{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":51,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":51,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a1e852829d09","filters":{"venue":"Software Quality Journal"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0318959053260117,"gpt":0.3304311199025112,"spread":0.2985352145764995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006367042,0.0001453744,0.0002490614,0.0001162522,0.0002303039,0.0003905287,0.0004636247,0.0000796656,0.00009655744],"category_scores_gemma":[0.004704433,0.0001336297,0.00008246922,0.0003119955,0.0001431119,0.00094655,0.00008969015,0.0005234445,0.000007536692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002610641,"about_ca_system_score_gemma":0.0003409733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003925326,"about_ca_topic_score_gemma":0.0001301991,"domain_scores_codex":[0.9972105,0.00102571,0.0006159425,0.0003444035,0.0004939741,0.0003094516],"domain_scores_gemma":[0.9983265,0.0006057774,0.0001540147,0.0004014829,0.0003291235,0.0001830438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000116895,0.0007743562,0.6923544,0.0002088196,0.0000985501,0.00006041231,0.06421291,0.0003732032,0.0005407538,0.1573096,0.002104677,0.08184545],"study_design_scores_gemma":[0.002900564,0.00070362,0.1777315,0.0003435652,0.00002499272,0.0008626055,0.002646427,0.002121191,0.003136615,0.7894859,0.01882635,0.001216591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3267286,0.0002234336,0.6717445,0.0005862222,0.0002467025,0.00008115736,0.000007886144,0.00005984826,0.0003216604],"genre_scores_gemma":[0.9274701,0.00001644448,0.07212339,0.0003242995,0.00001524786,0.000004077695,2.894368e-7,0.000006093976,0.00004003687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6321763,"threshold_uncertainty_score":0.5631985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1178730492397492,"gpt":0.4112353565501069,"spread":0.2933623073103577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007434753,0.0003698261,0.0005890381,0.0002547047,0.0006951986,0.0005364856,0.002140133,0.0002092455,0.000007778001],"category_scores_gemma":[0.03063371,0.0002550683,0.0002934762,0.001253316,0.0003495319,0.002621786,0.0006128036,0.002463571,5.057668e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002215804,"about_ca_system_score_gemma":0.0005882696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002857804,"about_ca_topic_score_gemma":0.000006720199,"domain_scores_codex":[0.9959363,0.001000191,0.0008600627,0.0005688756,0.0009779107,0.0006566467],"domain_scores_gemma":[0.9918966,0.004127741,0.0009013147,0.001607731,0.001256767,0.0002098113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000378135,0.0001158606,0.02504007,0.000406257,0.0001777286,0.00005615183,0.003165705,0.6592517,0.006631074,0.0118735,0.0001326432,0.2931114],"study_design_scores_gemma":[0.0007655829,0.0001392377,0.03856783,0.0001294997,0.00007912035,0.001806605,0.0006376865,0.05027962,0.008796374,0.8974959,0.0001932723,0.001109317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.232389,0.000442923,0.7642813,0.0005441096,0.001806843,0.0001862124,0.000008585816,0.0003387188,0.000002222663],"genre_scores_gemma":[0.3230781,0.000007059948,0.6765154,0.00006986452,0.0002891102,0.000002525797,0.000001451705,0.00002228621,0.0000141808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8856224,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2236840213549557,"gpt":0.3779922822970453,"spread":0.1543082609420896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003925539,0.000281374,0.0004755127,0.0003610355,0.0004718913,0.0002332665,0.001397548,0.0002070321,0.00002658641],"category_scores_gemma":[0.007430844,0.0002622787,0.0001808591,0.0005939433,0.00007773716,0.000916869,0.000243889,0.0007916695,0.000004409028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133697,"about_ca_system_score_gemma":0.0004771345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004931234,"about_ca_topic_score_gemma":0.0001212732,"domain_scores_codex":[0.9963475,0.0006729981,0.0009515778,0.0005312333,0.0008323308,0.0006642903],"domain_scores_gemma":[0.9945363,0.002716269,0.00046134,0.001022082,0.0008179394,0.0004460883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001979104,0.002548217,0.74652,0.0002102876,0.0002965702,0.002368192,0.04157648,0.000672715,0.0002611104,0.0005468196,0.0007777147,0.2040239],"study_design_scores_gemma":[0.06984302,0.06352174,0.5410385,0.002235792,0.0009475328,0.07507647,0.1468926,0.01248893,0.03082224,0.0439406,0.001575097,0.01161748],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5301688,0.00004155021,0.4687733,0.000007229631,0.0004666298,0.00032942,0.000006097092,0.0002042337,0.000002689392],"genre_scores_gemma":[0.8502163,0.000001551069,0.1493643,0.00002546719,0.0003000463,0.00003866416,0.000001643131,0.0000359895,0.00001611911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3200474,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04201576491452648,"gpt":0.3294821212926332,"spread":0.2874663563781067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654252,0.0001770978,0.0002337297,0.0002254558,0.0003359096,0.0004588585,0.0005562068,0.0001590406,0.00001112296],"category_scores_gemma":[0.00559213,0.0001867031,0.0001146054,0.0005210901,0.0000443427,0.001008295,0.0001479933,0.000771299,0.00002007826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004752032,"about_ca_system_score_gemma":0.0001639666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003873508,"about_ca_topic_score_gemma":0.000001285846,"domain_scores_codex":[0.9975289,0.0003626486,0.0005148526,0.0003678534,0.0007844833,0.0004412498],"domain_scores_gemma":[0.9974978,0.001132809,0.000254052,0.0004493097,0.00042066,0.0002453421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001242163,0.0004447578,0.04035271,0.0002590463,0.0001789774,0.00006599644,0.002965633,0.3840916,0.1304555,0.00189507,0.003632712,0.4355338],"study_design_scores_gemma":[0.0009167182,0.0001241652,0.008875567,0.000229825,0.00001968971,0.00149456,0.00006314544,0.9773676,0.007132694,0.001409538,0.001729734,0.0006367012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08397571,0.00004423807,0.9129728,0.0001468765,0.00227773,0.00008847454,0.000001211031,0.0004629096,0.0000300666],"genre_scores_gemma":[0.4330568,0.00001877975,0.5659333,0.000105666,0.0007770212,0.000003563288,0.000005985443,0.00003326248,0.00006563835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5932761,"threshold_uncertainty_score":0.7613533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.584142689272458,"gpt":0.5376677499733624,"spread":0.04647493929909563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01546414,0.0002186644,0.0004379614,0.0003398825,0.0004600593,0.0002236596,0.003324625,0.00009484882,0.00000826175],"category_scores_gemma":[0.03321121,0.0001478425,0.0001197568,0.002055946,0.0002403455,0.000959822,0.002167336,0.000841115,0.000003120526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005942535,"about_ca_system_score_gemma":0.0005002879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003935463,"about_ca_topic_score_gemma":0.00003114349,"domain_scores_codex":[0.9956052,0.0005114645,0.0009157251,0.0005113793,0.001800927,0.0006552886],"domain_scores_gemma":[0.9847707,0.01125903,0.0003041588,0.002209121,0.001088585,0.0003684673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001116269,0.0001481847,0.9314846,0.0003164432,0.0005754434,0.0001114976,0.008774693,0.004384493,0.0003427929,0.002143629,0.002318879,0.0492877],"study_design_scores_gemma":[0.002051297,0.0006184678,0.940396,0.0003880695,0.0001342592,0.001238568,0.008681998,0.01089276,0.005703185,0.02467877,0.003508594,0.001708083],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3805755,0.0005739692,0.6176198,0.0005673098,0.0004278945,0.0001170825,0.000014852,0.0001020964,0.000001443907],"genre_scores_gemma":[0.6083691,0.00001341927,0.3912923,0.000142935,0.0001579015,6.461445e-7,0.000001290897,0.00001526781,0.000007180141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2277935,"threshold_uncertainty_score":0.9749325,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1403867965763272,"gpt":0.4310662005548037,"spread":0.2906794039784765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006949306,0.000273748,0.0005860626,0.0004527429,0.0002020556,0.0001176045,0.001434333,0.0001372151,0.00002996096],"category_scores_gemma":[0.02011483,0.0002433185,0.0001469601,0.0009028541,0.0001518246,0.001679917,0.000276834,0.0006596664,0.00002327085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001777353,"about_ca_system_score_gemma":0.0004649703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001419931,"about_ca_topic_score_gemma":0.0000105522,"domain_scores_codex":[0.9942843,0.001459595,0.001373684,0.000351362,0.001903675,0.0006273479],"domain_scores_gemma":[0.9927788,0.00408783,0.000644152,0.0009740163,0.001027705,0.0004874312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005803139,0.001078918,0.9710569,0.0001017372,0.0000806953,0.000007084495,0.0106046,0.005532344,0.0001794804,0.000351264,0.0001258972,0.01082309],"study_design_scores_gemma":[0.0007039399,0.0006565462,0.995138,0.0001364611,0.0000117033,0.00004968108,0.0008178527,0.00006608856,0.001761603,0.0002589419,0.00009649785,0.0003026887],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8023817,0.00009313579,0.1967677,0.00008356012,0.0002285897,0.0002310653,0.00001488247,0.0001946355,0.000004723076],"genre_scores_gemma":[0.951821,0.000007681148,0.04787195,0.0001434494,0.0001037695,0.00001119563,0.000004465664,0.00002256535,0.00001387343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1494393,"threshold_uncertainty_score":0.9922239,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08279210101335747,"gpt":0.3992890786303233,"spread":0.3164969776169658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02889859,0.0006457652,0.001398985,0.0007865005,0.0009206492,0.0008841273,0.002071967,0.0005408289,0.00003435399],"category_scores_gemma":[0.01221715,0.0006378393,0.000773237,0.00147366,0.0002436