{"meta":{"query_hash":"a1e852829d09","filters":{"venue":"Software Quality Journal"},"cohort_total":51,"direct_labels_cover":0,"predictions_cover":51,"exported":51,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/a1e852829d09","api":"https://metacan.xera.ac/api/v1/cohort?venue=Software+Quality+Journal"},"results":[{"id":"W1537009764","doi":"10.1023/a:1021634422504","title":"Specification-based Testing for Gui-based Applications","year":2002,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Programming language; Java; Formal specification; Test harness; Finite-state machine; Graphical user interface testing; Test case; Implementation; Software engineering; Keyword-driven testing; Graphical user interface; Software; User interface; Software development","score_opus":0.15669253087361484,"score_gpt":0.34311759476107645,"score_spread":0.1864250638874616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537009764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029334179,0.00018821804,0.98984456,0.0022649865,0.00015911386,0.0003537163,0.000014305646,0.0066923494,0.00018940943],"genre_scores_gemma":[0.09473991,0.00000133184,0.90344274,0.0012417373,0.0002999048,0.00017686516,0.0000065877575,0.000022495977,0.00006843327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797404,0.0001597305,0.00063313695,0.00040666005,0.00042996835,0.00039648227],"domain_scores_gemma":[0.9938838,0.0038214517,0.000473415,0.0008533941,0.0007612299,0.00020674612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016008414,0.00019338891,0.00022359702,0.00019905453,0.00077510014,0.00042195144,0.0011496553,0.000093457274,0.000032675118],"category_scores_gemma":[0.0043260762,0.0001883012,0.0001697115,0.00064738217,0.000074297786,0.00024327559,0.000045792127,0.00030083625,0.000041350213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001531772,0.0007623015,0.07879934,0.00020201474,0.000035192865,0.000012257545,0.00034179544,0.0017962576,0.00027390942,0.007490197,0.10704433,0.80322707],"study_design_scores_gemma":[0.0031706574,0.00075455627,0.027204838,0.00050979806,0.00006530148,0.0002683369,0.000023781336,0.4179279,0.0024262676,0.46600154,0.079565674,0.0020813588],"about_ca_topic_score_codex":0.000013015048,"about_ca_topic_score_gemma":0.0000011906117,"teacher_disagreement_score":0.80114573,"about_ca_system_score_codex":0.0001313756,"about_ca_system_score_gemma":0.00017517095,"threshold_uncertainty_score":0.76787007},"labels":[],"label_agreement":null},{"id":"W1537911176","doi":"10.1023/a:1025869312943","title":"Usability Meanings and Interpretations in ISO Standards","year":2003,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":454,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"","keywords":"Usability; Computer science; Usability engineering; Software engineering; System usability scale; Component-based usability testing; Usability goals; Software quality; Standardization; Usability inspection; Software; Software development; Human–computer interaction; Programming language","score_opus":0.0318959053260117,"score_gpt":0.3304311199025112,"score_spread":0.29853521457649945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537911176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32672855,0.00022343356,0.6717445,0.00058622216,0.00024670252,0.00008115736,0.000007886144,0.00005984826,0.00032166037],"genre_scores_gemma":[0.92747015,0.000016444483,0.072123386,0.0003242995,0.000015247861,0.0000040776954,2.8943683e-7,0.000006093976,0.000040036866],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972105,0.0010257099,0.00061594247,0.0003444035,0.00049397413,0.00030945163],"domain_scores_gemma":[0.99832654,0.00060577743,0.00015401475,0.0004014829,0.00032912346,0.00018304375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063670417,0.00014537439,0.00024906136,0.00011625218,0.00023030386,0.0003905287,0.00046362466,0.0000796656,0.000096557436],"category_scores_gemma":[0.004704433,0.00013362967,0.00008246922,0.00031199554,0.00014311186,0.00094655005,0.00008969015,0.0005234445,0.0000075366925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011689505,0.00077435625,0.6923544,0.00020881962,0.0000985501,0.00006041231,0.06421291,0.00037320325,0.00054075377,0.15730958,0.0021046775,0.081845455],"study_design_scores_gemma":[0.0029005636,0.00070361997,0.17773154,0.00034356516,0.00002499272,0.0008626055,0.0026464267,0.002121191,0.0031366153,0.78948593,0.018826352,0.0012165913],"about_ca_topic_score_codex":0.000039253264,"about_ca_topic_score_gemma":0.00013019907,"teacher_disagreement_score":0.63217634,"about_ca_system_score_codex":0.0002610641,"about_ca_system_score_gemma":0.0003409733,"threshold_uncertainty_score":0.5631985},"labels":[],"label_agreement":null},{"id":"W1571880163","doi":"10.1023/a:1023764510838","title":"Towards a Software Change Classification System: A Rough Set Approach","year":2003,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Hydro","keywords":"Computer science; Rough set; Data mining; Software; Machine learning; Artificial intelligence; Benchmarking; Software deployment; Software engineering","score_opus":0.16672560978481335,"score_gpt":0.3304675520946508,"score_spread":0.16374194230983743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571880163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027266936,0.0007753653,0.9903188,0.0006056965,0.0010947769,0.00033089856,0.000022662985,0.00057795725,0.0035471905],"genre_scores_gemma":[0.44957152,0.00006031384,0.5488814,0.0008294678,0.00045979477,0.00007266949,0.000017857645,0.000028226288,0.00007871963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.996002,0.0010425451,0.0007895003,0.00059277716,0.0009186226,0.0006545635],"domain_scores_gemma":[0.9977118,0.00013938617,0.00054286607,0.00090822007,0.00033723682,0.0003604969],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031024753,0.00031346275,0.0004437839,0.0001686755,0.00064703135,0.0007230902,0.0012201312,0.00021732983,0.000024019648],"category_scores_gemma":[0.0006660706,0.0002545035,0.00026243692,0.00067061797,0.00007301889,0.0011495897,0.00013847767,0.0006161008,0.00008407017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053722186,0.00082315935,0.022313714,0.0009761323,0.00024658916,0.00016821992,0.019102456,0.00016336737,0.000029078907,0.5971699,0.010513186,0.34844047],"study_design_scores_gemma":[0.015240033,0.0026878472,0.36319995,0.0018426116,0.0004850162,0.031056322,0.027597958,0.039196026,0.00039635965,0.259499,0.24779238,0.011006472],"about_ca_topic_score_codex":0.00006146258,"about_ca_topic_score_gemma":0.0000032451699,"teacher_disagreement_score":0.44684482,"about_ca_system_score_codex":0.00032969657,"about_ca_system_score_gemma":0.00031101625,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W1967828228","doi":"10.1007/s11219-009-9082-y","title":"Improving design-pattern identification: a new approach and an exploratory study","year":2009,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Identification (biology); Computer science; Constraint (computer-aided design); False positive paradox; Data mining; Resource (disambiguation); Resource constraints; Machine learning; Engineering; Distributed computing","score_opus":0.09743104232199579,"score_gpt":0.355633719165051,"score_spread":0.2582026768430552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967828228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11960566,0.00018064903,0.8792096,0.00019186799,0.00020107623,0.00025488346,6.554234e-7,0.00035307312,0.0000025372167],"genre_scores_gemma":[0.8213772,0.000006876826,0.178004,0.00014966007,0.00034609775,0.0000092205355,0.0000011497006,0.00001620389,0.000089579546],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970349,0.0006945549,0.0005149773,0.0005413091,0.00080665597,0.0004075695],"domain_scores_gemma":[0.99783754,0.0004262479,0.00018761995,0.0008286879,0.00021034494,0.0005095694],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004675707,0.00019305796,0.00023458124,0.0002280286,0.0003459307,0.0012268121,0.0011777924,0.00006870763,0.000010435461],"category_scores_gemma":[0.0013759744,0.00018530844,0.000052411142,0.0004088125,0.000029419061,0.001744978,0.0001620848,0.0005622388,0.000020067466],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020103513,0.00071587146,0.028766437,0.00003388177,0.000047393685,0.00008970101,0.025949692,0.00069343956,0.0006933933,0.00018932731,0.0009850488,0.94181573],"study_design_scores_gemma":[0.0050059194,0.0028359191,0.9318355,0.000096258686,0.00006135779,0.0013570527,0.0071193413,0.03181051,0.0010868245,0.016554676,0.00017626303,0.0020603938],"about_ca_topic_score_codex":0.000024635428,"about_ca_topic_score_gemma":0.0000034812804,"teacher_disagreement_score":0.9397553,"about_ca_system_score_codex":0.00010643658,"about_ca_system_score_gemma":0.00031143785,"threshold_uncertainty_score":0.99981},"labels":[],"label_agreement":null},{"id":"W1968155288","doi":"10.1007/s11219-014-9250-6","title":"Empirical analysis of factors affecting confirmation bias levels of software engineers","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Confirmation bias; Software; Identification (biology); Metric (unit); Computer science; Software bug; Software engineering; Risk analysis (engineering); Engineering; Psychology; Social psychology; Operations management; Programming language; Business","score_opus":0.11496069501911305,"score_gpt":0.3726311614194243,"score_spread":0.25767046640031127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968155288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47020054,0.00003874399,0.5293165,0.00004514489,0.00019425114,0.000051837786,0.000016018479,0.00013356432,0.0000034331802],"genre_scores_gemma":[0.9077847,0.0000035167163,0.09209059,0.00002829721,0.00005548071,0.0000013184273,0.0000070931396,0.000017124761,0.000011853147],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996134,0.0007154867,0.0010713625,0.00032913798,0.0012954668,0.00045455876],"domain_scores_gemma":[0.9888532,0.008791779,0.0006679078,0.0007058204,0.0007094962,0.00027176834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046681613,0.00024063028,0.00077480695,0.0011599113,0.00014001461,0.00012690571,0.0010761364,0.00015831557,0.00006778838],"category_scores_gemma":[0.022730943,0.00021519621,0.0005154261,0.002415613,0.00009556127,0.0005261526,0.00019338557,0.000569017,0.0000043621385],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010464407,0.000099047225,0.94173044,0.00019675792,0.00091369654,0.0000036015156,0.0065981275,0.029693564,0.00043302518,0.00030097007,0.00013953238,0.019880766],"study_design_scores_gemma":[0.00038600923,0.00013730588,0.9836077,0.00007420144,0.00013441559,0.000014775489,0.00022297434,0.009626838,0.0050781583,0.00039143747,0.000054137832,0.0002720303],"about_ca_topic_score_codex":0.00005443571,"about_ca_topic_score_gemma":0.000007077355,"teacher_disagreement_score":0.4375842,"about_ca_system_score_codex":0.0001347486,"about_ca_system_score_gemma":0.00018961268,"threshold_uncertainty_score":0.985501},"labels":[],"label_agreement":null},{"id":"W1968405738","doi":"10.1007/s11219-006-9009-9","title":"A method to elicit architecturally sensitive usability requirements: its integration into a software development process","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Usability; Usability goals; Usability inspection; Usability engineering; Computer science; Software engineering; Cognitive walkthrough; Usability lab; Web usability; Heuristic evaluation; Component-based usability testing; Pluralistic walkthrough; Human–computer interaction","score_opus":0.06656961381106619,"score_gpt":0.39863685788634606,"score_spread":0.3320672440752799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968405738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28577623,0.000029104915,0.71210915,0.0010463208,0.00029272615,0.00043452063,0.000003971417,0.00028165506,0.000026315161],"genre_scores_gemma":[0.3081989,8.5205716e-7,0.6901049,0.0014691827,0.000115822506,0.000018087858,0.0000040043974,0.000017169983,0.00007106541],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9941247,0.0011674851,0.0015920418,0.0009117244,0.0013535457,0.00085047405],"domain_scores_gemma":[0.99503917,0.0012482473,0.0004963629,0.00066409545,0.0018867912,0.0006653121],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013901381,0.00043324145,0.0005249675,0.00034724464,0.00070113677,0.0005337415,0.001403796,0.0001807686,0.000041382507],"category_scores_gemma":[0.004485635,0.00037411487,0.00020382175,0.0009474858,0.0000745206,0.0012473742,0.00037402313,0.00089648104,0.000109160675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038316383,0.00038625355,0.003584388,0.00018733472,0.00013051913,0.000053242227,0.08989276,0.00065001444,0.0051210374,0.000620363,0.00016021653,0.8988307],"study_design_scores_gemma":[0.003111211,0.0021470052,0.1444183,0.0016842998,0.000091671645,0.0014797375,0.0077722585,0.0018389889,0.697002,0.12981702,0.0066727186,0.0039647855],"about_ca_topic_score_codex":0.00007813223,"about_ca_topic_score_gemma":0.0003607805,"teacher_disagreement_score":0.89486593,"about_ca_system_score_codex":0.00093535957,"about_ca_system_score_gemma":0.0007411796,"threshold_uncertainty_score":0.9998711},"labels":[],"label_agreement":null},{"id":"W1971146998","doi":"10.1007/s11219-015-9271-9","title":"On the use of design defect examples to detect model refactoring opportunities","year":2015,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Code refactoring; Computer science; Software bug; Set (abstract data type); Context (archaeology); Similarity (geometry); Data mining; Software; Machine learning; Reliability engineering; Artificial intelligence; Engineering; Programming