gemma":[0.2199706,0.0008969265,0.0003243153,0.00333429,0.001441348,0.009339746,0.001756128,0.002261292,0.002301545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00195843,"about_ca_system_score_gemma":0.003806575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01499959,"about_ca_topic_score_gemma":0.02827103,"domain_scores_codex":[0.9903328,0.002700974,0.0008634981,0.001204435,0.003983513,0.0009148067],"domain_scores_gemma":[0.6781005,0.1724916,0.07423481,0.03442839,0.0341231,0.006621558],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000289125,0.0004865327,0.8194011,0.0002158011,0.0001198435,0.0005933955,0.01137481,0.0005739231,0.001467936,0.005317968,0.01348078,0.1466789],"study_design_scores_gemma":[0.0001055522,0.0002601961,0.9167011,0.0004244061,0.0003495912,0.001663816,0.01642724,0.004835694,0.005213784,0.01223861,0.04166189,0.0001180459],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9548504,0.0007505639,0.005463851,0.005922866,0.0001151069,0.00006150495,0.001221592,0.0006858766,0.03092828],"genre_scores_gemma":[0.9886616,0.0003663168,0.002199165,0.0008819746,0.00005306782,0.00003228203,0.0006989458,0.0003302772,0.006776399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9896156,"threshold_uncertainty_score":0.05491877,"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","authors":[{"name":"Shane McIntosh","is_ca":true},{"name":"Yasutaka Kamei","is_ca":false},{"name":"Bram Adams","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01467052,0.0002526799,0.0002813511,0.003119311,0.0009291299,0.001873881,0.001062618,0.0009039212,0.001907798],"category_scores_gemma":[0.171371,0.0003713771,0.0004334131,0.003248774,0.001755534,0.002449424,0.001432291,0.001861462,0.0002026864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003458273,"about_ca_system_score_gemma":0.004257764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007591993,"about_ca_topic_score_gemma":0.01393116,"domain_scores_codex":[0.9840423,0.007693855,0.00114514,0.001125223,0.005061395,0.0009320385],"domain_scores_gemma":[0.4236476,0.4192705,0.1010286,0.01388963,0.03242593,0.009737784],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001368923,0.006450636,0.8537005,0.0005993317,0.0003711723,0.0002747418,0.005974135,0.002233168,0.003764087,0.001895181,0.001107091,0.1222611],"study_design_scores_gemma":[0.0001277591,0.003140408,0.9865919,0.0001501792,0.0001775923,0.0002183674,0.003483771,0.002770132,0.001310485,0.0005239119,0.001471242,0.00003427612],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981111,0.0003335443,0.0002890405,0.0001890469,0.000006397271,0.00002570278,0.00003518358,0.00001271137,0.0009971929],"genre_scores_gemma":[0.9990807,0.00013081,0.0004769174,0.00004606325,0.00001480144,0.00001453326,0.00003727883,0.000005180846,0.0001938165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9853295,"threshold_uncertainty_score":0.07758605,"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","authors":[{"name":"Christoffer Rosen","is_ca":false},{"name":"Emad Shihab","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005751692,0.0004887506,0.0004382991,0.002525331,0.003141792,0.002442545,0.0008518639,0.001663472,0.001894284],"category_scores_gemma":[0.05263684,0.0007215972,0.0002750181,0.002191047,0.001485167,0.004181307,0.002157345,0.002351156,0.0005235501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001890045,"about_ca_system_score_gemma":0.003394705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01676683,"about_ca_topic_score_gemma":0.04064523,"domain_scores_codex":[0.9968951,0.001451067,0.0002426888,0.0003550908,0.0006447904,0.0004112388],"domain_scores_gemma":[0.907984,0.06840722,0.01057587,0.002007544,0.006842412,0.00418298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002817505,0.002161656,0.7029215,0.0002576953,0.00006389122,0.001183259,0.2563147,0.0001113335,0.001772785,0.0007381536,0.002113847,0.03207939],"study_design_scores_gemma":[0.0001156879,0.0009109539,0.6762496,0.0003248202,0.0001161987,0.0006376585,0.3124281,0.0008770539,0.00109338,0.0005268846,0.006644589,0.00007508994],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988866,0.00004934704,0.00016807,0.0001833474,0.000004059008,0.00003792654,0.00005055216,0.000007002263,0.0006130934],"genre_scores_gemma":[0.9979048,0.0001626871,0.0005234713,0.000290651,0.0000131345,0.0001205092,0.000117254,0.00001886342,0.0008487525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01676683,"threshold_uncertainty_score":0.03333849,"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","authors":[{"name":"Stefan Wagner","is_ca":false},{"name":"Marcos Kalinowski","is_ca":false},{"name":"Michael Felderer","is_ca":false},{"name":"Priscilla Mafra","is_ca":false},{"name":"Antonio Vetrò","is_ca":false},{"name":"Tayana Conte","is_ca":false},{"name":"Marie-Therese Christiansson","is_ca":false},{"name":"Des Greer","is_ca":false},{"name":"Casper Lassenius","is_ca":false},{"name":"Tomi Männistö","is_ca":false},{"name":"M. Nayabi","is_ca":true},{"name":"Markku Oivo","is_ca":false},{"name":"Birgit Penzenstadler","is_ca":false},{"name":"Dietmar Pfahl","is_ca":false},{"name":"Rafael Prikladnicki","is_ca":false},{"name":"Guenther Ruhe","is_ca":true},{"name":"André Schekelmann","is_ca":false},{"name":"Sagar Sen","is_ca":false},{"name":"Rodrigo Spínola","is_ca":false},{"name":"Ahmed Tuzcu","is_ca":false},{"name":"José Luis de la Vara","is_ca":false},{"name":"Roel Wieringa","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03841539,0.0008819414,0.001262086,0.004851465,0.005132345,0.01088028,0.002486723,0.007969784,0.006196741],"category_scores_gemma":[0.1693643,0.0009413918,0.0005937642,0.005785988,0.05780578,0.03677944,0.006046708,0.01646021,0.001087661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004631608,"about_ca_system_score_gemma":0.004099431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052314,"about_ca_topic_score_gemma":0.00369195,"domain_scores_codex":[0.9438267,0.04521998,0.001686322,0.00186684,0.006225938,0.001174305],"domain_scores_gemma":[0.8050637,0.1648976,0.005308763,0.01120734,0.01122711,0.002295526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004268987,0.00003837059,0.0006624222,0.0002733029,0.00001348222,0.00007325925,0.008230126,0.0003880611,0.0003542585,0.9429311,0.01286209,0.03413098],"study_design_scores_gemma":[0.00003850929,0.00005887516,0.0009682866,0.0009907824,0.00001215465,0.0001387392,0.008025545,0.001163875,0.000403068,0.9276366,0.06051602,0.00004744482],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03641379,0.06810619,0.2503721,0.5120013,0.007921651,0.0001285083,0.0001517098,0.0004760727,0.1244288],"genre_scores_gemma":[0.8425066,0.01620349,0.07303412,0.04517174,0.006231092,0.0003400204,0.00008938541,0.0005846693,0.01583881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03841539,"threshold_uncertainty_score":0.2031624,"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)","authors":[{"name":"Eirini Kalliamvakou","is_ca":true},{"name":"Georgios Gousios","is_ca":false},{"name":"Kelly Blincoe","is_ca":true},{"name":"Leif Singer","is_ca":true},{"name":"Daniel M. Germán","is_ca":true},{"name":"Daniela Damian","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01439842,0.0003185126,0.0003713782,0.004433096,0.001505956,0.004565232,0.001379542,0.000858712,0.002294648],"category_scores_gemma":[0.1082374,0.0003601127,0.0003552323,0.008001745,0.002345739,0.01075979,0.001893437,0.001993944,0.0005213564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001897886,"about_ca_system_score_gemma":0.003857247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005744674,"about_ca_topic_score_gemma":0.018905,"domain_scores_codex":[0.9907132,0.005087964,0.0004583147,0.000490708,0.002865508,0.0003842478],"domain_scores_gemma":[0.8384849,0.1324434,0.008217656,0.009278706,0.009914197,0.001661186],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004784421,0.0006416168,0.2763022,0.002356691,0.00016052,0.0003207156,0.01696852,0.0042813,0.006003243,0.1194428,0.01344375,0.5596002],"study_design_scores_gemma":[0.00006988324,0.0007331321,0.46165,0.002946607,0.0002040488,0.001745457,0.07258553,0.0752271,0.01762821,0.2001055,0.1668907,0.00021411],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8565797,0.01586723,0.06180893,0.0270745,0.0001293646,0.0002915966,0.00198889,0.0002292863,0.03603052],"genre_scores_gemma":[0.9450833,0.00616323,0.04204987,0.001138075,0.0001827671,0.00007881095,0.001629256,0.0001131395,0.003561654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9856016,"threshold_uncertainty_score":0.07614708,"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","authors":[{"name":"Gustavo A. Oliva","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Zhen Ming