{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":28,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":28,"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":"210e62fba4a8","filters":{"venue":"Software Testing Verification and Reliability"}},"results":[{"id":"W1522741019","doi":"10.1002/stvr.1572","title":"Coverage‐based regression test case selection, minimization and prioritization: a case study on an industrial system","year":2015,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Regression testing; Minification; Selection (genetic algorithm); Computer science; Prioritization; Fault detection and isolation; Suite; Reliability engineering; Test suite; Regression; Fault (geology); Regression analysis; Data mining; Machine learning; Test case; Artificial intelligence; Statistics; Engineering; Software; Mathematics; Software system","retraction":null,"screen_n_in":null,"score":{"opus":0.08433280682020698,"gpt":0.3118294633298048,"spread":0.2274966565095978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001528536,0.0002350939,0.0002237536,0.0001543052,0.0006156221,0.0003189929,0.0001612534,0.0001696946,4.896787e-7],"category_scores_gemma":[0.01179017,0.0002070198,0.00001831861,0.0008144915,0.00008525265,0.000410123,0.0000805169,0.0002431698,0.000001325107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001762393,"about_ca_system_score_gemma":0.0002634479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007774481,"about_ca_topic_score_gemma":0.00001308529,"domain_scores_codex":[0.997766,0.0004723068,0.000436418,0.0008233655,0.0003086937,0.0001932843],"domain_scores_gemma":[0.9965063,0.001476215,0.0002705831,0.000704745,0.000768513,0.0002736364],"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":[0.00003835779,0.0009103609,0.9337693,0.0001060897,0.000005535681,0.001210001,0.002284081,0.001005991,0.00001489199,0.00008063306,0.0008807874,0.05969395],"study_design_scores_gemma":[0.004431493,0.005818601,0.04676836,0.000654847,0.0001035795,0.03263719,0.001711693,0.9041228,0.0002554952,0.002105565,0.0001787512,0.001211632],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7037818,0.00002036258,0.2873782,0.00009623001,0.0001935453,0.0007524516,0.000006784828,0.007744317,0.00002628226],"genre_scores_gemma":[0.8745881,4.5007e-7,0.1251789,0.00005092412,0.00008381901,0.00006288978,0.000009478461,0.000016569,0.000008839556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9031168,"threshold_uncertainty_score":0.9965339,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809981234","doi":"10.1002/stvr.1665","title":"P<scp>esto</scp>: Automated migration of DOM‐based Web tests towards the visual approach","year":2018,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Automation; Web application; Test (biology); Visual Basic; Visualization; Software engineering; Artificial intelligence; Programming language; Software; World Wide Web; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03380500827020957,"gpt":0.2887960861374015,"spread":0.254991077867192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001763683,0.0002321837,0.0002436839,0.0001181206,0.0004341105,0.0001453972,0.0006659018,0.000158467,0.000001184165],"category_scores_gemma":[0.01566003,0.0001690158,0.00006263643,0.001124219,0.0006025631,0.0002270493,0.0001594118,0.0002123788,0.000007086987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005754507,"about_ca_system_score_gemma":0.0003253063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003206249,"about_ca_topic_score_gemma":0.000004922293,"domain_scores_codex":[0.9978756,0.0002713655,0.0005006887,0.0006619146,0.0003997045,0.0002906859],"domain_scores_gemma":[0.9952805,0.002235677,0.0003769143,0.001082213,0.0009198497,0.0001048582],"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":[0.00002834051,0.001566861,0.7999141,0.0007867217,0.0000419197,0.000003228218,0.004518598,0.0007047011,0.007510026,0.001364117,0.04370694,0.1398545],"study_design_scores_gemma":[0.0002232311,0.0002914903,0.3108062,0.00008066803,0.00001710415,0.0000168645,0.00001621611,0.6807459,0.00259557,0.004378893,0.0007030349,0.0001247904],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4532532,0.00008767116,0.5252904,0.0002923208,0.000171652,0.0005097213,0.000008175788,0.01983161,0.0005551884],"genre_scores_gemma":[0.624447,0.000002035571,0.3752873,0.0001380533,0.00004534598,0.00004093827,0.00001029075,0.0000114715,0.00001751686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6800412,"threshold_uncertainty_score":0.9926315,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4236669998","doi":"10.1002/stvr.401","title":"Modelling methods for web application verification and testing: state of the art","year":2008,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Web testing; Software engineering; Software; Web application; Verification and validation; Web modeling; Software testing; Data mining; World Wide Web; Web service; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06046944475577618,"gpt":0.3077181642846764,"spread":0.2472487195289002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001637834,0.0001709019,0.0002129305,0.00006684853,0.0004958761,0.00004667848,0.0004133434,0.00008222745,1.806401e-7],"category_scores_gemma":[0.007729182,0.0001376734,0.00004543628,0.0006429994,0.0003070018,0.0001974693,0.0001360684,0.0001554743,8.840977e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004188083,"about_ca_system_score_gemma":0.0001520027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008202063,"about_ca_topic_score_gemma":4.429564e-7,"domain_scores_codex":[0.9983763,0.0001803384,0.0004659458,0.0006160024,0.0001707991,0.0001906636],"domain_scores_gemma":[0.995028,0.002833369,0.0004000493,0.0009932833,0.0006676403,0.0000776787],"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":[0.0000314201,0.0002574876,0.1890419,0.00056026,0.00001625221,2.976815e-7,0.001367252,0.01208211,0.01246452,0.001686375,0.0009714598,0.7815207],"study_design_scores_gemma":[0.0001712021,0.00007227209,0.05299445,0.00006279052,0.00001310312,0.00002818206,0.000002485729,0.883638,0.002289457,0.05975158,0.00078827,0.0001882326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07067727,0.0001348565,0.9257042,0.0002511447,0.00007943813,0.0006461166,0.000006648441,0.002448485,0.00005187588],"genre_scores_gemma":[0.4010731,0.00001105405,0.5987321,0.00003815601,0.00001193951,0.00009715554,0.000003491486,0.000009967124,0.00002298832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8715559,"threshold_uncertainty_score":0.9253111,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145149095","doi":"10.1002/stvr.461","title":"Regression test suite prioritization using system models","year":2011,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Regression testing; Test suite; Computer science; Prioritization; Reliability engineering; Test (biology); Test case; Fault detection and isolation; System under test; Test Management Approach; Empirical research; Overhead (engineering); Suite; Regression analysis; Data mining; Machine learning; Artificial intelligence; Engineering; Software