language","score_opus":0.5757960133181265,"score_gpt":0.376091517068576,"score_spread":0.19970449624955044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971146998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14841102,0.000062104,0.8504799,0.0004910531,0.00022529978,0.00014583192,0.0000057088023,0.00017170479,0.000007348427],"genre_scores_gemma":[0.5027377,0.000015723754,0.4966143,0.00032428783,0.00007797565,0.000015891326,4.2584313e-7,0.000027563088,0.00018610545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996961,0.0007252058,0.00044849332,0.00024874377,0.001177189,0.00043935538],"domain_scores_gemma":[0.9901539,0.007831263,0.00016179177,0.0008344755,0.00055477326,0.00046377568],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004921153,0.00018291254,0.00024830858,0.0002504717,0.00018323238,0.00039154777,0.0012570753,0.000065633125,0.000008001637],"category_scores_gemma":[0.021151133,0.00012855661,0.0001432411,0.0003467142,0.00005641729,0.0005673623,0.00030110596,0.0004900681,0.000014885875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016733953,0.00008364884,0.003221072,0.000054050088,0.00015845177,0.00008262026,0.0076040598,0.8834888,0.00055305986,0.017504154,0.02121721,0.06586556],"study_design_scores_gemma":[0.0062637758,0.009162107,0.042142265,0.0029109495,0.00016845748,0.001719555,0.0027878426,0.3331803,0.06014803,0.5067683,0.028093541,0.006654894],"about_ca_topic_score_codex":0.000053729604,"about_ca_topic_score_gemma":0.0000034397535,"teacher_disagreement_score":0.55030847,"about_ca_system_score_codex":0.00020894018,"about_ca_system_score_gemma":0.00055773125,"threshold_uncertainty_score":0.9870941},"labels":[],"label_agreement":null},{"id":"W1979334159","doi":"10.1007/s11219-007-9024-5","title":"The applicability analysis of ISO/IEC 9126 series of standards in telecom sector: the example of softswitch category of software","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Softswitch; Software; Quality (philosophy); Computer science; Grid; Code (set theory); Telecommunications; Engineering; Software engineering; Operating system; Telephony; Mathematics","score_opus":0.030915266403321102,"score_gpt":0.3234580157601795,"score_spread":0.2925427493568584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979334159","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25673935,0.00082146766,0.74188226,0.00013016837,0.00011819256,0.00016083269,0.00006440151,0.000069338406,0.000013950847],"genre_scores_gemma":[0.9165398,0.00019497807,0.08317912,0.000022128872,0.00003102635,0.00000682559,0.0000027889735,0.000013589069,0.000009733141],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958437,0.00050971255,0.0018101507,0.00029701547,0.0011594573,0.00037994824],"domain_scores_gemma":[0.9897682,0.0060685524,0.0017048313,0.0013149035,0.0010523435,0.00009113385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016184894,0.00021496485,0.0007836148,0.0003352017,0.00017296388,0.000055394397,0.0016748491,0.00013917743,0.000030533418],"category_scores_gemma":[0.0033545904,0.00013924997,0.00042206253,0.0020955107,0.00039880257,0.0004390536,0.00027848544,0.0005766902,1.4464453e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066840404,0.0006068287,0.7866846,0.00075534265,0.0016680552,0.000011026557,0.011320488,0.0042986707,0.0013513326,0.017507749,0.00054313696,0.17458437],"study_design_scores_gemma":[0.00082451396,0.00077674066,0.9115099,0.00019833517,0.0004515625,0.00006695563,0.0014001984,0.0007382472,0.030602492,0.04421721,0.008603259,0.0006106197],"about_ca_topic_score_codex":0.0025703388,"about_ca_topic_score_gemma":0.0012195329,"teacher_disagreement_score":0.65980047,"about_ca_system_score_codex":0.0001278441,"about_ca_system_score_gemma":0.00042046918,"threshold_uncertainty_score":0.56784487},"labels":[],"label_agreement":null},{"id":"W1986024814","doi":"10.1007/s11219-013-9203-5","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2013,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Manual testing; Code coverage; Regression testing; Test (biology); Software engineering; Graphical user interface testing; Reliability engineering; Test harness; Programming language; Software; Engineering; Software development; User interface; Software construction; Machine learning","score_opus":0.044124431323995406,"score_gpt":0.31495280582406704,"score_spread":0.27082837450007163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986024814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3127856,0.00047403152,0.67092526,0.0015607802,0.00087923126,0.00029020954,0.000027683103,0.012498986,0.00055820646],"genre_scores_gemma":[0.4497939,0.000019324418,0.5485925,0.00082742807,0.00040897776,0.000022634535,0.00000808861,0.000029957211,0.0002971634],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970093,0.00037417235,0.00084109587,0.00053961703,0.00062447897,0.0006113457],"domain_scores_gemma":[0.98949397,0.007897105,0.00056721526,0.0009827893,0.00063233665,0.00042659117],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013425177,0.00031027693,0.00041342943,0.0001606392,0.00067105354,0.0012382091,0.0012782876,0.00015765082,0.0002964768],"category_scores_gemma":[0.019695498,0.0002831947,0.00018551166,0.00044463895,0.00010860752,0.0010908463,0.00035026393,0.00070391706,0.00032976782],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058126834,0.0002630132,0.6208603,0.000027297589,0.000045634595,0.00020217868,0.0011215988,0.000007231225,0.00035243883,0.00020916873,0.13005118,0.24685417],"study_design_scores_gemma":[0.001004533,0.0006206285,0.5185486,0.000688762,0.000039470437,0.002705282,0.00012720657,0.0027217492,0.0013061396,0.46745294,0.003299395,0.0014852764],"about_ca_topic_score_codex":0.0051927213,"about_ca_topic_score_gemma":0.0000750686,"teacher_disagreement_score":0.46724376,"about_ca_system_score_codex":0.00013804533,"about_ca_system_score_gemma":0.0002343179,"threshold_uncertainty_score":0.99996203},"labels":[],"label_agreement":null},{"id":"W2001599472","doi":"10.1007/s11219-010-9128-1","title":"An industrial case study of classifier ensembles for locating software defects","year":2011,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Sabancı Üniversitesi","keywords":"Computer science; Software; Classifier (UML); False alarm; Software quality; Data mining; Domain (mathematical analysis); Ensemble learning; Embedded software; Machine learning; Artificial intelligence; Reliability engineering; Software development; Engineering; Operating system","score_opus":0.2236840213549557,"score_gpt":0.3779922822970453,"score_spread":0.1543082609420896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001599472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53016883,0.000041550215,0.4687733,0.000007229631,0.00046662978,0.00032942,0.000006097092,0.00020423373,0.000002689392],"genre_scores_gemma":[0.85021627,0.0000015510692,0.14936426,0.000025467194,0.00030004635,0.00003866416,0.0000016431311,0.000035989502,0.000016119111],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99634755,0.00067299814,0.0009515778,0.0005312333,0.00083233084,0.0006642903],"domain_scores_gemma":[0.9945363,0.002716269,0.00046133998,0.0010220817,0.0008179394,0.00044608832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003925539,0.000281374,0.00047551273,0.00036103546,0.00047189134,0.0002332665,0.0013975484,0.00020703214,0.000026586407],"category_scores_gemma":[0.007430844,0.00026227866,0.00018085906,0.0005939433,0.00007773716,0.000916869,0.00024388896,0.00079166953,0.0000044090284],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019791043,0.0025482168,0.74652004,0.00021028763,0.0002965702,0.0023681917,0.04157648,0.00067271496,0.00026111043,0.0005468196,0.0007777147,0.20402394],"study_design_scores_gemma":[0.069843024,0.06352174,0.54103845,0.002235792,0.0009475328,0.07507647,0.14689264,0.012488931,0.030822244,0.043940604,0.001575097,0.011617477],"about_ca_topic_score_codex":0.00049312337,"about_ca_topic_score_gemma":0.000121273224,"teacher_disagreement_score":0.3200474,"about_ca_system_score_codex":0.00013369702,"about_ca_system_score_gemma":0.00047713445,"threshold_uncertainty_score":0.99998295},"labels":[],"label_agreement":null},{"id":"W2001932992","doi":"10.1007/s11219-010-9127-2","title":"Assessing the maintainability of software product line feature models using structural metrics","year":2010,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; National Research Council Canada","funders":"","keywords":"Maintainability; Software product line; Feature model; Software metric; Computer science; Software; Data mining; Software quality; Feature (linguistics); Reliability engineering; Set (abstract data type); Software engineering; Software development; Engineering","score_opus":0.11787304923974923,"score_gpt":0.4112353565501069,"score_spread":0.2933623073103577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001932992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23238903,0.00044292305,0.76428133,0.00054410956,0.0018068432,0.00018621242,0.0000085858155,0.00033871882,0.000002222663],"genre_scores_gemma":[0.3230781,0.000007059948,0.6765154,0.00006986452,0.00028911023,0.0000025257973,0.000001451705,0.00002228621,0.000014180795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99593633,0.0010001907,0.0008600627,0.00056887564,0.0009779107,0.00065664673],"domain_scores_gemma":[0.9918966,0.004127741,0.0009013147,0.0016077311,0.0012567674,0.00020981133],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007434753,0.0003698261,0.00058903807,0.0002547047,0.0006951986,0.00053648563,0.002140133,0.0002092455,0.0000077780005],"category_scores_gemma":[0.030633708,0.0002550683,0.00029347616,0.0012533161,0.00034953185,0.0026217862,0.00061280356,0.002463571,5.0576676e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037813497,0.00011586065,0.025040073,0.000406257,0.00017772855,0.00005615183,0.003165705,0.65925175,0.0066310735,0.011873497,0.00013264317,0.29311144],"study_design_scores_gemma":[0.0007655829,0.00013923772,0.03856783,0.00012949968,0.00007912035,0.0018066053,0.0006376865,0.050279617,0.008796374,0.89749587,0.00019327231,0.0011093174],"about_ca_topic_score_codex":0.000028578044,"about_ca_topic_score_gemma":0.000006720199,"teacher_disagreement_score":0.8856224,"about_ca_system_score_codex":0.00022158041,"about_ca_system_score_gemma":0.00058826956,"threshold_uncertainty_score":0.99999017},"labels":[],"label_agreement":null},{"id":"W2015215117","doi":"10.1007/s11219-006-9218-2","title":"On evaluating the layout of UML diagrams for program comprehension","year":2006,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Class diagram; Sequence diagram; Applications of UML; Story-driven modeling; UML tool; Computer science; Unified Modeling Language; Communication diagram; Programming language; Activity diagram; Software engineering; Flowchart; Readability; Class (philosophy); Program comprehension; Use Case Diagram; Object Constraint Language; Software; Software system; Artificial intelligence","score_opus":0.08799721980182837,"score_gpt":0.4182070965023177,"score_spread":0.3302098767004893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015215117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41951665,0.00015477728,0.578863,0.0004886228,0.00035021684,0.00039883194,0.0000044039707,0.00021064233,0.000012827152],"genre_scores_gemma":[0.8164554,0.0000021190076,0.18303704,0.00007146276,0.00027390954,0.000055803554,0.0000045871957,0.000019200555,0.00008046856],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99735886,0.00034245776,0.00055601075,0.00025631973,0.0010563489,0.00042999326],"domain_scores_gemma":[0.9933971,0.005144774,0.00026679528,0.00057504757,0.00052550616,0.00009078209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036864528,0.000152654,0.00023478329,0.000104039274,0.00034299074,0.00024163647,0.001020319,0.00007053191,0.000008183885],"category_scores_gemma":[0.0038968776,0.00010304916,0.00020439323,0.0003566206,0.00008425364,0.00018817587,0.00015123446,0.00044209202,0.0000080523105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013398653,0.000735378,0.049057845,0.00022763926,0.000081656566,0.000009013556,0.0008028892,0.035489824,0.00072853855,0.031276032,0.004958478,0.8764987],"study_design_scores_gemma":[0.004485864,0.006264903,0.66344875,0.0006544281,0.00005073468,0.00021001388,0.0001227296,0.16360311,0.0029439006,0.15372944,0.0034239537,0.0010621345],"about_ca_topic_score_codex":0.000044402826,"about_ca_topic_score_gemma":0.0000064817214,"teacher_disagreement_score":0.8754366,"about_ca_system_score_codex":0.00008575178,"about_ca_system_score_gemma":0.00014511668,"threshold_uncertainty_score":0.4665208},"labels":[],"label_agreement":null},{"id":"W2015762629","doi":"10.1023/b:sqjo.0000013356.15791.3d","title":"Requirements for Maintaining Web Access for Hearing-Impaired Individuals","year":2004,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Digital Accessibility for Disabilities","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hearing impaired; Computer science; Dream; Sight; Visually impaired; Interface (matter); User interface; Human–computer interaction; World Wide Web; Multimedia; Audiology; Operating system; Psychology; Medicine","score_opus":0.2112760787145806,"score_gpt":0.4694726119693898,"score_spread":0.2581965332548092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015762629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9396341,0.00010597525,0.04852872,0.0058826716,0.0012322178,0.0016916153,0.0003917431,0.00035456964,0.00217839],"genre_scores_gemma":[0.98210853,0.000011975121,0.015755998,0.0006860465,0.00076391647,0.00013728841,0.000029090164,0.000036896996,0.00047025626],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658406,0.00024291889,0.0009452299,0.0003968492,0.0009000309,0.00093090994],"domain_scores_gemma":[0.99709755,0.0011818368,0.00049486896,0.00027330214,0.00055620156,0.00039623256],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007721369,0.00021911094,0.00040657606,0.00013551637,0.0018345877,0.0018232804,0.0010510149,0.00016385262,0.00010431328],"category_scores_gemma":[0.011822681,0.0002149688,0.00044850179,0.00027925242,0.0005181899,0.0028693287,0.0001665268,0.00023058617,0.000008916386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005685096,0.0012794473,0.6469088,0.0005770807,0.00047070565,0.000005034498,0.0533971,0.0005940362,0.000052028543,0.22603357,0.004735244,0.065378405],"study_design_scores_gemma":[0.0026009285,0.000270712,0.014785489,0.00019403793,0.00004310202,0.0000054799216,0.016462633,0.0000028317288,0.00011215742,0.947033,0.018055571,0.00043408203],"about_ca_topic_score_codex":0.00046441203,"about_ca_topic_score_gemma":0.001404644,"teacher_disagreement_score":0.7209994,"about_ca_system_score_codex":0.0009154307,"about_ca_system_score_gemma":0.0014748859,"threshold_uncertainty_score":0.99946487},"labels":[],"label_agreement":null},{"id":"W2021780242","doi":"10.1007/s11219-011-9153-8","title":"AoURN-based