Jiang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004057957,0.000191858,0.0002377502,0.0008804653,0.002313778,0.001631824,0.0008919979,0.00133138,0.007134326],"category_scores_gemma":[0.01826748,0.0002224486,0.0001258647,0.001624461,0.002289715,0.004655004,0.001540982,0.001705637,0.0005131551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001529233,"about_ca_system_score_gemma":0.001699234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004735863,"about_ca_topic_score_gemma":0.007162603,"domain_scores_codex":[0.9984185,0.0009441423,0.00004543208,0.0001219289,0.0002675327,0.0002024405],"domain_scores_gemma":[0.9721112,0.02312806,0.001624489,0.001053752,0.001024957,0.00105755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001986437,0.01337485,0.2952824,0.0006012956,0.00008605357,0.007224159,0.1520494,0.0149238,0.0108701,0.3913857,0.004479656,0.1077361],"study_design_scores_gemma":[0.0004071801,0.00430611,0.3036345,0.0005129401,0.00006493028,0.001734766,0.4000461,0.1175419,0.009334632,0.1193317,0.04293037,0.0001547553],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932293,0.00003334677,0.001037169,0.000199928,0.00000202559,0.00005533732,0.00004351441,0.000004788017,0.005394596],"genre_scores_gemma":[0.9975224,0.00003799384,0.0006480396,0.00002597531,0.00000228914,0.00002519528,0.00005363338,0.000004264914,0.001680135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007134326,"threshold_uncertainty_score":0.02386665,"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","authors":[{"name":"Steve Adolph","is_ca":true},{"name":"Wendy A. Hall","is_ca":true},{"name":"Philippe Kruchten","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0151673,0.0004794311,0.000485973,0.003185132,0.003806886,0.007022231,0.001893999,0.001690816,0.001746814],"category_scores_gemma":[0.045189,0.0004927095,0.0003644669,0.00306313,0.01346838,0.008110503,0.005466181,0.004098061,0.0001739036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006744926,"about_ca_system_score_gemma":0.006614895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006005622,"about_ca_topic_score_gemma":0.007505002,"domain_scores_codex":[0.9752279,0.0203968,0.0004420292,0.0005796641,0.002536635,0.0008170716],"domain_scores_gemma":[0.9000506,0.09212893,0.001695642,0.002158588,0.002551999,0.001414269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00007100894,0.00031517,0.007129055,0.00043291,0.00003319697,0.0003764475,0.8756862,0.0008607789,0.0009625224,0.07796057,0.0008139543,0.03535817],"study_design_scores_gemma":[0.0000846797,0.0002893808,0.007515091,0.001112166,0.00003689946,0.0004272148,0.8664188,0.003772938,0.001621001,0.09536196,0.02329783,0.0000619143],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8772358,0.001457956,0.06286541,0.005354784,0.0001077702,0.000532,0.0001304849,0.00005358151,0.05226208],"genre_scores_gemma":[0.9880185,0.0004715442,0.009718059,0.0003458486,0.000007053884,0.000180211,0.00005571199,0.00002244058,0.001180539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0151673,"threshold_uncertainty_score":0.08021331,"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","authors":[{"name":"Paul Ralph","is_ca":true},{"name":"Sebastian Baltes","is_ca":false},{"name":"Gianisa Adisaputri","is_ca":true},{"name":"Richard Torkar","is_ca":false},{"name":"Vladimir Kovalenko","is_ca":false},{"name":"Marcos Kalinowski","is_ca":false},{"name":"Nicole Novielli","is_ca":false},{"name":"Shin Yoo","is_ca":false},{"name":"Xavier Devroey","is_ca":false},{"name":"Xin Tan","is_ca":false},{"name":"Minghui Zhou","is_ca":false},{"name":"Burak Turhan","is_ca":false},{"name":"Rashina Hoda","is_ca":false},{"name":"Hideaki Hata","is_ca":false},{"name":"Gregório Robles","is_ca":false},{"name":"Amin Milani Fard","is_ca":true},{"name":"Rana Alkadhi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001086019,0.0006712708,0.0003596283,0.00110848,0.001381665,0.003582792,0.001658171,0.001117703,0.3421234],"category_scores_gemma":[0.004781862,0.0004028633,0.0007259308,0.001140964,0.0005214029,0.003746704,0.004148095,0.001908734,0.1467855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012307,"about_ca_system_score_gemma":0.001863222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003747679,"about_ca_topic_score_gemma":0.003469182,"domain_scores_codex":[0.9990523,0.0002363668,0.00006491843,0.0002402675,0.0002497198,0.0001563791],"domain_scores_gemma":[0.9981933,0.0004552294,0.0001283354,0.0004667211,0.0004566495,0.0002996869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002356825,0.0001069134,0.002214456,0.0003816423,0.0000197091,0.0003679215,0.0008162684,0.0006066466,0.001327314,0.05056483,0.7546141,0.1887446],"study_design_scores_gemma":[0.00002107475,0.00001741889,0.0005813187,0.00008187965,0.00000546743,0.0001397137,0.0001925983,0.0005002924,0.0003320326,0.005490041,0.9926242,0.00001384405],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.009144192,0.0009074251,0.0414239,0.011769,0.004133145,0.0007668211,0.02816626,0.03503076,0.8686585],"genre_scores_gemma":[0.0849103,0.001977771,0.05163088,0.009825068,0.001490777,0.001040826,0.04510552,0.01056148,0.7934574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3421234,"threshold_uncertainty_score":0.9383812,"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","authors":[{"name":"Lin Tan","is_ca":true},{"name":"Chen Liu","is_ca":true},{"name":"LI Zhen-min","is_ca":false},{"name":"Xuanhui Wang","is_ca":false},{"name":"Yuanyuan Zhou","is_ca":false},{"name":"ChengXiang Zhai","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00392572,0.0002474515,0.0003225896,0.006734596,0.0005876186,0.001431637,0.0006364435,0.001009253,0.001487998],"category_scores_gemma":[0.1011304,0.0004430387,0.0005419804,0.00479579,0.001058775,0.002991692,0.001378353,0.001157922,0.0002504782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009336495,"about_ca_system_score_gemma":0.0008422454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003796122,"about_ca_topic_score_gemma":0.006649665,"domain_scores_codex":[0.9959748,0.0009827387,0.0006363356,0.0005358008,0.001505009,0.0003651998],"domain_scores_gemma":[0.7644025,0.1366231,0.07284085,0.006835827,0.01452624,0.004771471],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001235778,0.0001029907,0.9868183,0.00002856628,0.00003950317,0.0000933248,0.0007917371,0.0005870449,0.0005107227,0.0004694743,0.0001834775,0.01025126],"study_design_scores_gemma":[0.000008939404,0.0001279336,0.9945679,0.00002812129,0.00003200799,0.0003422509,0.0008201026,0.002526794,0.000265639,0.001004922,0.0002604524,0.00001500719],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989327,0.0001388409,0.0004897184,0.00004809863,0.000002592566,0.000005336566,0.0000654107,0.0000150928,0.000302247],"genre_scores_gemma":[0.9993939,0.00003347878,0.0002706708,0.000007424515,0.000004548607,0.000005197378,0.0001206256,0.0000148046,0.0001493772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9960743,"threshold_uncertainty_score":0.02076149,"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","authors":[{"name":"Stuart Mcilroy","is_ca":true},{"name":"Nasir Ali","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002168712,0.0004925822,0.0004723883,0.003439503,0.002756922,0.005356488,0.001325884,0.001672109,0.006205405],"category_scores_gemma":[0.02806376,0.0007929093,0.0004265034,0.002937145,0.002382634,0.007089843,0.00227924,0.00273402,0.001385277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001505494,"about_ca_system_score_gemma":0.002332239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03637595,"about_ca_topic_score_gemma":0.07077061,"domain_scores_codex":[0.9984762,0.0003452973,0.0001177227,0.0001728789,0.0006248754,0.0002630049],"domain_scores_gemma":[0.968092,0.01887683,0.005770259,0.001226909,0.00363802,0.002396017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004477452,0.003887026,0.8434185,0.0001751132,0.00009137182,0.0009670822,0.1251052,0.00008408011,0.0008180938,0.00167355,0.00238379,0.02094831],"study_design_scores_gemma":[0.00004368273,0.0005065112,0.7996266,0.0001491047,0.0001152359,0.0004423427,0.1924354,0.0008281443,0.0003933659,0.0003974757,0.00498613,0.00007593937],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983158,0.00005934905,0.0000450999,0.0001047198,0.000004439657,0.00003702151,0.00009696736,0.000004968093,0.00133169],"genre_scores_gemma":[0.9968284,0.0001693855,0.0001958997,0.0001512777,0.00001699631,0.00004581447,0.0003042868,0.00002187092,0.002266113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03637595,"threshold_uncertainty_score":0.07232839,"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","authors":[{"name":"Qiao Huang","is_ca":false},{"name":"Emad Shihab","is_ca":true},{"name":"Xin Xia","is_ca":true},{"name":"David Lo","is_ca":false},{"name":"Shanping