{"meta":{"query_hash":"100aa09bc2bb","filters":{"topic":"Software Testing and Debugging Techniques"},"cohort_total":996,"direct_labels_cover":2,"predictions_cover":996,"exported":996,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/100aa09bc2bb","api":"https://metacan.xera.ac/api/v1/cohort?topic=Software+Testing+and+Debugging+Techniques"},"results":[{"id":"W110592620","doi":"10.5753/sbes.2007.21316","title":"Experimental Evaluation of Coverage Criteria for FSM-based Testing","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Code coverage; Finite-state machine; Reliability engineering; Test plan; Test strategy; Empirical research; Test (biology); Compromise; Plan (archaeology); Data mining; Machine learning; Artificial intelligence; Algorithm; Engineering; Mathematics; Statistics; Software","score_opus":0.1379830994562716,"score_gpt":0.4016068810919319,"score_spread":0.26362378163566025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W110592620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09081292,0.000031280353,0.9041971,0.00002828001,0.00010837636,0.00022211224,7.8859927e-7,0.002256973,0.0023421806],"genre_scores_gemma":[0.55760765,8.094848e-9,0.442253,0.000098690005,0.000016168076,0.000014338942,0.0000010677971,0.000003148574,0.0000059221416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991825,0.000029365972,0.00018468127,0.00017644725,0.00028390248,0.00014311036],"domain_scores_gemma":[0.9985507,0.0007678725,0.000077522935,0.0002553478,0.00031728589,0.00003127602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022240127,0.0000672547,0.00008112724,0.000079097146,0.000054551194,0.00003658345,0.00023687392,0.000029714773,0.000010663643],"category_scores_gemma":[0.00100625,0.00006274475,0.000031809683,0.00018016937,0.00001755558,0.00012209592,0.00004306542,0.000023551514,0.0000010701929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007963709,0.0009208931,0.025378885,0.00012756266,0.000024835786,0.0000070095903,0.0012782392,0.000987559,0.31962013,0.013854054,0.027441954,0.61027926],"study_design_scores_gemma":[0.00039072137,0.00019928553,0.0025526395,0.000029380592,0.000004491901,0.0000027918265,0.0000035220633,0.54149354,0.44282615,0.012368702,0.00003729758,0.00009151356],"about_ca_topic_score_codex":0.00004240994,"about_ca_topic_score_gemma":7.7234523e-7,"teacher_disagreement_score":0.6101877,"about_ca_system_score_codex":0.00004730587,"about_ca_system_score_gemma":0.00007542061,"threshold_uncertainty_score":0.25586566},"labels":[],"label_agreement":null},{"id":"W112845331","doi":"10.1007/978-3-662-45501-2_19","title":"Impact Analysis via Reachability and Alias Analysis","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Alias; Reachability; Computer science; False positive paradox; Aliasing; Test suite; Static analysis; Pointer analysis; Suite; Pointer (user interface); Set (abstract data type); Program analysis; False positives and false negatives; Path (computing); Continuation; Test case; Theoretical computer science; Data mining; Programming language; Machine learning; Artificial intelligence","score_opus":0.011863693441486176,"score_gpt":0.2617542064627766,"score_spread":0.2498905130212904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W112845331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020337386,0.00030088998,0.9937657,0.0002623277,0.000051380637,0.00016338343,0.0000074957416,0.0020698577,0.0031755765],"genre_scores_gemma":[0.86848307,0.000034048906,0.13051304,0.00049066794,0.00006264578,0.000016964112,0.00024725948,0.000022520759,0.00012978303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978934,0.000035461628,0.00081713527,0.000479058,0.00047584082,0.00029913164],"domain_scores_gemma":[0.9971235,0.00038700533,0.0008348674,0.00085540867,0.00071432686,0.000084918844],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007763976,0.00047515714,0.00086528866,0.0027342734,0.00018429679,0.00069753703,0.00058374193,0.00047643745,0.000021504022],"category_scores_gemma":[0.00086233305,0.00040295854,0.00024858626,0.0028541093,0.000114571616,0.0013036942,0.00024873804,0.00042903668,0.000005889901],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010170029,0.00000999841,0.017807353,0.00033610515,0.0004460405,0.0000024481187,0.0007899763,0.01793501,7.480389e-7,0.00062954304,0.000031544754,0.9620011],"study_design_scores_gemma":[0.00022629378,0.00004278144,0.05336795,0.00033148762,0.0017587313,0.000021676957,5.1291863e-7,0.8177269,0.000018664383,0.12425045,0.0012017849,0.0010527734],"about_ca_topic_score_codex":0.0003443782,"about_ca_topic_score_gemma":0.000099530924,"teacher_disagreement_score":0.9609483,"about_ca_system_score_codex":0.00018882613,"about_ca_system_score_gemma":0.00014685908,"threshold_uncertainty_score":0.9998422},"labels":[],"label_agreement":null},{"id":"W1151207335","doi":"","title":"Transformation by example","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transformation (genetics); Computer science; Set (abstract data type); Context (archaeology); Source code; Function (biology); Process (computing); Algorithm; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.01585661375620726,"score_gpt":0.26565639809918845,"score_spread":0.2497997843429812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1151207335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036295739,0.00010615789,0.86702234,0.00014927611,0.0010031633,0.00022545287,0.000003825082,0.027170116,0.100690074],"genre_scores_gemma":[0.16024286,0.000056236255,0.78487056,0.0008081274,0.00016415169,0.00020394062,0.0024665003,0.00007775292,0.051109884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920475,0.000013277152,0.00017846467,0.0002500452,0.00020636703,0.00014711844],"domain_scores_gemma":[0.9992938,0.00008199013,0.00008152915,0.00042160135,0.00007521659,0.00004587959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015696538,0.0001451611,0.00012573403,0.00009546452,0.00008235473,0.00015645736,0.0006371089,0.00026606992,0.000036193793],"category_scores_gemma":[0.000043240205,0.00013129717,0.000049853643,0.00014508131,0.000006108324,0.0002671304,0.000011953059,0.00030305053,0.000050503066],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033029853,0.000048855276,0.000022064603,0.000083674575,0.000009635477,0.0000015580251,0.0027252387,1.916396e-7,0.0019990485,0.023237936,0.49700063,0.47486788],"study_design_scores_gemma":[0.00056098006,0.000314129,0.0010870678,0.00033358924,0.00004526304,0.000043743872,0.000066298686,0.020150987,0.18723914,0.37209412,0.41564542,0.002419275],"about_ca_topic_score_codex":0.0005590427,"about_ca_topic_score_gemma":0.00011192297,"teacher_disagreement_score":0.4724486,"about_ca_system_score_codex":0.000012199227,"about_ca_system_score_gemma":0.000051996485,"threshold_uncertainty_score":0.53541434},"labels":[],"label_agreement":null},{"id":"W118100860","doi":"","title":"Test Generation Based On Control And Data Dependencies Within Multi-Process SDL Specifications.","year":2000,"lang":"en","type":"article","venue":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Interleaving; Control flow; Process (computing); Data flow diagram; Test data; Data modeling; Data-flow analysis; Distributed computing; Programming language; Database; Operating system","score_opus":0.10154280709632142,"score_gpt":0.30717166234079046,"score_spread":0.20562885524446906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W118100860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030053876,0.002235798,0.9282276,0.015910665,0.0013888055,0.0034983882,0.0009214706,0.014051767,0.00371162],"genre_scores_gemma":[0.8523576,0.0003979091,0.1381787,0.0042932476,0.00076141284,0.0005113014,0.0013371673,0.00022539856,0.0019372279],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9888568,0.0008483037,0.0021859182,0.003979944,0.0022548311,0.0018742174],"domain_scores_gemma":[0.9869155,0.0026792113,0.00086314103,0.007032601,0.0014800404,0.0010294564],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0038950474,0.0015417435,0.0012609548,0.0015800883,0.0019972355,0.0026507801,0.005980574,0.00087450125,0.0006977472],"category_scores_gemma":[0.0035602667,0.001511264,0.00024467587,0.0031023088,0.00059152284,0.0047656405,0.0006572764,0.0017201846,0.0012056226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080805615,0.017048588,0.11795323,0.0015442297,0.0014024668,0.0005668397,0.011614666,0.050968487,0.0070576635,0.027158476,0.47525728,0.28862002],"study_design_scores_gemma":[0.0033726546,0.00047433618,0.01143736,0.00023196271,0.00019067914,0.00013919758,0.00010221396,0.96552634,0.0022785875,0.005093351,0.009085801,0.0020675312],"about_ca_topic_score_codex":0.00032763902,"about_ca_topic_score_gemma":0.00021935125,"teacher_disagreement_score":0.9145578,"about_ca_system_score_codex":0.0003032356,"about_ca_system_score_gemma":0.0009140858,"threshold_uncertainty_score":0.9997331},"labels":[],"label_agreement":null},{"id":"W120366370","doi":"","title":"Towards the Verification and Validation of DEVS Models","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"DEVS; Rotation formalisms in three dimensions; Computer science; Software engineering; Software; Verification and validation of computer simulation models; Context (archaeology); Modeling and simulation; Programming language; Simulation; Mathematics","score_opus":0.0534625555270374,"score_gpt":0.27175700200499026,"score_spread":0.21829444647795285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W120366370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020543408,0.00004084847,0.97406495,0.0013767183,0.000013598999,0.000042819178,1.3366628e-7,0.0012580666,0.002659477],"genre_scores_gemma":[0.6849327,0.0000052199516,0.31493044,0.000092655544,0.000008147051,0.0000030893184,2.4655284e-7,9.956258e-7,0.000026464922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997062,0.000015483429,0.000074482974,0.00008116123,0.000080094804,0.000042550662],"domain_scores_gemma":[0.9996315,0.000056467616,0.000031679043,0.00022624223,0.000043258035,0.000010828293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021371967,0.000028960692,0.00003238902,0.000021602888,0.000033805725,0.000031214637,0.00019183948,0.000014941241,0.0000015188909],"category_scores_gemma":[0.000043042975,0.000018631528,0.000008279912,0.00008602174,0.000018426246,0.00021773239,0.000049314818,0.000021283804,0.0000018131046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014505969,0.000026275391,0.00055754685,0.0000067397323,0.0000038706357,9.593579e-8,0.0014935834,0.00090066117,0.0004624898,0.25772187,0.0061082207,0.73271716],"study_design_scores_gemma":[0.000051598454,0.00002512151,0.0017991454,0.000008577951,0.000002355987,0.0000061789374,0.0000034376744,0.7456711,0.050387,0.20147572,0.0005108785,0.000058901172],"about_ca_topic_score_codex":0.00004247,"about_ca_topic_score_gemma":6.945668e-7,"teacher_disagreement_score":0.7447704,"about_ca_system_score_codex":0.0000060514135,"about_ca_system_score_gemma":0.000014370617,"threshold_uncertainty_score":0.07597717},"labels":[],"label_agreement":null},{"id":"W125925145","doi":"10.1007/978-3-319-04921-2_15","title":"Solving Equations on Words with Morphisms and Antimorphisms","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Solver; Boolean satisfiability problem; Computer science; Range (aeronautics); Morphism; Theoretical computer science; Representation (politics); Graph; System of linear equations; Satisfiability; Boolean data type; Algorithm; Applied mathematics; Discrete mathematics; Mathematics; Programming language","score_opus":0.020719302508557077,"score_gpt":0.24294149421585456,"score_spread":0.22222219170729748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125925145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001070464,0.0001275603,0.99437577,0.0008428544,0.00043768203,0.0002541619,0.0000015707479,0.0023444598,0.0015089181],"genre_scores_gemma":[0.3537478,0.000010866064,0.64435726,0.0014907243,0.00018992626,0.000009398167,0.0000019666672,0.00003245071,0.00015959814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996891,0.00003039172,0.00032871924,0.0013995218,0.0008253901,0.0005249765],"domain_scores_gemma":[0.9965913,0.0014716283,0.00024647886,0.0013614037,0.00016762147,0.00016155008],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008436264,0.00048803914,0.0004431921,0.00085662777,0.00036128794,0.0006140318,0.0017955365,0.0002226239,0.0000054028787],"category_scores_gemma":[0.000276175,0.00039571302,0.00005450317,0.00048447365,0.00072296476,0.00027779586,0.0007580722,0.0006812671,0.000017094786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005121344,0.000018466126,0.00020102046,0.000025674637,0.000008152026,0.00006802678,0.00055792526,0.007990064,0.000026337937,0.053458985,0.00010288324,0.9375373],"study_design_scores_gemma":[0.00021802261,0.0005883812,0.00025572028,0.0012346748,0.000009450947,0.00012793644,2.90283e-8,0.5729464,0.00034886235,0.42314625,0.0003521364,0.00077213784],"about_ca_topic_score_codex":0.00003776545,"about_ca_topic_score_gemma":0.000022227896,"teacher_disagreement_score":0.9367652,"about_ca_system_score_codex":0.00013132366,"about_ca_system_score_gemma":0.00025364186,"threshold_uncertainty_score":0.9998495},"labels":[],"label_agreement":null},{"id":"W127597465","doi":"10.1007/978-3-642-39955-8_7","title":"Automatically Repairing Concurrency Bugs with ARC","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Concurrency; Crossover; Correctness; Java; Synchronization (alternating current); Programming language; Genetic algorithm; Parallel computing; Distributed computing; Artificial intelligence","score_opus":0.01690706949741025,"score_gpt":0.2442023236193368,"score_spread":0.22729525412192655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W127597465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007431678,0.00020822964,0.98382,0.0005412031,0.0006259106,0.00042988485,0.000001380024,0.0076621054,0.0066369437],"genre_scores_gemma":[0.07599147,0.000010173309,0.9224016,0.0009828134,0.00021656354,0.000024803274,0.0000019424897,0.00004283936,0.00032777028],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958289,0.000034209872,0.00055808254,0.0016649734,0.0011364052,0.000777406],"domain_scores_gemma":[0.9960108,0.0010225978,0.0003339275,0.00200396,0.00039215796,0.00023658852],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083473546,0.00061427586,0.0005969872,0.0007116552,0.00025548832,0.00080380077,0.0035707194,0.00028500793,0.00003330498],"category_scores_gemma":[0.00032832738,0.00048604998,0.00010467273,0.0006088689,0.0008653656,0.00064656447,0.0013307672,0.0009212359,0.000110682406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023196808,0.000028564606,0.00029947737,0.00007336926,0.00001252217,0.00014441645,0.0005087227,0.0014448605,0.000018659308,0.022350594,0.00049973704,0.97461677],"study_design_scores_gemma":[0.00016881071,0.00034834567,0.0002514095,0.0014101648,0.0000082964725,0.00026492373,2.1376591e-8,0.4732177,0.00029601256,0.5226706,0.0005459193,0.00081773836],"about_ca_topic_score_codex":0.00004877361,"about_ca_topic_score_gemma":0.000010591622,"teacher_disagreement_score":0.973799,"about_ca_system_score_codex":0.00023743097,"about_ca_system_score_gemma":0.0006759082,"threshold_uncertainty_score":0.99975914},"labels":[],"label_agreement":null},{"id":"W1416149289","doi":"10.1007/978-3-642-29860-8_16","title":"Efficient Techniques for Near-Optimal Instrumentation in Time-Triggered Runtime Verification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Heuristics; Overhead (engineering); Runtime verification; Instrumentation (computer programming); Set (abstract data type); Execution time; State (computer science); Completeness (order theory); Parallel computing; Real-time computing; Distributed computing; Formal verification; Algorithm; Programming language; Operating system","score_opus":0.016948309923076294,"score_gpt":0.26222442469566104,"score_spread":0.24527611477258474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1416149289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00086667115,0.00020996497,0.99451566,0.00022795502,0.00043154802,0.001001131,0.000006107893,0.002476234,0.00026473548],"genre_scores_gemma":[0.13754578,0.0000084782105,0.8617323,0.00033634796,0.00017774683,0.00008277342,0.000016138998,0.000035186073,0.00006524518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684584,0.000037772086,0.0005830578,0.0011577982,0.0007368852,0.00063866837],"domain_scores_gemma":[0.9976326,0.0006233955,0.00035075482,0.0010600417,0.00021955543,0.00011360919],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016498271,0.00043819452,0.00044253445,0.00088113244,0.00023306943,0.00054676016,0.0021623767,0.00034929797,0.000007982338],"category_scores_gemma":[0.00021424484,0.0004351472,0.00010765844,0.00064708287,0.00039873275,0.00033472673,0.0006114168,0.00046040726,0.000031543277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013021984,0.000072667164,0.0002456886,0.00003965424,0.000004368068,0.0000051398024,0.000639425,0.0073614414,0.00030440453,0.0017886208,0.00007812593,0.9894474],"study_design_scores_gemma":[0.00027478015,0.0002327618,0.00049646694,0.0005323841,0.000008797121,0.000033018077,4.05893e-8,0.9249299,0.006398867,0.06561404,0.00078892766,0.00068998383],"about_ca_topic_score_codex":0.000034240453,"about_ca_topic_score_gemma":0.0000036032363,"teacher_disagreement_score":0.98875743,"about_ca_system_score_codex":0.00048914616,"about_ca_system_score_gemma":0.00037089663,"threshold_uncertainty_score":0.99981004},"labels":[],"label_agreement":null},{"id":"W1471943874","doi":"10.1007/978-3-642-38230-7_7","title":"SiteHopper: Abstracting Navigation State Machines for the Efficient Verification of Web Applications","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Web crawler; Abstraction; State (computer science); Model checking; Finite-state machine; On the fly; Data mining; Programming language; Information retrieval; World Wide Web; Operating system","score_opus":0.01938348445182148,"score_gpt":0.2701109497937844,"score_spread":0.25072746534196294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1471943874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001642443,0.00026701202,0.99637353,0.00054814946,0.00036525173,0.0010353143,0.000010983232,0.0009066128,0.00032890655],"genre_scores_gemma":[0.44114286,0.000010916349,0.5583045,0.00016260734,0.00014467227,0.00014235482,0.000009471445,0.00002087259,0.000061780156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979661,0.000016912005,0.00047204128,0.00074716395,0.00050190574,0.0002958666],"domain_scores_gemma":[0.99577343,0.0020545803,0.000512463,0.0011589812,0.00044643052,0.000054123164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009774624,0.0002657444,0.0002504886,0.00029975816,0.0003317064,0.00028438418,0.0019409755,0.00012465823,0.000002935704],"category_scores_gemma":[0.00016361021,0.00019935032,0.00009398202,0.00031265966,0.00036365868,0.00019472695,0.0003475877,0.0003412816,0.000010698494],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001921226,0.0000204916,0.0000426501,0.000058415888,0.0000059511713,5.4528385e-7,0.0003212452,0.05333833,0.00071443006,0.008193643,0.000050340168,0.93725204],"study_design_scores_gemma":[0.00007271642,0.00004674539,0.0001404906,0.0002005571,0.00000695547,0.000012569314,5.7520182e-8,0.8320396,0.0021454652,0.16453734,0.00058864127,0.00020884548],"about_ca_topic_score_codex":0.000046100555,"about_ca_topic_score_gemma":0.000004261627,"teacher_disagreement_score":0.9370432,"about_ca_system_score_codex":0.0001123934,"about_ca_system_score_gemma":0.00024504145,"threshold_uncertainty_score":0.812927},"labels":[],"label_agreement":null},{"id":"W1479736339","doi":"10.1007/11813040_27","title":"Towards Automatic Exception Safety Verification","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Programming language; Exception handling; Java; Static analysis; Raising (metalworking); Software engineering; Software","score_opus":0.018498283578180015,"score_gpt":0.2547942841712107,"score_spread":0.2362960005930307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1479736339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003361073,0.0001663107,0.98703843,0.00051974086,0.0009919694,0.00032369257,0.0000033164004,0.0055867783,0.005336144],"genre_scores_gemma":[0.16840015,0.000018420233,0.83027583,0.00060295797,0.0003692765,0.0000149300695,0.000016376382,0.000035305442,0.00026674665],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664986,0.000039363975,0.0005750665,0.0012912238,0.00094274303,0.0005017548],"domain_scores_gemma":[0.9973152,0.00037269667,0.0003396864,0.0016308716,0.00023756435,0.000103968225],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010722703,0.00045220222,0.00042085373,0.00076990423,0.00027055875,0.00049847306,0.002581795,0.0003310961,0.000015357287],"category_scores_gemma":[0.00019897726,0.0004300604,0.00011447781,0.0006226987,0.00042320433,0.00051036547,0.00070077693,0.0005601384,0.000057519635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014781516,0.000017204802,0.000045739165,0.000029685949,0.0000026187681,0.000016306261,0.0001588613,0.003787794,0.000021866455,0.004961849,0.00039598605,0.9905606],"study_design_scores_gemma":[0.00009934671,0.00008818233,0.0011736117,0.0003814511,0.000005251238,0.000053632004,6.4651253e-9,0.48420325,0.00039428877,0.5121938,0.00093364774,0.00047355445],"about_ca_topic_score_codex":0.00009000627,"about_ca_topic_score_gemma":0.000012741049,"teacher_disagreement_score":0.99008703,"about_ca_system_score_codex":0.0005134656,"about_ca_system_score_gemma":0.0004863425,"threshold_uncertainty_score":0.9998151},"labels":[],"label_agreement":null},{"id":"W1481028594","doi":"10.1007/3-540-44585-4_1","title":"Software Documentation and the Verification Process","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Documentation; Computer science; Software engineering; Notation; Software documentation; Programming language; Software verification; Software; Process (computing); Verification and validation; Formal specification; Software development process; Software development; Software construction; Engineering","score_opus":0.015785737219104094,"score_gpt":0.269389319836322,"score_spread":0.25360358261721794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1481028594","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046489044,0.0004597958,0.9947029,0.001050447,0.00039370867,0.0003834779,8.436328e-7,0.0017898583,0.0011725023],"genre_scores_gemma":[0.23735473,0.00016971615,0.7595558,0.002266287,0.00031438394,0.00005442111,0.0000065648633,0.00003577467,0.00024234528],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99782044,0.000035798508,0.00031083348,0.0009179911,0.0006119358,0.00030299957],"domain_scores_gemma":[0.99770314,0.0008584008,0.00024412604,0.0009193732,0.00020805934,0.00006690724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010315673,0.00029260814,0.00027315307,0.00033120037,0.00031802157,0.0007019701,0.0017504914,0.00015758046,0.000005149062],"category_scores_gemma":[0.00035622614,0.00020947968,0.000047929338,0.0004433659,0.00086890446,0.0005562834,0.0004573178,0.00042633776,0.000009191413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007730972,0.000007741412,0.00022966364,0.000027871072,0.0000039861193,0.000010966286,0.0010497484,0.0013074138,0.000002613082,0.016215118,0.00005562256,0.98108155],"study_design_scores_gemma":[0.00027590105,0.000049166007,0.0001897469,0.00022501206,0.000006234484,0.00009532448,5.365757e-8,0.113221146,0.00014378717,0.88525337,0.00026141314,0.00027883484],"about_ca_topic_score_codex":0.000035732617,"about_ca_topic_score_gemma":0.000008349959,"teacher_disagreement_score":0.9808027,"about_ca_system_score_codex":0.000107596425,"about_ca_system_score_gemma":0.0002061256,"threshold_uncertainty_score":0.8542334},"labels":[],"label_agreement":null},{"id":"W1483143768","doi":"10.1007/3-540-45441-1_15","title":"A UML-Based Approach to System Testing","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Testability; Unified Modeling Language; Sequence diagram; Software engineering; Class diagram; Test case; Model-based testing; Programming language; Reliability engineering; Software; Engineering","score_opus":0.039470597645967595,"score_gpt":0.25275002028524485,"score_spread":0.21327942263927724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1483143768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010682663,0.000115484945,0.96219677,0.00021341554,0.0007661197,0.000554162,0.0000026153766,0.008670566,0.027470177],"genre_scores_gemma":[0.13642325,6.379529e-7,0.8615652,0.0014821361,0.00034203785,0.000033387427,0.000002374253,0.00004727607,0.000103710256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951694,0.00004645368,0.00058863603,0.0021081283,0.0011884295,0.0008989609],"domain_scores_gemma":[0.9956309,0.0011514646,0.00029250793,0.0021746394,0.00043091,0.0003195431],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001443631,0.0006620615,0.0006460708,0.0013735265,0.0003553962,0.00079882616,0.0046271486,0.00033788726,0.0000015921746],"category_scores_gemma":[0.0006367979,0.00061459787,0.00012379167,0.001790195,0.00031998364,0.00028494172,0.0013331614,0.00078673323,0.000049216924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003848422,0.00004988409,0.00030904447,0.0001552794,0.0000060848492,0.00015194537,0.0002983454,0.088567875,0.00002392487,0.011330688,0.00024572047,0.89885736],"study_design_scores_gemma":[0.0001376434,0.00019826401,0.00006119987,0.0014397716,0.000006545478,0.0002639338,3.8056143e-8,0.942509,0.00020195713,0.0538101,0.0005683819,0.0008031727],"about_ca_topic_score_codex":0.00008936403,"about_ca_topic_score_gemma":0.000004844915,"teacher_disagreement_score":0.8980542,"about_ca_system_score_codex":0.0006179955,"about_ca_system_score_gemma":0.00073160365,"threshold_uncertainty_score":0.9996305},"labels":[],"label_agreement":null},{"id":"W1484390872","doi":"10.1007/978-3-642-15585-7_12","title":"TeCReVis: A Tool for Test Coverage and Test Redundancy Visualization","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Redundancy (engineering); Computer science; Visualization; Eclipse; Code coverage; Graphical user interface testing; Graphical user interface; Set (abstract data type); Test (biology); Plug-in; Programming language; Software engineering; Data mining; Software; User interface; Operating system; User interface design","score_opus":0.015134570891314921,"score_gpt":0.2711252888983332,"score_spread":0.2559907180070183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484390872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006063149,0.0003180069,0.99504906,0.00035956755,0.00058375264,0.0007120251,0.000016155813,0.0025237799,0.00037702173],"genre_scores_gemma":[0.083291724,0.00007084852,0.91437215,0.00137917,0.00047722395,0.000051373372,0.000011146738,0.000057479723,0.00028891422],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99694365,0.000014190615,0.00048162744,0.0014357386,0.0005477852,0.00057698536],"domain_scores_gemma":[0.9936702,0.0043618535,0.00031778755,0.0011703358,0.0003514621,0.00012831006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010713049,0.00048920274,0.00046774014,0.00059582945,0.00043608464,0.00091334083,0.0017777687,0.0004074633,0.0000044168264],"category_scores_gemma":[0.0035655978,0.00045712516,0.000088531706,0.00045331178,0.00054718327,0.0005112156,0.0009659305,0.000600579,0.0000060743],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033567178,0.0000619325,0.0019553395,0.0001479502,0.0000049427654,0.000025325195,0.0004110049,0.00009793723,0.0006693531,0.013599058,0.00020624747,0.98281753],"study_design_scores_gemma":[0.00035143644,0.00062942004,0.0005404177,0.0010719845,0.000014696152,0.0001991978,1.8099465e-8,0.22795404,0.0027237239,0.75901085,0.006482665,0.001021539],"about_ca_topic_score_codex":0.000012397338,"about_ca_topic_score_gemma":0.000013391089,"teacher_disagreement_score":0.981796,"about_ca_system_score_codex":0.00011638217,"about_ca_system_score_gemma":0.00039505027,"threshold_uncertainty_score":0.99978805},"labels":[],"label_agreement":null},{"id":"W1485665058","doi":"10.1007/978-3-540-71289-3_22","title":"A Prioritization Approach for Software Test Cases Based on Bayesian Networks","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regression testing; Bayesian network; Computer science; Data mining; Software; Bayesian probability; Reliability engineering; Fault (geology); Fault detection and isolation; Test case; Code coverage; Machine learning; Regression analysis; Artificial intelligence; Software system; Software construction; Engineering; Programming language","score_opus":0.029998499637316784,"score_gpt":0.27108712254050804,"score_spread":0.24108862290319125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485665058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.929795e-7,0.00015591267,0.99340177,0.00012870494,0.0006400722,0.00085638394,0.000010349197,0.0041276193,0.000678512],"genre_scores_gemma":[0.04642642,0.000004884729,0.95031446,0.0025142843,0.00054504833,0.000041763346,0.00003337224,0.000059404356,0.00006037663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996094,0.000025925525,0.0005130261,0.0017316901,0.00084706716,0.000788328],"domain_scores_gemma":[0.99233407,0.0052652936,0.0003160311,0.0015035771,0.00039177184,0.00018925656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013692118,0.00060592993,0.00050631206,0.0010734359,0.00041090397,0.00057713455,0.002394394,0.00049416284,0.0000026690122],"category_scores_gemma":[0.001675657,0.0005724541,0.00016395439,0.0008112366,0.0004063555,0.0002784038,0.00042124704,0.00068927027,0.0000022985769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001131629,0.00008563103,0.0004985673,0.00007714674,0.0000036975225,0.00006928019,0.000073947514,0.21145083,0.0000012996275,0.0018394456,0.00028275754,0.7856061],"study_design_scores_gemma":[0.00021215594,0.00051425357,0.00007015211,0.00051684206,0.0000076013343,0.00007129617,1.4323551e-8,0.9248163,0.00007931064,0.072877735,0.00022294353,0.0006113723],"about_ca_topic_score_codex":0.000016828719,"about_ca_topic_score_gemma":0.000010236978,"teacher_disagreement_score":0.7849947,"about_ca_system_score_codex":0.00033939618,"about_ca_system_score_gemma":0.000487035,"threshold_uncertainty_score":0.9996727},"labels":[],"label_agreement":null},{"id":"W1496915765","doi":"10.1007/11759744_9","title":"Conformance Tests as Checking Experiments for Partial Nondeterministic FSM","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Nondeterministic algorithm; Computer science; Conformance testing; Equivalence (formal languages); Sequence (biology); Automaton; Algorithm; Programming language; Finite-state machine; Model checking; Theoretical computer science; Discrete mathematics; Mathematics; Operating system","score_opus":0.032897483581329594,"score_gpt":0.30610764226534015,"score_spread":0.27321015868401055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496915765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010799352,0.00021501354,0.9916809,0.00014062073,0.0015168603,0.00060314883,0.0000059654844,0.00258586,0.003143588],"genre_scores_gemma":[0.33109772,0.000005422217,0.6664483,0.0012683955,0.00059349404,0.00007441271,0.000009749469,0.000050678595,0.0004518438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628526,0.000015971915,0.00061239314,0.0014583594,0.0008027533,0.0008252882],"domain_scores_gemma":[0.9968824,0.00093609083,0.0003986817,0.0013610783,0.00026885784,0.0001529004],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006959859,0.0005841251,0.00054499897,0.00057858875,0.0003669008,0.00068150955,0.0029538104,0.0003207424,0.000005257337],"category_scores_gemma":[0.00034947635,0.0005632904,0.00015022473,0.00034431994,0.000539998,0.00048090657,0.0009486865,0.00046472315,0.000028643937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001815967,0.00008363936,0.0003552818,0.00013759547,0.000016273525,0.00016352395,0.0008515357,0.0054083723,0.0002923557,0.01326277,0.0012785189,0.97813195],"study_design_scores_gemma":[0.00043845247,0.0005281597,0.0001246238,0.0009149047,0.000011576181,0.00016046893,3.296451e-8,0.5644479,0.00941971,0.4188872,0.003930136,0.0011368347],"about_ca_topic_score_codex":0.00004731013,"about_ca_topic_score_gemma":0.000006537755,"teacher_disagreement_score":0.9769951,"about_ca_system_score_codex":0.00025443558,"about_ca_system_score_gemma":0.00058127125,"threshold_uncertainty_score":0.99968183},"labels":[],"label_agreement":null},{"id":"W1498052443","doi":"10.1109/iwsoc.2004.71","title":"Verification strategy determination using dependence analysis of transaction-level models","year":2004,"lang":"en","type":"article","venue":"IEEE International Workshop on System-on-Chip for Real-Time Applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Bottleneck; Modular design; Transaction-level modeling; Metric (unit); Functional verification; Database transaction; Formal verification; Embedded system; Programming language; Engineering","score_opus":0.09199069560637717,"score_gpt":0.3467204496117136,"score_spread":0.25472975400533643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498052443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098406905,0.0000061446563,0.9853975,0.00020927962,0.00017529273,0.0008537535,0.00016355191,0.0013472943,0.0020064618],"genre_scores_gemma":[0.90460545,0.000010303943,0.09427469,0.00004643115,0.00008439516,0.00076289655,0.000088705354,0.000025503736,0.000101646714],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977058,0.000054517946,0.00066417985,0.00069529575,0.00065371185,0.00022650257],"domain_scores_gemma":[0.99713624,0.00083273,0.00051711506,0.0009015288,0.0005213192,0.000091064656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045816952,0.000250325,0.00033387967,0.0009237657,0.00024339158,0.000141811,0.001022393,0.0001501883,0.0000047372355],"category_scores_gemma":[0.000052333242,0.00025706948,0.00026549134,0.0011701707,0.000049992515,0.0003809087,0.000019550958,0.00014400698,0.000028261647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061140294,0.00043009204,0.000040763112,0.000038713246,0.00030233717,0.0000015200451,0.00019595504,0.81047064,0.0037848924,0.16497567,0.000120508244,0.019577792],"study_design_scores_gemma":[0.00048586424,0.00013643537,0.00056018453,0.00040742272,0.00018216317,0.000015222913,0.00003745481,0.97118133,0.007922443,0.018703181,0.000031381573,0.00033692425],"about_ca_topic_score_codex":0.00014820314,"about_ca_topic_score_gemma":0.000011664367,"teacher_disagreement_score":0.8947647,"about_ca_system_score_codex":0.0004931832,"about_ca_system_score_gemma":0.00012421905,"threshold_uncertainty_score":0.99998814},"labels":[],"label_agreement":null},{"id":"W1498361645","doi":"10.1007/11754008_18","title":"Reducing the Lengths of Checking Sequences by Overlapping","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; A priori and a posteriori; Model checking; Set (abstract data type); Selection (genetic algorithm); State (computer science); Algorithm; Reduction (mathematics); Sequence (biology); Theoretical computer science; Artificial intelligence; Mathematics; Programming language","score_opus":0.01894883717841254,"score_gpt":0.25226917097699325,"score_spread":0.23332033379858072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498361645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013983644,0.0011952294,0.99240667,0.00055353076,0.00071693637,0.00023923715,0.00000383621,0.0013937465,0.0033509962],"genre_scores_gemma":[0.54762524,0.000035985882,0.45112482,0.0006478385,0.00030311994,0.000008896505,0.0000034793964,0.00003318119,0.0002174443],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670106,0.000044118246,0.0006018167,0.0011278922,0.00097729,0.00054783537],"domain_scores_gemma":[0.9964486,0.0013699929,0.0005340126,0.0013657097,0.0002164769,0.00006523049],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015049962,0.00042780416,0.00047666198,0.00044518206,0.00033546498,0.00040197922,0.003954565,0.00023614398,0.0000036315018],"category_scores_gemma":[0.0003090819,0.0003214318,0.00012932104,0.0006782037,0.0009676286,0.00040609261,0.0010965379,0.0007473652,0.0000033880315],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022480344,0.00002853512,0.00029226494,0.00008425071,0.000014649935,0.000032676006,0.0011247777,0.02184346,0.0012234281,0.010227751,0.0023126267,0.9628133],"study_design_scores_gemma":[0.00014157305,0.00016924861,0.00014766154,0.0021134496,0.000013292513,0.00012407315,1.4654931e-7,0.4550385,0.010322001,0.5294409,0.0015923217,0.0008968396],"about_ca_topic_score_codex":0.00037932655,"about_ca_topic_score_gemma":0.000011029348,"teacher_disagreement_score":0.9619165,"about_ca_system_score_codex":0.00019884002,"about_ca_system_score_gemma":0.00041148093,"threshold_uncertainty_score":0.99992377},"labels":[],"label_agreement":null},{"id":"W1499663647","doi":"10.11606/t.55.2011.tde-17082011-153853","title":"Contribuições para o Teste de Software","year":2011,"lang":"pt","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Software testing; Computer science; Software; Software engineering; Programming language","score_opus":0.046296639843976174,"score_gpt":0.30213648122741865,"score_spread":0.25583984138344246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499663647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031193022,0.0013868873,0.9564257,0.00008965159,0.0011069918,0.00056139415,0.000021379667,0.03304705,0.004241627],"genre_scores_gemma":[0.14147556,0.0001989277,0.8106901,0.0013919938,0.00025201007,0.00025873166,0.0002883202,0.00016397456,0.045280363],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996349,0.00020267774,0.00072930683,0.0011514822,0.00052764727,0.0010399378],"domain_scores_gemma":[0.99564385,0.0013006848,0.0005705132,0.0014589633,0.00066635164,0.00035965443],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083509996,0.00075233827,0.00074890815,0.00036874457,0.00042098656,0.0004779869,0.002162996,0.00079090765,0.00021749742],"category_scores_gemma":[0.0026425915,0.000719754,0.00031422288,0.0006084618,0.00009268432,0.00038031937,0.00026606576,0.0007238932,0.00048848725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016886773,0.0010082102,0.1151713,0.0012632632,0.0004122272,0.00059713714,0.016596857,0.000015696653,0.0002311097,0.014896205,0.17288242,0.6767567],"study_design_scores_gemma":[0.0034980236,0.003984965,0.14799035,0.011364089,0.0011903462,0.001209221,0.00045120972,0.08379472,0.04119954,0.6787643,0.014099706,0.012453559],"about_ca_topic_score_codex":0.0020486694,"about_ca_topic_score_gemma":0.00008034465,"teacher_disagreement_score":0.6643031,"about_ca_system_score_codex":0.0001249422,"about_ca_system_score_gemma":0.0007988979,"threshold_uncertainty_score":0.99952537},"labels":[],"label_agreement":null},{"id":"W1501211454","doi":"10.1007/978-90-481-3658-2_79","title":"Testing Grammars For Top-Down Parsers","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Programming language; Compiler; Parsing; Rule-based machine translation; Compiler construction; Grammar; Implementation; Natural language processing; Linguistics","score_opus":0.053056053212618005,"score_gpt":0.2653031525672882,"score_spread":0.2122470993546702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501211454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.74108e-7,0.00011920628,0.5223918,0.00033479306,0.00021339064,0.00034781263,0.0000039620277,0.018919658,0.4576687],"genre_scores_gemma":[0.00015635941,0.0000061781566,0.7804074,0.001044128,0.00015963223,0.000023482213,0.000008898347,0.000035649366,0.21815826],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99832636,0.0000073720303,0.00034266457,0.0006797619,0.00026583488,0.0003780307],"domain_scores_gemma":[0.99764425,0.00088961335,0.00021087256,0.0009142902,0.00022420802,0.000116766714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033611018,0.0003675407,0.00035634238,0.00019241608,0.00015199078,0.0002123487,0.001099028,0.00028247177,0.0000137838815],"category_scores_gemma":[0.00047773545,0.00033943125,0.00017876741,0.0000695101,0.0000453255,0.00013970053,0.00019438974,0.00024892882,0.000038380687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014994633,0.000006944859,0.000023885761,0.000021242298,0.000010975318,0.0000144540945,0.000017481641,0.0000028232298,0.000003508129,0.29841688,0.09526873,0.6062116],"study_design_scores_gemma":[0.00009582789,0.00022728149,0.000017208868,0.0002362402,0.000015874271,0.00003924606,1.9240528e-7,0.0038986956,0.00003839777,0.84396905,0.1509891,0.00047288227],"about_ca_topic_score_codex":0.00003677757,"about_ca_topic_score_gemma":0.000003147823,"teacher_disagreement_score":0.6057387,"about_ca_system_score_codex":0.000063540676,"about_ca_system_score_gemma":0.00012158775,"threshold_uncertainty_score":0.99990577},"labels":[],"label_agreement":null},{"id":"W1503243085","doi":"","title":"SCL: a language for security testing of network applications","year":2005,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Royal Military College of Canada","funders":"","keywords":"Computer science; Syntax; Programming language; Abstract syntax tree; Abstract syntax; Protocol (science); Artificial intelligence","score_opus":0.1341926941477668,"score_gpt":0.4334524182713786,"score_spread":0.2992597241236118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503243085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043080933,0.0112869,0.8900956,0.024860017,0.0007377557,0.021104086,0.0008822029,0.0031554005,0.004797104],"genre_scores_gemma":[0.69426125,0.00004779113,0.30469275,0.000032209256,0.000082810904,0.000664665,0.0000017094594,0.000009735431,0.00020710206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985318,0.00015278414,0.00028821774,0.00032683372,0.0003328213,0.0003675504],"domain_scores_gemma":[0.98946047,0.004986278,0.00024534308,0.0005904566,0.004673341,0.000044095665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011123543,0.00012292678,0.0002824285,0.00007500775,0.0004292563,0.000031959837,0.0009123078,0.000037748014,6.2386624e-7],"category_scores_gemma":[0.0066939183,0.00008901173,0.00006107924,0.0013765985,0.00032130105,0.00011555277,0.00037634198,0.00014634177,7.741942e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037954244,0.00069627265,0.0019612582,0.0010749397,0.00030703866,8.0304585e-7,0.0252772,0.0076447465,0.006090444,0.5021696,0.061629165,0.39276898],"study_design_scores_gemma":[0.0023461115,0.0017817022,0.0002552118,0.0025086035,0.000037738377,0.0000014580211,0.0065549207,0.08015892,0.24089853,0.6253981,0.03942234,0.0006363839],"about_ca_topic_score_codex":0.0000036637769,"about_ca_topic_score_gemma":0.000053821575,"teacher_disagreement_score":0.6511803,"about_ca_system_score_codex":0.000093209135,"about_ca_system_score_gemma":0.0002899272,"threshold_uncertainty_score":0.8013729},"labels":[],"label_agreement":null},{"id":"W1504886604","doi":"10.1007/0-306-47003-9_6","title":"Diagnosing Multiple Faults in Communicating Finite State Machines","year":2006,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Finite-state machine; Computer science; Component (thermodynamics); State (computer science); Abstract state machines; Extended finite-state machine; Fault (geology); Distributed computing; Algorithm","score_opus":0.029973827013449045,"score_gpt":0.26035638916998355,"score_spread":0.2303825621565345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504886604","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041428072,0.0019954252,0.049404778,0.00086278614,0.00090714503,0.0010536193,0.00005332589,0.017258363,0.9280503],"genre_scores_gemma":[0.164482,0.00014454266,0.23163134,0.005758362,0.00088467955,0.000464609,0.0003602427,0.0007287205,0.59554553],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960193,0.00013312584,0.0012213931,0.0011060229,0.0006888475,0.00083130033],"domain_scores_gemma":[0.9938974,0.0030373326,0.0008039797,0.0018896123,0.00017655961,0.00019516455],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013937054,0.00075925805,0.00078846695,0.00090508553,0.00024410768,0.000675029,0.0042444584,0.0009846156,0.0000076277256],"category_scores_gemma":[0.001273067,0.00078814034,0.00021390655,0.00012850855,0.00024654565,0.0011553641,0.0018732899,0.003924589,0.00002588781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022931708,0.000051890172,0.013524125,0.00019820771,0.000090904716,0.000399379,0.0028877985,0.00049454294,0.000026349424,0.009444671,0.49387378,0.4789854],"study_design_scores_gemma":[0.001288361,0.00010115191,0.00075060764,0.0036661564,0.000039748204,0.00012439373,0.000005339817,0.07716857,0.00009081779,0.5772998,0.33682525,0.0026398436],"about_ca_topic_score_codex":0.0011039638,"about_ca_topic_score_gemma":0.0001166951,"teacher_disagreement_score":0.56785506,"about_ca_system_score_codex":0.00031043382,"about_ca_system_score_gemma":0.00022188507,"threshold_uncertainty_score":0.99945694},"labels":[],"label_agreement":null},{"id":"W1505714538","doi":"10.1007/978-3-540-31810-1_10","title":"Applying Reduction Techniques to Software Functional Requirement Specifications","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Program slicing; Computer science; Slicing; Reuse; Functional requirement; Programming language; Non-functional requirement; Software requirements specification; Software engineering; Program comprehension; Software maintenance; Notation; Functional specification; Formal specification; Software development; Reliability engineering; Software; Software system; Software construction","score_opus":0.060229339611306124,"score_gpt":0.2776802005003229,"score_spread":0.21745086088901677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505714538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004334067,0.0001359517,0.98750687,0.0016202624,0.0011360098,0.00097498356,0.0000038470007,0.0069062603,0.0017115081],"genre_scores_gemma":[0.008719376,0.000022105722,0.9877673,0.0014407854,0.0012266419,0.00024159045,0.000009561729,0.00004172216,0.0005309373],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959794,0.000026092759,0.0005885568,0.0017026124,0.0011230981,0.00058021845],"domain_scores_gemma":[0.9970426,0.00032195193,0.00026945537,0.0017350477,0.00042255386,0.00020840776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010002883,0.0004948754,0.0003842698,0.0013515716,0.00044937048,0.00053284795,0.0023072038,0.00027758974,0.000033107102],"category_scores_gemma":[0.00026374465,0.00049973733,0.000118339376,0.0008834894,0.0003168478,0.0005847148,0.001105548,0.0006639016,0.00007965891],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027871479,0.000025585032,0.00002523654,0.00001210677,0.0000044491326,0.00000775603,0.00017021666,0.0031118793,0.00019169158,0.0059259892,0.0014621418,0.98906016],"study_design_scores_gemma":[0.0001835792,0.00042536206,0.0003022381,0.0015505372,0.000019204253,0.00043545023,1.7348523e-7,0.035399016,0.01630607,0.87699664,0.06636123,0.0020204906],"about_ca_topic_score_codex":0.000019230853,"about_ca_topic_score_gemma":0.000008772701,"teacher_disagreement_score":0.9870397,"about_ca_system_score_codex":0.00081574067,"about_ca_system_score_gemma":0.0004563295,"threshold_uncertainty_score":0.9997454},"labels":[],"label_agreement":null},{"id":"W1514771780","doi":"10.1007/978-3-642-20398-5_38","title":"A Tabular Expression Toolbox for Matlab/Simulink","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Toolbox; Computer science; MATLAB; Solver; Programming language; Interface (matter); Expression (computer science); Code (set theory); Completeness (order theory); Software engineering; Embedded system; Operating system","score_opus":0.03202961409431724,"score_gpt":0.2631017049716519,"score_spread":0.23107209087733468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514771780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015095787,0.00042919078,0.9920435,0.00025301095,0.0013236183,0.0006257635,0.0000062211934,0.0038690353,0.0014345981],"genre_scores_gemma":[0.032712996,0.000016810403,0.9651265,0.0012600641,0.00042382575,0.000046720616,0.0000057834905,0.00005373035,0.00035352592],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99631286,0.000025823798,0.00052489765,0.0016982983,0.00070136786,0.00073677534],"domain_scores_gemma":[0.99616534,0.0010332556,0.00033233923,0.0019359462,0.0003487346,0.00018439785],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010206586,0.0005763952,0.0005589116,0.00072476285,0.00031453298,0.0004720266,0.004057873,0.00044399875,0.000013318927],"category_scores_gemma":[0.0004091849,0.0005073948,0.00018163263,0.0003838467,0.00042919817,0.0005155275,0.0011651311,0.0006122916,0.000027953025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012837471,0.00004374572,0.00007188852,0.00009337509,0.000008163684,0.000062604675,0.00077202043,0.0013795799,0.0002217682,0.014771811,0.0011419707,0.9814202],"study_design_scores_gemma":[0.0002179802,0.00027020037,0.000022142178,0.0008616108,0.000007605082,0.000041006686,1.7123522e-8,0.14196663,0.006610407,0.84428877,0.004972643,0.0007409828],"about_ca_topic_score_codex":0.000022941502,"about_ca_topic_score_gemma":0.0000061858573,"teacher_disagreement_score":0.9806793,"about_ca_system_score_codex":0.00017315289,"about_ca_system_score_gemma":0.0004261639,"threshold_uncertainty_score":0.99973774},"labels":[],"label_agreement":null},{"id":"W1520324981","doi":"10.1007/11430230_8","title":"Multiplexing of Partially Ordered Events","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Multiplexer; Merge (version control); Computer science; Multiplexing; TRACE (psycholinguistics); Distributed computing; Code (set theory); Algorithm; Theoretical computer science; Parallel computing; Programming language; Telecommunications","score_opus":0.02697436365411322,"score_gpt":0.2704738527400422,"score_spread":0.243499489085929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520324981","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006005658,0.00027956397,0.99537295,0.00032308447,0.00069345685,0.00025932092,0.0000036264978,0.0019405658,0.0010673582],"genre_scores_gemma":[0.26204646,0.000017086912,0.73712486,0.0004345821,0.00022842179,0.0000056514054,0.0000021883561,0.000025241001,0.00011552492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967358,0.00003202818,0.00062251627,0.0011433747,0.0009177837,0.00054850173],"domain_scores_gemma":[0.9969822,0.0007216079,0.00041952284,0.0014568435,0.00029242062,0.00012738195],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009134579,0.0004291924,0.00053403556,0.00071347,0.0001453604,0.00013961115,0.0032830695,0.0002737321,0.000012002556],"category_scores_gemma":[0.0003968615,0.00040519758,0.0001343459,0.0005178434,0.00040617326,0.000384959,0.0012959449,0.00054192333,0.000016075051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000396855,0.00003649992,0.00057111564,0.00003536764,0.000008648972,0.000025031755,0.00043104542,0.019739904,0.00008725816,0.004014863,0.000058631318,0.9749877],"study_design_scores_gemma":[0.00025866544,0.0001817795,0.0004265613,0.0009595285,0.000006439352,0.00005690614,1.5861504e-8,0.5273583,0.0027373857,0.46648738,0.0008675175,0.0006595244],"about_ca_topic_score_codex":0.000043825312,"about_ca_topic_score_gemma":0.00004106996,"teacher_disagreement_score":0.97432816,"about_ca_system_score_codex":0.0001670744,"about_ca_system_score_gemma":0.00049102877,"threshold_uncertainty_score":0.99983996},"labels":[],"label_agreement":null},{"id":"W1520613697","doi":"10.1007/11754008_14","title":"Detecting Observability Problems in Distributed Testing","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observability; Controllability; Sequence (biology); Computer science; Construct (python library); State (computer science); Extension (predicate logic); Sequence diagram; Finite-state machine; Theoretical computer science; Algorithm; Test (biology); Distributed computing; Unified Modeling Language; Programming