system; Statistics; Software; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08413484429999112,"gpt":0.2648815431189903,"spread":0.1807466988189992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000945633,0.0002061799,0.000204353,0.0001113609,0.0004111127,0.0001146786,0.0004239031,0.0001428814,0.000001401075],"category_scores_gemma":[0.004143094,0.0001795158,0.00003872257,0.0006035186,0.0001172455,0.0005927942,0.0001847756,0.000172393,0.000004381627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000129563,"about_ca_system_score_gemma":0.0001056944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003525542,"about_ca_topic_score_gemma":6.31341e-7,"domain_scores_codex":[0.9982753,0.0001222026,0.0004146462,0.0006757239,0.0002511869,0.0002608725],"domain_scores_gemma":[0.9973971,0.000752153,0.0002705092,0.0009540851,0.0004930947,0.0001330091],"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":[0.00002658283,0.0005799589,0.8201281,0.001187835,0.00001416362,0.0000246051,0.004711619,0.0007955329,0.001894717,0.0130309,0.0009083586,0.1566976],"study_design_scores_gemma":[0.0002253526,0.0001320338,0.07373703,0.0006393236,0.00002227429,0.0001258418,0.00002902492,0.8645381,0.00108283,0.05896768,0.00003419626,0.0004662886],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0458025,0.0001063468,0.9375282,0.00002780739,0.0001878699,0.0003104212,0.000004116292,0.01548681,0.0005459447],"genre_scores_gemma":[0.5132034,0.000003265862,0.4867109,0.00002299783,0.00001998205,0.00001324352,0.000002727683,0.00001104981,0.00001240656],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8637426,"threshold_uncertainty_score":0.732044,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111584600","doi":"10.1002/stvr.452","title":"On reducing test length for FSMs with extra states","year":2011,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Tree traversal; Test suite; Computer science; Reduction (mathematics); Set (abstract data type); Algorithm; Finite-state machine; Test set; Implementation; Test case; Theoretical computer science; Mathematics; Programming language; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04516024558319632,"gpt":0.2535739498862984,"spread":0.2084137043031021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009024243,0.0002079537,0.0001856813,0.00008255292,0.0003450761,0.00009825994,0.0003929184,0.00008361241,0.000002647087],"category_scores_gemma":[0.008401562,0.0001629895,0.00003429518,0.0003554593,0.0001653673,0.0002257142,0.00006468542,0.0001705774,0.000004378289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005045336,"about_ca_system_score_gemma":0.00008996765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001946216,"about_ca_topic_score_gemma":0.000001427256,"domain_scores_codex":[0.9984455,0.0000569931,0.0002905969,0.0007343999,0.0001815129,0.0002910227],"domain_scores_gemma":[0.9950766,0.00334337,0.0001855413,0.0008974437,0.000375499,0.0001215513],"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":[0.0001802217,0.001503362,0.3624086,0.000770541,0.0000318474,0.00001211697,0.007477582,0.0004601003,0.0004187516,0.00894751,0.006991797,0.6107975],"study_design_scores_gemma":[0.001380897,0.004696745,0.3865828,0.001088554,0.00006168064,0.0001171352,0.00005464346,0.1046833,0.00629846,0.4927581,0.0006967282,0.001581024],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09054977,0.00004961233,0.8972841,0.0001830832,0.0001075207,0.0005319223,0.000008930456,0.01098693,0.0002981402],"genre_scores_gemma":[0.4733715,0.000003107327,0.5263883,0.00009615089,0.00001538354,0.00007687364,0.000004421178,0.00001359803,0.000030689],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6092165,"threshold_uncertainty_score":0.9999511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982395839","doi":"10.1002/1099-1689(200009)10:3<149::aid-stvr206>3.0.co;2-t","title":"State generation and automated class testing","year":2000,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Container (type theory); Computer science; White-box testing; Tree (set theory); Class (philosophy); Block (permutation group theory); Java; Reliability (semiconductor); Black box; Code coverage; Reliability engineering; Data mining; Programming language; Engineering; Artificial intelligence; Software; Software development","retraction":null,"screen_n_in":null,"score":{"opus":0.03457682983096203,"gpt":0.2649357170513301,"spread":0.2303588872203681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008853673,0.0001928843,0.0001770204,0.00006933148,0.0004361436,0.0002682875,0.0002468695,0.00009280637,0.000005619912],"category_scores_gemma":[0.005012273,0.0001802226,0.00001965242,0.0005847188,0.0001560789,0.0003601401,0.00008716468,0.00017891,0.00001165498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000475142,"about_ca_system_score_gemma":0.00007980576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002536048,"about_ca_topic_score_gemma":0.000002054479,"domain_scores_codex":[0.9983387,0.0001421461,0.00036544,0.0006952132,0.0001970731,0.0002614226],"domain_scores_gemma":[0.9978068,0.0009914916,0.0001302211,0.0006429853,0.0002921439,0.0001363296],"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":[0.000004662051,0.00007217468,0.1165146,0.0000742427,0.000004572283,0.000003922684,0.0004421703,0.0006366652,0.0008898388,0.000118505,0.002262131,0.8789765],"study_design_scores_gemma":[0.0001839499,0.0001131636,0.1968653,0.00006690897,0.000007610579,0.00006714497,0.000001795663,0.7877085,0.0002771073,0.0138714,0.0005394077,0.0002977861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7474529,0.0001805483,0.2058692,0.0004694187,0.0001222642,0.0003730819,0.000006595544,0.04511643,0.0004095673],"genre_scores_gemma":[0.4800227,0.00001275289,0.5196669,0.0001569893,0.00002946623,0.00002294961,0.000006254,0.00001093584,0.00007108366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8786787,"threshold_uncertainty_score":0.7349266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2461407631","doi":"10.1002/stvr.1609","title":"Prioritizing manual test cases in rapid release environments","year":2016,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; University of Manitoba","funders":"Mitacs; Lunds Universitet; University of Manitoba","keywords":"Computer science; Prioritization; Test suite; Unit testing; Agile software development; Test (biology); Code coverage; Suite; Test case; Embedded system; Software engineering; Operating system; Software; Engineering; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02512928207923182,"gpt":0.2599136809341788,"spread":0.234784398854947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009180242,0.0001870898,0.0001817063,0.0001113507,0.0001768303,0.00007300438,0.0003749304,0.0001027715,0.000003838044],"category_scores_gemma":[0.02162024,0.0001432476,0.00003234283,0.0003517996,0.0001826028,0.0003675911,0.0001898417,0.000145966,0.00002054876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001363377,"about_ca_system_score_gemma":0.00006676585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001365406,"about_ca_topic_score_gemma":0.000002366817,"domain_scores_codex":[0.9982302,0.000126756,0.000391066,0.0007185573,0.0002251409,0.000308287],"domain_scores_gemma":[0.9944291,0.004363752,0.0001510217,0.0008578129,0.00006698209,0.0001313479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005126714,0.0001463403,0.563756,0.00003120209,0.000001323095,0.00002377281,0.0001316748,0.000002395838,0.001628377,0.0001152392,0.0003648802,0.4337937],"study_design_scores_gemma":[0.0006079937,0.0002847598,0.9728398,0.0004605944,0.000007802855,0.000157523,0.000008868476,0.002652688,0.0013076,0.01956175,0.001586564,0.0005239962],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5501346,0.0003190046,0.4361752,0.001522891,0.0002306267,0.0005999396,0.00001925774,0.0107832,0.000215284],"genre_scores_gemma":[0.7481366,0.00003593298,0.2515905,0.0000995043,0.00002489196,0.00003664757,0.000001773297,0.00001129716,0.0000628204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4332697,"threshold_uncertainty_score":0.9866211,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013655954","doi":"10.1002/stvr.380","title":"Automated