Li","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003472366,0.0002633455,0.0003017028,0.006880254,0.000713843,0.001612203,0.0006649135,0.0009612949,0.001028692],"category_scores_gemma":[0.03971322,0.0001860112,0.0002806805,0.005615596,0.0003953213,0.002152466,0.001209338,0.0008259373,0.0005037529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005527096,"about_ca_system_score_gemma":0.0009208096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002375167,"about_ca_topic_score_gemma":0.004420753,"domain_scores_codex":[0.9970227,0.0006521685,0.0007276429,0.0004413209,0.0009093334,0.0002468158],"domain_scores_gemma":[0.9268764,0.03881427,0.02241508,0.002453806,0.007328088,0.002112351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001217976,0.0002080632,0.9606634,0.0001171363,0.00004186226,0.0003068089,0.001163281,0.0003719807,0.001937413,0.00049448,0.001406313,0.03316738],"study_design_scores_gemma":[0.0000142338,0.0001104508,0.9747272,0.0001559473,0.00005643192,0.0005643507,0.003298108,0.01267895,0.002632536,0.002212856,0.00351812,0.00003095637],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961922,0.0001392468,0.001305394,0.0001654391,0.00001214956,0.00002408645,0.00116835,0.00003299533,0.0009601532],"genre_scores_gemma":[0.9939329,0.0001288401,0.002197773,0.00004973359,0.00003499869,0.00004894513,0.002823114,0.00001670825,0.0007670712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006880254,"threshold_uncertainty_score":0.01836389,"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","authors":[{"name":"Stuart Mcilroy","is_ca":true},{"name":"Nasir Ali","is_ca":true},{"name":"Hammad Khalid","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006229083,0.0008031299,0.0007328273,0.01231966,0.001039726,0.002766008,0.0007881423,0.001449913,0.001066602],"category_scores_gemma":[0.08608788,0.0005188828,0.0006743261,0.004139348,0.0003684386,0.002666769,0.001302344,0.001066866,0.001180554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006993829,"about_ca_system_score_gemma":0.001927762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003718195,"about_ca_topic_score_gemma":0.01187222,"domain_scores_codex":[0.9889125,0.003520149,0.001347609,0.001193675,0.004675177,0.0003509439],"domain_scores_gemma":[0.8451639,0.1085085,0.0188138,0.003606429,0.02274385,0.00116364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001159987,0.000435178,0.360364,0.007534947,0.0004687168,0.002870316,0.01288431,0.001387844,0.05643315,0.002963752,0.04310456,0.5103933],"study_design_scores_gemma":[0.0001166104,0.001112487,0.6913583,0.003118112,0.001489217,0.008753801,0.01374798,0.07616106,0.06316012,0.005673286,0.1348716,0.0004373917],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9218228,0.008429823,0.0438677,0.002083048,0.0007294635,0.001015965,0.006626593,0.003083073,0.01234146],"genre_scores_gemma":[0.9067219,0.002408757,0.07367112,0.0005298289,0.0004055584,0.0006024953,0.008159434,0.0003939672,0.007106913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01231966,"threshold_uncertainty_score":0.03294295,"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","authors":[{"name":"Xin Xia","is_ca":true},{"name":"Lingfeng Bao","is_ca":false},{"name":"David Lo","is_ca":false},{"name":"Pavneet Singh Kochhar","is_ca":false},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Zhenchang Xing","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003909457,0.0003383023,0.0005178504,0.004285086,0.001190629,0.004964272,0.0007569347,0.002016313,0.007689649],"category_scores_gemma":[0.0618526,0.0003518779,0.0002661617,0.004783501,0.0009729045,0.009995463,0.001001718,0.001231845,0.002678263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001272019,"about_ca_system_score_gemma":0.002651234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01256895,"about_ca_topic_score_gemma":0.02016286,"domain_scores_codex":[0.9953418,0.001837943,0.000258318,0.0004364643,0.001586383,0.0005390823],"domain_scores_gemma":[0.9343048,0.04104603,0.01022754,0.002568299,0.009015879,0.002837509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000195862,0.0005003354,0.7339058,0.0008222071,0.000180056,0.001145784,0.0145411,0.0004075344,0.001272956,0.0119335,0.03618853,0.1989063],"study_design_scores_gemma":[0.0001823327,0.0002790456,0.7477002,0.002231744,0.0004917555,0.005375097,0.09320562,0.008510273,0.004786773,0.03491624,0.1021539,0.0001669435],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9015707,0.006162768,0.003219423,0.0200839,0.0001323231,0.00008436178,0.001070411,0.0002326165,0.06744352],"genre_scores_gemma":[0.9887983,0.001890336,0.001567555,0.000937304,0.00008712242,0.00002105054,0.0004256868,0.0001369648,0.006135672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01256895,"threshold_uncertainty_score":0.02572447,"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","authors":[{"name":"Lionel Briand","is_ca":true},{"name":"Jürgen Wüst","is_ca":false},{"name":"Hakim Lounis","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03770876,0.000669368,0.0007544509,0.002899524,0.00166486,0.002027266,0.003165937,0.002531408,0.00330282],"category_scores_gemma":[0.2325349,0.0007736171,0.001080426,0.002499433,0.002030574,0.003626407,0.002375607,0.001383029,0.0003290859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002116778,"about_ca_system_score_gemma":0.002147191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002473844,"about_ca_topic_score_gemma":0.005591773,"domain_scores_codex":[0.9327002,0.05449029,0.002794588,0.001903607,0.007510031,0.0006013677],"domain_scores_gemma":[0.5909102,0.3144413,0.01823542,0.05822511,0.0162577,0.00193026],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00699047,0.02484295,0.3475268,0.004299482,0.002162767,0.006673835,0.04968597,0.03797113,0.04321236,0.09964473,0.002875373,0.3741142],"study_design_scores_gemma":[0.008252302,0.06396508,0.2910159,0.002443034,0.004440895,0.01111863,0.05401892,0.272197,0.07645062,0.1850156,0.03025467,0.000827237],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8522003,0.001067517,0.1364351,0.0002688266,0.00007932439,0.002669565,0.0002084607,0.0001720441,0.00689876],"genre_scores_gemma":[0.8847176,0.0003856894,0.1122876,0.00007154132,0.00002900884,0.001590722,0.000150072,0.00003051646,0.0007373183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9622912,"threshold_uncertainty_score":0.1994253,"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","authors":[{"name":"Rongqi Pan","is_ca":true},{"name":"Mojtaba Bagherzadeh","is_ca":true},{"name":"Taher A. Ghaleb","is_ca":true},{"name":"Lionel Briand","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05975972,0.001958304,0.007467157,0.02102201,0.001261651,0.003955563,0.004611086,0.002447627,0.003002858],"category_scores_gemma":[0.2052746,0.00142136,0.006923026,0.01496554,0.00170537,0.005416324,0.002692281,0.001900032,0.0003908665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00584488,"about_ca_system_score_gemma":0.02783549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005622798,"about_ca_topic_score_gemma":0.01551792,"domain_scores_codex":[0.9552804,0.01828737,0.01479662,0.002736571,0.008360227,0.0005386744],"domain_scores_gemma":[0.7320911,0.2259438,0.02036279,0.0047324,0.01569577,0.00117415],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0006078061,0.0003359969,0.006460019,0.5391375,0.007851888,0.0002643355,0.001186836,0.001062972,0.00056656,0.000979983,0.003518856,0.4380272],"study_design_scores_gemma":[0.0009162746,0.0009945198,0.01088073,0.8951286,0.05081175,0.001148266,0.002354258,0.002496646,0.001964985,0.003350326,0.02975117,0.0002025231],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0106762,0.9761461,0.006802782,0.001649594,0.0002501492,0.002733733,0.0006866548,0.00006691495,0.0009878216],"genre_scores_gemma":[0.1295301,0.8321085,0.03072124,0.00201849,0.0002761134,0.0038158,0.001152724,0.00006986583,0.0003070944],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9402403,"threshold_uncertainty_score":0.3160434,"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)","authors":[{"name":"Jingzhou Li","is_ca":true},{"name":"Guenther Ruhe","is_ca":true},{"name":"Ahmed Al‐Emran","is_ca":true},{"name":"Michael M. Richter","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004920299,0.001170742,0.001786527,0.002897442,0.0009818826,0.001761558,0.003054273,0.002009135,0.006630953],"category_scores_gemma":[0.036009,0.0008102125,0.001667196,0.003314056,0.001216175,0.004890922,0.00394892,0.003021399,0.002122109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006541079,"about_ca_system_score_gemma":0.0009764062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001132431,"about_ca_topic_score_gemma":0.0009013037,"domain_scores_codex":[0.9929825,0.003278277,0.0002747822,0.001281801,0.001931789,0.0002508801],"domain_scores_gemma":[0.9895914,0.006159863,0.0004422825,0.002548449,0.00111903,0.0001389947],"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":[0.0001488976,0.0001929295,0.002401326,0.000195955,0.0001448947,0.0001941782,0.0003818966,0.07221169,0.006720628,0.3172714,0.003078588,0.5970577],"study_design_scores_gemma":[0.00006249863,0.0001938847,0.001863108,0.00006836536,0.00006941561,0.0004041722,0.00006197691,0.7168717,0.003910101,0.2675583,0.008845812,0.00009059444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001177523,0.00003062021,0.9976179,0.00002647975,0.00001477062,0.00002584342,0.000016134,0.0002143364,0.0008763423],"genre_scores_gemma":[0.1168824,0.0001293248,0.8787065,0.00008074004,0.0000821847,0.0004296694,0.000112616,0.0001894038,0.003387213],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006630953,"threshold_uncertainty_score":0.02602136,"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","authors":[{"name":"Stephen W. Thomas","is_ca":true},{"name":"Hadi