modeling and analysis of software product lines","year":2011,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Software product line; Feature model; Software engineering; Domain engineering; Domain (mathematical analysis); Computer science; Domain analysis; Feature-oriented domain analysis; Feature (linguistics); Notation; Product (mathematics); Systems engineering; Software; Model-driven architecture; Model transformation; Software development; Engineering; Programming language; Artificial intelligence; Software construction","score_opus":0.1482975576947659,"score_gpt":0.3486422211534545,"score_spread":0.2003446634586886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021780242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07696815,0.00097437826,0.92114234,0.000077678604,0.00032926153,0.000080273756,0.000010840729,0.00041251112,0.000004573316],"genre_scores_gemma":[0.1770522,0.000042563774,0.82274497,0.000071276634,0.000054350556,0.000004064989,0.0000026453458,0.000015935182,0.000011973694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973505,0.0004662917,0.0008477188,0.00045745992,0.00048438073,0.0003936136],"domain_scores_gemma":[0.99699676,0.001040309,0.00046100837,0.00076888484,0.00053879636,0.00019426475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029183207,0.00025824748,0.00068067684,0.0006671568,0.00019022453,0.00008106392,0.0008837745,0.00009348449,0.000016637317],"category_scores_gemma":[0.0065439125,0.00022664339,0.0002837258,0.0012290728,0.000109991386,0.0006374948,0.00020448674,0.0004437562,0.0000013169956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000769576,0.00019738417,0.08551835,0.00023958359,0.0010912206,0.00004570931,0.0050085094,0.75231457,0.00033641772,0.0013906875,0.000031438503,0.15374915],"study_design_scores_gemma":[0.002944484,0.000860368,0.20700452,0.0006081559,0.002129638,0.00035763782,0.0007444761,0.5357578,0.013844273,0.23210637,0.00015530924,0.0034869711],"about_ca_topic_score_codex":0.000034653985,"about_ca_topic_score_gemma":0.0000067216984,"teacher_disagreement_score":0.23071569,"about_ca_system_score_codex":0.000050758666,"about_ca_system_score_gemma":0.00015681023,"threshold_uncertainty_score":0.9242249},"labels":[],"label_agreement":null},{"id":"W2022628966","doi":"10.1007/s11219-006-9010-3","title":"Measuring size, complexity, and coupling of hypergraph abstractions of software: An information-theory approach","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; Mississippi State University; National Science Foundation","keywords":"Computer science; Software metric; Software sizing; Theoretical computer science; Hypergraph; Software; Data mining; Software development; Software quality; Software construction; Programming language; Mathematics","score_opus":0.07791100068699204,"score_gpt":0.32054010421443907,"score_spread":0.24262910352744704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022628966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.349833,0.00013671094,0.6496003,0.000023224015,0.0001541815,0.00008481683,0.000009046966,0.00013169186,0.000026986301],"genre_scores_gemma":[0.67294836,0.000017004091,0.32694215,0.000024204948,0.000047950474,0.0000018355317,0.0000030592207,0.0000101434325,0.000005318293],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972434,0.00009509905,0.001023945,0.00020766402,0.0010123643,0.00041754823],"domain_scores_gemma":[0.99442893,0.0034694483,0.00049449195,0.0005286477,0.0007623546,0.00031613302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077458904,0.00017786282,0.00035352798,0.00043028028,0.00028138168,0.00016173109,0.0008170361,0.00011666016,0.000015156551],"category_scores_gemma":[0.005116115,0.00017705242,0.00012216823,0.00053811906,0.00026214498,0.0018867081,0.00021010045,0.00062471745,0.0000027974243],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037117006,0.0013464042,0.694329,0.00230142,0.0006390602,0.00003163246,0.016066875,0.03054337,0.003807103,0.07504931,0.00026014258,0.1752545],"study_design_scores_gemma":[0.0012002473,0.00023080187,0.95790225,0.00014837508,0.000026303576,0.00055771397,0.0010750699,0.0020345969,0.003633794,0.032543242,0.00013310825,0.00051448814],"about_ca_topic_score_codex":0.000052154548,"about_ca_topic_score_gemma":0.000006814317,"teacher_disagreement_score":0.32311532,"about_ca_system_score_codex":0.00007674168,"about_ca_system_score_gemma":0.00019411134,"threshold_uncertainty_score":0.7219988},"labels":[],"label_agreement":null},{"id":"W2025855180","doi":"10.1007/s11219-009-9088-5","title":"An organizational maturity model of software product line engineering","year":2009,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Software product line; Capability Maturity Model; Software Engineering Process Group; Service Integration Maturity Model; Product management; Product engineering; Software quality management; Software development; Engineering; Process management; Software engineering; Systems engineering; Software development process; Product (mathematics); New product development; Computer science; Knowledge management; Software; Product design; Business; Marketing","score_opus":0.029049896642323363,"score_gpt":0.3048473787423666,"score_spread":0.27579748210004323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025855180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029277215,0.00026633524,0.9683663,0.0006690099,0.00026449113,0.00009595634,0.000014311027,0.0010400373,0.000006342192],"genre_scores_gemma":[0.35697013,0.000032462398,0.64261276,0.00016435244,0.00018442825,0.0000013026097,0.0000066060566,0.000014375297,0.000013592717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998017,0.00010652754,0.0006173477,0.000335671,0.00060184236,0.00032159148],"domain_scores_gemma":[0.9979355,0.0002585019,0.000352899,0.0006925045,0.0005421983,0.00021842473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015043021,0.00022308156,0.00030611004,0.00018642766,0.0001531683,0.00022295737,0.0011377871,0.000107443746,0.000021175923],"category_scores_gemma":[0.0022233215,0.00021385624,0.00010475935,0.0004868187,0.000021838798,0.0015747689,0.00008452978,0.0005742177,0.000003245964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011581478,0.0016477016,0.015449579,0.00040392773,0.00018532372,0.0000762589,0.003816595,0.7097818,0.017130459,0.08667268,0.00287873,0.16184108],"study_design_scores_gemma":[0.0019292912,0.0019157944,0.06265328,0.000550375,0.00011180292,0.0018518404,0.000048567894,0.58503175,0.056858707,0.28372204,0.0021869272,0.0031396504],"about_ca_topic_score_codex":0.000005898482,"about_ca_topic_score_gemma":5.664475e-7,"teacher_disagreement_score":0.32769293,"about_ca_system_score_codex":0.00007693525,"about_ca_system_score_gemma":0.00024462407,"threshold_uncertainty_score":0.87208045},"labels":[],"label_agreement":null},{"id":"W2029160271","doi":"10.1007/s11219-014-9232-8","title":"Toward a mature industrial practice of software test automation","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Automation; Software engineering; Test (biology); Software; Computer science; Software testing; Engineering; Operating system","score_opus":0.06356689489556629,"score_gpt":0.33149529574143893,"score_spread":0.26792840084587266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029160271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032039038,0.00011760859,0.9872405,0.0021752433,0.00074462756,0.00014529514,0.0000105847075,0.006179637,0.00018259777],"genre_scores_gemma":[0.22488697,0.0000101908645,0.77372146,0.00083148445,0.00047427748,0.0000074774134,0.0000052707524,0.000022484483,0.000040383868],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996466,0.00081374793,0.0009463619,0.00038787074,0.00097443984,0.00041159109],"domain_scores_gemma":[0.9900433,0.006654607,0.0012804619,0.00083796226,0.00093952514,0.00024414994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050344835,0.0002580498,0.00043935273,0.00024269748,0.00028985328,0.00037969477,0.0012705697,0.00030630938,0.000018360324],"category_scores_gemma":[0.071555875,0.00023111838,0.00019293587,0.00061922264,0.00009611782,0.0012199879,0.00027405488,0.0009615826,0.000021916108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009799298,0.0007801958,0.07028929,0.00025280126,0.00012249472,0.000065520144,0.004522687,0.00015220852,0.00015580788,0.008590733,0.120462395,0.79450786],"study_design_scores_gemma":[0.007509769,0.0041968464,0.052589606,0.0030018825,0.00030433387,0.00919276,0.0003438896,0.010624661,0.005369725,0.81695306,0.08632689,0.003586546],"about_ca_topic_score_codex":0.00007159421,"about_ca_topic_score_gemma":0.0000012362198,"teacher_disagreement_score":0.80836236,"about_ca_system_score_codex":0.00011553968,"about_ca_system_score_gemma":0.00033308417,"threshold_uncertainty_score":0.9424734},"labels":[],"label_agreement":null},{"id":"W2029277954","doi":"10.1007/s11219-014-9230-x","title":"Predicting defective modules in different test phases","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Reliability engineering; Computer science; Predictive modelling; Software; Data mining; Machine learning; Engineering; Programming language","score_opus":0.028114770166436563,"score_gpt":0.31264121370854725,"score_spread":0.2845264435421107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029277954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47622675,0.00007991007,0.52293724,0.00017278771,0.00026126837,0.00006412946,0.000002687952,0.00022836983,0.00002686639],"genre_scores_gemma":[0.9752147,0.000011208054,0.024291316,0.000070143724,0.0003423236,0.0000122597985,0.0000011840688,0.000017495851,0.000039365816],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974374,0.00039933203,0.0004949472,0.0003686375,0.0007339068,0.0005657681],"domain_scores_gemma":[0.99137753,0.007488403,0.00015805876,0.00051436934,0.00019330299,0.00026831694],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021851123,0.00020691036,0.00030638836,0.00029661792,0.00020609064,0.0003368088,0.0009748182,0.000083186475,0.00001972346],"category_scores_gemma":[0.02058557,0.00017213584,0.0001224646,0.000410061,0.000055017932,0.0005254085,0.00027016187,0.000795216,0.000016791644],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058583273,0.00017624613,0.955646,0.000029007599,0.000015552605,0.000020422289,0.0007374058,0.00082912436,0.00016720711,0.00059934426,0.00015599614,0.041617878],"study_design_scores_gemma":[0.0008814159,0.00022679326,0.9770135,0.00016083888,0.000003638562,0.00014979196,0.00005194082,0.009707811,0.0008735133,0.010444125,0.00019807846,0.0002884975],"about_ca_topic_score_codex":0.000055196095,"about_ca_topic_score_gemma":0.00003182158,"teacher_disagreement_score":0.49898797,"about_ca_system_score_codex":0.00024506563,"about_ca_system_score_gemma":0.00007455175,"threshold_uncertainty_score":0.98766446},"labels":[],"label_agreement":null},{"id":"W2044659433","doi":"10.1023/b:sqjo.0000013359.71560.47","title":"Multi-Project Management in Software Engineering Using Simulation Modelling","year":2004,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Software project management; Computer science; Project management; Interdependence; Systems engineering; Project management triangle; Software; Software development; Engineering; Software construction","score_opus":0.11692953807586136,"score_gpt":0.3729647007733453,"score_spread":0.25603516269748394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044659433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0316211,0.00033394332,0.96657455,0.000043168882,0.00043274913,0.00020335615,0.0000019210133,0.00078620744,0.000002987283],"genre_scores_gemma":[0.17720556,0.000056221565,0.82256067,0.00005851695,0.00007832225,0.0000063760644,0.0000014033436,0.00002458423,0.000008308593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980154,0.00009643077,0.0006192272,0.00036017215,0.0004543028,0.00045444662],"domain_scores_gemma":[0.99877805,0.00034274627,0.00023794555,0.00042679356,0.00010657522,0.000107883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014423936,0.00024205697,0.0002518931,0.00047011673,0.00017746893,0.0003549128,0.00067693996,0.000118217606,0.0000035665287],"category_scores_gemma":[0.0004292991,0.0002525142,0.00012446365,0.0006493354,0.000013230179,0.00146698,0.00019908459,0.0005928114,0.0000048428706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069195867,0.00006040797,0.00090009643,0.000059745733,0.000025629164,0.000093066585,0.000596613,0.99156064,0.00001763409,0.00077447895,0.0000032320113,0.005901568],"study_design_scores_gemma":[0.00094405696,0.00004094182,0.0016253947,0.0002929202,0.000015046393,0.00014086686,0.000048228874,0.99231964,0.00009571764,0.0032970135,0.0007086981,0.00047147172],"about_ca_topic_score_codex":0.00015459502,"about_ca_topic_score_gemma":0.0000042960405,"teacher_disagreement_score":0.14558446,"about_ca_system_score_codex":0.00042249094,"about_ca_system_score_gemma":0.00010188192,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W2047310403","doi":"10.1007/s11219-012-9185-8","title":"Foreword