discovery of state transitions and their functions in source code","year":2007,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Engineering and Physical Sciences Research Council; National Aeronautics and Space Administration","keywords":"Computer science; State (computer science); Source code; Finite-state machine; Reverse engineering; Set (abstract data type); Code (set theory); Programming language; Software; Software engineering; Transition (genetics); Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01937952920259313,"gpt":0.2572724153819903,"spread":0.2378928861793972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001241302,0.0001276903,0.000170476,0.0001391454,0.0001478406,0.00006074721,0.0001611913,0.00006681889,4.181825e-7],"category_scores_gemma":[0.002075296,0.0001099741,0.0000256101,0.0006147868,0.0002031498,0.0002884987,0.00006322138,0.0001518583,5.837786e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003594661,"about_ca_system_score_gemma":0.00005275707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003138384,"about_ca_topic_score_gemma":0.00003433544,"domain_scores_codex":[0.9988629,0.0000750759,0.000378488,0.0003899701,0.0001026697,0.0001909053],"domain_scores_gemma":[0.9978559,0.00134696,0.0001296856,0.0004433666,0.0001595837,0.00006451261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003790839,0.0004562417,0.7707582,0.0003082414,0.00001285464,0.000004733409,0.005274017,0.001132697,0.003989526,0.0004088314,0.0004502079,0.2171665],"study_design_scores_gemma":[0.0003122772,0.0001305194,0.872484,0.000177418,0.000006953577,0.0000432708,0.00008189931,0.103801,0.001440646,0.0211267,0.0001299749,0.0002653017],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4071725,0.00005439551,0.5880607,0.0001154023,0.0000343944,0.0001161595,0.00001098227,0.004406615,0.00002880859],"genre_scores_gemma":[0.8353387,0.000004755736,0.1645634,0.0000396818,0.000005933712,0.000009539333,0.000005903872,0.000007261479,0.00002478046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4281662,"threshold_uncertainty_score":0.4484613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4251245562","doi":"10.1002/stvr.396","title":"Transition covering tests for systems with queues","year":2008,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Nortel (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Queue; Metric (unit); Concurrency; Cover (algebra); Model-based testing; Test (biology); Test case; Reliability engineering; Distributed computing; Programming language; Engineering; Operations management; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0432607937311662,"gpt":0.2596500747047716,"spread":0.2163892809736054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005395967,0.0001661928,0.0001915752,0.00006603947,0.0004639795,0.00009845254,0.0002446733,0.00008318394,3.41911e-7],"category_scores_gemma":[0.002316723,0.0001386683,0.0000310083,0.0003443139,0.0001514578,0.0003122879,0.00003372233,0.0001127341,0.000001716273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005675885,"about_ca_system_score_gemma":0.000109528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002296852,"about_ca_topic_score_gemma":0.000001251416,"domain_scores_codex":[0.9987141,0.0000613941,0.0002666311,0.0005417321,0.0001922117,0.0002238789],"domain_scores_gemma":[0.9975461,0.0012199,0.0001373267,0.0005812602,0.0004222775,0.00009314607],"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":[0.000298989,0.001251404,0.7613959,0.003594196,0.00008900095,0.00006255285,0.0121199,0.02237647,0.002320742,0.006468949,0.01553989,0.1744819],"study_design_scores_gemma":[0.001948904,0.00184194,0.3484124,0.001058489,0.00006358248,0.001314664,0.00005963991,0.6089415,0.001432249,0.03019264,0.002964646,0.001769332],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1099899,0.0001310865,0.8794623,0.0001794664,0.0001020191,0.0004782872,0.000006738712,0.009595705,0.00005452879],"genre_scores_gemma":[0.587909,0.000007565455,0.4118569,0.00005515576,0.0000300046,0.0001051188,0.000006471044,0.00001087297,0.00001895681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.586565,"threshold_uncertainty_score":0.5654729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3092453472","doi":"10.1002/stvr.1751","title":"BUGSJS: a benchmark and taxonomy of JavaScript bugs","year":2020,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"European Social Fund; European Commission; Natural Sciences and Engineering Research Council of Canada; Advanced Remanufacturing and Technology Centre; National Research, Development and Innovation Office; Innovációs és Technológiai Minisztérium","keywords":"JavaScript; Computer science; Unobtrusive JavaScript; Benchmark (surveying); Unit testing; Software bug; Debugging; Taxonomy (biology); Programming language; Web application; Software; Software testing; Test case; Software engineering; Rich Internet application; World Wide Web; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05055143313862166,"gpt":0.2378494320064721,"spread":0.1872979988678504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511987,0.0001535577,0.0002276603,0.00004720159,0.000141496,0.00007274273,0.0003338023,0.00008280217,0.000003231376],"category_scores_gemma":[0.008090468,0.0001421531,0.00003347906,0.0004528615,0.0002107048,0.0002230042,0.0002191219,0.0001603851,0.000002226435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779868,"about_ca_system_score_gemma":0.00007726569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374339,"about_ca_topic_score_gemma":4.456587e-7,"domain_scores_codex":[0.9986395,0.00008598289,0.0003574573,0.0005738101,0.0001719139,0.0001713254],"domain_scores_gemma":[0.9980181,0.0008358285,0.0001982041,0.0005232494,0.0002554432,0.0001691689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001791479,0.000119171,0.7038515,0.0005764411,0.00001329723,0.000003301,0.001568819,0.00003494488,0.0009246173,0.001602984,0.006655946,0.284631],"study_design_scores_gemma":[0.001239783,0.001254531,0.759297,0.0005059661,0.00007543569,0.00009819389,0.00009084362,0.145851,0.003799074,0.06938388,0.01696659,0.001437711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1245939,0.0005449782,0.8630589,0.001984738,0.0001308656,0.000569618,0.000009754038,0.008673445,0.0004337709],"genre_scores_gemma":[0.5405484,0.00001007806,0.4591355,0.0002475098,0.00001903756,0.00002594316,0.000002179563,0.000005696434,0.000005655329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4159546,"threshold_uncertainty_score":0.9685631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1527815941","doi":"10.1002/stvr.1576","title":"Automatic fault localization for client‐side JavaScript","year":2015,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"JavaScript; Unobtrusive JavaScript; Computer science; Ajax; Scripting language; Web application; Debugging; Programming language; Rich Internet application; Document Object Model; Code (set theory); Source code; Dynamic web page; Tracing; Operating system; World Wide Web; Web service; Web