Hemmati","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Dorothea Blostein","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01008298,0.00173376,0.001728762,0.01111392,0.001078136,0.003485714,0.002431113,0.00192231,0.007127939],"category_scores_gemma":[0.06890455,0.001014186,0.002514977,0.005228688,0.0005267462,0.00470247,0.002073967,0.00204661,0.001583351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001991152,"about_ca_system_score_gemma":0.003448137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008395957,"about_ca_topic_score_gemma":0.01281657,"domain_scores_codex":[0.9887435,0.00588415,0.0008405673,0.001650548,0.002206416,0.0006749231],"domain_scores_gemma":[0.9297371,0.05603277,0.002119486,0.003859625,0.007100894,0.001150158],"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":[0.002298456,0.001120871,0.07243875,0.001190008,0.0008860973,0.000497332,0.002896034,0.1088954,0.01246731,0.02268837,0.0172624,0.757359],"study_design_scores_gemma":[0.0002269482,0.000357278,0.01059447,0.00009439843,0.0006066588,0.0003376809,0.0006551347,0.9425092,0.007078066,0.03263905,0.004808185,0.00009302979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1531271,0.0008959026,0.8264585,0.0008056418,0.0001358418,0.0008818822,0.001583622,0.009680969,0.006430659],"genre_scores_gemma":[0.7826588,0.00029061,0.2088859,0.0001286524,0.0001307931,0.0007405065,0.002977544,0.001102442,0.003084827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01111392,"threshold_uncertainty_score":0.05332452,"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","authors":[{"name":"Wesley K. G. Assunção","is_ca":false},{"name":"Roberto E. Lopez-Herrejon","is_ca":true},{"name":"Lukas Linsbauer","is_ca":false},{"name":"Sílvia Regina Vergílio","is_ca":false},{"name":"Alexander Egyed","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0175375,0.0006945649,0.0005380848,0.01776536,0.001651496,0.003015372,0.001521636,0.001044185,0.00205682],"category_scores_gemma":[0.08685675,0.0006714087,0.0009919513,0.008671902,0.001815201,0.006045409,0.003742128,0.001213486,0.0003688519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002442698,"about_ca_system_score_gemma":0.0115389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005614316,"about_ca_topic_score_gemma":0.0148681,"domain_scores_codex":[0.9840631,0.007651523,0.002269252,0.001707533,0.003811604,0.0004969339],"domain_scores_gemma":[0.8684052,0.08250038,0.01725858,0.01375741,0.01730504,0.0007734106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002124016,0.00117441,0.1469105,0.009951476,0.0005779249,0.0006069826,0.04231344,0.002131285,0.004918297,0.01232048,0.001394449,0.7774885],"study_design_scores_gemma":[0.0002798463,0.00400961,0.5806679,0.06058864,0.004354247,0.00497355,0.1307382,0.01916342,0.03545138,0.02798987,0.1314534,0.0003298569],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.9172637,0.01973402,0.04723055,0.0007007179,0.00003888868,0.002760069,0.00101932,0.0001533798,0.01109931],"genre_scores_gemma":[0.88835,0.01625385,0.09033921,0.0003356122,0.0000190781,0.0009197691,0.001345218,0.0000684065,0.002368859],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01776536,"threshold_uncertainty_score":0.09274828,"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","authors":[{"name":"Emad Shihab","is_ca":false},{"name":"Akinori Ihara","is_ca":false},{"name":"Yasutaka Kamei","is_ca":false},{"name":"Walid M. Ibrahim","is_ca":true},{"name":"Masao Ohira","is_ca":false},{"name":"Bram Adams","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Ken-ichi Matsumoto","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004608901,0.0003501129,0.0003280944,0.002582762,0.000849801,0.001363404,0.001107497,0.001120993,0.002064889],"category_scores_gemma":[0.1078762,0.0004210432,0.0004084917,0.002182501,0.001137315,0.004120362,0.001339046,0.001886203,0.0002385208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00100182,"about_ca_system_score_gemma":0.001152704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006470883,"about_ca_topic_score_gemma":0.01180909,"domain_scores_codex":[0.9965423,0.00135318,0.0002889581,0.000429693,0.001082291,0.0003036293],"domain_scores_gemma":[0.8241104,0.1286978,0.02488685,0.008768903,0.01118505,0.002351071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003537371,0.00209778,0.8862586,0.0003093868,0.0002367322,0.0007326549,0.01151197,0.003766404,0.004047874,0.005303929,0.001083681,0.08429722],"study_design_scores_gemma":[0.00006626383,0.001109465,0.9323799,0.0002640907,0.0001990095,0.001194715,0.0176819,0.02657224,0.004678101,0.01249629,0.003288076,0.00006996006],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978539,0.0001623411,0.001150629,0.0001011524,0.000004181842,0.000008830975,0.00002735718,0.00001800102,0.0006734681],"genre_scores_gemma":[0.9982238,0.0001057593,0.0009825827,0.0000225796,0.000006500551,0.000008775873,0.0001110881,0.00002532087,0.000513525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006470883,"threshold_uncertainty_score":0.02437449,"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","authors":[{"name":"Gema Rodríguez-Pérez","is_ca":true},{"name":"Reza Nadri","is_ca":true},{"name":"Meiyappan Nagappan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02604947,0.0008363159,0.004214243,0.01895303,0.001017088,0.004169642,0.001608837,0.00208854,0.002827277],"category_scores_gemma":[0.1104524,0.0009656984,0.004342409,0.01478935,0.001757252,0.00510043,0.002867959,0.00170526,0.0002493224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004114368,"about_ca_system_score_gemma":0.02039126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007049392,"about_ca_topic_score_gemma":0.02640167,"domain_scores_codex":[0.9792659,0.007078683,0.007050542,0.00170253,0.004449626,0.0004528947],"domain_scores_gemma":[0.8307122,0.1407658,0.01481803,0.001766658,0.01053359,0.001403755],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003235987,0.0002139602,0.02528023,0.7450328,0.00905435,0.000337829,0.005007915,0.0002809654,0.0003824999,0.001288761,0.002555375,0.2102417],"study_design_scores_gemma":[0.000258983,0.0003845706,0.04417701,0.8901016,0.03242538,0.0008210566,0.007582052,0.0002301818,0.0002990823,0.001370545,0.02222295,0.0001266785],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01844374,0.9772621,0.0009296095,0.001055028,0.0001481941,0.0005873853,0.0006248309,0.00001051693,0.0009386534],"genre_scores_gemma":[0.1188868,0.8747106,0.003185454,0.001577406,0.0001390516,0.0008214837,0.0005085592,0.00001404348,0.0001565568],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9739505,"threshold_uncertainty_score":0.1377644,"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)","authors":[{"name":"Yuhao Wu","is_ca":false},{"name":"Shaowei Wang","is_ca":true},{"name":"Cor‐Paul Bezemer","is_ca":true},{"name":"Katsuro Inoue","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01661297,0.0007421146,0.0004480428,0.00627989,0.002322475,0.004476807,0.001478441,0.00172242,0.00217407],"category_scores_gemma":[0.175441,0.001011575,0.000613814,0.004021391,0.002855998,0.01246735,0.004245877,0.001496183,0.001459963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002656428,"about_ca_system_score_gemma":0.004246478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01038539,"about_ca_topic_score_gemma":0.01194737,"domain_scores_codex":[0.9830078,0.005370624,0.001291992,0.00197964,0.007132105,0.001217825],"domain_scores_gemma":[0.8591958,0.08143572,0.0209034,0.01346395,0.02246361,0.002537445],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0003467943,0.0003426707,0.2894927,0.001026661,0.0001172464,0.003472979,0.3611617,0.0009053434,0.01001469,0.005389312,0.01523174,0.3124981],"study_design_scores_gemma":[0.0001151941,0.0008215495,0.4766175,0.003091797,0.0002780044,0.006989154,0.2148143,0.00983843,0.02156987,0.01217005,0.2530836,0.0006104334],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9576204,0.0008502946,0.02281361,0.004057585,0.00009546603,0.0002550305,0.0005785972,0.002272932,0.01145612],"genre_scores_gemma":[0.96653,0.001053503,0.0195248,0.001163846,0.00005849611,0.0002727035,0.001555031,0.002251667,0.007589886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9833871,"threshold_uncertainty_score":0.0878588,"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","authors":[{"name":"Taghi M. Khoshgoftaar","is_ca":false},{"name":"Naeem