to the special issue on quality engineering for software product lines","year":2012,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Alberta Innovates - Technology Futures","keywords":"Software product line; Domain engineering; Software engineering; Software development; Software quality management; Social software engineering; Computer science; Software construction; Software quality control; Product engineering; Software quality analyst; Software quality; Product (mathematics); Systems engineering; Engineering; Software; Product design","score_opus":0.09735351601825751,"score_gpt":0.37962411800898177,"score_spread":0.2822706019907243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047310403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054955864,0.00042141505,0.980439,0.0036655138,0.008453419,0.0006095156,0.00005033049,0.00085557747,0.000009612111],"genre_scores_gemma":[0.0050355117,0.000015661632,0.96748364,0.0010364803,0.025857324,0.000097880584,0.0000048381307,0.00006000115,0.00040868451],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960986,0.0005121124,0.0009145947,0.00053737167,0.000786046,0.0011512878],"domain_scores_gemma":[0.9921973,0.005325048,0.00036025455,0.0012385508,0.0004245209,0.00045434816],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0077790706,0.0004434968,0.00056465203,0.00020779371,0.00056075153,0.00023939078,0.0018319935,0.00013194741,0.000025964126],"category_scores_gemma":[0.0357344,0.00032684853,0.00032948182,0.0005850951,0.000051472376,0.00096968934,0.0003745593,0.000816052,0.000081669095],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023786597,0.00029950112,0.00633547,0.00035830084,0.00019303086,0.000009177199,0.008151645,0.15995581,0.00022906056,0.017872604,0.047819916,0.7585376],"study_design_scores_gemma":[0.0015872187,0.0007608202,0.07837372,0.00035408224,0.000060191964,0.00034186602,0.00040801486,0.00043693453,0.0066355695,0.026286112,0.8821768,0.0025786248],"about_ca_topic_score_codex":0.0000069077555,"about_ca_topic_score_gemma":0.000005745779,"teacher_disagreement_score":0.8343569,"about_ca_system_score_codex":0.0002476964,"about_ca_system_score_gemma":0.0001152874,"threshold_uncertainty_score":0.99991834},"labels":[],"label_agreement":null},{"id":"W2055986279","doi":"10.1007/s11219-014-9233-7","title":"Prioritizing code-smells correction tasks using chemical reaction optimization","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Code refactoring; Code smell; Computer science; Metaheuristic; Code (set theory); Search-based software engineering; Software; Software engineering; Software quality; Software design; Programming language; Artificial intelligence; Software development","score_opus":0.04201576491452648,"score_gpt":0.32948212129263316,"score_spread":0.2874663563781067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055986279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08397571,0.000044238073,0.9129728,0.00014687653,0.0022777298,0.00008847454,0.0000012110305,0.00046290958,0.000030066596],"genre_scores_gemma":[0.43305683,0.000018779754,0.5659333,0.00010566604,0.0007770212,0.0000035632884,0.0000059854433,0.00003326248,0.00006563835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975289,0.0003626486,0.00051485264,0.00036785344,0.0007844833,0.00044124984],"domain_scores_gemma":[0.9974978,0.0011328094,0.000254052,0.00044930974,0.00042065996,0.00024534212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654252,0.00017709778,0.0002337297,0.00022545585,0.0003359096,0.00045885853,0.0005562068,0.00015904063,0.000011122956],"category_scores_gemma":[0.0055921297,0.00018670314,0.00011460537,0.0005210901,0.000044342698,0.001008295,0.00014799333,0.000771299,0.000020078263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012421631,0.00044475784,0.04035271,0.00025904633,0.0001789774,0.00006599644,0.002965633,0.3840916,0.13045552,0.0018950704,0.0036327117,0.43553376],"study_design_scores_gemma":[0.0009167182,0.00012416524,0.008875567,0.00022982499,0.000019689709,0.0014945604,0.00006314544,0.97736764,0.007132694,0.0014095375,0.0017297345,0.0006367012],"about_ca_topic_score_codex":0.000038735077,"about_ca_topic_score_gemma":0.0000012858463,"teacher_disagreement_score":0.5932761,"about_ca_system_score_codex":0.00047520315,"about_ca_system_score_gemma":0.0001639666,"threshold_uncertainty_score":0.7613533},"labels":[],"label_agreement":null},{"id":"W2056306711","doi":"10.1007/s11219-012-9180-0","title":"Influence of confirmation biases of developers on software quality: an empirical study","year":2012,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Assertion; Empirical research; Software quality; Confirmation bias; Software metric; Software development; Cognitive bias; Context (archaeology); Empirical evidence; Software bug; Software; Metric (unit); Quality (philosophy); Data science; Cognition; Software engineering; Psychology; Social psychology; Statistics; Engineering; Operations management; Mathematics; Programming language","score_opus":0.14038679657632722,"score_gpt":0.43106620055480366,"score_spread":0.29067940397847647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056306711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8023817,0.00009313579,0.1967677,0.00008356012,0.00022858968,0.00023106529,0.000014882467,0.00019463555,0.000004723076],"genre_scores_gemma":[0.951821,0.0000076811475,0.04787195,0.00014344938,0.000103769504,0.000011195628,0.0000044656645,0.000022565348,0.000013873433],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99428433,0.0014595954,0.0013736836,0.000351362,0.0019036755,0.0006273479],"domain_scores_gemma":[0.99277884,0.00408783,0.000644152,0.0009740163,0.0010277048,0.00048743119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069493055,0.000273748,0.0005860626,0.00045274294,0.00020205555,0.00011760445,0.0014343333,0.00013721509,0.000029960962],"category_scores_gemma":[0.020114832,0.00024331847,0.00014696011,0.00090285414,0.00015182456,0.0016799172,0.000276834,0.00065966643,0.000023270848],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005803139,0.0010789182,0.9710569,0.00010173724,0.000080695296,0.0000070844953,0.010604597,0.005532344,0.00017948041,0.00035126403,0.0001258972,0.010823089],"study_design_scores_gemma":[0.00070393994,0.0006565462,0.995138,0.00013646114,0.000011703297,0.00004968108,0.00081785274,0.00006608856,0.0017616026,0.0002589419,0.00009649785,0.0003026887],"about_ca_topic_score_codex":0.00014199306,"about_ca_topic_score_gemma":0.000010552204,"teacher_disagreement_score":0.14943935,"about_ca_system_score_codex":0.00017773535,"about_ca_system_score_gemma":0.00046497033,"threshold_uncertainty_score":0.9922239},"labels":[],"label_agreement":null},{"id":"W2063462200","doi":"10.1007/s11219-012-9186-7","title":"Mining the impact of evolution categories on object-oriented metrics","year":2012,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cohesion (chemistry); Software evolution; Software; Computer science; Recall; Software metric; Software development; Data mining; Software engineering; Software construction; Programming language; Psychology; Cognitive psychology","score_opus":0.04837848210346001,"score_gpt":0.35755459381978144,"score_spread":0.3091761117163214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063462200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41203052,0.00054476596,0.5865371,0.00008340062,0.00060355285,0.00006559098,0.000003410006,0.000102688165,0.000028941351],"genre_scores_gemma":[0.9803008,0.0000112086445,0.019327158,0.000018646067,0.00027734583,0.000004148386,0.000001290946,0.000013603709,0.000045826986],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973299,0.0004233884,0.00045105576,0.00016582078,0.0010248332,0.00060502987],"domain_scores_gemma":[0.9951053,0.0033198567,0.00027583522,0.00061066315,0.000435019,0.0002533182],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003984725,0.00016857137,0.00023197968,0.00036738426,0.00030410488,0.00013185336,0.0008971909,0.000081127524,0.000022095492],"category_scores_gemma":[0.010183023,0.000107176595,0.00023678657,0.0015224118,0.00008873274,0.0006984471,0.0001875841,0.0005808052,0.000020293623],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005387477,0.00027891752,0.9515404,0.00003761635,0.00019629911,0.000007053321,0.007647877,0.0029316791,0.00025109333,0.014059903,0.0035008301,0.019494446],"study_design_scores_gemma":[0.0004469933,0.000384546,0.99449956,0.00004819665,0.0000106983125,0.00018259164,0.0003875309,0.0008005732,0.0010264191,0.0016931883,0.00027096644,0.00024874322],"about_ca_topic_score_codex":0.00015772475,"about_ca_topic_score_gemma":0.0000014498482,"teacher_disagreement_score":0.56827027,"about_ca_system_score_codex":0.0005166817,"about_ca_system_score_gemma":0.00032444583,"threshold_uncertainty_score":0.99815464},"labels":[],"label_agreement":null},{"id":"W2064132582","doi":"10.1007/s11219-010-9124-5","title":"Identification and analysis of attributes and base measures within ISO 9126","year":2010,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Measure (data warehouse); Software; Identification (biology); Task (project management); Software quality; Quality (philosophy); Reliability engineering; Set (abstract data type); Base (topology); Engineering; Computer science; Process (computing); Data mining; Systems engineering; Mathematics; Software development; Programming language","score_opus":0.03959637261930754,"score_gpt":0.3236045379643921,"score_spread":0.28400816534508455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064132582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5374719,0.00019845055,0.46180156,0.00027276506,0.00015338401,0.000035728437,0.0000105342215,0.000054863704,8.228877e-7],"genre_scores_gemma":[0.9541029,0.000032807653,0.045747057,0.00002808156,0.000042729796,0.000002623091,0.0000029750795,0.0000070146157,0.000033838714],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981958,0.00018558561,0.0005038261,0.00027736995,0.000630076,0.00020734195],"domain_scores_gemma":[0.99736476,0.0012449338,0.0002510394,0.00047173534,0.00044964286,0.00021786818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042799455,0.00011332642,0.00027755217,0.000477472,0.00019078393,0.0003382629,0.0004643442,0.00008126506,0.000014483222],"category_scores_gemma":[0.00645112,0.00010152554,0.00008514413,0.0008872362,0.00013188737,0.00048639337,0.00015699798,0.00049654365,0.0000017890021],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012649501,0.000065085995,0.9429852,0.000066317836,0.00046106757,0.000011022778,0.0021728305,0.00031618387,0.019843705,0.0033522486,0.00018694265,0.030526761],"study_design_scores_gemma":[0.00024881348,0.000036686695,0.98596364,0.00001707962,0.000097539785,0.000073809126,0.000054982273,0.0054485938,0.004867597,0.0029568297,0.000066373825,0.00016806724],"about_ca_topic_score_codex":0.000045471777,"about_ca_topic_score_gemma":0.000053498024,"teacher_disagreement_score":0.41663098,"about_ca_system_score_codex":0.000021003969,"about_ca_system_score_gemma":0.000093408475,"threshold_uncertainty_score":0.7723059},"labels":[],"label_agreement":null},{"id":"W2065045338","doi":"10.1007/s11219-009-9081-z","title":"A new perspective on data homogeneity in software cost estimation: a study in the embedded systems domain","year":2009,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Computer science; Software; Cost estimate; Domain (mathematical analysis); Estimation; Data mining; Empirical research; Perspective (graphical); Domain engineering; Software development; Cost driver; Software metric; Data science; Artificial intelligence; Software construction; Systems engineering; Engineering; Statistics","score_opus":0.08691323916499845,"score_gpt":0.4021292808525964,"score_spread":0.315216041687598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065045338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118963614,0.00046051698,0.8767722,0.0019634787,0.00042323238,0.0011370416,0.00001954148,0.00023528781,0.00002505376],"genre_scores_gemma":[0.90172446,0.000010237403,0.09754531,0.0003149806,0.0003070506,0.000033740605,0.000009705334,0.000020265394,0.000034229768],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938954,0.0020596879,0.00082439673,0.0007813437,0.0017514536,0.00068770634],"domain_scores_gemma":[0.9935262,0.0033758697,0.00023257254,0.0023602268,0.0002430006,0.00026212703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010348237,0.00030986514,0.00045828024,0.000508911,0.00027972364,0.0009939962,0.0045384555,0.00011413168,0.000011556086],"category_scores_gemma":[0.009332457,0.0002408376,0.000081955404,0.0017242098,0.00003940978,0.0010479135,0.00036909187,0.0014824445,0.00003584041],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050810847,0.0060295034,0.43259266,0.00013108268,0.00024757517,0.0045329514,0.15051794,0.09887799,0.000017220449,0.023595827,0.01764126,0.26530787],"study_design_scores_gemma":[0.0040716506,0.001061892,0.95113254,0.00035811565,0.000013234141,0.00075933716,0.011416438,0.008847158,0.0000052310443,0.02136545,0.0002458251,0.0007231396],"about_ca_topic_score_codex":0.0007121095,"about_ca_topic_score_gemma":0.00029930033,"teacher_disagreement_score":0.78276086,"about_ca_system_score_codex":0.0009142022,"about_ca_system_score_gemma":0.00076257845,"threshold_uncertainty_score":0.99901235},"labels":[],"label_agreement":null},{"id":"W2069963480","doi":"10.1007/s11219-005-4253-y","title":"Virtual Software Engineering Laboratories in Support of Trade-off Analyses","year":2005,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Bundesministerium für Bildung und Forschung","keywords":"Product (mathematics); Computer science; Software engineering; Software; Quality (philosophy); Software quality; Systems engineering; Empirical research; Software quality control; Engineering; Software development; Process management; Risk analysis (engineering); Business; Operating