page","retraction":null,"screen_n_in":null,"score":{"opus":0.05771615534496858,"gpt":0.2918301028476358,"spread":0.2341139475026673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001485305,0.0001751178,0.0001972681,0.00008647987,0.0002614884,0.000176076,0.0003952323,0.0001144963,0.000001050329],"category_scores_gemma":[0.02141985,0.0001603487,0.00004435334,0.0004928673,0.0001171864,0.0003331118,0.0001189686,0.0001096035,0.000009527867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001067102,"about_ca_system_score_gemma":0.0001725447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001212092,"about_ca_topic_score_gemma":0.000001354901,"domain_scores_codex":[0.9983643,0.0001120601,0.0004065572,0.0005941288,0.0002642286,0.0002587536],"domain_scores_gemma":[0.9969961,0.001026911,0.0001997627,0.0008111243,0.0007706847,0.0001954142],"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":[0.0000195952,0.0003481753,0.2088524,0.0005039118,0.00001495473,0.000002741102,0.002431423,0.001803986,0.00008382417,0.003430149,0.04190099,0.7406079],"study_design_scores_gemma":[0.0004612108,0.0002208083,0.01742193,0.0001061737,0.00001698596,0.00002515047,0.0000220372,0.8372286,0.0002412529,0.1396484,0.004269002,0.0003384624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01683364,0.000109932,0.9681287,0.0003743882,0.0003077101,0.0004925627,0.000004652573,0.01359751,0.000150837],"genre_scores_gemma":[0.3487271,0.000002183388,0.6508001,0.0002603794,0.00003719624,0.00009942232,0.00001582416,0.00001349123,0.00004432064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8354246,"threshold_uncertainty_score":0.9868231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4248647026","doi":"10.1002/stvr.410","title":"Improving the coverage criteria of UML state machines using data flow analysis","year":2009,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Unified Modeling Language; Guard (computer science); Finite-state machine; Data mining; Data flow diagram; Test suite; Context (archaeology); State (computer science); Control flow; Data-flow analysis; Tree (set theory); Test case; Algorithm; Machine learning; Database; Programming language; Mathematics; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.04962212616320409,"gpt":0.3113156837427992,"spread":0.2616935575795951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001839679,0.0001683473,0.0002624078,0.0001189439,0.0003132579,0.0001804482,0.001065316,0.00005744,0.000002656537],"category_scores_gemma":[0.007380912,0.0001226545,0.00005503769,0.00123147,0.0001345251,0.0004047441,0.0003360815,0.0001664225,5.669326e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003287774,"about_ca_system_score_gemma":0.00009130535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007832915,"about_ca_topic_score_gemma":0.000004212645,"domain_scores_codex":[0.9982409,0.0001821735,0.0004515154,0.0006582876,0.0002586932,0.0002083536],"domain_scores_gemma":[0.9960285,0.0009673744,0.0003361685,0.002271335,0.0003301094,0.00006644199],"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":[0.00001184047,0.0001272607,0.1546931,0.00009100228,0.00003677086,0.000002272476,0.0005318355,0.003208461,0.001567979,0.00007493391,0.0003307207,0.8393238],"study_design_scores_gemma":[0.00007157257,0.00004548904,0.1667177,0.00002723086,0.00006940669,0.000008101148,0.000001506323,0.8212285,0.0001861691,0.01148616,0.00001975917,0.0001383599],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1042186,0.0001180031,0.8926222,0.0002507176,0.00007623665,0.0001703985,0.0000350882,0.002489477,0.00001930493],"genre_scores_gemma":[0.5423722,0.000004415052,0.4574846,0.00009513962,0.00001608656,0.000001967961,0.00001635225,0.000004273185,0.000004936439],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8391854,"threshold_uncertainty_score":0.8836174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806282111","doi":"10.1002/stvr.1669","title":"MuMonDE: A framework for evaluating model clone detectors using model mutation analysis","year":2018,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"clone (Java method); Preprocessor; Mutation; Computer science; Mutation testing; Data mining; Detector; Precision and recall; Software engineering; Artificial intelligence; Genetics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1031035430604409,"gpt":0.3755641998763948,"spread":0.2724606568159539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001894408,0.0001848413,0.0002376226,0.0002470752,0.0004810793,0.0001702951,0.0004145512,0.0001566119,0.000001839753],"category_scores_gemma":[0.0294845,0.0001849019,0.00009184403,0.001735409,0.0001550966,0.0003381261,0.0001381276,0.0002145131,0.000002508162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001778609,"about_ca_system_score_gemma":0.0002364366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004814708,"about_ca_topic_score_gemma":0.000001723217,"domain_scores_codex":[0.9979345,0.00008509376,0.0003996741,0.0008015328,0.0004218349,0.0003573792],"domain_scores_gemma":[0.9948491,0.002770693,0.0001831385,0.000939868,0.001110206,0.0001469438],"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":[0.00001733581,0.00005473328,0.02515528,0.0001069596,0.00004430519,3.134092e-7,0.001149725,0.9471109,0.002028612,0.0009891633,0.00001058552,0.02333208],"study_design_scores_gemma":[0.0001469682,0.00008464389,0.01149756,0.00002938034,0.00007682997,0.000002348462,0.0000105422,0.9474027,0.0005640456,0.03998723,0.000001082486,0.0001966872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3954381,0.00002227311,0.6036503,0.00004463151,0.00006049246,0.0002779367,0.000007986967,0.000495792,0.000002521333],"genre_scores_gemma":[0.4895285,6.732877e-7,0.5103564,0.00002122538,0.00002748511,0.00004111289,0.000005690792,0.00001132039,0.000007650186],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09409037,"threshold_uncertainty_score":0.9786906,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2994711059","doi":"10.1002/stvr.1721","title":"Leveraging metamorphic testing to automatically detect inconsistencies in code generator families","year":2019,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Software quality; Oracle; Software; Leverage (statistics); Regression testing; Code (set theory); Code coverage; Unreachable code; Software development; Code generation; Programming language; Redundant code; Software construction; Set (abstract data type); Operating system; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03641849049665075,"gpt":0.2574023251371866,"spread":0.2209838346405358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002001292,0.0002723082,0.0003881939,0.0002713242,0.0002233855,0.0002329327,0.0006089333,0.0001229892,0.000003856164],"category_scores_gemma":[0.02494671,0.0002525929,0.00004626013,0.001487493,0.0001059209,0.000327642,0.0003531842,0.0003040622,0.00004518104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458521,"about_ca_system_score_gemma":0.0002463042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004311439,"about_ca_topic_score_gemma":0.00001188851,"domain_scores_codex":[0.997443,0.0002155186,0.0006381865,0.0009389655,0.0003471924,0.0004171457],"domain_scores_gemma":[0.9947007,0.003336112,0.0001974934,0.001136562,0.0004458889,0.0001832364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007048522,0.00007850052,0.88073,0.0002335309,0.000006837165,0.000006950198,0.001243892,0.001569211,0.003856068,0.0002216704,0.0002358661,0.1118104],"study_design_scores_gemma":[0.0003309694,0.000237423,0.7676047,0.0004172467,0.00001266913,0.00004986554,0.00004680414,0.2091079,0.001236007,0.02008365,0.0002381691,0.0006346508],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7547442,0.00008471105,0.2352684,0.0003811302,0.0001679172,0.0005106825,0.00000302064,0.008630551,0.0002093776],"genre_scores_gemma":[0.5078698,0.000001461708,0.4917551,0.0002826804,0.00001312113,0.00004517073,0.000001230338,0.00001221928,0.00001920475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2564867,"threshold_uncertainty_score":0.9999926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1516438975","doi":"10.1002/stvr.1573","title":"Anomaly