Seliya","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009127711,0.001388179,0.001914033,0.006072673,0.0005506693,0.001360064,0.002671942,0.001518341,0.001093708],"category_scores_gemma":[0.04170169,0.000462617,0.001695392,0.004516779,0.0005509867,0.003461767,0.001352356,0.001327667,0.0003598735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167705,"about_ca_system_score_gemma":0.001221229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01091064,"about_ca_topic_score_gemma":0.007657822,"domain_scores_codex":[0.9945322,0.002550719,0.0004172797,0.0005544063,0.001724745,0.0002204871],"domain_scores_gemma":[0.9385799,0.05106867,0.00302878,0.002796893,0.004254357,0.0002713654],"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":[0.001286863,0.0005207744,0.02582925,0.000956558,0.001152456,0.00005050145,0.0003388249,0.3516938,0.0008224197,0.005231755,0.001555847,0.6105609],"study_design_scores_gemma":[0.00007871245,0.0004765113,0.008125781,0.0001473865,0.0003856381,0.00008432059,0.0001605712,0.9793963,0.000921906,0.009486163,0.0006949401,0.00004175597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2186677,0.01265556,0.7622088,0.0009445917,0.0001371771,0.0001533787,0.0006193991,0.002165653,0.002447799],"genre_scores_gemma":[0.8536903,0.006941518,0.137444,0.0001367704,0.0001548182,0.0001680449,0.0007252484,0.0001933283,0.0005460717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01091064,"threshold_uncertainty_score":0.04827249,"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","authors":[{"name":"Patanamon Thongtanunam","is_ca":false},{"name":"Shane McIntosh","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Hajimu Iida","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1678306,0.00104188,0.002366232,0.02901888,0.005077004,0.01371072,0.004169462,0.009296178,0.02956756],"category_scores_gemma":[0.6227236,0.00121525,0.001497742,0.01698516,0.003899182,0.01205956,0.01440798,0.004901427,0.008521236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009304824,"about_ca_system_score_gemma":0.03813744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003562577,"about_ca_topic_score_gemma":0.009522077,"domain_scores_codex":[0.7297186,0.1496015,0.0245331,0.01825003,0.0680493,0.009847349],"domain_scores_gemma":[0.2415008,0.4027857,0.07370254,0.05416102,0.1844803,0.04336959],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001024876,0.0001542322,0.02444622,0.01545717,0.0008522132,0.0007407256,0.01855441,0.0003559648,0.002765418,0.0282469,0.5953298,0.3120721],"study_design_scores_gemma":[0.0001104165,0.00008550012,0.01300675,0.005360022,0.000262447,0.0003223674,0.001447338,0.0002906734,0.0007312641,0.005720784,0.9726058,0.00005663093],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06788662,0.1913787,0.02551728,0.3875414,0.04440885,0.004592807,0.007906985,0.001879842,0.2688875],"genre_scores_gemma":[0.5896322,0.08556865,0.01935616,0.1022086,0.03891201,0.01107677,0.008021806,0.002275514,0.1429484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8321694,"threshold_uncertainty_score":0.8875835,"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","authors":[{"name":"Venera Arnaoudova","is_ca":true},{"name":"Massimiliano Di Penta","is_ca":false},{"name":"Giuliano Antoniol","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005078733,0.0003302138,0.0003319666,0.001464488,0.0009523791,0.004166773,0.0007893291,0.001853094,0.00320907],"category_scores_gemma":[0.04985293,0.0006791536,0.0002109786,0.00106217,0.002471637,0.009136185,0.002029949,0.001745322,0.0007937949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006758377,"about_ca_system_score_gemma":0.001380595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002013777,"about_ca_topic_score_gemma":0.002544217,"domain_scores_codex":[0.9929349,0.003056821,0.0005336074,0.0007204741,0.002449091,0.0003050735],"domain_scores_gemma":[0.9493569,0.02565562,0.009115425,0.005201783,0.009469068,0.001201088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004322052,0.0003173319,0.3484979,0.0008962366,0.0001047998,0.001133668,0.1929518,0.0007535458,0.06438965,0.0895457,0.01034395,0.2906332],"study_design_scores_gemma":[0.0001465166,0.0005513046,0.4561874,0.001030701,0.0003778651,0.003664132,0.1915695,0.022423,0.02899441,0.1863097,0.1084877,0.0002576612],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8677104,0.0006497867,0.08680447,0.00636733,0.0001493008,0.00008770213,0.0002442326,0.001046203,0.03694057],"genre_scores_gemma":[0.9760399,0.0002705875,0.01941634,0.0005960909,0.00005425437,0.00007086951,0.0001814373,0.0004859003,0.002884604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005078733,"threshold_uncertainty_score":0.02685922,"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","authors":[{"name":"Feng Zhang","is_ca":true},{"name":"Audris Mockus","is_ca":false},{"name":"Iman Keivanloo","is_ca":true},{"name":"Ying Zou","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004624921,0.001173321,0.002166807,0.001849971,0.0005935525,0.001742359,0.002333835,0.001537334,0.001880942],"category_scores_gemma":[0.01195783,0.000783088,0.001352248,0.001884197,0.00098097,0.003192469,0.002755806,0.002346403,0.001605855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000569749,"about_ca_system_score_gemma":0.002172701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005129556,"about_ca_topic_score_gemma":0.006056506,"domain_scores_codex":[0.9980559,0.000593817,0.0001505251,0.0005882534,0.0003944602,0.0002171509],"domain_scores_gemma":[0.9941295,0.002699067,0.0005349945,0.001098779,0.001313796,0.0002239122],"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":[0.00029183,0.0005802307,0.02328132,0.0002691939,0.0004952291,0.000384242,0.000355543,0.5150514,0.008271501,0.03904298,0.006487436,0.405489],"study_design_scores_gemma":[0.000008381884,0.00005016097,0.0008098582,0.00002082588,0.0000407945,0.00004603464,0.00002070858,0.9835768,0.0006385483,0.01413597,0.0006383376,0.00001357046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03149454,0.0002372748,0.9655889,0.000301637,0.00004266449,0.00004755598,0.0002721072,0.001329428,0.0006858637],"genre_scores_gemma":[0.5897877,0.000607118,0.402182,0.0003833298,0.0002029379,0.0002579888,0.00178938,0.0002857455,0.00450384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005129556,"threshold_uncertainty_score":0.02445918,"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","authors":[{"name":"Mika Mäntylä","is_ca":false},{"name":"Bram Adams","is_ca":true},{"name":"Foutse Khomh","is_ca":true},{"name":"Emelie Engström","is_ca":false},{"name":"Kai Petersen","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02303179,0.0006149614,0.001146476,0.01595971,0.001666285,0.002429589,0.001555555,0.001776177,0.002354048],"category_scores_gemma":[0.06054345,0.0005362562,0.00103523,0.0151588,0.001875564,0.003771844,0.002642617,0.001166006,0.0003995851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003465379,"about_ca_system_score_gemma":0.01595458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004378614,"about_ca_topic_score_gemma":0.01370758,"domain_scores_codex":[0.9768734,0.0111823,0.004196422,0.001113187,0.005888236,0.0007464995],"domain_scores_gemma":[0.7839958,0.1880927,0.01123132,0.003712899,0.01197508,0.000992185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0004212466,0.0008285102,0.02440714,0.1423393,0.0006001983,0.01505051,0.08042626,0.001375739,0.007270369,0.01133761,0.01063186,0.7053112],"study_design_scores_gemma":[0.0001931819,0.002017755,0.09426519,0.3618445,0.002899361,0.01448214,0.2001253,0.001517544,0.01137942,0.008958283,0.3019783,0.0003391879],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.4678476,0.4406667,0.02484396,0.01048364,0.0006090443,0.00710003,0.002929332,0.0001667045,0.04535301],"genre_scores_gemma":[0.6567097,0.3082301,0.02434525,0.002848104,0.0002335793,0.002498043,0.001667849,0.0000873259,0.003379987],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02303179,"threshold_uncertainty_score":0.1218052,"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","authors":[{"name":"Heng Li","is_ca":true},{"name":"Weiyi Shang","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008143733,0.0002944368,0.0002919412,0.000998745,0.0005188838,0.001698208,0.0006490369,0.001254261,0.004732789],"category_scores_gemma":[0.09121022,0.0004232149,0.0002866578,0.0005140971,0.0006998166,0.003073175,0.0006072848,0.001392272,0.001838258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007618146,"about_ca_system_score_gemma":0.001491885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002211501,"about_ca_topic_score_gemma":0.009467151,"domain_scores_codex":[0.9958662,0.001645915,0.0003938384,0.0006092099,0.001035364,0.0004495366],"domain_scores_gemma":[0.9215124,0.04864463,0.01010276,0.005220728,0.009682205,0.004837272],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001928629,0.001183169,0.6853866,0.000482137,0.0001823653,0.0008978263,0.00351067,0.001864639,0.01687762,0.004213073,0.01807809,0.2653952],"study_design_scores_gemma":[0.0006321674,0.002066515,0.8243482,0.000847475,0.0005696043,0.002096843,0.02409402,0.03514585,0.03728324,0.03256024,0.03995826,0.0003976187],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9616467,0.000361596,0.01399364,0.00962304,0.000122808,0.0001534964,0.0007853953,0.0006566903,0.01265661],"genre_scores_gemma":[0.9881621,0.000119133,0.008767188,0.0005837741,0.00003552836,0.00004485624,0.0001843526,0.000143524,0.001959507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9918563,"threshold_uncertainty_score":0.04306871,"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","authors":[{"name":"Olga Baysal","is_ca":true},{"name":"Oleksii Kononenko","is_ca":true},{"name":"Reid Holmes","is_ca":true},{"name":"Michael