language; Mathematics; Software","score_opus":0.04026543076394748,"score_gpt":0.2534101892339219,"score_spread":0.2131447584699744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520613697","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000646158,0.00021468417,0.99272645,0.00018529996,0.0005604085,0.00049748167,0.0000065175036,0.004264896,0.00089808286],"genre_scores_gemma":[0.39452922,0.0000015710938,0.60502255,0.00020985381,0.00015691566,0.000019229972,0.0000063276857,0.00003020161,0.000024137898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99529207,0.00007194253,0.00086092844,0.0019621225,0.0008687918,0.00094417227],"domain_scores_gemma":[0.9947601,0.002683399,0.0004186906,0.0016627271,0.00034513444,0.00012996858],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024080793,0.0006114773,0.00063330086,0.00079177914,0.00027063,0.0005988322,0.0032512734,0.00039034232,0.0000021302953],"category_scores_gemma":[0.0020339065,0.000595326,0.00010533691,0.0017568544,0.00050774607,0.0005405069,0.0016571538,0.0012940409,0.000007998749],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018992403,0.00006266527,0.026931027,0.0001248854,0.0000035840792,0.000115608935,0.00028329412,0.12744078,0.00009280704,0.00054913544,0.000060357434,0.84433395],"study_design_scores_gemma":[0.00013845795,0.00010875706,0.0053444584,0.000983365,0.0000028119932,0.00006202351,1.6903645e-8,0.5436146,0.00029041758,0.44875747,0.000089413676,0.0006082005],"about_ca_topic_score_codex":0.0005943726,"about_ca_topic_score_gemma":0.00024400634,"teacher_disagreement_score":0.84372574,"about_ca_system_score_codex":0.0006981522,"about_ca_system_score_gemma":0.00053541653,"threshold_uncertainty_score":0.9996498},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08433280682020698,"score_gpt":0.31182946332980477,"score_spread":0.22749665650959777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522741019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7037818,0.000020362579,0.28737822,0.00009623001,0.00019354532,0.0007524516,0.000006784828,0.007744317,0.000026282263],"genre_scores_gemma":[0.87458813,4.5006996e-7,0.12517887,0.000050924118,0.00008381901,0.00006288978,0.000009478461,0.000016568996,0.000008839556],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776596,0.00047230677,0.00043641796,0.00082336547,0.00030869368,0.00019328434],"domain_scores_gemma":[0.99650633,0.0014762147,0.00027058314,0.000704745,0.00076851295,0.0002736364],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015285356,0.00023509393,0.00022375357,0.00015430523,0.00061562215,0.00031899294,0.00016125344,0.00016969464,4.8967865e-7],"category_scores_gemma":[0.011790175,0.00020701981,0.000018318608,0.00081449153,0.00008525265,0.00041012297,0.000080516904,0.0002431698,0.000001325107],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003835779,0.00091036095,0.93376935,0.00010608967,0.000005535681,0.0012100006,0.002284081,0.0010059907,0.000014891988,0.00008063306,0.00088078744,0.059693955],"study_design_scores_gemma":[0.004431493,0.005818601,0.04676836,0.00065484695,0.00010357954,0.03263719,0.0017116934,0.90412277,0.0002554952,0.0021055646,0.00017875119,0.001211632],"about_ca_topic_score_codex":0.0007774481,"about_ca_topic_score_gemma":0.000013085286,"teacher_disagreement_score":0.9031168,"about_ca_system_score_codex":0.00017623932,"about_ca_system_score_gemma":0.00026344787,"threshold_uncertainty_score":0.99653393},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05771615534496858,"score_gpt":0.29183010284763583,"score_spread":0.23411394750266726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527815941","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016833642,0.000109932014,0.96812874,0.0003743882,0.0003077101,0.0004925627,0.000004652573,0.013597507,0.00015083698],"genre_scores_gemma":[0.34872708,0.0000021833878,0.6508001,0.00026037943,0.00003719624,0.00009942232,0.000015824158,0.000013491225,0.000044320637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836427,0.00011206006,0.00040655717,0.0005941288,0.00026422864,0.00025875363],"domain_scores_gemma":[0.9969961,0.0010269108,0.00019976265,0.0008111243,0.00077068474,0.00019541418],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014853051,0.00017511778,0.00019726812,0.00008647987,0.00026148843,0.000176076,0.0003952323,0.00011449634,0.0000010503294],"category_scores_gemma":[0.021419846,0.00016034866,0.00004435334,0.0004928673,0.00011718638,0.0003331118,0.000118968564,0.00010960354,0.000009527867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000195952,0.00034817532,0.20885241,0.00050391175,0.000014954735,0.0000027411018,0.0024314234,0.0018039865,0.00008382417,0.0034301486,0.04190099,0.74060786],"study_design_scores_gemma":[0.00046121085,0.00022080827,0.017421933,0.00010617373,0.000016985961,0.000025150468,0.000022037197,0.8372286,0.00024125293,0.13964836,0.004269002,0.0003384624],"about_ca_topic_score_codex":0.00012120922,"about_ca_topic_score_gemma":0.0000013549005,"teacher_disagreement_score":0.8354246,"about_ca_system_score_codex":0.00010671016,"about_ca_system_score_gemma":0.00017254466,"threshold_uncertainty_score":0.98682314},"labels":[],"label_agreement":null},{"id":"W1536265389","doi":"10.1007/3-540-46423-9_2","title":"Optimizing Java Bytecode Using the Soot Framework: Is It Feasible?","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":313,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bytecode; Java bytecode; Computer science; Java; Programming language; Java annotation; Class (philosophy); Generics in Java; Program optimization; Java applet; Operating system; Compiler; Artificial intelligence","score_opus":0.05289934935660727,"score_gpt":0.30319578851342266,"score_spread":0.2502964391568154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536265389","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003298611,0.0008121623,0.9894285,0.0026329164,0.0011014126,0.00038074565,0.0000043929767,0.0024158808,0.0031909556],"genre_scores_gemma":[0.02900715,0.00008981725,0.9614568,0.008648426,0.0005217352,0.000008803256,0.0000012413069,0.00005785926,0.00020819964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952644,0.00006079028,0.0006299246,0.0018138889,0.001232889,0.0009980998],"domain_scores_gemma":[0.9949201,0.0015743528,0.00036163928,0.0027416826,0.00022262268,0.00017962666],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012817301,0.0007173932,0.0005900614,0.0007478898,0.0007985505,0.0013530281,0.006140446,0.0005461646,0.000074369294],"category_scores_gemma":[0.00026800198,0.0005573237,0.0002172527,0.0009954231,0.0009063488,0.0005604887,0.001808911,0.001712616,0.000045369237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074236364,0.000038977625,0.00011878748,0.000040734132,0.000024892686,0.0001340492,0.004689309,0.06349618,0.00002923421,0.0086476635,0.001194181,0.9215786],"study_design_scores_gemma":[0.000065330256,0.000061489096,0.0000107832,0.0009310442,0.000010107378,0.00016039071,9.893617e-8,0.4985569,0.00045226343,0.49769604,0.001489595,0.0005659456],"about_ca_topic_score_codex":0.00010008978,"about_ca_topic_score_gemma":0.000012885049,"teacher_disagreement_score":0.92101264,"about_ca_system_score_codex":0.0003368097,"about_ca_system_score_gemma":0.00067467167,"threshold_uncertainty_score":0.99968785},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Programming language; Java; Formal specification; Test harness; Finite-state machine; Graphical user interface testing; Test case; Implementation; Software engineering; Keyword-driven testing; Graphical user interface; Software; User interface; Software development","score_opus":0.15669253087361484,"score_gpt":0.34311759476107645,"score_spread":0.1864250638874616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537009764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029334179,0.00018821804,0.98984456,0.0022649865,0.00015911386,0.0003537163,0.000014305646,0.0066923494,0.00018940943],"genre_scores_gemma":[0.09473991,0.00000133184,0.90344274,0.0012417373,0.0002999048,0.00017686516,0.0000065877575,0.000022495977,0.00006843327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797404,0.0001597305,0.00063313695,0.00040666005,0.00042996835,0.00039648227],"domain_scores_gemma":[0.9938838,0.0038214517,0.000473415,0.0008533941,0.0007612299,0.00020674612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016008414,0.00019338891,0.00022359702,0.00019905453,0.00077510014,0.00042195144,0.0011496553,0.000093457274,0.000032675118],"category_scores_gemma":[0.0043260762,0.0001883012,0.0001697115,0.00064738217,0.000074297786,0.00024327559,0.000045792127,0.00030083625,0.000041350213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001531772,0.0007623015,0.07879934,0.00020201474,0.000035192865,0.000012257545,0.00034179544,0.0017962576,0.00027390942,0.007490197,0.10704433,0.80322707],"study_design_scores_gemma":[0.0031706574,0.00075455627,0.027204838,0.00050979806,0.00006530148,0.0002683369,0.000023781336,0.4179279,0.0024262676,0.46600154,0.079565674,0.0020813588],"about_ca_topic_score_codex":0.000013015048,"about_ca_topic_score_gemma":0.0000011906117,"teacher_disagreement_score":0.80114573,"about_ca_system_score_codex":0.0001313756,"about_ca_system_score_gemma":0.00017517095,"threshold_uncertainty_score":0.76787007},"labels":[],"label_agreement":null},{"id":"W1537363352","doi":"10.11606/d.45.2008.tde-11082008-134008","title":"Ambiente de testes utilizando verificação de componentes java com tratamento de exceções","year":2008,"lang":"pt","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Gender and Health","funders":"","keywords":"Computer science; Maintainability; Java; Programming language; Source lines of code; Robustness (evolution); Software; Operating system; Reliability engineering; Software engineering","score_opus":0.04053729441339841,"score_gpt":0.30015764380422694,"score_spread":0.2596203493908285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537363352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21598136,0.003649925,0.7554606,0.00054981105,0.0009477606,0.0009722268,0.00005822965,0.019457005,0.0029230842],"genre_scores_gemma":[0.78912544,0.0011212786,0.19737262,0.0010488294,0.0001452793,0.000198933,0.0003892663,0.00014806142,0.010450275],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948799,0.00048113934,0.00095436437,0.0013281406,0.0007840044,0.0015724511],"domain_scores_gemma":[0.9955814,0.0015241324,0.00055656245,0.0013776935,0.00037755238,0.00058268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010157867,0.00095637934,0.0009048672,0.00048928475,0.00080453936,0.0007666577,0.0023184547,0.0006518779,0.00007056864],"category_scores_gemma":[0.00094956084,0.000987897,0.00040942465,0.0007735353,0.00024076643,0.0004049664,0.00024767942,0.00087998214,0.00008906997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006548903,0.0044547,0.3667744,0.0019771159,0.00067163387,0.0016207583,0.059417296,0.00037089706,0.024453145,0.0062059956,0.4172752,0.116124],"study_design_scores_gemma":[0.0031168265,0.0020290122,0.08751945,0.0059093,0.00044900455,0.002146144,0.0018928621,0.7653452,0.09838436,0.018895315,0.009355744,0.0049567893],"about_ca_topic_score_codex":0.0040696915,"about_ca_topic_score_gemma":0.000103214385,"teacher_disagreement_score":0.7649743,"about_ca_system_score_codex":0.0004890529,"about_ca_system_score_gemma":0.001118991,"threshold_uncertainty_score":0.99925715},"labels":[],"label_agreement":null},{"id":"W1540848743","doi":"10.1007/978-3-540-70567-3_21","title":"Towards Automation of Testing High-Level Security Properties","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Security testing; Software security assurance; Computer science; System integration testing; Computer security; Software reliability testing; Automation; Software; Argument (complex analysis); Software testing; Software engineering; Software development; Software construction; Engineering; Cloud computing security; Security information and event management; Information security; Security service; Operating system; Cloud computing","score_opus":0.05668893060895422,"score_gpt":0.2531988604468793,"score_spread":0.19650992983792506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540848743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063448714,0.00032435884,0.9937643,0.00023173852,0.0006712174,0.0002981768,0.000005481844,0.0026933472,0.0013769171],"genre_scores_gemma":[0.39969924,0.000013176204,0.5998992,0.00019147487,0.0001260686,0.0000065068584,0.0000015587545,0.000017048795,0.000045767712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967266,0.000038891518,0.00062216586,0.0010715086,0.0010666436,0.00047424427],"domain_scores_gemma":[0.99701726,0.00054764276,0.00047006537,0.0012370519,0.000626312,0.00010163693],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008101678,0.00044783717,0.00055882183,0.00075994205,0.00023757562,0.00020413582,0.0026555147,0.00029048356,0.0000040512436],"category_scores_gemma":[0.0009846757,0.00038854254,0.000092811206,0.0007641573,0.0007723352,0.00052389177,0.0012486598,0.0005845507,0.000011450273],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000319572,0.000040584746,0.00023659688,0.00013454467,0.000008560399,0.000048005546,0.0017871759,0.005086007,0.00021874375,0.0026190148,0.00024014269,0.9895774],"study_design_scores_gemma":[0.00015164759,0.0003030839,0.0008921886,0.0014318035,0.0000065573836,0.00019930143,3.5503977e-8,0.5662834,0.008762676,0.4212406,0.00007859079,0.0006501366],"about_ca_topic_score_codex":0.00023715585,"about_ca_topic_score_gemma":0.000011834306,"teacher_disagreement_score":0.9889273,"about_ca_system_score_codex":0.00022322152,"about_ca_system_score_gemma":0.00076731405,"threshold_uncertainty_score":0.99985665},"labels":[],"label_agreement":null},{"id":"W1546593066","doi":"10.1109/ccece.2001.933644","title":"Component interaction testing using model-checking","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Component (thermodynamics); Model checking; Model-based testing; Programming language; Simple (philosophy); Semantics (computer science); Test case; Formal semantics (linguistics); Object-oriented programming; Formal specification; Formal methods; Theoretical computer science; Software engineering; Machine learning","score_opus":0.2274275624985504,"score_gpt":0.31140505006873614,"score_spread":0.08397748757018575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546593066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03152224,0.000024079238,0.9513677,0.00011185908,0.00011790711,0.000048733396,8.7932115e-8,0.010802794,0.0060046455],"genre_scores_gemma":[0.5066623,4.5065516e-7,0.4931241,0.00014607128,0.000018247338,0.0000016633443,9.251281e-8,0.0000045237116,0.000042527397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922705,0.00002160578,0.00016288647,0.00024518755,0.00015323052,0.00019001751],"domain_scores_gemma":[0.9992886,0.00019957653,0.00007023296,0.0003261395,0.00006757605,0.00004784694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015844934,0.00009638933,0.00008910546,0.00010076281,0.00014636308,0.00015168336,0.00032407138,0.00003209631,0.000009186049],"category_scores_gemma":[0.0001935011,0.00008980975,0.000029667446,0.00026843377,0.000013432985,0.00041330454,0.00018563081,0.00011295993,0.00001913738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003598508,0.000469448,0.019319743,0.00006037957,0.000035955054,0.00008238677,0.0027432828,0.18170524,0.030052386,0.016483495,0.022388306,0.7266558],"study_design_scores_gemma":[0.000042437805,0.000016873159,0.000070059265,0.00005357594,0.0000019897293,0.00007264054,0.0000015945257,0.9906038,0.0010207068,0.007949566,0.000047401565,0.00011933771],"about_ca_topic_score_codex":0.00011927652,"about_ca_topic_score_gemma":6.478712e-7,"teacher_disagreement_score":0.80889857,"about_ca_system_score_codex":0.00006476061,"about_ca_system_score_gemma":0.000007713173,"threshold_uncertainty_score":0.36623353},"labels":[],"label_agreement":null},{"id":"W1550040990","doi":"10.1007/978-3-642-05031-2_4","title":"Implementing MSC Tests with Quiescence Observation","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Asynchronous communication; Test (biology); Chart; Fault detection and isolation; Sequence (biology); Distributed computing; Fault (geology); Test case; Class (philosophy); Reliability engineering; Real-time computing; Embedded system; Programming language; Artificial intelligence; Computer network; Machine learning; Engineering","score_opus":0.02877733741771017,"score_gpt":0.26947884009723283,"score_spread":0.24070150267952267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550040990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001490284,0.00017622893,0.99294525,0.00072387734,0.00031999356,0.0003399534,0.0000015757649,0.0037452513,0.0015988655],"genre_scores_gemma":[0.09658715,0.000013447226,0.9011765,0.001713495,0.00024438062,0.00000934766,0.0000050437325,0.000030545947,0.00022007726],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99593794,0.00002626207,0.0004935771,0.0015263392,0.0010819958,0.0009338527],"domain_scores_gemma":[0.99692553,0.0006295548,0.0004004809,0.0015301013,0.00037511004,0.00013923724],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012258876,0.0005402119,0.0004441507,0.00066294154,0.0004135407,0.00073738577,0.0030228293,0.00021379803,0.0000056685485],"category_scores_gemma":[0.0002378573,0.00046106926,0.0000736264,0.00087917794,0.00038280792,0.00078429916,0.0010127132,0.0006907822,0.000013876473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027626706,0.000017668277,0.0016470973,0.000023038885,0.0000043026557,0.00007132951,0.0002957274,0.0014304973,0.000061378654,0.0060363114,0.000087235436,0.99032265],"study_design_scores_gemma":[0.00032294044,0.00073938293,0.004015154,0.0019990036,0.000014543169,0.00026015154,6.8398236e-8,0.2508256,0.0018198658,0.73595494,0.0025604118,0.0014878856],"about_ca_topic_score_codex":0.00005561455,"about_ca_topic_score_gemma":0.00008575537,"teacher_disagreement_score":0.98883474,"about_ca_system_score_codex":0.0002713197,"about_ca_system_score_gemma":0.0005343001,"threshold_uncertainty_score":0.9997841},"labels":[],"label_agreement":null},{"id":"W1553735400","doi":"10.1007/11888116_32","title":"Minimizing Coordination Channels in Distributed Testing","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Sabancı Üniversitesi; Government of Ontario","keywords":"Computer science; Architecture; Distributed computing; Test (biology); Test case; Transitive relation; Systems architecture","score_opus":0.028546060329400658,"score_gpt":0.25505638375437323,"score_spread":0.22651032342497257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553735400","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001599927,0.00018424647,0.9937188,0.0004906203,0.0009220647,0.0003234677,0.0000054093084,0.0028776487,0.0013177621],"genre_scores_gemma":[0.39080974,0.000001656259,0.60843074,0.00033420388,0.0002746904,0.000015141359,0.000015176063,0.000030439465,0.0000882123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964106,0.00004120738,0.0006320153,0.0014295245,0.00076211715,0.0007245255],"domain_scores_gemma":[0.9966621,0.0015757171,0.00034680462,0.0010027629,0.0003120607,0.00010058556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012406695,0.0004990208,0.00050883536,0.0012616058,0.00021321113,0.0006074014,0.0024174436,0.00033089044,0.0000020248472],"category_scores_gemma":[0.00092674274,0.0005052417,0.000076923956,0.0015196219,0.0003420772,0.0005346269,0.0010475845,0.0007831556,0.00000956666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003054505,0.000058571815,0.0025337653,0.00006333127,0.0000042444653,0.0002564792,0.0003436073,0.10237932,0.00009434758,0.0026144618,0.0006259769,0.89102286],"study_design_scores_gemma":[0.00016547083,0.00008788857,0.0006108081,0.0008935054,0.000002717392,0.00006233307,2.0599005e-8,0.68062675,0.0004688185,0.3163786,0.00016737796,0.00053574605],"about_ca_topic_score_codex":0.00020676485,"about_ca_topic_score_gemma":0.000030234987,"teacher_disagreement_score":0.8904871,"about_ca_system_score_codex":0.0005072118,"about_ca_system_score_gemma":0.00037153126,"threshold_uncertainty_score":0.99973994},"labels":[],"label_agreement":null},{"id":"W1558340936","doi":"10.1109/iccad.1988.122492","title":"Parallel PLA fault simulation based on Boolean vector operations","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Set (abstract data type); Computer science; Representation (politics); Fault (geology); Bitwise operation; Parallel computing; Theoretical computer science; Algorithm; Programming language","score_opus":0.03182257309000146,"score_gpt":0.2904699293622739,"score_spread":0.2586473562722724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558340936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008649366,0.000004544831,0.98378664,0.00036785327,0.00008832306,0.00010559825,5.162417e-7,0.006464906,0.008316699],"genre_scores_gemma":[0.612962,1.4999162e-7,0.38588673,0.0009241213,0.000010108405,0.000010025102,0.0000012340412,0.0000042374954,0.00020141318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927944,0.000062470324,0.00011884031,0.00023303743,0.00016670431,0.00013952157],"domain_scores_gemma":[0.99896246,0.000471413,0.000018404062,0.00043494612,0.000060127146,0.000052659365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018396671,0.00009000864,0.00007009642,0.00007652365,0.00014097235,0.00013103982,0.0002322538,0.000041738593,0.000039313552],"category_scores_gemma":[0.0006859499,0.00007662772,0.000031190822,0.00019528948,0.000012156935,0.00015116193,0.00001778322,0.000072189156,0.00006164192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002115592,0.00007803446,0.0005622775,0.0000023885893,0.0000021113658,0.0000034699108,0.00006888165,0.92622495,0.000027015465,0.06355217,0.0055455486,0.0039310525],"study_design_scores_gemma":[0.0001424421,0.000084726715,0.00059069734,0.000011724915,0.0000011999756,9.101995e-7,7.2088676e-7,0.99313056,0.00044619883,0.0041503394,0.0013271931,0.00011329161],"about_ca_topic_score_codex":0.000027495787,"about_ca_topic_score_gemma":0.00000464756,"teacher_disagreement_score":0.612097,"about_ca_system_score_codex":0.00002705365,"about_ca_system_score_gemma":0.000052386917,"threshold_uncertainty_score":0.3124788},"labels":[],"label_agreement":null},{"id":"W1561010165","doi":"10.1109/snpd-sawn.2005.4","title":"A Method Level Based Approach for OO Integration Testing: An Experimental Study","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Integration testing; Java; Dependency (UML); Class (philosophy); Task (project management); Object-oriented programming; Software testing; Object (grammar); Software; Distributed computing; Software engineering; Programming language; Artificial intelligence; Systems engineering; Engineering","score_opus":0.21674407275810278,"score_gpt":0.39720876769489744,"score_spread":0.18046469493679465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561010165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004231007,0.000007818102,0.98572505,0.00008235264,0.000027607943,0.00056115206,0.000001040696,0.008487227,0.00087676296],"genre_scores_gemma":[0.45307153,4.8195172e-9,0.546465,0.00021089555,0.00003957342,0.00015802069,0.0000029760195,0.0000068274335,0.00004518548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989068,0.00010174668,0.00018671669,0.00044030786,0.00017998488,0.00018447523],"domain_scores_gemma":[0.99886733,0.00042048437,0.000057716534,0.00047132222,0.000114245966,0.00006889678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083932024,0.00013618846,0.0001287757,0.000104081475,0.00014064241,0.00017549371,0.0005410941,0.000039236507,0.000002979055],"category_scores_gemma":[0.00028140322,0.000111320325,0.00003637963,0.00025611103,0.000010244826,0.00038856914,0.00007667434,0.000069415284,0.0000017982995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035498542,0.00854193,0.0036554942,0.000014128397,0.000018532677,0.0000030677554,0.0050738156,0.0024701797,0.010731684,0.00833449,0.009553269,0.9515679],"study_design_scores_gemma":[0.0003559592,0.0010462054,0.00021623362,0.0000047917138,0.00000375653,0.0000072653856,0.00009494793,0.95701194,0.04003065,0.0010083594,0.000057978723,0.00016192796],"about_ca_topic_score_codex":0.00012214255,"about_ca_topic_score_gemma":0.000007129352,"teacher_disagreement_score":0.95454174,"about_ca_system_score_codex":0.00005292682,"about_ca_system_score_gemma":0.00005339881,"threshold_uncertainty_score":0.45395112},"labels":[],"label_agreement":null},{"id":"W1564813932","doi":"10.1109/icnp.1993.340889","title":"A framework for interoperability testing of network protocols","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interoperability; Computer science; Programming language; Protocol (science); Implementation; Formal specification; Relation (database); Interpretation (philosophy); Formal methods; Expressive power; Theoretical computer science; Data mining; World Wide Web","score_opus":0.15236436299207198,"score_gpt":0.3469682107810886,"score_spread":0.1946038477890166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564813932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054979394,0.000013251742,0.9889313,0.00019772867,0.000047890273,0.0035460347,4.3498562e-7,0.0054060807,0.0013075067],"genre_scores_gemma":[0.15063849,1.0670837e-7,0.8463661,0.00019792054,0.000056727833,0.0026899837,7.886337e-8,0.000005885176,0.000044704047],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916196,0.000033167904,0.00023988944,0.00024861222,0.000104425955,0.00021192533],"domain_scores_gemma":[0.9976614,0.0014642589,0.00009193883,0.0005820781,0.00016001328,0.000040315936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000432572,0.00008603355,0.00015216804,0.000026599628,0.00006805501,0.000054552707,0.000600664,0.00005444472,0.000015395528],"category_scores_gemma":[0.002774988,0.00006909862,0.000049625432,0.00035912872,0.000036896145,0.00011471495,0.00016304,0.000088921544,0.0000041284097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000120191025,0.00038554438,0.10272594,0.00026261157,0.000020295804,0.0000024989222,0.0008759936,0.00020320562,0.00008689449,0.17381305,0.087165564,0.6344464],"study_design_scores_gemma":[0.0001161889,0.00045428332,0.0009575064,0.00040225283,0.000002019866,0.0000071368045,0.0000011233926,0.28407454,0.0010724259,0.71154684,0.0012094348,0.0001562253],"about_ca_topic_score_codex":0.000015797417,"about_ca_topic_score_gemma":5.1332955e-7,"teacher_disagreement_score":0.63429016,"about_ca_system_score_codex":0.000014059959,"about_ca_system_score_gemma":0.000011043149,"threshold_uncertainty_score":0.33221203},"labels":[],"label_agreement":null},{"id":"W1564936289","doi":"","title":"Model based test suite minimization using metaheuristics","year":2011,"lang":"en","type":"article","venue":"Australasian Journal of Paramedicine","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Edith Cowan University; Royal Academy of Engineering; Carleton University","keywords":"Minification; Metaheuristic; Test suite; Computer science; Suite; Test (biology); Algorithm; Test case; Machine learning; Geology; Geography; Programming language","score_opus":0.09792129475973263,"score_gpt":0.3059081618920331,"score_spread":0.2079868671323005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564936289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009900418,0.000047854322,0.98878914,0.0003518977,0.00019950625,0.0000577138,0.000001182075,0.0004105069,0.00024179384],"genre_scores_gemma":[0.51650584,0.000002491733,0.48326743,0.00014204087,0.000055498323,3.6030488e-7,3.6007512e-7,0.000006784249,0.000019193032],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987262,0.000043817578,0.0005184929,0.0001481441,0.0003415263,0.00022184338],"domain_scores_gemma":[0.99842834,0.00027291555,0.0004895998,0.00032047305,0.00030638574,0.00018226697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053049024,0.00014261852,0.00026964757,0.00026502408,0.000057000358,0.000034313187,0.0005781031,0.00006759163,0.000012361295],"category_scores_gemma":[0.0012183503,0.00011398573,0.0000760317,0.0003484005,0.00008679443,0.0002777588,0.000034083187,0.0002416964,0.0000022081008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003003792,0.0038310841,0.5973595,0.00048977486,0.00053043186,0.0058859135,0.014401867,0.087988615,0.008856443,0.01390726,0.14014037,0.12630835],"study_design_scores_gemma":[0.00053925946,0.0005905351,0.0037722136,0.00027122325,0.000088558765,0.00054878474,0.000010143968,0.97496593,0.0018893079,0.01711351,0.000048322905,0.00016219272],"about_ca_topic_score_codex":0.000011859183,"about_ca_topic_score_gemma":3.762294e-7,"teacher_disagreement_score":0.8869773,"about_ca_system_score_codex":0.00003868195,"about_ca_system_score_gemma":0.0001956045,"threshold_uncertainty_score":0.4648203},"labels":[],"label_agreement":null},{"id":"W1568097335","doi":"10.1007/978-1-4471-0719-4_31","title":"Using UML to Partially Automate Generation of Scenario-Based Test Drivers","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Unified Modeling Language; Schedule; Computer science; Software engineering; Task (project management); Software development; Software; Systems engineering; Engineering; Programming language; Operating system","score_opus":0.10470659731656258,"score_gpt":0.29566436622660186,"score_spread":0.1909577689100393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568097335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007496382,0.000017271384,0.93658483,0.00023650372,0.0001931581,0.00022466943,0.0000053707167,0.006968165,0.05569509],"genre_scores_gemma":[0.01741333,0.00000483982,0.96050704,0.0008257725,0.00015326354,0.0000060994907,0.000012051921,0.00004326176,0.021034332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985599,0.000013850204,0.00036491727,0.00047852437,0.00036244027,0.00022040098],"domain_scores_gemma":[0.99852717,0.00015123286,0.00022790504,0.0007485867,0.00023420161,0.0001108852],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022716803,0.00026430425,0.0003002514,0.00030187934,0.00009345176,0.00010637023,0.00059920456,0.00019670316,0.000052534124],"category_scores_gemma":[0.00014066478,0.00025882263,0.00010147694,0.00010383688,0.000045230114,0.000114963324,0.0001774355,0.00012444232,0.00003381545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002272193,0.00038174697,0.0048708417,0.00032984806,0.00018220299,0.0005226149,0.0007986175,0.041390784,0.014147359,0.26027602,0.33299997,0.34407726],"study_design_scores_gemma":[0.00015531649,0.000266315,0.00004282509,0.00046238067,0.000032489403,0.00002199682,1.765212e-7,0.971035,0.0051453635,0.011206808,0.011047981,0.00058335223],"about_ca_topic_score_codex":0.00016795665,"about_ca_topic_score_gemma":0.000040588802,"teacher_disagreement_score":0.9296442,"about_ca_system_score_codex":0.00010787411,"about_ca_system_score_gemma":0.0002699586,"threshold_uncertainty_score":0.9999864},"labels":[],"label_agreement":null},{"id":"W1568757735","doi":"10.1007/978-3-642-12200-2_32","title":"Finding the Best CAFE Is NP-Hard","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Clique; Binary number; Computer science; Reduction (mathematics); Time complexity; Enhanced Data Rates for GSM Evolution; Computational complexity theory; Polynomial; Hardness of approximation; Theoretical computer science; Discrete mathematics; Combinatorics; Algorithm; Approximation algorithm; Mathematics; Arithmetic; Artificial intelligence","score_opus":0.03334229128567038,"score_gpt":0.2729033384576659,"score_spread":0.23956104717199553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568757735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000090302834,0.00029859395,0.98879707,0.0032150082,0.0021759544,0.00031509306,0.0000047478634,0.0023373892,0.002765845],"genre_scores_gemma":[0.06267611,0.000037094775,0.9273721,0.00802697,0.0008619195,0.000019534033,0.0000022811703,0.00005614564,0.0009478405],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961702,0.00003308303,0.00045736783,0.0015179076,0.001077362,0.0007440812],"domain_scores_gemma":[0.9953367,0.0014016414,0.00031008237,0.0025351394,0.00025933408,0.00015710565],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014017815,0.0005579655,0.00044387876,0.0006044915,0.00068571203,0.0010263337,0.0062376317,0.00045126324,0.000024630099],"category_scores_gemma":[0.00039605712,0.00040497255,0.00016319935,0.0006551088,0.0010225915,0.00040045404,0.002065055,0.0018491071,0.000116026255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024012763,0.000030222582,0.00059104257,0.0000316187,0.00001270003,0.00009861789,0.001817043,0.0005180994,0.00021947894,0.0092810355,0.0012931497,0.9861046],"study_design_scores_gemma":[0.00014910707,0.00019502868,0.00015319766,0.0005778165,0.000014667352,0.00037748116,7.4310734e-8,0.09266762,0.0041631577,0.8861525,0.01450246,0.0010468907],"about_ca_topic_score_codex":0.00009066815,"about_ca_topic_score_gemma":0.00003256631,"teacher_disagreement_score":0.9850577,"about_ca_system_score_codex":0.00016538647,"about_ca_system_score_gemma":0.00048752656,"threshold_uncertainty_score":0.9998402},"labels":[],"label_agreement":null},{"id":"W1570631586","doi":"10.1002/sec.1290","title":"An empirical investigation into path divergences for concolic execution using CREST","year":2015,"lang":"en","type":"article","venue":"Security and Communication Networks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Core Research for Evolutional Science and Technology; National Natural Science Foundation of China","keywords":"Concolic testing; Computer science; Soundness; Path (computing); Test suite; Empirical research; Divergence (linguistics); Test case; Symbolic execution; Test (biology); Theoretical computer science; Software; Programming language; Machine learning; Mathematics; Statistics","score_opus":0.08112494552671053,"score_gpt":0.35457969414723567,"score_spread":0.27345474862052516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570631586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2141053,0.0012727336,0.7819917,0.00070676266,0.000105395164,0.00022451875,9.80965e-7,0.001542392,0.00005018905],"genre_scores_gemma":[0.81844074,0.00008676121,0.18097802,0.00037587967,0.000052896863,0.000032364605,0.00002722149,0.000004654109,0.0000014452476],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990663,0.0002767657,0.00018452689,0.00021465492,0.00012166603,0.0001360957],"domain_scores_gemma":[0.9986419,0.00024793492,0.00012047632,0.00062521384,0.00021653251,0.00014795229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008474615,0.000094467454,0.00011139569,0.000047485206,0.00037026955,0.0001801021,0.000591459,0.00010832735,3.5983052e-7],"category_scores_gemma":[0.00016708024,0.00009441032,0.000022164171,0.00023368002,0.00013378578,0.0005671082,0.00022367836,0.0001395311,3.8931012e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019189347,0.0008349524,0.38368687,0.00016552395,0.0000913167,0.000004988049,0.15591015,0.018086191,0.00024376142,0.17806141,0.0847594,0.17796354],"study_design_scores_gemma":[0.00012752689,0.00010012732,0.0010899565,0.00003798286,0.0000055336836,0.0000045354595,0.00007178791,0.736252,0.000022649285,0.2616937,0.00049199513,0.000102249825],"about_ca_topic_score_codex":0.0005056485,"about_ca_topic_score_gemma":0.00007527951,"teacher_disagreement_score":0.7181658,"about_ca_system_score_codex":0.000047334604,"about_ca_system_score_gemma":0.00008042856,"threshold_uncertainty_score":0.38499412},"labels":[],"label_agreement":null},{"id":"W1571486493","doi":"10.1109/ccece.2000.849660","title":"The architecture of a Java coverage tool","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Java; Instrumentation (computer programming); Computer science; Flexibility (engineering); Architecture; Domain (mathematical analysis); Software engineering; Operating system; Embedded system; Computer architecture","score_opus":0.015406256352965074,"score_gpt":0.2183285589213015,"score_spread":0.20292230256833643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571486493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020013903,0.0002054563,0.97635823,0.0013188253,0.00007012325,0.00006358497,3.5157817e-7,0.003817654,0.016164394],"genre_scores_gemma":[0.82352287,0.000017230774,0.17455593,0.00041557217,0.000019471923,0.000005714728,7.169935e-8,0.0000035752346,0.0014595471],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99951696,0.000024255241,0.00010154462,0.000110329136,0.00013202814,0.00011489516],"domain_scores_gemma":[0.9989931,0.0004460561,0.000036583744,0.00047716865,0.000029922669,0.000017176051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015143128,0.00005142769,0.000056755554,0.000023786826,0.00008203671,0.000057277128,0.00056971004,0.000020346164,0.000015340333],"category_scores_gemma":[0.00022196976,0.000029353056,0.000033752305,0.00015670402,0.000034225795,0.00004788747,0.00012002198,0.000066398556,0.000014950511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011566405,0.000032355518,0.00093592785,0.000005891724,0.0000067382502,0.000005214108,0.0004521189,0.00003110174,0.00007250832,0.06050733,0.13913898,0.79881066],"study_design_scores_gemma":[0.00036139772,0.0003523872,0.0036375464,0.00007085382,0.000006096941,0.00014289873,0.0000035515968,0.148302,0.009303467,0.7484438,0.08893862,0.00043738933],"about_ca_topic_score_codex":0.000021155593,"about_ca_topic_score_gemma":0.0000015957224,"teacher_disagreement_score":0.8215215,"about_ca_system_score_codex":0.000005142753,"about_ca_system_score_gemma":0.0000059532654,"threshold_uncertainty_score":0.119698286},"labels":[],"label_agreement":null},{"id":"W1576774211","doi":"10.1007/978-3-642-01187-0_26","title":"Integration Testing of Web Applications and Databases Using TTCN-3","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Variety (cybernetics); Java; Integration testing; SQL; Web application; Database; Software engineering; Programming language; Data integration; World Wide Web; Software; Artificial intelligence","score_opus":0.04183812627414476,"score_gpt":0.2798233376161275,"score_spread":0.23798521134198272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576774211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000055444427,0.00067884155,0.9919416,0.00011315963,0.00004299197,0.0003053624,0.000010654845,0.0013354168,0.005516547],"genre_scores_gemma":[0.1014816,0.00005693456,0.89788496,0.0003286016,0.000076598786,0.000020031424,0.00010188468,0.000020549785,0.000028854789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985802,0.000011289113,0.0006856726,0.00026051424,0.00028947517,0.00017280558],"domain_scores_gemma":[0.9976572,0.00033021066,0.0008242375,0.00039547216,0.00075901585,0.000033875458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028646598,0.0002937507,0.00032721407,0.00070738036,0.00016155418,0.00025221135,0.0003589403,0.00020617788,0.0000019165757],"category_scores_gemma":[0.000987943,0.00027999334,0.000025152929,0.0006634753,0.00009066408,0.002057733,0.00016014632,0.0003142365,0.0000013676508],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002467486,0.000006974872,0.000117473806,0.0003648583,0.0000023333787,7.622177e-7,0.00019159523,0.001226402,0.000090087466,0.0038591626,0.00001014097,0.99412775],"study_design_scores_gemma":[0.00036813246,0.000044522585,0.0006726552,0.007818469,0.00005446148,0.00015374298,0.0000036889032,0.7472238,0.0014418174,0.23535278,0.005875606,0.000990351],"about_ca_topic_score_codex":0.00003939931,"about_ca_topic_score_gemma":0.000009751838,"teacher_disagreement_score":0.9931374,"about_ca_system_score_codex":0.00008333661,"about_ca_system_score_gemma":0.0003287778,"threshold_uncertainty_score":0.99996525},"labels":[],"label_agreement":null},{"id":"W1576968470","doi":"10.1007/978-3-642-16901-4_14","title":"API Conformance Verification for Java Programs","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Programming language; Executable; Java; Control flow; Operating system; Concurrency; Conformance testing; Application programming interface; Software engineering","score_opus":0.02692841412498071,"score_gpt":0.2677013130703781,"score_spread":0.24077289894539738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576968470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027821647,0.00014934511,0.9923562,0.00039647086,0.0015671062,0.00079684507,0.0000033364408,0.003557208,0.0011456812],"genre_scores_gemma":[0.049552497,0.000013660299,0.9489929,0.000731,0.00037399016,0.00007413929,0.000014084972,0.000033137676,0.00021461118],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971398,0.000010651015,0.00044130386,0.001225397,0.0006032571,0.00057956734],"domain_scores_gemma":[0.9969884,0.0005123334,0.00034707057,0.0016093354,0.000411225,0.00013163601],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009963816,0.00041759436,0.00037847678,0.0004980819,0.00030379614,0.00063092326,0.0031913847,0.00041051427,0.0000031484738],"category_scores_gemma":[0.00026377643,0.0003850664,0.000116382864,0.00039241323,0.0006227203,0.0004916139,0.00056294614,0.00071578193,0.000021315109],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032021685,0.000018743154,0.00005536904,0.000041049116,0.0000035531482,0.0000046747896,0.0002626759,0.0001645254,0.00013105609,0.016890459,0.00006815403,0.98235655],"study_design_scores_gemma":[0.00021149559,0.00031296513,0.000070567075,0.00040796286,0.0000070497954,0.00006480653,1.7060588e-8,0.29303378,0.0044636307,0.6848918,0.015815765,0.0007201133],"about_ca_topic_score_codex":0.00002072162,"about_ca_topic_score_gemma":0.000018047185,"teacher_disagreement_score":0.9816364,"about_ca_system_score_codex":0.00012968344,"about_ca_system_score_gemma":0.00045943246,"threshold_uncertainty_score":0.9998601},"labels":[],"label_agreement":null},{"id":"W1577013748","doi":"10.1109/pacrim.2001.953527","title":"Routing reliability analysis of partially disjoint paths","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Computer network; Static routing; Equal-cost multi-path routing; Open Shortest Path First; Link-state routing protocol; Routing protocol; Dynamic Source Routing; Routing Information Protocol; Zone Routing Protocol; Multipath routing; Enhanced Interior Gateway Routing Protocol; Reliability (semiconductor); Distributed computing; Path vector protocol; Routing (electronic design automation)","score_opus":0.0308666070486083,"score_gpt":0.25693357631026786,"score_spread":0.22606696926165956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577013748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026000734,0.000021376422,0.9654816,0.00029087573,0.000043156197,0.000047646336,8.736361e-7,0.0050102463,0.0031035102],"genre_scores_gemma":[0.73138297,0.000002078631,0.26843232,0.00009074824,0.0000066646144,0.0000033985702,4.245738e-7,0.0000022725308,0.00007911341],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900115,0.00005467365,0.0002902391,0.00028578535,0.00020189158,0.00016623583],"domain_scores_gemma":[0.9986448,0.0003167695,0.00010140098,0.0007926941,0.00009358086,0.000050746916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000510136,0.0000794214,0.00021179434,0.00014158573,0.000050198687,0.000041947394,0.0004524839,0.000034808876,0.00007012669],"category_scores_gemma":[0.00066884723,0.00006439292,0.00013923363,0.0011631334,0.00003498062,0.00013610156,0.0001810967,0.00006066147,0.000008887786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003417861,0.00062205706,0.6358845,0.000033553304,0.00035691133,0.000019184065,0.0031145697,0.0047427122,0.00026804753,0.035122424,0.017984308,0.3018483],"study_design_scores_gemma":[0.000035726764,0.000040714545,0.030432068,0.000008789701,0.000053948505,9.895327e-7,0.0000019215852,0.9630229,0.0007202003,0.005512932,0.000071178496,0.000098653014],"about_ca_topic_score_codex":0.00020876984,"about_ca_topic_score_gemma":0.000009439562,"teacher_disagreement_score":0.95828015,"about_ca_system_score_codex":0.000019347668,"about_ca_system_score_gemma":0.000008240103,"threshold_uncertainty_score":0.2625867},"labels":[],"label_agreement":null},{"id":"W1577404745","doi":"10.1007/s10009-007-0044-z","title":"The software model checker Blast","year":2007,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":594,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Predicate abstraction; Predicate (mathematical logic); Programming language; Memory safety; Model checking; Programmer; Program analysis; Symbolic execution; Static analysis; Software","score_opus":0.029266124064769698,"score_gpt":0.3019749021356067,"score_spread":0.272708778070837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577404745","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007489565,0.00015196574,0.97859174,0.0048406124,0.0012464693,0.00025083817,0.000020766423,0.0073170555,0.000090959446],"genre_scores_gemma":[0.262687,0.00009126679,0.7343988,0.0020310886,0.0002855171,0.000080122016,0.0000068075856,0.000053157684,0.00036629],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975857,0.000022617658,0.0006160554,0.00043229284,0.0007136144,0.0006297166],"domain_scores_gemma":[0.9971406,0.0011310207,0.00011722586,0.0005876943,0.0008975687,0.00012592578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013047513,0.0002882028,0.00022722298,0.0005495513,0.0006265812,0.0006346113,0.0033769312,0.00031835746,0.00000516752],"category_scores_gemma":[0.0024796089,0.00020977636,0.00027353046,0.0003686378,0.00022132552,0.0006114863,0.00014417435,0.0008166314,0.00002634934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021733234,0.00018527055,0.0016168162,0.000006059486,0.0002118439,0.00014238816,0.00016601897,0.00056613,0.00014448597,0.16971655,0.014462394,0.81256473],"study_design_scores_gemma":[0.0027186621,0.0011100281,0.0011345732,0.0003471548,0.000048338505,0.0024251367,0.000037234673,0.022046564,0.020354163,0.839809,0.10886308,0.0011060373],"about_ca_topic_score_codex":0.0000014865402,"about_ca_topic_score_gemma":0.000006861332,"teacher_disagreement_score":0.81145865,"about_ca_system_score_codex":0.00021168333,"about_ca_system_score_gemma":0.00015783278,"threshold_uncertainty_score":0.8554432},"labels":[],"label_agreement":null},{"id":"W1581911077","doi":"10.1007/978-3-540-68255-4_33","title":"Build Notifications in Agile Environments","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Codebase; Agile software development; Computer science; Software engineering; Suite; Software; Timeout; Software development; Operating system","score_opus":0.017591760877402635,"score_gpt":0.23294724924668386,"score_spread":0.21535548836928123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581911077","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030659354,0.0005376204,0.9803268,0.0006438787,0.00016921986,0.00028667558,0.0000052322484,0.0015606188,0.016439326],"genre_scores_gemma":[0.44899958,0.0009273149,0.5437827,0.003445913,0.00023667487,0.00020122422,0.0004895117,0.000121328834,0.001795743],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982202,0.0000133784,0.00073404727,0.0003319443,0.00041828633,0.00028213274],"domain_scores_gemma":[0.99855125,0.00017898166,0.0005114885,0.00057857117,0.00013796872,0.000041757303],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021247963,0.0003509451,0.0003209561,0.0009233242,0.00016368067,0.00025189333,0.00075077254,0.00042029124,0.000012792483],"category_scores_gemma":[0.0005210253,0.00035730025,0.00004260471,0.00049368996,0.00009451199,0.0019233084,0.00020112,0.0005505521,0.0000611181],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006314278,0.00003680816,0.00069087534,0.00028164315,0.0000052897904,0.000018720319,0.0023472817,0.011394194,0.000008457394,0.001891974,0.0006532859,0.9826652],"study_design_scores_gemma":[0.0018007355,0.00008002608,0.01669644,0.009181941,0.000039597347,0.00038508285,0.000004998439,0.24233818,0.0013118839,0.3619356,0.36191666,0.0043088803],"about_ca_topic_score_codex":0.00003510115,"about_ca_topic_score_gemma":0.000014446244,"teacher_disagreement_score":0.9783563,"about_ca_system_score_codex":0.00025689395,"about_ca_system_score_gemma":0.00023125409,"threshold_uncertainty_score":0.9998879},"labels":[],"label_agreement":null},{"id":"W1582381037","doi":"10.1007/978-3-540-68255-4_27","title":"Multi-modal Functional Test Execution","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Debugging; Computer science; Modal; Layer (electronics); Programming language; Software engineering; Test case; Overhead (engineering); Embedded system","score_opus":0.02655807541538957,"score_gpt":0.23848792422266754,"score_spread":0.21192984880727797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582381037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000076140373,0.0005020417,0.9841101,0.00044875746,0.00037310983,0.00023302723,0.0000074134446,0.004479702,0.009838208],"genre_scores_gemma":[0.17802015,0.0002783867,0.8163075,0.0028401145,0.00050339336,0.00008990804,0.0005226739,0.000089901914,0.0013480124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980877,0.000010118803,0.00068995106,0.00035780412,0.00055174506,0.00030267838],"domain_scores_gemma":[0.9977649,0.00031173395,0.00059973646,0.00044513683,0.0008229579,0.000055573462],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022127878,0.00043631525,0.00034008795,0.0007758615,0.00031246693,0.00039125545,0.000545189,0.00054642785,0.000020926573],"category_scores_gemma":[0.0013384006,0.00042101447,0.00006897774,0.0004601609,0.00011088475,0.0025722657,0.00020470702,0.00060434,0.00006407758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014792452,0.000050419523,0.00047199117,0.00050189695,0.000009518103,0.000021944128,0.0011472019,0.0073038833,0.000015340578,0.0009820425,0.0022879357,0.98719305],"study_design_scores_gemma":[0.0020828976,0.00012854073,0.014376671,0.00613754,0.00005193561,0.0011477458,0.0000027616495,0.789213,0.00062370126,0.100844815,0.0818261,0.003564286],"about_ca_topic_score_codex":0.000021070473,"about_ca_topic_score_gemma":0.000006596523,"teacher_disagreement_score":0.98362875,"about_ca_system_score_codex":0.0002454495,"about_ca_system_score_gemma":0.00048571243,"threshold_uncertainty_score":0.99982417},"labels":[],"label_agreement":null},{"id":"W1582552606","doi":"","title":"Signature required making simulink data flow and interfaces explicit","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Signature (topology); Computer science; Reuse; Generalization; Interface (matter); Comprehension; Automotive industry; Software engineering; Programming language; Embedded system; Operating system; Engineering","score_opus":0.05427294548107347,"score_gpt":0.30487206208818773,"score_spread":0.25059911660711426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582552606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020141148,0.00015282359,0.9866668,0.0008295598,0.0001343459,0.000062738385,0.0000013943247,0.008356238,0.0017820068],"genre_scores_gemma":[0.556743,0.0000026933567,0.44251847,0.00061454804,0.000047165882,0.0000013706766,0.0000022673628,0.0000051691322,0.000065285145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990063,0.000048363745,0.00013647322,0.00048459924,0.00014083397,0.00018343003],"domain_scores_gemma":[0.9980861,0.0005125699,0.00004976535,0.0012672397,0.00003748768,0.000046862766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048077834,0.00011582437,0.0001250565,0.000060543796,0.000091824295,0.00024484526,0.0014159133,0.00006902421,0.0000059310937],"category_scores_gemma":[0.00066259457,0.00009324524,0.000011177954,0.0001467752,0.00002629581,0.00051401387,0.0013847771,0.00012574311,0.000010920673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005350686,0.000032390486,0.0012663507,0.000038887873,0.000015108663,0.000009205868,0.0008565537,0.00008270791,0.00072408904,0.013798525,0.103303105,0.87986773],"study_design_scores_gemma":[0.00008489741,0.000056341192,0.00015668897,0.00007735331,0.0000029786336,0.000014553768,0.0000040594914,0.9605242,0.0007365225,0.034521077,0.0036585375,0.00016277986],"about_ca_topic_score_codex":0.000016018666,"about_ca_topic_score_gemma":0.000004302849,"teacher_disagreement_score":0.9604415,"about_ca_system_score_codex":0.00000770348,"about_ca_system_score_gemma":0.000011946731,"threshold_uncertainty_score":0.38024303},"labels":[],"label_agreement":null},{"id":"W1582795712","doi":"10.1007/b95400","title":"Formal approaches to software testing : third International Workshop on Formal Approaches to Testing of Software, FATES 2003, Montreal, Quebec, Canada, October 6th, 2003 : revised papers","year":2004,"lang":"en","type":"book","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"White-box testing; Computer science; Test Management Approach; Non-regression testing; Keyword-driven testing; Manual testing; Model-based testing; Programming language; Test script; System integration testing; Software engineering; Black-box testing; Regression testing; Test case; Code coverage; Test strategy; Conformance testing; Software reliability testing; Software testing; Software; Software system; Software development; Operating system; Software quality; Software construction; Machine