system","score_opus":0.04235531741497253,"score_gpt":0.3502672804459467,"score_spread":0.3079119630309741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069963480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3134292,0.00084027415,0.68392396,0.00072295073,0.0005111177,0.00011089879,0.000027779297,0.00042787753,0.000005935917],"genre_scores_gemma":[0.77941996,0.00008957035,0.21981494,0.0001935268,0.00036401083,0.000010454935,0.0000057203433,0.000042040825,0.000059762955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964014,0.00022029932,0.001082866,0.00040492404,0.0011751723,0.00071528263],"domain_scores_gemma":[0.9965168,0.001943679,0.00025603964,0.0006738553,0.00027724696,0.00033237823],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023431142,0.00029717074,0.00056087435,0.0006691994,0.00010742994,0.00022310538,0.0014163601,0.00016443276,0.00007723877],"category_scores_gemma":[0.008157671,0.00029356554,0.00019713318,0.0016137247,0.00007929729,0.0013041168,0.0002479091,0.00092893315,0.000022229979],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010011921,0.0008473053,0.61304057,0.00039342607,0.00041189732,0.00048613426,0.01162261,0.1346746,0.003703352,0.006886707,0.009138545,0.21869475],"study_design_scores_gemma":[0.00446357,0.0011508504,0.90166855,0.0004731137,0.000054628275,0.0009344105,0.0005399687,0.00534007,0.030473992,0.001149903,0.051229402,0.002521549],"about_ca_topic_score_codex":0.000020464142,"about_ca_topic_score_gemma":0.000019262407,"teacher_disagreement_score":0.46599075,"about_ca_system_score_codex":0.00028591204,"about_ca_system_score_gemma":0.0005380887,"threshold_uncertainty_score":0.99995166},"labels":[],"label_agreement":null},{"id":"W2073102918","doi":"10.1007/s11219-014-9238-2","title":"Studying the relationship between source code quality and mobile platform dependence","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Android (operating system); Source code; Software quality; Computer science; Software quality assurance; Software; Operating system; Source lines of code; Mobile apps; Mobile device; Mobile computing; Quality assurance; Software development; World Wide Web; Engineering","score_opus":0.152923259708518,"score_gpt":0.38289060231190514,"score_spread":0.22996734260338714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073102918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45816332,0.00015888043,0.54080653,0.00039321845,0.00014405664,0.0001186968,0.0000030884917,0.00020131368,0.000010926043],"genre_scores_gemma":[0.97522956,0.0000085751835,0.024125319,0.0001579686,0.00030915617,0.000019054012,0.0000016104519,0.000019947924,0.00012877745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99622655,0.0008819788,0.00072309107,0.00041757108,0.0011977598,0.0005530662],"domain_scores_gemma":[0.9720845,0.025975714,0.0003355311,0.0009799869,0.00025657393,0.00036769346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012143868,0.0002107183,0.0003140349,0.00013686213,0.0011144328,0.0007361775,0.0015282005,0.00012505752,0.0000096436015],"category_scores_gemma":[0.018728223,0.00015782523,0.00010747072,0.00044997362,0.00015709181,0.00081663835,0.0005503035,0.0013331422,0.000034783625],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048375064,0.000017986178,0.95129675,0.000037610964,0.000023403274,0.000002215851,0.002323008,0.00040784694,0.0000074014592,0.003308408,0.000121623554,0.042448916],"study_design_scores_gemma":[0.00038484528,0.000086572,0.9800092,0.000048728376,0.000008195246,0.0000938964,0.00021687392,0.00041894635,0.000034280092,0.016916499,0.001538271,0.0002437078],"about_ca_topic_score_codex":0.00006892381,"about_ca_topic_score_gemma":0.00001527295,"teacher_disagreement_score":0.5170663,"about_ca_system_score_codex":0.00013296846,"about_ca_system_score_gemma":0.00013861334,"threshold_uncertainty_score":0.9895374},"labels":[],"label_agreement":null},{"id":"W2073803340","doi":"10.1007/s11219-007-9029-0","title":"In search for a widely applicable and accepted software quality model for software quality engineering","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Ubisoft (Canada)","funders":"","keywords":"Software quality control; Software quality; Software quality analyst; Software quality management; Quality (philosophy); Software engineering; Computer science; Software development; Social software engineering; Software construction; Verification and validation; Software; Engineering; Operations management","score_opus":0.08279210101335747,"score_gpt":0.39928907863032326,"score_spread":0.31649697761696577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073803340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12419852,0.00054313353,0.87214404,0.0010971193,0.00020902189,0.0011854316,0.00016711948,0.0004502744,0.0000053418003],"genre_scores_gemma":[0.23379922,0.000102431055,0.7642924,0.0007604843,0.00039832015,0.0002292554,0.000047712398,0.00009046024,0.00027970213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99117464,0.00067201944,0.002689131,0.001516405,0.0018096265,0.0021381828],"domain_scores_gemma":[0.9848168,0.010456649,0.0006047134,0.0014100822,0.0016839411,0.0010278013],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028898586,0.0006457652,0.001398985,0.0007865005,0.00092064915,0.00088412734,0.0020719669,0.0005408289,0.000034353994],"category_scores_gemma":[0.012217147,0.0006378393,0.000773237,0.0014736602,0.0002436185,0.0018137443,0.0007145758,0.0014830015,0.000009560914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025125348,0.0024665887,0.28799257,0.006681212,0.0009092254,0.00008316275,0.011748579,0.08919263,0.002410642,0.029105661,0.0028974984,0.5639997],"study_design_scores_gemma":[0.021671552,0.0013914393,0.21004494,0.0009882029,0.00022278092,0.00038320024,0.0026164881,0.52846545,0.006903578,0.21275382,0.007416884,0.0071416916],"about_ca_topic_score_codex":0.0004532177,"about_ca_topic_score_gemma":0.0002916127,"teacher_disagreement_score":0.556858,"about_ca_system_score_codex":0.00070289534,"about_ca_system_score_gemma":0.0008714026,"threshold_uncertainty_score":0.99995327},"labels":[],"label_agreement":null},{"id":"W2077174673","doi":"10.1007/s11219-010-9112-9","title":"A comparative study for estimating software development effort intervals","year":2010,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Research Council Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Computer science; Estimation; Software; Interval estimation; Interval (graph theory); Point (geometry); Point estimation; Data mining; Cluster (spacecraft); Machine learning; Statistics; Confidence interval; Engineering; Mathematics","score_opus":0.08125202920087467,"score_gpt":0.3986317212269463,"score_spread":0.31737969202607164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077174673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41218877,0.000021359936,0.58551633,0.0000733561,0.0013148047,0.00047811389,0.0000036546242,0.0003992131,0.000004375589],"genre_scores_gemma":[0.3688814,2.0667704e-7,0.6306214,0.000050863822,0.00024463242,0.00010086386,0.0000031930845,0.000021478469,0.00007596906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99641955,0.00018804058,0.0010046568,0.00057087914,0.0010512728,0.0007656082],"domain_scores_gemma":[0.9943773,0.003227397,0.00035741823,0.0007635722,0.0008377911,0.00043653557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0053080884,0.00033542226,0.0005751696,0.00028669508,0.00076975295,0.0007706695,0.0019398667,0.00011604811,0.000041512085],"category_scores_gemma":[0.0069728163,0.00030176676,0.00018930716,0.0004253848,0.00007255397,0.00074780313,0.00053559337,0.0012637415,0.000053515385],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014725044,0.002268085,0.5921211,0.00045256136,0.0009207936,0.00016182137,0.08122735,0.00271942,0.000856224,0.0009051199,0.0056269583,0.31259328],"study_design_scores_gemma":[0.009780193,0.002685521,0.92521703,0.0006444354,0.00008820319,0.0013725782,0.0035271982,0.020476537,0.007742492,0.012469112,0.012224876,0.0037718255],"about_ca_topic_score_codex":0.00001304527,"about_ca_topic_score_gemma":0.000046088397,"teacher_disagreement_score":0.33309588,"about_ca_system_score_codex":0.00017956394,"about_ca_system_score_gemma":0.0006495728,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W2098513273","doi":"10.1007/s11219-006-5997-8","title":"PEM: The small company-dedicated software process quality evaluation method combining CMMISM and ISO/IEC 14598","year":2006,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Motorola (Canada); Computer Research Institute of Montréal","funders":"","keywords":"Capability Maturity Model Integration; LeanCMMI; Software quality control; Software quality; Personal software process; Software quality management; Computer science; Software engineering; Software quality analyst; Team software process; Software; Software development process; Verification and validation; Process (computing); Quality (philosophy); Software development; Systems engineering; Engineering; Software construction; Operations management","score_opus":0.07220551126872021,"score_gpt":0.3888549613939644,"score_spread":0.3166494501252442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098513273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07674356,0.0013078891,0.91739696,0.0024015994,0.00053380994,0.00039975188,0.000010559767,0.0011323992,0.00007347252],"genre_scores_gemma":[0.38969982,0.000058225065,0.60900474,0.00066739804,0.0003727566,0.00005895512,0.000022006385,0.00004189734,0.00007420118],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.993785,0.0023712334,0.0011966622,0.0006565858,0.001391646,0.0005988234],"domain_scores_gemma":[0.9930247,0.0037678583,0.0011157213,0.0009084932,0.0009441241,0.0002391192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01710258,0.00039382983,0.0005256277,0.00018124083,0.0010119295,0.0010170282,0.0014955223,0.00022656433,0.000048257778],"category_scores_gemma":[0.0044240914,0.0003022249,0.00018272821,0.0006741976,0.00014576653,0.0010891409,0.00030871874,0.0012476789,0.000009294738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024992475,0.0010806487,0.20247708,0.0009640371,0.0005337707,0.00010578459,0.013102631,0.011910701,0.00041508846,0.03621204,0.010218606,0.7227297],"study_design_scores_gemma":[0.0040769354,0.00051981874,0.5146725,0.0005533178,0.00037069974,0.00218495,0.0009128006,0.044309597,0.0015746569,0.41495457,0.01343757,0.0024325775],"about_ca_topic_score_codex":0.0005977256,"about_ca_topic_score_gemma":0.000057343655,"teacher_disagreement_score":0.7202971,"about_ca_system_score_codex":0.00015494693,"about_ca_system_score_gemma":0.00037794895,"threshold_uncertainty_score":0.99994296},"labels":[],"label_agreement":null},{"id":"W2106743089","doi":"10.1007/s11219-004-5259-6","title":"The Evolution Path for Industrial Software Quality Evaluation Methods Applying ISO/IEC 9126:2001 Quality Model: Example of MITRE?s SQAE Method","year":2005,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Software quality; Reliability engineering; Quality (philosophy); Software; Computer science; Verification and validation; Software quality control; Engineering; Systems engineering; Software development; Operations management; Operating system","score_opus":0.25675761791988566,"score_gpt":0.4826588867655611,"score_spread":0.22590126884567546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106743089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021780068,0.0011127173,0.97277987,0.0008916855,0.0011865367,0.0016341762,0.00009246745,0.00050691917,0.000015550277],"genre_scores_gemma":[0.05185347,0.00004157792,0.94637007,0.0001245281,0.00093103823,0.00041459865,0.000029468676,0.00006963521,0.00016560487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9802424,0.01003974,0.0032495589,0.0012249496,0.0036603136,0.0015830746],"domain_scores_gemma":[0.960273,0.030798502,0.002195593,0.0025776771,0.0034572948,0.0006979331],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.107179284,0.0005626433,0.0010406768,0.00039629827,0.0014346071,0.00062150083,0.0027318355,0.00054489094,0.000035801433],"category_scores_gemma":[0.06929023,0.00047127085,0.0007739559,0.0012632525,0.00022505136,0.0014611991,0.0006007062,0.0017106939,0.000008687248],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028000685,0.00031465437,0.014235704,0.0001867794,0.00024544555,0.0000010842826,0.0022672918,0.05972912,0.0010844506,0.01081831,0.0024667555,0.9083704],"study_design_scores_gemma":[0.011071807,0.00071845815,0.063452154,0.00043484944,0.00033801296,0.00017812442,0.0016213548,0.66989154,0.005442594,0.2292525,0.014732548,0.0028660556],"about_ca_topic_score_codex":0.0012319303,"about_ca_topic_score_gemma":0.00015528571,"teacher_disagreement_score":0.90550435,"about_ca_system_score_codex":0.0020101194,"about_ca_system_score_gemma":0.0025049476,"threshold_uncertainty_score":0.9998654},"labels":[],"label_agreement":null},{"id":"W2129182946","doi":"10.1007/s11219-007-9030-7","title":"Empirical studies to assess the understandability of data warehouse schemas using structural metrics","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Data mining; Metric (unit); Schema (genetic algorithms); Data warehouse; Similarity (geometry); Empirical research; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.584142689272458,"score_gpt":0.5376677499733624,"score_spread":0.04647493929909563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129182946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38057554,0.0005739692,0.6176198,0.00056730985,0.00042789453,0.00011708255,0.000014852004,0.00010209639,0.0000014439066],"genre_scores_gemma":[0.60836905,0.000013419273,0.39129233,0.00014293502,0.00015790146,6.461445e-7,0.0000012908972,0.00001526781,0.0000071801405],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99560523,0.0005114645,0.0009157251,0.00051137933,0.001800927,0.0006552886],"domain_scores_gemma":[0.98477066,0.011259029,0.00030415884,0.0022091211,0.0010885845,0.0003684673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015464135,0.0002186644,0.00043796143,0.00033988254,0.0004600593,0.00022365958,0.0033246248,0.000094848816,0.00000826175],"category_scores_gemma":[0.03321121,0.00014784251,0.000119756754,0.0020559458,0.00024034554,0.00095982203,0.0021673362,0.00084111496,0.0000031205261],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001116269,0.00014818466,0.93148464,0.00031644315,0.00057544344,0.00011149764,0.008774693,0.0043844935,0.00034279295,0.0021436294,0.0023188791,0.049287703],"study_design_scores_gemma":[0.002051297,0.0006184678,0.94039595,0.0003880695,0.00013425917,0.0012385682,0.008681998,0.010892761,0.005703185,0.02467877,0.0035085941,0.0017080831],"about_ca_topic_score_codex":0.000039354632,"about_ca_topic_score_gemma":0.00003114349,"teacher_disagreement_score":0.22779348,"about_ca_system_score_codex":0.0005942535,"about_ca_system_score_gemma":0.0005002879,"threshold_uncertainty_score":0.9749325},"labels":[],"label_agreement":null},{"id":"W2139435518","doi":"10.1007/s11219-007-9015-6","title":"Introduction to the special issue on: “Software Quality Improvements and Estimations with Intelligence-based Methods”","year":2007,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Software quality; Quality (philosophy); Software engineering; Software; Software development; Programming language","score_opus":0.0479755089915145,"score_gpt":0.39931576881835573,"score_spread":0.35134025982684125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139435518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010203244,0.00005048611,0.97870815,0.008842733,0.0014587448,0.00041168564,0.000009410041,0.00029077614,0.000024779076],"genre_scores_gemma":[0.009128784,0.000007039796,0.98146117,0.0010965768,0.008015012,0.000024129895,0.000005318854,0.000031393785,0.00023059078],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959593,0.00070800696,0.00079178246,0.0006326862,0.001234084,0.0006741723],"domain_scores_gemma":[0.9935989,0.003969801,0.00027788474,0.0010432393,0.0006281006,0.00048212262],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012107716,0.00029422183,0.00032999564,0.00035776652,0.0007395163,0.00060617435,0.0011337848,0.00010434261,0.0001416696],"category_scores_gemma":[0.011553432,0.00020598751,0.0000972645,0.001110461,0.000146731,0.00047158383,0.0002335063,0.00095832034,0.00008810751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018102235,0.00015988018,0.008114277,0.000063315,0.00007221444,0.00002044188,0.0018692847,0.0057305642,0.00005793617,0.0030143477,0.0069178245,0.9737989],"study_design_scores_gemma":[0.0033729419,0.004935079,0.63068634,0.00056851975,0.000108781474,0.0008206319,0.0019837315,0.004339291,0.024841523,0.020861464,0.30406103,0.0034206808],"about_ca_topic_score_codex":0.000067043926,"about_ca_topic_score_gemma":0.000059344966,"teacher_disagreement_score":0.9703782,"about_ca_system_score_codex":0.00033918346,"about_ca_system_score_gemma":0.00028157613,"threshold_uncertainty_score":0.99677265},"labels":[],"label_agreement":null},{"id":"W2308674594","doi":"10.1007/s11219-015-9304-4","title":"Efficient and scalable omniscient debugging for model transformations","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"U.S. Department of Education","keywords":"Debugging; Computer science; Scalability; Algorithmic program debugging; Session (web analytics); Programming language; Software; Software engineering; Operating system","score_opus":0.030488092346449166,"score_gpt":0.2932194760941157,"score_spread":0.2627313837476665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2308674594","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011143844,0.00011850509,0.9857825,0.001799558,0.00017989472,0.00023110943,0.00002703409,0.00070000027,0.000017566408],"genre_scores_gemma":[0.17663153,0.000021166941,0.82306594,0.000120425975,0.00003758771,0.000033287062,6.090882e-7,0.0000133281,0.00007612202],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983463,0.00006266162,0.0005078338,0.00028411706,0.0003826393,0.00041640227],"domain_scores_gemma":[0.9987917,0.00023734468,0.0001447998,0.0003565208,0.00023504799,0.00023461528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017871147,0.00016372185,0.00020206413,0.00017392637,0.00042265156,0.0002206304,0.00054699817,0.00007182621,0.0000041453904],"category_scores_gemma":[0.00010064419,0.00011552041,0.00011806575,0.0001602168,0.00006398333,0.00045383643,0.00010534293,0.00014550312,0.000003531829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020030458,0.00013064529,0.00060744316,0.00011382643,0.000045890618,0.0000037499242,0.0027077345,0.0704713,0.0022349237,0.331278,0.0023084553,0.590078],"study_design_scores_gemma":[0.0009712754,0.00010668484,0.0003350004,0.00022432793,0.000015704296,0.00021180435,0.0000070248902,0.9284227,0.0017494289,0.059186433,0.008314809,0.00045479607],"about_ca_topic_score_codex":0.0000026298542,"about_ca_topic_score_gemma":0.000001397145,"teacher_disagreement_score":0.8579514,"about_ca_system_score_codex":0.00013284886,"about_ca_system_score_gemma":0.00015011903,"threshold_uncertainty_score":0.47107857},"labels":[],"label_agreement":null},{"id":"W2340362696","doi":"10.1007/s11219-016-9311-0","title":"A declarative framework for stateful analysis of execution traces","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Debugging; Tracing; TRACE (psycholinguistics); Programming language; Abstraction; Software engineering; Distributed computing; Theoretical computer science","score_opus":0.04390968862051765,"score_gpt":0.35937246303747283,"score_spread":0.3154627744169552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340362696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24929951,0.00016400027,0.7492566,0.00063878566,0.0003737232,0.00013983877,0.00004382748,0.000077468394,0.0000062403988],"genre_scores_gemma":[0.7776979,0.00006348386,0.2219818,0.000085934225,0.0000975314,0.000017913397,0.0000023028347,0.000006548271,0.00004654755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99762154,0.00034275078,0.00087130547,0.00032782648,0.00050773524,0.00032886805],"domain_scores_gemma":[0.9959424,0.0019426295,0.00071789976,0.00055407657,0.00069499045,0.00014796309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002824309,0.00015918171,0.00052301533,0.00031321618,0.00024175867,0.000091539034,0.00067135395,0.00015230358,0.000039615494],"category_scores_gemma":[0.0017258826,0.00009418092,0.0005013914,0.00096615875,0.000117165095,0.00082732283,0.0000665299,0.00016638864,0.0000070751744],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039846098,0.00053911615,0.4494413,0.0003081956,0.0035082716,0.000008174954,0.013868543,0.0005993065,0.0009256155,0.07464842,0.0011493985,0.4546052],"study_design_scores_gemma":[0.0023734304,0.0010236889,0.47283703,0.00065637025,0.00078095763,0.000057432986,0.0009904932,0.0017972625,0.007970309,0.50749373,0.0030371568,0.0009821367],"about_ca_topic_score_codex":0.000016608188,"about_ca_topic_score_gemma":0.000014883216,"teacher_disagreement_score":0.52839845,"about_ca_system_score_codex":0.00012929951,"about_ca_system_score_gemma":0.00021215489,"threshold_uncertainty_score":0.38405862},"labels":[],"label_agreement":null},{"id":"W2466590866","doi":"10.1007/s11219-016-9319-5","title":"Industry–academia collaborations in software testing: experience and success stories from Canada and Turkey","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Hacettepe Üniversitesi; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Empirical research; Relevance (law); Confidentiality; Set (abstract data type); Software; Engineering; Engineering management; Knowledge management; Computer science; Software engineering; Business; Political science; Computer security","score_opus":0.05220059938723919,"score_gpt":0.31836247764262326,"score_spread":0.26616187825538407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466590866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6971951,0.00047149215,0.29968026,0.0020190112,0.00031831046,0.000071093775,0.00004026361,0.00020020393,0.0000042749707],"genre_scores_gemma":[0.7921905,0.000093752446,0.20717297,0.00035584575,0.00012323337,0.000014587096,0.0000010512616,0.000012028412,0.000036013313],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99826986,0.00020496338,0.0004489138,0.00035672906,0.0004039915,0.00031552115],"domain_scores_gemma":[0.99611413,0.0027515062,0.00026532047,0.00030558414,0.00023674342,0.00032670755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007304319,0.00018939229,0.00023782777,0.00009150283,0.0002737211,0.00036147333,0.00053228985,0.0003847609,0.000020383563],"category_scores_gemma":[0.008764965,0.00014686155,0.000015496125,0.000477643,0.00009552455,0.0015176913,0.00023023774,0.0012330245,4.1104695e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008730395,0.000013186518,0.9597453,0.000013442109,0.000011865641,0.00005467831,0.0017918833,0.000032313168,0.00010745255,0.0004784145,0.00103105,0.03671168],"study_design_scores_gemma":[0.00072362454,0.000093401475,0.975002,0.0003973954,0.0000105804575,0.00024325406,0.00043007272,0.00013210665,0.000814217,0.0107132,0.010760783,0.0006793916],"about_ca_topic_score_codex":0.16776037,"about_ca_topic_score_gemma":0.047530398,"teacher_disagreement_score":0.120229974,"about_ca_system_score_codex":0.00020429211,"about_ca_system_score_gemma":0.00091943215,"threshold_uncertainty_score":0.9995846},"labels":[],"label_agreement":null},{"id":"W2512805961","doi":"10.1007/s11219-016-9333-7","title":"Onboarding inexperienced developers: struggles and perceptions regarding automated testing","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Onboarding; Perception; Software testing; Software engineering; Computer science; Engineering; Psychology; Software; Social psychology; Programming language","score_opus":0.04988978108270573,"score_gpt":0.33398380233613445,"score_spread":0.2840940212534287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512805961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25057682,0.0001036028,0.7460604,0.00066645344,0.00024170497,0.000052356165,0.0000023421233,0.0022446238,0.000051752104],"genre_scores_gemma":[0.445788,0.00004419975,0.55395615,0.00007982361,0.000085527376,0.0000059473596,2.3832914e-7,0.000010879745,0.00002923869],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99834067,0.00020038684,0.0004376918,0.00032070532,0.000337717,0.00036284106],"domain_scores_gemma":[0.9974597,0.0015231532,0.00023493309,0.0003206391,0.00025759786,0.00020395647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014870907,0.00018205727,0.00021684768,0.00016465475,0.0005438769,0.0005476035,0.0005632787,0.0000880776,0.00002313949],"category_scores_gemma":[0.005395107,0.00012698099,0.00006033614,0.00038594956,0.00007277176,0.0018741543,0.0002662126,0.0002614274,0.000008956864],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017647628,0.000049216706,0.084514715,0.00006276478,0.000088822446,0.00008110562,0.0073703104,0.000077320765,0.018014409,0.0067798235,0.0016867593,0.8812571],"study_design_scores_gemma":[0.0058982675,0.0013705079,0.82264555,0.0061059603,0.00013381428,0.015776154,0.0070040696,0.023348583,0.010017218,0.07460336,0.026730599,0.0063659516],"about_ca_topic_score_codex":0.000019879495,"about_ca_topic_score_gemma":0.0000017112919,"teacher_disagreement_score":0.87489116,"about_ca_system_score_codex":0.00011955935,"about_ca_system_score_gemma":0.00012505637,"threshold_uncertainty_score":0.6458837},"labels":[],"label_agreement":null},{"id":"W2521099350","doi":"10.1007/s11219-016-9340-8","title":"An empirical study on the effects of code visibility on program testability","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities","keywords":"Testability; Visibility; Computer science; Code coverage; Artifact (error); Code (set theory); Software; Software quality; Software engineering; Software metric; Programming language; Software development; Reliability engineering; Engineering; Artificial intelligence; Set (abstract data type)","score_opus":0.06644119961895152,"score_gpt":0.4136435348790582,"score_spread":0.3472023352601067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521099350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7852594,0.000012217798,0.20879549,0.0012085388,0.00025563463,0.0006927643,0.0000057821962,0.003752549,0.000017619375],"genre_scores_gemma":[0.9632718,0.0000015146484,0.036106028,0.00045536555,0.000088276414,0.00005459535,2.6602578e-7,0.000014861058,0.0000073036285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945282,0.0027310932,0.00072116626,0.00061069394,0.0009982913,0.00041058907],"domain_scores_gemma":[0.9846166,0.012283374,0.00042236169,0.002040383,0.0004003301,0.00023700426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068087303,0.00026096494,0.0003901827,0.00010261777,0.00036655657,0.00018908732,0.0016808811,0.000099957106,0.000009249187],"category_scores_gemma":[0.019795487,0.0001273579,0.00018477562,0.000392445,0.00023645915,0.00030462997,0.0001842068,0.0005245456,0.000011539339],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067623245,0.004386267,0.7518306,0.00003611468,0.000027928736,0.000019707903,0.0014092292,0.0000012115349,0.0001281693,0.0003431398,0.0017934047,0.2399566],"study_design_scores_gemma":[0.00068074977,0.009271407,0.8872189,0.00026956806,0.00001338168,0.00002897989,0.000039543396,0.00007038843,0.0020785022,0.09997556,0.0000796896,0.00027333232],"about_ca_topic_score_codex":0.000025670737,"about_ca_topic_score_gemma":0.000006919623,"teacher_disagreement_score":0.23968327,"about_ca_system_score_codex":0.00016050144,"about_ca_system_score_gemma":0.00019084204,"threshold_uncertainty_score":0.9884612},"labels":[],"label_agreement":null},{"id":"W2593117527","doi":"10.1007/s11219-017-9361-y","title":"An