W. Godfrey","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02281567,0.0002124226,0.0003273773,0.006928952,0.00141744,0.004311479,0.0009769073,0.0008618725,0.003958115],"category_scores_gemma":[0.356922,0.0003327578,0.0004785622,0.006150205,0.001607735,0.003650684,0.001503184,0.001513632,0.0005186999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003396297,"about_ca_system_score_gemma":0.007930938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01060999,"about_ca_topic_score_gemma":0.02444933,"domain_scores_codex":[0.9790224,0.008113833,0.002254816,0.001488583,0.007621475,0.001498859],"domain_scores_gemma":[0.3626739,0.4221527,0.1270808,0.009903139,0.0695596,0.008629865],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003051897,0.000171396,0.9261365,0.0004716568,0.0002028277,0.0002795087,0.005334309,0.0005329262,0.001286107,0.002957347,0.001879202,0.060443],"study_design_scores_gemma":[0.00001542456,0.0001872827,0.9832,0.0002616745,0.0001304858,0.0003667104,0.005194132,0.001511406,0.001201273,0.00140321,0.006487501,0.00004097562],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855213,0.002428637,0.001735596,0.001948917,0.00005005244,0.0000853879,0.0001686845,0.00004970989,0.008011801],"genre_scores_gemma":[0.9971733,0.0006378111,0.0008177828,0.0001734969,0.00004453115,0.00002247298,0.0001055676,0.00003255546,0.0009923936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9771844,"threshold_uncertainty_score":0.1206623,"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","authors":[{"name":"Owura Asare","is_ca":true},{"name":"Meiyappan Nagappan","is_ca":true},{"name":"N. Asokan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01284018,0.0007556767,0.0005805771,0.002195365,0.001953775,0.004201843,0.00148113,0.003567981,0.007533938],"category_scores_gemma":[0.1135264,0.0005736612,0.0004657946,0.001622883,0.005434384,0.00982682,0.003005204,0.003289641,0.003115741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001564931,"about_ca_system_score_gemma":0.004348669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01272423,"about_ca_topic_score_gemma":0.01876717,"domain_scores_codex":[0.9867927,0.005636173,0.0003781918,0.001327821,0.004550868,0.001314382],"domain_scores_gemma":[0.9246243,0.03559589,0.008131279,0.01611131,0.01120339,0.004333802],"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":[0.001873805,0.0006240356,0.2007792,0.0009830421,0.0005266014,0.00113212,0.0146606,0.004594635,0.007666979,0.07533218,0.2782953,0.4135316],"study_design_scores_gemma":[0.0004531831,0.00168336,0.1989031,0.002518631,0.0007303943,0.005750274,0.03573762,0.03147067,0.02586375,0.2132635,0.4830087,0.0006168806],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6374408,0.004350051,0.0443414,0.1714395,0.002593075,0.0001521607,0.001369019,0.01016487,0.1281492],"genre_scores_gemma":[0.9504278,0.001140921,0.01825848,0.01746825,0.000322523,0.00005797809,0.0008132141,0.00237447,0.009136404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01284018,"threshold_uncertainty_score":0.0679062,"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","authors":[{"name":"Masanari Kondo","is_ca":false},{"name":"Cor‐Paul Bezemer","is_ca":true},{"name":"Yasutaka Kamei","is_ca":false},{"name":"Ahmed E. Hassan","is_ca":true},{"name":"Osamu Mizuno","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003613619,0.001202762,0.001145099,0.001430772,0.0003709361,0.001188762,0.001032858,0.0009811593,0.001654359],"category_scores_gemma":[0.02470349,0.0003781466,0.001137829,0.001068913,0.0003424486,0.002086393,0.000473687,0.001585542,0.0005932565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004254022,"about_ca_system_score_gemma":0.001004276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063413,"about_ca_topic_score_gemma":0.007165811,"domain_scores_codex":[0.998353,0.00077576,0.0001162035,0.0002999745,0.0003336922,0.0001214645],"domain_scores_gemma":[0.9639595,0.03162028,0.0007300295,0.001886629,0.00165803,0.0001454389],"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":[0.001082804,0.0008157186,0.0165107,0.0001654875,0.0003541095,0.0001035984,0.00005338413,0.3927362,0.005534599,0.001287865,0.002996939,0.5783587],"study_design_scores_gemma":[0.00001925954,0.0001395233,0.002836507,0.00001051522,0.00007050117,0.00004054817,0.00001668207,0.9936801,0.001804766,0.001149227,0.0002237104,0.000008596446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6060867,0.005455708,0.3762033,0.001830049,0.0002882191,0.0001087475,0.001158342,0.004365603,0.004503358],"genre_scores_gemma":[0.9222826,0.0007645126,0.07395417,0.0001322793,0.0001176443,0.00003202606,0.001183522,0.0001611523,0.001372075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01063413,"threshold_uncertainty_score":0.02114445,"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","authors":[{"name":"Heng Li","is_ca":true},{"name":"Tse-Hsun Chen","is_ca":true},{"name":"Weiyi Shang","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007309626,0.0007300656,0.0008348735,0.002591935,0.001011094,0.004020339,0.001142146,0.00159393,0.003253059],"category_scores_gemma":[0.06072639,0.0007223399,0.0008938548,0.00410205,0.001039978,0.01049256,0.001217949,0.002413932,0.0006526088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00130392,"about_ca_system_score_gemma":0.0009043756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003164484,"about_ca_topic_score_gemma":0.003283634,"domain_scores_codex":[0.9963007,0.002672363,0.0001235669,0.0003721203,0.0003120316,0.0002193018],"domain_scores_gemma":[0.8847153,0.1064671,0.002951738,0.003227614,0.001690347,0.0009480038],"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":[0.001305202,0.002517969,0.2996075,0.00107492,0.0008271981,0.0006077637,0.01995619,0.1158635,0.007061965,0.2207856,0.01067179,0.3197205],"study_design_scores_gemma":[0.0001189582,0.0005209794,0.0523946,0.0002086508,0.0003331522,0.0005483581,0.00903551,0.6887113,0.00328295,0.2353581,0.009396489,0.00009102552],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.755968,0.002650151,0.2279945,0.00247939,0.00007404296,0.0001172486,0.0002920903,0.0004830382,0.009941475],"genre_scores_gemma":[0.9888076,0.0007088084,0.008644212,0.00006840607,0.00009874165,0.00005865646,0.0002608903,0.00008941415,0.001263141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007309626,"threshold_uncertainty_score":0.03865749,"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","authors":[{"name":"Yingying Wang","is_ca":true},{"name":"Harshavardhan Kadiyala","is_ca":true},{"name":"Julia Rubin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009827132,0.0002099441,0.0002183865,0.001218196,0.002481442,0.003357129,0.001247703,0.001191907,0.006403757],"category_scores_gemma":[0.05078385,0.0003379662,0.0002157706,0.001562591,0.002812938,0.008007493,0.002207865,0.00216533,0.0006014331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00181771,"about_ca_system_score_gemma":0.002431742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002042811,"about_ca_topic_score_gemma":0.003786691,"domain_scores_codex":[0.9953328,0.002596754,0.0001441072,0.0002638568,0.001158555,0.0005038641],"domain_scores_gemma":[0.8690165,0.1090996,0.009849322,0.002703977,0.005428968,0.003901607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.002261501,0.005444599,0.550806,0.001097283,0.00008187971,0.002402335,0.1716835,0.002381747,0.004322764,0.1286432,0.004805667,0.1260696],"study_design_scores_gemma":[0.0001031497,0.003138684,0.3668398,0.0007035791,0.0000965827,0.001220107,0.5562902,0.008558925,0.003509512,0.02181684,0.03763445,0.00008810324],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863787,0.0002440002,0.0006984822,0.00117758,0.000006108991,0.00005690576,0.00005051915,0.00000862753,0.01137911],"genre_scores_gemma":[0.9987263,0.0001568734,0.0002879404,0.00006552373,0.000006898863,0.00002537192,0.0000217402,0.000005060059,0.0007042467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009827132,"threshold_uncertainty_score":0.0519715,"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","authors":[{"name":"Lauren R. Biggers","is_ca":false},{"name":"Cecylia Bocovich","is_ca":true},{"name":"Riley Capshaw","is_ca":false},{"name":"Brian P. Eddy","is_ca":false},{"name":"Letha H. Etzkorn","is_ca":false},{"name":"Nicholas A. Kraft","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004691952,0.001172293,0.001994057,0.001771715,0.001198845,0.002288966,0.003565405,0.002996026,0.005946101],"category_scores_gemma":[0.02617802,0.001117412,0.001562748,0.002036664,0.001130444,0.004341395,0.004427487,0.0025514,0.00408932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001247305,"about_ca_system_score_gemma":0.001734929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005126292,"about_ca_topic_score_gemma":0.006945486,"domain_scores_codex":[0.9952041,0.002340378,0.0002778222,0.001211521,0.0005941085,0.0003720744],"domain_scores_gemma":[0.9893944,0.006382376,0.0002859529,0.002386235,0.001230207,0.0003208873],"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":[0.002806083,0.0006807047,0.01138373,0.0002170039,0.000360265,0.0003402931,0.0006890604,0.1710555,0.0198756,0.01983182,0.01693756,0.7558224],"study_design_scores_gemma":[0.00009839551,0.00005694141,0.0006162566,0.00001183574,0.00005144429,0.00008170229,0.00009459545,0.9660085,0.006740224,0.02454561,0.001665583,0.00002891898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02798516,0.0001884386,0.9646391,0.000317795,0.0001225927,0.00008263373,0.0003234452,0.00535415,0.0009866538],"genre_scores_gemma":[0.4894229,0.0001269988,0.503398,0.0003601254,0.0001442928,0.0004010892,0.002122656,0.0009832985,0.003040629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005946101,"threshold_uncertainty_score":0.02481377,"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","authors":[{"name":"Abram