185,0.001813744,0.0007145758,0.001483002,0.000009560914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007028953,"about_ca_system_score_gemma":0.0008714026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004532177,"about_ca_topic_score_gemma":0.0002916127,"domain_scores_codex":[0.9911746,0.0006720194,0.002689131,0.001516405,0.001809626,0.002138183],"domain_scores_gemma":[0.9848168,0.01045665,0.0006047134,0.001410082,0.001683941,0.001027801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002512535,0.002466589,0.2879926,0.006681212,0.0009092254,0.00008316275,0.01174858,0.08919263,0.002410642,0.02910566,0.002897498,0.5639997],"study_design_scores_gemma":[0.02167155,0.001391439,0.2100449,0.0009882029,0.0002227809,0.0003832002,0.002616488,0.5284654,0.006903578,0.2127538,0.007416884,0.007141692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1241985,0.0005431335,0.872144,0.001097119,0.0002090219,0.001185432,0.0001671195,0.0004502744,0.0000053418],"genre_scores_gemma":[0.2337992,0.0001024311,0.7642924,0.0007604843,0.0003983201,0.0002292554,0.0000477124,0.00009046024,0.0002797021],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.556858,"threshold_uncertainty_score":0.9999533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05220059938723919,"gpt":0.3183624776426233,"spread":0.2661618782553841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007304319,0.0001893923,0.0002378278,0.00009150283,0.0002737211,0.0003614733,0.0005322899,0.0003847609,0.00002038356],"category_scores_gemma":[0.008764965,0.0001468616,0.00001549613,0.000477643,0.00009552455,0.001517691,0.0002302377,0.001233025,4.11047e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002042921,"about_ca_system_score_gemma":0.0009194321,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1677604,"about_ca_topic_score_gemma":0.0475304,"domain_scores_codex":[0.9982699,0.0002049634,0.0004489138,0.0003567291,0.0004039915,0.0003155211],"domain_scores_gemma":[0.9961141,0.002751506,0.0002653205,0.0003055841,0.0002367434,0.0003267076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008730395,0.00001318652,0.9597453,0.00001344211,0.00001186564,0.00005467831,0.001791883,0.00003231317,0.0001074525,0.0004784145,0.00103105,0.03671168],"study_design_scores_gemma":[0.0007236245,0.00009340148,0.975002,0.0003973954,0.00001058046,0.0002432541,0.0004300727,0.0001321067,0.000814217,0.0107132,0.01076078,0.0006793916],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6971951,0.0004714922,0.2996803,0.002019011,0.0003183105,0.00007109377,0.00004026361,0.0002002039,0.000004274971],"genre_scores_gemma":[0.7921905,0.00009375245,0.207173,0.0003558458,0.0001232334,0.0000145871,0.000001051262,0.00001202841,0.00003601331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.12023,"threshold_uncertainty_score":0.9995846,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.152923259708518,"gpt":0.3828906023119051,"spread":0.2299673426033871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01214387,0.0002107183,0.0003140349,0.0001368621,0.001114433,0.0007361775,0.0015282,0.0001250575,0.000009643602],"category_scores_gemma":[0.01872822,0.0001578252,0.0001074707,0.0004499736,0.0001570918,0.0008166383,0.0005503035,0.001333142,0.00003478362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329685,"about_ca_system_score_gemma":0.0001386133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006892381,"about_ca_topic_score_gemma":0.00001527295,"domain_scores_codex":[0.9962265,0.0008819788,0.0007230911,0.0004175711,0.00119776,0.0005530662],"domain_scores_gemma":[0.9720845,0.02597571,0.0003355311,0.0009799869,0.0002565739,0.0003676935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004837506,0.00001798618,0.9512967,0.00003761096,0.00002340327,0.000002215851,0.002323008,0.0004078469,0.000007401459,0.003308408,0.0001216236,0.04244892],"study_design_scores_gemma":[0.0003848453,0.000086572,0.9800092,0.00004872838,0.000008195246,0.0000938964,0.0002168739,0.0004189464,0.00003428009,0.0169165,0.001538271,0.0002437078],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4581633,0.0001588804,0.5408065,0.0003932184,0.0001440566,0.0001186968,0.000003088492,0.0002013137,0.00001092604],"genre_scores_gemma":[0.9752296,0.000008575184,0.02412532,0.0001579686,0.0003091562,0.00001905401,0.000001610452,0.00001994792,0.0001287775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5170663,"threshold_uncertainty_score":0.9895374,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08691323916499845,"gpt":0.4021292808525964,"spread":0.315216041687598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01034824,0.0003098651,0.0004582802,0.000508911,0.0002797236,0.0009939962,0.004538456,0.0001141317,0.00001155609],"category_scores_gemma":[0.009332457,0.0002408376,0.0000819554,0.00172421,0.00003940978,0.001047913,0.0003690919,0.001482444,0.00003584041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009142022,"about_ca_system_score_gemma":0.0007625784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007121095,"about_ca_topic_score_gemma":0.0002993003,"domain_scores_codex":[0.9938954,0.002059688,0.0008243967,0.0007813437,0.001751454,0.0006877063],"domain_scores_gemma":[0.9935262,0.00337587,0.0002325725,0.002360227,0.0002430006,0.000262127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005081085,0.006029503,0.4325927,0.0001310827,0.0002475752,0.004532951,0.1505179,0.09887799,0.00001722045,0.02359583,0.01764126,0.2653079],"study_design_scores_gemma":[0.004071651,0.001061892,0.9511325,0.0003581156,0.00001323414,0.0007593372,0.01141644,0.008847158,0.000005231044,0.02136545,0.0002458251,0.0007231396],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1189636,0.000460517,0.8767722,0.001963479,0.0004232324,0.001137042,0.00001954148,0.0002352878,0.00002505376],"genre_scores_gemma":[0.9017245,0.0000102374,0.09754531,0.0003149806,0.0003070506,0.00003374061,0.000009705334,0.00002026539,0.00003422977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7827609,"threshold_uncertainty_score":0.9990124,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09743104232199579,"gpt":0.355633719165051,"spread":0.2582026768430552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004675707,0.000193058,0.0002345812,0.0002280286,0.0003459307,0.001226812,0.001177792,0.00006870763,0.00001043546],"category_scores_gemma":[0.001375974,0.0001853084,0.00005241114,0.0004088125,0.00002941906,0.001744978,0.0001620848,0.0005622388,0.00002006747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064366,"about_ca_system_score_gemma":0.0003114378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002463543,"about_ca_topic_score_gemma":0.00000348128,"domain_scores_codex":[0.9970349,0.0006945549,0.0005149773,0.0005413091,0.000806656,0.0004075695],"domain_scores_gemma":[0.9978375,0.0004262479,0.00018762,0.0008286879,0.0002103449,0.0005095694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002010351,0.0007158715,0.02876644,0.00003388177,0.00004739369,0.00008970101,0.02594969,0.0006934396,0.0006933933,0.0001893273,0.0009850488,0.9418157],"study_design_scores_gemma":[0.005005919,0.002835919,0.9318355,0.00009625869,0.00006135779,0.001357053,0.007119341,0.03181051,0.001086824,0.01655468,0.000176263,0.002060394],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1196057,0.000180649,0.8792096,0.000191868,0.0002010762,0.0002548835,6.554234e-7,0.0003530731,0.000002537217],"genre_scores_gemma":[0.8213772,0.000006876826,0.178004,0.0001496601,0.0003460977,0.000009220536,0.000001149701,0.00001620389,0.00008957955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9397553,"threshold_uncertainty_score":0.99981,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5757960133181265,"gpt":0.376091517068576,"spread":0.1997044962495504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004921153,0.0001829125,0.0002483086,0.0002504717,0.0001832324,0.0003915478,0.001257075,0.00006563312,0.000008001637],"category_scores_gemma":[0.02115113,0.0001285566,0.0001432411,0.0003467142,0.00005641729,0.0005673623,0.000301106,0.0004900681,0.00001488588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002089402,"about_ca_system_score_gemma":0.0005577313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000537296,"about_ca_topic_score_gemma":0.000003439754,"domain_scores_codex":[0.996961,0.0007252058,0.0004484933,0.0002487438,0.001177189,0.0004393554],"domain_scores_gemma":[0.9901539,0.007831263,0.0001617918,0.0008344755,0.0005547733,0.0004637757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001673395,0.00008364884,0.003221072,0.00005405009,0.0001584518,0.00008262026,0.00760406,0.8834888,0.0005530599,0.01750415,0.02121721,0.06586556],"study_design_scores_gemma":[0.006263776,0.009162107,0.04214226,0.00291095,0.0001684575,0.001719555,0.002787843,0.3331803,0.06014803,0.5067683,0.02809354,0.006654894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.148411,0.000062104,0.8504799,0.0004910531,0.0002252998,0.0001458319,0.000005708802,0.0001717048,0.000007348427],"genre_scores_gemma":[0.5027377,0.00001572375,0.4966143,0.0003242878,0.00007797565,0.00001589133,4.258431e-7,0.00002756309,0.0001861054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5503085,"threshold_uncertainty_score":0.9870941,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1482975576947659,"gpt":0.3486422211534545,"spread":0.2003446634586886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002918321,0.0002582475,0.0006806768,0.0006671568,0.0001902245,0.00008106392,0.0008837745,0.00009348449,0.00001663732],"category_scores_gemma":[0.006543912,0.0002266434,0.0002837258,0.001229073,0.0001099914,0.0006374948,0.0002044867,0.0004437562,0.000001316996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005075867,"about_ca_system_score_gemma":0.0001568102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003465399,"about_ca_topic_score_gemma":0.000006721698,"domain_scores_codex":[0.9973505,0.0004662917,0.0008477188,0.0004574599,0.0004843807,0.0003936136],"domain_scores_gemma":[0.9969968,0.001040309,0.0004610084,0.0007688848,0.0005387964,0.0001942648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000