learning","score_opus":0.10958301892259165,"score_gpt":0.23538909870121832,"score_spread":0.12580607977862668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582795712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012348374,0.00039728644,0.7838911,0.0010678099,0.0010465027,0.002742002,0.00015104677,0.011224377,0.19935638],"genre_scores_gemma":[0.0015380826,0.000005356799,0.8597612,0.0020542797,0.00041557124,0.00033363997,0.00018631556,0.00017345608,0.13553211],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99288636,0.00010429135,0.0015890294,0.0018894903,0.0018469266,0.0016838978],"domain_scores_gemma":[0.9928469,0.0024862944,0.0009447199,0.0017701467,0.0012353568,0.0007165469],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0011185175,0.0013434907,0.001309449,0.0008432043,0.0005094138,0.00053441327,0.0036011168,0.00061514706,0.000026977317],"category_scores_gemma":[0.015738785,0.0012461374,0.00020632698,0.0021955995,0.00014399998,0.0009436582,0.0017970451,0.0011260123,0.000020121568],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087071116,0.00025788695,0.0031565705,0.0006147542,0.0002570711,0.000120236924,0.0012212783,0.022730755,0.0000034111142,0.004600806,0.3469099,0.62004024],"study_design_scores_gemma":[0.013586136,0.00836074,0.046565022,0.122592166,0.0019718795,0.002015223,0.0010857725,0.23861542,0.004372229,0.106732115,0.4050557,0.049047586],"about_ca_topic_score_codex":0.18789317,"about_ca_topic_score_gemma":0.17705293,"teacher_disagreement_score":0.57099265,"about_ca_system_score_codex":0.0024852203,"about_ca_system_score_gemma":0.010018211,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W1586015080","doi":"","title":"Qualitative observations from software code inspection experiments","year":2002,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Software inspection; Computer science; Software; Code (set theory); Software engineering; Software quality; Programming language; Software development","score_opus":0.4511467688952683,"score_gpt":0.4903815943352252,"score_spread":0.03923482543995693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586015080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3239427,0.011348554,0.57581484,0.05792503,0.0045503597,0.011149557,0.0024040393,0.010438491,0.0024264227],"genre_scores_gemma":[0.82106453,0.0002672737,0.17707041,0.00008626765,0.000040903324,0.00038472275,0.000006018158,0.000016630045,0.0010632456],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976156,0.000593545,0.00031876084,0.0004883636,0.0006311451,0.00035260688],"domain_scores_gemma":[0.9902802,0.0042901305,0.00022727734,0.0007113124,0.004429352,0.00006173582],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006142534,0.00017622807,0.00029776813,0.00012198191,0.00081541855,0.00008307708,0.0009776854,0.000053127587,0.0000060101092],"category_scores_gemma":[0.010196,0.00012892437,0.000067363675,0.0013645899,0.00045562582,0.00032725558,0.00042477806,0.00023306908,0.000007825384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033749198,0.0013765169,0.0029861927,0.00019173246,0.00072599185,0.0000056976396,0.46645543,0.00084822247,0.010075072,0.2125891,0.26704752,0.037361015],"study_design_scores_gemma":[0.002938466,0.0018204659,0.0013704672,0.0020718728,0.000028411254,7.1675726e-7,0.07098541,0.027216649,0.23239994,0.648752,0.011513984,0.00090165815],"about_ca_topic_score_codex":0.00001688302,"about_ca_topic_score_gemma":0.000069219495,"teacher_disagreement_score":0.49712184,"about_ca_system_score_codex":0.00025201327,"about_ca_system_score_gemma":0.00012022982,"threshold_uncertainty_score":0.9981415},"labels":[],"label_agreement":null},{"id":"W1590993614","doi":"10.1007/978-3-642-12566-9_13","title":"On Software Certification: We Need Product-Focused Approaches","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Certification; Software engineering; Product (mathematics); Software; Programming language; Management; Mathematics","score_opus":0.05594045579544545,"score_gpt":0.2496989663611623,"score_spread":0.19375851056571683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590993614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033936405,0.000314165,0.9869749,0.0032884513,0.0017175957,0.0005691704,0.0000037372333,0.0059151975,0.0011828335],"genre_scores_gemma":[0.052955218,0.000013862149,0.944983,0.00096839387,0.00057043426,0.000039053368,0.0000074951495,0.00006007614,0.00040244372],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951881,0.000043260803,0.0005544587,0.0023288256,0.0011788767,0.00070644077],"domain_scores_gemma":[0.9947919,0.0010519901,0.0003798362,0.00329351,0.00027863056,0.00020409384],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010890272,0.0006921342,0.0005577114,0.0010396286,0.0004321059,0.0007678309,0.0047510685,0.0004575122,0.00001671293],"category_scores_gemma":[0.0008981464,0.0006080346,0.00014636431,0.00082685455,0.000851738,0.0004419968,0.0010822733,0.0016711652,0.00007101653],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006145495,0.00005479601,0.00007516827,0.00004667971,0.000006993989,0.000029015164,0.0005724704,0.0017387033,0.000057504545,0.017639896,0.00033190864,0.97944075],"study_design_scores_gemma":[0.00017525915,0.0002182481,0.0001111571,0.00057996414,0.000008268505,0.000083835694,2.8525916e-8,0.080434985,0.0056834365,0.9095946,0.0021242534,0.0009859591],"about_ca_topic_score_codex":0.000016080498,"about_ca_topic_score_gemma":0.000012582112,"teacher_disagreement_score":0.97845477,"about_ca_system_score_codex":0.00021276734,"about_ca_system_score_gemma":0.00057763216,"threshold_uncertainty_score":0.9996371},"labels":[],"label_agreement":null},{"id":"W1591778339","doi":"10.33915/etd.1237","title":"Random search of AND-OR graphs representing finite-state models","year":2002,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Finite-state machine; Testability; Theoretical computer science; Model checking; State (computer science); Random graph; Graph; Algorithm; Mathematics","score_opus":0.06222283750590606,"score_gpt":0.31411476337761907,"score_spread":0.251891925871713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591778339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03676145,0.0010374233,0.92287576,0.00007598976,0.00029713826,0.0006302977,0.0000074507043,0.010589052,0.027725438],"genre_scores_gemma":[0.53318256,0.00063342904,0.4378212,0.00006958847,0.000026559494,0.00005412583,0.00004735793,0.000048676055,0.028116466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983642,0.00008065302,0.00039912315,0.0005135801,0.00038722708,0.00025519507],"domain_scores_gemma":[0.99767464,0.001199145,0.00018860174,0.00064065505,0.00022796253,0.00006900168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005181916,0.0002058843,0.0003699969,0.0003736393,0.00009542501,0.00012802663,0.00064024155,0.00013617887,0.000017488033],"category_scores_gemma":[0.00047883505,0.00016366577,0.00009793266,0.0004579159,0.000034485947,0.000246491,0.000141339,0.00024596477,0.000003639179],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000601147,0.00044594018,0.0019495186,0.0025267114,0.00031319904,0.00038719986,0.029433168,0.0068683657,0.00025522948,0.02073528,0.039951455,0.8965328],"study_design_scores_gemma":[0.0005089305,0.00008678705,0.00009944931,0.00044601652,0.0000146472985,0.000016611431,0.000029354836,0.85761493,0.0022283224,0.13861254,0.000025350198,0.00031707287],"about_ca_topic_score_codex":0.00040003713,"about_ca_topic_score_gemma":0.000023606824,"teacher_disagreement_score":0.89621574,"about_ca_system_score_codex":0.000008102615,"about_ca_system_score_gemma":0.000058006382,"threshold_uncertainty_score":0.6674096},"labels":[],"label_agreement":null},{"id":"W1593362647","doi":"10.1007/978-3-642-01187-0_12","title":"Model-Based Penetration Test Framework for Web Applications Using TTCN-3","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Penetration (warfare); Engineering; Operations research","score_opus":0.03229845071128463,"score_gpt":0.2863652810987781,"score_spread":0.2540668303874935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593362647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032479397,0.00029227283,0.9925359,0.0006355863,0.000086001455,0.00089613086,0.000020270614,0.003140871,0.002389745],"genre_scores_gemma":[0.0678007,0.000012161208,0.9298267,0.0017684945,0.00016580589,0.00015468014,0.00018563704,0.00003930965,0.000046554997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981085,0.000007844477,0.0007666036,0.00039608395,0.00039832393,0.0003226081],"domain_scores_gemma":[0.9968474,0.0006645019,0.0008208226,0.00060778524,0.0010034702,0.000056014647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032061143,0.0004438629,0.00037186337,0.000762915,0.00036573596,0.0007337403,0.00071746635,0.00069908885,0.000002615279],"category_scores_gemma":[0.0011636213,0.0004565305,0.00008237528,0.00062793464,0.00006401035,0.0016747469,0.00007112596,0.00047617726,0.000005286371],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000846642,0.000026004083,0.00004819805,0.0006233477,0.0000033484623,5.874417e-7,0.00017877396,0.18046957,0.000017643233,0.02013634,0.000055688746,0.79843205],"study_design_scores_gemma":[0.000120261335,0.000014933992,0.00001931702,0.0009168661,0.000013695641,0.0000052680325,1.7524927e-7,0.6035346,0.000072275725,0.3933588,0.0016147343,0.0003291036],"about_ca_topic_score_codex":0.000004103195,"about_ca_topic_score_gemma":0.0000039579613,"teacher_disagreement_score":0.7981029,"about_ca_system_score_codex":0.0002612479,"about_ca_system_score_gemma":0.00097621843,"threshold_uncertainty_score":0.99978864},"labels":[],"label_agreement":null},{"id":"W1593942753","doi":"10.1007/978-3-642-16612-9_15","title":"Clara: A Framework for Partially Evaluating Finite-State Runtime Monitors Ahead of Time","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"","keywords":"Computer science; Runtime verification; AspectJ; Compile time; Compiler; Residual; Static analysis; State (computer science); Runtime system; Property (philosophy); Programming language; Distributed computing; Aspect-oriented programming; Formal verification; Software; Algorithm","score_opus":0.034323428866062475,"score_gpt":0.3122384992071882,"score_spread":0.2779150703411257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593942753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003343325,0.00022531956,0.99509835,0.00030648356,0.0013156602,0.00068815704,0.000013683504,0.0018670722,0.00015091054],"genre_scores_gemma":[0.040593736,0.000009661749,0.95834166,0.00044744954,0.000388946,0.00003546349,0.000004217802,0.000050520845,0.00012832003],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99588615,0.000049527604,0.0008014248,0.0014429846,0.0010745174,0.00074537826],"domain_scores_gemma":[0.9911831,0.005572352,0.00068144803,0.0017558067,0.00064550206,0.00016181153],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023470481,0.00056337257,0.0007485481,0.0007376799,0.00030023843,0.00037836636,0.0034940408,0.00058176334,0.000012572197],"category_scores_gemma":[0.0027842438,0.00052749383,0.00022622639,0.0006015964,0.00073893915,0.00034204443,0.001102364,0.0012439684,0.00002565282],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024907642,0.000066841276,0.00026039357,0.00012729639,0.000027495193,0.0000387547,0.0016889174,0.024873078,0.00086125993,0.0052587036,0.000098335695,0.96667403],"study_design_scores_gemma":[0.000114715185,0.0003410521,0.000036937916,0.00079651846,0.000010141052,0.00001622447,1.3311368e-8,0.40463737,0.0036136976,0.5899448,0.000091177106,0.00039735562],"about_ca_topic_score_codex":0.000036522204,"about_ca_topic_score_gemma":0.000008941185,"teacher_disagreement_score":0.96627665,"about_ca_system_score_codex":0.000113586124,"about_ca_system_score_gemma":0.00079953927,"threshold_uncertainty_score":0.99971765},"labels":[],"label_agreement":null},{"id":"W1594634494","doi":"10.1007/978-3-642-04468-7_19","title":"Towards Model-Based Automatic Testing of Attack Scenarios","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","score_opus":0.043578089789563096,"score_gpt":0.28380566725869855,"score_spread":0.24022757746913545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594634494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014168996,0.0001661912,0.9921116,0.0003643517,0.00033468186,0.00033608713,0.0000031287311,0.004007119,0.002535114],"genre_scores_gemma":[0.19083038,0.000001892676,0.8079874,0.0010097867,0.00008908209,0.0000054426,0.0000016492621,0.000027560938,0.000046836918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960629,0.000034737644,0.00074536353,0.001322505,0.001178969,0.00065554556],"domain_scores_gemma":[0.9958973,0.0010407745,0.00053961744,0.0018560598,0.00050128775,0.00016494497],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011866083,0.0005777329,0.0007259929,0.0010277611,0.00019261503,0.00030501612,0.0038804205,0.00034005317,0.000004059602],"category_scores_gemma":[0.0009059872,0.0005348062,0.00015528368,0.0009801731,0.00059355237,0.00034856232,0.0007991444,0.0007158501,0.000008276922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010130364,0.000026501597,0.00006563299,0.000063702435,0.0000027731544,0.000025391531,0.00014458912,0.21886402,0.000030883723,0.0007357085,0.0000510758,0.7799887],"study_design_scores_gemma":[0.000112379326,0.00019884975,0.00009541392,0.001158366,0.000006623537,0.000029154957,5.4873683e-9,0.7433535,0.0008507242,0.25375912,0.000021860715,0.00041401945],"about_ca_topic_score_codex":0.000035288864,"about_ca_topic_score_gemma":0.0000064623337,"teacher_disagreement_score":0.7795747,"about_ca_system_score_codex":0.00027648726,"about_ca_system_score_gemma":0.0016229962,"threshold_uncertainty_score":0.9997103},"labels":[],"label_agreement":null},{"id":"W1595781181","doi":"10.1007/978-3-642-02818-2_21","title":"Script InSight: Using Models to Explore JavaScript Code from the Browser View","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"JavaScript; Computer science; Unobtrusive JavaScript; Java; Rich Internet application; Tracing; World Wide Web; Scripting language; Context (archaeology); Programming language; Web application; Source code; Code (set theory); Software engineering","score_opus":0.11687458812616955,"score_gpt":0.2886179972318393,"score_spread":0.17174340910566974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595781181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011062554,0.0020623477,0.9900233,0.0018018091,0.0015088716,0.00058802025,0.000009160569,0.0028308085,0.0010650598],"genre_scores_gemma":[0.04569759,0.00006021407,0.934331,0.019040337,0.0006635544,0.000015817901,0.0000054394195,0.00006265033,0.00012338611],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950074,0.00008316643,0.00067131745,0.0020412875,0.0013446562,0.00085219066],"domain_scores_gemma":[0.99536055,0.00083275064,0.00028570087,0.0028838462,0.00036550203,0.00027164022],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009666588,0.0007593434,0.0007129804,0.00058212935,0.0005374888,0.0011441627,0.0064666644,0.00035164837,0.000008485133],"category_scores_gemma":[0.00021338393,0.0005689731,0.00018655264,0.0010073831,0.0004516929,0.0008875731,0.0021252413,0.0010177146,0.00003421837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051548236,0.000028827619,0.000035708486,0.000012716533,0.000013319689,0.0000846371,0.0051879324,0.049981937,0.00009784389,0.004406129,0.0012898429,0.93885595],"study_design_scores_gemma":[0.00008546317,0.00009539318,0.000035705445,0.000987167,0.000010883863,0.000043675154,1.3852784e-7,0.44990593,0.00035796946,0.5439788,0.0039169393,0.0005819162],"about_ca_topic_score_codex":0.00037291882,"about_ca_topic_score_gemma":0.00008522025,"teacher_disagreement_score":0.938274,"about_ca_system_score_codex":0.0003807572,"about_ca_system_score_gemma":0.00056493643,"threshold_uncertainty_score":0.9998928},"labels":[],"label_agreement":null},{"id":"W1598641709","doi":"10.1007/978-3-540-73066-8_23","title":"An EFSM-Based Passive Fault Detection Approach","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Government of Ontario","keywords":"Computer science; Extended finite-state machine; Fault detection and isolation; Fault (geology); Finite-state machine; Artificial intelligence; Algorithm","score_opus":0.027082481015822873,"score_gpt":0.2738637657798862,"score_spread":0.24678128476406333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1598641709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004635974,0.000099267956,0.990853,0.00009496918,0.0009609649,0.00038565407,0.0000025378868,0.0055218595,0.0020354043],"genre_scores_gemma":[0.27625874,0.0000026374387,0.7220569,0.001242999,0.00034686102,0.000013837555,0.0000061808128,0.000037253005,0.000034573637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99558735,0.000053413492,0.0005019001,0.0019263364,0.0011646003,0.0007664237],"domain_scores_gemma":[0.9962493,0.0006904265,0.0003472533,0.0020694744,0.0003889799,0.00025453308],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012971819,0.0006071472,0.00048724806,0.0013888074,0.00037276096,0.0006755381,0.0035932679,0.0005399847,0.0000042202228],"category_scores_gemma":[0.0002204487,0.0005636685,0.00013929131,0.0009170391,0.0006257887,0.0005850997,0.00050731463,0.0010690393,0.000017003758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053127583,0.00004915695,0.000049784194,0.00002682067,0.000003928976,0.000054308846,0.00021081482,0.020888207,0.00009433699,0.0013825368,0.000020593436,0.9772142],"study_design_scores_gemma":[0.0001677162,0.00034791924,0.00011877166,0.0001986707,0.000006346905,0.00008479208,3.7237292e-8,0.83740926,0.004858955,0.15580219,0.00030846725,0.0006969043],"about_ca_topic_score_codex":0.000071077724,"about_ca_topic_score_gemma":0.00003429395,"teacher_disagreement_score":0.9765173,"about_ca_system_score_codex":0.00040882433,"about_ca_system_score_gemma":0.0004809331,"threshold_uncertainty_score":0.9996815},"labels":[],"label_agreement":null},{"id":"W1601589757","doi":"10.1007/978-3-540-24723-4_19","title":"Integrating the Soot Compiler Infrastructure into an IDE","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Compiler; Computer science; Debugging; Eclipse; Software engineering; Programming language; Byte; Development environment","score_opus":0.015372989434315964,"score_gpt":0.2634255679722774,"score_spread":0.24805257853796142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601589757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014398084,0.0002447307,0.9919192,0.0010916761,0.0013182146,0.00038033247,0.0000023408127,0.003453677,0.0014458216],"genre_scores_gemma":[0.2656575,0.000009588684,0.73081416,0.0029301995,0.0004913172,0.000012059637,0.0000054298466,0.00004230474,0.00003742427],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99583966,0.00007182338,0.0006127105,0.0016496072,0.0011023358,0.0007238839],"domain_scores_gemma":[0.99571174,0.0008906063,0.0003871768,0.0024709646,0.00033847618,0.00020103143],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013031195,0.0007076012,0.00054535846,0.00062829745,0.0007140574,0.0012073508,0.006665409,0.0004070129,0.000019275698],"category_scores_gemma":[0.0004026521,0.0004890643,0.00014442918,0.0007741208,0.0011912136,0.00077881647,0.001960531,0.0017995415,0.000019905008],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002989876,0.000019290568,0.00025603254,0.00002874345,0.000008564763,0.000058708705,0.0031812352,0.01921997,0.000054666954,0.05692877,0.00018235255,0.92005867],"study_design_scores_gemma":[0.000113848044,0.00018102193,0.00029631588,0.00052652875,0.0000057456377,0.00012066511,2.0996859e-7,0.16676179,0.0003531084,0.8305943,0.000494169,0.0005522796],"about_ca_topic_score_codex":0.00022442602,"about_ca_topic_score_gemma":0.00013875209,"teacher_disagreement_score":0.9195064,"about_ca_system_score_codex":0.00053010276,"about_ca_system_score_gemma":0.0009892096,"threshold_uncertainty_score":0.9998295},"labels":[],"label_agreement":null},{"id":"W1601919490","doi":"10.1007/978-3-540-76650-6_11","title":"Reducing Test Sequence Length Using Invertible Sequences","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Invertible matrix; Sequence (biology); Computer science; Finite-state machine; Conformance testing; Context (archaeology); Test (biology); Algorithm; Fault coverage; State (computer science); Mathematics; Engineering","score_opus":0.08039159151183822,"score_gpt":0.312587205035642,"score_spread":0.2321956135238038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601919490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026371266,0.00050152483,0.99102116,0.0002439192,0.0012931278,0.0003284523,0.000004548197,0.004015001,0.002328544],"genre_scores_gemma":[0.15431824,0.000035092587,0.8437412,0.0012850664,0.0004374019,0.00000452681,0.0000025318081,0.000049529495,0.00012643544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99458975,0.000038538947,0.00077525305,0.0021264853,0.0013554322,0.0011145486],"domain_scores_gemma":[0.995018,0.0018620729,0.00048335528,0.001954842,0.00041020854,0.0002714903],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022352256,0.00073185185,0.0006492202,0.0015196836,0.00052274734,0.000810998,0.0044842153,0.00047268436,0.000010307599],"category_scores_gemma":[0.0009890854,0.000697189,0.00014624877,0.0014004941,0.0012306031,0.0010252756,0.0016176197,0.0009694718,0.00002737946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033845754,0.000045220215,0.0011249848,0.00009009122,0.000011758967,0.00047574312,0.0009337344,0.021625107,0.0017525281,0.004715927,0.00009670363,0.9691248],"study_design_scores_gemma":[0.00010297236,0.00019235266,0.00004097819,0.0014711303,0.000009470936,0.0004904428,6.957388e-8,0.62237793,0.006589961,0.36751944,0.00025266435,0.0009525994],"about_ca_topic_score_codex":0.00034736074,"about_ca_topic_score_gemma":0.00004316669,"teacher_disagreement_score":0.9681722,"about_ca_system_score_codex":0.00079904916,"about_ca_system_score_gemma":0.0013389001,"threshold_uncertainty_score":0.9995479},"labels":[],"label_agreement":null},{"id":"W1602279527","doi":"10.1007/11902140_106","title":"Test Suite Reduction Based on Dependence Analysis","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test suite; Computer science; Java; Test case; Suite; Equivalence (formal languages); Programming language; Test (biology); Algorithm; Mathematics; Machine learning; Discrete mathematics","score_opus":0.01573036673521473,"score_gpt":0.24977390180548278,"score_spread":0.23404353507026807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602279527","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027834938,0.000083147796,0.9915679,0.0004779805,0.0006862569,0.0002601648,0.0000066375237,0.0035874438,0.003302604],"genre_scores_gemma":[0.44757575,0.000004106849,0.55102074,0.00074890116,0.00028163116,0.000011893471,0.00001195103,0.000028834795,0.00031620738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541485,0.000040846655,0.0005296732,0.0019854899,0.0013848165,0.0006443147],"domain_scores_gemma":[0.99537015,0.0015624948,0.00037235994,0.0022373404,0.0003092406,0.00014842697],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011382453,0.0005796823,0.00058999844,0.002595135,0.00031490743,0.0006674527,0.0031482638,0.00035304893,0.000012035245],"category_scores_gemma":[0.0004411758,0.000542774,0.0002576946,0.0024272955,0.00049900945,0.00038017056,0.0005552477,0.0008363771,0.000029948462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006337731,0.000120572884,0.0025629988,0.000033409906,0.000027461789,0.00015877307,0.0001189528,0.46908945,0.00007133067,0.001880533,0.0007348878,0.5251953],"study_design_scores_gemma":[0.000105742,0.00023125,0.0009843732,0.0002708552,0.00004234145,0.000036632093,6.8798025e-9,0.870444,0.0009307788,0.12615424,0.00017191446,0.00062784366],"about_ca_topic_score_codex":0.00015408017,"about_ca_topic_score_gemma":0.000040825893,"teacher_disagreement_score":0.5245675,"about_ca_system_score_codex":0.00042319068,"about_ca_system_score_gemma":0.00045855978,"threshold_uncertainty_score":0.9997024},"labels":[],"label_agreement":null},{"id":"W1603540703","doi":"","title":"Proceedings of the ACM SIGPLAN International Workshop on State of the Art in Java Program analysis","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Java; Computer science; State (computer science); Programming language; Software engineering","score_opus":0.02634602667210924,"score_gpt":0.295679964043182,"score_spread":0.26933393737107275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603540703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9597576,0.000021765009,0.017141161,0.0051277047,0.00034845676,0.0005544828,0.0000028376621,0.0020599451,0.014986006],"genre_scores_gemma":[0.9355128,0.0000011792367,0.06395331,0.00014430625,0.00001163247,0.000015806869,2.896384e-7,0.0000026785804,0.0003580223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992609,0.000014232637,0.00018631537,0.000119934055,0.0002881739,0.00013046259],"domain_scores_gemma":[0.9991091,0.0001723643,0.00014437923,0.0004631713,0.00009066954,0.000020341262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041885843,0.000063720574,0.00010060247,0.00012460996,0.000022415114,0.000025550828,0.0018235578,0.000022082651,0.0000046165014],"category_scores_gemma":[0.0006908695,0.000032829266,0.00008083003,0.0010833076,0.00004663441,0.0001336657,0.000609526,0.00009842145,0.0000014406522],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050090694,0.0002587118,0.93293643,0.000007121658,0.000057769837,1.02832566e-7,0.0009943546,0.000066975386,0.000112868714,0.0036476792,0.011863337,0.050049614],"study_design_scores_gemma":[0.00013979796,0.000059664868,0.9335878,0.00016957281,0.000034338456,0.0000037571701,0.000022201471,0.024561541,0.014171813,0.025946379,0.0011516142,0.0001515579],"about_ca_topic_score_codex":0.000036096306,"about_ca_topic_score_gemma":0.000012661434,"teacher_disagreement_score":0.04989806,"about_ca_system_score_codex":0.000020762778,"about_ca_system_score_gemma":0.000014291129,"threshold_uncertainty_score":0.33886546},"labels":[],"label_agreement":null},{"id":"W1607747749","doi":"","title":"Specification-based regression test selection with risk analysis","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Regression testing; Computer science; Test suite; Test Management Approach; Test case; Regression analysis; Traceability; Risk-based testing; Data mining; Unified Modeling Language; Reliability engineering; Machine learning; Software engineering; Programming language; Software; Engineering; Software development","score_opus":0.019136167122428327,"score_gpt":0.22858352951678404,"score_spread":0.2094473623943557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607747749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023573306,0.000018104649,0.98512757,0.0005153825,0.000014256623,0.000055597673,5.394043e-7,0.008956606,0.0029545918],"genre_scores_gemma":[0.5906422,0.0000036628196,0.40881497,0.00009377509,0.00001583267,0.000008142538,0.0000011475448,0.000003448908,0.0004168358],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992281,0.00003755043,0.00011299675,0.00029868612,0.00019823271,0.00012440489],"domain_scores_gemma":[0.99887234,0.00040543228,0.000103530445,0.00046320911,0.000107127235,0.000048347723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001540663,0.00008893486,0.00009844838,0.00025204956,0.00015906857,0.00010431168,0.00028538037,0.000033878423,0.0000894202],"category_scores_gemma":[0.00020274468,0.000059602993,0.000043835655,0.0019827187,0.000019807505,0.00013257994,0.000019349054,0.00008629404,0.000039421007],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019105485,0.00017689228,0.9091217,0.0000030504805,0.000038896393,0.000003385313,0.00008358416,0.0011859733,0.00006006388,0.0005285446,0.039395526,0.049400464],"study_design_scores_gemma":[0.00008677049,0.00011331191,0.050805207,0.000011868498,0.00004456945,0.0000034885388,6.87823e-7,0.9452366,0.0021056118,0.0010040831,0.0004625999,0.00012518447],"about_ca_topic_score_codex":0.00011780933,"about_ca_topic_score_gemma":0.000025330353,"teacher_disagreement_score":0.94405067,"about_ca_system_score_codex":0.000031255604,"about_ca_system_score_gemma":0.000010809882,"threshold_uncertainty_score":0.24305394},"labels":[],"label_agreement":null},{"id":"W1618890699","doi":"10.1007/3-540-44830-6_12","title":"Generating Checking Sequences for a Distributed Test Architecture","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observability; Controllability; Computer science; Sequence (biology); Communication source; Test (biology); Current (fluid); Sequence diagram; Algorithm; Programming language; Mathematics; Software; Unified Modeling Language; Telecommunications; Engineering","score_opus":0.02648434062110274,"score_gpt":0.26619954363372705,"score_spread":0.2397152030126243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1618890699","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027750686,0.00045555676,0.9938212,0.00094172667,0.0009030253,0.0005967915,0.000031516687,0.0028981115,0.00032432185],"genre_scores_gemma":[0.02489534,0.0000107901415,0.97225934,0.0021838997,0.00044506375,0.00004886249,0.000019113502,0.00004785462,0.00008971941],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959381,0.000034919034,0.0005981086,0.0017810975,0.00076059066,0.00088718336],"domain_scores_gemma":[0.99532706,0.002384258,0.00040918987,0.0013422942,0.00036005373,0.00017717828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012887118,0.00065890147,0.0006055754,0.0006358571,0.0005516656,0.0008970287,0.0030436448,0.00037985496,0.0000039613537],"category_scores_gemma":[0.0016848474,0.00059058756,0.00018664084,0.00070564955,0.00055404584,0.00032788437,0.00071064394,0.00082184124,0.0000041817116],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033218905,0.000040859974,0.00031761682,0.000117487696,0.000014719572,0.00007623302,0.0006264025,0.055194963,0.0005154709,0.005136663,0.00052671926,0.93742955],"study_design_scores_gemma":[0.0001822323,0.00023726086,0.000015685164,0.00064737874,0.000009314993,0.00018148865,4.1618495e-8,0.44953656,0.0021580437,0.5444542,0.0017796932,0.0007981124],"about_ca_topic_score_codex":0.000020852809,"about_ca_topic_score_gemma":0.000022648228,"teacher_disagreement_score":0.93663144,"about_ca_system_score_codex":0.00031639799,"about_ca_system_score_gemma":0.0005524714,"threshold_uncertainty_score":0.99965453},"labels":[],"label_agreement":null},{"id":"W1623765515","doi":"10.1109/qsic.2004.8","title":"Antipattern-based detection of deficiencies in Java multithreaded software","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Computer Research Institute of Montréal","funders":"","keywords":"Multithreading; Java; Computer science; Programming language; Template; Software; Real time Java; Operating system; Software engineering; Computer architecture; Thread (computing)","score_opus":0.019939213965241606,"score_gpt":0.24618437800177057,"score_spread":0.22624516403652895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1623765515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24799925,0.000023912913,0.7484376,0.000076317694,0.0000554418,0.00006844382,3.8854603e-7,0.0032834697,0.000055214983],"genre_scores_gemma":[0.6724721,5.534311e-7,0.32738876,0.00012001631,0.0000037843756,0.000006703855,2.8763282e-7,0.000003830548,0.000003952831],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917686,0.00002096329,0.0002029742,0.00023689092,0.00018386183,0.00017847706],"domain_scores_gemma":[0.99932134,0.00015315678,0.000068296824,0.00036291525,0.00006514471,0.00002916262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021422021,0.00009329671,0.00012425735,0.00022798467,0.00003846657,0.000030463685,0.0003969431,0.000051804087,0.0000017896742],"category_scores_gemma":[0.00028907505,0.00008299918,0.00003973098,0.00050645747,0.000047639103,0.00015654249,0.000063817075,0.00007836102,0.0000065745885],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037063204,0.001242931,0.50663996,0.00024563514,0.0000137192255,0.00009020268,0.0028533177,0.021365078,0.059242498,0.0044132187,0.00026259007,0.40359378],"study_design_scores_gemma":[0.0011532906,0.00034698597,0.1101454,0.00025227887,0.000003460924,0.000021535025,0.000015292153,0.048944563,0.8027313,0.035984114,0.000020815474,0.00038096606],"about_ca_topic_score_codex":0.0012152891,"about_ca_topic_score_gemma":0.00014297677,"teacher_disagreement_score":0.7434888,"about_ca_system_score_codex":0.000051785282,"about_ca_system_score_gemma":0.00006917551,"threshold_uncertainty_score":0.3384608},"labels":[],"label_agreement":null},{"id":"W163528057","doi":"10.1007/978-3-319-11743-0_11","title":"Acceptance Test Optimization","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Redundancy (engineering); Integration testing; Test (biology); Test case; System under test; Acceptance testing; Test Management Approach; Reliability engineering; Test strategy; System testing; Programming language; Software; Software engineering; Machine learning; Software system; Engineering; Operating system; Software construction","score_opus":0.01633792998939871,"score_gpt":0.24762005690595135,"score_spread":0.23128212691655264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W163528057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018084096,0.0001883898,0.98934174,0.0005236647,0.000985715,0.00024727147,0.0000019946178,0.004464032,0.004245387],"genre_scores_gemma":[0.040859595,0.000027339018,0.95656174,0.001702485,0.0004005969,0.00001026585,0.0000039116026,0.00003904803,0.00039500507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966632,0.000025029927,0.00045508696,0.0014691985,0.00081888767,0.0005685668],"domain_scores_gemma":[0.99606127,0.0013802117,0.00032126534,0.0017901269,0.0002996606,0.00014744897],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009023633,0.000485532,0.00045228523,0.0007094791,0.00025351028,0.0006526917,0.0037760404,0.00031892664,0.00002020785],"category_scores_gemma":[0.0008246322,0.00045978054,0.00009874375,0.00063782005,0.00048370738,0.0004107244,0.0011628438,0.00063840824,0.000043187978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010631646,0.000016917758,0.00023870319,0.000024605859,0.0000028239836,0.000027390357,0.00014371233,0.13362005,0.000009547646,0.0066314866,0.00035755284,0.8589261],"study_design_scores_gemma":[0.00008998152,0.00012552702,0.000055880017,0.0003466209,0.000003362814,0.00005503009,3.8334536e-9,0.7722825,0.00024581826,0.22549553,0.00080235716,0.0004973916],"about_ca_topic_score_codex":0.000013677026,"about_ca_topic_score_gemma":0.0000076215442,"teacher_disagreement_score":0.8584287,"about_ca_system_score_codex":0.00023435477,"about_ca_system_score_gemma":0.00033459632,"threshold_uncertainty_score":0.99978536},"labels":[],"label_agreement":null},{"id":"W1637346","doi":"10.5753/sbac-pad.2001.22210","title":"Using the SGI Pro64 Open Source Compiler Infra-Structure for Teaching and Research","year":2001,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Compiler; Computer science; Suite; Compiler construction; Compiler correctness; Interprocedural optimization; Class (philosophy); Optimizing compiler; Programming language; Source code; Parallel computing; Loop optimization; Artificial intelligence","score_opus":0.1797832101432179,"score_gpt":0.43337448754289815,"score_spread":0.25359127739968024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1637346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040219147,0.000042784133,0.9532687,0.0018205419,0.00005144967,0.00063239026,9.994537e-7,0.0018424449,0.0021215319],"genre_scores_gemma":[0.38240007,0.0000010310785,0.6163377,0.00058321346,0.000063354004,0.00002049448,6.54365e-7,0.000009354366,0.00058412587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988234,0.00021624519,0.00012557412,0.0003125918,0.00021914057,0.00030303],"domain_scores_gemma":[0.9981331,0.0011238176,0.00003900116,0.00052975584,0.00012067427,0.000053632873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022187608,0.00009144952,0.000106883985,0.000078501515,0.0010508876,0.00087245833,0.0014263821,0.000051757175,0.0000048161573],"category_scores_gemma":[0.0006890005,0.000056427736,0.000018764245,0.00023524083,0.000113513335,0.00033158288,0.0013175593,0.0003923214,8.4483975e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041607025,0.00009334728,0.023618666,0.00005936027,0.000035531684,0.000012198993,0.009863192,0.00026455926,0.0017022456,0.08645667,0.25857732,0.6192753],"study_design_scores_gemma":[0.00041184793,0.00018395657,0.0011486893,0.0001206104,0.000005933985,0.00031343644,0.00014904185,0.58952844,0.00089248474,0.30075374,0.10617614,0.0003157168],"about_ca_topic_score_codex":0.00061782065,"about_ca_topic_score_gemma":0.00001505401,"teacher_disagreement_score":0.61895955,"about_ca_system_score_codex":0.000026938536,"about_ca_system_score_gemma":0.00005536287,"threshold_uncertainty_score":0.84131354},"labels":[],"label_agreement":null},{"id":"W1647188876","doi":"10.1007/978-90-481-3660-5_48","title":"A Survey of Using Model-Based Testing to Improve Quality Attributes in Distributed Systems","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Correctness; Computer science; Reliability engineering; Reliability (semiconductor); Conformance testing; Quality (philosophy); Engineering; Programming language; Operating system; Standardization","score_opus":0.17022237723475778,"score_gpt":0.33347656235550827,"score_spread":0.1632541851207505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1647188876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045811525,0.00013076316,0.99090946,0.000036637837,0.00011380973,0.0005425656,0.0003301369,0.0038218272,0.003656669],"genre_scores_gemma":[0.46577024,0.0000010267754,0.53082424,0.00018966976,0.000040496463,0.000019188159,0.00012478948,0.000056951525,0.0029733535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970343,0.00013443209,0.0010936264,0.0008191726,0.00050590746,0.00041257663],"domain_scores_gemma":[0.9951332,0.0019979961,0.0005983901,0.0012341727,0.00088801264,0.000148193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002574438,0.00043805668,0.0009148148,0.00040400674,0.00006310343,0.00014006304,0.0010793514,0.0003440011,0.000001043763],"category_scores_gemma":[0.0027580732,0.0004274565,0.00009826883,0.0004154573,0.00004712042,0.00012399195,0.00031694875,0.00033690108,0.0000029062883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015294513,0.0006929846,0.088195376,0.0021864523,0.00016209378,0.00017979718,0.0003176713,0.6642751,0.0016595301,0.09370232,0.010001115,0.13847458],"study_design_scores_gemma":[0.00017155905,0.00012921385,0.00338978,0.0011028025,0.000008655541,0.0000034162595,2.876014e-7,0.98095286,0.00011439809,0.013545602,0.000022766219,0.00055864867],"about_ca_topic_score_codex":0.008595604,"about_ca_topic_score_gemma":0.000148491,"teacher_disagreement_score":0.46531215,"about_ca_system_score_codex":0.00029397075,"about_ca_system_score_gemma":0.0005432446,"threshold_uncertainty_score":0.9998177},"labels":[],"label_agreement":null},{"id":"W1656270692","doi":"10.1007/978-3-642-36757-1_2","title":"Identification and Selection of Interaction Test Scenarios for Integration Testing","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Integration testing; Unit testing; Computer science; Interoperability; Test (biology); Context (archaeology); Test case; Test Management Approach; Identification (biology); Model-based testing; Reliability engineering; Data mining; Machine learning; Programming language; Engineering; Software; Software development; Software construction; Operating system","score_opus":0.030546618663785892,"score_gpt":0.2768479638866936,"score_spread":0.2463013452229077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1656270692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039544582,0.000051622887,0.9973476,0.0001738848,0.000408022,0.00052521663,0.000002166833,0.00094852794,0.00014752476],"genre_scores_gemma":[0.42186302,0.0000051898724,0.577826,0.0000819826,0.0001119636,0.000026230662,0.0000025946802,0.000014051934,0.000068922236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981509,0.000016112874,0.00048349693,0.0007914585,0.000326,0.00023202715],"domain_scores_gemma":[0.99638015,0.001970367,0.0005019572,0.00038145366,0.0007124221,0.000053623946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007535449,0.0002537494,0.0002706246,0.0006664352,0.00017904754,0.0003887609,0.0006957392,0.00018557232,0.000002275381],"category_scores_gemma":[0.0017941482,0.00023928672,0.00004583928,0.0004435019,0.00021845277,0.0007193503,0.0002500207,0.0003175104,0.000003325024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019058286,0.00001889519,0.00034555528,0.000056152465,0.000002745651,4.7461273e-7,0.00023824029,0.0014908097,0.0056304834,0.0014867845,0.000064742606,0.99066323],"study_design_scores_gemma":[0.000073697716,0.00022256482,0.00047578232,0.00053353445,0.0000061350215,0.00004048941,6.616505e-8,0.79420936,0.009770604,0.1944255,0.00003132815,0.0002109642],"about_ca_topic_score_codex":0.00006346575,"about_ca_topic_score_gemma":0.000019995516,"teacher_disagreement_score":0.99045223,"about_ca_system_score_codex":0.00016775391,"about_ca_system_score_gemma":0.00017041306,"threshold_uncertainty_score":0.97578293},"labels":[],"label_agreement":null},{"id":"W1672898643","doi":"10.1002/smr.1559","title":"Regression test suite selection using dependence analysis","year":2012,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test suite; Regression testing; Computer science; Suite; Test case; Data mining; Representation (politics); Process (computing); Regression analysis; Machine learning; Software; Software system; Programming language","score_opus":0.024025132744568693,"score_gpt":0.30849297701315503,"score_spread":0.28446784426858635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1672898643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12749681,0.0014247705,0.8702408,0.000049081886,0.00014872078,0.000034812692,6.599993e-7,0.0005950492,0.000009295192],"genre_scores_gemma":[0.8026327,0.000019992389,0.19715859,0.00004350131,0.00012344116,9.324397e-7,2.9226814e-7,0.000005062876,0.000015502008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99888164,0.000057713645,0.0003205231,0.00014209357,0.0003693137,0.00022871367],"domain_scores_gemma":[0.99843997,0.00029659522,0.00048018814,0.00012826531,0.00049314735,0.00016183525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008666534,0.00011863979,0.00021510996,0.0004644123,0.00021334906,0.000095444055,0.00027163682,0.00008342952,0.000004795181],"category_scores_gemma":[0.0012216745,0.000092540446,0.000083015824,0.0013158799,0.000032816824,0.0013963402,0.000060361843,0.00021027803,0.0000010703328],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007866474,0.000070683884,0.98960096,0.00003282799,0.000039885377,0.000002774272,0.0003706337,0.00024759123,0.00017124352,0.00008570749,0.00034531447,0.009024533],"study_design_scores_gemma":[0.0007430617,0.000581054,0.79814535,0.0007891034,0.00075557793,0.0035200834,0.00008055542,0.1593345,0.0037523175,0.031131828,0.0003363464,0.0008302288],"about_ca_topic_score_codex":0.000023148057,"about_ca_topic_score_gemma":0.000001996572,"teacher_disagreement_score":0.67513585,"about_ca_system_score_codex":0.00010016018,"about_ca_system_score_gemma":0.00010997054,"threshold_uncertainty_score":0.377369},"labels":[],"label_agreement":null},{"id":"W1724543665","doi":"10.1007/978-3-642-05031-2_3","title":"Testing k-Safe Petri Nets","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Petri net; Computer science; Conformance testing; Formal specification; Programming language; Formal methods; Process architecture; Finite-state machine; Formal verification; Theoretical computer science; Operating system","score_opus":0.03099014295615103,"score_gpt":0.2624275698264454,"score_spread":0.23143742687029434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724543665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018366743,0.00046695498,0.9773161,0.0007740016,0.0010010125,0.00028414125,0.0000016209406,0.005742859,0.014394947],"genre_scores_gemma":[0.043768533,0.0000107869755,0.95237803,0.0029266546,0.0004492493,0.0000059470676,0.0000023899204,0.000038332557,0.0004200424],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99549896,0.00003555194,0.0005971896,0.0018373263,0.0011376496,0.0008933328],"domain_scores_gemma":[0.99534464,0.0017086597,0.0003695844,0.0019585786,0.0003909816,0.00022754134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012223542,0.00065351627,0.0005961014,0.0011428946,0.00036095077,0.0007832756,0.0045391642,0.0003745154,0.000008503565],"category_scores_gemma":[0.0011041767,0.0006176058,0.00012920113,0.0012279832,0.00048236907,0.00054121565,0.0013746355,0.0010777791,0.0000613045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011851739,0.000016931184,0.00017128458,0.000013023429,0.0000028389707,0.0001403334,0.00013055265,0.0025511493,0.000029690747,0.0030192044,0.00027973278,0.99364406],"study_design_scores_gemma":[0.00013532458,0.00030218204,0.0006518925,0.0008021158,0.0000055621204,0.0002801316,7.670215e-9,0.2640119,0.00037302193,0.7304015,0.0021996521,0.00083668716],"about_ca_topic_score_codex":0.00004593626,"about_ca_topic_score_gemma":0.000008593782,"teacher_disagreement_score":0.9928074,"about_ca_system_score_codex":0.00031773886,"about_ca_system_score_gemma":0.0006655377,"threshold_uncertainty_score":0.99962753},"labels":[],"label_agreement":null},{"id":"W172667635","doi":"","title":"An Algebraic Query Method for Static Program Analysis and Measurement.","year":2008,"lang":"en","type":"article","venue":"Software Engineering and Data Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Query optimization; Query language; Algebraic number; Programming language; Theoretical computer science; Information retrieval; Mathematics","score_opus":0.04551195105983421,"score_gpt":0.3039288780590528,"score_spread":0.2584169269992186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W172667635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077169277,0.00070573814,0.9794314,0.000026770278,0.00010270953,0.00027532692,0.000043222164,0.011697293,5.977981e-7],"genre_scores_gemma":[0.13564023,0.000043765674,0.864017,0.000028702305,0.000052987627,0.00009910111,0.00008074271,0.00003512077,0.0000023496707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982553,0.000021983664,0.0002805321,0.0007447686,0.00028512927,0.00041228096],"domain_scores_gemma":[0.9978941,0.0005210312,0.00005475144,0.0012050401,0.00009874179,0.00022629797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094900845,0.0002852155,0.0003616084,0.00043205338,0.00014296819,0.00014207565,0.0007274965,0.000083985564,5.6104267e-7],"category_scores_gemma":[0.0015236347,0.00029414674,0.000051418818,0.0007063431,0.000020535792,0.0007299885,0.00029961503,0.00016573275,3.9270597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003765783,0.0006423058,0.06491062,0.0029725768,0.003284759,0.00021614159,0.0034710688,0.21376614,0.0032605194,0.0048851166,0.0066033383,0.69594973],"study_design_scores_gemma":[0.00018749996,0.00012632455,0.009031465,0.000058719455,0.00011712279,0.00007401121,0.0000019220247,0.9885877,0.0001819017,0.00016130753,0.0010845066,0.0003875426],"about_ca_topic_score_codex":0.000074813375,"about_ca_topic_score_gemma":0.0000035025857,"teacher_disagreement_score":0.7748215,"about_ca_system_score_codex":0.000033853885,"about_ca_system_score_gemma":0.000041435105,"threshold_uncertainty_score":0.99995106},"labels":[],"label_agreement":null},{"id":"W1748160142","doi":"","title":"Clara: partially evaluating runtime monitors at compile time tutorial supplement","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"AspectJ; Computer science; Compile time; Compiler; Runtime verification; Static analysis; Runtime system; Context (archaeology); Programming language; Property (philosophy); Residual; State (computer science); Aspect-oriented programming; Software; Formal verification; Algorithm","score_opus":0.021986125714112147,"score_gpt":0.3046886914802215,"score_spread":0.28270256576610936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1748160142","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7010349,0.000045556768,0.23138765,0.0029779887,0.009239316,0.0010354734,0.000015522182,0.046566322,0.0076972917],"genre_scores_gemma":[0.47874883,4.7636183e-7,0.5192084,0.00018681498,0.000680899,0.00003576146,0.000009132242,0.000014900134,0.0011148378],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981723,0.00008049174,0.00032754263,0.00046531975,0.0005415521,0.00041281327],"domain_scores_gemma":[0.9984035,0.00040397584,0.0001117404,0.00081017794,0.00013366202,0.00013697548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010779431,0.0001875622,0.00019400631,0.000078922305,0.0003023133,0.00022217832,0.00090295024,0.000104212144,0.00060463883],"category_scores_gemma":[0.0003456647,0.00016470977,0.00007843103,0.000209981,0.00005374772,0.00023897528,0.0007032731,0.00025327282,0.00066814455],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029309036,0.00025272806,0.026985975,0.0000149084435,0.000046642923,0.00002873924,0.0010756939,0.00008009508,0.060438517,0.012645588,0.8657346,0.032667227],"study_design_scores_gemma":[0.002267123,0.0013987988,0.009923282,0.00009396523,0.0000612749,0.00014528906,0.0000077508585,0.7561748,0.10086374,0.07223956,0.05496391,0.0018605068],"about_ca_topic_score_codex":0.00015326263,"about_ca_topic_score_gemma":0.000018356312,"teacher_disagreement_score":0.8107707,"about_ca_system_score_codex":0.000057380345,"about_ca_system_score_gemma":0.000103523416,"threshold_uncertainty_score":0.85878694},"labels":[],"label_agreement":null},{"id":"W1757839379","doi":"10.1007/978-3-642-23716-4_19","title":"Divide-by-Zero Exception Raising via Branch Coverage","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Testability; Hill climbing; Simulated annealing; Computer science; Genetic programming; Constraint programming; Algorithm; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.02637198270498408,"score_gpt":0.2512384320766876,"score_spread":0.22486644937170353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1757839379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005196416,0.0005329198,0.99049985,0.000213081,0.0014921636,0.00032500137,0.000004789441,0.003796797,0.003083414],"genre_scores_gemma":[0.9617137,0.000044815544,0.036063693,0.0015187932,0.00028021508,0.000010579192,0.000008655055,0.000049089074,0.00031047963],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959328,0.000052547588,0.0005695788,0.0017034849,0.0009767008,0.0007648519],"domain_scores_gemma":[0.9967857,0.00068623445,0.00038688284,0.0017099491,0.00023459557,0.00019663775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011036386,0.00063663203,0.00056542625,0.00072140683,0.00036148875,0.0006347927,0.0031884664,0.00043092744,0.00003432281],"category_scores_gemma":[0.00020711728,0.0006136106,0.00015831164,0.000559889,0.0005858688,0.0008237235,0.0014283252,0.00086011516,0.00006761462],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028218803,0.000022540056,0.00017984456,0.000022675054,0.000005228744,0.000021072081,0.00032384763,0.00038337964,0.00013864401,0.0013033035,0.00087307027,0.9967236],"study_design_scores_gemma":[0.00015217232,0.00015862682,0.00012962041,0.0004836846,0.0000063962084,0.00010330836,3.1650055e-10,0.0019162616,0.0016300072,0.9932732,0.0014405794,0.0007061168],"about_ca_topic_score_codex":0.00013465532,"about_ca_topic_score_gemma":0.000014027864,"teacher_disagreement_score":0.99601746,"about_ca_system_score_codex":0.00040554846,"about_ca_system_score_gemma":0.0002672843,"threshold_uncertainty_score":0.9996315},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W176867143","doi":"10.1007/978-3-642-33119-0_16","title":"Boosting Search Based Testing by Using Constraint Based Testing","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Population; Boosting (machine learning); Selection (genetic algorithm); Constraint (computer-aided design); Test case; Evolutionary computation; Evolutionary algorithm; Mathematical optimization; Machine learning; Algorithm; Mathematics","score_opus":0.07689082099450231,"score_gpt":0.29115087053938743,"score_spread":0.21426004954488512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W176867143","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003077388,0.00047231946,0.99148566,0.00021201343,0.0006658034,0.00048272035,0.000012287,0.004980758,0.0013806758],"genre_scores_gemma":[0.28989258,5.621761e-7,0.7085101,0.001209839,0.00029981448,0.0000070545684,0.000005183056,0.00006217932,0.000012663148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99387515,0.00012117075,0.00085844006,0.001989261,0.0015567237,0.0015992807],"domain_scores_gemma":[0.98886514,0.0076877447,0.0005457011,0.0016961914,0.0007985539,0.00040667193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034567208,0.0008750442,0.0007370238,0.0011170111,0.000803583,0.0010017644,0.0034453068,0.00045734827,0.000013060794],"category_scores_gemma":[0.0032004395,0.00087627495,0.0001396858,0.0016437151,0.0011535147,0.0006254359,0.0013493373,0.0015776143,0.000015187936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002733893,0.00005024745,0.005926311,0.00011858135,0.000006501562,0.000095501025,0.00014740284,0.054417785,0.0020170265,0.00021370623,0.000052357194,0.9369519],"study_design_scores_gemma":[0.00023094918,0.00016137882,0.00011039737,0.0020697834,0.000013588768,0.00015096318,6.337268e-8,0.97456056,0.003992653,0.017635169,0.00007627061,0.0009982231],"about_ca_topic_score_codex":0.00024635336,"about_ca_topic_score_gemma":0.000004593463,"teacher_disagreement_score":0.9359536,"about_ca_system_score_codex":0.0006687248,"about_ca_system_score_gemma":0.0020755415,"threshold_uncertainty_score":0.9993688},"labels":[],"label_agreement":null},{"id":"W1769260096","doi":"10.1007/3-540-45745-3_15","title":"Towards