Hindle","is_ca":true},{"name":"Anahita Alipour","is_ca":true},{"name":"Eleni Stroulia","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005544561,0.001646617,0.003092136,0.009286934,0.001823549,0.004161783,0.002875402,0.002600113,0.004491334],"category_scores_gemma":[0.03724048,0.0009301592,0.001420258,0.007033832,0.0009347146,0.004100184,0.004323479,0.002293311,0.002688098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008416561,"about_ca_system_score_gemma":0.004171381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005432454,"about_ca_topic_score_gemma":0.01689432,"domain_scores_codex":[0.9870529,0.003792562,0.001200853,0.00292764,0.004370277,0.0006557617],"domain_scores_gemma":[0.9631404,0.01139809,0.003810285,0.009844602,0.01093853,0.000868063],"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":[0.001119903,0.001252666,0.03931684,0.00138094,0.0005058724,0.0006815734,0.001097397,0.02977865,0.06742103,0.01926846,0.02520061,0.8129761],"study_design_scores_gemma":[0.0002642877,0.001337421,0.03280336,0.000430585,0.0009339345,0.001849571,0.001258672,0.7933056,0.06508187,0.05318017,0.04916038,0.0003942113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04620775,0.001991755,0.9377167,0.0008581258,0.0003215049,0.0003849154,0.001888142,0.007198961,0.003432136],"genre_scores_gemma":[0.2923484,0.0005453317,0.7003278,0.0004502418,0.0005377682,0.0003080186,0.002719136,0.0005315918,0.002231716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009286934,"threshold_uncertainty_score":0.0293228,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.07468481,0.001962229,0.003245499,0.01674091,0.01139717,0.02705084,0.004361659,0.01591273,0.004707928],"category_scores_gemma":[0.06251721,0.002234474,0.001435377,0.01043794,0.153904,0.05962122,0.0108777,0.01373572,0.0008919235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01319076,"about_ca_system_score_gemma":0.02718721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005760077,"about_ca_topic_score_gemma":0.005149952,"domain_scores_codex":[0.9352764,0.04800886,0.003856852,0.00321504,0.007889889,0.001752958],"domain_scores_gemma":[0.8263888,0.1463443,0.005866309,0.005801778,0.008385471,0.007213371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008446341,0.00005708988,0.0006356813,0.0002096988,0.00001506737,0.00008293033,0.004156868,0.0002701133,0.0001098468,0.9866121,0.001799308,0.006042958],"study_design_scores_gemma":[0.00002131922,0.00002477069,0.000459288,0.0006899047,0.00001284683,0.000137923,0.006234747,0.001115653,0.0001342861,0.9685956,0.02254445,0.0000292528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01490135,0.04415028,0.279399,0.5593503,0.002646405,0.0006779404,0.0003853255,0.0002410194,0.09824842],"genre_scores_gemma":[0.7266641,0.02690211,0.197346,0.03575724,0.00487037,0.001703787,0.0002256688,0.0003264917,0.006204146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9886028,"threshold_uncertainty_score":0.3949758,"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","authors":[{"name":"Junxiao Han","is_ca":false},{"name":"Emad Shihab","is_ca":true},{"name":"Zhiyuan Wan","is_ca":false},{"name":"Shuiguang Deng","is_ca":false},{"name":"Xin Xia","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01687423,0.0006551857,0.0006053128,0.002296552,0.003335093,0.01004635,0.002152918,0.005931432,0.007407367],"category_scores_gemma":[0.1126468,0.0007393904,0.0007338767,0.002898097,0.006763819,0.0319939,0.002587687,0.008907746,0.001557145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0022939,"about_ca_system_score_gemma":0.003750404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002873661,"about_ca_topic_score_gemma":0.003119077,"domain_scores_codex":[0.9898347,0.004696473,0.0004708842,0.001122402,0.002770402,0.00110508],"domain_scores_gemma":[0.9206953,0.0564694,0.004114738,0.00505788,0.01006784,0.003594804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001883414,0.0001398243,0.01186907,0.001179392,0.0001307136,0.0002728134,0.006104995,0.002818903,0.001338631,0.5466093,0.09053764,0.3388104],"study_design_scores_gemma":[0.00003901858,0.00006488232,0.003575496,0.002943536,0.0001083497,0.0007943588,0.01025494,0.005216299,0.002813343,0.6622452,0.3118443,0.000100261],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03961806,0.02565322,0.1656904,0.6940899,0.005777477,0.00004972883,0.0002900498,0.000631028,0.06820028],"genre_scores_gemma":[0.691624,0.03574362,0.0970789,0.1316925,0.01473747,0.000199935,0.0006086273,0.001914928,0.02639988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01687423,"threshold_uncertainty_score":0.08924049,"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","authors":[{"name":"Yan‐Fu Li","is_ca":false},{"name":"Min Xie","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005097798,0.00050176,0.0006935793,0.000860425,0.0005238915,0.001421834,0.002796942,0.0009425477,0.006110389],"category_scores_gemma":[0.07071627,0.0004878539,0.0008755066,0.002246784,0.0009844913,0.003252907,0.00123394,0.002426063,0.0004967222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010721,"about_ca_system_score_gemma":0.001001279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003754575,"about_ca_topic_score_gemma":0.002800257,"domain_scores_codex":[0.9954054,0.002944316,0.0001427923,0.0005233604,0.0008295633,0.0001545559],"domain_scores_gemma":[0.9700991,0.02481494,0.001216358,0.002349575,0.001368428,0.0001515436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002444767,0.0002524268,0.006156703,0.0004205481,0.0002059304,0.0002255875,0.0005378405,0.2664249,0.004636369,0.3861949,0.002366531,0.3323338],"study_design_scores_gemma":[0.00002001176,0.0001229019,0.003301916,0.00002722127,0.0000502994,0.0001352422,0.00007817421,0.8979145,0.001646143,0.09288818,0.003777108,0.00003827146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03515997,0.0005199751,0.95855,0.000500372,0.00008865102,0.00007555517,0.00003178488,0.0002426617,0.004831104],"genre_scores_gemma":[0.6860912,0.0003858065,0.3058991,0.0001916173,0.0001155112,0.0001130186,0.0001029605,0.0002417248,0.00685907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006110389,"threshold_uncertainty_score":0.02696002,"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","authors":[{"name":"Maleknaz Nayebi","is_ca":true},{"name":"Henry Cho","is_ca":true},{"name":"Guenther Ruhe","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01076294,0.002037523,0.002373668,0.006136754,0.001694082,0.005938727,0.00320959,0.002605909,0.007900404],"category_scores_gemma":[0.1002599,0.001148416,0.001552414,0.004262989,0.001610925,0.01972388,0.002048558,0.004213605,0.008334548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001230145,"about_ca_system_score_gemma":0.004016206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005084589,"about_ca_topic_score_gemma":0.008800792,"domain_scores_codex":[0.9870325,0.003134628,0.001085506,0.001793518,0.006229762,0.0007238835],"domain_scores_gemma":[0.8506922,0.0712537,0.010459,0.02631956,0.0388659,0.002409575],"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":[0.0003610436,0.001262975,0.1814674,0.00121822,0.0005818627,0.0002331555,0.000633903,0.003864944,0.004481129,0.007210069,0.08108281,0.7176025],"study_design_scores_gemma":[0.0002414391,0.001883648,0.2184519,0.003634074,0.001854045,0.002660835,0.006684524,0.3296129,0.03052205,0.1805318,0.223533,0.0003898426],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5167426,0.01612417,0.2313608,0.1272828,0.002833852,0.001305341,0.0114547,0.02215057,0.07074511],"genre_scores_gemma":[0.8316839,0.003511346,0.1341305,0.007935736,0.001497342,0.0003503844,0.006574576,0.00111683,0.01319938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01076294,"threshold_uncertainty_score":0.05692059,"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)","authors":[{"name":"Weiyi Shang","is_ca":true},{"name":"Meiyappan