detection in performance regression testing by transaction profile estimation","year":2015,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Science Foundation Ireland","keywords":"Computer science; Regression testing; Workload; Anomaly detection; Data mining; Software performance testing; Software regression; Regression analysis; Regression; Non-regression testing; Software; Machine learning; Software quality; Statistics; Software system; Operating system; Software development","retraction":null,"screen_n_in":null,"score":{"opus":0.02938539619239948,"gpt":0.2524789475198476,"spread":0.2230935513274481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001929767,0.0002208593,0.0002323832,0.0001283945,0.0002721793,0.0001110696,0.0002756256,0.0001901713,0.000001805713],"category_scores_gemma":[0.003299922,0.0001865492,0.00002962808,0.0011521,0.0001050616,0.001235154,0.00005406051,0.0002952946,0.00002034396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002848464,"about_ca_system_score_gemma":0.0001708186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003442207,"about_ca_topic_score_gemma":0.000006932316,"domain_scores_codex":[0.9978537,0.0001943199,0.0005750292,0.0007147665,0.0003638329,0.0002983711],"domain_scores_gemma":[0.9981153,0.0003822539,0.000260836,0.0006286632,0.0004525615,0.0001603933],"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":[0.00003637037,0.0001505478,0.3654985,0.0002951489,0.000002232373,7.647214e-7,0.0007417316,0.002854885,0.001882943,0.00000571389,0.00009483311,0.6284363],"study_design_scores_gemma":[0.000617818,0.000273753,0.358707,0.0001997264,0.000006728042,0.00003421579,0.00005503312,0.6332483,0.005865254,0.000501832,0.0001824974,0.0003078927],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7072811,0.00008577246,0.2909878,0.0001127639,0.0003030442,0.0004193423,0.000002384817,0.0006720973,0.0001357021],"genre_scores_gemma":[0.8725328,0.00000757046,0.1272496,0.00002537708,0.00002767152,0.00009068862,0.00001175431,0.00001160483,0.00004291932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6303934,"threshold_uncertainty_score":0.7607256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087103218","doi":"10.1002/stvr.295","title":"Eight maxims for software inspectors","year":2004,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Cover (algebra); Set (abstract data type); Software; Engineering; Engineering ethics; Software inspection; Computer science; Software engineering; Management science; Software development; Software quality; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02767475553459849,"gpt":0.2663009924304416,"spread":0.2386262368958431,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007521953,0.0001971628,0.0001912876,0.0001146737,0.0003192217,0.0001563429,0.0005889853,0.0001242919,0.000003372734],"category_scores_gemma":[0.01928198,0.0001837383,0.00006305463,0.0006616428,0.0001431157,0.0003480761,0.0001583662,0.000222457,0.00002050055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002010149,"about_ca_system_score_gemma":0.0002078274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005650781,"about_ca_topic_score_gemma":0.000001377951,"domain_scores_codex":[0.9982103,0.00003781724,0.0003135838,0.0007449359,0.0003049433,0.0003884516],"domain_scores_gemma":[0.9963874,0.001977853,0.00009020945,0.0009395287,0.0004127153,0.0001923041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000063135,0.000823482,0.698514,0.001477995,0.00005685108,0.0000175053,0.002723732,0.0148332,0.001728781,0.01869366,0.001713663,0.259354],"study_design_scores_gemma":[0.002393684,0.0005691067,0.8579366,0.0002305575,0.00002506398,0.00007209215,0.00003711071,0.005967003,0.004254228,0.1170717,0.01022953,0.001213252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1430147,0.0001408564,0.8537269,0.0005100871,0.0003198569,0.0005179575,0.00001715681,0.001733451,0.000018969],"genre_scores_gemma":[0.3684474,0.000007709378,0.631273,0.00006222145,0.00005774544,0.00006908581,0.00001662857,0.00002009991,0.00004611246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2581407,"threshold_uncertainty_score":0.988979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035512953","doi":"10.1002/stvr.418","title":"Fault‐driven stress testing of distributed real‐time software based on UML models","year":2009,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Stress testing (software); Unified Modeling Language; Test case; Test (biology); Stress test; Node (physics); Stress (linguistics); Cover (algebra); Real-time computing; Software; Reliability engineering; Programming language; Engineering; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02393212963172253,"gpt":0.2497538415845723,"spread":0.2258217119528498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001105781,0.0003637279,0.0005058644,0.0001369675,0.0003952302,0.0001063738,0.0007609984,0.0002449694,0.000005499673],"category_scores_gemma":[0.006559453,0.0003090088,0.000112434,0.001187268,0.0002246261,0.0005375303,0.0001069676,0.0003146885,0.00001386131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001556976,"about_ca_system_score_gemma":0.0002791361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001515652,"about_ca_topic_score_gemma":9.265351e-7,"domain_scores_codex":[0.9968071,0.0002392066,0.0008695753,0.001042875,0.0005887711,0.0004524468],"domain_scores_gemma":[0.9947598,0.001832829,0.000520788,0.001693446,0.0009738277,0.0002193306],"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":[0.0001070893,0.001304161,0.4540191,0.0008704739,0.00001981961,0.000007773583,0.0006960541,0.3186733,0.001623289,0.0004889934,0.0003770631,0.2218128],"study_design_scores_gemma":[0.0005145411,0.0004828806,0.284514,0.000405739,0.00001872964,0.000006168737,0.00001341084,0.7087105,0.0008167946,0.004091346,0.00003099579,0.0003948712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3717332,0.00004193806,0.6242728,0.0004387101,0.0001952455,0.0007649856,0.0001411488,0.002061017,0.0003509382],"genre_scores_gemma":[0.7374184,0.000005787259,0.2623325,0.00008841745,0.00003771448,0.00002372435,0.00006146114,0.00001359026,0.00001845688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3900371,"threshold_uncertainty_score":0.9999362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084111010","doi":"10.1002/stvr.458","title":"An approach for testing pointcut descriptors in AspectJ","year":2011,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"RealNetworks (Canada)","funders":"","keywords":"AspectJ; Computer science; Aspect-oriented programming; Modularity (biology); Set (abstract data type); Programming language; Compile time; Compiler; Software engineering; Base (topology); Test case; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.1369196117904165,"gpt":0.2954368131809403,"spread":0.1585172013905238,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001684977,0.0001769475,0.0002061577,0.0001047114,0.0001474953,0.00005282319,0.000498236,0.0001028522,7.876711e-7],"category_scores_gemma":[0.02028851,0.0001689383,0.00002796144,0.0006020815,0.0001140607,0.0005339528,0.00008291402,0.0001940596,8.584961e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008272285,"about_ca_system_score_gemma":0.00006621487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008584629,"about_ca_topic_score_gemma":9.13515e-7,"domain_scores_codex":[0.9983699,0.0001542343,0.0003431094,0.0007111022,0.0001165644,0.0003051255],"domain_scores_gemma":[0.9971772,0.00158693,0.0001263243,0.0007664767,0.0002411293,0.0001018896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006173898,0.0008421857,0.5698472,0.0007871458,0.00001305244,0.000005617818,0.007146311,0.03990547,0.00625396,0.01063513,0.00003696838,0.3644652],"study_design_scores_gemma":[0.0005087358,0.0003708475,0.7124223,0.00006695178,0.00001025174,0.00002711231,0.0001826324,0.185561,0.002130215,0.09806064,0.00003648475,0.0006228291],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04277359,0.00005067754,0.9550318,0.0000143898,0.0001571098,0.000385086,0.000002521306,0.001447366,0.0001374535],"genre_scores_gemma":[0.2736073,0.000001592282,0.7262425,0.00002365504,0.00001978839,0.00008151251,0.00000370259,0.00001292764,0.000007026221],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3638424,"threshold_uncertainty_score":0.987964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3207636857","doi":"10.1002/stvr.1796","title":"GPU acceleration of finite state machine input execution: Improving scale and performance","year":2021,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Engineering and Physical Sciences Research Council; University of Edinburgh","keywords":"Computer science; Scalability; Parallel computing; Kernel (algebra); Speedup; Multi-core processor; Finite-state machine; Acceleration; Process (computing); CUDA; Computer engineering; Algorithm; Programming language; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02022802077216418,"gpt":0.2404493400978162,"spread":0.220221319325652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007053636,0.0001336271,0.0001741934,0.00005903649,0.0002436582,0.0001131139,0.0001744915,0.00006722315,0.000002223478],"category_scores_gemma":[0.003511393,0.0001282623,0.00002296494,0.0004475175,0.0001336393,0.0003673717,0.0001967917,0.0001581676,0.000001112818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003114371,"about_ca_system_score_gemma":0.0001212148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001358715,"about_ca_topic_score_gemma":0.000003854899,"domain_scores_codex":[0.9987197,0.00009393516,0.000354331,0.0004942879,0.0001775886,0.0001601705],"domain_scores_gemma":[0.9979702,0.0006885423,0.0001994987,0.000579562,0.0004873944,0.00007485422],"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":[0.00001029419,0.00008814393,0.4916123,0.0003867586,0.000003823034,0.000002827568,0.0006835577,0.0002108675,0.001546477,0.00007788542,0.0000908866,0.5052862],"study_design_scores_gemma":[0.0003453129,0.0002178066,0.5767328,0.0002118791,0.00001501781,0.00009899086,0.00001002001,0.3983274,0.01298362,0.01055687,0.0001501467,0.0003500873],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5194383,0.0002488302,0.4777898,0.0001813873,0.0000809946,0.0001201357,0.000005788275,0.002075255,0.00005952479],"genre_scores_gemma":[0.6426042,0.00003921373,0.3572326,0.00005568458,0.00001114883,0.00001068618,0.000008495219,0.000005668596,0.00003224888],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5049361,"threshold_uncertainty_score":0.5230383,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155388066","doi":"10.1002/stvr.210","title":"A rigorous method for test templates generation from object‐oriented specifications","year":2001,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Template; Computer science; Formal specification; Programming language; Focus (optics); Test case; White-box testing; Object-oriented programming; Formal methods; Extension (predicate logic); Specification language; Test (biology); Software engineering; Software; Software development; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.07291649913695267,"gpt":0.3055475201157303,"spread":0.2326310209787777,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00102734,0.0002275169,0.0002351661,0.00009744792,0.000591554,0.0002015825,0.0004133029,0.0001449733,0.000007394136],"category_scores_gemma":[0.01485229,0.0002151237,0.00006315443,0.0006720645,0.00009358101,0.0003153115,0.00009457287,0.0001664994,0.00001258479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000925909,"about_ca_system_score_gemma":0.0001020741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007342249,"about_ca_topic_score_gemma":0.00001387056,"domain_scores_codex":[0.9979649,0.0001270247,0.0004856567,0.0009225514,0.000214657,0.0002851659],"domain_scores_gemma":[0.9929975,0.00483635,0.0002633724,0.001105716,0.00065842,0.0001386797],"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":[0.00003357093,0.0008529499,0.5234631,0.00008308635,0.00003200232,0.000006022084,0.001857446,0.00045712,0.01120727,0.006298813,0.02085363,0.434855],"study_design_scores_gemma":[0.0008003493,0.0003704811,0.2675537,0.0001081497,0.00005824233,0.00008491831,0.0000293969,0.5603237,0.003225307,0.1482161,0.01836441,0.0008653242],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02000184,0.00009917531,0.9689596,0.0009338536,0.0002357658,0.0005860906,0.00004148125,0.009017361,0.0001248739],"genre_scores_gemma":[0.1846107,0.00001657932,0.814645,0.000163444,0.0001569152,0.0002048657,0.00009233974,0.00001846682,0.00009168612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5598665,"threshold_uncertainty_score":0.9934461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979327180","doi":"10.1002/stvr.1713","title":"An end‐user‐centric test generation methodology for performance evaluation of mobile networked applications","year":2019,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Computer network; Test suite; Wireless network; End user; Wireless; Test case; Machine learning; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06774374964768788,"gpt":0.3249485911742777,"spread":0.2572048415265898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005779985,0.0001813975,0.000306524,0.0001036773,0.0002597064,0.00005502846,0.0004541818,0.000175505,0.00001501628],"category_scores_gemma":[0.001924395,0.0001601831,0.00006016159,0.0006897963,0.0001169935,0.0005740107,0.00006038291,0.0001273153,0.00001176744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263453,"about_ca_system_score_gemma":0.0003007767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003393951,"about_ca_topic_score_gemma":0.000002124606,"domain_scores_codex":[0.9975204,0.0003930608,0.0006559382,0.0007765924,0.0003968841,0.0002570626],"domain_scores_gemma":[0.9951156,0.001466109,0.0004234387,0.001294108,0.001605269,0.00009541725],"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":[0.00001605227,0.0003323393,0.4847988,0.0004300596,0.000009851371,1.930671e-8,0.0004701174,0.03208456,0.006148008,0.0003803486,0.00005834352,0.4752715],"study_design_scores_gemma":[0.0006921017,0.0004894845,0.2111628,0.00003284337,0.00004570402,0.000005731747,0.00004196344,0.782271,0.003074805,0.0008424615,0.001095546,0.0002456335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5904573,0.0001687715,0.4066138,0.00003184286,0.0003097449,0.002127274,0.000009762835,0.0002462066,0.00003529469],"genre_scores_gemma":[0.7562675,0.00002419404,0.2426087,0.00002820738,0.00009814756,0.0008767645,0.0000614942,0.00001067637,0.00002433449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7501864,"threshold_uncertainty_score":0.6532076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3040858112","doi":"10.1002/stvr.1745","title":"TimelyRep: Timing deterministic replay for Android web applications","year":2020,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Green IT and Sustainability","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Debugging; Computer science; Android (operating system); Web application; Touchscreen; Backward compatibility; Mobile device; Operating system; Embedded system; Event (particle physics); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03088089899466809,"gpt":0.2437286771006506,"spread":0.2128477781059825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003139032,0.000149393,0.0001806377,0.00002477159,0.0002097444,0.00004452186,0.0001199183,0.00009085902,0.00001185308],"category_scores_gemma":[0.002769525,0.0001516012,0.00004787532,0.0002388625,0.0001007766,0.00008607397,0.00002673972,0.0001363695,0.00001087908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005946182,"about_ca_system_score_gemma":0.00005530176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004755047,"about_ca_topic_score_gemma":8.867045e-7,"domain_scores_codex":[0.9989527,0.00002548288,0.0003255504,0.0003994391,0.0000904996,0.0002063464],"domain_scores_gemma":[0.9987327,0.0004811593,0.00005362829,0.0003666402,0.0002062262,0.0001596665],"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":[0.0002139298,0.0003592239,0.3972574,0.01220398,0.00009232587,0.000006651623,0.00510914,0.02417345,0.01697698,0.001006811,0.00886202,0.5337381],"study_design_scores_gemma":[0.00106763,0.0002641921,0.08159151,0.00005403625,0.0001216755,0.00001709325,0.0003591299,0.8360751,0.0009993715,0.006387408,0.07212888,0.0009339581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5158427,0.0003374589,0.4758656,0.0008163847,0.0001870595,0.00241707,0.0001297923,0.003408002,0.0009959221],"genre_scores_gemma":[0.9508666,0.000006680102,0.04855774,0.0000839671,0.00008690196,0.0002949939,0.00003686926,0.00002673766,0.00003949605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8119017,"threshold_uncertainty_score":0.6182119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4322489317","doi":"10.1002/stvr.1842","title":"An investigation of distributed computing for combinatorial testing","year":2023,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hypergraph; Computer science; Graph; Theoretical computer science; Vertex (graph theory); Algorithm; Parallel computing; Mathematics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0456312420782707,"gpt":0.2955049233390974,"spread":0.2498736812608267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002019296,0.0001614624,0.0002278625,0.00009998125,0.0003682111,0.0001020171,0.0004442715,0.0001137824,2.642769e-7],"category_scores_gemma":[0.01684681,0.0001611818,0.00003771846,0.001451455,0.0001732074,0.0002834905,0.0001245046,0.0001307866,0.000001602507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004434993,"about_ca_system_score_gemma":0.0001302473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001176257,"about_ca_topic_score_gemma":3.580352e-7,"domain_scores_codex":[0.9983119,0.0001397546,0.0004851511,0.0005776148,0.0002206235,0.0002649607],"domain_scores_gemma":[0.9937956,0.004178403,0.0003389191,0.0007160111,0.0008451125,0.0001259712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001188984,0.00008093044,0.9205869,0.0003644202,0.00000634468,9.222547e-7,0.0007635624,0.001207599,0.002893696,0.002519441,0.001064881,0.07049934],"study_design_scores_gemma":[0.0002936623,0.0002558788,0.4257725,0.000117302,0.000009659437,0.000005298505,0.0000127473,0.4243022,0.001238737,0.1477593,0.00002303252,0.0002096751],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4673586,0.00001072606,0.5207145,0.0001100937,0.0002350969,0.0003240871,0.00001917196,0.01122111,0.000006618931],"genre_scores_gemma":[0.5790918,6.040834e-7,0.4207527,0.00002110248,0.0000410796,0.0000228951,0.00005871048,0.000009815505,0.000001296317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4948145,"threshold_uncertainty_score":0.9914347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969864380","doi":"10.1002/stvr.241","title":"Editorial: <i>Mutation 2000—A Symposium on Mutation Testing</i>","year":2001,"lang":"en","type":"editorial","venue":"Software Testing Verification and Reliability","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Citation; Mutation; Library science; Computer science; World Wide Web; Information retrieval; Genetics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01499552356034459,"gpt":0.281196696684783,"spread":0.2662011731244384,"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":[0.001528627,0.0004352254,0.0003492836,0.0001191997,0.0003283242,0.0001666506,0.0003624372,0.001508798,0.000008319182],"category_scores_gemma":[0.04617828,0.0003994057,0.0000947703,0.0003580548,0.0004056841,0.00001349546,0.0001421744,0.0007672104,0.00004842463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001520347,"about_ca_system_score_gemma":0.001059982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001632216,"about_ca_topic_score_gemma":0.000008477906,"domain_scores_codex":[0.9964309,0.000197885,0.0007584469,0.0009612472,0.001174972,0.0004764991],"domain_scores_gemma":[0.9951255,0.001231603,0.0004713813,0.000824809,0.002058951,0.0002877057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001155192,0.0001480839,0.0003851198,0.0004069504,0.00001999232,0.000002165498,0.00007173909,0.0001439481,0.002349174,9.121472e-7,0.9805149,0.01584145],"study_design_scores_gemma":[0.0007127103,0.001243797,0.0006522395,0.000182469,0.00005625954,0.000007841997,0.00003897732,0.0004283776,0.0009566601,0.0003142862,0.9948747,0.0005316465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.006536853,0.0002481391,0.003327454,0.0002959601,0.9860494,0.001114995,0.000396038,0.0002904227,0.001740695],"genre_scores_gemma":[0.002508649,0.0005582625,0.01314227,0.0001167007,0.9767427,0.0001183945,0.004945113,0.00008544831,0.001782415],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.04464965,"threshold_uncertainty_score":0.9998458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4230255398","doi":"10.1002/stvr.385","title":"Error‐preserving reductions on communication protocols","year":2007,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Reachability; Computer science; Model checking; Variety (cybernetics); State (computer science); Process (computing); Transformation (genetics); Formal methods; Communications protocol; Distributed computing; Theoretical computer science; Programming language; Artificial