769576,0.0001973842,0.08551835,0.0002395836,0.001091221,0.00004570931,0.005008509,0.7523146,0.0003364177,0.001390688,0.0000314385,0.1537492],"study_design_scores_gemma":[0.002944484,0.000860368,0.2070045,0.0006081559,0.002129638,0.0003576378,0.0007444761,0.5357578,0.01384427,0.2321064,0.0001553092,0.003486971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07696815,0.0009743783,0.9211423,0.0000776786,0.0003292615,0.00008027376,0.00001084073,0.0004125111,0.000004573316],"genre_scores_gemma":[0.1770522,0.00004256377,0.822745,0.00007127663,0.00005435056,0.000004064989,0.000002645346,0.00001593518,0.00001197369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2307157,"threshold_uncertainty_score":0.9242249,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02904989664232336,"gpt":0.3048473787423666,"spread":0.2757974821000432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504302,0.0002230816,0.00030611,0.0001864277,0.0001531683,0.0002229574,0.001137787,0.0001074437,0.00002117592],"category_scores_gemma":[0.002223321,0.0002138562,0.0001047593,0.0004868187,0.0000218388,0.001574769,0.00008452978,0.0005742177,0.000003245964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007693525,"about_ca_system_score_gemma":0.0002446241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005898482,"about_ca_topic_score_gemma":5.664475e-7,"domain_scores_codex":[0.998017,0.0001065275,0.0006173477,0.000335671,0.0006018424,0.0003215915],"domain_scores_gemma":[0.9979355,0.0002585019,0.000352899,0.0006925045,0.0005421983,0.0002184247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001158148,0.001647702,0.01544958,0.0004039277,0.0001853237,0.0000762589,0.003816595,0.7097818,0.01713046,0.08667268,0.00287873,0.1618411],"study_design_scores_gemma":[0.001929291,0.001915794,0.06265328,0.000550375,0.0001118029,0.00185184,0.00004856789,0.5850317,0.05685871,0.283722,0.002186927,0.00313965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02927721,0.0002663352,0.9683663,0.0006690099,0.0002644911,0.00009595634,0.00001431103,0.001040037,0.000006342192],"genre_scores_gemma":[0.3569701,0.0000324624,0.6426128,0.0001643524,0.0001844283,0.00000130261,0.000006606057,0.0000143753,0.00001359272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3276929,"threshold_uncertainty_score":0.8720804,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07791100068699204,"gpt":0.3205401042144391,"spread":0.242629103527447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00774589,0.0001778628,0.000353528,0.0004302803,0.0002813817,0.0001617311,0.0008170361,0.0001166602,0.00001515655],"category_scores_gemma":[0.005116115,0.0001770524,0.0001221682,0.0005381191,0.000262145,0.001886708,0.0002101005,0.0006247174,0.000002797424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007674168,"about_ca_system_score_gemma":0.0001941113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005215455,"about_ca_topic_score_gemma":0.000006814317,"domain_scores_codex":[0.9972434,0.00009509905,0.001023945,0.000207664,0.001012364,0.0004175482],"domain_scores_gemma":[0.9944289,0.003469448,0.0004944919,0.0005286477,0.0007623546,0.000316133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003711701,0.001346404,0.694329,0.00230142,0.0006390602,0.00003163246,0.01606688,0.03054337,0.003807103,0.07504931,0.0002601426,0.1752545],"study_design_scores_gemma":[0.001200247,0.0002308019,0.9579023,0.0001483751,0.00002630358,0.000557714,0.00107507,0.002034597,0.003633794,0.03254324,0.0001331082,0.0005144881],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.349833,0.0001367109,0.6496003,0.00002322401,0.0001541815,0.00008481683,0.000009046966,0.0001316919,0.0000269863],"genre_scores_gemma":[0.6729484,0.00001700409,0.3269421,0.00002420495,0.00004795047,0.000001835532,0.000003059221,0.00001014343,0.000005318293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3231153,"threshold_uncertainty_score":0.7219988,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05973784110211131,"gpt":0.3694728962888241,"spread":0.3097350551867127,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004178948,0.0001947202,0.0004851792,0.0004343114,0.00007733444,0.0001554385,0.001423954,0.0001099782,0.00005874952],"category_scores_gemma":[0.001690533,0.000175115,0.0001235822,0.00104587,0.00003030021,0.0005189037,0.0004678425,0.0009321042,0.00007738193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001862599,"about_ca_system_score_gemma":0.0003697567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006367522,"about_ca_topic_score_gemma":0.0001099011,"domain_scores_codex":[0.9961197,0.0006633212,0.0008098973,0.0004668787,0.001289224,0.0006509519],"domain_scores_gemma":[0.9972848,0.001124191,0.0002074834,0.0008761083,0.0002957201,0.0002116652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002817,0.001062072,0.9769372,0.00006943525,0.00003099132,0.0000557639,0.0192068,0.0004974657,0.00009467009,0.00004508367,0.0006682539,0.001304056],"study_design_scores_gemma":[0.003511086,0.0009943951,0.9871629,0.0001316416,0.000006040178,0.0001166384,0.003837762,0.001979762,0.0002747253,0.0007613236,0.0008537408,0.0003699149],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8690603,0.0001114442,0.1295436,0.0001584692,0.0005166353,0.0004389801,0.000005446087,0.0001364511,0.00002866065],"genre_scores_gemma":[0.9831858,0.000006204973,0.01640411,0.00009486674,0.00006495244,0.00001193826,8.025594e-7,0.00002073967,0.0002105473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1141255,"threshold_uncertainty_score":0.7140982,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04988978108270573,"gpt":0.3339838023361344,"spread":0.2840940212534287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001487091,0.0001820573,0.0002168477,0.0001646547,0.0005438769,0.0005476035,0.0005632787,0.0000880776,0.00002313949],"category_scores_gemma":[0.005395107,0.000126981,0.00006033614,0.0003859496,0.00007277176,0.001874154,0.0002662126,0.0002614274,0.000008956864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195594,"about_ca_system_score_gemma":0.0001250564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000198795,"about_ca_topic_score_gemma":0.000001711292,"domain_scores_codex":[0.9983407,0.0002003868,0.0004376918,0.0003207053,0.000337717,0.0003628411],"domain_scores_gemma":[0.9974597,0.001523153,0.0002349331,0.0003206391,0.0002575979,0.0002039565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001764763,0.00004921671,0.08451471,0.00006276478,0.00008882245,0.00008110562,0.00737031,0.00007732076,0.01801441,0.006779823,0.001686759,0.8812571],"study_design_scores_gemma":[0.005898267,0.001370508,0.8226455,0.00610596,0.0001338143,0.01577615,0.00700407,0.02334858,0.01001722,0.07460336,0.0267306,0.006365952],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2505768,0.0001036028,0.7460604,0.0006664534,0.000241705,0.00005235616,0.000002342123,0.002244624,0.0000517521],"genre_scores_gemma":[0.445788,0.00004419975,0.5539562,0.00007982361,0.00008552738,0.00000594736,2.383291e-7,0.00001087974,0.00002923869],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8748912,"threshold_uncertainty_score":0.6458837,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.114960695019113,"gpt":0.3726311614194243,"spread":0.2576704664003113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004668161,0.0002406303,0.0007748069,0.001159911,0.0001400146,0.0001269057,0.001076136,0.0001583156,0.00006778838],"category_scores_gemma":[0.02273094,0.0002151962,0.0005154261,0.002415613,0.00009556127,0.0005261526,0.0001933856,0.000569017,0.000004362138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001347486,"about_ca_system_score_gemma":0.0001896127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005443571,"about_ca_topic_score_gemma":0.000007077355,"domain_scores_codex":[0.996134,0.0007154867,0.001071363,0.000329138,0.001295467,0.0004545588],"domain_scores_gemma":[0.9888532,0.008791779,0.0006679078,0.0007058204,0.0007094962,0.0002717683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001046441,0.00009904723,0.9417304,0.0001967579,0.0009136965,0.000003601516,0.006598128,0.02969356,0.0004330252,0.0003009701,0.0001395324,0.01988077],"study_design_scores_gemma":[0.0003860092,0.0001373059,0.9836077,0.00007420144,0.0001344156,0.00001477549,0.0002229743,0.009626838,0.005078158,0.0003914375,0.00005413783,0.0002720303],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4702005,0.00003874399,0.5293165,0.00004514489,0.0001942511,0.00005183779,0.00001601848,0.0001335643,0.00000343318],"genre_scores_gemma":[0.9077847,0.000003516716,0.09209059,0.00002829721,0.00005548071,0.000001318427,0.00000709314,0.00001712476,0.00001185315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4375842,"threshold_uncertainty_score":0.985501,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08799721980182837,"gpt":0.4182070965023177,"spread":0.3302098767004893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003686453,0.000152654,0.0002347833,0.0001040393,0.0003429907,0.0002416365,0.001020319,0.00007053191,0.000008183885],"category_scores_gemma":[0.003896878,0.0001030492,0.0002043932,0.0003566206,0.00008425364,0.0001881759,0.0001512345,0.000442092,0.00000805231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008575178,"about_ca_system_score_gemma":0.0001451167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004440283,"about_ca_topic_score_gemma":0.000006481721,"domain_scores_codex":[0.9973589,0.0003424578,0.0005560108,0.0002563197,0.001056349,0.0004299933],"domain_scores_gemma":[0.9933971,0.005144774,0.0002667953,0.0005750476,0.0005255062,0.00009078209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001339865,0.000735378,0.04905785,0.0002276393,0.00008165657,0.000009013556,0.0008028892,0.03548982,0.0007285386,0.03127603,0.004958478,0.8764987],"study_design_scores_gemma":[0.004485864,0.006264903,0.6634488,0.0006544281,0.00005073468,0.0002100139,0.0001227296,0.1636031,0.002943901,0.1537294,0.003423954,0.001062135],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4195167,0.0001547773,0.578863,0.0004886228,0.0003502168,0.0003988319,0.000004403971,0.0002106423,0.00001