Nagappan","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003225627,0.0002696241,0.0001672387,0.00172377,0.0004061348,0.00150635,0.0005910607,0.0006848436,0.002097047],"category_scores_gemma":[0.06716347,0.000351052,0.0003790522,0.002637096,0.0007499626,0.002399227,0.0007434319,0.001340403,0.0002878787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000748504,"about_ca_system_score_gemma":0.001101173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004894789,"about_ca_topic_score_gemma":0.008909918,"domain_scores_codex":[0.9980084,0.0006725447,0.0001985416,0.0003030215,0.0005433173,0.0002740679],"domain_scores_gemma":[0.8040397,0.1425558,0.03768033,0.005471352,0.007526554,0.002726274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001269394,0.000175908,0.9928051,0.00001532955,0.00006362877,0.00004367427,0.000231879,0.0009770009,0.00082951,0.0002409002,0.00003945484,0.004450831],"study_design_scores_gemma":[0.000008034489,0.0002423134,0.9897236,0.000007778283,0.00005354316,0.0000952793,0.0005756542,0.007289979,0.001380524,0.0004694559,0.0001419272,0.00001194367],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992967,0.00002996669,0.0003842799,0.00002842717,9.790556e-7,0.000002613628,0.00002345012,0.000005776899,0.0002277489],"genre_scores_gemma":[0.9996004,0.00001808362,0.0002068109,0.000004415531,0.000002183159,0.000001823471,0.00005280666,0.000004130736,0.0001093562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004894789,"threshold_uncertainty_score":0.01705891,"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","authors":[{"name":"Taher A. Ghaleb","is_ca":true},{"name":"Daniel Alencar da Costa","is_ca":false},{"name":"Ying Zou","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005240301,0.0001914908,0.0002611335,0.001383115,0.001179337,0.002568677,0.001029676,0.001046969,0.007110722],"category_scores_gemma":[0.07605561,0.0002761992,0.0002075801,0.002357331,0.00121285,0.003408808,0.001828542,0.00200776,0.0007326227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044201,"about_ca_system_score_gemma":0.001264331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003075729,"about_ca_topic_score_gemma":0.00481151,"domain_scores_codex":[0.9978466,0.0007039348,0.0001520153,0.0002711765,0.0007782484,0.000247914],"domain_scores_gemma":[0.8275707,0.1255152,0.02704307,0.006366929,0.00743384,0.006070194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001439175,0.001655875,0.8718597,0.0002634481,0.0001364641,0.0007902127,0.01431735,0.001622475,0.002770205,0.01442274,0.001466695,0.08925547],"study_design_scores_gemma":[0.00009187996,0.001574022,0.9559712,0.0001373388,0.0001553832,0.0007594613,0.01675153,0.005341699,0.001538511,0.009628538,0.007986527,0.00006396296],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938267,0.0004429358,0.0009305709,0.0002733141,0.0000105122,0.00001494202,0.0001213222,0.00001858898,0.004360995],"genre_scores_gemma":[0.9989154,0.00008873181,0.0002433094,0.00002904351,0.00001379009,0.000009839599,0.0001102304,0.000007832455,0.0005818794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007110722,"threshold_uncertainty_score":0.02771372,"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","authors":[{"name":"Shaowei Wang","is_ca":true},{"name":"David Lo","is_ca":false},{"name":"Bogdan Vasilescu","is_ca":false},{"name":"Alexander Serebrenik","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001348254,0.002136433,0.001820965,0.00656359,0.0008174213,0.001751794,0.001866828,0.001464525,0.01829223],"category_scores_gemma":[0.00472981,0.0007555838,0.001085889,0.004202435,0.0001555013,0.002598465,0.001932231,0.0010509,0.02448685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005588545,"about_ca_system_score_gemma":0.000764681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01012002,"about_ca_topic_score_gemma":0.02454728,"domain_scores_codex":[0.9985982,0.0002472289,0.0001167807,0.0002694004,0.0006571586,0.0001112676],"domain_scores_gemma":[0.9968401,0.0008089839,0.000229141,0.001014995,0.0007411945,0.000365675],"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":[0.00257105,0.0007895195,0.009116318,0.0009400913,0.0005154988,0.0004918572,0.0002275178,0.003730399,0.0317568,0.001738963,0.2596158,0.6885062],"study_design_scores_gemma":[0.001048348,0.001483612,0.02750801,0.0001927493,0.0008484466,0.001502642,0.000484764,0.5298834,0.09586393,0.009831788,0.3305325,0.0008197309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.04843058,0.001659951,0.2989514,0.0006614004,0.0005055787,0.0012362,0.05757356,0.5786976,0.01228381],"genre_scores_gemma":[0.1789683,0.00125164,0.6316577,0.0008744651,0.0004250022,0.0008415827,0.1246404,0.008985099,0.05235577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01829223,"threshold_uncertainty_score":0.06119359,"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","authors":[{"name":"Heng Li","is_ca":true},{"name":"Weiyi Shang","is_ca":true},{"name":"Ying Zou","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02371935,0.002258967,0.001423964,0.003264017,0.002568688,0.00862879,0.005701107,0.006374546,0.02686177],"category_scores_gemma":[0.2246955,0.001736048,0.001002985,0.001576123,0.001475647,0.01373593,0.004859458,0.005312875,0.01094687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001582777,"about_ca_system_score_gemma":0.006489072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002659793,"about_ca_topic_score_gemma":0.005934548,"domain_scores_codex":[0.959419,0.02467216,0.001952343,0.003548679,0.009324773,0.001083133],"domain_scores_gemma":[0.7762057,0.139467,0.01177633,0.03109156,0.03606172,0.005397722],"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":[0.003515255,0.002540964,0.02447411,0.001490565,0.000234641,0.001336822,0.007051249,0.01668623,0.02841831,0.03264712,0.07699145,0.8046133],"study_design_scores_gemma":[0.001494286,0.001807459,0.02063756,0.001291501,0.0004114346,0.001522172,0.01542156,0.6136001,0.04240712,0.1531932,0.1474875,0.0007262007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07856402,0.001003655,0.8317036,0.0175772,0.0009555122,0.001133787,0.001405605,0.0462151,0.02144154],"genre_scores_gemma":[0.3262251,0.000252903,0.6619252,0.001179949,0.0002643001,0.0003474188,0.001312732,0.00184363,0.006648803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02686177,"threshold_uncertainty_score":0.1254414,"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","authors":[{"name":"Jingzhou Li","is_ca":true},{"name":"Guenther Ruhe","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007072041,0.000478251,0.000793784,0.001614667,0.000616811,0.001364545,0.001406066,0.0008045983,0.003092284],"category_scores_gemma":[0.04570426,0.0003029659,0.0004887783,0.001697677,0.00030542,0.002132728,0.00108384,0.0009902479,0.000348295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007429414,"about_ca_system_score_gemma":0.001383266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002589422,"about_ca_topic_score_gemma":0.003038796,"domain_scores_codex":[0.9948006,0.00335007,0.0002836245,0.0005009549,0.0008875476,0.0001772734],"domain_scores_gemma":[0.959873,0.0339116,0.0009830343,0.002117869,0.002872254,0.0002422946],"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":[0.001375963,0.0009320373,0.02903207,0.0004686963,0.0002281688,0.00007973331,0.0009529974,0.05086263,0.007308756,0.01491679,0.003835783,0.8900064],"study_design_scores_gemma":[0.0001272438,0.0004868147,0.0104635,0.00005040032,0.0001631826,0.0001390158,0.0003622378,0.9681334,0.005691226,0.01226142,0.002078482,0.00004312222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4599824,0.0006777401,0.5317091,0.0002533361,0.0000602984,0.0003554786,0.0003126321,0.001747672,0.004901384],"genre_scores_gemma":[0.7402712,0.00008547048,0.258083,0.00007637611,0.00001352817,0.0001934131,0.0003824156,0.0001169991,0.0007776467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007072041,"threshold_uncertainty_score":0.03740102,"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","authors":[{"name":"Gema Rodríguez-Pérez","is_ca":true},{"name":"Gregório Robles","is_ca":false},{"name":"Alexander Serebrenik","is_ca":false},{"name":"Andy Zaidman","is_ca":false},{"name":"Daniel M. Germán","is_ca":true},{"name":"Jesus M. Gonzalez-Barahona","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007021497,0.001335622,0.001045068,0.00929131,0.0009392814,0.003845833,0.002130301,0.003091578,0.001811786],"category_scores_gemma":[0.04929294,0.0007353934,0.001804496,0.003447786,0.002521064,0.006107893,0.002321217,0.001607981,0.0007701086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002377215,"about_ca_system_score_gemma":0.001597568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01113884,"about_ca_topic_score_gemma":0.009765143,"domain_scores_codex":[0.9958449,0.001261345,0.0003803117,0.001313354,0.0008557821,0.000344249],"domain_scores_gemma":[0.939931,0.04215767,0.008307773,0.003470333,0.004912148,0.001221157],"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":[0.001368946,0.0005830828,0.5505127,0.001018617,0.0005237153,0.001182789,0.003410992,0.2692018,0.006679441,0.02390862,0.01221562,0.1293938],"study_design_scores_gemma":[0.00004769728,0.0001418221,0.03347481,0.0000883963,0.00007424544,0.0004268779,0.0004507943,0.9415368,0.001237047,0.02076133,0.001705557,0.00005461078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6244081,0.002124251,0.3592568,0.003666377,0.0001052938,0.0003507322,0.002888395,0.003922355,0.003277577],"genre_scores_gemma":[0.9424195,0.0002768179,0.05380355,0.0002613464,0.00004399051,0.000118649,0.002167532,0.0001172587,0.0007913049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01113884,"threshold_uncertainty_score":0.03713369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}