empirical study of crash-inducing commits in Mozilla Firefox","year":2017,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Crash; Computer science; Empirical research; Software engineering; Business; Programming language; Mathematics; Statistics","score_opus":0.09836511809479921,"score_gpt":0.4380468293221385,"score_spread":0.3396817112273393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593117527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9137052,0.000043257656,0.08517729,0.00033223577,0.0004394382,0.00016086934,0.000002363047,0.00011783559,0.000021484428],"genre_scores_gemma":[0.9862659,0.000005315326,0.013508258,0.000039002338,0.00013320676,0.0000060770813,4.59783e-7,0.000017857312,0.000023948753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99661607,0.00065002125,0.00073456985,0.00041228175,0.0010797571,0.00050732243],"domain_scores_gemma":[0.99606794,0.0010129161,0.00038557767,0.0019138223,0.00030538952,0.00031437946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004349916,0.00018829423,0.00042830576,0.0002894164,0.0005442905,0.0006339924,0.0032762517,0.00011026897,0.000018224266],"category_scores_gemma":[0.0056073745,0.00017174537,0.000087690125,0.00026382765,0.00008372436,0.0011774694,0.00055006973,0.00095274264,0.000010434681],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010908561,0.0005971917,0.97513527,0.000021593642,0.000022413524,0.00012409486,0.0049330937,0.0005680699,0.0000685604,0.00002685749,0.00012767826,0.01836425],"study_design_scores_gemma":[0.0010642787,0.0004448012,0.995825,0.00006774872,0.000003057089,0.000062170046,0.00035888836,0.00093326415,0.00013826937,0.0008521971,0.000050400256,0.00019992195],"about_ca_topic_score_codex":0.00042746653,"about_ca_topic_score_gemma":0.00023762684,"teacher_disagreement_score":0.072560646,"about_ca_system_score_codex":0.00016491176,"about_ca_system_score_gemma":0.00023935793,"threshold_uncertainty_score":0.7003573},"labels":[],"label_agreement":null},{"id":"W2626932320","doi":"10.1007/s11219-017-9375-5","title":"An investigation of the fault-proneness of clone evolutionary patterns","year":2017,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"clone (Java method); Cloning (programming); Software maintenance; Similarity (geometry); Biology; Genetics; Computer science; Software system; Software; Gene; Artificial intelligence; Programming language","score_opus":0.049937006655939524,"score_gpt":0.34101401970992457,"score_spread":0.29107701305398503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626932320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6944123,0.0000654796,0.30453423,0.00044568625,0.00042079223,0.000068248984,0.0000122692045,0.000038763894,0.000002215959],"genre_scores_gemma":[0.97871435,0.000008490475,0.021107027,0.000026872916,0.00010764587,0.000003309657,0.0000014526814,0.000009016153,0.000021810909],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99791265,0.0003450412,0.00045836766,0.00019167642,0.0008684303,0.0002238241],"domain_scores_gemma":[0.9968853,0.00040200455,0.00059425196,0.001482972,0.00049525965,0.0001402181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017755678,0.00010439145,0.00019511221,0.00008563082,0.0004499974,0.00014534002,0.00274581,0.000075156386,0.00001136052],"category_scores_gemma":[0.0022768264,0.00007868648,0.00011206352,0.0001340837,0.00022667904,0.00092924613,0.00038059225,0.00036380385,0.0000021669714],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005257091,0.000036698817,0.9899302,0.00007374339,0.000018457511,0.0000026898401,0.00078463694,0.00051592273,0.0019838943,0.000912085,0.00008307042,0.0056533343],"study_design_scores_gemma":[0.00024175015,0.000057960227,0.98731476,0.00011690157,0.0000037994762,0.000040234598,0.000030565418,0.0006300053,0.0056001726,0.00586161,0.000010457861,0.00009180622],"about_ca_topic_score_codex":0.00021988795,"about_ca_topic_score_gemma":0.0000103370085,"teacher_disagreement_score":0.2843021,"about_ca_system_score_codex":0.00007435639,"about_ca_system_score_gemma":0.00031417495,"threshold_uncertainty_score":0.51024437},"labels":[],"label_agreement":null},{"id":"W2904898906","doi":"10.1007/s11219-018-9429-3","title":"FSM inference and checking sequence construction are two sides of the same coin","year":2018,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"TRACE (psycholinguistics); Sequence (biology); Inference; Computer science; Nondeterministic algorithm; Finite-state machine; Model checking; Permutation (music); A priori and a posteriori; Algorithm; Automaton; Theoretical computer science; Artificial intelligence","score_opus":0.04786971646388845,"score_gpt":0.3511958778392323,"score_spread":0.30332616137534385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904898906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53939384,0.000090843445,0.45874804,0.0010713219,0.0005407394,0.00003799383,0.0000035745763,0.00005505858,0.000058607373],"genre_scores_gemma":[0.9097965,0.000013103421,0.089682944,0.0002461665,0.00022135561,6.036545e-7,1.845223e-7,0.0000040518826,0.000035124645],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856716,0.0003828975,0.0003332053,0.00018961226,0.0003407574,0.0001863727],"domain_scores_gemma":[0.9985569,0.00026781423,0.0005167551,0.00029717133,0.00027961182,0.00008174576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011355514,0.00010327604,0.00017189943,0.000048647762,0.00043557948,0.00018619369,0.0005184705,0.000040743,0.000016022417],"category_scores_gemma":[0.001247122,0.00007142965,0.00005943541,0.00025626548,0.00041553695,0.00032685444,0.00021406102,0.00042542373,0.0000038798903],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008225118,0.000025835943,0.682459,0.000050170926,0.000027806276,0.000006931996,0.0031493497,0.000119120574,0.0013237516,0.013514275,0.00006609264,0.29924947],"study_design_scores_gemma":[0.0012717127,0.00027314268,0.8068561,0.00092338165,0.000025685238,0.002220952,0.0009974488,0.016554933,0.0072238273,0.16210738,0.0009511731,0.00059424527],"about_ca_topic_score_codex":0.00017220392,"about_ca_topic_score_gemma":0.000048131675,"teacher_disagreement_score":0.37040263,"about_ca_system_score_codex":0.00002913802,"about_ca_system_score_gemma":0.00012995754,"threshold_uncertainty_score":0.33501694},"labels":[],"label_agreement":null},{"id":"W2911476493","doi":"10.1007/s11219-018-9428-4","title":"API trustworthiness: an ontological approach for software library adoption","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Trustworthiness; License; Software engineering; Quality (philosophy); Application programming interface; Software; World Wide Web; Data science; Computer security","score_opus":0.046976021699527935,"score_gpt":0.3156316965895039,"score_spread":0.268655674889976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911476493","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12154892,0.0003022225,0.875169,0.0002478034,0.00082046667,0.0004952891,0.000018630852,0.0013389977,0.000058686303],"genre_scores_gemma":[0.17431405,0.000024552352,0.82397425,0.00037549058,0.00057158124,0.000058533176,0.00006914572,0.00005704346,0.0005553528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962965,0.0004351836,0.0007009719,0.00076515717,0.0009626257,0.00083955977],"domain_scores_gemma":[0.9961678,0.001695377,0.0002608028,0.0010535774,0.00030026483,0.00052222447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022694957,0.00033589828,0.0005035143,0.00027172727,0.00033359352,0.00087526266,0.002202555,0.00030464723,0.00014967592],"category_scores_gemma":[0.0021985532,0.00028701953,0.00030668327,0.00057851017,0.00007009717,0.0031426104,0.0003663604,0.0009685941,0.00006149699],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034420117,0.0010526282,0.72685575,0.0007342375,0.00018556295,0.00006816292,0.0018651144,0.01125145,0.00012854811,0.02389747,0.0060929884,0.2275239],"study_design_scores_gemma":[0.008861175,0.003708106,0.8255603,0.00035413873,0.00006821187,0.0023979913,0.00077670487,0.061992384,0.0005280351,0.064550966,0.027130278,0.004071711],"about_ca_topic_score_codex":0.000009610738,"about_ca_topic_score_gemma":8.8222384e-7,"teacher_disagreement_score":0.22345218,"about_ca_system_score_codex":0.00012604376,"about_ca_system_score_gemma":0.00035708744,"threshold_uncertainty_score":0.9999582},"labels":[],"label_agreement":null},{"id":"W2913863212","doi":"10.1007/s11219-019-9440-3","title":"Fault model-driven testing from FSM with symbolic inputs","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Finite-state machine; Test suite; Computer science; Symbolic execution; Implementation; Fault model; Fault injection; Fault (geology); Set (abstract data type); Model-based testing; Theoretical computer science; Fault coverage; Process (computing); Constraint (computer-aided design); Algorithm; Programming language; Test case; Software; Engineering; Machine learning","score_opus":0.044427028615976964,"score_gpt":0.29178708709886186,"score_spread":0.2473600584828849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913863212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2594619,0.000066193825,0.7339607,0.00035395383,0.0002013466,0.00011996136,0.00000895074,0.005599815,0.00022715944],"genre_scores_gemma":[0.44114226,0.0000026078558,0.557918,0.0007083543,0.000112934744,0.0000049695677,0.0000030705096,0.000022149408,0.00008561619],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972501,0.0002435857,0.0005736787,0.0005675721,0.00081597746,0.00054910354],"domain_scores_gemma":[0.9965021,0.0012550928,0.00048187244,0.0009599077,0.0005167761,0.0002842793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009903419,0.00030289314,0.00042815384,0.00016579518,0.0003306573,0.0005436343,0.0014245835,0.00014090714,0.000017560295],"category_scores_gemma":[0.0012744962,0.00024250304,0.00011184451,0.0005173126,0.000065036285,0.0007943929,0.0003204677,0.0007953312,0.000096253956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057787183,0.00026200223,0.8400493,0.0000853286,0.00015699827,0.00016843906,0.005117735,0.020790711,0.00091144023,0.002108641,0.008331842,0.12195974],"study_design_scores_gemma":[0.002792967,0.0010302863,0.07412617,0.0019408294,0.00006784285,0.0015512967,0.000058289013,0.46693456,0.0012853334,0.44698933,0.00080492254,0.0024181642],"about_ca_topic_score_codex":0.00022309586,"about_ca_topic_score_gemma":0.000008632122,"teacher_disagreement_score":0.76592314,"about_ca_system_score_codex":0.00012761014,"about_ca_system_score_gemma":0.00039172356,"threshold_uncertainty_score":0.9888987},"labels":[],"label_agreement":null},{"id":"W2924144435","doi":"10.1007/s11219-019-09442-9","title":"A large-scale empirical study of code smells in JavaScript projects","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Code smell; JavaScript; Computer science; Scripting language; Software quality; World Wide Web; Programming language; Software development; Software","score_opus":0.05973784110211131,"score_gpt":0.36947289628882407,"score_spread":0.30973505518671274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924144435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86906034,0.00011144419,0.12954357,0.00015846919,0.0005166353,0.0004389801,0.0000054460866,0.00013645114,0.000028660654],"genre_scores_gemma":[0.9831858,0.0000062049735,0.016404105,0.000094866744,0.000064952445,0.0000119382585,8.025594e-7,0.000020739673,0.00021054734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99611974,0.0006633212,0.00080989726,0.00046687873,0.0012892241,0.00065095193],"domain_scores_gemma":[0.9972848,0.0011241909,0.00020748345,0.0008761083,0.00029572012,0.00021166519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004178948,0.00019472015,0.00048517916,0.00043431137,0.00007733444,0.00015543852,0.0014239536,0.00010997815,0.000058749523],"category_scores_gemma":[0.001690533,0.000175115,0.00012358218,0.0010458699,0.000030300213,0.0005189037,0.0004678425,0.00093210425,0.00007738193],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028170001,0.0010620723,0.97693723,0.00006943525,0.000030991316,0.0000557639,0.019206796,0.0004974657,0.00009467009,0.00004508367,0.00066825387,0.001304056],"study_design_scores_gemma":[0.003511086,0.0009943951,0.98716295,0.00013164165,0.000006040178,0.0001166384,0.0038377622,0.001979762,0.0002747253,0.0007613236,0.0008537408,0.0003699149],"about_ca_topic_score_codex":0.000063675216,"about_ca_topic_score_gemma":0.00010990115,"teacher_disagreement_score":0.114125505,"about_ca_system_score_codex":0.0001862599,"about_ca_system_score_gemma":0.00036975674,"threshold_uncertainty_score":0.7140982},"labels":[],"label_agreement":null},{"id":"W2925127136","doi":"10.1007/s11219-018-9437-3","title":"Testing self-healing cyber-physical systems under uncertainty: a fragility-oriented approach","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Horizon 2020 Framework Programme; Norges Forskningsråd","keywords":"Fragility; Reliability engineering; Normality; Computer science; Reliability (semiconductor); Cyber-physical system; Data