Specification-Based Web Testing","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Web testing; Correctness; Robustness (evolution); Software engineering; Non-regression testing; Web application; Software performance testing; Web modeling; Robustness testing; White-box testing; Reliability engineering; Web service; Programming language; Web application security; Web development; World Wide Web; Software construction; Software development; Software","score_opus":0.04896644395236944,"score_gpt":0.2608482569094928,"score_spread":0.21188181295712338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769260096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011838017,0.00024941302,0.97784454,0.0008859307,0.000922104,0.00029149483,0.000003969351,0.005789808,0.0140009085],"genre_scores_gemma":[0.098817706,0.0000093363315,0.8991173,0.0013642791,0.00041862766,0.000013816291,0.0000030356548,0.00004288862,0.00021301447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590284,0.00003469675,0.00057045603,0.0016870131,0.0011198767,0.00068512507],"domain_scores_gemma":[0.99541837,0.0014980563,0.0003636146,0.002071171,0.0004599931,0.0001887656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009837671,0.0005675999,0.00048331497,0.0010490617,0.0003192609,0.00071199914,0.0041057193,0.000321585,0.000030394405],"category_scores_gemma":[0.0009146662,0.0005413883,0.00012216577,0.001169023,0.0005853147,0.0003523793,0.0007982066,0.00084578345,0.000087688015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010777115,0.000030339046,0.00032067052,0.000029944526,0.0000034446673,0.00007264402,0.0001205777,0.006704781,0.00004162867,0.00490174,0.00037061516,0.98740256],"study_design_scores_gemma":[0.00011984208,0.00011648631,0.00019508705,0.00049393816,0.000004233847,0.000050001086,5.8960095e-9,0.74094385,0.00052614295,0.2556261,0.0013397826,0.00058455503],"about_ca_topic_score_codex":0.00003204423,"about_ca_topic_score_gemma":0.000005839128,"teacher_disagreement_score":0.98681796,"about_ca_system_score_codex":0.00037664062,"about_ca_system_score_gemma":0.0008613099,"threshold_uncertainty_score":0.99970376},"labels":[],"label_agreement":null},{"id":"W1773476055","doi":"10.5281/zenodo.1079180","title":"Generating State-Based Testing Models For Object-Oriented Framework Interface Classes","year":2008,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Interface (matter); Class (philosophy); Implementation; Object-oriented programming; State (computer science); Software; Object (grammar); Programming language; Model-based testing; White-box testing; Test case; Software engineering; Software system; Software construction; Artificial intelligence; Operating system; Machine learning","score_opus":0.07828415661528232,"score_gpt":0.2790379239856586,"score_spread":0.20075376737037626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1773476055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010501155,0.00005094485,0.9725714,0.00023465877,0.00009679675,0.0003673377,0.000032288808,0.013831831,0.0023135908],"genre_scores_gemma":[0.5124106,0.0000050720187,0.4866146,0.00022543428,0.000072127754,2.4543988e-7,0.00007652337,0.0005046334,0.00009078297],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981707,0.00020400368,0.00029311347,0.00055102585,0.00033908957,0.0004421092],"domain_scores_gemma":[0.99770707,0.00038200966,0.0001494663,0.000634037,0.0009842565,0.00014318852],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00064767606,0.00017331235,0.00016149388,0.00021184683,0.0027085596,0.0006635676,0.0013419762,0.00006679736,0.00007418565],"category_scores_gemma":[0.0043339985,0.0001831981,0.00005146449,0.00085308164,0.000113702365,0.0004323034,0.0008731997,0.0002776185,0.00019146907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013684324,0.0006630596,0.00017317456,0.00032005383,0.00009537429,0.00008790255,0.009180878,0.09880297,0.00941727,0.017214667,0.4642583,0.3996495],"study_design_scores_gemma":[0.00038470636,0.0005212017,0.000069273505,0.0001596172,0.000005577753,0.00013328693,0.00002301067,0.91943145,0.0037953393,0.010888784,0.06423921,0.00034856124],"about_ca_topic_score_codex":0.000020847003,"about_ca_topic_score_gemma":9.3167614e-8,"teacher_disagreement_score":0.82062846,"about_ca_system_score_codex":0.00012278146,"about_ca_system_score_gemma":0.000018316014,"threshold_uncertainty_score":0.99858975},"labels":[],"label_agreement":null},{"id":"W1774577175","doi":"10.1007/978-3-540-45070-2_17","title":"Java Subtype Tests in Real-Time","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defense Advanced Research Projects Agency; McGill University","keywords":"Computer science; Java; Speedup; Byte; Constant (computer programming); C dynamic memory allocation; Class (philosophy); Real time Java; Operating system; Programming language; Parallel computing; Memory management; Artificial intelligence","score_opus":0.021264871785459775,"score_gpt":0.26276019879943985,"score_spread":0.24149532701398008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1774577175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014365937,0.00024263338,0.98409414,0.00058903126,0.0008494072,0.00034796726,0.0000020187206,0.0032232495,0.010507876],"genre_scores_gemma":[0.033243984,0.00007115787,0.96337175,0.0022834586,0.00022111967,0.000014957666,0.000004183077,0.00006367071,0.00072571717],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99589694,0.00006262825,0.00059419696,0.0017309331,0.00088181393,0.0008334738],"domain_scores_gemma":[0.99630916,0.0011355565,0.0002807173,0.001886444,0.00021311369,0.00017502472],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014470345,0.0005855997,0.0006227233,0.001280832,0.00015681183,0.00043912622,0.003406274,0.0004217228,0.000020904725],"category_scores_gemma":[0.00053854927,0.0005618057,0.00010597273,0.0011354184,0.00050494197,0.00044393216,0.0009984422,0.000874122,0.0001092782],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009119046,0.00012250438,0.0035888306,0.000080822414,0.0000117616655,0.0007796572,0.001048433,0.0060241693,0.00036100962,0.014697417,0.0029939513,0.9702823],"study_design_scores_gemma":[0.0002696115,0.00026261946,0.001126975,0.0009693689,0.0000052632854,0.00021348752,1.5869325e-8,0.15614133,0.0007531446,0.8375748,0.0014980581,0.0011853679],"about_ca_topic_score_codex":0.00013870871,"about_ca_topic_score_gemma":0.000053521395,"teacher_disagreement_score":0.96909696,"about_ca_system_score_codex":0.00041493942,"about_ca_system_score_gemma":0.00057640305,"threshold_uncertainty_score":0.9996833},"labels":[],"label_agreement":null},{"id":"W1775351421","doi":"10.1007/978-3-642-20677-1_16","title":"Test-Driven Development of Graphical User Interfaces: A Pilot Evaluation","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Graphical user interface; Graphical user interface testing; Computer science; Human–computer interaction; User interface; Pilot test; Process (computing); Test (biology); Interface (matter); Software engineering; User interface design; User experience design; Operating system","score_opus":0.04664004837837124,"score_gpt":0.2719769454355778,"score_spread":0.22533689705720658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1775351421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017153785,0.0002498294,0.98890775,0.00010304045,0.00016381983,0.0004154945,0.0000025168713,0.0014470817,0.008538925],"genre_scores_gemma":[0.55030906,0.000019746149,0.4491662,0.00025274506,0.000036311107,0.000064012034,0.000064035754,0.000029304427,0.000058606645],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99772596,0.000020503743,0.0010204213,0.00029949634,0.00070126913,0.00023231775],"domain_scores_gemma":[0.99686015,0.00027079473,0.0009514875,0.00044163177,0.0014337446,0.00004217132],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068350154,0.00037134488,0.00039293856,0.00090881315,0.00012579725,0.00019317846,0.0007677594,0.0003365392,0.000027951828],"category_scores_gemma":[0.0014187808,0.00033556143,0.000039669238,0.00048006373,0.00009901638,0.0015788276,0.00027798172,0.00040669114,0.0000149793195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017261846,0.00004317076,0.00043173885,0.00068738725,0.000013124934,0.0000011900906,0.0037716194,0.0007228992,0.00001854963,0.0019859935,0.00006183018,0.99224526],"study_design_scores_gemma":[0.0019378313,0.00039450589,0.006830619,0.019235052,0.00014639061,0.00009556759,0.0000065354025,0.18749517,0.008393546,0.76099604,0.011468559,0.0030001628],"about_ca_topic_score_codex":0.000014696424,"about_ca_topic_score_gemma":0.000022275626,"teacher_disagreement_score":0.98924506,"about_ca_system_score_codex":0.00016825435,"about_ca_system_score_gemma":0.0007940298,"threshold_uncertainty_score":0.99990964},"labels":[],"label_agreement":null},{"id":"W1785201090","doi":"10.1007/978-3-642-15585-7_10","title":"Linguistic Security Testing for Text Communication Protocols","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Protocol (science); Syntax; Programming language; Grammar; Formal grammar; Cryptographic protocol; Communications protocol; Language Of Temporal Ordering Specification; Formal specification; Natural language processing; Rule-based machine translation; Computer security; Computer network; Linguistics","score_opus":0.04246884196833257,"score_gpt":0.3168149333576922,"score_spread":0.2743460913893596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1785201090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000914453,0.0000904108,0.9874941,0.00029629245,0.0004887313,0.0053658797,0.000005615515,0.0035782056,0.0026716369],"genre_scores_gemma":[0.041977257,0.0000017126946,0.95587045,0.0005936742,0.00039088042,0.0010618403,0.0000058008754,0.000041106832,0.00005729693],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996937,0.000036067515,0.00056076754,0.0012618853,0.0006152462,0.00058905844],"domain_scores_gemma":[0.9924018,0.003636628,0.00046234776,0.002506512,0.0008511237,0.00014160771],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018686034,0.00047154984,0.00047626512,0.00053824554,0.0005653404,0.00076255726,0.0047876486,0.0004293499,0.0000033105325],"category_scores_gemma":[0.0042464933,0.00045281617,0.000109005116,0.0005196741,0.00068019464,0.00028409724,0.0015075199,0.0012724415,0.000010500944],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000709391,0.000065629334,0.00040432796,0.00021774296,0.000007314756,0.0000187653,0.0017255278,0.00057124847,0.00020524228,0.023264209,0.00010985943,0.97340304],"study_design_scores_gemma":[0.0001396907,0.00019637708,0.00004686542,0.0010077974,0.0000044029844,0.00004556056,9.047202e-9,0.23844385,0.0009813533,0.7564603,0.0022174409,0.00045636916],"about_ca_topic_score_codex":0.00004656199,"about_ca_topic_score_gemma":0.000037837293,"teacher_disagreement_score":0.97294664,"about_ca_system_score_codex":0.00017758449,"about_ca_system_score_gemma":0.0006608161,"threshold_uncertainty_score":0.99979234},"labels":[],"label_agreement":null},{"id":"W179471450","doi":"","title":"A new optimal algorithm for outerplanar graph testing.","year":2004,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Algorithm; Outerplanar graph; Graph; Computer science; Mathematics; Combinatorics; Pathwidth; Line graph","score_opus":0.029008118115395207,"score_gpt":0.23751809974421426,"score_spread":0.20850998162881906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W179471450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05877715,0.0000943594,0.93604565,0.000878807,0.0001884228,0.00031642758,0.000028118015,0.0033496907,0.0003213619],"genre_scores_gemma":[0.077539675,0.0000034848015,0.9215582,0.00016406785,0.00007164199,0.0000010692233,0.000011464451,0.00002173023,0.00062865077],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99814147,0.00005432026,0.00020572294,0.00066439336,0.00042021036,0.0005138773],"domain_scores_gemma":[0.99805206,0.0003357774,0.00023826168,0.00078523054,0.00027427782,0.00031438848],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057402154,0.00026320992,0.00034483103,0.00038806157,0.00053641346,0.00009631864,0.001821317,0.00021175665,0.00001561531],"category_scores_gemma":[0.00030389914,0.00032466618,0.00023591208,0.0008731007,0.00011612457,0.0009739116,0.00051908306,0.0002997776,0.000042196218],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027295324,0.0007426784,0.062396217,0.00022062425,0.00041088538,0.0005485357,0.009500352,0.0014185589,0.004201678,0.0107778,0.026790706,0.88271904],"study_design_scores_gemma":[0.02361466,0.0062778364,0.23635407,0.0020896918,0.000545379,0.0012667843,0.0004933542,0.033931196,0.024230823,0.64579266,0.019630654,0.00577291],"about_ca_topic_score_codex":0.00043322265,"about_ca_topic_score_gemma":0.000031980482,"teacher_disagreement_score":0.8769461,"about_ca_system_score_codex":0.00014415746,"about_ca_system_score_gemma":0.00031118223,"threshold_uncertainty_score":0.99992055},"labels":[],"label_agreement":null},{"id":"W1795706927","doi":"10.1007/978-3-540-31832-3_9","title":"An Evaluation of Auto-Scoping in OpenMP","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministerstvo Školství, Mládeže a Tělovýchovy","keywords":"Computer science; Compiler; Suite; Programming language; Benchmark (surveying); Speedup; Parallel computing; Fortran; Compiler construction; Reduction (mathematics)","score_opus":0.051708513546617735,"score_gpt":0.33146923269746137,"score_spread":0.27976071915084366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1795706927","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046671391,0.00043496245,0.9953737,0.00017132558,0.0004718704,0.00052938546,0.0000012107124,0.001028113,0.001522679],"genre_scores_gemma":[0.4243402,0.000010921063,0.5751515,0.00030691226,0.00014388037,0.000012535283,0.0000023549355,0.000017609713,0.000014067571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626917,0.000096955875,0.00060491223,0.0011717179,0.0014304607,0.00042680764],"domain_scores_gemma":[0.9971487,0.0004938435,0.0003345025,0.0015030687,0.00042747732,0.00009241057],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040418534,0.0003397754,0.00046637858,0.0011341614,0.00009081247,0.00025331267,0.0030564351,0.00025405688,0.000015394862],"category_scores_gemma":[0.0003696223,0.00033389637,0.00006305038,0.00067290646,0.00032574483,0.0007688668,0.0006684368,0.0005030504,0.0000069018306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015274704,0.000030861826,0.0003086361,0.00002843031,0.0000017537044,0.00000855411,0.00056913524,0.048957597,0.00006846113,0.00196923,0.000008608336,0.9480472],"study_design_scores_gemma":[0.00017321257,0.00011979179,0.0005588728,0.0018015329,0.0000047088624,0.000019029443,2.4157337e-8,0.7617866,0.0009793927,0.23422885,0.00001737506,0.00031060982],"about_ca_topic_score_codex":0.00008676458,"about_ca_topic_score_gemma":0.00013482786,"teacher_disagreement_score":0.9477366,"about_ca_system_score_codex":0.00040076516,"about_ca_system_score_gemma":0.0011292978,"threshold_uncertainty_score":0.9999113},"labels":[],"label_agreement":null},{"id":"W1819615023","doi":"10.1109/aswec.2000.844580","title":"Tools and techniques for Java API testing","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Java; Software portability; Reuse; Component (thermodynamics); Software engineering; Unit testing; Programming language; JavaBeans; Object-oriented programming; Real time Java; Component-based software engineering; Software; Software development; Engineering","score_opus":0.11025616659943181,"score_gpt":0.27524183244310696,"score_spread":0.16498566584367513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819615023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006180047,0.00011935176,0.96370006,0.00062850723,0.00003639445,0.0002181257,0.000001325257,0.022541301,0.012136927],"genre_scores_gemma":[0.10689093,0.000005018742,0.8919973,0.000574167,0.000041925625,0.00005976295,3.4198433e-7,0.000007821346,0.00042272915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993193,0.000011920759,0.00012890666,0.0002645689,0.00008438957,0.00019090043],"domain_scores_gemma":[0.9986295,0.0008917932,0.00004021985,0.00030571275,0.00008241326,0.000050342474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023741888,0.00009359029,0.00009954196,0.00006677217,0.00011896871,0.0002245391,0.00032261954,0.000045344575,0.000005114754],"category_scores_gemma":[0.0010500543,0.00008005777,0.000021975611,0.00018410203,0.00002855896,0.0003045988,0.00014371536,0.000053272703,0.0000050877934],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3794313e-7,0.000018419887,0.0019413513,0.000014162841,0.0000021528695,0.0000022725746,0.00007874963,1.6599941e-7,0.0003358699,0.008105651,0.05002323,0.9394776],"study_design_scores_gemma":[0.00044973922,0.001076282,0.0023694832,0.00027431967,0.000015276702,0.00035918943,0.0000073059246,0.4649245,0.046447176,0.43675935,0.046172116,0.0011452505],"about_ca_topic_score_codex":0.000017898989,"about_ca_topic_score_gemma":4.779084e-7,"teacher_disagreement_score":0.9383324,"about_ca_system_score_codex":0.0000106457555,"about_ca_system_score_gemma":0.0000058997657,"threshold_uncertainty_score":0.3264661},"labels":[],"label_agreement":null},{"id":"W1827797309","doi":"10.1109/hcc.2001.995275","title":"A testing methodology for a dataflow based visual programming language","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Dataflow; Computer science; Dataflow architecture; Programming language; Testability; Control flow; Reliability engineering","score_opus":0.19604624704805348,"score_gpt":0.37455743884055015,"score_spread":0.17851119179249667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1827797309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001546683,0.000058719404,0.9829895,0.0003049056,0.00007418048,0.0002381262,0.0000011540673,0.0142978355,0.00048892305],"genre_scores_gemma":[0.07457126,9.6479134e-8,0.92442775,0.0006827815,0.000052836916,0.00010167791,0.0000027686397,0.000011434253,0.00014941959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989587,0.000091176604,0.00016118686,0.0003584087,0.00011182722,0.0003186922],"domain_scores_gemma":[0.9963565,0.00303996,0.000061716564,0.00040361146,0.000076434786,0.000061799255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007774333,0.00011023646,0.00014606366,0.00010794591,0.00011339498,0.00012267653,0.00052918197,0.00005278555,0.000013147146],"category_scores_gemma":[0.0037474434,0.00009826629,0.000045706678,0.00038338048,0.000026756274,0.0001587963,0.0001320694,0.00007681593,0.00001180603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001701542,0.00007767252,0.0009710101,0.000027116841,0.0000048248544,0.000014430208,0.00024614306,0.000007357144,0.0010516875,0.0011255156,0.007647736,0.9888248],"study_design_scores_gemma":[0.0002654947,0.0003123707,0.00011104239,0.000032621796,0.0000063498433,0.000036102603,0.000008337191,0.99004894,0.00404256,0.0028794813,0.0020495774,0.00020709063],"about_ca_topic_score_codex":0.00008709611,"about_ca_topic_score_gemma":0.0000034426134,"teacher_disagreement_score":0.9900416,"about_ca_system_score_codex":0.00001629388,"about_ca_system_score_gemma":0.000018904222,"threshold_uncertainty_score":0.44863105},"labels":[],"label_agreement":null},{"id":"W1833943521","doi":"10.1007/978-3-540-25940-4_65","title":"Toward an Undergraduate League for RoboCup","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"League; Computer science; Artificial intelligence; Political science; Mathematics education; Engineering; Psychology","score_opus":0.04226289565341727,"score_gpt":0.2829359307603361,"score_spread":0.2406730351069188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1833943521","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011172461,0.00022233238,0.9900759,0.0017893113,0.0013461467,0.0005617202,0.0000061472656,0.0046448126,0.0013424814],"genre_scores_gemma":[0.11494794,0.000023042468,0.8830245,0.0012389071,0.0004378218,0.000029931887,0.000009737347,0.000055040757,0.00023306976],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960044,0.000026559326,0.00050612696,0.0018859276,0.00077634375,0.0008006209],"domain_scores_gemma":[0.9966216,0.0007337895,0.00028655707,0.0017874661,0.00033228754,0.00023828713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009834395,0.0006071738,0.00056958786,0.00077799335,0.0003176346,0.00074458437,0.0042132083,0.00037622964,0.000005789749],"category_scores_gemma":[0.00028238213,0.00056718173,0.00017893995,0.00047828682,0.0005583648,0.0007276112,0.0009216255,0.0006465557,0.0000166955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062043105,0.000045437144,0.000035684607,0.00007532803,0.000009631028,0.000043944485,0.0005417739,0.023168888,0.000023615286,0.11503991,0.00021609488,0.8607935],"study_design_scores_gemma":[0.00022210008,0.00046501486,0.000023511257,0.00039881995,0.0000065598906,0.00005312559,1.8977289e-8,0.16990116,0.0006356702,0.827165,0.00051729014,0.00061175274],"about_ca_topic_score_codex":0.00007652028,"about_ca_topic_score_gemma":0.00003823719,"teacher_disagreement_score":0.86018175,"about_ca_system_score_codex":0.0004427721,"about_ca_system_score_gemma":0.00096984336,"threshold_uncertainty_score":0.99967796},"labels":[],"label_agreement":null},{"id":"W1845490991","doi":"10.1007/11901433_25","title":"Conditions for Avoiding Controllability Problems in Distributed Testing","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Controllability; Computer science; Finite-state machine; Context (archaeology); Sequence (biology); Distributed computing; Conformance testing; Test (biology); State (computer science); Architecture; Test case; System under test; Algorithm; Machine learning; Operating system; Mathematics","score_opus":0.032157442413021396,"score_gpt":0.2695266468818414,"score_spread":0.23736920446882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1845490991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019660393,0.00015370394,0.99440664,0.00039536727,0.0005263344,0.0010554909,0.000055712364,0.0027142887,0.0004958314],"genre_scores_gemma":[0.5562126,0.0000012659176,0.44317338,0.00027577573,0.00016762705,0.00008501871,0.000031483833,0.000025860045,0.000027018808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99634624,0.000057999863,0.00074849004,0.001525182,0.0005427564,0.0007793246],"domain_scores_gemma":[0.99263704,0.005318275,0.00036394421,0.001100499,0.00047086054,0.00010936715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021689208,0.00048784816,0.0006250362,0.0007463936,0.00041292654,0.0005110108,0.0020947272,0.00030923053,0.0000017138319],"category_scores_gemma":[0.002441773,0.00047673643,0.00012049675,0.0009971828,0.0005297707,0.00042012727,0.00064025144,0.00081415277,0.0000035550197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014494494,0.00029653145,0.025906134,0.00051272154,0.000024607032,0.00011181063,0.0008526353,0.49419776,0.00059293146,0.023207285,0.0014149641,0.45286813],"study_design_scores_gemma":[0.00026976917,0.00010431167,0.00097219774,0.0005580682,0.000003928236,0.000023648005,1.9828152e-8,0.4654063,0.00013054954,0.5320332,0.00012130509,0.0003767028],"about_ca_topic_score_codex":0.00019287837,"about_ca_topic_score_gemma":0.00012995854,"teacher_disagreement_score":0.55601597,"about_ca_system_score_codex":0.00054463965,"about_ca_system_score_gemma":0.00054422446,"threshold_uncertainty_score":0.99976844},"labels":[],"label_agreement":null},{"id":"W1846902312","doi":"10.1007/11532378_14","title":"The Use of Traces for Inlining in Java Programs","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Java; TRACE (psycholinguistics); Programming language; Operating system; Overhead (engineering); Just-in-time compilation; Code (set theory); Virtual machine; Parallel computing","score_opus":0.0715089159885698,"score_gpt":0.29134742622707543,"score_spread":0.21983851023850565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1846902312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001633421,0.00047848918,0.9966685,0.0005867439,0.00050739513,0.00058656035,0.0000019380095,0.0009077086,0.00009930593],"genre_scores_gemma":[0.059867796,0.00004174711,0.93938595,0.0003494287,0.00018566131,0.00003626971,0.0000018638088,0.000023641267,0.00010762822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973805,0.000030543124,0.0006039146,0.0008788633,0.00056528894,0.00054090057],"domain_scores_gemma":[0.9949966,0.0032595175,0.00036123366,0.0010760456,0.00024035198,0.0000662607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013905468,0.00033002332,0.00040074732,0.00048521702,0.0002044495,0.0005537438,0.0027318427,0.00022337727,5.231505e-7],"category_scores_gemma":[0.0006661929,0.00024297764,0.0001129723,0.0005297698,0.0006717907,0.00046385566,0.0006530734,0.00049879594,0.0000012973728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004445475,0.000020259435,0.00041010947,0.000019285928,0.0000029811138,0.000005398543,0.00045245775,0.0052232537,0.0000052189753,0.004132674,0.000046173012,0.9896777],"study_design_scores_gemma":[0.00019220111,0.0003046843,0.00021808145,0.00096854917,0.000004418381,0.000027165868,6.8354865e-8,0.69999087,0.0003595545,0.28989846,0.0076013943,0.0004345801],"about_ca_topic_score_codex":0.000047655743,"about_ca_topic_score_gemma":0.00016086253,"teacher_disagreement_score":0.98924315,"about_ca_system_score_codex":0.00012687304,"about_ca_system_score_gemma":0.00033911882,"threshold_uncertainty_score":0.99083406},"labels":[],"label_agreement":null},{"id":"W1852182718","doi":"10.1007/978-0-387-35497-2_21","title":"Formulation of the Interaction Test Coverage Problem as an Integer Program","year":2002,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Integer programming; Completeness (order theory); Cover (algebra); Computer science; Set (abstract data type); Integer (computer science); Set cover problem; Mathematical optimization; Test (biology); Function (biology); Test case; Theoretical computer science; Mathematics; Algorithm; Engineering; Programming language; Machine learning","score_opus":0.013116465940273079,"score_gpt":0.2831618641821669,"score_spread":0.2700453982418938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1852182718","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010396731,0.0051007355,0.1622578,0.0040263785,0.00043947613,0.004110898,0.000022522756,0.014938679,0.8080638],"genre_scores_gemma":[0.8716252,0.010024789,0.11466258,0.00041621926,0.000013551458,0.00037005392,0.00008952512,0.00002715609,0.002770916],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989177,0.000027284093,0.00062657485,0.0001361374,0.00017600186,0.000116282514],"domain_scores_gemma":[0.99751073,0.0001987689,0.00081268547,0.0012290825,0.00022790719,0.00002079729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023091516,0.00017599731,0.00020198661,0.0005281643,0.00012524803,0.00008263561,0.0011360798,0.0003175648,0.00000963723],"category_scores_gemma":[0.00023703798,0.00014781067,0.000037943526,0.00024653625,0.0001717298,0.002467435,0.00046908023,0.0005396943,0.0000109374205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002254261,0.00002686184,0.00030803803,0.000030715724,0.0000021375565,6.194947e-8,0.0003172564,0.000025706444,5.9888606e-7,0.41580203,0.00006370602,0.58342063],"study_design_scores_gemma":[0.00018778304,0.0002332944,0.00007927133,0.00048616578,0.000005173465,0.00004129089,0.000029971457,0.015002956,0.00013488406,0.79630375,0.18730411,0.00019131968],"about_ca_topic_score_codex":0.000016325643,"about_ca_topic_score_gemma":0.00001975439,"teacher_disagreement_score":0.87058556,"about_ca_system_score_codex":0.0000841379,"about_ca_system_score_gemma":0.00003323083,"threshold_uncertainty_score":0.6027544},"labels":[],"label_agreement":null},{"id":"W1867551913","doi":"10.1109/icst.2015.7102602","title":"Prioritizing Manual Test Cases in Traditional and Rapid Release Environments","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Mitacs; Aalto-Yliopisto; University of Manitoba","keywords":"Computer science; Prioritization; Test suite; Agile software development; Unit testing; Code coverage; Ranking (information retrieval); Test case; Test (biology); Reliability engineering; Test Management Approach; White-box testing; Regression testing; Test script; Software engineering; Software; Software system; Machine learning; Operating system; Engineering","score_opus":0.07290767552958227,"score_gpt":0.26705351917657033,"score_spread":0.19414584364698806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1867551913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6981211,0.0009196204,0.27942872,0.0020494913,0.0003141525,0.00044674406,0.000015404092,0.009667686,0.009037097],"genre_scores_gemma":[0.8172106,0.000008063497,0.18239231,0.00026446854,0.000026099699,0.00000810904,0.0000017129186,0.0000036951924,0.00008489376],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993561,0.000025950952,0.00011118117,0.00021374303,0.00015955033,0.0001334925],"domain_scores_gemma":[0.9993078,0.00038692297,0.000022807026,0.00017130235,0.0000073516762,0.00010377792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023131284,0.0000727211,0.000072406256,0.0000746929,0.000034762914,0.00005716584,0.00016155536,0.000029193994,0.0000027298872],"category_scores_gemma":[0.00046771645,0.00006880588,0.000010472138,0.00009004623,0.00003809615,0.00024944425,0.00007027547,0.00007014684,0.000010393136],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002578951,0.0014421222,0.4410338,0.000045230216,0.000015349602,0.002834835,0.002699083,0.000023036717,0.0010819979,0.038063224,0.1284613,0.3842742],"study_design_scores_gemma":[0.0036299475,0.002615577,0.50342876,0.00035554502,0.000016097454,0.0049960846,0.00014679832,0.12074549,0.004883307,0.3455433,0.011860588,0.0017785025],"about_ca_topic_score_codex":0.00008424553,"about_ca_topic_score_gemma":0.000003777578,"teacher_disagreement_score":0.38249573,"about_ca_system_score_codex":0.000038566133,"about_ca_system_score_gemma":0.000030322219,"threshold_uncertainty_score":0.28058222},"labels":[],"label_agreement":null},{"id":"W1880492488","doi":"10.1120/jacmp.v14i1.4052","title":"Automated IMRT planning with regional optimization using planning scripts","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Clinical Medical Physics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Cancer Care Ontario","keywords":"Scripting language; Radiation treatment planning; Computer science; Medical physics; Medicine; Radiation therapy; Radiology; Programming language","score_opus":0.09085317414621082,"score_gpt":0.3731214052892368,"score_spread":0.282268231143026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1880492488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031495687,0.000038219136,0.96554023,0.0005005991,0.0002711295,0.00010705155,1.5245266e-7,0.0017227281,0.00032418323],"genre_scores_gemma":[0.4371929,0.000004603128,0.5606228,0.0015387734,0.00061820884,0.000003284814,0.0000011377698,0.000016576378,0.0000017231213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734646,0.00007689585,0.00093533954,0.00026152283,0.00109493,0.00028487566],"domain_scores_gemma":[0.99701244,0.0011520352,0.00081401475,0.00028743988,0.000331796,0.00040225332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011700062,0.00017555969,0.00044991166,0.000077787074,0.00012158261,0.00013351817,0.00081661146,0.00018958484,0.000011249823],"category_scores_gemma":[0.00059826893,0.00012580922,0.0001060154,0.00039218378,0.00018477232,0.00041441715,0.0001496864,0.0008070896,0.000006205971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041761424,0.0017929077,0.033510108,0.0001290635,0.00057946134,0.0007785934,0.0017441313,0.55675215,0.00015240045,0.008316708,0.19892614,0.19690071],"study_design_scores_gemma":[0.00081398623,0.00032305805,0.0016291944,0.0006334143,0.000025628142,0.0001693426,0.000013949349,0.9699625,0.00004405787,0.026093394,0.000089853995,0.00020165162],"about_ca_topic_score_codex":0.0000077797995,"about_ca_topic_score_gemma":2.2632397e-8,"teacher_disagreement_score":0.4132103,"about_ca_system_score_codex":0.000044398137,"about_ca_system_score_gemma":0.0003870436,"threshold_uncertainty_score":0.5130351},"labels":[],"label_agreement":null},{"id":"W1883222843","doi":"10.1109/cmpsac.1991.170177","title":"A new control flow representation","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Research Council Canada","keywords":"Representation (politics); Computer science; Control flow graph; Control flow; Flow (mathematics); Theoretical computer science; Control (management); Graph; Information flow; Control flow analysis; Programming language; Artificial intelligence; Mathematics; Procedural programming","score_opus":0.03387879740053827,"score_gpt":0.25941588629852164,"score_spread":0.22553708889798335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1883222843","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053977477,0.000046051846,0.9748181,0.0018200631,0.00008488545,0.000052438125,9.472328e-8,0.011531585,0.011592769],"genre_scores_gemma":[0.24510606,0.0000019877314,0.75152236,0.0007742122,0.000047029058,0.0000041449434,1.4974367e-7,0.0000027360265,0.002541304],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952114,0.000018810928,0.00008005631,0.0001648278,0.00011204145,0.0001031378],"domain_scores_gemma":[0.9994139,0.00013592165,0.000021994845,0.0003481513,0.00002552392,0.000054527554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006552872,0.000047195805,0.000056732533,0.000041172792,0.000037406087,0.000085300315,0.00028161812,0.0000211954,0.00012496102],"category_scores_gemma":[0.00015261702,0.00004032827,0.000025224026,0.00017977433,0.0000053602957,0.00018842134,0.00003632328,0.000037172307,0.00015691911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0985154e-7,0.000009758035,0.0015701238,6.552908e-7,0.0000025387315,0.000005281739,0.00013955511,0.000030823525,0.000024036312,0.0037262014,0.59119564,0.40329498],"study_design_scores_gemma":[0.00026720244,0.000040738374,0.00091658684,0.0000065123413,0.0000018801363,0.000023297369,5.040184e-7,0.9385599,0.00046462214,0.057230107,0.002394227,0.00009442049],"about_ca_topic_score_codex":0.0001175506,"about_ca_topic_score_gemma":0.0000013884076,"teacher_disagreement_score":0.9385291,"about_ca_system_score_codex":0.000008606755,"about_ca_system_score_gemma":0.0000066077673,"threshold_uncertainty_score":0.201693},"labels":[],"label_agreement":null},{"id":"W1898227670","doi":"10.1109/tools.1997.681887","title":"Object-Oriented Testing","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; System integration testing; White-box testing; Software reliability testing; Manual testing; Software engineering; Non-regression testing; Keyword-driven testing; Software performance testing; Integration testing; Black-box testing; Object-oriented programming; Test strategy; Software construction; Test Management Approach; Software; Class (philosophy); Software testing; System testing; Programming language; Software development; Artificial intelligence","score_opus":0.0277080684817965,"score_gpt":0.26312562346130897,"score_spread":0.23541755497951247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898227670","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036106294,0.000027887982,0.92380977,0.00056072924,0.00007628531,0.000045651024,1.0304185e-7,0.031507112,0.040361833],"genre_scores_gemma":[0.36280176,2.3338318e-7,0.63617086,0.00059204415,0.000054647055,0.0000043631658,1.6298853e-7,0.0000033615195,0.00037257624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934703,0.00001509651,0.0001125372,0.00020996651,0.00013095613,0.0001843931],"domain_scores_gemma":[0.9992049,0.00025778933,0.000030817082,0.00037965327,0.00007425384,0.000052624408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001838384,0.00007186839,0.000063608364,0.00006205625,0.0000813882,0.00006646802,0.0003935098,0.000025887406,0.000010084521],"category_scores_gemma":[0.00053650397,0.000061296676,0.000020260079,0.00040120576,0.000014378121,0.00023840697,0.00015562095,0.00006844807,0.000116610325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.1227046e-7,0.00006998814,0.019212363,0.0000045590473,0.0000046876685,0.000010745038,0.00028878855,0.000052938638,0.00040464036,0.03469397,0.085352354,0.85990417],"study_design_scores_gemma":[0.000480344,0.00027956025,0.017497836,0.00010157846,0.00000628996,0.00026209877,0.000006062902,0.8281844,0.02005868,0.06874638,0.06352229,0.0008544855],"about_ca_topic_score_codex":0.000048026894,"about_ca_topic_score_gemma":0.0000025253778,"teacher_disagreement_score":0.8590497,"about_ca_system_score_codex":0.000022868366,"about_ca_system_score_gemma":0.000029200874,"threshold_uncertainty_score":0.2499606},"labels":[],"label_agreement":null},{"id":"W1900631367","doi":"10.1109/qrs-c.2015.26","title":"On the Effect of Counters in Guard Conditions When State-Based Multi-objective Testing","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Extended finite-state machine; Tree traversal; Guard (computer science); Finite-state machine; Computer science; Executable; Automaton; Graph; State (computer science); Deterministic finite automaton; Graph traversal; Theoretical computer science; Algorithm; Programming language","score_opus":0.047483217440556086,"score_gpt":0.2939482613152094,"score_spread":0.24646504387465332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1900631367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3698293,0.000012376883,0.62321967,0.00046312032,0.00011555953,0.00045623156,0.000006314152,0.0038632064,0.0020342544],"genre_scores_gemma":[0.9098083,4.3442867e-8,0.08978605,0.00032856825,0.0000037723878,0.000043322903,9.591665e-7,0.0000056710396,0.000023348854],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910927,0.00019666067,0.00015261053,0.00019158513,0.00019802726,0.00015186273],"domain_scores_gemma":[0.99475294,0.0046487367,0.000077250785,0.00036463264,0.00011529755,0.00004112777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096031977,0.00010078999,0.00013072114,0.000117187665,0.000044599947,0.00004352851,0.00041525438,0.000025522819,0.0000024189214],"category_scores_gemma":[0.0032562907,0.0000625829,0.000028055163,0.0003095135,0.00006711622,0.00009275668,0.00006759598,0.0001192755,0.000010270465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021531079,0.0007234698,0.74985635,0.00013539218,0.00008206217,0.00013176329,0.011058092,0.022329351,0.0012415373,0.011390604,0.16622537,0.036610663],"study_design_scores_gemma":[0.0020412598,0.0028400032,0.018084068,0.0004914831,0.000008741071,0.000009768627,0.000036077534,0.86650306,0.036274854,0.07331852,0.000034586657,0.00035757027],"about_ca_topic_score_codex":0.0008506278,"about_ca_topic_score_gemma":0.00003166529,"teacher_disagreement_score":0.8441737,"about_ca_system_score_codex":0.0000722936,"about_ca_system_score_gemma":0.00008598609,"threshold_uncertainty_score":0.38983193},"labels":[],"label_agreement":null},{"id":"W191325165","doi":"10.1007/978-3-642-31491-9_8","title":"Combining UML Sequence and State Machine Diagrams for Data-Flow Based Integration Testing","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Unified Modeling Language; Sequence diagram; Control flow; Finite-state machine; Applications of UML; Data flow diagram; Integration testing; Activity diagram; Abstract state machines; Graph; Data mining; Programming language; Class diagram; State (computer science); Theoretical computer science; Database; Software","score_opus":0.08609689577891642,"score_gpt":0.30227431284458683,"score_spread":0.2161774170656704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191325165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034810408,0.0006176091,0.9953819,0.00033723176,0.00066539604,0.0005269673,0.000043072516,0.0022886745,0.00010434142],"genre_scores_gemma":[0.13085504,0.000012347008,0.86798793,0.0008488823,0.00015739126,0.000020747637,0.00006214508,0.00003551037,0.00001998185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966542,0.00004412883,0.00049864914,0.0015378853,0.00059191993,0.0006732005],"domain_scores_gemma":[0.99422085,0.0030812162,0.00037564326,0.0018124961,0.00032192573,0.0001878763],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022707665,0.00051504275,0.0004761693,0.00051456736,0.00037706655,0.0007448095,0.002992476,0.0001974631,0.0000015971904],"category_scores_gemma":[0.001503831,0.00045763998,0.000049624097,0.00048622926,0.00052489934,0.00097382604,0.0015757609,0.0006430937,0.0000030252004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032687572,0.000015053223,0.0006385924,0.000045906057,0.0000035474213,0.000010046289,0.00022294742,0.0022291758,0.000067927154,0.0007343821,0.000032249154,0.9959969],"study_design_scores_gemma":[0.00016608775,0.00016300216,0.00008782559,0.0006041823,0.000008819519,0.000045766763,1.579045e-8,0.82708466,0.00038114097,0.17086467,0.0001449801,0.0004488625],"about_ca_topic_score_codex":0.00011574014,"about_ca_topic_score_gemma":0.00005676622,"teacher_disagreement_score":0.99554807,"about_ca_system_score_codex":0.00015874128,"about_ca_system_score_gemma":0.00040047994,"threshold_uncertainty_score":0.9997875},"labels":[],"label_agreement":null},{"id":"W1916225420","doi":"10.1109/ictta.2004.1307898","title":"Timed test cases generation based on test purposes expressed as message sequence charts","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Test (biology); Test case; Process (computing); Reliability engineering; Test Management Approach; Test suite; Fault (geology); Formal specification; Sequence (biology); Software engineering; Programming language; Software; Software system; Engineering; Software construction; Machine learning","score_opus":0.054010909486074114,"score_gpt":0.2868837883451243,"score_spread":0.23287287885905017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916225420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04532987,0.000054951302,0.90304035,0.0055669937,0.00032981476,0.0007353628,0.000023297676,0.034039017,0.010880322],"genre_scores_gemma":[0.80476415,0.000004098451,0.19247985,0.0023385538,0.00008126488,0.00006847033,0.00001077155,0.000014645556,0.00023816884],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998525,0.000037887774,0.00022022518,0.00054208725,0.0003785828,0.00029617708],"domain_scores_gemma":[0.9975289,0.0013044893,0.00009136903,0.0008321956,0.00012210611,0.00012094188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002505576,0.00021621969,0.00015864019,0.00016410842,0.00021870913,0.00029253078,0.0006110718,0.00007839667,0.000037740265],"category_scores_gemma":[0.0028569987,0.00018599241,0.00005082696,0.0003905982,0.000057175126,0.0003785236,0.00009084675,0.00011927001,0.00014795028],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037895257,0.0049362113,0.01866233,0.00015917356,0.00003557429,0.004198713,0.0014844984,0.014669432,0.62394375,0.032774862,0.171422,0.12767556],"study_design_scores_gemma":[0.000703838,0.0013530841,0.0007623158,0.0002504279,0.000009762332,0.0001596649,0.0000027867386,0.21607259,0.76523,0.013799939,0.00096646807,0.000689132],"about_ca_topic_score_codex":0.00041078197,"about_ca_topic_score_gemma":0.000013729214,"teacher_disagreement_score":0.7594343,"about_ca_system_score_codex":0.00008944888,"about_ca_system_score_gemma":0.00020320139,"threshold_uncertainty_score":0.75845504},"labels":[],"label_agreement":null},{"id":"W1920048997","doi":"10.1109/ase.1998.732614","title":"Testing using log file analysis: tools, methods, and issues","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Computer science; Scope (computer science); Software; Software testing; Programming language; Database; Software engineering","score_opus":0.16286346450439254,"score_gpt":0.37333172560894495,"score_spread":0.2104682611045524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1920048997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013083023,0.00071305135,0.9870311,0.0001874937,0.000033453765,0.000049218987,0.0000027804808,0.00781964,0.0028549444],"genre_scores_gemma":[0.03167396,0.000005051592,0.96771955,0.00024372952,0.000030783394,0.0000047090484,0.0000013129173,0.000005961815,0.00031491855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990399,0.00010016943,0.00017451313,0.0003537142,0.00012120341,0.0002105349],"domain_scores_gemma":[0.9981249,0.0012123862,0.000067212495,0.000453807,0.00007521314,0.00006646885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004371672,0.00011494429,0.0001958263,0.0002000114,0.00014523281,0.00031623812,0.0003452349,0.00004620666,0.00019602387],"category_scores_gemma":[0.0015142816,0.000099108336,0.000044717337,0.0012380233,0.000032761076,0.00035382318,0.00024889046,0.00008079648,0.000008951569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.240184e-7,0.000057064917,0.018757515,0.00001748709,0.00013084215,0.000026937882,0.00055175397,0.00018404779,0.0007506427,0.0018072398,0.07736847,0.9003476],"study_design_scores_gemma":[0.000035217614,0.00003101115,0.003934338,0.000022811135,0.000049429713,0.000035053334,0.0000046469127,0.9840805,0.0005648592,0.009908004,0.0011515041,0.00018262418],"about_ca_topic_score_codex":0.0003782385,"about_ca_topic_score_gemma":0.0000023797638,"teacher_disagreement_score":0.98389643,"about_ca_system_score_codex":0.0000141480305,"about_ca_system_score_gemma":0.0000069797206,"threshold_uncertainty_score":0.40415207},"labels":[],"label_agreement":null},{"id":"W1923117336","doi":"10.1007/978-3-642-10677-4_27","title":"Quasi-Deterministic Partially Observable Markov Decision Processes","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Observability; Computer science; Observable; Markov decision process; Hierarchy; Mathematical optimization; Theoretical computer science; Polynomial hierarchy; Decision problem; Time complexity; Markov process; Algorithm; Mathematics; Applied mathematics","score_opus":0.027048840545886504,"score_gpt":0.2727263273379048,"score_spread":0.2456774867920183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1923117336","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041197836,0.0005907216,0.9917412,0.00038214828,0.00096510735,0.00036452495,0.0000031517566,0.004002237,0.0019097367],"genre_scores_gemma":[0.07771048,0.00007112316,0.9195482,0.0018581821,0.0003681332,0.000015268337,0.0000039997917,0.000043227603,0.00038138725],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99517787,0.000035573852,0.0007051977,0.0019291571,0.001293438,0.00085875846],"domain_scores_gemma":[0.99476147,0.0021144198,0.0003787969,0.002005952,0.0005026248,0.00023673738],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011611744,0.000677921,0.00067934167,0.0007493699,0.0003678025,0.0010338308,0.004748776,0.00039554958,0.00001224004],"category_scores_gemma":[0.0014941394,0.0006103259,0.00012412391,0.00097524363,0.00047282455,0.0006705331,0.0012053628,0.0007438942,0.000048488586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007364449,0.000061163126,0.0001066383,0.000059145863,0.0000033552985,0.00016822793,0.00017990693,0.0017727074,0.0000070020965,0.0010523278,0.00025312952,0.996329],"study_design_scores_gemma":[0.00016612063,0.00069883687,0.00019404682,0.0015773007,0.0000100424795,0.0001777898,1.5432763e-8,0.2130864,0.00038362996,0.78061604,0.0022291353,0.0008606567],"about_ca_topic_score_codex":0.000024024615,"about_ca_topic_score_gemma":0.00005550406,"teacher_disagreement_score":0.9954684,"about_ca_system_score_codex":0.00024773396,"about_ca_system_score_gemma":0.0013758283,"threshold_uncertainty_score":0.9996348},"labels":[],"label_agreement":null},{"id":"W1925282067","doi":"10.1109/icst.2015.7102588","title":"Exploring Test Suite Diversification and Code Coverage in Multi-Objective Test Case Selection","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Test suite; Heuristics; Computer science; Code coverage; Selection (genetic algorithm); Fault coverage; Test case; Suite; Code (set theory); Test (biology); Programming language; Machine learning; Software; Operating system; Engineering","score_opus":0.18669848225657762,"score_gpt":0.3023859569594612,"score_spread":0.11568747470288357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1925282067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2919998,0.000024337483,0.70264703,0.00013195485,0.0000839142,0.00018301701,0.000003756998,0.004554693,0.0003714785],"genre_scores_gemma":[0.8886666,0.000008658908,0.11115659,0.00005268784,0.000013714979,0.000029063085,9.1307334e-7,0.0000053867016,0.00006633205],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927807,0.000033268276,0.00012210761,0.00030456018,0.00010995147,0.00015201996],"domain_scores_gemma":[0.99890274,0.000666389,0.000047511356,0.00018454576,0.0001166442,0.0000821778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037413725,0.00009233442,0.000086430955,0.00015705786,0.000088114146,0.00010864562,0.00013605949,0.000033215423,5.740089e-7],"category_scores_gemma":[0.0016235278,0.00009040637,0.000010911812,0.0004289142,0.00002218747,0.00079346704,0.0001301644,0.00010299635,0.0000074893815],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004907018,0.00024246963,0.9597102,0.000011992041,0.0000035899002,0.00029464584,0.004700144,0.000116437426,0.00043817802,0.00040427144,0.0012820158,0.032791182],"study_design_scores_gemma":[0.0016180566,0.000641493,0.24742462,0.00009689035,0.00001007429,0.0023418826,0.0002948926,0.73138785,0.009356446,0.00588735,0.00029955097,0.0006408703],"about_ca_topic_score_codex":0.0014415814,"about_ca_topic_score_gemma":0.00041798386,"teacher_disagreement_score":0.73127145,"about_ca_system_score_codex":0.0001226368,"about_ca_system_score_gemma":0.000039149865,"threshold_uncertainty_score":0.36866647},"labels":[],"label_agreement":null},{"id":"W1928770023","doi":"10.1109/icsm.1989.65194","title":"Insights into regression testing (software testing)","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regression testing; Testability; Test plan; Computer science; Non-regression testing; Test (biology); Plan (archaeology); Risk-based testing; Regression analysis; Test Management Approach; Manual testing; Test strategy; Set (abstract data type); Reliability engineering; Regression; Keyword-driven testing; White-box testing; Machine learning; Data mining; Measure (data warehouse); Software; Statistics; Programming language; Mathematics; Engineering; Software system","score_opus":0.04500660842911066,"score_gpt":0.27565002333236094,"score_spread":0.23064341490325027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1928770023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01244072,0.00026647744,0.93416595,0.00008708886,0.0002647283,0.00013255268,7.6426886e-8,0.033763915,0.018878464],"genre_scores_gemma":[0.33635107,7.832864e-7,0.66307634,0.00033094664,0.000024731919,0.000013527759,3.7904817e-7,0.000012904629,0.00018933903],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998454,0.00010890484,0.00027154514,0.0005431021,0.00030991467,0.00031256344],"domain_scores_gemma":[0.9968427,0.0017152785,0.00012503841,0.0008639247,0.00030512954,0.00014795219],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00029132917,0.00021897422,0.00018209184,0.00016426676,0.00035294626,0.00019035515,0.0007287529,0.000094796116,0.0000064370915],"category_scores_gemma":[0.013341531,0.00016588112,0.000038974846,0.0012607746,0.000047799957,0.00040000692,0.0002453153,0.00019771767,0.00006231046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002985186,0.00025342015,0.15669163,0.00009658474,0.0000152204775,0.00021845155,0.0012772823,0.00009087018,0.004193676,0.05923986,0.059403166,0.7185169],"study_design_scores_gemma":[0.00036812323,0.0003924211,0.0070156455,0.0006252732,0.00000889057,0.00022154485,0.000010323052,0.033311974,0.021345194,0.92652583,0.0092113735,0.00096339406],"about_ca_topic_score_codex":0.00013901558,"about_ca_topic_score_gemma":0.0000034328814,"teacher_disagreement_score":0.86728597,"about_ca_system_score_codex":0.000052149368,"about_ca_system_score_gemma":0.00013455149,"threshold_uncertainty_score":0.9949695},"labels":[],"label_agreement":null},{"id":"W1947217269","doi":"10.1109/ase.1998.732610","title":"Programmatic testing of the Standard Template Library containers","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Test suite; Computer science; White-box testing; Conformance testing; Suite; Unit testing; Software engineering; Programming language; Code coverage; Key (lock); Keyword-driven testing; Code (set theory); Black box; Component (thermodynamics); Test case; Software; Operating system; Software development; Software construction; Artificial intelligence; Standardization; Machine learning; Set (abstract data