282715],"genre_scores_gemma":[0.8164554,0.000002119008,0.183037,0.00007146276,0.0002739095,0.00005580355,0.000004587196,0.00001920056,0.00008046856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8754366,"threshold_uncertainty_score":0.4665208,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08125202920087467,"gpt":0.3986317212269463,"spread":0.3173796920260716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005308088,0.0003354223,0.0005751696,0.0002866951,0.000769753,0.0007706695,0.001939867,0.0001160481,0.00004151208],"category_scores_gemma":[0.006972816,0.0003017668,0.0001893072,0.0004253848,0.00007255397,0.0007478031,0.0005355934,0.001263742,0.00005351538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795639,"about_ca_system_score_gemma":0.0006495728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001304527,"about_ca_topic_score_gemma":0.0000460884,"domain_scores_codex":[0.9964195,0.0001880406,0.001004657,0.0005708791,0.001051273,0.0007656082],"domain_scores_gemma":[0.9943773,0.003227397,0.0003574182,0.0007635722,0.0008377911,0.0004365356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001472504,0.002268085,0.5921211,0.0004525614,0.0009207936,0.0001618214,0.08122735,0.00271942,0.000856224,0.0009051199,0.005626958,0.3125933],"study_design_scores_gemma":[0.009780193,0.002685521,0.925217,0.0006444354,0.00008820319,0.001372578,0.003527198,0.02047654,0.007742492,0.01246911,0.01222488,0.003771825],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4121888,0.00002135994,0.5855163,0.0000733561,0.001314805,0.0004781139,0.000003654624,0.0003992131,0.000004375589],"genre_scores_gemma":[0.3688814,2.06677e-7,0.6306214,0.00005086382,0.0002446324,0.0001008639,0.000003193084,0.00002147847,0.00007596906],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3330959,"threshold_uncertainty_score":0.9999434,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1169295380758614,"gpt":0.3729647007733453,"spread":0.2560351626974839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001442394,0.000242057,0.0002518931,0.0004701167,0.0001774689,0.0003549128,0.00067694,0.0001182176,0.000003566529],"category_scores_gemma":[0.0004292991,0.0002525142,0.0001244637,0.0006493354,0.00001323018,0.00146698,0.0001990846,0.0005928114,0.000004842871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004224909,"about_ca_system_score_gemma":0.0001018819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000154595,"about_ca_topic_score_gemma":0.000004296041,"domain_scores_codex":[0.9980154,0.00009643077,0.0006192272,0.0003601722,0.0004543028,0.0004544466],"domain_scores_gemma":[0.998778,0.0003427463,0.0002379456,0.0004267936,0.0001065752,0.000107883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006919587,0.00006040797,0.0009000964,0.00005974573,0.00002562916,0.00009306658,0.000596613,0.9915606,0.00001763409,0.0007744789,0.000003232011,0.005901568],"study_design_scores_gemma":[0.000944057,0.00004094182,0.001625395,0.0002929202,0.00001504639,0.0001408669,0.00004822887,0.9923196,0.00009571764,0.003297013,0.0007086981,0.0004714717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0316211,0.0003339433,0.9665745,0.00004316888,0.0004327491,0.0002033561,0.000001921013,0.0007862074,0.000002987283],"genre_scores_gemma":[0.1772056,0.00005622156,0.8225607,0.00005851695,0.00007832225,0.000006376064,0.000001403344,0.00002458423,0.000008308593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1455845,"threshold_uncertainty_score":0.9999927,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2567576179198857,"gpt":0.4826588867655611,"spread":0.2259012688456755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1071793,0.0005626433,0.001040677,0.0003962983,0.001434607,0.0006215008,0.002731835,0.0005448909,0.00003580143],"category_scores_gemma":[0.06929023,0.0004712708,0.0007739559,0.001263252,0.0002250514,0.001461199,0.0006007062,0.001710694,0.000008687248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002010119,"about_ca_system_score_gemma":0.002504948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00123193,"about_ca_topic_score_gemma":0.0001552857,"domain_scores_codex":[0.9802424,0.01003974,0.003249559,0.00122495,0.003660314,0.001583075],"domain_scores_gemma":[0.960273,0.0307985,0.002195593,0.002577677,0.003457295,0.0006979331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002800068,0.0003146544,0.0142357,0.0001867794,0.0002454456,0.000001084283,0.002267292,0.05972912,0.001084451,0.01081831,0.002466755,0.9083704],"study_design_scores_gemma":[0.01107181,0.0007184581,0.06345215,0.0004348494,0.000338013,0.0001781244,0.001621355,0.6698915,0.005442594,0.2292525,0.01473255,0.002866056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02178007,0.001112717,0.9727799,0.0008916855,0.001186537,0.001634176,0.00009246745,0.0005069192,0.00001555028],"genre_scores_gemma":[0.05185347,0.00004157792,0.9463701,0.0001245281,0.0009310382,0.0004145986,0.00002946868,0.00006963521,0.0001656049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9055043,"threshold_uncertainty_score":0.9998654,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02811477016643656,"gpt":0.3126412137085472,"spread":0.2845264435421107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002185112,0.0002069104,0.0003063884,0.0002966179,0.0002060906,0.0003368088,0.0009748182,0.00008318647,0.00001972346],"category_scores_gemma":[0.02058557,0.0001721358,0.0001224646,0.000410061,0.00005501793,0.0005254085,0.0002701619,0.000795216,0.00001679164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002450656,"about_ca_system_score_gemma":0.00007455175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005519609,"about_ca_topic_score_gemma":0.00003182158,"domain_scores_codex":[0.9974374,0.000399332,0.0004949472,0.0003686375,0.0007339068,0.0005657681],"domain_scores_gemma":[0.9913775,0.007488403,0.0001580588,0.0005143693,0.000193303,0.0002683169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005858327,0.0001762461,0.955646,0.0000290076,0.0000155526,0.00002042229,0.0007374058,0.0008291244,0.0001672071,0.0005993443,0.0001559961,0.04161788],"study_design_scores_gemma":[0.0008814159,0.0002267933,0.9770135,0.0001608389,0.000003638562,0.000149792,0.00005194082,0.009707811,0.0008735133,0.01044413,0.0001980785,0.0002884975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4762267,0.00007991007,0.5229372,0.0001727877,0.0002612684,0.00006412946,0.000002687952,0.0002283698,0.00002686639],"genre_scores_gemma":[0.9752147,0.00001120805,0.02429132,0.00007014372,0.0003423236,0.0000122598,0.000001184069,0.00001749585,0.00003936582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.498988,"threshold_uncertainty_score":0.9876645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1566925308736148,"gpt":0.3431175947610764,"spread":0.1864250638874616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001600841,0.0001933889,0.000223597,0.0001990545,0.0007751001,0.0004219514,0.001149655,0.00009345727,0.00003267512],"category_scores_gemma":[0.004326076,0.0001883012,0.0001697115,0.0006473822,0.00007429779,0.0002432756,0.00004579213,0.0003008363,0.00004135021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313756,"about_ca_system_score_gemma":0.0001751709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001301505,"about_ca_topic_score_gemma":0.000001190612,"domain_scores_codex":[0.997974,0.0001597305,0.000633137,0.0004066601,0.0004299683,0.0003964823],"domain_scores_gemma":[0.9938838,0.003821452,0.000473415,0.0008533941,0.0007612299,0.0002067461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001531772,0.0007623015,0.07879934,0.0002020147,0.00003519286,0.00001225754,0.0003417954,0.001796258,0.0002739094,0.007490197,0.1070443,0.8032271],"study_design_scores_gemma":[0.003170657,0.0007545563,0.02720484,0.0005097981,0.00006530148,0.0002683369,0.00002378134,0.4179279,0.002426268,0.4660015,0.07956567,0.002081359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002933418,0.000188218,0.9898446,0.002264987,0.0001591139,0.0003537163,0.00001430565,0.006692349,0.0001894094],"genre_scores_gemma":[0.09473991,0.00000133184,0.9034427,0.001241737,0.0002999048,0.0001768652,0.000006587758,0.00002249598,0.00006843327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8011457,"threshold_uncertainty_score":0.7678701,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04131213216160864,"gpt":0.308153895772097,"spread":0.2668417636104884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003802481,0.0004022081,0.000663919,0.0002317314,0.0005845209,0.0007376798,0.001319511,0.0001910835,0.000004268882],"category_scores_gemma":[0.002277284,0.0003510251,0.0002445272,0.001042716,0.00007362645,0.0006964321,0.0004087612,0.001208559,0.00006055661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004090498,"about_ca_system_score_gemma":0.0004712151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000427374,"about_ca_topic_score_gemma":9.07589e-7,"domain_scores_codex":[0.995387,0.0009014855,0.0008913888,0.0008112765,0.001167248,0.0008416513],"domain_scores_gemma":[0.9942878,0.002727387,0.000639811,0.001177315,0.0007771322,0.0003905093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001438142,0.004180976,0.630176,0.002323812,0.0009155284,0.0002248075,0.02204707,0.1194564,0.0008043359,0.1149248,0.01351378,0.09128857],"study_design_scores_gemma":[0.002353506,0.0008946191,0.03088864,0.001191143,0.00009622679,0.002946803,0.0007637883,0.7796924,0.00007792472,0.1764179,0.002280673,0.002396305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2131119,0.0001736458,0.7741698,0.0001506888,0.0008486091,0.0003105159,0.000005189641,0.010833,0.0003967088],"genre_scores_gemma":[0.5869105,0.00000181538,0.4123117,0.0002931548,0.0003736795,0.00001716336,0.000005159036,0.00003165197,0.00005510158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.660236,"threshold_uncertainty_score":0.9998942,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07220551126872021,"gpt":0.3888549613939644,"spread":0.3166494501252442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01710258,0.0003938298,0.0005256277,0.0001812408,0.001011929,0.001017028,0.001