intelligence; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.08466286065561494,"gpt":0.3648461685731593,"spread":0.2801833079175443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003952032,0.0001532844,0.0001403504,0.0001177569,0.0005765895,0.000136076,0.0007636563,0.0001352435,0.000007374735],"category_scores_gemma":[0.007521872,0.0001470414,0.00003192825,0.0007252151,0.0001918786,0.0005704486,0.0001829533,0.0003570334,0.00002430442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001285009,"about_ca_system_score_gemma":0.00006642528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005763042,"about_ca_topic_score_gemma":0.000002510005,"domain_scores_codex":[0.9981577,0.000274734,0.0004827742,0.0005389791,0.0002871508,0.0002585997],"domain_scores_gemma":[0.9964501,0.0008801289,0.0002734004,0.001894107,0.0003782667,0.0001240167],"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":[0.0001396872,0.001175676,0.07472285,0.0004797709,0.00002263583,0.000002573569,0.004322018,0.002171974,0.007479655,0.2047545,0.001944128,0.7027845],"study_design_scores_gemma":[0.0006498436,0.0003894192,0.8761221,0.0003412075,0.0000150783,0.00004782625,0.0002458205,0.04964841,0.009363617,0.04004879,0.0223836,0.0007442519],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04164127,0.0000324732,0.94832,0.000691749,0.0002068033,0.00377698,0.000003030647,0.001278572,0.004049143],"genre_scores_gemma":[0.1753927,0.000004008882,0.823647,0.0001116623,0.00003678574,0.0006820834,0.000008918691,0.00001133669,0.0001054968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8013993,"threshold_uncertainty_score":0.9004927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2053464286","doi":"10.1002/stvr.1476","title":"Status and Awards","year":2012,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Labor Movements and Unions","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Business","retraction":null,"screen_n_in":null,"score":{"opus":0.03552312542783721,"gpt":0.314535663699376,"spread":0.2790125382715388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008452899,0.00005451884,0.00006313028,0.00001759278,0.0005422407,0.00004305405,0.00003948348,0.00005278545,0.00003690671],"category_scores_gemma":[0.003282905,0.00004677218,0.000009750552,0.0001599825,0.0002561261,0.0001886394,0.0000249221,0.00006766929,0.000001805691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000426791,"about_ca_system_score_gemma":0.00006500125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002607361,"about_ca_topic_score_gemma":0.00005642266,"domain_scores_codex":[0.999285,0.00009763855,0.0001095518,0.0001421444,0.0001285398,0.0002371332],"domain_scores_gemma":[0.9992614,0.000255426,0.00004705609,0.0001324701,0.0001132428,0.0001904233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001415072,0.00004463659,0.9462782,0.000007447652,0.000001581391,2.70154e-8,0.003125854,5.937089e-7,0.0000341232,0.01716811,0.0001244469,0.03321363],"study_design_scores_gemma":[0.00006780568,0.000009119533,0.9009945,0.000005334679,0.00000620746,1.537396e-7,0.0005577803,0.000007197001,0.000008831574,0.001418779,0.09686091,0.00006343341],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99504,0.0003054148,0.0004948131,0.0005217865,0.0002026631,0.0001547463,0.000009401919,0.0001949465,0.003076207],"genre_scores_gemma":[0.9907029,0.0001134694,0.008589012,0.00016607,0.00009376262,0.000008450692,0.000004379348,0.000004457812,0.0003174941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09673646,"threshold_uncertainty_score":0.4170532,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2196997841","doi":"","title":"Eight maxims for software inspectors: Research Articles","year":2004,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Cover (algebra); Set (abstract data type); Software; Software inspection; Engineering; Engineering ethics; Computer science; Software engineering; Engineering management; Sociology; Software development; Software quality; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07757743155948835,"gpt":0.3266650500084117,"spread":0.2490876184489233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002593285,0.0001857335,0.000194649,0.0002233198,0.0005728105,0.0002735248,0.0007593373,0.000141001,0.000004400768],"category_scores_gemma":[0.04088176,0.0001716825,0.00005756211,0.00132196,0.0003104099,0.0004266097,0.0002729326,0.0004112062,0.00003834186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002864425,"about_ca_system_score_gemma":0.0002991193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001213372,"about_ca_topic_score_gemma":0.000003286685,"domain_scores_codex":[0.99744,0.0001206035,0.0003593127,0.0008781088,0.0005948228,0.0006071428],"domain_scores_gemma":[0.9927427,0.004725212,0.00007117191,0.001185035,0.001024544,0.0002513421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001147948,0.00138141,0.593982,0.001725583,0.00005960307,0.00002794834,0.005745394,0.008603259,0.00534464,0.02987722,0.003191093,0.349947],"study_design_scores_gemma":[0.002406048,0.0008830105,0.6582407,0.0003543096,0.00001630711,0.00006473493,0.0001365829,0.007497168,0.01165483,0.3089428,0.008719991,0.001083491],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3133171,0.0002033525,0.6832892,0.0009311247,0.0002017435,0.0006679296,0.00001410256,0.00135574,0.00001977169],"genre_scores_gemma":[0.5151458,0.000009636501,0.4845638,0.00003254882,0.00007042922,0.0001014246,0.000009586724,0.00002016871,0.00004658891],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3488635,"threshold_uncertainty_score":0.9671973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206885924","doi":"10.1002/stvr.1799","title":"A mutation framework for evaluating security analysis tools in IoT applications","year":2021,"lang":"en","type":"preprint","venue":"Software Testing Verification and Reliability","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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":"Computer science; Taint checking; Internet of Things; Sensitivity (control systems); Precision and recall; Context (archaeology); Security analysis; Set (abstract data type); Data mining; Process (computing); Domain (mathematical analysis); Information flow; Information retrieval; Computer security; Software; Engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06271620279564884,"gpt":0.3700882404693309,"spread":0.3073720376736821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00182656,0.0002730773,0.000466911,0.0003219348,0.0002556565,0.0004734725,0.0005404156,0.0004327725,0.000004020081],"category_scores_gemma":[0.01553046,0.0003100929,0.0001717055,0.001968158,0.00009235778,0.0003057405,0.0004844356,0.0007149883,8.283541e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002989965,"about_ca_system_score_gemma":0.0002990219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088865,"about_ca_topic_score_gemma":0.00002346966,"domain_scores_codex":[0.9969627,0.0002661759,0.0007622357,0.001449154,0.0003054375,0.0002543067],"domain_scores_gemma":[0.9940093,0.002561984,0.0006279821,0.001584116,0.001126082,0.00009054028],"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":[0.0000279585,0.0004973632,0.02706878,0.00192872,0.0001424933,0.000003400678,0.003560679,0.0654598,0.0003384553,0.008099604,0.00001366494,0.8928591],"study_design_scores_gemma":[0.0002037585,0.00008629293,0.06501123,0.000264722,0.0001931167,0.000005645298,0.000163021,0.4129376,0.001135118,0.5192478,0.0001346839,0.000617062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04529462,0.0002290147,0.9510121,0.0002289709,0.0001478548,0.001838984,0.00003637441,0.001197693,0.00001436978],"genre_scores_gemma":[0.3583991,0.00001650067,0.6394122,0.00005135117,0.00002930413,0.001964024,0.0001115261,0.00001202642,0.000003971987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.892242,"threshold_uncertainty_score":0.9999351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}