type)","score_opus":0.037983183024864135,"score_gpt":0.22401962082305504,"score_spread":0.1860364377981909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1947217269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04285995,0.00025514187,0.8369682,0.0053454903,0.00030675525,0.0007658677,0.0000031012896,0.04075612,0.0727394],"genre_scores_gemma":[0.54064393,6.767221e-7,0.4588044,0.00017502972,0.000008284949,0.0000068138725,7.256532e-8,0.000005164098,0.0003556532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931216,0.00003862303,0.00017729883,0.00014011355,0.00018091161,0.00015088767],"domain_scores_gemma":[0.9990113,0.00036105188,0.00009244692,0.000462585,0.000039345057,0.000033286477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013999116,0.00007459781,0.00010214926,0.000037935653,0.00007554044,0.00008792365,0.00070720597,0.000024895771,0.000019078538],"category_scores_gemma":[0.00039356278,0.000045071774,0.00003886464,0.00051202974,0.000054076423,0.00023973215,0.00024656492,0.000074836,0.000004843238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036003978,0.00009979164,0.21453628,0.00011537427,0.000024758003,0.000018282877,0.00106969,0.000040447525,0.00028792187,0.044858735,0.16624457,0.57270056],"study_design_scores_gemma":[0.0008519372,0.00086195,0.009393509,0.0008797734,0.000023998546,0.00021073213,0.000028416058,0.65124494,0.034558572,0.28758258,0.013564339,0.00079926604],"about_ca_topic_score_codex":0.0000200202,"about_ca_topic_score_gemma":3.051991e-7,"teacher_disagreement_score":0.65120447,"about_ca_system_score_codex":0.000007613693,"about_ca_system_score_gemma":0.00002183557,"threshold_uncertainty_score":0.18379736},"labels":[],"label_agreement":null},{"id":"W1952910495","doi":"10.1109/enabl.1999.805197","title":"Static analysis of binary code to isolate malicious behaviors","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Executable; Program slicing; Static program analysis; Static analysis; Programming language; Slicing; Program analysis; Code (set theory); Binary code; Semantics (computer science); Source code; Binary number; Software; Software development","score_opus":0.02127857445463315,"score_gpt":0.29714079144376576,"score_spread":0.2758622169891326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1952910495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2697143,0.000010914124,0.7265163,0.00016026838,0.000041863204,0.00007256852,0.0000026120479,0.0027820745,0.00069908815],"genre_scores_gemma":[0.6262445,8.5434885e-7,0.3731856,0.0003767273,9.786819e-7,0.0000065778936,5.8842994e-7,0.0000037445484,0.00018047146],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991521,0.000055469183,0.00020994396,0.00024153687,0.00016669057,0.00017425588],"domain_scores_gemma":[0.9990419,0.00015566075,0.000058815207,0.000585465,0.000077167555,0.00008095486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028838922,0.000087475106,0.00020035877,0.00044963922,0.000038479153,0.00003303465,0.00040629678,0.00002888579,0.000029682711],"category_scores_gemma":[0.00015353633,0.00007688254,0.00007638699,0.0018384563,0.0000172026,0.000080519516,0.00008220478,0.000044391814,0.000012789673],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028185468,0.0017708124,0.62602884,0.00010165851,0.0014031673,0.00029798344,0.011252992,0.019498723,0.020339422,0.12143296,0.14904527,0.048799954],"study_design_scores_gemma":[0.0007731686,0.002722969,0.24754494,0.00016135837,0.0017869091,0.00007136022,0.0000935765,0.6475948,0.038349748,0.054248847,0.004423162,0.002229142],"about_ca_topic_score_codex":0.0002444431,"about_ca_topic_score_gemma":0.000020302268,"teacher_disagreement_score":0.6280961,"about_ca_system_score_codex":0.000019355513,"about_ca_system_score_gemma":0.00002951664,"threshold_uncertainty_score":0.3135179},"labels":[],"label_agreement":null},{"id":"W1953128469","doi":"10.1109/scam.2001.972662","title":"A hybrid program slicing framework","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Program slicing; Slicing; Computer science; Program comprehension; Executable; Debugging; Programming language; Software maintenance; Software; Object-oriented programming; Software engineering; Software system","score_opus":0.032270738660680844,"score_gpt":0.276433132802871,"score_spread":0.24416239414219018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953128469","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002125719,0.000072619885,0.93579185,0.000806449,0.000108642955,0.00011117898,8.539855e-8,0.04843324,0.012550223],"genre_scores_gemma":[0.39215043,0.0000027668607,0.60691625,0.0006195987,0.000032897784,0.00002129246,8.706724e-8,0.000004382095,0.00025231641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992679,0.000017771203,0.00010745806,0.00023757968,0.00014786534,0.00022142717],"domain_scores_gemma":[0.99914587,0.00020532148,0.00002918642,0.0005240746,0.000033453944,0.00006211376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011599753,0.00008291416,0.00008202622,0.000058531674,0.00008438743,0.00017236486,0.0005489926,0.000030511384,0.000053508677],"category_scores_gemma":[0.00027963982,0.00006969683,0.00003669187,0.00022204232,0.000019432937,0.00015825841,0.00014682392,0.00012644916,0.0001505616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.8302447e-7,0.00009266688,0.0015230452,0.000004907589,0.0000035905198,0.000025122505,0.00019849613,0.0000024813685,0.0000043034865,0.030207219,0.10962605,0.85831195],"study_design_scores_gemma":[0.00009217195,0.00025854426,0.00059587276,0.00011242922,0.00000329379,0.0001519486,0.0000014054974,0.54916257,0.001258735,0.42896217,0.019030664,0.00037017654],"about_ca_topic_score_codex":0.000026688296,"about_ca_topic_score_gemma":2.1401819e-7,"teacher_disagreement_score":0.85794175,"about_ca_system_score_codex":0.00001335896,"about_ca_system_score_gemma":0.0000044496037,"threshold_uncertainty_score":0.28421542},"labels":[],"label_agreement":null},{"id":"W1956656014","doi":"10.1007/3-540-44830-6_15","title":"Fault Diagnosis in Extended Finite State Machines","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Finite-state machine; Computer science; Test suite; State (computer science); Suite; Fault (geology); Finite state; Algorithm; Test case; Machine learning","score_opus":0.020160453791129414,"score_gpt":0.26465815315733293,"score_spread":0.24449769936620352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1956656014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011272608,0.00071560126,0.99342525,0.00074053777,0.0010875409,0.00036930596,0.000006624901,0.002259171,0.0012832384],"genre_scores_gemma":[0.06991727,0.00019605263,0.9248983,0.004309698,0.00015840428,0.00006545737,0.0000049387922,0.0000648493,0.0003850161],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957508,0.00007682295,0.0006592483,0.0017740618,0.00090365653,0.0008354127],"domain_scores_gemma":[0.99577427,0.0019086301,0.00029732857,0.0016491706,0.00019914295,0.00017146919],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001246385,0.00064972666,0.00063943746,0.0014363694,0.00018270656,0.000563489,0.003303803,0.00029693646,0.000014792163],"category_scores_gemma":[0.0007709268,0.00059803866,0.00012941688,0.0010856864,0.00049212977,0.0005154662,0.0010907801,0.0010399413,0.000028959532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031968561,0.000053443735,0.0017623882,0.000034627436,0.0000052106557,0.0004137159,0.0005558921,0.015309648,0.0000038929006,0.001763738,0.0003459201,0.9797483],"study_design_scores_gemma":[0.00020413577,0.00014253915,0.0005421765,0.00063889165,0.0000033708297,0.00008735077,1.3904143e-8,0.2801848,0.00032452104,0.7158982,0.00122933,0.0007446249],"about_ca_topic_score_codex":0.000136009,"about_ca_topic_score_gemma":0.00013664123,"teacher_disagreement_score":0.9790037,"about_ca_system_score_codex":0.00029947187,"about_ca_system_score_gemma":0.00033041672,"threshold_uncertainty_score":0.9996471},"labels":[],"label_agreement":null},{"id":"W1959797194","doi":"10.1007/978-3-642-31057-7_30","title":"Application-Only Call Graph Construction","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Call graph; Computer science; Graph; Theoretical computer science; Programming language","score_opus":0.013995644423430504,"score_gpt":0.24472505283389454,"score_spread":0.23072940841046402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1959797194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013164164,0.00060034276,0.9916472,0.0003577781,0.0011242578,0.00032787514,0.0000029212413,0.0038056544,0.0021208264],"genre_scores_gemma":[0.07829445,0.000038619655,0.9201715,0.0008731374,0.00047748993,0.000018500996,0.000005464871,0.00003069966,0.000090147805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99698305,0.000025509864,0.0004331319,0.0012085874,0.0007501396,0.0005995514],"domain_scores_gemma":[0.99708813,0.00053717114,0.00031047477,0.001617839,0.00025652352,0.00018983192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007889556,0.00044024247,0.00038745612,0.0008011725,0.00026396126,0.0003333879,0.0026205047,0.0003384859,0.0000070423052],"category_scores_gemma":[0.00012037266,0.000418575,0.000112883274,0.0006548959,0.00080437993,0.00051512604,0.00085616176,0.00068553514,0.00005968016],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001036344,0.000013588202,0.00095394993,0.000016558964,0.0000046141317,0.0000070384085,0.00015159491,0.00048987806,0.000022443865,0.03367247,0.00013119767,0.96453565],"study_design_scores_gemma":[0.00011142208,0.00007607608,0.0004831036,0.00022342133,0.0000102996355,0.00039735637,1.4923176e-8,0.076600134,0.00044806438,0.9179512,0.0030001195,0.00069876097],"about_ca_topic_score_codex":0.000055760167,"about_ca_topic_score_gemma":0.000015004016,"teacher_disagreement_score":0.96383685,"about_ca_system_score_codex":0.00021296034,"about_ca_system_score_gemma":0.00042179634,"threshold_uncertainty_score":0.9998266},"labels":[],"label_agreement":null},{"id":"W1962250603","doi":"10.1109/esem.2015.7321218","title":"Will This Bug-Fixing Change Break Regression Testing?","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regression testing; Computer science; Regression analysis; Machine learning; Programming language; Software; Software development","score_opus":0.15915339063956024,"score_gpt":0.3114980059185787,"score_spread":0.15234461527901844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1962250603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009364437,0.00065602385,0.8127023,0.0044803605,0.0011886305,0.00042592504,0.0000014279378,0.08559494,0.085585974],"genre_scores_gemma":[0.4015623,0.000002131176,0.59572554,0.0014179457,0.00022210876,0.000030032628,0.0000010660267,0.000015188864,0.0010236875],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877524,0.000052849773,0.00016612365,0.00037300983,0.00033410336,0.00029865265],"domain_scores_gemma":[0.9985269,0.00030119834,0.00008803959,0.00067015976,0.00022268663,0.00019101784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005828865,0.00015265468,0.00014482545,0.00011827504,0.00011128883,0.00015103257,0.0007557553,0.00007539132,0.000009686041],"category_scores_gemma":[0.00119748,0.00011351675,0.000032613756,0.0005332645,0.000031847685,0.000913587,0.0004755094,0.00013369528,0.00008449813],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006283636,0.00012472765,0.09395907,0.000028371776,0.000008679145,0.000112698595,0.002697248,0.000003351099,0.00023031762,0.0055541676,0.5564756,0.3407995],"study_design_scores_gemma":[0.0016808821,0.0015251643,0.01619217,0.001950473,0.000029399856,0.0012201513,0.000046271536,0.32397163,0.009130392,0.55315536,0.08849192,0.0026061938],"about_ca_topic_score_codex":0.0007383232,"about_ca_topic_score_gemma":0.000003653725,"teacher_disagreement_score":0.5476012,"about_ca_system_score_codex":0.00005286033,"about_ca_system_score_gemma":0.000065512824,"threshold_uncertainty_score":0.46290788},"labels":[],"label_agreement":null},{"id":"W1963583462","doi":"10.1109/issre.2012.20","title":"Mutation Testing of Event Processing Queries","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Event (particle physics); Benchmark (surveying); Complex event processing; Mutation; Data mining; Process (computing); SQL; Quality (philosophy); Mutation testing; Database; Programming language","score_opus":0.0418201916147039,"score_gpt":0.29719331305155433,"score_spread":0.2553731214368504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963583462","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027296599,0.000122068035,0.9650761,0.000059404792,0.00005403496,0.000038484908,7.2568156e-8,0.004595184,0.0027580524],"genre_scores_gemma":[0.5442558,1.05337726e-7,0.45567316,0.000030487345,0.000014812552,0.000003077669,1.2655073e-7,0.0000018625836,0.000020611804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995357,0.000015988104,0.00012535759,0.00007930912,0.00011315035,0.00013052447],"domain_scores_gemma":[0.99950385,0.00015627849,0.000078681514,0.00014206959,0.0000883281,0.00003080338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028989385,0.000047543475,0.000059703172,0.0000463019,0.000048375463,0.00002642484,0.00016314491,0.000018110382,0.0000017938332],"category_scores_gemma":[0.00049395685,0.000039613766,0.000013100004,0.00024878062,0.000018933559,0.000444565,0.000068319016,0.00003103185,0.0000030234842],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.079313e-7,0.00008024478,0.13162452,0.00007178897,0.000002852395,0.0000013165374,0.00197483,0.00003096457,0.0009157717,0.012456092,0.0012894005,0.8515513],"study_design_scores_gemma":[0.00037578595,0.00042995237,0.19695093,0.0007750334,0.00002210132,0.00035362548,0.0001160408,0.3936271,0.22450876,0.18083008,0.0010807059,0.0009299039],"about_ca_topic_score_codex":0.00005995758,"about_ca_topic_score_gemma":4.2260297e-7,"teacher_disagreement_score":0.8506214,"about_ca_system_score_codex":0.000010835966,"about_ca_system_score_gemma":0.000029316012,"threshold_uncertainty_score":0.16154024},"labels":[],"label_agreement":null},{"id":"W1963871921","doi":"10.1145/2532352.2532353","title":"Document driven certification of computational science and engineering software","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Software engineering; Computer science; Documentation; Certification; Programmer; Programming language; Traceability; Software development; Verification and validation; Software quality; Software construction; Software requirements specification; Software; Engineering","score_opus":0.013694360057219442,"score_gpt":0.23651953913174364,"score_spread":0.2228251790745242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963871921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0513666,0.00001329563,0.94594276,0.00036338344,0.00003656461,0.00009612759,1.415122e-7,0.00209456,0.00008657546],"genre_scores_gemma":[0.5200536,4.0212927e-7,0.4798922,0.000034610835,0.0000025957036,0.000007949715,2.1340475e-7,0.0000013075295,0.0000070989986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993523,0.0000050671097,0.000114211354,0.00017351712,0.00025438034,0.00010055606],"domain_scores_gemma":[0.9992834,0.00014739938,0.000039458264,0.00018629323,0.0002954062,0.000048041897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019819349,0.000048788563,0.00005496547,0.00011676197,0.000056350775,0.00010979887,0.00031290017,0.000013618654,0.0000057140924],"category_scores_gemma":[0.0003181549,0.000042811145,0.000008149018,0.00030467115,0.000074001735,0.00045742758,0.00014947423,0.000029301062,0.0000067551277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018791637,0.00015197186,0.050533496,0.00016840512,0.000024379713,0.0000023955563,0.0023526629,0.017540557,0.019937765,0.23092723,0.022572663,0.6557866],"study_design_scores_gemma":[0.000081258375,0.00005102179,0.123680905,0.000038258084,0.0000015335452,0.0000133789445,0.0000028721972,0.7733951,0.0061049596,0.096424736,0.00006431056,0.00014166006],"about_ca_topic_score_codex":0.00007148176,"about_ca_topic_score_gemma":1.3207082e-7,"teacher_disagreement_score":0.75585455,"about_ca_system_score_codex":0.00002572967,"about_ca_system_score_gemma":0.00005295929,"threshold_uncertainty_score":0.17457879},"labels":[],"label_agreement":null},{"id":"W1965117069","doi":"10.1145/2070336.2070357","title":"Enhancing spark's contract checking facilities using symbolic execution","year":2011,"lang":"en","type":"article","venue":"ACM SIGAda Ada Letters","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Symbolic execution; SPARK (programming language); Software engineering; Usability; Programming language; Automation; Design by contract; Software; Model checking; Formal methods; Software development; Software construction; Operating system; Engineering","score_opus":0.06601541650421534,"score_gpt":0.25624669602452055,"score_spread":0.19023127952030522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965117069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52259547,0.000078529025,0.47224662,0.00032266244,0.00032166144,0.000109347275,0.0000012167569,0.004124087,0.00020041094],"genre_scores_gemma":[0.73467857,0.0000021337505,0.2635339,0.0016692481,0.00007775585,0.000010936705,0.0000011407614,0.000014598409,0.0000117191275],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983309,0.000081309874,0.00032054432,0.00045641075,0.0003170657,0.00049380574],"domain_scores_gemma":[0.9983162,0.0003672179,0.00016065183,0.0010002076,0.00006111559,0.00009460219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042745873,0.00023224439,0.00023697378,0.00016184288,0.00023117579,0.00015376645,0.0011299015,0.00007785767,0.000016452726],"category_scores_gemma":[0.0006658025,0.00023533354,0.00008849719,0.0002667883,0.000080967475,0.0006870411,0.0003569728,0.00022408526,0.000016497968],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006784341,0.00027931237,0.06071586,0.00037477573,0.00025162855,0.0008546796,0.052694388,0.00031161308,0.80829525,0.008330189,0.018318182,0.049506295],"study_design_scores_gemma":[0.0012286954,0.00031226047,0.038052846,0.0016175635,0.000103406084,0.00068502926,0.00031261527,0.039131556,0.85673517,0.055704672,0.0028811423,0.0032350256],"about_ca_topic_score_codex":0.0025344722,"about_ca_topic_score_gemma":0.000019240502,"teacher_disagreement_score":0.2120831,"about_ca_system_score_codex":0.00011085384,"about_ca_system_score_gemma":0.00005834852,"threshold_uncertainty_score":0.9596623},"labels":[],"label_agreement":null},{"id":"W1967187747","doi":"10.1007/s10515-011-0093-0","title":"Prioritizing test cases with string distances","year":2011,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":125,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; String (physics); Computer science; Random testing; Code (set theory); Test case; Algorithm; Property (philosophy); Suite; Test (biology); Data mining; Mathematics; Machine learning; Programming language","score_opus":0.019894860361199286,"score_gpt":0.21321092719486978,"score_spread":0.1933160668336705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967187747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06265202,0.00027908958,0.8099237,0.000007692455,0.00016620122,0.00012492044,0.000004552677,0.12676029,0.00008151012],"genre_scores_gemma":[0.55881816,0.0000035919213,0.4410919,0.000016807686,0.000019796827,0.00001707644,0.0000015889235,0.000023388218,0.000007682995],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987245,0.000011808471,0.00021985703,0.000388863,0.00022421655,0.00043074464],"domain_scores_gemma":[0.998471,0.00073222094,0.00007672774,0.0005236892,0.0000810785,0.00011525441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015651,0.00024636457,0.00020194278,0.00016755679,0.00013265581,0.00013423101,0.00059486757,0.00006828119,0.0000024650362],"category_scores_gemma":[0.0009920719,0.00022215655,0.000039080325,0.00057884265,0.000028479948,0.0005427253,0.00014443592,0.00017644984,0.000010528012],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005477021,0.0009697861,0.78552204,0.0012752295,0.00047107963,0.012319081,0.014773709,0.0044429037,0.002822207,0.038921025,0.010449682,0.1279785],"study_design_scores_gemma":[0.0015551953,0.0018356701,0.29444796,0.0042056246,0.000107592066,0.00470699,0.00006854574,0.6601063,0.023248056,0.003551501,0.0016050447,0.00456149],"about_ca_topic_score_codex":0.00010730385,"about_ca_topic_score_gemma":0.000004500158,"teacher_disagreement_score":0.65566343,"about_ca_system_score_codex":0.00005773294,"about_ca_system_score_gemma":0.000046684123,"threshold_uncertainty_score":0.90592813},"labels":[],"label_agreement":null},{"id":"W1967729292","doi":"10.1145/1541822.1541824","title":"Cookies","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Software deployment; Web testing; Web application security; The Internet; Web engineering; World Wide Web; Web application; Software engineering; Test strategy; Web analytics; Software; Web development; Computer security; Programming language","score_opus":0.028206095281323475,"score_gpt":0.2571300410262274,"score_spread":0.2289239457449039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967729292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019226839,0.00002680054,0.96667486,0.021963116,0.00012051512,0.00007475297,0.0000012465026,0.007364205,0.0018518352],"genre_scores_gemma":[0.9141318,0.000011707796,0.08309252,0.0024582054,0.000014723452,0.000009660133,1.2722347e-7,0.000003314039,0.00027792825],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994899,0.000034447698,0.000079579135,0.00014775015,0.00012557523,0.00012276783],"domain_scores_gemma":[0.99860024,0.00038473433,0.000020980962,0.000939064,0.000026453496,0.000028551392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016512003,0.000074501324,0.000058691272,0.000058322254,0.00022909889,0.000076864024,0.0009661157,0.000029412166,0.000016506634],"category_scores_gemma":[0.0000836198,0.00004984763,0.00004912377,0.0002554375,0.00002753077,0.00010832016,0.0000049498644,0.0001397073,0.00007898258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007186734,0.0001777942,0.000032322157,0.0000023075982,0.000016292759,0.00000843559,0.0004597847,0.00015947528,0.00054032076,0.032145113,0.03813488,0.9283161],"study_design_scores_gemma":[0.00017694675,0.0003686533,0.0010338572,0.000054966367,0.000012112193,0.00006219273,0.000009903095,0.018000124,0.0122529995,0.9606854,0.0070659537,0.00027694475],"about_ca_topic_score_codex":0.000007851743,"about_ca_topic_score_gemma":0.0000014593279,"teacher_disagreement_score":0.9285402,"about_ca_system_score_codex":0.000013981241,"about_ca_system_score_gemma":0.00002418287,"threshold_uncertainty_score":0.20327273},"labels":[],"label_agreement":null},{"id":"W1968023441","doi":"10.5555/2818754.2818831","title":"DASE: document-assisted symbolic execution for improving automated software testing","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Symbolic execution; Computer science; Documentation; Heuristics; Software; Programming language; Focus (optics); Software bug; Static analysis; Software engineering; Data mining; Operating system","score_opus":0.06403600449072984,"score_gpt":0.30777833418900413,"score_spread":0.2437423296982743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968023441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005053209,0.000054632335,0.9070886,0.0001863517,0.00026693844,0.00032172046,0.0000019884885,0.086496264,0.000530335],"genre_scores_gemma":[0.31709167,1.1320595e-7,0.68236464,0.00022526862,0.000049143764,0.00008270022,0.000007790409,0.000015266141,0.0001634045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985198,0.00004934123,0.0002934736,0.00045986153,0.00026963992,0.00040792229],"domain_scores_gemma":[0.998035,0.0005985473,0.00015003291,0.0005880016,0.0004430905,0.00018531365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074309163,0.00018569248,0.00018395808,0.0001495206,0.00019264921,0.00033435834,0.0006556452,0.000090308306,0.0000014148394],"category_scores_gemma":[0.0039218613,0.00016746418,0.000051943563,0.0005793909,0.000028412644,0.00054133,0.0002827651,0.00008962421,0.000017059287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017815846,0.00016855613,0.009771464,0.00018595981,0.00003021404,0.000030284582,0.0007290398,0.00016713071,0.0021635587,0.008425066,0.15045579,0.8278551],"study_design_scores_gemma":[0.00096427224,0.00045600496,0.0034680322,0.00013018034,0.00002280442,0.00015277379,0.000018005136,0.928667,0.004522392,0.06011955,0.00086295075,0.00061603665],"about_ca_topic_score_codex":0.0003546543,"about_ca_topic_score_gemma":0.000003960042,"teacher_disagreement_score":0.9284999,"about_ca_system_score_codex":0.00013646542,"about_ca_system_score_gemma":0.00020863628,"threshold_uncertainty_score":0.6828991},"labels":[],"label_agreement":null},{"id":"W1969019712","doi":"10.5555/1899721.1899863","title":"Managing verification error traces with bounded model debugging","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Vennsa Technologies (Canada)","funders":"","keywords":"Debugging; Debugger; Computer science; Bounded function; Model checking; Key (lock); Programming language; Theoretical computer science; Computer engineering; Operating system","score_opus":0.021675010745560185,"score_gpt":0.2617063323891501,"score_spread":0.2400313216435899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969019712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024095574,0.000009922156,0.9527354,0.0013987111,0.000079752936,0.00008687517,1.795085e-7,0.015498256,0.006095322],"genre_scores_gemma":[0.50626117,5.905069e-7,0.4933775,0.00017080917,0.000012038905,0.000012428614,5.6042546e-7,0.000006249808,0.00015865357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991455,0.000011860143,0.0001179109,0.0003255654,0.00018866333,0.00021047427],"domain_scores_gemma":[0.99911755,0.00007670704,0.000058406313,0.00061952445,0.00006546314,0.00006236459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025625798,0.00011157464,0.00008842819,0.00010004099,0.00017733902,0.00025004492,0.00058950234,0.00004442626,0.000005249905],"category_scores_gemma":[0.000052290536,0.000087252694,0.000021958433,0.00022684295,0.0000453528,0.00047666806,0.000071914226,0.00017742862,0.000012264889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002732788,0.00024068644,0.008752429,0.00006611513,0.000045073208,0.000036647278,0.0029307585,0.0037981865,0.014510472,0.40177107,0.018383272,0.54943794],"study_design_scores_gemma":[0.000076502816,0.000023097406,0.0005094573,0.000013581851,0.0000035524113,0.000027919683,0.000002655108,0.84662676,0.0026272812,0.14979608,0.00014760501,0.00014552164],"about_ca_topic_score_codex":0.00006460877,"about_ca_topic_score_gemma":0.00004146644,"teacher_disagreement_score":0.8428286,"about_ca_system_score_codex":0.000012926504,"about_ca_system_score_gemma":0.00006265657,"threshold_uncertainty_score":0.35580614},"labels":[],"label_agreement":null},{"id":"W1969596141","doi":"10.3166/jesa.43.889-904","title":"Test exhaustif de contrôleurs logiques spécifiés en Grafcet Apports et limites d'une modélisation par machines de Mealy","year":2009,"lang":"fr","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche","keywords":"Mathematics","score_opus":0.03647001407798449,"score_gpt":0.30049436481604463,"score_spread":0.26402435073806013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969596141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09725787,0.010664033,0.86428666,0.01349135,0.001170344,0.00050506345,0.000032688204,0.010187167,0.0024048483],"genre_scores_gemma":[0.6592117,0.001561419,0.33547783,0.0019230141,0.000737934,0.00001494938,0.000008107625,0.00007356778,0.0009914794],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934799,0.0021243724,0.001423106,0.0007261548,0.00085038954,0.0013960785],"domain_scores_gemma":[0.9940184,0.0026502958,0.0012288078,0.0007454829,0.000650911,0.0007061515],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005323936,0.00077044807,0.0008959195,0.0005154696,0.0007837016,0.0022348352,0.0013607363,0.00043372638,0.00004180863],"category_scores_gemma":[0.0070849997,0.0007287031,0.00036804934,0.0009679198,0.00035267332,0.0018029393,0.00022857278,0.0013238007,0.000056168912],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002511664,0.000565054,0.044694945,0.0002621835,0.00010013914,0.0022361588,0.00572119,0.003224853,0.0015076288,0.006273274,0.06063486,0.8747546],"study_design_scores_gemma":[0.00038053942,0.0009299415,0.42183012,0.0018055195,0.00011661456,0.01210643,0.00002589656,0.30030018,0.0006399771,0.2603316,0.00095510104,0.0005780665],"about_ca_topic_score_codex":0.000793575,"about_ca_topic_score_gemma":0.00005244485,"teacher_disagreement_score":0.87417656,"about_ca_system_score_codex":0.00078607176,"about_ca_system_score_gemma":0.0009622959,"threshold_uncertainty_score":0.9995164},"labels":[],"label_agreement":null},{"id":"W1971159340","doi":"10.1145/2534397","title":"Test compaction techniques for assertion-based test generation","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Design Automation of Electronic Systems","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"","keywords":"Assertion; Computer science; Compaction; Test (biology); Automatic test pattern generation; Path (computing); Scheme (mathematics); Reduction (mathematics); Test case; Cluster analysis; Algorithm; Programming language; Artificial intelligence; Machine learning; Mathematics","score_opus":0.03796342581928601,"score_gpt":0.272911710833078,"score_spread":0.234948285013792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971159340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057971117,0.000049779374,0.9904862,0.00058991,0.00016866348,0.0016937844,0.000006129074,0.006390461,0.00003537821],"genre_scores_gemma":[0.72285396,0.000004381279,0.27568388,0.000064030086,0.00004198764,0.0012431471,0.000011861947,0.000018519404,0.00007826219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983096,0.00013797979,0.0005345448,0.0003653703,0.0003173595,0.0003351564],"domain_scores_gemma":[0.9955892,0.002706799,0.0003374765,0.00080731645,0.0004987252,0.000060512273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069752074,0.00020973934,0.00024802994,0.0004000572,0.00025739105,0.00020138806,0.00055477803,0.0001492658,0.000013147751],"category_scores_gemma":[0.0006094017,0.00020556267,0.000105671315,0.00051039096,0.000029930585,0.00059919996,0.0000034392008,0.00014908583,0.00002604867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004758293,0.0030457906,0.0007232117,0.00057633076,0.00019547793,0.0000011368234,0.00046463215,0.12697937,0.37474844,0.006651944,0.051841147,0.43472496],"study_design_scores_gemma":[0.00023555449,0.0011182461,0.00018024843,0.000099370314,0.00001652295,0.000011217505,0.000003818268,0.8384647,0.15549476,0.004050916,0.0001371024,0.00018753801],"about_ca_topic_score_codex":0.00016166198,"about_ca_topic_score_gemma":0.000004254512,"teacher_disagreement_score":0.72227424,"about_ca_system_score_codex":0.0003198873,"about_ca_system_score_gemma":0.00023928922,"threshold_uncertainty_score":0.83826023},"labels":[],"label_agreement":null},{"id":"W1973085420","doi":"10.1145/1858996.1859079","title":"Search-carrying code","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Certification; Code (set theory); Programming language; Redundant code; State (computer science); Dead code; Code generation; Operating system; Key (lock)","score_opus":0.029951446062903547,"score_gpt":0.2906130173078692,"score_spread":0.26066157124496564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973085420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027985463,0.0000041275566,0.9280493,0.00091606425,0.00025822778,0.00004222205,2.3061288e-7,0.021217726,0.021526633],"genre_scores_gemma":[0.53486276,2.8836968e-7,0.46457052,0.0002673802,0.000027815524,0.0000023633413,1.3325717e-7,0.000002840237,0.00026591925],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99944544,0.000012016281,0.00006792763,0.00017769518,0.00013377651,0.00016313944],"domain_scores_gemma":[0.99925554,0.00014528737,0.000011936923,0.00047926605,0.000045726887,0.000062232524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028769957,0.000052592648,0.000050364713,0.000052327334,0.00008020056,0.000117244024,0.0006144509,0.000034659188,0.000024447765],"category_scores_gemma":[0.00015648149,0.000043589782,0.000022120212,0.0001554359,0.000028580196,0.0001551016,0.00019607795,0.00018029078,0.00008170044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014110633,0.00006538601,0.043282267,0.000012370582,0.000008022405,0.000038376773,0.0007091344,0.000008904865,0.016898453,0.35202408,0.17438808,0.4125635],"study_design_scores_gemma":[0.00041554697,0.00017232673,0.01884574,0.000046044526,0.0000047090707,0.0003273538,0.000008404598,0.37977773,0.11612812,0.43216974,0.051169783,0.00093452603],"about_ca_topic_score_codex":0.00007368665,"about_ca_topic_score_gemma":0.000009336227,"teacher_disagreement_score":0.50687724,"about_ca_system_score_codex":0.0000043456344,"about_ca_system_score_gemma":0.000029642271,"threshold_uncertainty_score":0.17775397},"labels":[],"label_agreement":null},{"id":"W1973842727","doi":"10.1145/2304510.2304517","title":"Targeted genetic test SQL generation for the DB2 database","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Polytechnique Montréal","funders":"","keywords":"Computer science; SQL; Data mining; Generator (circuit theory); Test case; Randomness; Genetic algorithm; Database; Machine learning; Mathematics","score_opus":0.05671190167372239,"score_gpt":0.2868569559503927,"score_spread":0.23014505427667029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973842727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010749295,0.000578852,0.99348265,0.00050879753,0.00029176305,0.00019987446,0.0000039634388,0.0036460857,0.00021309534],"genre_scores_gemma":[0.416564,0.0000048633265,0.5824725,0.00042274612,0.0002439758,0.00006382892,0.000004911997,0.0000052082673,0.00021798561],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939084,0.00001812598,0.00010466042,0.00015299044,0.0001087909,0.00022460459],"domain_scores_gemma":[0.99856085,0.0007251263,0.000034461584,0.00056948245,0.00005778877,0.00005231952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037224696,0.00007390182,0.00005109045,0.000029179182,0.00018026747,0.00009166783,0.0004374637,0.000024682564,0.000010394829],"category_scores_gemma":[0.0006046519,0.000046518977,0.000027079157,0.00013848922,0.000018145638,0.00024483047,0.00011652739,0.000041883344,0.000021773922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015305849,0.00015506876,0.017168142,0.000013679228,0.000012788374,9.867175e-7,0.00051158713,0.00004438868,0.01143645,0.017060416,0.8630231,0.09057184],"study_design_scores_gemma":[0.00017674302,0.00009837682,0.00761577,0.000009490299,0.000015903615,0.000027227885,0.0000031398604,0.93807966,0.023875682,0.006037604,0.023797354,0.00026304083],"about_ca_topic_score_codex":0.000041049658,"about_ca_topic_score_gemma":0.0000034989152,"teacher_disagreement_score":0.9380353,"about_ca_system_score_codex":0.000012162594,"about_ca_system_score_gemma":0.000021813536,"threshold_uncertainty_score":0.18969889},"labels":[],"label_agreement":null},{"id":"W1974201381","doi":"10.1145/1463788.1463817","title":"SIFT","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Western University","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Scale-invariant feature transform; Software; Software development; Scalability; Set (abstract data type); Software system; Programming language; Artificial intelligence; Operating system; Feature extraction","score_opus":0.03447392060513783,"score_gpt":0.23421270695678428,"score_spread":0.19973878635164646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974201381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003967748,0.000018314002,0.94368136,0.0003371163,0.00005718442,0.000017861094,2.9054348e-8,0.022635477,0.029284893],"genre_scores_gemma":[0.52160853,0.000001854894,0.4771706,0.00046678013,0.00001190075,0.0000018130715,6.026621e-8,0.0000014041634,0.0007370901],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996833,0.000006820623,0.000045481844,0.0001048526,0.00007569939,0.000083812265],"domain_scores_gemma":[0.99960995,0.00006242237,0.000009632138,0.0002702038,0.000019873327,0.000027933183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005132293,0.000033123186,0.000035011126,0.000028226272,0.00006466524,0.0000141109995,0.00031273533,0.000013952188,0.000009398601],"category_scores_gemma":[0.00006174937,0.000026699554,0.00001541764,0.00012052499,0.000016130149,0.000101885715,0.00007983039,0.000029173327,0.000094103314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.4724325e-7,0.000049917366,0.030143134,0.0000025244863,0.0000034815591,0.000107686465,0.00046000286,0.00000389301,0.0000920828,0.0932013,0.8143472,0.061588198],"study_design_scores_gemma":[0.00049866183,0.00035896624,0.08997586,0.00003714746,0.000002948959,0.0021879685,0.0000026603072,0.11562225,0.019712033,0.6801811,0.09038101,0.001039401],"about_ca_topic_score_codex":0.000029704699,"about_ca_topic_score_gemma":2.756015e-7,"teacher_disagreement_score":0.72396624,"about_ca_system_score_codex":0.0000044002654,"about_ca_system_score_gemma":0.000016523032,"threshold_uncertainty_score":0.12095391},"labels":[],"label_agreement":null},{"id":"W1974536975","doi":"10.1145/1639622.1639623","title":"Run-time conformance checking of mobile and distributed systems using executable models","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Executable; Computer science; Conformance testing; Unified Modeling Language; Distributed computing; Mobile device; Programming language; Operating system; Software","score_opus":0.024181503865814632,"score_gpt":0.25414855034019235,"score_spread":0.2299670464743777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974536975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052836213,0.0003183135,0.94303197,0.000013303374,0.0000354806,0.0001372659,0.0000040082923,0.0028759204,0.0007475483],"genre_scores_gemma":[0.86527073,0.00000655268,0.13461618,0.000036547055,0.000009746583,0.000003654478,0.000002029057,0.0000033739548,0.0000511663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999233,0.000015340305,0.00022571532,0.00019048649,0.00014481015,0.00019064723],"domain_scores_gemma":[0.99935883,0.000069286376,0.000108726366,0.00032182434,0.00009105605,0.00005029241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024408182,0.000098691875,0.00019813541,0.000064985885,0.00007144549,0.00010588876,0.00028580273,0.000046605328,0.0000011451959],"category_scores_gemma":[0.000025061365,0.00008655721,0.000018100805,0.0002430253,0.000027566417,0.00050594716,0.00009245032,0.000052078496,0.0000013455472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005567926,0.0007167396,0.006979768,0.0007050252,0.00012689251,0.00006678687,0.0051818267,0.5831,0.06831027,0.18236436,0.029061956,0.12333069],"study_design_scores_gemma":[0.00008148527,0.00008771382,0.0000730649,0.00011212739,0.000003143028,0.00003248386,0.000004364168,0.9882194,0.0022274128,0.008990563,0.000056156976,0.0001121234],"about_ca_topic_score_codex":0.00012217641,"about_ca_topic_score_gemma":6.935964e-8,"teacher_disagreement_score":0.81243455,"about_ca_system_score_codex":0.000022501004,"about_ca_system_score_gemma":0.000032070882,"threshold_uncertainty_score":0.35297006},"labels":[],"label_agreement":null},{"id":"W1975057653","doi":"10.1142/s0218194010004621","title":"ASSESSING TEST SUITES FOR BUFFER OVERFLOW VULNERABILITIES","year":2010,"lang":"en","type":"article","venue":"International Journal of Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Buffer overflow; Test suite; Computer science; Secure coding; Software security assurance; Benchmark (surveying); Test case; Mutation; Software; Exploit; Reliability engineering; Vulnerability (computing); Computer security; Engineering; Operating system; Machine learning; Information security","score_opus":0.01213610208872551,"score_gpt":0.27433133318351743,"score_spread":0.2621952310947919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975057653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10464574,0.0005243644,0.8898626,0.00010747945,0.0033198567,0.00006222065,0.000004821053,0.0014605409,0.000012413011],"genre_scores_gemma":[0.6011841,0.000010229298,0.39813378,0.000011794769,0.0006070625,0.000008048333,0.0000011505672,0.000021502063,0.00002229989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989421,0.00000681621,0.0003928117,0.00019302845,0.00023236114,0.00023289508],"domain_scores_gemma":[0.9942897,0.004542482,0.00013046105,0.00018629416,0.00072027044,0.00013082354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006171823,0.00020272026,0.00023449061,0.00039583148,0.00005646357,0.00046226726,0.00068431,0.000095640324,0.000002688546],"category_scores_gemma":[0.013627586,0.00019317088,0.000104355866,0.00014918347,0.000022162505,0.00084077986,0.00014070558,0.00043566342,0.0000010343647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005510281,0.0010482946,0.17088811,0.0014447952,0.0010913179,0.00031402323,0.006246776,0.03296103,0.14947513,0.040222064,0.012916859,0.58333653],"study_design_scores_gemma":[0.001474695,0.00035587474,0.028686939,0.0012869274,0.000048719114,0.0018223139,0.00002296929,0.920059,0.017760215,0.0026030268,0.024784338,0.0010949274],"about_ca_topic_score_codex":0.000003470847,"about_ca_topic_score_gemma":6.837544e-7,"teacher_disagreement_score":0.887098,"about_ca_system_score_codex":0.000053382286,"about_ca_system_score_gemma":0.00009404313,"threshold_uncertainty_score":0.99468106},"labels":[],"label_agreement":null},{"id":"W1975319166","doi":"10.1145/1321211.1321239","title":"A test framework for integration testing of object-oriented programs","year":2007,"lang":"en","type":"article","venue":"Proceedings of CASCON","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Integration testing; Unified Modeling Language; Sequence diagram; Software engineering; Class diagram; Implementation; Programming language; White-box testing; Java; Object-oriented programming; Test case; Automation; Test Management Approach; Test strategy; Model-based testing; Software development; Software; Engineering; Machine learning","score_opus":0.034891224725824996,"score_gpt":0.2971395826582922,"score_spread":0.2622483579324672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975319166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14619832,0.000046064088,0.8496361,0.00005543826,0.0000886773,0.00042913726,0.0000011196544,0.0024425685,0.0011026184],"genre_scores_gemma":[0.5024583,4.6666975e-7,0.49745896,0.000015556248,0.000032478063,0.000020374528,5.995092e-7,0.000006851692,0.0000064323362],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988441,0.0000015974493,0.00039784465,0.0002682286,0.00023339501,0.0002548256],"domain_scores_gemma":[0.99718493,0.0010779364,0.0004185981,0.00012889285,0.0011342842,0.0000553342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00096394075,0.0001257744,0.00020735714,0.00017194421,0.000057687008,0.000050275856,0.00039136125,0.00010200978,2.9398748e-7],"category_scores_gemma":[0.0084901275,0.00011566719,0.00006184499,0.0008124803,0.000065669694,0.00029117707,0.00008808665,0.00012493024,3.7519183e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041811883,0.00034153118,0.13119248,0.00045310313,0.000016973248,0.0000012392379,0.0025545575,4.3073578e-7,0.0415585,0.17452678,0.00072975503,0.6485828],"study_design_scores_gemma":[0.00038077714,0.0022020596,0.0059945523,0.0018872062,0.000025515978,0.000042115265,0.000149153,0.013223997,0.6811029,0.29440588,0.00024423384,0.00034164902],"about_ca_topic_score_codex":0.000041380732,"about_ca_topic_score_gemma":0.0000012218484,"teacher_disagreement_score":0.64824116,"about_ca_system_score_codex":0.000029042356,"about_ca_system_score_gemma":0.00003662309,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W1975581743","doi":"10.1109/icst.2012.107","title":"Generating String Test Data for Code Coverage","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Nebraska-Lincoln","keywords":"Computer science; Programming language; Grammar; Code coverage; String (physics); Heuristic; Code (set theory); Rule-based machine translation; Code generation; Java; Theoretical computer science; Natural language processing; Artificial intelligence; Mathematics; Set (abstract data type); Software; Linguistics","score_opus":0.10267725710357246,"score_gpt":0.3291761569067954,"score_spread":0.22649889980322296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975581743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016531385,0.000089186484,0.990311,0.00015426773,0.00017579725,0.00010811316,0.000020696461,0.0068473364,0.0006404094],"genre_scores_gemma":[0.36438936,0.0000014631065,0.63490844,0.0003720739,0.0001646849,0.000009992418,0.0000136257,0.000006098447,0.00013430307],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923646,0.000012145202,0.0001269042,0.00024139603,0.0001040403,0.00027906772],"domain_scores_gemma":[0.9979013,0.0009024751,0.00004511665,0.0010450566,0.000036040237,0.00006998689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006174447,0.00007898721,0.000080505284,0.00003295814,0.00013698995,0.0001436172,0.0010245419,0.000029615241,0.0000036253568],"category_scores_gemma":[0.0012943674,0.000068828274,0.00001677284,0.000106746855,0.0000089344585,0.0007146373,0.00062330277,0.00005221227,0.000008881391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019724405,0.00024434438,0.12922455,0.000057110126,0.000018824785,0.000003128694,0.00037100405,0.00012116093,0.0023849627,0.042379662,0.5286054,0.29658788],"study_design_scores_gemma":[0.00022982483,0.00007416912,0.0011544339,0.0000358243,0.000007127374,0.000032916116,0.0000025997729,0.95915383,0.004250304,0.009312642,0.025405504,0.0003408478],"about_ca_topic_score_codex":0.000024719213,"about_ca_topic_score_gemma":0.000002663388,"teacher_disagreement_score":0.95903265,"about_ca_system_score_codex":0.000015379992,"about_ca_system_score_gemma":0.000025204072,"threshold_uncertainty_score":0.28067356},"labels":[],"label_agreement":null},{"id":"W1977244105","doi":"10.1145/2559936","title":"Automated cookie collection testing","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; The King's University","funders":"","keywords":"Computer science; Web testing; Web application; Web application security; Security testing; Software engineering; World Wide Web; Web development; Web service; Operating system; Cloud computing","score_opus":0.08726401518129814,"score_gpt":0.3104312761742673,"score_spread":0.22316726099296916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977244105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032180666,0.000039363247,0.96353626,0.0001346348,0.00047656594,0.000082188715,0.0000010441934,0.032491084,0.000020795596],"genre_scores_gemma":[0.12897411,0.0000073377278,0.87072116,0.00016530689,0.00002708987,0.000039106024,7.9257796e-7,0.000019371568,0.00004571965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882925,0.00021147444,0.00019650115,0.0003805169,0.00010641842,0.0002758533],"domain_scores_gemma":[0.9926466,0.006567273,0.00005056926,0.00055574474,0.00008058334,0.00009926839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093887,0.00017938492,0.0002343313,0.00028702785,0.00021923501,0.000053322176,0.0003483219,0.00014092047,0.0000023808047],"category_scores_gemma":[0.007006174,0.00018272556,0.00004294939,0.00056949316,0.000032636697,0.00012055883,0.000020777257,0.00026991038,0.0000059900353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017827088,0.00009209381,0.0011728947,0.00010410665,0.00007010684,0.000011422791,0.0005794611,0.04225078,0.0015626374,0.0017776402,0.0010827788,0.95127827],"study_design_scores_gemma":[0.0004611598,0.0006046862,0.0045005823,0.000120728524,0.000033063498,0.0004295753,0.0000035808412,0.9754988,0.0052933423,0.010813221,0.0017483121,0.00049293786],"about_ca_topic_score_codex":0.000059782084,"about_ca_topic_score_gemma":0.0000011887824,"teacher_disagreement_score":0.95078534,"about_ca_system_score_codex":0.000033967706,"about_ca_system_score_gemma":0.000027004719,"threshold_uncertainty_score":0.8387551},"labels":[],"label_agreement":null},{"id":"W1978219123","doi":"10.5555/2818754.2818796","title":"Detecting inconsistencies in JavaScript MVC applications","year":2015,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; JavaScript; Web application; Consistency (knowledge bases); Model–view–controller; Identifier; Data mining; Software engineering; Programming language; Operating system; Artificial intelligence; User interface","score_opus":0.07089629372013515,"score_gpt":0.2861331090805849,"score_spread":0.21523681536044978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978219123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052073835,0.00004689501,0.98722625,0.00023149159,0.00057767547,0.00012773697,0.0000026850637,0.005160685,0.0014191812],"genre_scores_gemma":[0.7099158,0.0000032838195,0.28970525,0.00011444583,0.00007834446,0.00011477428,0.0000030579902,0.000010744827,0.00005431411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988809,0.000017915916,0.00023945143,0.00031732162,0.00033745685,0.00020690853],"domain_scores_gemma":[0.9989703,0.00020664868,0.000063286,0.0003423707,0.00031816275,0.00009920416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032929567,0.00014815578,0.00013035355,0.00033644028,0.000034454213,0.0001723751,0.0008465488,0.000060675866,0.0000051774527],"category_scores_gemma":[0.0018344469,0.00015832277,0.000037302787,0.00030800977,0.00001807816,0.00031590264,0.00019447366,0.00023043649,0.000038771865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037124384,0.00042810504,0.10568913,0.000095547395,0.00012290235,0.00020515648,0.005364533,0.028625596,0.00094503746,0.5608283,0.007693801,0.28996474],"study_design_scores_gemma":[0.0010487118,0.0002310239,0.0094201835,0.0007164508,0.0000072626617,0.00014149895,0.0001569076,0.8956931,0.0029065597,0.07384338,0.014599916,0.0012349882],"about_ca_topic_score_codex":0.00007031124,"about_ca_topic_score_gemma":0.000009394919,"teacher_disagreement_score":0.8670675,"about_ca_system_score_codex":0.00018036478,"about_ca_system_score_gemma":0.00010608431,"threshold_uncertainty_score":0.64562154},"labels":[],"label_agreement":null},{"id":"W1979107890","doi":"10.1109/compsac.2012.50","title":"On Capturing Effects of Modifications as Data Dependencies","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test suite; Computer science; Extended finite-state machine; Suite; Regression testing; Data mining; Representation (politics); Set (abstract data type); Test case; Finite-state machine; Theoretical computer science; Regression analysis; Algorithm; Machine learning; Software; Programming language; Software system","score_opus":0.055943871091449014,"score_gpt":0.3048740989086774,"score_spread":0.24893022781722837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979107890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027659927,0.00015014007,0.959704,0.00013903104,0.00017669647,0.00009509053,0.0000010019922,0.0045455047,0.007528609],"genre_scores_gemma":[0.8097589,0.0000019355289,0.1900055,0.00010429383,0.00001659302,0.0000055514693,0.0000013537309,0.0000030019874,0.00010285234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994484,0.00002375608,0.00008641535,0.00015249313,0.00014971019,0.00013921363],"domain_scores_gemma":[0.9979958,0.0007000728,0.000039779872,0.0011899314,0.00002576812,0.000048627702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022155527,0.0000564397,0.00006565939,0.000060454444,0.000046468274,0.00002447369,0.00096078066,0.000024414909,0.0000028899647],"category_scores_gemma":[0.0008232051,0.000045748053,0.000013297659,0.000122334,0.000017769771,0.0003473833,0.00035778346,0.00005128376,0.000040301195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029498938,0.00047537705,0.0092450045,0.00012402602,0.000029671586,0.0000053544504,0.0020086537,0.000045898523,0.0024542948,0.8504998,0.0698577,0.06525128],"study_design_scores_gemma":[0.0005539427,0.00044044055,0.051766634,0.0004830451,0.000048470396,0.00011653472,0.00002896813,0.10573053,0.41791806,0.42024967,0.0016477078,0.0010159833],"about_ca_topic_score_codex":0.00019057603,"about_ca_topic_score_gemma":0.0000012551793,"teacher_disagreement_score":0.782099,"about_ca_system_score_codex":0.0000092765795,"about_ca_system_score_gemma":0.000019370653,"threshold_uncertainty_score":0.18655513},"labels":[],"label_agreement":null},{"id":"W1980713699","doi":"10.1145/2610384.2610406","title":"DOM-based test adequacy criteria for web applications","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Code coverage; Granularity; Code (set theory); Set (abstract data type); Web application; Data mining; Test (biology); Quality (philosophy); Web testing; Measure (data warehouse); Information retrieval; Database; Web page; World Wide Web; Web application security; Software; Web development; Programming