495522,0.0002265643,0.00004825778],"category_scores_gemma":[0.004424091,0.0003022249,0.0001827282,0.0006741976,0.0001457665,0.001089141,0.0003087187,0.001247679,0.000009294738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001549469,"about_ca_system_score_gemma":0.0003779489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005977256,"about_ca_topic_score_gemma":0.00005734366,"domain_scores_codex":[0.993785,0.002371233,0.001196662,0.0006565858,0.001391646,0.0005988234],"domain_scores_gemma":[0.9930247,0.003767858,0.001115721,0.0009084932,0.0009441241,0.0002391192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002499247,0.001080649,0.2024771,0.0009640371,0.0005337707,0.0001057846,0.01310263,0.0119107,0.0004150885,0.03621204,0.01021861,0.7227297],"study_design_scores_gemma":[0.004076935,0.0005198187,0.5146725,0.0005533178,0.0003706997,0.00218495,0.0009128006,0.0443096,0.001574657,0.4149546,0.01343757,0.002432578],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07674356,0.001307889,0.917397,0.002401599,0.0005338099,0.0003997519,0.00001055977,0.001132399,0.00007347252],"genre_scores_gemma":[0.3896998,0.00005822507,0.6090047,0.000667398,0.0003727566,0.00005895512,0.00002200638,0.00004189734,0.00007420118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7202971,"threshold_uncertainty_score":0.999943,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06656961381106619,"gpt":0.3986368578863461,"spread":0.3320672440752799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01390138,0.0004332415,0.0005249675,0.0003472446,0.0007011368,0.0005337415,0.001403796,0.0001807686,0.00004138251],"category_scores_gemma":[0.004485635,0.0003741149,0.0002038217,0.0009474858,0.0000745206,0.001247374,0.0003740231,0.000896481,0.0001091607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009353596,"about_ca_system_score_gemma":0.0007411796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007813223,"about_ca_topic_score_gemma":0.0003607805,"domain_scores_codex":[0.9941247,0.001167485,0.001592042,0.0009117244,0.001353546,0.0008504741],"domain_scores_gemma":[0.9950392,0.001248247,0.0004963629,0.0006640955,0.001886791,0.0006653121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003831638,0.0003862536,0.003584388,0.0001873347,0.0001305191,0.00005324223,0.08989276,0.0006500144,0.005121037,0.000620363,0.0001602165,0.8988307],"study_design_scores_gemma":[0.003111211,0.002147005,0.1444183,0.0016843,0.00009167165,0.001479737,0.007772258,0.001838989,0.697002,0.129817,0.006672719,0.003964785],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2857762,0.00002910491,0.7121091,0.001046321,0.0002927262,0.0004345206,0.000003971417,0.0002816551,0.00002631516],"genre_scores_gemma":[0.3081989,8.520572e-7,0.6901049,0.001469183,0.0001158225,0.00001808786,0.000004004397,0.00001716998,0.00007106541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8948659,"threshold_uncertainty_score":0.9998711,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1667256097848134,"gpt":0.3304675520946508,"spread":0.1637419423098374,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003102475,0.0003134627,0.0004437839,0.0001686755,0.0006470314,0.0007230902,0.001220131,0.0002173298,0.00002401965],"category_scores_gemma":[0.0006660706,0.0002545035,0.0002624369,0.000670618,0.00007301889,0.00114959,0.0001384777,0.0006161008,0.00008407017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003296966,"about_ca_system_score_gemma":0.0003110163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006146258,"about_ca_topic_score_gemma":0.00000324517,"domain_scores_codex":[0.996002,0.001042545,0.0007895003,0.0005927772,0.0009186226,0.0006545635],"domain_scores_gemma":[0.9977118,0.0001393862,0.0005428661,0.0009082201,0.0003372368,0.0003604969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00005372219,0.0008231594,0.02231371,0.0009761323,0.0002465892,0.0001682199,0.01910246,0.0001633674,0.00002907891,0.5971699,0.01051319,0.3484405],"study_design_scores_gemma":[0.01524003,0.002687847,0.3631999,0.001842612,0.0004850162,0.03105632,0.02759796,0.03919603,0.0003963597,0.259499,0.2477924,0.01100647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002726694,0.0007753653,0.9903188,0.0006056965,0.001094777,0.0003308986,0.00002266299,0.0005779573,0.00354719],"genre_scores_gemma":[0.4495715,0.00006031384,0.5488814,0.0008294678,0.0004597948,0.00007266949,0.00001785764,0.00002822629,0.00007871963],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4468448,"threshold_uncertainty_score":0.9999907,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04235531741497253,"gpt":0.3502672804459467,"spread":0.3079119630309741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002343114,0.0002971707,0.0005608744,0.0006691994,0.0001074299,0.0002231054,0.00141636,0.0001644328,0.00007723877],"category_scores_gemma":[0.008157671,0.0002935655,0.0001971332,0.001613725,0.00007929729,0.001304117,0.0002479091,0.0009289332,0.00002222998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000285912,"about_ca_system_score_gemma":0.0005380887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002046414,"about_ca_topic_score_gemma":0.00001926241,"domain_scores_codex":[0.9964014,0.0002202993,0.001082866,0.000404924,0.001175172,0.0007152826],"domain_scores_gemma":[0.9965168,0.001943679,0.0002560396,0.0006738553,0.000277247,0.0003323782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001001192,0.0008473053,0.6130406,0.0003934261,0.0004118973,0.0004861343,0.01162261,0.1346746,0.003703352,0.006886707,0.009138545,0.2186947],"study_design_scores_gemma":[0.00446357,0.00115085,0.9016685,0.0004731137,0.00005462828,0.0009344105,0.0005399687,0.00534007,0.03047399,0.001149903,0.0512294,0.002521549],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3134292,0.0008402742,0.683924,0.0007229507,0.0005111177,0.0001108988,0.0000277793,0.0004278775,0.000005935917],"genre_scores_gemma":[0.77942,0.00008957035,0.2198149,0.0001935268,0.0003640108,0.00001045494,0.000005720343,0.00004204083,0.00005976296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4659908,"threshold_uncertainty_score":0.9999517,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04319073875896441,"gpt":0.3805174876703231,"spread":0.3373267489113587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002452576,0.0001112427,0.0001648669,0.00002066047,0.0004969219,0.00002209513,0.0001885599,0.0001365041,0.0000746584],"category_scores_gemma":[0.0004262311,0.00007036126,0.0001247004,0.00005890687,0.00007484012,0.000003921445,0.00004326643,0.0006296574,0.000006116481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000013605,"about_ca_system_score_gemma":0.00005528211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006653979,"about_ca_topic_score_gemma":0.00002752958,"domain_scores_codex":[0.9953783,0.003956208,0.0002540006,0.0001100239,0.0001616636,0.0001397767],"domain_scores_gemma":[0.999095,0.000230009,0.0001185397,0.0003993181,0.00009804565,0.00005904187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004833383,0.001672374,0.8846633,0.00001191381,0.00008901789,0.00001486228,0.0007401993,0.00003631671,0.107806,0.000005358791,0.001344054,0.003133315],"study_design_scores_gemma":[0.0007998858,0.009949506,0.697359,0.000012147,0.00004812665,0.00005117624,0.001111805,8.280898e-7,0.2903753,0.00006802034,0.0001369878,0.00008719221],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990572,0.00002243184,0.0002767541,0.0001651126,0.000264999,0.0001259757,0.00002658394,0.000009585147,0.00005138008],"genre_scores_gemma":[0.9992116,0.000005606222,0.00001840866,0.0004358364,0.000197035,0.000007307013,0.00004567531,0.000007926186,0.00007059208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1873042,"threshold_uncertainty_score":0.3821972,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04993700665593952,"gpt":0.3410140197099246,"spread":0.291077013053985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001775568,0.0001043915,0.0001951122,0.00008563082,0.0004499974,0.00014534,0.00274581,0.00007515639,0.00001136052],"category_scores_gemma":[0.002276826,0.00007868648,0.0001120635,0.0001340837,0.000226679,0.0009292461,0.0003805922,0.0003638038,0.000002166971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007435639,"about_ca_system_score_gemma":0.0003141749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000219888,"about_ca_topic_score_gemma":0.00001033701,"domain_scores_codex":[0.9979126,0.0003450412,0.0004583677,0.0001916764,0.0008684303,0.0002238241],"domain_scores_gemma":[0.9968853,0.0004020045,0.000594252,0.001482972,0.0004952597,0.0001402181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005257091,0.00003669882,0.9899302,0.00007374339,0.00001845751,0.00000268984,0.0007846369,0.0005159227,0.001983894,0.000912085,0.00008307042,0.005653334],"study_design_scores_gemma":[0.0002417502,0.00005796023,0.9873148,0.0001169016,0.000003799476,0.0000402346,0.00003056542,0.0006300053,0.005600173,0.00586161,0.00001045786,0.00009180622],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6944123,0.0000654796,0.3045342,0.0004456863,0.0004207922,0.00006824898,0.0000122692,0.00003876389,0.000002215959],"genre_scores_gemma":[0.9787143,0.000008490475,0.02110703,0.00002687292,0.0001076459,0.000003309657,0.000001452681,0.000009016153,0.00002181091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2843021,"threshold_uncertainty_score":0.5102444,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04390968862051765,"gpt":0.3593724630374728,"spread":0.3154627744169552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002824309,0.0001591817,0.0005230153,0.0003132162,0.0002417587,0.00009153903,0.0006713539,0.0001523036,0.00003961549],"category_scores_gemma":[0.001725883,0.00009418092,0.0005013914,0.0009661588,0.0001171651,0.0008273228,0.0000665299,0.0001663886,0.000007075174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001292995,"about_ca_system_score_gemma":0.0002121549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001660819,"about_ca_topic_score_gemma":0.00001488322,"domain_scores_codex":[0.9976215,0.0003427508,0.0008713055,0.0003278265,0.0005077352,0.