mining; Engineering; Mathematics; Statistics","score_opus":0.04131213216160864,"score_gpt":0.308153895772097,"score_spread":0.2668417636104884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925127136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21311186,0.00017364582,0.7741698,0.00015068882,0.00084860914,0.0003105159,0.0000051896413,0.010832998,0.00039670884],"genre_scores_gemma":[0.58691055,0.0000018153796,0.41231173,0.0002931548,0.0003736795,0.000017163364,0.000005159036,0.000031651965,0.000055101584],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99538696,0.0009014855,0.0008913888,0.0008112765,0.0011672477,0.0008416513],"domain_scores_gemma":[0.99428785,0.0027273868,0.00063981104,0.0011773148,0.0007771322,0.00039050935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003802481,0.00040220807,0.000663919,0.00023173142,0.0005845209,0.00073767983,0.0013195105,0.00019108345,0.000004268882],"category_scores_gemma":[0.0022772837,0.00035102514,0.00024452718,0.0010427161,0.00007362645,0.00069643214,0.0004087612,0.0012085594,0.000060556613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014381425,0.0041809757,0.630176,0.0023238119,0.0009155284,0.00022480747,0.022047073,0.11945642,0.00080433587,0.11492485,0.013513778,0.091288574],"study_design_scores_gemma":[0.0023535057,0.0008946191,0.030888643,0.0011911432,0.000096226795,0.0029468029,0.0007637883,0.7796924,0.00007792472,0.17641795,0.0022806728,0.002396305],"about_ca_topic_score_codex":0.00042737403,"about_ca_topic_score_gemma":9.0758897e-7,"teacher_disagreement_score":0.660236,"about_ca_system_score_codex":0.00040904977,"about_ca_system_score_gemma":0.00047121508,"threshold_uncertainty_score":0.9998942},"labels":[],"label_agreement":null},{"id":"W2955136383","doi":"10.1007/s11219-019-09456-3","title":"Pieces of contextual information suitable for predicting co-changes? An empirical study","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Commit; Computer science; Artifact (error); Metadata; Baseline (sea); Software; Software engineering; Set (abstract data type); Software development; Data science; Data mining; Information retrieval; Artificial intelligence; World Wide Web; Database; Programming language","score_opus":0.06126340530962837,"score_gpt":0.39334973887793756,"score_spread":0.3320863335683092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955136383","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57011247,0.000027964365,0.428822,0.00010970536,0.00036980948,0.00038840025,0.00002089489,0.00013765297,0.000011100268],"genre_scores_gemma":[0.9769861,0.0000025053735,0.022648752,0.000099183,0.00015954839,0.000022377248,0.000012029578,0.000011992198,0.000057509485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99749225,0.00028467324,0.0006305187,0.00021803961,0.0009406762,0.0004338396],"domain_scores_gemma":[0.9963126,0.001973662,0.0003348053,0.00050372886,0.000667333,0.00020784611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004995416,0.00014767719,0.0003229419,0.0002589879,0.00018204171,0.00033438235,0.0009844273,0.00009358486,0.000035051256],"category_scores_gemma":[0.003915562,0.00013325337,0.00008553276,0.0003095038,0.000028056373,0.0021534772,0.00015643568,0.00041654188,0.000029095085],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059490332,0.00021743003,0.96389836,0.00011833294,0.000059846247,0.0000019340525,0.011656036,0.0007175649,0.000044757224,0.00014733445,0.00084476324,0.022234129],"study_design_scores_gemma":[0.005607712,0.006491943,0.9540273,0.00015517761,0.000025923453,0.00014393528,0.008683534,0.01544537,0.0009060905,0.00096280815,0.006855824,0.0006944113],"about_ca_topic_score_codex":0.000045035016,"about_ca_topic_score_gemma":0.000023814724,"teacher_disagreement_score":0.40687364,"about_ca_system_score_codex":0.00010677825,"about_ca_system_score_gemma":0.00024516243,"threshold_uncertainty_score":0.54339147},"labels":[],"label_agreement":null},{"id":"W3130726859","doi":"10.1007/s11219-020-09538-7","title":"An empirical study on the effect of community smells on bug prediction","year":2021,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Insect and Arachnid Ecology and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Empirical research; Computer science; Computer security; Business; Statistics; Mathematics","score_opus":0.04319073875896441,"score_gpt":0.38051748767032306,"score_spread":0.33732674891135866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130726859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990572,0.000022431836,0.0002767541,0.00016511264,0.00026499905,0.00012597567,0.000026583935,0.000009585147,0.000051380077],"genre_scores_gemma":[0.9992116,0.000005606222,0.000018408662,0.00043583644,0.000197035,0.0000073070128,0.000045675308,0.000007926186,0.000070592076],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953783,0.0039562075,0.00025400062,0.000110023946,0.00016166361,0.00013977673],"domain_scores_gemma":[0.999095,0.00023000897,0.0001185397,0.0003993181,0.000098045646,0.00005904187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002452576,0.000111242676,0.00016486687,0.00002066047,0.0004969219,0.000022095128,0.00018855992,0.00013650414,0.0000746584],"category_scores_gemma":[0.00042623107,0.00007036126,0.00012470037,0.000058906866,0.00007484012,0.000003921445,0.000043266427,0.0006296574,0.0000061164806],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004833383,0.0016723736,0.8846633,0.000011913809,0.00008901789,0.000014862277,0.00074019935,0.00003631671,0.10780599,0.0000053587914,0.0013440538,0.0031333154],"study_design_scores_gemma":[0.0007998858,0.009949506,0.697359,0.000012147001,0.000048126647,0.000051176245,0.0011118047,8.280898e-7,0.2903753,0.000068020345,0.0001369878,0.00008719221],"about_ca_topic_score_codex":0.0000066539787,"about_ca_topic_score_gemma":0.000027529584,"teacher_disagreement_score":0.18730421,"about_ca_system_score_codex":0.000013605004,"about_ca_system_score_gemma":0.00005528211,"threshold_uncertainty_score":0.38219717},"labels":[],"label_agreement":null},{"id":"W3149010935","doi":"10.1007/s11219-021-09552-3","title":"Reconciliation of scrum and the project management process of the ISO/IEC 29110 standard-Entry profile—an experimental evaluation through usability measures","year":2021,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Scrum; Agile software development; Usability; Process management; Process (computing); Engineering management; Engineering; Software development process; Best practice; Software; Computer science; Software development; Software engineering; Knowledge management; Management","score_opus":0.06787216461876273,"score_gpt":0.38606037768116114,"score_spread":0.3181882130623984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149010935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42065373,0.00214329,0.57423705,0.0010886755,0.00053815416,0.000996472,0.000021954907,0.00011527785,0.00020537815],"genre_scores_gemma":[0.91051733,0.00010345543,0.08915615,0.00008964811,0.00004875037,0.000052609874,0.0000027615522,0.000008083969,0.000021199681],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963562,0.0014450168,0.00060300605,0.0002728101,0.0011648387,0.00015815329],"domain_scores_gemma":[0.99758905,0.0003620064,0.00062960957,0.0006125102,0.0007737758,0.000033055883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006755449,0.00013075149,0.00024425026,0.000032496773,0.0002445236,0.00016278082,0.00056544103,0.000059917038,0.000021339429],"category_scores_gemma":[0.001643712,0.000080219776,0.00010991063,0.00034852696,0.00016113164,0.00093946414,0.00019861119,0.00027259727,1.6705147e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027910788,0.0025697115,0.105774894,0.0034264957,0.0013816053,0.000022075845,0.16235024,0.003580648,0.0027645475,0.08245988,0.0042203777,0.6286585],"study_design_scores_gemma":[0.015039379,0.0017591617,0.13354468,0.0019704048,0.0007472065,0.0008216354,0.031441618,0.020038273,0.50994515,0.27633527,0.006539133,0.0018180872],"about_ca_topic_score_codex":0.000052299823,"about_ca_topic_score_gemma":0.000012913937,"teacher_disagreement_score":0.62684035,"about_ca_system_score_codex":0.000121242214,"about_ca_system_score_gemma":0.00039089494,"threshold_uncertainty_score":0.32712674},"labels":[],"label_agreement":null},{"id":"W4361275045","doi":"10.1007/s11219-023-09621-9","title":"Machine learning application development: practitioners’ insights","year":2023,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Best practice; Leverage (statistics); Computer science; Engineering management; Process (computing); Software development process; Software development; Quality (philosophy); Software; Knowledge management; Software engineering; Data science; Engineering; Artificial intelligence","score_opus":0.0405552949918816,"score_gpt":0.3248114528857969,"score_spread":0.2842561578939153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361275045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038325787,0.00028565573,0.9586843,0.0006819536,0.00032834287,0.00010632115,7.768603e-7,0.0015063456,0.00008048837],"genre_scores_gemma":[0.8426002,0.00023473283,0.15523517,0.00017798203,0.00032343264,0.000056721776,0.000056337525,0.000045995963,0.0012693781],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977593,0.00025726823,0.0004153517,0.00031048222,0.000852966,0.00040462727],"domain_scores_gemma":[0.99785507,0.0011389928,0.00018570936,0.000346404,0.0002508054,0.00022302379],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020170088,0.00014231875,0.00015895927,0.00039314755,0.00061754556,0.00033308286,0.0007709584,0.000079596,0.00001927998],"category_scores_gemma":[0.002966557,0.0001356633,0.00006540035,0.0012345,0.000028019487,0.0007691055,0.00026359226,0.0008028084,0.0007995388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027898508,0.00019199212,0.18225074,0.00019211313,0.00019313862,0.000239699,0.015186098,0.008089398,0.0015136554,0.01765336,0.002779831,0.7716821],"study_design_scores_gemma":[0.001286801,0.00012866982,0.49385664,0.00012356899,0.000008561686,0.00050895684,0.000303261,0.015416118,0.0018831982,0.014546155,0.4709223,0.001015775],"about_ca_topic_score_codex":0.000013115445,"about_ca_topic_score_gemma":0.0000058619867,"teacher_disagreement_score":0.80427444,"about_ca_system_score_codex":0.00018654621,"about_ca_system_score_gemma":0.00026811167,"threshold_uncertainty_score":0.9999785},"labels":[],"label_agreement":null},{"id":"W4392591292","doi":"10.1007/s11219-024-09663-7","title":"A comprehensive catalog of refactoring strategies to handle test smells in Java-based systems","year":2024,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Instituto Nacional de Ciência e Tecnologia para Engenharia de Software; Fundação de Amparo à Pesquisa do Estado da Bahia; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Code refactoring; Java; Computer science; Programming language; Software engineering; Operating system; Software","score_opus":0.05475254564650548,"score_gpt":0.3527974695137458,"score_spread":0.2980449238672403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392591292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2538302,0.0021667925,0.74208015,0.00021945157,0.0011467388,0.00019960135,0.000030284296,0.00031161864,0.000015168503],"genre_scores_gemma":[0.98266584,0.000012859692,0.017080007,0.000026624719,0.000126155,0.000013543423,0.0000029348616,0.000022441925,0.000049592058],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974284,0.00021509313,0.00068555045,0.0003758384,0.000806667,0.0004884108],"domain_scores_gemma":[0.99458134,0.0042221923,0.000093203445,0.0005139222,0.00034375783,0.00024556363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014258925,0.00019806478,0.00037483042,0.0006021703,0.000080975304,0.00085643545,0.00094707264,0.00009238979,0.000008512197],"category_scores_gemma":[0.0016285805,0.00018117079,0.00010986341,0.0011037594,0.000050735413,0.0006222518,0.00018325177,0.0006598628,0.00004404885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016506016,0.0011331018,0.47347936,0.01294166,0.0005132713,0.0038401384,0.0333253,0.34280914,0.052761897,0.017984822,0.005861834,0.05518443],"study_design_scores_gemma":[0.0043330677,0.002974535,0.8407213,0.014870934,0.000054123848,0.0014444812,0.0045387014,0.061296523,0.03120124,0.008227777,0.02662834,0.0037089933],"about_ca_topic_score_codex":0.0004074642,"about_ca_topic_score_gemma":0.000023365965,"teacher_disagreement_score":0.72883564,"about_ca_system_score_codex":0.00030322283,"about_ca_system_score_gemma":0.0007869947,"threshold_uncertainty_score":0.82586265},"labels":[],"label_agreement":null},{"id":"W4413024210","doi":"10.1007/s11219-025-09727-2","title":"Investigating adversarial attacks in software analytics via machine learning explainability","year":2025,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software analytics; Analytics; Computer science; Adversarial system; Software; Artificial intelligence; Software engineering; Machine learning; Data science; Software development; Software construction; Operating system","score_opus":0.026464954080557494,"score_gpt":0.32756341787785526,"score_spread":0.30109846379729777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413024210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061861638,0.0002464135,0.9341301,0.001571724,0.0013636991,0.00020398073,0.0000031693644,0.00045795477,0.00016136316],"genre_scores_gemma":[0.61245203,0.000017555989,0.38613567,0.00073501153,0.00030916007,0.00001014785,0.000012927116,0.000031661686,0.00029583764],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935946,0.0022844453,0.0015198212,0.00081481086,0.00091172324,0.0008746293],"domain_scores_gemma":[0.9955427,0.002109006,0.0007909643,0.000822451,0.0004236218,0.000311256],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006713177,0.00043840217,0.0007253532,0.0006158717,0.0010591315,0.0005039972,0.0018502653,0.0002925392,0.000062811676],"category_scores_gemma":[0.020383341,0.0004483873,0.00029663136,0.0017938247,0.00022616083,0.00134307,0.0010788555,0.0034703831,0.000016550792],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003703893,0.000111268964,0.7744151,0.0001351934,0.0000739831,0.00007694494,0.0022724392,0.14188477,0.000049337366,0.0033542046,0.00014361246,0.07744615],"study_design_scores_gemma":[0.008175482,0.00038919543,0.2938416,0.0011270166,0.00012782608,0.0003229644,0.0014871256,0.46060053,0.00030701063,0.22468159,0.006495264,0.002444381],"about_ca_topic_score_codex":0.00043302952,"about_ca_topic_score_gemma":0.00018358792,"teacher_disagreement_score":0.5505904,"about_ca_system_score_codex":0.0008084079,"about_ca_system_score_gemma":0.0007868223,"threshold_uncertainty_score":0.9997968},"labels":[],"label_agreement":null}]}