language","score_opus":0.02655093496977057,"score_gpt":0.30859088909850024,"score_spread":0.2820399541287297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980713699","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000060024755,0.00000964568,0.9824358,0.0014762984,0.00005153345,0.00026064724,0.0000031770599,0.012420597,0.0032822832],"genre_scores_gemma":[0.36147517,1.8786251e-7,0.63689154,0.0011150117,0.00006672881,0.00031838284,0.0000032438013,0.0000064202422,0.00012330698],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999323,0.000017888793,0.00013084758,0.00026749595,0.00008782378,0.00017293787],"domain_scores_gemma":[0.9977652,0.0014103798,0.000042357777,0.0006218446,0.0000991222,0.00006109962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031227336,0.00008532198,0.00008990056,0.00006764918,0.00012510836,0.00013238711,0.00060567504,0.000038158363,0.00001012435],"category_scores_gemma":[0.00051750144,0.00007448029,0.00004430823,0.00019086384,0.000025442821,0.00010184649,0.000062617015,0.000038910995,0.000038750248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004114505,0.00031567976,0.0042055915,0.000090780755,0.0000059608296,5.5947515e-7,0.000063338404,0.000018208206,0.004580051,0.21353652,0.43242824,0.34475094],"study_design_scores_gemma":[0.00032750503,0.0001790127,0.0005463932,0.000025223646,0.0000046184227,0.000003538754,4.7353677e-7,0.6791898,0.004376611,0.16761632,0.14749822,0.00023226217],"about_ca_topic_score_codex":0.000013075177,"about_ca_topic_score_gemma":0.0000018274401,"teacher_disagreement_score":0.6791716,"about_ca_system_score_codex":0.0000127063595,"about_ca_system_score_gemma":0.000047175003,"threshold_uncertainty_score":0.30372182},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03457682983096203,"score_gpt":0.2649357170513301,"score_spread":0.2303588872203681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982395839","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74745286,0.00018054826,0.20586921,0.00046941874,0.00012226416,0.00037308186,0.000006595544,0.04511643,0.00040956726],"genre_scores_gemma":[0.48002267,0.000012752895,0.5196669,0.0001569893,0.000029466233,0.000022949607,0.0000062540003,0.000010935836,0.00007108366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983387,0.0001421461,0.00036543998,0.0006952132,0.00019707308,0.0002614226],"domain_scores_gemma":[0.99780685,0.0009914916,0.0001302211,0.0006429853,0.0002921439,0.0001363296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008853673,0.0001928843,0.00017702035,0.00006933148,0.0004361436,0.0002682875,0.00024686955,0.00009280637,0.000005619912],"category_scores_gemma":[0.005012273,0.00018022265,0.000019652422,0.00058471883,0.00015607888,0.0003601401,0.00008716468,0.00017891,0.000011654979],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046620507,0.00007217468,0.116514646,0.0000742427,0.000004572283,0.000003922684,0.00044217033,0.00063666515,0.00088983885,0.000118504955,0.0022621308,0.87897646],"study_design_scores_gemma":[0.00018394992,0.00011316361,0.19686529,0.00006690897,0.0000076105794,0.000067144974,0.0000017956635,0.78770846,0.00027710735,0.013871395,0.0005394077,0.00029778611],"about_ca_topic_score_codex":0.0002536048,"about_ca_topic_score_gemma":0.000002054479,"teacher_disagreement_score":0.8786787,"about_ca_system_score_codex":0.0000475142,"about_ca_system_score_gemma":0.00007980576,"threshold_uncertainty_score":0.73492664},"labels":[],"label_agreement":null},{"id":"W1984849298","doi":"10.1109/cseet.2010.29","title":"Current State of the Software Testing Education in North American Academia and Some Recommendations for the New Educators","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Florida Institute of Technology; University of Florida; Purdue University","keywords":"Software testing; Curriculum; Software peer review; Software; Software engineering; State (computer science); System integration testing; Computer science; Engineering management; Engineering ethics; Software development; Medical education; Software construction; Engineering; Psychology; Pedagogy; Medicine","score_opus":0.028580521714709435,"score_gpt":0.326672967562545,"score_spread":0.29809244584783556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984849298","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7202861,0.0002220139,0.2581193,0.017891683,0.0012910293,0.00070866395,0.0000058870387,0.0014583159,0.000017086903],"genre_scores_gemma":[0.44737568,0.0000225058,0.5517423,0.0006454525,0.00008748088,0.000061072526,0.0000014434667,0.000007863625,0.000056149987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994022,0.000024931915,0.0001807683,0.0001749211,0.00008249827,0.00013464909],"domain_scores_gemma":[0.99797887,0.0013882626,0.00015695063,0.00035417694,0.000074875614,0.000046873414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025535177,0.00007571654,0.00007931505,0.00006707993,0.00013005703,0.0000495418,0.00054209295,0.000015902751,5.063307e-7],"category_scores_gemma":[0.0015641111,0.00004489466,0.00002162795,0.00055917696,0.000077166595,0.00016546738,0.00016164094,0.00034875,3.6028095e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.2087746e-7,0.000018543777,0.17899582,0.0000045791244,9.593982e-7,3.617321e-9,0.00027979232,0.000003193209,0.0000075276002,0.00044263244,0.012938975,0.80730766],"study_design_scores_gemma":[0.00008184411,0.00003986436,0.91864663,0.00005655021,0.0000068620066,0.000004954105,0.00002002528,0.005167722,0.0003778282,0.068252936,0.007201722,0.0001430529],"about_ca_topic_score_codex":0.0007227825,"about_ca_topic_score_gemma":0.00064700836,"teacher_disagreement_score":0.8071646,"about_ca_system_score_codex":0.000015853377,"about_ca_system_score_gemma":0.00062161486,"threshold_uncertainty_score":0.18725},"labels":[],"label_agreement":null},{"id":"W1986024814","doi":"10.1007/s11219-013-9203-5","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2013,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Manual testing; Code coverage; Regression testing; Test (biology); Software engineering; Graphical user interface testing; Reliability engineering; Test harness; Programming language; Software; Engineering; Software development; User interface; Software construction; Machine learning","score_opus":0.044124431323995406,"score_gpt":0.31495280582406704,"score_spread":0.27082837450007163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986024814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3127856,0.00047403152,0.67092526,0.0015607802,0.00087923126,0.00029020954,0.000027683103,0.012498986,0.00055820646],"genre_scores_gemma":[0.4497939,0.000019324418,0.5485925,0.00082742807,0.00040897776,0.000022634535,0.00000808861,0.000029957211,0.0002971634],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970093,0.00037417235,0.00084109587,0.00053961703,0.00062447897,0.0006113457],"domain_scores_gemma":[0.98949397,0.007897105,0.00056721526,0.0009827893,0.00063233665,0.00042659117],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013425177,0.00031027693,0.00041342943,0.0001606392,0.00067105354,0.0012382091,0.0012782876,0.00015765082,0.0002964768],"category_scores_gemma":[0.019695498,0.0002831947,0.00018551166,0.00044463895,0.00010860752,0.0010908463,0.00035026393,0.00070391706,0.00032976782],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058126834,0.0002630132,0.6208603,0.000027297589,0.000045634595,0.00020217868,0.0011215988,0.000007231225,0.00035243883,0.00020916873,0.13005118,0.24685417],"study_design_scores_gemma":[0.001004533,0.0006206285,0.5185486,0.000688762,0.000039470437,0.002705282,0.00012720657,0.0027217492,0.0013061396,0.46745294,0.003299395,0.0014852764],"about_ca_topic_score_codex":0.0051927213,"about_ca_topic_score_gemma":0.0000750686,"teacher_disagreement_score":0.46724376,"about_ca_system_score_codex":0.00013804533,"about_ca_system_score_gemma":0.0002343179,"threshold_uncertainty_score":0.99996203},"labels":[],"label_agreement":null},{"id":"W1986867802","doi":"10.1016/j.entcs.2007.08.002","title":"Can a Model Checker Generate Tests for Non-Deterministic Systems?","year":2007,"lang":"en","type":"article","venue":"Electronic Notes in Theoretical Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Model checking; Computer science; Determinism; Modular design; Counterexample; Model-based testing; Programming language; Theoretical computer science; CTL*; Temporal logic; Software; Distributed computing; Test case; Mathematics; Machine learning","score_opus":0.017236272022157544,"score_gpt":0.2968998082688012,"score_spread":0.27966353624664364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986867802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025830347,0.00006159863,0.9714103,0.00026586806,0.00034450254,0.00044761496,0.0000017463825,0.0014988574,0.0001392014],"genre_scores_gemma":[0.6473121,0.0000018649496,0.3522244,0.00031355195,0.00009251084,0.000037350426,6.1771595e-7,0.000013217138,0.000004372953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632037,0.00004758809,0.00047240104,0.0009991769,0.0005358078,0.0016246744],"domain_scores_gemma":[0.99736255,0.0010976231,0.0001112824,0.00095807883,0.0002351469,0.0002352857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004436238,0.00027898443,0.00031052684,0.00038584427,0.00033204863,0.00043341963,0.0024108845,0.000102577906,7.9686515e-7],"category_scores_gemma":[0.00082293147,0.0002460624,0.00007293803,0.0012466433,0.0009749284,0.00028219688,0.00055609556,0.0003397229,0.000004923368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011687649,0.00006376939,0.00025983664,0.00001979794,0.0000029099344,0.00001547702,0.00023768622,0.0031381368,0.00051729265,0.9775777,0.00005070042,0.018105015],"study_design_scores_gemma":[0.00016420714,0.00024354277,0.00017717638,0.00004705555,0.0000025210873,0.000046280944,2.754787e-7,0.6367869,0.0026670727,0.35964197,0.0000061418086,0.00021691012],"about_ca_topic_score_codex":0.000013897058,"about_ca_topic_score_gemma":0.000009320121,"teacher_disagreement_score":0.6336487,"about_ca_system_score_codex":0.0003870961,"about_ca_system_score_gemma":0.0006731179,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W1986927667","doi":"10.1007/s11265-013-0845-0","title":"Enhancing Hardware Assisted Test Insertion Capabilities on Embedded Processors using an FPGA-based Agile Test Support Co-processor","year":2013,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Alberta; University of Calgary","funders":"","keywords":"Agile software development; Embedded system; Debugging; Computer science; Overhead (engineering); Field-programmable gate array; Software; Test (biology); Computer hardware; Operating system; Computer architecture; Software engineering","score_opus":0.04360086151967359,"score_gpt":0.2980660064033549,"score_spread":0.2544651448836813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986927667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34753913,0.00044125688,0.6475243,0.00019275518,0.0003409029,0.00065421767,0.000009258941,0.0030208523,0.00027732668],"genre_scores_gemma":[0.9488133,0.0000015141844,0.050378166,0.00024035061,0.00036788904,0.000045640638,0.000005329528,0.000059893737,0.00008791846],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958023,0.0002003564,0.0015224993,0.000575859,0.0012901077,0.000608886],"domain_scores_gemma":[0.9936025,0.0010879539,0.0020276823,0.0004630223,0.0024632795,0.00035552317],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018753083,0.00046023956,0.0007278686,0.00065031974,0.00055281585,0.0016353208,0.0012043521,0.00022660653,0.000019886185],"category_scores_gemma":[0.0014466519,0.0003787173,0.00015170817,0.0008279741,0.00013386091,0.00286977,0.000052594303,0.0005849688,0.000018479848],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027924613,0.008375871,0.06823571,0.0152497515,0.00021638794,0.0007213283,0.019818233,0.039103396,0.64705163,0.00007766169,0.01442069,0.18645008],"study_design_scores_gemma":[0.0016812689,0.005485659,0.0031492575,0.011868346,0.00011426525,0.0020391128,0.0013768475,0.78710157,0.18345168,0.001847471,0.00028337017,0.0016011527],"about_ca_topic_score_codex":0.00014103326,"about_ca_topic_score_gemma":0.0000023094194,"teacher_disagreement_score":0.7479982,"about_ca_system_score_codex":0.0003730065,"about_ca_system_score_gemma":0.0013830523,"threshold_uncertainty_score":0.9998665},"labels":[],"label_agreement":null},{"id":"W1987534773","doi":"10.1007/s10515-010-0079-3","title":"Example-based model-transformation testing","year":2011,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Transformation (genetics); Oracle; Computer science; Model transformation; Function (biology); Premise; Quality (philosophy); Data mining; Reliability engineering; Artificial intelligence; Theoretical computer science; Industrial engineering; Machine learning; Software engineering; Engineering","score_opus":0.06099352935504673,"score_gpt":0.23204957400922685,"score_spread":0.17105604465418012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987534773","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007008173,0.000022975786,0.85445946,0.000008250304,0.00012361085,0.00012042507,0.0000014785442,0.13798775,0.00026789494],"genre_scores_gemma":[0.47452646,2.7192746e-7,0.52535546,0.000057293924,0.000008637307,0.00002686308,0.0000031707316,0.000019599089,0.0000022715374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987591,0.000022680919,0.0002899104,0.00031228692,0.00022149767,0.00039455056],"domain_scores_gemma":[0.99872464,0.00043998746,0.00006819108,0.000536527,0.00012427049,0.000106356754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038949726,0.0002213166,0.00016679273,0.00024459747,0.00010880879,0.00008591049,0.00061101833,0.00010319587,0.0000031101004],"category_scores_gemma":[0.0009206948,0.00023276727,0.00005255716,0.00065321155,0.000014584146,0.0005632502,0.00007330612,0.0001701425,0.000021333262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015765823,0.00023167816,0.013913655,0.00048388928,0.00006968146,0.00012237174,0.0056126383,0.90680933,0.0017820819,0.019039277,0.0034390832,0.048480522],"study_design_scores_gemma":[0.00013966634,0.000044136665,0.002748862,0.000120711804,0.000005710026,0.000021646629,7.150706e-7,0.9916118,0.003022907,0.0019665004,0.00002926073,0.0002881031],"about_ca_topic_score_codex":0.0001321606,"about_ca_topic_score_gemma":0.0000010204498,"teacher_disagreement_score":0.4675183,"about_ca_system_score_codex":0.00005894604,"about_ca_system_score_gemma":0.000076714154,"threshold_uncertainty_score":0.94919735},"labels":[],"label_agreement":null},{"id":"W1987538235","doi":"10.1145/1297846.1297882","title":"Open framework for conformance testing via scenarios","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Conformance testing; Computer science; Software engineering; Software testing; Formal specification; Conformance checking; Software; Reliability engineering; Programming language; Operating system; Engineering; Compatibility (geochemistry); Business process; Standardization","score_opus":0.07472432542418293,"score_gpt":0.35178939586205554,"score_spread":0.2770650704378726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987538235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040909534,0.000017258539,0.98231554,0.0002745795,0.00017649785,0.00035442348,3.4800362e-7,0.007991269,0.008460968],"genre_scores_gemma":[0.19028093,2.4090625e-7,0.80786777,0.0016067273,0.000056329234,0.000022431957,5.251823e-7,0.000007749342,0.0001572996],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990405,0.000006801831,0.00021342353,0.00027631718,0.00012416489,0.00033880386],"domain_scores_gemma":[0.9973463,0.001798658,0.00008997955,0.00052742846,0.0001549834,0.000082641054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011381097,0.00010264836,0.00012266693,0.00006611507,0.00021347101,0.00032431073,0.0017675327,0.000070848546,0.000004142383],"category_scores_gemma":[0.0015105278,0.0000890097,0.000027125041,0.00039180406,0.000027254857,0.0004438362,0.00060222636,0.00011020764,0.000020237214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009501151,0.00004747703,0.0088415835,0.000022412183,0.000006921788,0.000008117354,0.00025245306,0.000015583353,0.00010226799,0.25393233,0.014924446,0.7218369],"study_design_scores_gemma":[0.00022455383,0.00023389813,0.0029897764,0.00015219854,0.0000029624723,0.00004777287,0.0000045883194,0.14350355,0.0047231484,0.84218115,0.0055954363,0.0003409891],"about_ca_topic_score_codex":0.00014714009,"about_ca_topic_score_gemma":0.000006006562,"teacher_disagreement_score":0.7214959,"about_ca_system_score_codex":0.000025230771,"about_ca_system_score_gemma":0.00005554132,"threshold_uncertainty_score":0.362971},"labels":[],"label_agreement":null},{"id":"W1988040396","doi":"10.1109/icst.2012.120","title":"Automated Unit Testing of a SCADA Control Software: An Industrial Case Study Based on Action Research","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"SCADA; Test suite; Unit testing; Regression testing; White-box testing; Computer science; Keyword-driven testing; Test Management Approach; Reliability engineering; Test (biology); Suite; Manual testing; Software engineering; Rocket (weapon); Software; Black box; Engineering; Test case; Software development; Software construction; Operating system; Regression analysis; Artificial intelligence; Machine learning; Aeronautics","score_opus":0.3842958960814827,"score_gpt":0.4381098421641235,"score_spread":0.05381394608264084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988040396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81604,0.000004035332,0.16210495,0.000052590865,0.00019808691,0.0005896841,0.0000019006909,0.02084189,0.00016690769],"genre_scores_gemma":[0.88136137,2.4768664e-8,0.11838958,0.000070788905,0.00010878157,0.00004188717,9.113579e-7,0.00001323597,0.000013402866],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741423,0.0008799398,0.0002972189,0.00031837018,0.0006344466,0.00045578077],"domain_scores_gemma":[0.99463457,0.003816316,0.00011923337,0.00079810916,0.00044478846,0.00018697837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042599333,0.00014248828,0.00019748231,0.00043390808,0.00029312627,0.00011556598,0.0004985066,0.00011358612,0.000007142227],"category_scores_gemma":[0.005094531,0.00012059033,0.000027138472,0.0014113013,0.00005816599,0.00050181145,0.00011755563,0.0004003653,0.0000074324676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075706565,0.00285378,0.8470885,0.000018847832,0.000024527362,0.00039033205,0.00089984154,0.0006312143,0.0002542077,0.00014966448,0.0058048284,0.14180854],"study_design_scores_gemma":[0.002171711,0.0036034603,0.014824554,0.00009563245,0.000017520075,0.00040847753,0.00022654177,0.9761679,0.0017501229,0.0003889285,0.000043838085,0.00030131632],"about_ca_topic_score_codex":0.005074534,"about_ca_topic_score_gemma":0.000034310142,"teacher_disagreement_score":0.9755367,"about_ca_system_score_codex":0.00006977118,"about_ca_system_score_gemma":0.00021189952,"threshold_uncertainty_score":0.76712114},"labels":[],"label_agreement":null},{"id":"W1989734351","doi":"10.1145/2614106.2614206","title":"OpenVL","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.010473633179819484,"score_gpt":0.22952648707943524,"score_spread":0.21905285389961576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989734351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031929868,0.00000368401,0.92330825,0.00043953434,0.000060622646,0.000016514252,1.26022055e-8,0.0139549505,0.061897144],"genre_scores_gemma":[0.36273104,1.9522022e-7,0.6356617,0.00094126584,0.000017283652,0.0000023653326,6.711726e-8,0.0000016108485,0.0006444518],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996828,0.000015546764,0.000044680237,0.00011303458,0.000063137144,0.00008084045],"domain_scores_gemma":[0.9995047,0.00010404831,0.000010775207,0.0003353938,0.000016711034,0.000028371564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018884098,0.000032574826,0.000037226662,0.000023601096,0.000031487547,0.00006542387,0.0004478185,0.000013274065,0.000009743109],"category_scores_gemma":[0.00014349612,0.000025481393,0.000012180471,0.00008748993,0.000007656412,0.000102624035,0.00012462535,0.000026213524,0.00012317266],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.829586e-7,0.000012711999,0.0022128602,0.000001801206,0.0000011127066,0.000001108568,0.000057623503,0.0000024723006,0.00004100557,0.3662507,0.17330468,0.45811376],"study_design_scores_gemma":[0.0000976658,0.00008701975,0.0025180748,0.000011646114,8.083655e-7,0.000022494203,3.2089085e-7,0.117010705,0.0027293107,0.79846233,0.07887666,0.00018295167],"about_ca_topic_score_codex":0.000034903045,"about_ca_topic_score_gemma":5.7088175e-7,"teacher_disagreement_score":0.4579308,"about_ca_system_score_codex":0.000003430946,"about_ca_system_score_gemma":0.000005711669,"threshold_uncertainty_score":0.15831764},"labels":[],"label_agreement":null},{"id":"W1991113092","doi":"10.1109/issre.2014.15","title":"An Orchestrated Survey of Available Algorithms and Tools for Combinatorial Testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Algorithm; Test suite; Computer science; Suite; Software; Process (computing); Domain (mathematical analysis); Selection (genetic algorithm); Random testing; Test case; Data mining; Machine learning; Mathematics; Programming language","score_opus":0.13194195746342552,"score_gpt":0.3054927914941669,"score_spread":0.1735508340307414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991113092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040204737,0.000011676827,0.95489544,0.000017552238,0.00017467012,0.00016286857,0.0000035384608,0.003643504,0.00088599196],"genre_scores_gemma":[0.49361667,2.8524266e-7,0.5063059,0.000026010875,0.000020148918,0.00000747794,0.000004212713,0.0000048806755,0.000014473885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991687,0.0001047287,0.0001841082,0.00026783085,0.0001065216,0.0001681205],"domain_scores_gemma":[0.99596745,0.0031715294,0.000081930884,0.0003666825,0.00034519748,0.000067220346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016916633,0.00008840307,0.0001609846,0.000036691672,0.00007495813,0.00022804586,0.00037030253,0.000054846412,0.0000017708156],"category_scores_gemma":[0.0043966467,0.000078211815,0.000012006905,0.0002740316,0.00004038323,0.00046955302,0.00006907462,0.0000495496,0.000001585793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037982136,0.00043093166,0.17369293,0.00014576888,0.000028199041,0.0000021209144,0.00025313528,0.000037327,0.0048107775,0.06871024,0.021780241,0.73007035],"study_design_scores_gemma":[0.00063808786,0.0013081741,0.045614485,0.000041727388,0.000004826999,0.000009575186,0.0000017484622,0.8549071,0.009610514,0.087456755,0.00013840145,0.00026858677],"about_ca_topic_score_codex":0.0012051173,"about_ca_topic_score_gemma":0.000008488305,"teacher_disagreement_score":0.8548698,"about_ca_system_score_codex":0.0000067983915,"about_ca_system_score_gemma":0.000060469913,"threshold_uncertainty_score":0.52635145},"labels":[],"label_agreement":null},{"id":"W1992815253","doi":"10.1007/s10515-009-0061-0","title":"Generating a checking sequence with a minimum number of reset transitions","year":2009,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Leverhulme Trust","keywords":"Reset (finance); Sequence (biology); Model checking; State (computer science); Computer science; Finite-state machine; Algorithm","score_opus":0.015982541555149138,"score_gpt":0.2662486012595593,"score_spread":0.2502660597044102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992815253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09330336,0.000047875164,0.87027615,0.00012846965,0.000053900472,0.00009924185,0.0000036574752,0.036043774,0.000043560165],"genre_scores_gemma":[0.5174589,0.0000011754541,0.4824345,0.000059398764,0.000017990322,0.000009084178,0.0000037535508,0.000011295785,0.0000038776816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877644,0.000024840258,0.00029497631,0.00032024467,0.0002549778,0.0003285021],"domain_scores_gemma":[0.99898624,0.00022074862,0.0000966358,0.0004831218,0.0001347751,0.00007846706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022175659,0.00020312802,0.00024110393,0.00014663348,0.00010227047,0.00006398863,0.00046212887,0.00007948564,0.0000038280896],"category_scores_gemma":[0.00041108817,0.00018595958,0.000044924207,0.0008007052,0.000031691452,0.00034953575,0.00003671811,0.00016602401,0.000003535344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005564063,0.00064400496,0.02260115,0.0010343516,0.00040056618,0.0013154101,0.025989931,0.6168274,0.1728696,0.03275355,0.019036945,0.10647146],"study_design_scores_gemma":[0.00023370922,0.00015136346,0.0017618492,0.0007264933,0.000012251151,0.0003116763,0.000004898143,0.9916026,0.0037233147,0.001072482,0.000043509626,0.00035587925],"about_ca_topic_score_codex":0.000031484287,"about_ca_topic_score_gemma":6.8802154e-7,"teacher_disagreement_score":0.42415556,"about_ca_system_score_codex":0.00004408484,"about_ca_system_score_gemma":0.00005569723,"threshold_uncertainty_score":0.75832117},"labels":[],"label_agreement":null},{"id":"W1993945834","doi":"10.1049/ic.2013.0038","title":"Prototype test insertion co-processor for agile development in multi-threaded embedded environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Agile software development; Computer science; Embedded system; Test (biology); Operating system; Computer architecture; Software engineering; Geology","score_opus":0.05255001405290805,"score_gpt":0.2996759811936519,"score_spread":0.24712596714074386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993945834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056587663,0.00001546407,0.9375741,0.00017089772,0.000043551412,0.0021826536,7.3574245e-7,0.0031702423,0.0002547273],"genre_scores_gemma":[0.4097484,8.6108867e-7,0.58769643,0.00022345012,0.000006193223,0.0018760962,0.0000057283364,0.000009343689,0.00043352015],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890965,0.000017126222,0.00026840103,0.0003601511,0.00016420046,0.00028049437],"domain_scores_gemma":[0.9993515,0.00016982252,0.000073851574,0.00029938106,0.00004040027,0.00006503526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022926934,0.00014023829,0.00013055757,0.000109987,0.000086861684,0.00009482928,0.00044350658,0.00007122037,0.000020528349],"category_scores_gemma":[0.00033714625,0.00012128342,0.000021999276,0.00016397607,0.00002274429,0.00036353557,0.00008826343,0.000073772855,0.00015377367],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005599745,0.004066915,0.37166962,0.00040386937,0.000045542278,0.000013960435,0.0076280967,0.000086331085,0.05132335,0.0013108869,0.037596073,0.52579933],"study_design_scores_gemma":[0.0028496457,0.00074994966,0.27976257,0.0002623972,0.000004976712,0.000014867794,0.000031534782,0.25692374,0.43301332,0.017930226,0.007273891,0.0011829119],"about_ca_topic_score_codex":0.00007050736,"about_ca_topic_score_gemma":0.000011387488,"teacher_disagreement_score":0.5246164,"about_ca_system_score_codex":0.00008157966,"about_ca_system_score_gemma":0.000060853876,"threshold_uncertainty_score":0.4945794},"labels":[],"label_agreement":null},{"id":"W1997272604","doi":"10.4236/jsea.2013.610a006","title":"A Survey of Software Test Estimation Techniques","year":2013,"lang":"en","type":"article","venue":"Journal of Software Engineering and Applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Software reliability testing; Regression testing; Estimation; Computer science; Software; Reliability engineering; System integration testing; Software development; Verification and validation; Software construction; Software testing; Software engineering; Systems engineering; Engineering; Operating system; Operations management","score_opus":0.011629271299270256,"score_gpt":0.23709443368206978,"score_spread":0.22546516238279954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997272604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050427876,0.000403375,0.99273205,0.00006656226,0.000030587755,0.00016997314,0.0000063569037,0.0015434492,0.0000048411102],"genre_scores_gemma":[0.32282764,0.00003482864,0.6770174,0.000019927513,0.000031076444,0.000048291222,0.0000022312133,0.000010629756,0.000007990393],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99910754,0.000016832013,0.00042537155,0.00013445187,0.00018310836,0.0001327247],"domain_scores_gemma":[0.9974148,0.0013477859,0.00030426477,0.00030024513,0.0005366383,0.000096241594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043916848,0.000120943914,0.00021823429,0.00021485373,0.000058696227,0.00007930049,0.0004102005,0.00006686312,0.0000022728443],"category_scores_gemma":[0.002225751,0.000108787426,0.000046020832,0.00043322824,0.000032717126,0.0003538114,0.00008200292,0.00017228337,0.0000027014096],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020513228,0.00024354976,0.108247206,0.00024123541,0.000046258396,0.0000030422952,0.00021895162,0.0015199671,0.0010560914,0.0008755135,0.008710105,0.87883604],"study_design_scores_gemma":[0.0005379523,0.0008080239,0.8387016,0.0013118788,0.00006548032,0.0005895721,0.000009183904,0.11614229,0.011621818,0.026176164,0.0030383829,0.0009976471],"about_ca_topic_score_codex":0.000104156104,"about_ca_topic_score_gemma":6.384076e-7,"teacher_disagreement_score":0.8778384,"about_ca_system_score_codex":0.00002472238,"about_ca_system_score_gemma":0.000055221906,"threshold_uncertainty_score":0.44362226},"labels":[],"label_agreement":null},{"id":"W1997386306","doi":"10.1145/2484313.2484372","title":"Fuzzing the ActionScript virtual machine","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; China Postdoctoral Science Foundation; University of Ottawa","keywords":"Computer science; Fuzz testing; Programming language; Test suite; Compiler; Suite; JavaScript; Context (archaeology); Code coverage; Source code; Code (set theory); Virtual machine; Test case; Software; Machine learning","score_opus":0.013828792639697263,"score_gpt":0.22308164968322258,"score_spread":0.2092528570435253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997386306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002642486,0.00004061613,0.970189,0.0048239124,0.00023408992,0.00009839436,1.2438936e-7,0.012236983,0.009734414],"genre_scores_gemma":[0.80357957,0.0000019245979,0.19304016,0.0015666947,0.000039083792,0.000031648982,2.6003138e-7,0.0000042765787,0.0017364097],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994994,0.000028500886,0.000083273684,0.00013998253,0.00011327934,0.00013559438],"domain_scores_gemma":[0.9992476,0.00020897633,0.000024172261,0.0004419911,0.00004307951,0.000034168097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015101634,0.000061726394,0.000046597215,0.000035626847,0.00018138572,0.00022405146,0.0006047653,0.00002043103,0.00006495882],"category_scores_gemma":[0.00012341236,0.000035166253,0.000026904792,0.00018160023,0.00002534151,0.00031526314,0.00017624705,0.000099004224,0.00028420874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.1517262e-7,0.00003452304,0.0030640336,0.0000018041317,0.000008975913,0.0000019119934,0.00036484742,0.000024109604,0.0005336883,0.09065087,0.526614,0.37870082],"study_design_scores_gemma":[0.00020786299,0.00020160688,0.021002794,0.000030122472,0.0000065819218,0.00015331284,0.0000410578,0.65982026,0.0027451087,0.28368175,0.031630244,0.00047930088],"about_ca_topic_score_codex":0.0006664023,"about_ca_topic_score_gemma":0.000004898622,"teacher_disagreement_score":0.80093706,"about_ca_system_score_codex":0.0000117901245,"about_ca_system_score_gemma":0.000013266497,"threshold_uncertainty_score":0.36530232},"labels":[],"label_agreement":null},{"id":"W1997899845","doi":"10.1145/1291535.1291541","title":"Model-based regression test suite generation using dependence analysis","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extended finite-state machine; Test suite; Computer science; Regression analysis; Finite-state machine; Set (abstract data type); Suite; Model-based testing; Test case; Algorithm; Programming language; Machine learning","score_opus":0.0783813480523774,"score_gpt":0.33227034257455085,"score_spread":0.25388899452217345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997899845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03496578,0.000023985764,0.9599465,0.000084791296,0.000043885313,0.000054542474,4.2287422e-7,0.0045655374,0.00031454436],"genre_scores_gemma":[0.5134124,3.4380798e-7,0.48626027,0.0002503298,0.000020068814,9.945921e-7,0.0000018797682,0.0000031532174,0.000050534338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891025,0.000022149492,0.00020283407,0.0003472758,0.0002933955,0.00022409076],"domain_scores_gemma":[0.99883765,0.0002929034,0.000089169356,0.0005672549,0.00013470626,0.00007830011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007965226,0.00011033557,0.0001223865,0.00035589418,0.00016705845,0.00013080805,0.00041196874,0.00006612706,0.000004792737],"category_scores_gemma":[0.00029665531,0.000089474255,0.000073659416,0.0011776581,0.000019372306,0.00026630855,0.000088717956,0.00007788941,0.0000034171414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010154244,0.00035436777,0.35608286,0.000023244966,0.00008082381,0.00010719675,0.0003815332,0.42074785,0.09341462,0.0055236532,0.006795889,0.11647781],"study_design_scores_gemma":[0.00004639893,0.00001857748,0.0012798803,0.000011929256,0.000025860096,0.0000037781729,4.2819056e-7,0.9687942,0.02768741,0.0020007044,0.0000048687375,0.0001259251],"about_ca_topic_score_codex":0.00015236395,"about_ca_topic_score_gemma":0.000074767806,"teacher_disagreement_score":0.5480464,"about_ca_system_score_codex":0.00006221639,"about_ca_system_score_gemma":0.00006749363,"threshold_uncertainty_score":0.36486542},"labels":[],"label_agreement":null},{"id":"W1998421080","doi":"10.1007/s10009-010-0164-8","title":"Towards an industrial grade IVE for Java and next generation research platform for JML","year":2010,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Programming language; Java; Java Modeling Language; Compiler; Assertion; Eclipse; Java annotation; Real time Java; Software engineering","score_opus":0.26508377289896135,"score_gpt":0.4006144419160369,"score_spread":0.13553066901707556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998421080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16103627,0.000029314859,0.82753915,0.0068753753,0.0017433261,0.00088148273,0.000102900594,0.0017831068,0.000009103049],"genre_scores_gemma":[0.4953875,0.000024286384,0.502119,0.00047899748,0.0012610524,0.00059794175,0.000055445606,0.000038614166,0.000037172427],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998048,0.000028573048,0.00044923899,0.000512246,0.00050186453,0.00046007434],"domain_scores_gemma":[0.9968562,0.0011937172,0.00008044822,0.00034775547,0.0013889401,0.00013294061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001577094,0.0002162837,0.00024547553,0.0008879078,0.0005152882,0.0008682634,0.0015219024,0.0005621305,0.000005364119],"category_scores_gemma":[0.0036854895,0.0001934642,0.00014977268,0.00023365648,0.00019362812,0.0012293018,0.00007704188,0.000985408,0.0000015326958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026935022,0.00018839017,0.00027852287,0.000009299957,0.00009438912,0.000010635464,0.00028786424,0.00001121231,0.0065401536,0.15183122,0.0061811586,0.8342978],"study_design_scores_gemma":[0.006112284,0.005436201,0.00018116533,0.00014483953,0.000040153987,0.00086412765,0.000047033867,0.021923915,0.077564314,0.7921787,0.094827965,0.0006793308],"about_ca_topic_score_codex":0.000008895621,"about_ca_topic_score_gemma":0.000019765457,"teacher_disagreement_score":0.83361846,"about_ca_system_score_codex":0.00010583563,"about_ca_system_score_gemma":0.00024889834,"threshold_uncertainty_score":0.8372684},"labels":[],"label_agreement":null},{"id":"W1998661399","doi":"10.1145/505776.505782","title":"Summary report of the OOPSLA 2000 workshop on scenario-based round-trip engineering","year":2001,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Software engineering; State (computer science); Conjunction (astronomy); World Wide Web; Library science; Programming language","score_opus":0.021462812271053417,"score_gpt":0.24234626439310675,"score_spread":0.22088345212205332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998661399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12072215,0.0010899837,0.8540074,0.0011540015,0.0015855865,0.0005082746,0.000010245934,0.020899436,0.00002287075],"genre_scores_gemma":[0.7392018,0.000017109614,0.26016107,0.00023172746,0.00014067133,0.00004996439,0.000009205418,0.00007058955,0.00011784845],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99740416,0.000039404356,0.00060018746,0.0006656184,0.0006566097,0.0006340245],"domain_scores_gemma":[0.9623958,0.033906642,0.00026311362,0.0030719787,0.00019377474,0.00016867295],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006100081,0.00046261615,0.00042923013,0.00033509787,0.00015388237,0.00011128063,0.0023566573,0.00022181241,0.000008691405],"category_scores_gemma":[0.124966085,0.00039323597,0.000257342,0.0014201007,0.000050132483,0.00028961606,0.0005418495,0.0005662142,0.0000101102605],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004188309,0.00038995236,0.7289042,0.00035274652,0.00012903618,0.00093088654,0.0005906144,0.2122261,0.0013418671,0.0006873361,0.014406304,0.039999098],"study_design_scores_gemma":[0.0028385385,0.0008172256,0.65924007,0.0115214,0.00022988615,0.0026658375,0.00001052654,0.21189061,0.049189046,0.002009862,0.053488478,0.0060985396],"about_ca_topic_score_codex":0.00009853252,"about_ca_topic_score_gemma":0.000002784627,"teacher_disagreement_score":0.61847967,"about_ca_system_score_codex":0.00018613982,"about_ca_system_score_gemma":0.00022148456,"threshold_uncertainty_score":0.99985194},"labels":[],"label_agreement":null},{"id":"W2000579079","doi":"10.1016/s0167-6423(99)00046-5","title":"A calculus of program adaptation and its applications","year":2000,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software engineering; Software development; Programming language; Reuse; Component-based software engineering; Software construction; Adaptation (eye); Software","score_opus":0.02702946033575281,"score_gpt":0.29345959545317046,"score_spread":0.26643013511741764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000579079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037923366,0.00016907511,0.9590505,0.00008235716,0.000037229922,0.0005536832,4.5908897e-7,0.0020097988,0.00017355767],"genre_scores_gemma":[0.4911479,0.000004366489,0.5087666,0.000009120067,0.00001208496,0.000051909872,2.8168515e-7,0.0000022591776,0.0000055018895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882287,0.000019959838,0.0002465857,0.00033581702,0.00034402075,0.00023074356],"domain_scores_gemma":[0.9991531,0.00008678871,0.00011895681,0.0003256551,0.00023423454,0.00008128429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054486515,0.00008746323,0.00013540954,0.00016401205,0.00013471395,0.00011190968,0.00073937804,0.000027460577,0.0000015235513],"category_scores_gemma":[0.000034732788,0.00008090057,0.000030397125,0.0012170253,0.00030809562,0.00045719024,0.00015879002,0.000057832523,0.0000018740847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.6217244e-7,0.00007215484,0.000080362726,0.000024981768,0.0000016377112,3.768977e-7,0.00045971738,0.0000949735,0.00011801603,0.007725982,0.0000112433645,0.9914097],"study_design_scores_gemma":[0.00013858665,0.00042344496,0.0010952171,0.00010007539,0.000005173552,0.000028538047,0.000006890581,0.9864919,0.0037170325,0.005952259,0.0018814446,0.00015944488],"about_ca_topic_score_codex":0.000026638147,"about_ca_topic_score_gemma":6.457424e-7,"teacher_disagreement_score":0.9912503,"about_ca_system_score_codex":0.0000127596695,"about_ca_system_score_gemma":0.00010701999,"threshold_uncertainty_score":0.32990295},"labels":[],"label_agreement":null},{"id":"W2002136372","doi":"10.1145/1363686.1363857","title":"An approach for supporting system-level test scenarios generation from textual use cases","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Tree traversal; Control flow; Finite-state machine; Test (biology); Scenario testing; Test case; State (computer science); Code coverage; Programming language; Theoretical computer science; Artificial intelligence; Machine learning; Software","score_opus":0.16133295948694185,"score_gpt":0.3028323202864848,"score_spread":0.14149936079954298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002136372","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11412795,0.0000101395335,0.8764164,0.00002791975,0.00006549059,0.00025349896,0.000025852467,0.008977925,0.00009484994],"genre_scores_gemma":[0.50833166,3.0390737e-7,0.49124154,0.00010405419,0.00012518156,0.00004064469,0.00005748131,0.000008659205,0.00009049137],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986977,0.000043509637,0.00029918712,0.00049451273,0.00019828537,0.00026680302],"domain_scores_gemma":[0.9980286,0.0009723908,0.00012515427,0.00061254785,0.00015916581,0.000102141945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002864712,0.00015100001,0.00016812893,0.00007431868,0.00037453897,0.00024475265,0.00046565515,0.00007816122,0.0000018546025],"category_scores_gemma":[0.0011514507,0.0001310152,0.000050270624,0.00015565587,0.00003145254,0.0007164063,0.00007734361,0.0000680082,0.00000426228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030613024,0.002212354,0.5341378,0.00016504125,0.00008496441,0.00052815187,0.0048259166,0.0028593151,0.020350153,0.03579733,0.3226224,0.076386],"study_design_scores_gemma":[0.00017558136,0.00019822459,0.003976591,0.00001702077,0.00000688231,0.00033754628,0.000029817194,0.9907494,0.0040593194,0.00013211727,0.0000656379,0.0002518139],"about_ca_topic_score_codex":0.0019047126,"about_ca_topic_score_gemma":0.000018879631,"teacher_disagreement_score":0.9878901,"about_ca_system_score_codex":0.000049983537,"about_ca_system_score_gemma":0.000093705996,"threshold_uncertainty_score":0.53426445},"labels":[],"label_agreement":null},{"id":"W2002702549","doi":"10.1017/s0960129513000054","title":"Verification of tree-processing programs via higher-order mode checking","year":2014,"lang":"en","type":"article","venue":"Mathematical Structures in Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Career Trek","funders":"","keywords":"Soundness; Computer science; Programmer; Tree (set theory); Recursion (computer science); Programming language; Data structure; Algorithm; Theoretical computer science; Mathematics","score_opus":0.023457602234503876,"score_gpt":0.29050006344815543,"score_spread":0.26704246121365155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002702549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016255587,0.000020759446,0.9815697,0.00014322909,0.00017671593,0.00013357525,1.08898995e-7,0.0013105724,0.00038973938],"genre_scores_gemma":[0.518228,1.6516398e-7,0.4816722,0.00005757952,0.000029460722,0.000006502842,2.6317605e-7,0.000004459939,0.0000013827038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980049,0.000052897,0.00040796094,0.00054852245,0.00061328127,0.00037240153],"domain_scores_gemma":[0.9986246,0.00018475408,0.0001789147,0.0007455865,0.00017562107,0.000090528134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008888525,0.00016716831,0.00025188868,0.00020687177,0.00013899348,0.00026878767,0.0017970669,0.000056249428,0.0000030616156],"category_scores_gemma":[0.00019987435,0.00013492675,0.00003761514,0.0013507255,0.00046216,0.00045121426,0.0004511421,0.00014720272,0.0000026548205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011908526,0.000051119263,0.0009987433,0.00006733483,9.1201434e-7,0.0000011029373,0.00048578493,0.0004076306,0.00052896404,0.06274278,0.000015598656,0.9346988],"study_design_scores_gemma":[0.00006250571,0.000031210082,0.003646879,0.000081531776,0.0000010830188,0.000012240669,3.0958915e-7,0.5607793,0.0014705072,0.4338043,0.000011478594,0.000098685785],"about_ca_topic_score_codex":0.000019143989,"about_ca_topic_score_gemma":9.74606e-7,"teacher_disagreement_score":0.9346002,"about_ca_system_score_codex":0.000053034313,"about_ca_system_score_gemma":0.00006405175,"threshold_uncertainty_score":0.55021536},"labels":[],"label_agreement":null},{"id":"W2004981790","doi":"10.1016/j.dam.2010.12.022","title":"On a labeling problem in graphs","year":2011,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Indian Institute of Technology Roorkee","keywords":"Combinatorics; Mathematics; Vertex (graph theory); Time complexity; Graph; Alphabet; Discrete mathematics","score_opus":0.03362565585068039,"score_gpt":0.24749419453963428,"score_spread":0.2138685386889539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004981790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015253811,0.000018608698,0.8827211,0.000046522247,0.00004576898,0.00042799534,0.00000104963,0.006507334,0.094977774],"genre_scores_gemma":[0.33301798,0.0000018256479,0.6667737,0.00011357538,0.000003518992,0.00006435304,6.179376e-7,0.000012010023,0.00001241228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990347,0.000008849231,0.00025430895,0.00026552624,0.00018765152,0.00024894008],"domain_scores_gemma":[0.9990836,0.00018192874,0.00009394403,0.0005721028,0.000019210927,0.000049216862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033517918,0.00014544206,0.00017385205,0.0001560462,0.00004842459,0.000046475914,0.0006022438,0.00005716205,0.000006286434],"category_scores_gemma":[0.00006260958,0.00012265002,0.000035231587,0.00036583343,0.000028922412,0.000073245195,0.00014798038,0.00014646581,0.000048192054],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023815812,0.00010740262,0.00007395926,0.000048294358,0.0000041252533,0.000007840846,0.0039680977,0.00000553265,0.00013548254,0.99140996,0.00052114885,0.0037157543],"study_design_scores_gemma":[0.00013440737,0.000044763256,0.00006381044,0.00011719849,0.0000028667741,0.00000469604,0.000020493619,0.0069604428,0.0017288831,0.9907443,0.000010953005,0.00016718541],"about_ca_topic_score_codex":0.000016343765,"about_ca_topic_score_gemma":0.0000019355093,"teacher_disagreement_score":0.31776416,"about_ca_system_score_codex":0.000018528315,"about_ca_system_score_gemma":0.000017224334,"threshold_uncertainty_score":0.5001523},"labels":[],"label_agreement":null},{"id":"W2005595981","doi":"10.1109/icstw.2013.41","title":"Experimenting with Category Partition's 1-Way and 2-Way Test Selection Criteria","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Intuition; Computer science; Selection (genetic algorithm); Test (biology); Partition (number theory); Test case; Machine learning; Artificial intelligence; Mathematics; Psychology","score_opus":0.015210897683390385,"score_gpt":0.24812051166885588,"score_spread":0.2329096139854655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005595981","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2037339,0.000068026624,0.77312523,0.0008118081,0.000088541914,0.00025404888,2.5186213e-7,0.014335446,0.0075827525],"genre_scores_gemma":[0.7575469,0.0000013114599,0.24184813,0.00023314598,0.000028416238,0.00006236769,6.041681e-7,0.0000063753564,0.00027277105],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930936,0.000022731292,0.00010496556,0.00026687793,0.00010625534,0.00018980008],"domain_scores_gemma":[0.99945366,0.0001486888,0.00004233327,0.00019540604,0.0000951538,0.00006478331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000120041776,0.000099950004,0.00008146019,0.00006141712,0.0001600178,0.0003519793,0.0001476251,0.000032372816,0.000066074375],"category_scores_gemma":[0.00007700894,0.0000761413,0.000010698653,0.00018163549,0.000036972095,0.0005702643,0.000083441264,0.00006145623,0.000029908912],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079827505,0.0005127812,0.34509116,0.00011105618,0.000049703434,0.000025896037,0.0040022493,0.000014596684,0.10883338,0.02812563,0.35355145,0.15967411],"study_design_scores_gemma":[0.0011713122,0.0019249441,0.24376427,0.00027327053,0.000024900619,0.0007666544,0.00015710175,0.31259662,0.31833476,0.116306506,0.0028588201,0.0018208447],"about_ca_topic_score_codex":0.00038452595,"about_ca_topic_score_gemma":0.000007085207,"teacher_disagreement_score":0.553813,"about_ca_system_score_codex":0.000015811722,"about_ca_system_score_gemma":0.000014440842,"threshold_uncertainty_score":0.33941448},"labels":[],"label_agreement":null},{"id":"W2006253492","doi":"10.1016/j.jss.2007.05.037","title":"Traffic-aware stress testing of distributed real-time systems based on UML models using genetic algorithms","year":2007,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Calgary","funders":"","keywords":"Computer science; Unified Modeling Language; Real-time computing; Test case; Focus (optics); Sequence diagram; Scenario testing; Algorithm; Stress test; Distributed computing; Artificial intelligence; Machine learning; Software; Variety (cybernetics)","score_opus":0.03951929322770974,"score_gpt":0.26828445766643977,"score_spread":0.22876516443873002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006253492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14298958,0.00061487267,0.85506684,0.000009141711,0.00035839324,0.00018088262,0.000042224696,0.00072655897,0.000011539397],"genre_scores_gemma":[0.78752804,0.000008356415,0.21225363,0.000008313388,0.0001688264,0.0000018482386,0.0000023298546,0.000021917496,0.0000067542146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742305,0.00013528769,0.0010913528,0.00028766837,0.0007013597,0.0003612499],"domain_scores_gemma":[0.99622726,0.0011412135,0.0011375633,0.00043747912,0.0008322273,0.0002242381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015321905,0.0002497462,0.00062554114,0.00035151257,0.0001629931,0.00020574557,0.00052694685,0.00015629834,3.9931663e-7],"category_scores_gemma":[0.00042388085,0.00020453267,0.000108586144,0.0004949077,0.000055082404,0.00028293635,0.00007208999,0.00023218295,3.3282186e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037093552,0.00018576473,0.013020456,0.00071340293,0.000059356433,0.0004174041,0.00035483617,0.96148854,0.00023775193,0.000069390975,0.00054118945,0.022874782],"study_design_scores_gemma":[0.00038787336,0.00045277915,0.0016192357,0.0031412407,0.000030015522,0.0005647543,0.000044139895,0.9932927,0.0000905339,0.0001481929,0.000007849203,0.00022072489],"about_ca_topic_score_codex":0.00035618793,"about_ca_topic_score_gemma":7.120583e-7,"teacher_disagreement_score":0.64453846,"about_ca_system_score_codex":0.00012496233,"about_ca_system_score_gemma":0.00018619167,"threshold_uncertainty_score":0.83406},"labels":[],"label_agreement":null},{"id":"W2006575153","doi":"10.1109/icst.2013.23","title":"Efficient JavaScript Mutation Testing","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Mutation testing; JavaScript; Test suite; Mutation; Programming language; Web application; Process (computing); Set (abstract data type); Focus (optics); Test case; Software engineering; Data mining; Machine learning; Operating system","score_opus":0.0277027010756055,"score_gpt":0.23972739194392326,"score_spread":0.21202469086831777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006575153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03740062,0.00001722789,0.9325864,0.00035277873,0.00011955545,0.00011808462,4.947403e-8,0.017438754,0.011966571],"genre_scores_gemma":[0.5175262,3.4173638e-8,0.48204085,0.00027182364,0.000012795853,0.000017136346,1.5474572e-7,0.0000027578549,0.00012823787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935764,0.00001953938,0.00011675143,0.0001970635,0.00014403486,0.00016497617],"domain_scores_gemma":[0.99921143,0.00025175145,0.0000368555,0.00030836946,0.0001411959,0.00005040129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015883439,0.00006749804,0.000056696095,0.000065046646,0.00008198915,0.00017366973,0.00032958938,0.000023695879,0.00001921919],"category_scores_gemma":[0.0005483338,0.000055271,0.000018305404,0.00031921864,0.00001478805,0.00010814615,0.00011058387,0.00005121615,0.00031866797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5771123e-7,0.00011476258,0.008822633,0.000017789227,0.00000737324,0.000019688892,0.0006761164,0.0019260586,0.0018119004,0.020259436,0.11503044,0.8513135],"study_design_scores_gemma":[0.000050601702,0.00004092584,0.008788317,0.000016054513,8.8551457e-7,0.000036900125,0.0000029907703,0.9511132,0.0010152642,0.038751062,0.00007561588,0.00010816851],"about_ca_topic_score_codex":0.0004247464,"about_ca_topic_score_gemma":4.108723e-7,"teacher_disagreement_score":0.94918716,"about_ca_system_score_codex":0.000018532022,"about_ca_system_score_gemma":0.000020295614,"threshold_uncertainty_score":0.40959382},"labels":[],"label_agreement":null},{"id":"W2007279641","doi":"10.5555/2662593.2662596","title":"Towards model checking of computer games with Java