000328868],"domain_scores_gemma":[0.9959424,0.001942629,0.0007178998,0.0005540766,0.0006949904,0.0001479631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000398461,0.0005391162,0.4494413,0.0003081956,0.003508272,0.000008174954,0.01386854,0.0005993065,0.0009256155,0.07464842,0.001149399,0.4546052],"study_design_scores_gemma":[0.00237343,0.001023689,0.472837,0.0006563702,0.0007809576,0.00005743299,0.0009904932,0.001797262,0.007970309,0.5074937,0.003037157,0.0009821367],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2492995,0.0001640003,0.7492566,0.0006387857,0.0003737232,0.0001398388,0.00004382748,0.00007746839,0.000006240399],"genre_scores_gemma":[0.7776979,0.00006348386,0.2219818,0.00008593423,0.0000975314,0.0000179134,0.000002302835,0.000006548271,0.00004654755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5283985,"threshold_uncertainty_score":0.3840586,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03048809234644917,"gpt":0.2932194760941157,"spread":0.2627313837476665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001787115,0.0001637219,0.0002020641,0.0001739264,0.0004226516,0.0002206304,0.0005469982,0.00007182621,0.00000414539],"category_scores_gemma":[0.0001006442,0.0001155204,0.0001180657,0.0001602168,0.00006398333,0.0004538364,0.0001053429,0.0001455031,0.000003531829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001328489,"about_ca_system_score_gemma":0.000150119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002629854,"about_ca_topic_score_gemma":0.000001397145,"domain_scores_codex":[0.9983463,0.00006266162,0.0005078338,0.0002841171,0.0003826393,0.0004164023],"domain_scores_gemma":[0.9987917,0.0002373447,0.0001447998,0.0003565208,0.000235048,0.0002346153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002003046,0.0001306453,0.0006074432,0.0001138264,0.00004589062,0.000003749924,0.002707734,0.0704713,0.002234924,0.331278,0.002308455,0.590078],"study_design_scores_gemma":[0.0009712754,0.0001066848,0.0003350004,0.0002243279,0.0000157043,0.0002118043,0.00000702489,0.9284227,0.001749429,0.05918643,0.008314809,0.0004547961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01114384,0.0001185051,0.9857825,0.001799558,0.0001798947,0.0002311094,0.00002703409,0.0007000003,0.00001756641],"genre_scores_gemma":[0.1766315,0.00002116694,0.8230659,0.000120426,0.00003758771,0.00003328706,6.090882e-7,0.0000133281,0.00007612202],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8579514,"threshold_uncertainty_score":0.4710786,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09836511809479921,"gpt":0.4380468293221385,"spread":0.3396817112273393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004349916,0.0001882942,0.0004283058,0.0002894164,0.0005442905,0.0006339924,0.003276252,0.000110269,0.00001822427],"category_scores_gemma":[0.005607374,0.0001717454,0.00008769012,0.0002638276,0.00008372436,0.001177469,0.0005500697,0.0009527426,0.00001043468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001649118,"about_ca_system_score_gemma":0.0002393579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004274665,"about_ca_topic_score_gemma":0.0002376268,"domain_scores_codex":[0.9966161,0.0006500212,0.0007345699,0.0004122817,0.001079757,0.0005073224],"domain_scores_gemma":[0.9960679,0.001012916,0.0003855777,0.001913822,0.0003053895,0.0003143795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001090856,0.0005971917,0.9751353,0.00002159364,0.00002241352,0.0001240949,0.004933094,0.0005680699,0.0000685604,0.00002685749,0.0001276783,0.01836425],"study_design_scores_gemma":[0.001064279,0.0004448012,0.995825,0.00006774872,0.000003057089,0.00006217005,0.0003588884,0.0009332641,0.0001382694,0.0008521971,0.00005040026,0.000199922],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9137052,0.00004325766,0.08517729,0.0003322358,0.0004394382,0.0001608693,0.000002363047,0.0001178356,0.00002148443],"genre_scores_gemma":[0.9862659,0.000005315326,0.01350826,0.00003900234,0.0001332068,0.000006077081,4.59783e-7,0.00001785731,0.00002394875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07256065,"threshold_uncertainty_score":0.7003573,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0405552949918816,"gpt":0.3248114528857969,"spread":0.2842561578939153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002017009,0.0001423187,0.0001589593,0.0003931476,0.0006175456,0.0003330829,0.0007709584,0.000079596,0.00001927998],"category_scores_gemma":[0.002966557,0.0001356633,0.00006540035,0.0012345,0.00002801949,0.0007691055,0.0002635923,0.0008028084,0.0007995388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001865462,"about_ca_system_score_gemma":0.0002681117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001311544,"about_ca_topic_score_gemma":0.000005861987,"domain_scores_codex":[0.9977593,0.0002572682,0.0004153517,0.0003104822,0.000852966,0.0004046273],"domain_scores_gemma":[0.9978551,0.001138993,0.0001857094,0.000346404,0.0002508054,0.0002230238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002789851,0.0001919921,0.1822507,0.0001921131,0.0001931386,0.000239699,0.0151861,0.008089398,0.001513655,0.01765336,0.002779831,0.7716821],"study_design_scores_gemma":[0.001286801,0.0001286698,0.4938566,0.000123569,0.000008561686,0.0005089568,0.000303261,0.01541612,0.001883198,0.01454615,0.4709223,0.001015775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03832579,0.0002856557,0.9586843,0.0006819536,0.0003283429,0.0001063212,7.768603e-7,0.001506346,0.00008048837],"genre_scores_gemma":[0.8426002,0.0002347328,0.1552352,0.000177982,0.0003234326,0.00005672178,0.00005633753,0.00004599596,0.001269378],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8042744,"threshold_uncertainty_score":0.9999785,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04786971646388845,"gpt":0.3511958778392323,"spread":0.3033261613753439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001135551,0.000103276,0.0001718994,0.00004864776,0.0004355795,0.0001861937,0.0005184705,0.000040743,0.00001602242],"category_scores_gemma":[0.001247122,0.00007142965,0.00005943541,0.0002562655,0.000415537,0.0003268544,0.000214061,0.0004254237,0.00000387989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002913802,"about_ca_system_score_gemma":0.0001299575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001722039,"about_ca_topic_score_gemma":0.00004813167,"domain_scores_codex":[0.9985672,0.0003828975,0.0003332053,0.0001896123,0.0003407574,0.0001863727],"domain_scores_gemma":[0.9985569,0.0002678142,0.0005167551,0.0002971713,0.0002796118,0.00008174576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008225118,0.00002583594,0.682459,0.00005017093,0.00002780628,0.000006931996,0.00314935,0.0001191206,0.001323752,0.01351427,0.00006609264,0.2992495],"study_design_scores_gemma":[0.001271713,0.0002731427,0.8068561,0.0009233817,0.00002568524,0.002220952,0.0009974488,0.01655493,0.007223827,0.1621074,0.0009511731,0.0005942453],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5393938,0.00009084344,0.458748,0.001071322,0.0005407394,0.00003799383,0.000003574576,0.00005505858,0.00005860737],"genre_scores_gemma":[0.9097965,0.00001310342,0.08968294,0.0002461665,0.0002213556,6.036545e-7,1.845223e-7,0.000004051883,0.00003512465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3704026,"threshold_uncertainty_score":0.3350169,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04697602169952794,"gpt":0.3156316965895039,"spread":0.268655674889976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002269496,0.0003358983,0.0005035143,0.0002717273,0.0003335935,0.0008752627,0.002202555,0.0003046472,0.0001496759],"category_scores_gemma":[0.002198553,0.0002870195,0.0003066833,0.0005785102,0.00007009717,0.00314261,0.0003663604,0.0009685941,0.00006149699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260438,"about_ca_system_score_gemma":0.0003570874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009610738,"about_ca_topic_score_gemma":8.822238e-7,"domain_scores_codex":[0.9962965,0.0004351836,0.0007009719,0.0007651572,0.0009626257,0.0008395598],"domain_scores_gemma":[0.9961678,0.001695377,0.0002608028,0.001053577,0.0003002648,0.0005222245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003442012,0.001052628,0.7268558,0.0007342375,0.000185563,0.00006816292,0.001865114,0.01125145,0.0001285481,0.02389747,0.006092988,0.2275239],"study_design_scores_gemma":[0.008861175,0.003708106,0.8255603,0.0003541387,0.00006821187,0.002397991,0.0007767049,0.06199238,0.0005280351,0.06455097,0.02713028,0.004071711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1215489,0.0003022225,0.875169,0.0002478034,0.0008204667,0.0004952891,0.00001863085,0.001338998,0.0000586863],"genre_scores_gemma":[0.1743141,0.00002455235,0.8239743,0.0003754906,0.0005715812,0.00005853318,0.00006914572,0.00005704346,0.0005553528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2234522,"threshold_uncertainty_score":0.9999582,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.06644119961895152,"gpt":0.4136435348790582,"spread":0.3472023352601067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00680873,0.0002609649,0.0003901827,0.0001026178,0.0003665566,0.0001890873,0.001680881,0.00009995711,0.000009249187],"category_scores_gemma":[0.01979549,0.0001273579,0.0001847756,0.000392445,0.0002364591,0.00030463,0.0001842068,0.0005245456,0.00001153934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001605014,"about_ca_system_score_gemma":0.000190842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002567074,"about_ca_topic_score_gemma":0.000006919623,"domain_scores_codex":[0.9945282,0.002731093,0.0007211663,0.0006106939,0.0009982913,0.0004105891],"domain_scores_gemma":[0.9846166,0.01228337,0.0004223617,0.002040383,0.0004003301,0.0002370043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006762324,0.004386267,0.7518306,0.00003611468,0.00002792874,0.0000197079,0.001409229,0.000001211535,0.0001281693,0.0003431398,0.001793405,0.2399566],"study_design_scores_gemma":[0.0006807498,0.009271407,0.8872189,0.0002695681,0.00001338168,0.00002897989,0.0000395434,0.00007038843,0.002078502,0.09997556,0.0000796