PathFinder","year":2013,"lang":"en","type":"article","venue":"Computer Games","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Java; Computer science; Pathfinder; Programming language; Model checking; Code (set theory); State (computer science); Space (punctuation); Source code; State space; Operating system; World Wide Web; Mathematics; Set (abstract data type)","score_opus":0.022824778103721067,"score_gpt":0.23745149531079765,"score_spread":0.21462671720707657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007279641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03594613,0.00010559357,0.9581458,0.0004252514,0.00021840085,0.00025394306,0.0000014640974,0.004426611,0.00047680514],"genre_scores_gemma":[0.42587268,0.0000044176545,0.5733234,0.00059908436,0.00010922508,0.00002471334,0.0000016619733,0.000019297418,0.00004549937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980121,0.000062460094,0.0003986721,0.000630719,0.00044058115,0.00045541357],"domain_scores_gemma":[0.99807996,0.0001736319,0.00021996662,0.0010371875,0.00034946314,0.00013980665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002312615,0.00032460265,0.00043525588,0.00021159824,0.00008553445,0.00029484503,0.0013170282,0.00010872047,0.000010698088],"category_scores_gemma":[0.000019214067,0.00025324756,0.00011405517,0.00036530726,0.00013988465,0.0005842246,0.0007318888,0.0002136993,0.00002813903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006718829,0.00023615807,0.009116001,0.0001280358,0.000092452836,0.000022027776,0.0030586168,0.011100754,0.00011124252,0.006532201,0.077591814,0.89200395],"study_design_scores_gemma":[0.00029898493,0.0002600893,0.012854513,0.00023680547,0.000008682365,0.00004638535,0.0000025096995,0.96563447,0.000961239,0.019090312,0.00023293885,0.00037310427],"about_ca_topic_score_codex":0.000125801,"about_ca_topic_score_gemma":0.000001250182,"teacher_disagreement_score":0.9545337,"about_ca_system_score_codex":0.000036431473,"about_ca_system_score_gemma":0.00012808156,"threshold_uncertainty_score":0.99999195},"labels":[],"label_agreement":null},{"id":"W2008105683","doi":"10.2200/s00587ed1v01y201407swe002","title":"Hard Problems in Software Testing: Solutions Using Testing as a Service (TaaS)","year":2014,"lang":"en","type":"article","venue":"Synthesis lectures on software engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Software testing; Computer science; Software; Service (business); Reliability engineering; Operating system; Engineering; Business","score_opus":0.0546395552355538,"score_gpt":0.2417101058015125,"score_spread":0.1870705505659587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008105683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04017561,0.00015680329,0.9393264,0.00013187806,0.00027747164,0.00032650854,0.000003873251,0.019514486,0.00008694224],"genre_scores_gemma":[0.40381062,8.711957e-7,0.5955133,0.0003801248,0.00010953835,0.000104853156,0.0000013101723,0.00007333265,0.0000060421085],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967693,0.00014078007,0.0005493311,0.00095490564,0.0005371794,0.0010485039],"domain_scores_gemma":[0.9901075,0.008013722,0.00020360238,0.0011565138,0.00029328786,0.00022540208],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001053655,0.00056105386,0.00051590096,0.0006959756,0.0003601581,0.00032648214,0.0012603479,0.00024258318,0.000005523419],"category_scores_gemma":[0.050088152,0.00057390775,0.000106000756,0.0022926002,0.000033268727,0.00037973368,0.00039363225,0.0006380904,0.00004044193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075665116,0.00018629,0.035654083,0.00050815893,0.000051389874,0.00004591276,0.00071061344,0.8524227,0.0041424367,0.0008594903,0.00044316924,0.104968175],"study_design_scores_gemma":[0.00029991972,0.00020910184,0.02246408,0.0032402992,0.000036179765,0.00026771857,0.0000037385535,0.9588069,0.0040316037,0.008708777,0.0005355263,0.0013962022],"about_ca_topic_score_codex":0.00061290665,"about_ca_topic_score_gemma":0.0000192672,"teacher_disagreement_score":0.36363503,"about_ca_system_score_codex":0.00027491336,"about_ca_system_score_gemma":0.0001725118,"threshold_uncertainty_score":0.9996712},"labels":[],"label_agreement":null},{"id":"W2012086719","doi":"10.1145/1022494.1022541","title":"Empirical studies of software testing techniques","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Empirical research; Software testing; Software reliability testing; Software engineering; Regression testing; Test strategy; Software; Software construction; System integration testing; Software performance testing; Software development; Programming language","score_opus":0.07925087812671783,"score_gpt":0.3242008907103558,"score_spread":0.24495001258363797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012086719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09857077,0.0017430652,0.85252416,0.00043247704,0.00037384618,0.0003106184,0.000009758553,0.046031848,0.000003462849],"genre_scores_gemma":[0.42501682,0.000015440863,0.57465255,0.00013890331,0.00007862172,0.000049864306,0.000002663561,0.00004153188,0.0000036214446],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974838,0.00003503407,0.00065266335,0.00069406896,0.000513784,0.0006206591],"domain_scores_gemma":[0.92915267,0.06768756,0.00029717968,0.0020002043,0.0006653249,0.00019705872],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005781625,0.0004744522,0.0006260723,0.00040596304,0.00017029887,0.000089205656,0.0019248708,0.00020452481,0.0000018472261],"category_scores_gemma":[0.41442454,0.0004554234,0.00016564559,0.0012701451,0.0001308739,0.0005043705,0.0011440475,0.0003988775,0.000011918838],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010497527,0.00029128525,0.8581385,0.0009064623,0.00018994551,0.00017163195,0.0025241,0.002862707,0.003657379,0.0011284704,0.0026810933,0.1274379],"study_design_scores_gemma":[0.0023420772,0.0032317515,0.30015436,0.009991746,0.0002487356,0.0011980156,0.000057123576,0.0009996144,0.5547635,0.118077345,0.0026721016,0.006263646],"about_ca_topic_score_codex":0.000071452036,"about_ca_topic_score_gemma":0.0000015402779,"teacher_disagreement_score":0.5579842,"about_ca_system_score_codex":0.00016965029,"about_ca_system_score_gemma":0.00017575547,"threshold_uncertainty_score":0.9997898},"labels":[],"label_agreement":null},{"id":"W2013579017","doi":"10.1109/coase.2010.5584605","title":"A Quality Framework to check the applicability of engineering and statistical assumptions for automated gauges","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistical process control; Correctness; Outlier; Computer science; Process (computing); Process capability; Automotive industry; Quality (philosophy); Industrial engineering; Data mining; Statistical model; Gauge (firearms); Work in process; Engineering; Algorithm; Artificial intelligence","score_opus":0.025020753896220906,"score_gpt":0.3472391183472207,"score_spread":0.32221836445099983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013579017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062210843,0.000002815984,0.93130004,0.0006970191,0.000052710242,0.00023239986,0.000010548887,0.005463482,0.000030165878],"genre_scores_gemma":[0.48009008,1.063885e-7,0.519785,0.000059496862,0.000009120595,0.000050988157,3.6207058e-7,0.0000021819774,0.0000026683683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994079,0.000018141,0.00016227135,0.00019152346,0.00009604007,0.00012414844],"domain_scores_gemma":[0.9966592,0.0027105429,0.000029892919,0.0004662529,0.00007214654,0.00006191684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007241981,0.00006513545,0.00010893422,0.000025455402,0.00005949543,0.000050241262,0.00029884337,0.000054112636,0.000003918271],"category_scores_gemma":[0.002947103,0.000044570243,0.000020022084,0.00013862517,0.000046393267,0.000038919454,0.00012911,0.00012252513,0.0000010635972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072375874,0.00010763124,0.009855836,0.00011522518,0.000015442962,2.7774522e-7,0.00089802867,0.00010514112,0.0061719497,0.9311397,0.0068754065,0.044708133],"study_design_scores_gemma":[0.000081756174,0.000083187864,0.21064708,0.0000213887,0.0000053314493,0.0000055780133,0.0000058366377,0.5862877,0.0020450873,0.19978297,0.0008565376,0.0001775568],"about_ca_topic_score_codex":0.00005626258,"about_ca_topic_score_gemma":0.000006395041,"teacher_disagreement_score":0.73135674,"about_ca_system_score_codex":0.000005194995,"about_ca_system_score_gemma":0.000019503961,"threshold_uncertainty_score":0.35281703},"labels":[],"label_agreement":null},{"id":"W2013851052","doi":"10.1007/s10664-006-9031-3","title":"A practical approach to testing GUI systems","year":2006,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Component (thermodynamics); Set (abstract data type); Graph; Graphical user interface; Software engineering; Programming language; Theoretical computer science","score_opus":0.060666448574408956,"score_gpt":0.297102360528753,"score_spread":0.23643591195434405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013851052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028374242,0.000077122866,0.9698866,0.0002629286,0.00030675152,0.00022248867,0.0000013363268,0.025578536,0.00082681555],"genre_scores_gemma":[0.2356102,1.2194582e-7,0.7637761,0.00016568328,0.00026885746,0.000082154926,0.0000024079275,0.00002993466,0.00006452641],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980383,0.00004196115,0.0003577538,0.0005757607,0.00041954877,0.0005667061],"domain_scores_gemma":[0.99748415,0.0014893449,0.00006131068,0.0006127401,0.00013114723,0.00022133162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046672722,0.0002568958,0.00026891378,0.00018931033,0.00011697963,0.00033708868,0.00059890916,0.00012003678,7.6655033e-7],"category_scores_gemma":[0.005435978,0.00024465655,0.00006342433,0.0011456606,0.000014414478,0.00027855468,0.0003455993,0.0003012332,0.000050097395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008425411,0.0007264138,0.19109246,0.00036824337,0.000049092363,0.00027173868,0.00040577305,0.26204482,0.00024584236,0.018188946,0.5183488,0.008249395],"study_design_scores_gemma":[0.00024864974,0.00017860137,0.03210743,0.00022612516,0.000014951265,0.0006707009,0.0000027851872,0.93158793,0.00017004681,0.0023264624,0.031379864,0.0010864591],"about_ca_topic_score_codex":0.00019548635,"about_ca_topic_score_gemma":2.5199813e-7,"teacher_disagreement_score":0.6695431,"about_ca_system_score_codex":0.0001283614,"about_ca_system_score_gemma":0.00006809859,"threshold_uncertainty_score":0.9976805},"labels":[],"label_agreement":null},{"id":"W2015146187","doi":"10.1109/ase.2013.6693121","title":"PYTHIA: Generating test cases with oracles for JavaScript applications","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"JavaScript; Computer science; Unobtrusive JavaScript; Unit testing; Programming language; Test case; Web application; Point (geometry); Code (set theory); Operating system; Rich Internet application; Software; Machine learning","score_opus":0.023159578142140497,"score_gpt":0.2505283463855822,"score_spread":0.22736876824344168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015146187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014136437,0.000061903585,0.98804235,0.0005428516,0.000020186175,0.0005000796,0.0000020345694,0.008782474,0.00063446834],"genre_scores_gemma":[0.18631059,0.0000012191085,0.81170994,0.00064077706,0.00006185805,0.0009039334,0.0000028905772,0.000009816805,0.00035896534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931437,0.0000085396405,0.00012585719,0.0002682559,0.000097920376,0.00018505375],"domain_scores_gemma":[0.9984598,0.0007872266,0.00005219502,0.0004450872,0.00019710584,0.000058541464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104051134,0.00009712108,0.00008856831,0.00004873804,0.00021828433,0.00026663914,0.00037740043,0.00003073007,0.000007848923],"category_scores_gemma":[0.00022422087,0.00006993031,0.00002380435,0.00019801268,0.000031028325,0.0002952026,0.0000765073,0.0000467863,0.00003183029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012026004,0.00019357876,0.012218186,0.000044482356,0.000018514014,0.000005949886,0.00021902716,0.00006800358,0.0024730233,0.027972477,0.39838815,0.5583974],"study_design_scores_gemma":[0.0007064752,0.0012652788,0.0025957345,0.00015900908,0.00003344242,0.0006166488,0.000063797896,0.817906,0.023020416,0.127708,0.024609383,0.0013157695],"about_ca_topic_score_codex":0.0003626388,"about_ca_topic_score_gemma":0.00002558226,"teacher_disagreement_score":0.8178381,"about_ca_system_score_codex":0.00001374019,"about_ca_system_score_gemma":0.00004069666,"threshold_uncertainty_score":0.28516752},"labels":[],"label_agreement":null},{"id":"W2016250485","doi":"10.1016/s0140-3664(99)00227-3","title":"Test generation based on control and data dependencies within system specifications in SDL","year":2000,"lang":"en","type":"article","venue":"Computer Communications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Instituto de Telecomunicações","keywords":"Computer science; Control flow; Data flow diagram; Programming language; Specification language; Extended finite-state machine; System requirements specification; Control (management); Test data; Finite-state machine; Distributed computing; Software engineering; Database; Artificial intelligence","score_opus":0.13848095803885363,"score_gpt":0.2977731457244659,"score_spread":0.15929218768561226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016250485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001942061,0.00024139177,0.98906696,0.0036420117,0.000086767046,0.0003379184,0.000032065644,0.0032727947,0.0013780574],"genre_scores_gemma":[0.605007,0.000018057424,0.39448246,0.00034517597,0.000037493013,0.00003766634,0.00005191741,0.000006373786,0.000013888236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871826,0.00022660989,0.00032673305,0.00041996414,0.00016037113,0.00014804336],"domain_scores_gemma":[0.9933405,0.0011895092,0.000085306405,0.005253809,0.00007100228,0.0000598678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061411876,0.00012942668,0.00014989369,0.0001655684,0.00032545518,0.000276641,0.0031159802,0.000054055323,0.0000028453505],"category_scores_gemma":[0.00011242318,0.00012963667,0.000017902048,0.00038078704,0.00008984855,0.0003324698,0.0004383057,0.0002034285,0.000030017276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002273226,0.002628459,0.07180318,0.0001245706,0.00006018369,0.000039595387,0.0038649687,0.029539607,0.0004978102,0.18981823,0.07195115,0.6296495],"study_design_scores_gemma":[0.00027901953,0.00005015544,0.010143236,0.00009212362,0.000004812064,0.000017351966,0.0000034146321,0.9875729,0.00001444644,0.0005274506,0.0011594938,0.00013559981],"about_ca_topic_score_codex":0.0000806289,"about_ca_topic_score_gemma":0.000113722184,"teacher_disagreement_score":0.95803326,"about_ca_system_score_codex":0.000060046394,"about_ca_system_score_gemma":0.00008000883,"threshold_uncertainty_score":0.5790318},"labels":[],"label_agreement":null},{"id":"W2019724127","doi":"10.1109/icst.2012.205","title":"Incremental Test Case Generation for UML-RT Models Using Symbolic Execution","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Unified Modeling Language; Test case; Software engineering; Leverage (statistics); Iterative and incremental development; Test Management Approach; Symbolic execution; Code coverage; Code generation; System under test; Software development; Software; Programming language; Software construction; Artificial intelligence; Machine learning; Operating system","score_opus":0.15395948223293526,"score_gpt":0.32926824706890745,"score_spread":0.1753087648359722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019724127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11262434,0.000050449744,0.8835557,0.000042588414,0.00017030047,0.00018478674,0.000002178991,0.0031183818,0.00025129283],"genre_scores_gemma":[0.573266,5.795255e-7,0.42639783,0.00014495879,0.00014667449,0.000018988532,0.0000027845792,0.000005219161,0.000016953461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992949,0.00002078676,0.00014527982,0.00018345755,0.00011103336,0.00024458775],"domain_scores_gemma":[0.9994249,0.000115936324,0.000049534196,0.00026942432,0.00006794566,0.000072307914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037625365,0.000093845854,0.00007896931,0.000076125034,0.00021150078,0.00009652756,0.00014839253,0.00004772533,0.000002325225],"category_scores_gemma":[0.00010871044,0.000086928914,0.000034288045,0.00013335356,0.0000132171635,0.00086404727,0.00009246816,0.00003915411,0.0000027970357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017974884,0.0018980635,0.0386808,0.0001720707,0.00008352353,0.00015199374,0.008486325,0.005232563,0.22557876,0.29710758,0.1429736,0.27961677],"study_design_scores_gemma":[0.00009738836,0.000040761723,0.000030531108,0.000009074465,0.0000065708223,0.0007360756,0.0000041193084,0.9776279,0.01520647,0.006086188,0.000026571633,0.00012837655],"about_ca_topic_score_codex":0.00035898908,"about_ca_topic_score_gemma":0.0000064497517,"teacher_disagreement_score":0.9723953,"about_ca_system_score_codex":0.00007811578,"about_ca_system_score_gemma":0.000025811465,"threshold_uncertainty_score":0.3544858},"labels":[],"label_agreement":null},{"id":"W2019797727","doi":"10.1016/j.jss.2009.05.019","title":"Exploring alternatives for transition verification","year":2009,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Sequence (biology); Invertible matrix; Finite-state machine; Computer science; Model checking; State (computer science); Range (aeronautics); Transition system; Automaton; Algorithm; Conformance testing; Theoretical computer science; Programming language; Mathematics; Engineering","score_opus":0.10664762297229999,"score_gpt":0.28679998609778135,"score_spread":0.18015236312548136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019797727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06422527,0.0006866842,0.9339904,0.00031944283,0.00027041964,0.00007958612,0.0000010063706,0.00042068644,0.0000064845835],"genre_scores_gemma":[0.8505719,0.00008132497,0.1491281,0.000049919858,0.0001551514,0.000003835327,3.1870593e-7,0.0000030401804,0.000006424065],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943435,0.000023695324,0.00023949263,0.00008951941,0.00013174755,0.00008121007],"domain_scores_gemma":[0.9993274,0.00013133367,0.00019677958,0.00010658691,0.00019119505,0.0000466721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039482318,0.000060217306,0.00013593565,0.00009900901,0.0000735715,0.00011414591,0.00016185395,0.00002234436,8.694262e-8],"category_scores_gemma":[0.00014668473,0.00004863079,0.00004489035,0.000071474584,0.000007944867,0.0006612098,0.0000055508976,0.00005670491,1.7745586e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007644833,0.00017375908,0.0016420962,0.00030418293,0.000065553344,0.00004665197,0.014765823,0.0008772199,0.0017585657,0.019926379,0.0046702162,0.9556931],"study_design_scores_gemma":[0.009835579,0.018604252,0.19914693,0.012984223,0.00028017166,0.007643033,0.0020229674,0.18711405,0.015474283,0.5116182,0.031861167,0.0034151766],"about_ca_topic_score_codex":0.0000062132412,"about_ca_topic_score_gemma":5.6647277e-8,"teacher_disagreement_score":0.9522779,"about_ca_system_score_codex":0.00001937091,"about_ca_system_score_gemma":0.000018523773,"threshold_uncertainty_score":0.19831061},"labels":[],"label_agreement":null},{"id":"W2020104929","doi":"10.1145/2591062.2591168","title":"A compiler project with learning progressions","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Compiler; Computer science; Compiler construction; Structuring; Programming language; Optimizing compiler; Compiler correctness; Course (navigation); Software engineering; Mathematics education; Engineering; Psychology","score_opus":0.023419842353767893,"score_gpt":0.27901821184150116,"score_spread":0.2555983694877333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020104929","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028668798,0.0000065632667,0.9607025,0.00028346493,0.000025358186,0.00010410164,4.0642938e-8,0.020231377,0.015779724],"genre_scores_gemma":[0.49139643,2.4475034e-7,0.50803703,0.00013555106,0.00001584399,0.000018115148,4.584363e-7,0.0000046166897,0.00039172807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934834,0.000061374216,0.000070690214,0.0002115715,0.00014468201,0.0001633564],"domain_scores_gemma":[0.9994063,0.00017422663,0.000037911053,0.00029376094,0.000051747174,0.000036072877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022934687,0.00007552002,0.0000788629,0.00006470553,0.00013506976,0.00010725333,0.00033631272,0.000023272007,0.0000035003586],"category_scores_gemma":[0.00014128709,0.000046780424,0.000015662481,0.00025736113,0.00002952762,0.00012454407,0.00012141276,0.00012076323,0.00002044227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012287055,0.00020358381,0.21777536,0.000031719126,0.000021597383,0.000020331008,0.0014388318,0.00012901635,0.00008778171,0.086217254,0.112856925,0.5812053],"study_design_scores_gemma":[0.00078916247,0.0023393724,0.020049317,0.0005000782,0.000012140975,0.00028395347,0.000013869993,0.8372437,0.001696114,0.031201305,0.10491071,0.00096027413],"about_ca_topic_score_codex":0.000054399912,"about_ca_topic_score_gemma":0.0000032334347,"teacher_disagreement_score":0.8371147,"about_ca_system_score_codex":0.0000069186126,"about_ca_system_score_gemma":0.000034498473,"threshold_uncertainty_score":0.19076502},"labels":[],"label_agreement":null},{"id":"W2021654859","doi":"10.1109/asqed.2013.6643604","title":"Mu-GSIM: A mutation testing simulator on GPUs","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; CMC Microsystems (Canada)","funders":"","keywords":"Computer science; Parallel computing; Speedup; Leverage (statistics); Kernel (algebra); Graphics; CUDA; Computer architecture; Operating system","score_opus":0.031850754151639356,"score_gpt":0.2596742175700641,"score_spread":0.22782346341842474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021654859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10902883,0.000010998004,0.8498199,0.0006576975,0.00017569517,0.00025878564,2.2311853e-7,0.027997395,0.0120504955],"genre_scores_gemma":[0.6523478,7.714126e-8,0.34661737,0.00078476535,0.000028518622,0.000020426687,3.501665e-7,0.000005743506,0.00019497969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919033,0.000026399002,0.00014065515,0.00026531436,0.0001818061,0.00019550006],"domain_scores_gemma":[0.99850607,0.0008314676,0.00005334198,0.0004058021,0.00013506407,0.000068250585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001430965,0.000100109806,0.00008258098,0.00008833772,0.00009652396,0.0002054847,0.00037216803,0.000039939372,0.000023219995],"category_scores_gemma":[0.001048258,0.000081901206,0.00002340043,0.00033818508,0.00001542767,0.00030408462,0.00009376697,0.00008439912,0.00042029258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020934785,0.00016296217,0.015932102,0.000022674902,0.000011824283,0.000043147815,0.00046963696,0.0023572317,0.00081226934,0.016549597,0.08592953,0.87770694],"study_design_scores_gemma":[0.00013009823,0.00021319743,0.009576261,0.000047687543,0.000001648285,0.000024977078,0.0000025723405,0.8877041,0.0026259401,0.09928865,0.00018115633,0.00020375635],"about_ca_topic_score_codex":0.00034499398,"about_ca_topic_score_gemma":8.5272336e-7,"teacher_disagreement_score":0.88534683,"about_ca_system_score_codex":0.00002663399,"about_ca_system_score_gemma":0.000026836522,"threshold_uncertainty_score":0.5402151},"labels":[],"label_agreement":null},{"id":"W2022255738","doi":"10.1109/ccece.2008.4564528","title":"Verification of program dynamic behaviours based on static analysis","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Static analysis; Coding (social sciences); Program analysis; Dynamic program analysis; Static program analysis; Source code; Dynamic programming; State (computer science); Code (set theory); Programming language; Algorithm; Software; Software development","score_opus":0.02033448777341849,"score_gpt":0.2336014875384555,"score_spread":0.21326699976503702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022255738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15135124,0.000023926017,0.8449303,0.00060233864,0.00007407189,0.00038916784,0.000008678645,0.0022618682,0.0003584121],"genre_scores_gemma":[0.93533945,0.000014865908,0.06437527,0.00016100428,0.000014106712,0.0000604724,0.000010113821,0.000012965569,0.000011727449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983286,0.000012332684,0.00029341568,0.0005685697,0.00030913387,0.00048790523],"domain_scores_gemma":[0.9987844,0.00010384188,0.00011254869,0.00026477125,0.00033730787,0.00039711193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014416517,0.00027229654,0.00036541483,0.0010225857,0.00013170337,0.00017865858,0.0005927665,0.00011401442,0.0000058251617],"category_scores_gemma":[0.00007663551,0.0002716351,0.000080058475,0.0014512046,0.00006599464,0.00016824454,0.000036901332,0.00030390444,0.0000023601106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006105139,0.0008777627,0.06682237,0.0002530283,0.00037815174,0.00014532031,0.0024172307,0.007956398,0.000543046,0.21140611,0.0018224815,0.70731705],"study_design_scores_gemma":[0.00013733601,0.00066847994,0.043202978,0.000084682295,0.00003330273,0.000012697676,0.0000012947088,0.9547184,0.00016250384,0.00065485376,0.00003661892,0.00028681755],"about_ca_topic_score_codex":0.0015314561,"about_ca_topic_score_gemma":0.0001277447,"teacher_disagreement_score":0.946762,"about_ca_system_score_codex":0.00012893754,"about_ca_system_score_gemma":0.00039679723,"threshold_uncertainty_score":0.9999736},"labels":[],"label_agreement":null},{"id":"W2022887099","doi":"10.1145/1569901.1570123","title":"MC/DC automatic test input data generation","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Software quality; Computer science; Reliability engineering; Code coverage; Fitness function; Software; Random testing; Chaining; Test suite; Test data; Test case; Algorithm; Engineering; Software development; Machine learning; Software engineering; Genetic algorithm; Programming language","score_opus":0.07731818523370544,"score_gpt":0.30886928560908844,"score_spread":0.231551100375383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022887099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026468262,0.000035524827,0.972467,0.0021405322,0.00009833312,0.0000730389,0.0000013654,0.019821554,0.0027158356],"genre_scores_gemma":[0.4482652,0.00000179318,0.5500507,0.0014325633,0.00007460635,0.0000017212931,0.000012085362,0.0000026323198,0.0001587146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918646,0.000021058904,0.00014975609,0.00032886417,0.00016608961,0.00014776732],"domain_scores_gemma":[0.9982303,0.00016468346,0.000042937914,0.0014754325,0.00003938066,0.000047291753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031213072,0.00008356671,0.000081161816,0.00006325028,0.00008767629,0.0002093175,0.0012534207,0.000035754052,0.00001100205],"category_scores_gemma":[0.0006475874,0.000069971364,0.000012852706,0.00024283229,0.000010847053,0.0005263779,0.00023846896,0.00006027968,0.000062808496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6692934e-8,0.000078704405,0.0010410337,0.0000032277137,0.0000018575242,0.000008383234,0.00007622258,0.0000075477765,0.0009405853,0.0036862502,0.41152653,0.5826296],"study_design_scores_gemma":[0.00005484989,0.000088354296,0.0031758016,0.000013401393,0.000002587853,0.000027905733,2.806464e-7,0.97758365,0.0016348774,0.016354075,0.0009384594,0.00012576926],"about_ca_topic_score_codex":0.000027275186,"about_ca_topic_score_gemma":0.0000032954406,"teacher_disagreement_score":0.9775761,"about_ca_system_score_codex":0.000016007423,"about_ca_system_score_gemma":0.000041613224,"threshold_uncertainty_score":0.28533494},"labels":[],"label_agreement":null},{"id":"W2023975198","doi":"10.1109/sera.2010.46","title":"Modeling and Validating Requirements Using Executable Cotnracts and Scenarios","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Executable; Software engineering; Functional requirement; Context (archaeology); Non-functional requirement; Set (abstract data type); Model-based testing; Test (biology); Key (lock); Conformance testing; Test case; Software; Software development; Programming language; Machine learning; Software construction; Standardization; Operating system","score_opus":0.05552498095438944,"score_gpt":0.30476977822824,"score_spread":0.24924479727385054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023975198","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46696362,0.000020630296,0.5306854,0.000057760735,0.000075114105,0.00005100655,1.4948188e-7,0.0018356786,0.0003105954],"genre_scores_gemma":[0.5430408,0.0000018185132,0.45680678,0.0001123825,0.000015503909,0.000001248748,1.8837193e-7,0.000004446812,0.00001679256],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921507,0.000016307871,0.00014039845,0.00029056365,0.00013404856,0.00020358988],"domain_scores_gemma":[0.99944425,0.00009124805,0.000038649174,0.00028457865,0.000057185734,0.000084100015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004271683,0.00009649231,0.00009851815,0.00006568963,0.0002161675,0.0003179363,0.0001950519,0.000049540697,0.0000022834047],"category_scores_gemma":[0.00026926305,0.000086335276,0.000009861541,0.000110606554,0.000027694137,0.0005350552,0.0003444013,0.00014164324,8.6247235e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018583965,0.00029205577,0.16045749,0.00030461018,0.00008190246,0.00010924628,0.006109739,0.007178248,0.4145958,0.055119697,0.0030372967,0.35269532],"study_design_scores_gemma":[0.00008526047,0.00001603434,0.000059974514,0.000038307287,0.0000033042934,0.000071903945,0.0000048942097,0.9836597,0.0023204046,0.013593326,0.0000266618,0.000120244804],"about_ca_topic_score_codex":0.00042906482,"about_ca_topic_score_gemma":0.0000073189963,"teacher_disagreement_score":0.97648144,"about_ca_system_score_codex":0.00000782679,"about_ca_system_score_gemma":0.000027863856,"threshold_uncertainty_score":0.35206503},"labels":[],"label_agreement":null},{"id":"W2024965224","doi":"10.4236/jsea.2013.610a005","title":"Traceability in Acceptance Testing","year":2013,"lang":"en","type":"article","venue":"Journal of Software Engineering and Applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Traceability; Computer science; Software engineering; Acceptance testing; Requirements traceability; Executable; Quality (philosophy); Process (computing); Stakeholder; Model-based testing; Systems engineering; Test strategy; Risk analysis (engineering); Software; Reliability engineering; Test case; Software development; Engineering; Requirement; Programming language","score_opus":0.012713276665239758,"score_gpt":0.2267064411533581,"score_spread":0.21399316448811836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024965224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04808828,0.00035194398,0.94999486,0.00014590725,0.000032896605,0.00011700558,3.3102557e-7,0.0012506038,0.00001817792],"genre_scores_gemma":[0.4666194,0.000007892457,0.5332757,0.000020220483,0.000037602116,0.000031594784,6.6080574e-8,0.000004031436,0.0000034743086],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993954,0.000008718402,0.00026650628,0.00011307428,0.000096234166,0.00012012166],"domain_scores_gemma":[0.99890006,0.00059424684,0.00010567282,0.00019053939,0.0001397786,0.00006969423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025904295,0.00007366214,0.00012230461,0.000118735545,0.000036584373,0.00007682176,0.0002949903,0.000033601456,0.000001723816],"category_scores_gemma":[0.0007888365,0.00006707135,0.000024066429,0.00038997259,0.00001486535,0.00032815765,0.000047609825,0.0001840588,0.0000026423982],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.021478e-7,0.00013460827,0.1812689,0.00009170941,0.000011061036,0.000006496376,0.00031320995,0.0036711397,0.00065187854,0.0018631587,0.0016865919,0.81030035],"study_design_scores_gemma":[0.00041142423,0.00014667881,0.8111067,0.00040031335,0.000009652204,0.0004048507,0.000015785345,0.13415556,0.00039662846,0.049481284,0.0030313728,0.0004397687],"about_ca_topic_score_codex":0.000020897676,"about_ca_topic_score_gemma":2.974679e-7,"teacher_disagreement_score":0.8098606,"about_ca_system_score_codex":0.000028310431,"about_ca_system_score_gemma":0.000026941589,"threshold_uncertainty_score":0.27350903},"labels":[],"label_agreement":null},{"id":"W2025618033","doi":"10.1007/s10270-002-0004-8","title":"A UML-Based Approach to System Testing","year":2002,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":303,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Unified Modeling Language; Sequence diagram; Class diagram; Object Constraint Language; Software engineering; Applications of UML; Testability; Model-based testing; Programming language; UML tool; Context (archaeology); Test case; Test Management Approach; Systems Modeling Language; Activity diagram; System testing; Software development; Reliability engineering; Software; Software construction","score_opus":0.09020794658056883,"score_gpt":0.23924228661756475,"score_spread":0.14903434003699592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025618033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017127586,0.00056513114,0.95263827,0.00004528631,0.00054279296,0.0005968832,0.0000040986133,0.041766766,0.002128015],"genre_scores_gemma":[0.5439675,2.148012e-7,0.45553225,0.0001202785,0.00012467791,0.00016833228,0.0000015247389,0.00003598197,0.00004925389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996735,0.00016491904,0.000681472,0.0009957913,0.0006867924,0.00073601946],"domain_scores_gemma":[0.99722147,0.00045304262,0.00018222781,0.0014332054,0.0003928039,0.00031726522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009811245,0.00038692364,0.00048160035,0.0003797993,0.00042856325,0.0005823767,0.001422891,0.00016188304,6.658205e-7],"category_scores_gemma":[0.001130128,0.0003706245,0.00011726163,0.001226306,0.000019286721,0.00032932407,0.0002815387,0.0002723805,0.00011189516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028662357,0.00012304272,0.0024490238,0.0006973682,0.000019953743,0.000036373054,0.00083346723,0.9679515,0.000032206284,0.002499116,0.0045248126,0.020830266],"study_design_scores_gemma":[0.00017323722,0.000068747366,0.0000053360154,0.0009278898,0.0000100808575,0.00013784482,0.000030102483,0.99784034,0.000011057658,0.00022067073,0.000117361946,0.00045732362],"about_ca_topic_score_codex":0.00056374876,"about_ca_topic_score_gemma":5.240738e-7,"teacher_disagreement_score":0.54225475,"about_ca_system_score_codex":0.0002764631,"about_ca_system_score_gemma":0.00006921546,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W2026184507","doi":"10.1093/comjnl/bxm096","title":"The Effect of the Distributed Test Architecture on the Power of Testing","year":2007,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Observability; Controllability; Finite-state machine; Computer science; Equivalence (formal languages); Conformance testing; Architecture; Mathematics; Algorithm; Discrete mathematics","score_opus":0.012032451917902767,"score_gpt":0.24116125434326105,"score_spread":0.22912880242535827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026184507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16552193,0.00013976787,0.8273381,0.005315108,0.0006989802,0.00025819495,0.0000032301361,0.0004344258,0.00029026018],"genre_scores_gemma":[0.9850399,0.0000015612992,0.014378653,0.0003532142,0.00020413875,0.000002002561,1.2030408e-7,0.000009312205,0.000011106355],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982392,0.00043620713,0.0003750853,0.00014083115,0.00049553,0.0003131489],"domain_scores_gemma":[0.9789176,0.0194368,0.00045557058,0.0009778477,0.00016496418,0.00004721305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046008616,0.00016386966,0.00017110647,0.00004278666,0.00081601576,0.00016834914,0.0029947334,0.0000409809,0.000001260374],"category_scores_gemma":[0.0018338845,0.000052732543,0.0001602706,0.00058640324,0.00026923264,0.00004294717,0.0005453811,0.0007641062,0.0000018099657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014259933,0.00021914944,0.09781213,0.000049863393,0.00022556218,0.000060264483,0.0040874635,0.005621076,0.0022442846,0.008141104,0.09775137,0.78364515],"study_design_scores_gemma":[0.0019032069,0.008811815,0.49101666,0.0028232078,0.00014314639,0.0064372793,0.000042716405,0.12947184,0.08041006,0.2734515,0.004504855,0.0009836811],"about_ca_topic_score_codex":0.000008413074,"about_ca_topic_score_gemma":0.0000011835708,"teacher_disagreement_score":0.81951797,"about_ca_system_score_codex":0.000028735292,"about_ca_system_score_gemma":0.00004744054,"threshold_uncertainty_score":0.6276216},"labels":[],"label_agreement":null},{"id":"W2028661287","doi":"10.1016/j.ipl.2005.01.011","title":"Minimizing the number of inputs while applying adaptive test cases","year":2005,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computerized adaptive testing; Test (biology); Algorithm; Mathematics; Statistics","score_opus":0.024393448385554278,"score_gpt":0.26021796415042353,"score_spread":0.23582451576486926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028661287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021635376,0.000033697892,0.9678478,0.0053969463,0.000071575414,0.00019127355,0.0000025173545,0.0028336444,0.0019871397],"genre_scores_gemma":[0.7702257,7.9081707e-7,0.22401124,0.0056740926,0.000040229173,0.000037287107,0.000001903611,0.000004015559,0.000004728418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990907,0.000019615836,0.00034117483,0.00010117492,0.00027032418,0.00017701257],"domain_scores_gemma":[0.9988467,0.0004135391,0.00031907778,0.00025331508,0.00013831475,0.000029050598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031325212,0.00010828253,0.0001018391,0.00009064045,0.00022860062,0.00024216057,0.00049490685,0.000034285385,0.000003001271],"category_scores_gemma":[0.00033458308,0.000081951715,0.000033765216,0.00037420876,0.00007207973,0.002597292,0.00011101911,0.00012463423,0.000032619762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069645503,0.00004069176,0.0075578936,0.00011339885,0.000010442701,0.000003488033,0.0122267455,0.0012699574,0.00043528533,0.0006573555,0.027489226,0.9501886],"study_design_scores_gemma":[0.0012037439,0.0001604776,0.007187108,0.0018534913,0.000051696858,0.0013232472,0.00048991246,0.8931198,0.035751436,0.0037598184,0.053549398,0.0015498569],"about_ca_topic_score_codex":0.00002363226,"about_ca_topic_score_gemma":5.8328374e-7,"teacher_disagreement_score":0.9486387,"about_ca_system_score_codex":0.000041908777,"about_ca_system_score_gemma":0.0000572276,"threshold_uncertainty_score":0.33418941},"labels":[],"label_agreement":null},{"id":"W2029160271","doi":"10.1007/s11219-014-9232-8","title":"Toward a mature industrial practice of software test automation","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Automation; Software engineering; Test (biology); Software; Computer science; Software testing; Engineering; Operating system","score_opus":0.06356689489556629,"score_gpt":0.33149529574143893,"score_spread":0.26792840084587266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029160271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032039038,0.00011760859,0.9872405,0.0021752433,0.00074462756,0.00014529514,0.0000105847075,0.006179637,0.00018259777],"genre_scores_gemma":[0.22488697,0.0000101908645,0.77372146,0.00083148445,0.00047427748,0.0000074774134,0.0000052707524,0.000022484483,0.000040383868],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996466,0.00081374793,0.0009463619,0.00038787074,0.00097443984,0.00041159109],"domain_scores_gemma":[0.9900433,0.006654607,0.0012804619,0.00083796226,0.00093952514,0.00024414994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050344835,0.0002580498,0.00043935273,0.00024269748,0.00028985328,0.00037969477,0.0012705697,0.00030630938,0.000018360324],"category_scores_gemma":[0.071555875,0.00023111838,0.00019293587,0.00061922264,0.00009611782,0.0012199879,0.00027405488,0.0009615826,0.000021916108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009799298,0.0007801958,0.07028929,0.00025280126,0.00012249472,0.000065520144,0.004522687,0.00015220852,0.00015580788,0.008590733,0.120462395,0.79450786],"study_design_scores_gemma":[0.007509769,0.0041968464,0.052589606,0.0030018825,0.00030433387,0.00919276,0.0003438896,0.010624661,0.005369725,0.81695306,0.08632689,0.003586546],"about_ca_topic_score_codex":0.00007159421,"about_ca_topic_score_gemma":0.0000012362198,"teacher_disagreement_score":0.80836236,"about_ca_system_score_codex":0.00011553968,"about_ca_system_score_gemma":0.00033308417,"threshold_uncertainty_score":0.9424734},"labels":[],"label_agreement":null},{"id":"W2030063053","doi":"10.1142/s0129054102001497","title":"CONSTRUCTING RED-BLACK TREE SHAPES","year":2002,"lang":"en","type":"article","venue":"International Journal of Foundations of Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Tree (set theory); Correctness; Binary tree; Mathematics; Combinatorics; Sequence (biology); Optimal binary search tree; Random binary tree; K-ary tree; Range tree; Algorithm; Ternary search tree; Weight-balanced tree; Interval tree; Discrete mathematics; Binary search tree; Tree structure; Chemistry","score_opus":0.03742748328499703,"score_gpt":0.30269494474112313,"score_spread":0.2652674614561261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030063053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015472008,0.000030884188,0.9779466,0.0027118283,0.0012806824,0.00003668886,0.0000010460104,0.00026796316,0.002252291],"genre_scores_gemma":[0.57532775,0.000007819819,0.42442408,0.0000905254,0.00013486344,3.5227833e-7,1.488792e-7,0.0000022524066,0.000012185146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980405,0.000032373555,0.0005689518,0.00019987441,0.0009980077,0.00016027717],"domain_scores_gemma":[0.99679077,0.00034034895,0.00065555645,0.00025120133,0.0018765144,0.00008561745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007931378,0.00009526921,0.00015969586,0.0006948585,0.0001066958,0.00040047982,0.0032010777,0.000024859366,0.0000262806],"category_scores_gemma":[0.0005431979,0.0000865906,0.0000956853,0.00066268025,0.00051523175,0.0017171503,0.0003697842,0.00013828247,0.000009428954],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004047915,0.00015156255,0.006466536,0.000004963716,0.000045339693,0.00003131118,0.0008620359,0.000757698,0.00059469347,0.054917492,0.0056698234,0.9304945],"study_design_scores_gemma":[0.00059584226,0.00033333976,0.008835312,0.00031386098,0.000011078328,0.00150699,0.000015463776,0.8908471,0.0041198675,0.09153701,0.001613971,0.00027015118],"about_ca_topic_score_codex":0.0000066352786,"about_ca_topic_score_gemma":0.0000010166498,"teacher_disagreement_score":0.93022436,"about_ca_system_score_codex":0.000115554874,"about_ca_system_score_gemma":0.00014831978,"threshold_uncertainty_score":0.59484524},"labels":[],"label_agreement":null},{"id":"W2030553922","doi":"10.1093/comjnl/bxp073","title":"Fault Coverage-Driven Incremental Test Generation","year":2009,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Test suite; Fault coverage; Computer science; Generalization; Completeness (order theory); Test case; Finite-state machine; Fault (geology); Algorithm; Automatic test pattern generation; Test (biology); Code coverage; Programming language; Mathematics; Software; Machine learning; Engineering","score_opus":0.026847956045254667,"score_gpt":0.2612589342968718,"score_spread":0.23441097825161714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030553922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019053519,0.000069524605,0.97469914,0.0037150204,0.00050412427,0.000072486575,5.212725e-7,0.0016407132,0.00024496968],"genre_scores_gemma":[0.74296594,0.000016441554,0.25216118,0.003687617,0.0011351471,0.0000011113102,0.0000011795947,0.0000049147147,0.000026474356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898475,0.000101963284,0.0002242124,0.00017052554,0.00029877917,0.00021976879],"domain_scores_gemma":[0.99915165,0.0001709447,0.00013183255,0.00036796858,0.00009794876,0.00007963824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004881779,0.00012188009,0.000107956635,0.00007353425,0.00045378093,0.00062253076,0.0010389582,0.0000348161,0.0000058597716],"category_scores_gemma":[0.000055424294,0.00008185911,0.00006671166,0.00017490142,0.00002344749,0.0003617926,0.00015360484,0.00030477138,0.000027398219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031039515,0.0001508294,0.0020511032,0.0000014950607,0.000017763778,0.00009219054,0.0008225388,0.002306354,0.002445939,0.0027358108,0.35020715,0.63916576],"study_design_scores_gemma":[0.00039160755,0.0006007895,0.008791755,0.000042884196,0.000008554766,0.0024698274,0.0000010692095,0.9334044,0.0015844472,0.050794274,0.0016621778,0.0002482122],"about_ca_topic_score_codex":0.000004362009,"about_ca_topic_score_gemma":5.182861e-7,"teacher_disagreement_score":0.93109804,"about_ca_system_score_codex":0.000060867125,"about_ca_system_score_gemma":0.000047035952,"threshold_uncertainty_score":0.6003078},"labels":[],"label_agreement":null},{"id":"W2032695995","doi":"10.1145/1822090.1822100","title":"Enbug","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Debugger; Exploit; Reuse; Software engineering; Robustness (evolution); Code reuse; Software; Software security assurance; Software bug; Software construction; Software development; Programming language; Computer security; Debugging; Engineering; Information security","score_opus":0.007335514611735122,"score_gpt":0.23704308351393724,"score_spread":0.22970756890220212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032695995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011548767,0.0000030627891,0.9136774,0.0008612875,0.00036699013,0.000027667502,5.5525458e-8,0.031182684,0.042332098],"genre_scores_gemma":[0.47766972,1.1964333e-7,0.521608,0.0003345617,0.000022142847,0.0000020336208,5.456401e-8,0.0000013349352,0.00036204662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999696,0.00000408506,0.00004253978,0.000108993874,0.00006388229,0.00008447259],"domain_scores_gemma":[0.99949086,0.00007487459,0.0000101796795,0.00036869667,0.000022216169,0.00003320256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001153821,0.00003336198,0.00002991411,0.00002840069,0.000034313427,0.00005857128,0.00042316114,0.000023761955,0.000028569157],"category_scores_gemma":[0.00012443868,0.000026300531,0.000013948658,0.00009506735,0.000012558763,0.00010281504,0.00009455329,0.000089486544,0.00008872746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.5540794e-7,0.000030154493,0.008988316,0.0000018391,0.0000018145622,0.000009012986,0.00009431886,2.463364e-7,0.0043441528,0.51089656,0.19786425,0.27776906],"study_design_scores_gemma":[0.000112003734,0.000056822126,0.00850579,0.000005835048,0.0000011848933,0.000114213675,6.114489e-7,0.024810325,0.038443055,0.8767014,0.050957788,0.0002909439],"about_ca_topic_score_codex":0.000029003586,"about_ca_topic_score_gemma":0.0000041256435,"teacher_disagreement_score":0.46612096,"about_ca_system_score_codex":0.0000014711167,"about_ca_system_score_gemma":0.000013006526,"threshold_uncertainty_score":0.11404416},"labels":[],"label_agreement":null},{"id":"W2032754744","doi":"10.1109/tse.2014.2371458","title":"Guided Mutation Testing for JavaScript Web Applications","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Mutation testing; Test suite; Mutation; JavaScript; Programming language; Metric (unit); Web application; Process (computing); Set (abstract data type); Focus (optics); Data mining; Test case; Theoretical computer science; Machine learning; Operating system; Regression analysis","score_opus":0.057086510097033846,"score_gpt":0.2734156176940332,"score_spread":0.21632910759699936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032754744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047930575,0.000045283938,0.98037195,0.00007084835,0.0005310741,0.00045241142,0.0000134883185,0.017999249,0.000036416943],"genre_scores_gemma":[0.23868392,8.243497e-7,0.76030755,0.000087973815,0.000069043694,0.0007294634,0.0000028239342,0.00003266124,0.0000857473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988224,0.000014935452,0.0002699827,0.0003717976,0.00023005239,0.00029083726],"domain_scores_gemma":[0.99830866,0.0006595137,0.00006249839,0.0005022534,0.00030475168,0.00016230572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003254718,0.00019322729,0.00015892395,0.00026110507,0.00016470267,0.00011899346,0.0004259478,0.000085625376,0.0000010696787],"category_scores_gemma":[0.00038489373,0.00021455895,0.00008179875,0.0006668848,0.000015086295,0.00033126606,0.000003601663,0.00016971433,0.000021327884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011540604,0.00024234093,0.00021232499,0.00016567277,0.00007452751,0.000014219061,0.00066772796,0.63482517,0.0011756805,0.0012834147,0.018110322,0.34321705],"study_design_scores_gemma":[0.00063341967,0.00025123364,0.00004592787,0.00011401516,0.000029183628,0.000120356635,0.00000700593,0.97958916,0.009538671,0.0030638028,0.006105619,0.0005015986],"about_ca_topic_score_codex":0.000018615783,"about_ca_topic_score_gemma":0.0000011833647,"teacher_disagreement_score":0.344764,"about_ca_system_score_codex":0.00013626392,"about_ca_system_score_gemma":0.00012536091,"threshold_uncertainty_score":0.874946},"labels":[],"label_agreement":null},{"id":"W2034691511","doi":"10.1093/logcom/exn077","title":"Collaborative Runtime Verification with Tracematches","year":2008,"lang":"en","type":"article","venue":"Journal of Logic and Computation","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Runtime verification; Computer science; Software deployment; Overhead (engineering); Benchmark (surveying); Instrumentation (computer programming); Distributed computing; Runtime system; Static analysis; Embedded system; Formal verification; Operating system; Programming language","score_opus":0.024144604480013293,"score_gpt":0.26188223756999995,"score_spread":0.23773763308998666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034691511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13877004,0.0001998859,0.8601109,0.0004466631,0.000035334004,0.00003893435,1.316693e-7,0.0002311424,0.00016700073],"genre_scores_gemma":[0.6796269,0.000027458695,0.32024905,0.00006452539,0.000021923777,7.2584487e-7,2.50674e-7,0.0000015592769,0.000007658782],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995216,0.000039553935,0.00015845774,0.0000779249,0.00014810018,0.000054327713],"domain_scores_gemma":[0.9992525,0.000119176286,0.00025203323,0.000055695,0.00028836905,0.00003221872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018180761,0.000054212185,0.000107195345,0.00007117557,0.00009524948,0.000040161263,0.0001027145,0.000023081415,4.3188197e-7],"category_scores_gemma":[0.000042190957,0.00003735483,0.00001395124,0.0002147523,0.000042662137,0.00028792606,0.00001316971,0.00006503052,9.817512e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070421345,0.0015186873,0.109337315,0.00019749021,0.00039367212,0.001478543,0.062041342,0.026511878,0.0027176496,0.07084962,0.08404407,0.6402055],"study_design_scores_gemma":[0.0027893155,0.0063235876,0.36187708,0.0004086702,0.0000682565,0.009741308,0.00042600444,0.20029023,0.0028258003,0.41360727,0.00085875764,0.0007837234],"about_ca_topic_score_codex":0.0000022710976,"about_ca_topic_score_gemma":1.3432172e-7,"teacher_disagreement_score":0.6394218,"about_ca_system_score_codex":0.00001346102,"about_ca_system_score_gemma":0.00006941161,"threshold_uncertainty_score":0.15232857},"labels":[],"label_agreement":null},{"id":"W2034869573","doi":"10.1023/b:ause.0000008668.12782.6c","title":"Granularity-Driven Dynamic Predicate Slicing Algorithms for Message Passing Systems","year":2003,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Program slicing; Computer science; Predicate (mathematical logic); Slicing; Correctness; Granularity; Algorithm; Computation; Theoretical computer science; Programming