896,0.0002733323],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7852594,0.0000122178,0.2087955,0.001208539,0.0002556346,0.0006927643,0.000005782196,0.003752549,0.00001761938],"genre_scores_gemma":[0.9632718,0.000001514648,0.03610603,0.0004553655,0.00008827641,0.00005459535,2.660258e-7,0.00001486106,0.000007303629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2396833,"threshold_uncertainty_score":0.9884612,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03959637261930754,"gpt":0.3236045379643921,"spread":0.2840081653450846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004279946,0.0001133264,0.0002775522,0.000477472,0.0001907839,0.0003382629,0.0004643442,0.00008126506,0.00001448322],"category_scores_gemma":[0.00645112,0.0001015255,0.00008514413,0.0008872362,0.0001318874,0.0004863934,0.000156998,0.0004965437,0.000001789002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002100397,"about_ca_system_score_gemma":0.00009340847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004547178,"about_ca_topic_score_gemma":0.00005349802,"domain_scores_codex":[0.9981958,0.0001855856,0.0005038261,0.00027737,0.000630076,0.0002073419],"domain_scores_gemma":[0.9973648,0.001244934,0.0002510394,0.0004717353,0.0004496429,0.0002178682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000126495,0.00006508599,0.9429852,0.00006631784,0.0004610676,0.00001102278,0.002172831,0.0003161839,0.0198437,0.003352249,0.0001869426,0.03052676],"study_design_scores_gemma":[0.0002488135,0.0000366867,0.9859636,0.00001707962,0.00009753979,0.00007380913,0.00005498227,0.005448594,0.004867597,0.00295683,0.00006637382,0.0001680672],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5374719,0.0001984506,0.4618016,0.0002727651,0.000153384,0.00003572844,0.00001053422,0.0000548637,8.228877e-7],"genre_scores_gemma":[0.9541029,0.00003280765,0.04574706,0.00002808156,0.0000427298,0.000002623091,0.000002975079,0.000007014616,0.00003383871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.416631,"threshold_uncertainty_score":0.7723059,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06787216461876273,"gpt":0.3860603776811611,"spread":0.3181882130623984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006755449,0.0001307515,0.0002442503,0.00003249677,0.0002445236,0.0001627808,0.000565441,0.00005991704,0.00002133943],"category_scores_gemma":[0.001643712,0.00008021978,0.0001099106,0.000348527,0.0001611316,0.0009394641,0.0001986112,0.0002725973,1.670515e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212422,"about_ca_system_score_gemma":0.0003908949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005229982,"about_ca_topic_score_gemma":0.00001291394,"domain_scores_codex":[0.9963562,0.001445017,0.000603006,0.0002728101,0.001164839,0.0001581533],"domain_scores_gemma":[0.9975891,0.0003620064,0.0006296096,0.0006125102,0.0007737758,0.00003305588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002791079,0.002569712,0.1057749,0.003426496,0.001381605,0.00002207584,0.1623502,0.003580648,0.002764547,0.08245988,0.004220378,0.6286585],"study_design_scores_gemma":[0.01503938,0.001759162,0.1335447,0.001970405,0.0007472065,0.0008216354,0.03144162,0.02003827,0.5099452,0.2763353,0.006539133,0.001818087],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4206537,0.00214329,0.574237,0.001088675,0.0005381542,0.000996472,0.00002195491,0.0001152778,0.0002053781],"genre_scores_gemma":[0.9105173,0.0001034554,0.08915615,0.00008964811,0.00004875037,0.00005260987,0.000002761552,0.000008083969,0.00002119968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6268404,"threshold_uncertainty_score":0.3271267,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05475254564650548,"gpt":0.3527974695137458,"spread":0.2980449238672403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001425892,0.0001980648,0.0003748304,0.0006021703,0.0000809753,0.0008564355,0.0009470726,0.00009238979,0.000008512197],"category_scores_gemma":[0.001628581,0.0001811708,0.0001098634,0.001103759,0.00005073541,0.0006222518,0.0001832518,0.0006598628,0.00004404885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003032228,"about_ca_system_score_gemma":0.0007869947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004074642,"about_ca_topic_score_gemma":0.00002336596,"domain_scores_codex":[0.9974284,0.0002150931,0.0006855504,0.0003758384,0.000806667,0.0004884108],"domain_scores_gemma":[0.9945813,0.004222192,0.00009320345,0.0005139222,0.0003437578,0.0002455636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001650602,0.001133102,0.4734794,0.01294166,0.0005132713,0.003840138,0.0333253,0.3428091,0.0527619,0.01798482,0.005861834,0.05518443],"study_design_scores_gemma":[0.004333068,0.002974535,0.8407213,0.01487093,0.00005412385,0.001444481,0.004538701,0.06129652,0.03120124,0.008227777,0.02662834,0.003708993],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2538302,0.002166793,0.7420802,0.0002194516,0.001146739,0.0001996013,0.0000302843,0.0003116186,0.0000151685],"genre_scores_gemma":[0.9826658,0.00001285969,0.01708001,0.00002662472,0.000126155,0.00001354342,0.000002934862,0.00002244193,0.00004959206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7288356,"threshold_uncertainty_score":0.8258626,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0309152664033211,"gpt":0.3234580157601795,"spread":0.2925427493568584,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01618489,0.0002149648,0.0007836148,0.0003352017,0.0001729639,0.0000553944,0.001674849,0.0001391774,0.00003053342],"category_scores_gemma":[0.00335459,0.00013925,0.0004220625,0.002095511,0.0003988026,0.0004390536,0.0002784854,0.0005766902,1.446445e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001278441,"about_ca_system_score_gemma":0.0004204692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002570339,"about_ca_topic_score_gemma":0.001219533,"domain_scores_codex":[0.9958437,0.0005097126,0.001810151,0.0002970155,0.001159457,0.0003799482],"domain_scores_gemma":[0.9897682,0.006068552,0.001704831,0.001314903,0.001052344,0.00009113385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000668404,0.0006068287,0.7866846,0.0007553427,0.001668055,0.00001102656,0.01132049,0.004298671,0.001351333,0.01750775,0.000543137,0.1745844],"study_design_scores_gemma":[0.000824514,0.0007767407,0.9115099,0.0001983352,0.0004515625,0.00006695563,0.001400198,0.0007382472,0.03060249,0.04421721,0.008603259,0.0006106197],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2567393,0.0008214677,0.7418823,0.0001301684,0.0001181926,0.0001608327,0.00006440151,0.00006933841,0.00001395085],"genre_scores_gemma":[0.9165398,0.0001949781,0.08317912,0.00002212887,0.00003102635,0.00000682559,0.000002788973,0.00001358907,0.000009733141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6598005,"threshold_uncertainty_score":0.5678449,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04412443132399541,"gpt":0.314952805824067,"spread":0.2708283745000716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001342518,0.0003102769,0.0004134294,0.0001606392,0.0006710535,0.001238209,0.001278288,0.0001576508,0.0002964768],"category_scores_gemma":[0.0196955,0.0002831947,0.0001855117,0.000444639,0.0001086075,0.001090846,0.0003502639,0.0007039171,0.0003297678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001380453,"about_ca_system_score_gemma":0.0002343179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005192721,"about_ca_topic_score_gemma":0.0000750686,"domain_scores_codex":[0.9970093,0.0003741723,0.0008410959,0.000539617,0.000624479,0.0006113457],"domain_scores_gemma":[0.989494,0.007897105,0.0005672153,0.0009827893,0.0006323367,0.0004265912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005812683,0.0002630132,0.6208603,0.00002729759,0.0000456346,0.0002021787,0.001121599,0.000007231225,0.0003524388,0.0002091687,0.1300512,0.2468542],"study_design_scores_gemma":[0.001004533,0.0006206285,0.5185486,0.000688762,0.00003947044,0.002705282,0.0001272066,0.002721749,0.00130614,0.4674529,0.003299395,0.001485276],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3127856,0.0004740315,0.6709253,0.00156078,0.0008792313,0.0002902095,0.0000276831,0.01249899,0.0005582065],"genre_scores_gemma":[0.4497939,0.00001932442,0.5485925,0.0008274281,0.0004089778,0.00002263453,0.00000808861,0.00002995721,0.0002971634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4672438,"threshold_uncertainty_score":0.999962,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hearing impaired; Computer science; Dream; Sight; Visually impaired; Interface (matter); User interface; Human–computer interaction; World Wide Web; Multimedia; Audiology; Operating system; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2112760787145806,"gpt":0.4694726119693898,"spread":0.2581965332548092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007721369,0.0002191109,0.0004065761,0.0001355164,0.001834588,0.00182328,0.001051015,0.0001638526,0.0001043133],"category_scores_gemma":[0.01182268,0.0002149688,0.0004485018,0.0002792524,0.0005181899,0.002869329,0.0001665268,0.0002305862,0.000008916386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009154307,"about_ca_system_score_gemma":0.001474886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000464412,"about_ca_topic_score_gemma":0.001404644,"domain_scores_codex":[0.9965841,0.0002429189,0.0009452299,0.0003968492,0.0009000309,0.0009309099],"domain_scores_gemma":[0.9970976,0.001181837,0.000494869,0.0002733021,0.0005562016,0.0003962326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005685096,0.001279447,0.6469088,0.0005770807,0.0004707057,0.000005034498,0.0533971,0.0005940362,0.00005202854,0.2260336,0.004735244,0.06537841],"study_design_scores_gemma":[0.002600929,0.000270712,0.01478549,0.0001940379,0.00004310202,0.000005479922,0.01646263,0.000002831729,0.0001121574,0.947033,0.01805557,0.000434082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9396341,0.0001059752,0.04852872,0.005882672,0.001232218,0.001691615,0.0003917431,0.0003545696,0.00217839],"genre_scores_gemma":[0.9821085,0.00001197512,0.015756,0.0006860465,0.0007639165,0.0001372884,0.00002909016,0.000036897,0.0004702563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7209994,"threshold_uncertainty_score":0.9994649,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04442702861597696,"gpt":0.2917870870988619,"spread":0.2473600584828849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009903419,0.0003028931,0.0004281538,0.0001657952,0.0003306573,0.0005436343,0.001424583,0.0001409071,0.00001756029],"category_scores_gemma":[0.001274496,0.000242503,0.0001118445,0.0005173126,0.00006503629,0.0007943929,0.0003204677,0.0007953312,0.00009625396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276101,"about_ca_system_score_gemma":0.0003917236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002230959,"about_ca_topic_score_gemma":0.000008632122,"domain_scores_codex":[0.9972501,0.0002435857,0.0005736787,0.0005675721,0.0008159775,0.0005491035],"domain_scores_gemma":[0.9965021,0.001255093,0.0004818724,0.0009599077,0.0005167761,0.0002842793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005778718,0.0002620022,0.8400493,0.0000853286,0.0001569983,0.0001684391,0.005117735,0.02079071,0.0009114402,0.002108641,0.008331842,0.1219597],"study_design_scores_gemma":[0.002792967,0.001030286,0.07412617,0.001940829,0.00006784285,0.001551297,0.00005828901,0.4669346,0.001285333,0.4469893,0.0008049225,0.002418164],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2594619,0.00006619382,0.7339607,0.0003539538,0.0002013466,0.0001199614,0.00000895074,0.005599815,0.0002271594],"genre_scores_gemma":[0.4411423,0.000002607856,0.557918,0.0007083543,0.0001129347,0.000004969568,0.00000307051,0.00002214941,0.00008561619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7659231,"threshold_uncertainty_score":0.9888987,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Software quality; Quality (philosophy); Software engineering; Software; Software development; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0479755089915145,"gpt":0.3993157688183557,"spread":0.3513402598268413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01210772,0.0002942218,0.0003299956,0.0003577665,0.0007395163,0.0006061743,0.001133785,0.0001043426,0.0001416696],"category_scores_gemma":[0.01155343,0.0002059875,0.0000972645,0.001110461,0.000146731,0.0004715838,0.0002335063,0.0009583203,0.00008810751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003391835,"about_ca_system_score_gemma":0.0002815761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006704393,"about_ca_topic_score_gemma":0.00005934497,"domain_scores_codex":[0.9959593,0.000708007,0.0007917825,0.0006326862,0.001234084,0.0006741723],"domain_scores_gemma":[0.9935989,0.003969801,0.0002778847,0.001043239,0.0006281006,0.0004821226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001810223,0.0001598802,0.008114277,0.000063315,0.00007221444,0.00002044188,0.001869285,0.005730564,0.00005793617,0.003014348,0.006917825,0.9737989],"study_design_scores_gemma":[0.003372942,0.004935079,0.6306863,0.0005685198,0.0001087815,0.0008206319,0.001983732,0.004339291,0.02484152,0.02086146,0.304061,0.003420681],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01020324,0.00005048611,0.9787081,0.008842733,0.001458745,0.0004116856,0.000009410041,0.0002907761,0.00002477908],"genre_scores_gemma":[0.009128784,0.000007039796,0.9814612,0.001096577,0.008015012,0.00002412989,0.000005318854,0.00003139379,0.0002305908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9703782,"threshold_uncertainty_score":0.9967726,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06126340530962837,"gpt":0.3933497388779376,"spread":0.3320863335683092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004995416,0.0001476772,0.0003229419,0.0002589879,0.0001820417,0.0003343823,0.0009844273,0.00009358486,0.00003505126],"category_scores_gemma":[0.003915562,0.0001332534,0.00008553276,0.0003095038,0.00002805637,0.002153477,0.0001564357,0.0004165419,0.00002909508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001067783,"about_ca_system_score_gemma":0.0002451624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004503502,"about_ca_topic_score_gemma":0.00002381472,"domain_scores_codex":[0.9974923,0.0002846732,0.0006305187,0.0002180396,0.0009406762,0.0004338396],"domain_scores_gemma":[0.9963126,0.001973662,0.0003348053,0.0005037289,0.000667333,0.0002078461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005949033,0.00021743,0.9638984,0.0001183329,0.00005984625,0.000001934053,0.01165604,0.0007175649,0.00004475722,0.0001473344,0.0008447632,0.02223413],"study_design_scores_gemma":[0.005607712,0.006491943,0.9540273,0.0001551776,0.00002592345,0.0001439353,0.008683534,0.01544537,0.0009060905,0.0009628081,0.006855824,0.0006944113],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5701125,0.00002796436,0.428822,0.0001097054,0.0003698095,0.0003884003,0.00002089489,0.000137653,0.00001110027],"genre_scores_gemma":[0.9769861,0.000002505373,0.02264875,0.000099183,0.0001595484,0.00002237725,0.00001202958,0.0000119922,0.00005750949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4068736,"threshold_uncertainty_score":0.5433915,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04837848210346001,"gpt":0.3575545938197814,"spread":0.3091761117163214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003984725,0.0001685714,0.0002319797,0.0003673843,0.0003041049,0.0001318534,0.0008971909,0.00008112752,0.00002209549],"category_scores_gemma":[0.01018302,0.0001071766,0.0002367866,0.001522412,0.00008873274,0.0006984471,0.0001875841,0.0005808052,0.00002029362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005166817,"about_ca_system_score_gemma":0.0003244458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001577247,"about_ca_topic_score_gemma":0.000001449848,"domain_scores_codex":[0.9973299,0.0004233884,0.0004510558,0.0001658208,0.001024833,0.0006050299],"domain_scores_gemma":[0.9951053,0.003319857,0.0002758352,0.0006106631,0.000435019,0.0002533182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005387477,0.0002789175,0.9515404,0.00003761635,0.0001962991,0.000007053321,0.007647877,0.002931679,0.0002510933,0.0140599,0.00350083,0.01949445],"study_design_scores_gemma":[0.0004469933,0.000384546,0.9944996,0.00004819665,0.00001069831,0.0001825916,0.0003875309,0.0008005732,0.001026419,0.001693188,0.0002709664,0.0002487432],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4120305,0.000544766,0.5865371,0.00008340062,0.0006035528,0.00006559098,0.000003410006,0.0001026882,0.00002894135],"genre_scores_gemma":[0.9803008,0.00001120864,0.01932716,0.00001864607,0.0002773458,0.000004148386,0.000001290946,0.00001360371,0.00004582699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5682703,"threshold_uncertainty_score":0.9981546,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09735351601825751,"gpt":0.3796241180089818,"spread":0.2822706019907243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007779071,0.0004434968,0.000564652,0.0002077937,0.0005607515,0.0002393908,0.001831993,0.0001319474,0.00002596413],"category_scores_gemma":[0.0357344,0.0003268485,0.0003294818,0.0005850951,0.00005147238,0.0009696893,0.0003745593,0.000816052,0.0000816691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002476964,"about_ca_system_score_gemma":0.0001152874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006907756,"about_ca_topic_score_gemma":0.000005745779,"domain_scores_codex":[0.9960986,0.0005121124,0.0009145947,0.0005373717,0.000786046,0.001151288],"domain_scores_gemma":[0.9921973,0.005325048,0.0003602545,0.001238551,0.0004245209,0.0004543482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000237866,0.0002995011,0.00633547,0.0003583008,0.0001930309,0.000009177199,0.008151645,0.1599558,0.0002290606,0.0178726,0.04781992,0.7585376],"study_design_scores_gemma":[0.001587219,0.0007608202,0.07837372,0.0003540822,0.00006019196,0.000341866,0.0004080149,0.0004369345,0.00663557,0.02628611,0.8821768,0.002578625],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005495586,0.0004214151,0.980439,0.003665514,0.008453419,0.0006095156,0.00005033049,0.0008555775,0.000009612111],"genre_scores_gemma":[0.005035512,0.00001566163,0.9674836,0.00103648,0.02585732,0.00009788058,0.000004838131,0.00006000115,0.0004086845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8343569,"threshold_uncertainty_score":0.9999183,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Automation; Software engineering; Test (biology); Software; Computer science; Software testing; Engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06356689489556629,"gpt":0.3314952957414389,"spread":0.2679284008458727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005034484,0.0002580498,0.0004393527,0.0002426975,0.0002898533,0.0003796948,0.00127057,0.0003063094,0.00001836032],"category_scores_gemma":[0.07155588,0.0002311184,0.0001929359,0.0006192226,0.00009611782,0.001219988,0.0002740549,0.0009615826,0.00002191611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155397,"about_ca_system_score_gemma":0.0003330842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007159421,"about_ca_topic_score_gemma":0.00000123622,"domain_scores_codex":[0.996466,0.0008137479,0.0009463619,0.0003878707,0.0009744398,0.0004115911],"domain_scores_gemma":[0.9900433,0.006654607,0.001280462,0.0008379623,0.0009395251,0.0002441499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009799298,0.0007801958,0.07028929,0.0002528013,0.0001224947,0.00006552014,0.004522687,0.0001522085,0.0001558079,0.008590733,0.1204624,0.7945079],"study_design_scores_gemma":[0.007509769,0.004196846,0.05258961,0.003001882,0.0003043339,0.00919276,0.0003438896,0.01062466,0.005369725,0.8169531,0.08632689,0.003586546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003203904,0.0001176086,0.9872405,0.002175243,0.0007446276,0.0001452951,0.00001058471,0.006179637,0.0001825978],"genre_scores_gemma":[0.224887,0.00001019086,0.7737215,0.0008314844,0.0004742775,0.000007477413,0.000005270752,0.00002248448,0.00004038387],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8083624,"threshold_uncertainty_score":0.9424734,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}