language","score_opus":0.014441274826881756,"score_gpt":0.2554814375190623,"score_spread":0.24104016269218057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034869573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035463672,0.00065521145,0.9127122,0.000029730412,0.00087177433,0.00041692157,0.000011512018,0.08174272,0.000013561061],"genre_scores_gemma":[0.39516702,0.000007738038,0.604533,0.000030384532,0.000027125898,0.00014580405,0.000012783009,0.000056916328,0.00001918352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979315,0.00006589736,0.00043191315,0.0005816012,0.0003162789,0.0006728333],"domain_scores_gemma":[0.9980929,0.00075628626,0.00014126905,0.0007061725,0.00013899202,0.00016437807],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006500683,0.00033846174,0.00036870074,0.0002943271,0.00027952984,0.00036872007,0.00069451105,0.00019039535,9.477958e-7],"category_scores_gemma":[0.0016322949,0.0003586421,0.00011740739,0.00058813015,0.000025235204,0.0004322404,0.00011129653,0.00025147767,0.000006673993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001322642,0.00041124184,0.013756948,0.0031613556,0.0006593129,0.00036765824,0.003391539,0.8578479,0.0034232396,0.02915529,0.014710819,0.073101446],"study_design_scores_gemma":[0.00030723787,0.000054603715,0.00075840804,0.00044154163,0.000020818854,0.00011661113,0.0000036449783,0.9958031,0.0005452197,0.0005661377,0.0009442845,0.00043838128],"about_ca_topic_score_codex":0.00003866799,"about_ca_topic_score_gemma":6.0870366e-7,"teacher_disagreement_score":0.39162067,"about_ca_system_score_codex":0.00016215722,"about_ca_system_score_gemma":0.000082964536,"threshold_uncertainty_score":0.9998866},"labels":[],"label_agreement":null},{"id":"W2034873526","doi":"10.1007/s00446-008-0062-4","title":"Checking sequences for distributed test architectures","year":2008,"lang":"en","type":"article","venue":"Distributed Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Observability; Controllability; Computer science; Sequence (biology); Construct (python library); Sequence diagram; Distributed computing; Test (biology); Model checking; Digraph; Theoretical computer science; Programming language; Unified Modeling Language; Mathematics; Software","score_opus":0.033862512938887826,"score_gpt":0.2757959318795185,"score_spread":0.2419334189406307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034873526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04993527,0.00012625697,0.937053,0.00041749913,0.00020106435,0.00027164948,0.00017659328,0.0117539335,0.000064726955],"genre_scores_gemma":[0.79041576,0.000001979198,0.20905448,0.00016122998,0.00014457884,0.000021545817,0.00018066347,0.000015683174,0.000004039162],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979245,0.000054358123,0.00041931763,0.00063200825,0.0003043259,0.0006654899],"domain_scores_gemma":[0.99703836,0.0016995316,0.0002340567,0.0006446163,0.00023913005,0.00014430108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004148962,0.00028628882,0.00031691624,0.00011688059,0.00086647266,0.0001864089,0.0013084562,0.00010501044,0.0000015849032],"category_scores_gemma":[0.001871619,0.00027234925,0.00015651554,0.00076953595,0.00013333588,0.00011504889,0.00027263406,0.00024388998,0.0000057153497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060494855,0.0011749227,0.54310775,0.0004293135,0.00027225623,0.00054474943,0.00480683,0.041614097,0.005512746,0.018855192,0.14221185,0.24140978],"study_design_scores_gemma":[0.0007685233,0.0003327656,0.036348216,0.00025637756,0.00001929675,0.0006502106,0.00001838127,0.907324,0.011624095,0.038982123,0.0027068714,0.0009691376],"about_ca_topic_score_codex":0.00005289096,"about_ca_topic_score_gemma":0.0000011497563,"teacher_disagreement_score":0.8657099,"about_ca_system_score_codex":0.00009239567,"about_ca_system_score_gemma":0.00012730413,"threshold_uncertainty_score":0.9999729},"labels":[],"label_agreement":null},{"id":"W2036316394","doi":"10.1145/2814270.2814297","title":"SATCheck: SAT-directed stateless model checking for SC and TSO","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Model checking; Scalability; Stateless protocol; Parallel computing; Memory model; Programming language; Thread (computing); Concurrency; Shared memory; Operating system","score_opus":0.09452424806707642,"score_gpt":0.3089662886004712,"score_spread":0.21444204053339477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036316394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024425928,0.00007800015,0.9590717,0.00048353345,0.000071137176,0.00015481302,0.0000017905929,0.014753027,0.0009600883],"genre_scores_gemma":[0.36791793,0.0000021272087,0.63143474,0.00024185982,0.000018350514,0.000021513546,0.000001753402,0.000008779365,0.0003529125],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991444,0.000017978393,0.00014077763,0.00030998822,0.00014999499,0.00023689694],"domain_scores_gemma":[0.9991508,0.00016465792,0.000046987083,0.00032971645,0.00017378556,0.0001340589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046660448,0.00011289884,0.00014115029,0.00007045525,0.00007540283,0.00015319469,0.00033347297,0.000051955638,5.013603e-7],"category_scores_gemma":[0.0003209544,0.00009757136,0.000024487394,0.00015935529,0.000029765633,0.00024148058,0.00019365216,0.000061880666,0.000002674853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006828906,0.00025639313,0.022160055,0.00013449494,0.000062345876,0.000023558207,0.008831943,0.0021383266,0.0010238719,0.053440116,0.5596038,0.3522568],"study_design_scores_gemma":[0.00024717752,0.000063615844,0.00020663292,0.000020164987,0.0000029688679,0.000010311207,0.0000068324684,0.86635673,0.0015396738,0.1310332,0.00035892363,0.0001537668],"about_ca_topic_score_codex":0.00012081753,"about_ca_topic_score_gemma":0.0000114133145,"teacher_disagreement_score":0.8642184,"about_ca_system_score_codex":0.000030358653,"about_ca_system_score_gemma":0.000106475636,"threshold_uncertainty_score":0.3978845},"labels":[],"label_agreement":null},{"id":"W2036633739","doi":"10.1109/trustcom.2011.151","title":"Tool Support for Automated Traceability of Test/Code Artifacts in Embedded Software Systems","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Traceability; Computer science; Software engineering; Embedded system; Software development; Software construction; Verification and validation; Static program analysis; Development testing; Unit testing; Software; Source code; Software system; Embedded software; Software framework; Operating system; Engineering","score_opus":0.05771103409542019,"score_gpt":0.28947700816024985,"score_spread":0.23176597406482966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036633739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1312958,0.000021355896,0.81844634,0.00003364579,0.00024458056,0.001000728,0.000020176785,0.048109014,0.00082834426],"genre_scores_gemma":[0.569954,2.2854964e-7,0.42984504,0.00003117521,0.0000054026577,0.0000732744,0.0000017219337,0.0000079749225,0.000081223865],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851984,0.00005048905,0.0005314663,0.00039766644,0.00018497946,0.00031556614],"domain_scores_gemma":[0.99790335,0.0009104092,0.00015506183,0.00077244814,0.00019450951,0.00006423073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009308289,0.0001516705,0.00029803842,0.00014227859,0.00003714774,0.000039248855,0.000640624,0.00010044208,0.00001424674],"category_scores_gemma":[0.0021866208,0.0001315759,0.000069565074,0.00033836084,0.000047057467,0.00021206637,0.00011123687,0.000077921824,0.000008969705],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009388449,0.0030648187,0.8612608,0.0014031385,0.000056546134,0.00007089522,0.008879269,0.00041841637,0.0012883845,0.009486728,0.06878911,0.045188017],"study_design_scores_gemma":[0.0007280236,0.00089081714,0.11096635,0.00018989964,0.000012493426,0.000048748327,0.00002848383,0.84054935,0.016220123,0.02971626,0.000105085004,0.00054438465],"about_ca_topic_score_codex":0.0002859038,"about_ca_topic_score_gemma":0.000019328318,"teacher_disagreement_score":0.8401309,"about_ca_system_score_codex":0.00004325552,"about_ca_system_score_gemma":0.0001309469,"threshold_uncertainty_score":0.53655094},"labels":[],"label_agreement":null},{"id":"W2036896594","doi":"10.1016/j.infsof.2013.02.006","title":"A systematic mapping study of web application testing","year":2013,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Bibliometrics; Computer science; Data science; Field (mathematics); Schema (genetic algorithms); Information retrieval; Systematic review; World Wide Web; MEDLINE","score_opus":0.012898108410190436,"score_gpt":0.22467908839648615,"score_spread":0.21178097998629572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036896594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23259471,0.000049183633,0.75476533,0.00013963126,0.000032401895,0.00097646134,4.0266553e-7,0.011314547,0.00012731465],"genre_scores_gemma":[0.80936646,0.0000011620859,0.19023505,0.000070282265,0.0000025476086,0.00031831913,8.027576e-7,0.0000029571725,0.0000024343785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990491,0.00002503709,0.00052118336,0.00012585608,0.00014713935,0.00013165572],"domain_scores_gemma":[0.99857074,0.00026046918,0.00034690087,0.00048291657,0.00030930204,0.000029670744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027220408,0.000101258316,0.00021570717,0.0005718073,0.000099490775,0.00008455176,0.00043937136,0.00009718306,9.1019143e-7],"category_scores_gemma":[0.001494459,0.00008865416,0.000013680493,0.0008966145,0.00004224016,0.00082791597,0.00023481529,0.000106266816,0.000030504725],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017777526,0.000277513,0.2528964,0.006278553,0.00007019582,0.000002131798,0.006678794,0.000049213446,0.00029434476,0.015883727,0.0011626629,0.7164047],"study_design_scores_gemma":[0.00246202,0.0018170235,0.056314252,0.0041733016,0.00005612393,0.00050483365,0.004144008,0.6778311,0.0005615389,0.25062832,0.00023678254,0.0012706828],"about_ca_topic_score_codex":0.00010109406,"about_ca_topic_score_gemma":0.0000018287504,"teacher_disagreement_score":0.715134,"about_ca_system_score_codex":0.000018929248,"about_ca_system_score_gemma":0.000027018486,"threshold_uncertainty_score":0.36152115},"labels":[],"label_agreement":null},{"id":"W2040768172","doi":"10.1145/2304510.2304512","title":"BloomUnit","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Microsoft Research","keywords":"Computer science; Programming language; Semantics (computer science); Bloom filter; Software; Test (biology); Operating system","score_opus":0.02562895817678755,"score_gpt":0.2599044611156117,"score_spread":0.23427550293882415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040768172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030816868,0.00008213436,0.93391913,0.00023488642,0.00013911049,0.000021147074,3.7366274e-8,0.018889043,0.0436328],"genre_scores_gemma":[0.5702992,5.431941e-7,0.428865,0.00038204098,0.000031310537,0.0000022295194,7.687603e-8,0.0000015223773,0.00041804183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996748,0.000011918962,0.00004234331,0.00005542985,0.00006515991,0.00015033434],"domain_scores_gemma":[0.9995567,0.00007717466,0.000010487805,0.00028702346,0.000014735866,0.000053875367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017553104,0.000034428867,0.000031442178,0.000029858003,0.00003759485,0.000030338515,0.00030101257,0.000015457435,0.000020837491],"category_scores_gemma":[0.000066549284,0.000027344033,0.000013311238,0.000119153934,0.000007486132,0.00025095287,0.00011004772,0.0000345398,0.00016125664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5263838e-7,0.00011158684,0.100567855,0.0000042323372,0.00000529083,0.0000021222518,0.0006598467,5.4129e-7,0.00010851187,0.40682423,0.28518334,0.20653208],"study_design_scores_gemma":[0.00047188002,0.00022132066,0.110691555,0.000059174858,0.000012840491,0.00044420615,0.000014111748,0.031527475,0.03290664,0.51788926,0.3043872,0.0013743306],"about_ca_topic_score_codex":0.000025001067,"about_ca_topic_score_gemma":1.5086877e-7,"teacher_disagreement_score":0.5672175,"about_ca_system_score_codex":0.000004998052,"about_ca_system_score_gemma":0.0000056716917,"threshold_uncertainty_score":0.20726816},"labels":[],"label_agreement":null},{"id":"W2040973615","doi":"10.5555/777092.777204","title":"Optimal depth-first strategies for and-or trees","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Probabilistic logic; Computer science; Node (physics); Set (abstract data type); Tree (set theory); Task (project management); Test (biology); Sequence (biology); Focus (optics); Algorithm; Mathematical optimization; Mathematics; Theoretical computer science; Artificial intelligence; Combinatorics","score_opus":0.061381381103267206,"score_gpt":0.28324691919071004,"score_spread":0.22186553808744283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040973615","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031954932,0.00012385397,0.98343915,0.0008798071,0.00005244499,0.00010901692,5.982262e-7,0.00823205,0.0039676097],"genre_scores_gemma":[0.3846311,0.00001069423,0.6145164,0.0001579141,0.00002438496,0.000026568918,1.8118232e-7,0.00000433793,0.0006284269],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994419,0.0000070346778,0.00009252675,0.00021538517,0.00007374949,0.00016937857],"domain_scores_gemma":[0.9993308,0.0003343413,0.000024070452,0.00023263266,0.000031105155,0.00004701172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008796012,0.000084675405,0.000087265675,0.00004836097,0.00011831978,0.0002500943,0.000301347,0.000034909554,0.000017810433],"category_scores_gemma":[0.00008709692,0.000060626844,0.000025186975,0.00010197808,0.000034874425,0.00030666363,0.00008123839,0.00003428089,0.000006637806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017956236,0.00018212922,0.004839116,0.00007587415,0.000027333655,0.000028622588,0.0025368717,0.00018078228,0.000052041145,0.19887523,0.47600377,0.31718025],"study_design_scores_gemma":[0.0006011767,0.0009405982,0.0024598546,0.00006885802,0.000010237062,0.0001419775,0.00006259418,0.9004582,0.0007837287,0.077119894,0.016829833,0.0005230107],"about_ca_topic_score_codex":0.00003708996,"about_ca_topic_score_gemma":0.0000576647,"teacher_disagreement_score":0.90027744,"about_ca_system_score_codex":0.000006748876,"about_ca_system_score_gemma":0.000012111865,"threshold_uncertainty_score":0.2472291},"labels":[],"label_agreement":null},{"id":"W2042380289","doi":"10.1109/ccece.2010.5575202","title":"Specification-based test oracles with JUnit","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Memorial University of Newfoundland","keywords":"Computer science; Oracle; Test Management Approach; Test case; Test harness; Software engineering; Programming language; Process (computing); Test (biology); Unit testing; Software; Software development; Software construction","score_opus":0.01030708878419913,"score_gpt":0.2239426817707521,"score_spread":0.21363559298655296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042380289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074152076,0.0000029714017,0.96474284,0.0016849948,0.0000745813,0.00007315629,5.783398e-7,0.015256028,0.010749656],"genre_scores_gemma":[0.49904412,1.13160425e-7,0.50044936,0.00027899217,0.000022800401,0.000007277425,7.8858704e-7,0.0000042232555,0.00019234672],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944407,0.000007778135,0.00008096503,0.00020533694,0.00013952496,0.00012230418],"domain_scores_gemma":[0.99860996,0.00052668765,0.00003891607,0.0006632666,0.000105048675,0.000056144603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014560133,0.00007456015,0.000057940026,0.00006969366,0.00008411814,0.00013300887,0.0005533342,0.00003213909,0.000039945706],"category_scores_gemma":[0.00026137583,0.000053046184,0.0000137394945,0.00029265115,0.000050059865,0.00012720797,0.00003652886,0.00012980566,0.000076378834],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008991373,0.0006508317,0.4269137,0.000026148775,0.000010565357,0.000048266458,0.0002610413,0.000038065085,0.009614351,0.18448468,0.1533808,0.22456257],"study_design_scores_gemma":[0.0012702114,0.0010577488,0.24171409,0.0001429827,0.00001933239,0.00020241321,0.000013044672,0.34561345,0.16444829,0.14117892,0.1024308,0.0019087337],"about_ca_topic_score_codex":0.000057272384,"about_ca_topic_score_gemma":0.00003364878,"teacher_disagreement_score":0.49162892,"about_ca_system_score_codex":0.0000051966517,"about_ca_system_score_gemma":0.00006943985,"threshold_uncertainty_score":0.21631606},"labels":[],"label_agreement":null},{"id":"W2043042437","doi":"10.1109/issre.2013.6698880","title":"Feedback-directed exploration of web applications to derive test models","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test (biology); Geology","score_opus":0.04747123082249917,"score_gpt":0.2710008017299474,"score_spread":0.22352957090744824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043042437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014105428,0.000009880366,0.98280275,0.00094177277,0.000017804678,0.00039729988,0.0000011694842,0.010054244,0.0043645552],"genre_scores_gemma":[0.47810954,0.0000018083474,0.5212451,0.00018564292,0.00001010802,0.00030947465,0.0000012124167,0.000004024679,0.00013310582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936444,0.000014250374,0.00016395068,0.0002103376,0.00012745245,0.00011958807],"domain_scores_gemma":[0.99888325,0.00023797931,0.00005186315,0.00047453883,0.00028321476,0.000069171525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007638475,0.00007381365,0.00009041765,0.000104496925,0.000051315936,0.00006750741,0.0004271586,0.00003214392,0.000014212019],"category_scores_gemma":[0.00012468503,0.00006565731,0.000021410873,0.0005212882,0.000016770207,0.00073146564,0.0001293892,0.00003704718,0.0001551288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030544193,0.0006782372,0.0031350725,0.000056413854,0.000026105048,0.000001224099,0.003684194,0.0028450172,0.037377164,0.12164787,0.40967694,0.4208687],"study_design_scores_gemma":[0.00008020212,0.00009184547,0.00083078706,0.00002621831,0.0000025424827,0.000002852781,0.000012391858,0.6447146,0.01262736,0.3410065,0.00042672598,0.00017799919],"about_ca_topic_score_codex":0.0001535811,"about_ca_topic_score_gemma":0.000006550986,"teacher_disagreement_score":0.6418696,"about_ca_system_score_codex":0.000016046786,"about_ca_system_score_gemma":0.000038604387,"threshold_uncertainty_score":0.26774275},"labels":[],"label_agreement":null},{"id":"W2043839920","doi":"10.1016/j.jss.2014.01.010","title":"Web application testing: A systematic literature review","year":2014,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Web testing; Dependability; Systematic review; Field (mathematics); Web application; World Wide Web; Empirical research; Data science; Set (abstract data type); Web engineering; Software engineering; Information retrieval; Web application security; The Internet; Web development","score_opus":0.016224326302853694,"score_gpt":0.2516204591044873,"score_spread":0.23539613280163363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043839920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040943583,0.14625199,0.8512502,0.00024300028,0.00027134715,0.00035693104,0.0000010050145,0.0011465302,0.00006955572],"genre_scores_gemma":[0.62515724,0.0045579067,0.36847124,0.0010499508,0.000537314,0.00007638586,0.0000013888609,0.000032149135,0.00011641015],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9985767,0.00018174724,0.0006417306,0.00016014217,0.00031561375,0.00012408862],"domain_scores_gemma":[0.99737155,0.00070715905,0.0007854306,0.00041390432,0.0006111374,0.000110796806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019127908,0.00013075244,0.0005026064,0.00012651659,0.00008645634,0.0002508042,0.00046230885,0.00006635509,1.2301936e-7],"category_scores_gemma":[0.0030688862,0.00008831288,0.00006840118,0.00041534164,0.000015889442,0.00029207696,0.000065764136,0.00018161414,0.0000027547196],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000095530995,0.00020148375,0.027526451,0.77710044,0.00017470877,0.0002028885,0.0012128882,0.00008333251,0.00032585318,0.01916789,0.09112327,0.08287123],"study_design_scores_gemma":[0.00064322614,0.0008241173,0.0012589371,0.8988911,0.00017720346,0.015003542,0.0000137388115,0.06318143,0.000015673919,0.013317453,0.0060197255,0.00065386755],"about_ca_topic_score_codex":0.000004104212,"about_ca_topic_score_gemma":1.4596418e-7,"teacher_disagreement_score":0.6247478,"about_ca_system_score_codex":0.000024244307,"about_ca_system_score_gemma":0.00004613293,"threshold_uncertainty_score":0.3673965},"labels":[],"label_agreement":null},{"id":"W2044138969","doi":"10.1016/s0140-3664(03)00116-6","title":"Context independent unique state identification sequences for testing communication protocols modelled as extended finite state machines","year":2003,"lang":"en","type":"article","venue":"Computer Communications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Nortel (Canada)","funders":"","keywords":"Extended finite-state machine; Computer science; Finite-state machine; Executable; Observability; Sequence (biology); Identification (biology); Conformance testing; Context (archaeology); State (computer science); Theoretical computer science; Control flow; Algorithm; Mathematics; Programming language","score_opus":0.09491792874771247,"score_gpt":0.3503298570391113,"score_spread":0.2554119282913988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044138969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012871503,0.00028633466,0.98543817,0.0010136055,0.00008570585,0.0068096183,0.000019460842,0.0044930405,0.00056692713],"genre_scores_gemma":[0.40066597,0.000044031876,0.591543,0.00036140298,0.000008809596,0.007145124,0.000045360583,0.000026770205,0.00015948147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996898,0.00093723636,0.0008768738,0.0005759721,0.0003120683,0.00039986722],"domain_scores_gemma":[0.9899274,0.0033565487,0.00063889095,0.0049309256,0.0010079208,0.00013828729],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018603608,0.00031524315,0.00033347687,0.0002684733,0.0010645709,0.0007452376,0.00448017,0.0000930348,0.0000026668304],"category_scores_gemma":[0.0011478747,0.00032377508,0.000113393835,0.0007496486,0.00022064624,0.00079672155,0.0009930019,0.00039910828,0.00002728166],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004351852,0.0013885883,0.003788612,0.00021378203,0.00018306835,0.000009275113,0.009546468,0.014802217,0.00092673267,0.2501138,0.0050302153,0.71395373],"study_design_scores_gemma":[0.00041011165,0.00012855465,0.00045873108,0.00018889122,0.000008887507,0.000039886418,0.00000893341,0.63200206,0.0007784809,0.3627016,0.0029557282,0.00031813525],"about_ca_topic_score_codex":0.00032313407,"about_ca_topic_score_gemma":0.00008916064,"teacher_disagreement_score":0.71363556,"about_ca_system_score_codex":0.00013040048,"about_ca_system_score_gemma":0.0003447876,"threshold_uncertainty_score":0.99992144},"labels":[],"label_agreement":null},{"id":"W2044863546","doi":"10.1007/s10009-013-0277-y","title":"Generating effective tests for concurrent programs via AI automated planning techniques","year":2013,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Concurrency; Atomicity; Correctness; Interleaving; Programming language; Debugging; Set (abstract data type); Theory of computation","score_opus":0.029292245096745266,"score_gpt":0.33535090047419397,"score_spread":0.3060586553774487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044863546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018823108,0.000102987266,0.9490025,0.0028554462,0.0009711447,0.00178665,0.00001868436,0.02643009,0.000009404893],"genre_scores_gemma":[0.44891235,0.0000051758116,0.54730666,0.0010922644,0.00021584894,0.0023833208,0.000026763913,0.000042146195,0.000015495298],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99789673,0.00004757668,0.00058947044,0.000528432,0.00041293306,0.0005248273],"domain_scores_gemma":[0.99700326,0.0009718363,0.0001533913,0.0003175418,0.0014455923,0.000108406995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046899036,0.0003455321,0.00035184913,0.00068061857,0.00033160968,0.0008320075,0.0016263227,0.0003453835,0.00000525516],"category_scores_gemma":[0.0012313159,0.00029972172,0.00024593357,0.00030736811,0.00012156743,0.0009502738,0.00009385577,0.0005918337,0.000010877332],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025853718,0.00018617627,0.0015613443,0.000019884636,0.00015321169,0.000024459252,0.00010619421,0.00009755297,0.0022132471,0.003812407,0.0065332293,0.98526645],"study_design_scores_gemma":[0.005981523,0.010893971,0.0020312136,0.0032395886,0.00013229408,0.003632688,0.00003389769,0.35770217,0.18633397,0.39133653,0.035971813,0.0027103743],"about_ca_topic_score_codex":0.0000071215322,"about_ca_topic_score_gemma":9.595544e-7,"teacher_disagreement_score":0.98255605,"about_ca_system_score_codex":0.00021871163,"about_ca_system_score_gemma":0.00008577346,"threshold_uncertainty_score":0.99994546},"labels":[],"label_agreement":null},{"id":"W2045837563","doi":"10.1007/s10664-012-9219-7","title":"Static test case prioritization using topic models","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test suite; Computer science; Code coverage; Test case; Source code; Black box; Test Management Approach; Programming language; White-box testing; Test (biology); Test data; Operating system; Software; Software development; Artificial intelligence; Machine learning","score_opus":0.06432137932201937,"score_gpt":0.3036697114581389,"score_spread":0.23934833213611956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045837563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07237958,0.00019094166,0.91803277,0.000064403575,0.00028314855,0.00009874723,0.0000017364483,0.008934137,0.000014525311],"genre_scores_gemma":[0.5370809,0.0000011681489,0.46265408,0.00012494679,0.000105368155,0.000007784058,0.0000011274052,0.000015419158,0.000009191915],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988658,0.00002193053,0.00022477267,0.00023234509,0.00020371418,0.00045146263],"domain_scores_gemma":[0.9985216,0.0008052508,0.000046362056,0.00037276084,0.000059430306,0.00019457041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024203016,0.00017304359,0.00015985416,0.00011911046,0.0001122495,0.000097553835,0.00025512563,0.00008151158,0.000003972741],"category_scores_gemma":[0.0014001232,0.00017392183,0.000048634698,0.00044923666,0.00001219212,0.00079739053,0.00016901048,0.00017064612,0.000008227141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002932833,0.00056414015,0.76315516,0.00042846313,0.000058909205,0.0012897438,0.0058282507,0.17192984,0.0002808286,0.0032404785,0.009944203,0.043277074],"study_design_scores_gemma":[0.000111651236,0.000036636575,0.0033980168,0.000075157615,0.000011008084,0.0014713063,0.000002664606,0.99075234,0.00024905204,0.0029967315,0.0005388826,0.0003565747],"about_ca_topic_score_codex":0.000036821933,"about_ca_topic_score_gemma":2.968668e-7,"teacher_disagreement_score":0.8188225,"about_ca_system_score_codex":0.00012609163,"about_ca_system_score_gemma":0.00003353302,"threshold_uncertainty_score":0.7092326},"labels":[],"label_agreement":null},{"id":"W2046760913","doi":"10.1109/icmla.2011.69","title":"Fault Detection through Sequential Filtering of Novelty Patterns","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Debugging; Concurrency; Novelty; Fault detection and isolation; Software; Domain (mathematical analysis); Preprocessor; Set (abstract data type); Data mining; Computer engineering; Parallel computing; Distributed computing; Programming language; Artificial intelligence","score_opus":0.0841736094413681,"score_gpt":0.2738196785469875,"score_spread":0.18964606910561943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046760913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04571931,0.0000042209217,0.94607216,0.00001045978,0.00018639855,0.000044251396,8.8116167e-7,0.0043158215,0.0036464669],"genre_scores_gemma":[0.674216,0.0000010168169,0.32568246,0.0000459588,0.000014889599,0.000004076574,2.1433918e-7,0.0000036091426,0.000031813204],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994087,0.000017788865,0.00014885885,0.00018233921,0.00011512155,0.00012719857],"domain_scores_gemma":[0.9994728,0.00003537967,0.000065817025,0.00034989894,0.000054221957,0.000021883008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010859786,0.00007273702,0.00008424521,0.00004149745,0.00003833522,0.000020902144,0.00036513028,0.00003954555,0.000031887244],"category_scores_gemma":[0.00004408197,0.00006383892,0.00004054335,0.00012470216,0.000014580106,0.00028431922,0.00017541672,0.000057880257,0.0000073807505],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053595948,0.0007558826,0.077166244,0.0003341631,0.000138002,0.00009139076,0.021571185,0.000037888803,0.12344177,0.05161332,0.005464518,0.71933204],"study_design_scores_gemma":[0.00014517429,0.00019615439,0.010298338,0.00005463424,0.0000050548088,0.000048908787,0.0000081554235,0.013963524,0.9404588,0.034468625,0.00014795303,0.00020470217],"about_ca_topic_score_codex":0.0015954793,"about_ca_topic_score_gemma":0.000024918585,"teacher_disagreement_score":0.817017,"about_ca_system_score_codex":0.000013017221,"about_ca_system_score_gemma":0.000011002847,"threshold_uncertainty_score":0.26032755},"labels":[],"label_agreement":null},{"id":"W2047291464","doi":"10.1109/issre.2008.57","title":"Discovering&amp;#x0A0;&amp;#x0A0;the Fault Origin from Field Traces","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Fault (geology); Computer science; Field (mathematics); Geology; Seismology; Mathematics","score_opus":0.06807463427558917,"score_gpt":0.29667765318752226,"score_spread":0.22860301891193308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047291464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17528084,0.00020495261,0.8085206,0.002810205,0.0004527411,0.00013533005,0.0000045260194,0.008895063,0.003695736],"genre_scores_gemma":[0.44391245,0.000058822454,0.54917294,0.0021538103,0.00024624693,0.000032250966,0.000007269664,0.00001914233,0.00439707],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983097,0.00007067037,0.00029154998,0.00053327455,0.00040764932,0.0003871634],"domain_scores_gemma":[0.99713993,0.0013136141,0.00009280021,0.0012810627,0.000064624845,0.000107938526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023499907,0.00023926001,0.0002253361,0.000076062875,0.00040050823,0.00022739658,0.0015599851,0.00011022729,0.0001217924],"category_scores_gemma":[0.00048437645,0.00016047653,0.000116985735,0.00038972183,0.00009725639,0.00043402868,0.00034207833,0.00029635723,0.00028239455],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023693696,0.00024053337,0.044318616,0.000017937642,0.00007246937,0.00005831523,0.005749553,0.0001705001,0.0011886583,0.008023668,0.8834531,0.056682993],"study_design_scores_gemma":[0.00076329266,0.00031257636,0.015963832,0.00019847661,0.000036244433,0.0004046722,0.00004085504,0.012733807,0.013042157,0.12372862,0.8309869,0.0017885341],"about_ca_topic_score_codex":0.0043484485,"about_ca_topic_score_gemma":0.00028374392,"teacher_disagreement_score":0.26863158,"about_ca_system_score_codex":0.000033586748,"about_ca_system_score_gemma":0.000079688514,"threshold_uncertainty_score":0.6573582},"labels":[],"label_agreement":null},{"id":"W2048753738","doi":"10.1145/2432497.2432502","title":"Model transformation testing","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Correctness; Computer science; Model transformation; Transformation (genetics); Model-based testing; Software engineering; Integration testing; Key (lock); Programming language; Software; Artificial intelligence; Test case; Machine learning","score_opus":0.09826907079709217,"score_gpt":0.28726679453888104,"score_spread":0.18899772374178886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048753738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029900288,0.000016485947,0.9506406,0.0001503484,0.000044076456,0.000034168075,8.6424635e-8,0.012889289,0.033234905],"genre_scores_gemma":[0.5168532,1.5735874e-7,0.48292446,0.00016914115,0.000012414589,0.0000033284884,1.4342463e-7,0.0000015509335,0.000035573077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995931,0.000008118504,0.00007986427,0.00006354168,0.000089801266,0.00016559399],"domain_scores_gemma":[0.9996378,0.0000916068,0.000017478264,0.00017310937,0.000030922994,0.000049098624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002439003,0.000045422967,0.000037962167,0.00003846466,0.00005736792,0.00003822086,0.00020462822,0.000020484742,0.0000014709401],"category_scores_gemma":[0.00010868327,0.000037815396,0.000013513418,0.00016319916,0.000005835632,0.00074363727,0.00003219717,0.000039924005,0.000026176336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.645695e-7,0.00010436233,0.019832196,0.000022291828,0.0000043072027,5.5357646e-7,0.0039863507,0.0010692838,0.000914841,0.36312354,0.020118468,0.59082294],"study_design_scores_gemma":[0.000026636639,0.000008594934,0.00064806227,0.0000060631564,7.793906e-7,0.000011757644,9.537639e-7,0.9539901,0.001147349,0.043991957,0.000100364814,0.00006740761],"about_ca_topic_score_codex":0.000013781944,"about_ca_topic_score_gemma":1.645815e-7,"teacher_disagreement_score":0.9529208,"about_ca_system_score_codex":0.000011155795,"about_ca_system_score_gemma":0.000012531863,"threshold_uncertainty_score":0.15420672},"labels":[],"label_agreement":null},{"id":"W2049046432","doi":"10.1109/qsic.2007.4385488","title":"Alternative B-Sequences","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Finite-state machine; Computer science; Invertible matrix; Model checking; State (computer science); Algorithm; Automaton; Conformance testing; Theoretical computer science; Programming language; Mathematics","score_opus":0.02940926357054684,"score_gpt":0.3015885118565895,"score_spread":0.2721792482860427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049046432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002542652,0.000021526525,0.94962275,0.00018702076,0.00013454964,0.000026577138,5.5151194e-8,0.009944797,0.037520092],"genre_scores_gemma":[0.56537855,8.6463507e-7,0.4340224,0.00039169996,0.000027107537,9.481922e-7,7.264376e-8,0.0000014018427,0.00017694785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994894,0.00000812531,0.000082346996,0.00014836951,0.00012531379,0.0001464207],"domain_scores_gemma":[0.99945354,0.00021582718,0.000025544185,0.00022197454,0.000040979292,0.00004212234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042340814,0.000047626643,0.000043738542,0.00006162122,0.000044078617,0.000050970608,0.0004904928,0.000017737571,0.000010087048],"category_scores_gemma":[0.00008934182,0.000036954858,0.000017855815,0.00014280943,0.000024335384,0.0001692362,0.0000907415,0.000044279506,0.00005748625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016830269,0.00003557631,0.010825505,0.0000028686552,0.0000072486923,0.00009038109,0.0005152541,0.0000071743475,0.0002675978,0.6118449,0.020674217,0.3557276],"study_design_scores_gemma":[0.00006854496,0.000080269056,0.0034466952,0.000012599386,8.218583e-7,0.000049162078,0.0000039150473,0.01180119,0.03225985,0.94960177,0.0025044312,0.0001707221],"about_ca_topic_score_codex":0.00019971449,"about_ca_topic_score_gemma":0.0000063101643,"teacher_disagreement_score":0.5628359,"about_ca_system_score_codex":0.000014316268,"about_ca_system_score_gemma":0.000013053011,"threshold_uncertainty_score":0.15069753},"labels":[],"label_agreement":null},{"id":"W2050254119","doi":"10.1109/icstw.2013.49","title":"On Adequacy of Assertions in Automated Test Suites: An Empirical Investigation","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Computer science; Oracle; Assertion; Test script; Test (biology); Context (archaeology); Programming language; Unit testing; Test case; Test suite; Source code; Code coverage; Class (philosophy); Empirical research; Keyword-driven testing; Test Management Approach; Test data; Artificial intelligence; Software; Machine learning; Statistics; Mathematics; Software development","score_opus":0.040256608223908114,"score_gpt":0.3265405027542841,"score_spread":0.28628389453037595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050254119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94895977,0.000003478615,0.032134842,0.0011600052,0.000034138888,0.00017318569,5.254011e-7,0.016920483,0.000613585],"genre_scores_gemma":[0.8208869,2.3187188e-7,0.17852128,0.00052397634,0.000005211756,0.000026409769,0.0000027403908,0.000004395716,0.000028872773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992007,0.000062800354,0.0002261546,0.00021452013,0.0001539169,0.00014193456],"domain_scores_gemma":[0.99793744,0.0014232743,0.00005950149,0.0004069808,0.00009735679,0.00007545578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020948293,0.0000802255,0.00010166174,0.00019830902,0.00003286532,0.00006788106,0.00037396452,0.000057757636,0.0000183575],"category_scores_gemma":[0.0021560136,0.00006699626,0.000018544488,0.0005852335,0.000036810747,0.00047224792,0.000057576824,0.00008706601,0.00004451933],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8449065e-7,0.00040753334,0.9337842,0.000013195466,0.0000024495016,0.0000028133386,0.00085314823,0.00007824652,0.0032376046,0.007596234,0.046555627,0.0074680788],"study_design_scores_gemma":[0.00008281386,0.00023861892,0.4967163,0.000045892728,6.817373e-7,0.0000026040343,0.0000036999809,0.433683,0.0036704005,0.0654619,0.000005296802,0.00008880973],"about_ca_topic_score_codex":0.0006436924,"about_ca_topic_score_gemma":0.000023885777,"teacher_disagreement_score":0.4370679,"about_ca_system_score_codex":0.000027965298,"about_ca_system_score_gemma":0.000058364287,"threshold_uncertainty_score":0.27320284},"labels":[],"label_agreement":null},{"id":"W2050254654","doi":"10.1007/s00165-009-0135-6","title":"Lower bounds on lengths of checking sequences","year":2009,"lang":"en","type":"article","venue":"Formal Aspects of Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Theory of computation; Sequence (biology); State (computer science); Model checking; Computer science; Algorithm; Upper and lower bounds; Finite-state machine; Mathematics; Theoretical computer science; Combinatorics","score_opus":0.016043546045305543,"score_gpt":0.2687929526499507,"score_spread":0.2527494066046451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050254654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53676516,0.00010081761,0.427908,0.00026156873,0.00034633288,0.00012198124,7.4991846e-7,0.0034121813,0.031083174],"genre_scores_gemma":[0.87147814,0.0000013609946,0.1282906,0.00015324607,0.00006526981,3.0974556e-7,4.503586e-7,0.0000046236737,0.0000060076027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987211,0.000026005175,0.00036647762,0.00022741365,0.0003427554,0.0003162166],"domain_scores_gemma":[0.9988706,0.00025518014,0.00031350972,0.000389501,0.00012452266,0.000046682388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005171874,0.00013776025,0.0002455193,0.0001594608,0.00011811194,0.000052708132,0.0007533006,0.000052075582,0.0000019690247],"category_scores_gemma":[0.00022372171,0.0001240387,0.00008944876,0.00036777186,0.00005475712,0.00035637652,0.00015431487,0.00015089818,0.0000029211135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029407294,0.00035297766,0.0022435235,0.00009320941,0.000028360542,0.00004509968,0.002394162,0.0026019798,0.0019418902,0.5231649,0.0009593487,0.4661451],"study_design_scores_gemma":[0.00075342157,0.004955353,0.04280179,0.0019308816,0.000016911787,0.00011940702,0.00003473968,0.33312485,0.14750856,0.4676234,0.00028283463,0.00084785966],"about_ca_topic_score_codex":0.000027759208,"about_ca_topic_score_gemma":5.068068e-7,"teacher_disagreement_score":0.46529725,"about_ca_system_score_codex":0.000026599986,"about_ca_system_score_gemma":0.00006354132,"threshold_uncertainty_score":0.5058152},"labels":[],"label_agreement":null},{"id":"W2050316559","doi":"10.1109/cec.2013.6557873","title":"Dynamic white-box software testing using a recursive hybrid evolutionary strategy/genetic algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Larus Technologies (Canada); University of Ottawa","funders":"","keywords":"Computer science; Programmer; Code coverage; Software; White-box testing; Test case; Software development; Programming language; Software engineering; Software construction; Machine learning","score_opus":0.023485224363464535,"score_gpt":0.2549484371156779,"score_spread":0.23146321275221335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050316559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013704844,0.0003026133,0.97212523,0.00013106376,0.00019415343,0.00033292503,0.0000038098603,0.012839327,0.0003660391],"genre_scores_gemma":[0.12434934,0.0000024571991,0.87510854,0.00021897124,0.00004210238,0.000043146192,0.0000039964875,0.000026119236,0.00020535366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979881,0.0000844644,0.0003566051,0.00065511506,0.00035512884,0.0005605825],"domain_scores_gemma":[0.9979712,0.0004644561,0.00015778572,0.0007502629,0.0004826405,0.00017365128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016823046,0.00027728823,0.00022125215,0.00020733204,0.00031022623,0.00032243406,0.00089972455,0.00007902206,0.000048220107],"category_scores_gemma":[0.00057299284,0.00026343422,0.0000716866,0.00068050233,0.000084588355,0.00068361976,0.0003943363,0.00022944056,0.00011743797],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001479912,0.00016004077,0.02124028,0.00005593464,0.000036217196,0.00014623572,0.0001978568,0.00398758,0.00028899073,0.00026467605,0.022545692,0.951075],"study_design_scores_gemma":[0.00010967627,0.00013591589,0.0159098,0.00013731116,0.000008316054,0.00054108916,0.000010540679,0.8670269,0.00009489446,0.11562739,0.000015202317,0.0003829256],"about_ca_topic_score_codex":0.000739916,"about_ca_topic_score_gemma":0.0000017875117,"teacher_disagreement_score":0.9506921,"about_ca_system_score_codex":0.00017714512,"about_ca_system_score_gemma":0.00024135169,"threshold_uncertainty_score":0.99998176},"labels":[],"label_agreement":null},{"id":"W2051066030","doi":"10.1007/s10009-013-0278-x","title":"Innovation and evolution in integrated web application testing with TTCN-3","year":2013,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Integration testing; Software engineering; Vendor; Web service; Web application security; Web application; Test strategy; Unit testing; Model-based testing; Conformance testing; Web development; World Wide Web; Test case; Operating system; Software","score_opus":0.02034142140810467,"score_gpt":0.26195024814189677,"score_spread":0.2416088267337921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051066030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28728825,0.000023152043,0.7079019,0.002240051,0.00009690474,0.0003040054,0.0000045310953,0.002114463,0.000026764821],"genre_scores_gemma":[0.729242,0.0000038481003,0.27020645,0.00027050314,0.000032083135,0.0002157458,0.000007539189,0.000013227642,0.000008574433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987562,0.00002323158,0.00040391946,0.00032835148,0.00027003436,0.00021827861],"domain_scores_gemma":[0.9981099,0.0004030382,0.00009911943,0.00020430992,0.0011485972,0.000035030138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033480418,0.00017018238,0.0001622314,0.0012395149,0.000107801854,0.00030458556,0.0006805933,0.00017840507,0.0000025747645],"category_scores_gemma":[0.0011890047,0.00013977695,0.000025268382,0.001264918,0.0000876419,0.00093221565,0.00004034346,0.00043740362,0.0000073541764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006209778,0.00015505851,0.10506145,0.000011461423,0.000049912374,0.00001915615,0.00006304615,0.00012186384,0.003960522,0.11540728,0.00042866205,0.7746595],"study_design_scores_gemma":[0.0038799797,0.0019064997,0.100175746,0.00093320623,0.00002086167,0.0018483009,0.000055993038,0.07098611,0.005390318,0.8121743,0.0017638719,0.0008647751],"about_ca_topic_score_codex":0.000028843526,"about_ca_topic_score_gemma":0.00000843945,"teacher_disagreement_score":0.7737947,"about_ca_system_score_codex":0.00020708483,"about_ca_system_score_gemma":0.0001171175,"threshold_uncertainty_score":0.56999385},"labels":[],"label_agreement":null},{"id":"W2052416974","doi":"10.1109/qsic.2008.35","title":"Targeting Security Vulnerabilities: From Specification to Detection (Short Paper)","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software security assurance; Security testing; Vulnerability management; Automaton; Vulnerability (computing); Software engineering; Chaining; Software; Computer security; Security information and event management; Information security; Vulnerability assessment; Programming language; Security service; Cloud computing security; Theoretical computer science; Operating system; Cloud computing","score_opus":0.026150733046258593,"score_gpt":0.24967659123988803,"score_spread":0.22352585819362944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052416974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14633882,0.000028580687,0.84132236,0.0002631408,0.00019483345,0.00012456973,0.0000011363926,0.01013526,0.0015913054],"genre_scores_gemma":[0.7517413,0.000006389893,0.24772425,0.0003186286,0.00012338981,0.000024320692,0.0000025293527,0.000006219686,0.000052978772],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989263,0.000058791542,0.00020961261,0.000406918,0.00021361324,0.00018478178],"domain_scores_gemma":[0.99895597,0.00029658174,0.000029106961,0.0005323982,0.00009914114,0.00008681822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026210427,0.00010676953,0.0001069869,0.00007329395,0.00023912414,0.00006472576,0.00040855986,0.000054004646,0.00003432686],"category_scores_gemma":[0.00047092463,0.00010071226,0.00003572116,0.00030370685,0.0000243873,0.00035331928,0.0001249008,0.000116305935,0.0000659288],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006149155,0.0007124855,0.07899755,0.000052565178,0.00006834736,0.00009888456,0.04207504,0.0012149718,0.10560496,0.012525612,0.3173069,0.4412812],"study_design_scores_gemma":[0.0003744933,0.00060375046,0.05572566,0.00010329778,0.000012365178,0.00012085184,0.00021054018,0.27897048,0.2681625,0.3514722,0.042355318,0.0018885579],"about_ca_topic_score_codex":0.000990567,"about_ca_topic_score_gemma":0.000016582164,"teacher_disagreement_score":0.60540247,"about_ca_system_score_codex":0.00006932836,"about_ca_system_score_gemma":0.000023757366,"threshold_uncertainty_score":0.4106927},"labels":[],"label_agreement":null},{"id":"W2053418084","doi":"10.1109/iceccs.2013.32","title":"Merging Test Models","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Computer science; Unified Modeling Language; Test (biology); Model-based testing; Integration testing; Unit testing; Test Management Approach; Test case; Software engineering; Data mining; Programming language; Machine learning; Software; Software development","score_opus":0.02302779249184031,"score_gpt":0.2329466223616793,"score_spread":0.20991882986983898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053418084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094757386,0.000021020942,0.94471365,0.0009985025,0.0000466451,0.00005981697,5.720982e-8,0.018772196,0.034440555],"genre_scores_gemma":[0.52080107,9.167959e-7,0.47830898,0.0003831493,0.000011333067,0.000014675826,9.047276e-8,0.0000029344221,0.0004768417],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994781,0.000007890427,0.000083598265,0.0001699926,0.0001039844,0.00015644655],"domain_scores_gemma":[0.9992461,0.00024548493,0.00001964713,0.00038052132,0.000057004316,0.000051220468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008667657,0.0000611239,0.00005645973,0.000049714534,0.000057109115,0.00015057085,0.00047941486,0.000021900512,0.000036655187],"category_scores_gemma":[0.00012093709,0.000048733906,0.000020548609,0.00016293085,0.000012126646,0.0005702994,0.00015973633,0.00004832175,0.00028742655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3855855e-7,0.00008779276,0.005807247,0.000008511437,0.00000573704,0.00000726114,0.00046033354,0.0002528174,0.00076349184,0.25536937,0.50576854,0.23146874],"study_design_scores_gemma":[0.000020723293,0.000014362955,0.00033165075,0.0000066953335,3.38975e-7,0.0000070393658,7.177171e-7,0.5570823,0.0007178621,0.4415771,0.00017089958,0.00007028917],"about_ca_topic_score_codex":0.00023991971,"about_ca_topic_score_gemma":4.3145874e-7,"teacher_disagreement_score":0.5568295,"about_ca_system_score_codex":0.000009576101,"about_ca_system_score_gemma":0.000013456143,"threshold_uncertainty_score":0.3694383},"labels":[],"label_agreement":null},{"id":"W2053941028","doi":"10.5539/cis.v8n1p25","title":"Best Test Cases Selection Approach Using Genetic Algorithm","year":2015,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequence diagram; Computer science; Test case; Algorithm; Sequence (biology); Unified Modeling Language; Automatic test pattern generation; Graph; Relation (database); Path (computing); Genetic algorithm; Class diagram; Data mining; Theoretical computer science; Programming language; Software; Machine learning","score_opus":0.0559674720454713,"score_gpt":0.28562672178452114,"score_spread":0.22965924973904983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053941028","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054261163,0.00002915343,0.99230796,0.00002567313,0.00020390864,0.00009017502,8.615634e-7,0.0012928293,0.0006233487],"genre_scores_gemma":[0.19107263,0.0000036189554,0.808583,0.0002769696,0.000054279648,0.0000035612918,8.832344e-7,0.0000017184113,0.0000033107501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990082,0.000017966278,0.00020228939,0.00019377594,0.00037160932,0.00020618166],"domain_scores_gemma":[0.99904966,0.000093111914,0.00009047817,0.00021716757,0.00038949997,0.00016006056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067391916,0.00009479281,0.000083777006,0.00030126594,0.0002879504,0.00076682214,0.0004767507,0.000029803425,2.8022578e-7],"category_scores_gemma":[0.00024090441,0.0000842606,0.000013144894,0.0010545927,0.00015857088,0.005971873,0.0003110255,0.00006850085,0.000012151726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.917332e-7,0.0000410259,0.0048567997,0.000014142651,0.0000014494744,0.0000018075641,0.0015683117,0.002795286,0.0000174193,0.0011205472,0.0016267896,0.98795575],"study_design_scores_gemma":[0.000094668954,0.00012765657,0.0023492156,0.000014064727,0.0000016074218,0.00069971214,0.000008210873,0.99474776,0.0001488603,0.0010255635,0.0006615009,0.00012117385],"about_ca_topic_score_codex":0.000064002605,"about_ca_topic_score_gemma":5.8104636e-8,"teacher_disagreement_score":0.9919525,"about_ca_system_score_codex":0.00006211877,"about_ca_system_score_gemma":0.00021798404,"threshold_uncertainty_score":0.73944837},"labels":[],"label_agreement":null},{"id":"W2054446920","doi":"10.1109/icstw.2014.39","title":"Murphy Tools: Utilizing Extracted GUI Models for Industrial Software Testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graphical user interface; Software engineering; Graphical user interface testing; Keyword-driven testing; Process (computing); Model-based testing; Non-regression testing; Software; White-box testing; Manual testing; User interface; Test case; Software development; Software construction; Programming language; Machine learning; User interface design","score_opus":0.2133653832814831,"score_gpt":0.2982011252407428,"score_spread":0.08483574195925972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054446920","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00169875,0.000017470982,0.97047734,0.00018244046,0.00030379486,0.00030578885,0.000002985527,0.023423819,0.0035876126],"genre_scores_gemma":[0.27739748,2.923077e-7,0.7217969,0.00040492296,0.00022003935,0.000060757753,0.000004338633,0.000019293246,0.00009599687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983441,0.00006460961,0.000351811,0.0005361011,0.00025171167,0.00045167064],"domain_scores_gemma":[0.9949849,0.0037288605,0.00014745307,0.0007343436,0.0002830392,0.00012139466],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009296309,0.00020803999,0.00023607942,0.00013695478,0.00026033018,0.0004105239,0.0009665584,0.00016844271,0.000003898685],"category_scores_gemma":[0.009454413,0.00018951637,0.000084761865,0.00046090176,0.00003285946,0.00085258094,0.00027608537,0.00020435225,0.000007848902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006821039,0.000051496656,0.0017930195,0.000019278803,0.000009518398,0.000002153057,0.00012457218,0.0004575882,0.0001370915,0.023230061,0.028416399,0.945752],"study_design_scores_gemma":[0.00043698226,0.00018158233,0.00017747105,0.00010884667,0.000007903076,0.000018618486,0.0000036777685,0.7716656,0.0008424869,0.22340953,0.0028094247,0.0003378754],"about_ca_topic_score_codex":0.00009294223,"about_ca_topic_score_gemma":0.0000021458784,"teacher_disagreement_score":0.9454141,"about_ca_system_score_codex":0.00003804498,"about_ca_system_score_gemma":0.000096596676,"threshold_uncertainty_score":0.9988894},"labels":[],"label_agreement":null},{"id":"W2056339801","doi":"10.1002/j.2334-5837.2002.tb02569.x","title":"1.6.2 Formalizing a Structured Natural Language Requirements Specification Notation","year":2002,"lang":"en","type":"article","venue":"INCOSE International Symposium","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Notation; Computer science; Programming language; B-Method; Formal specification; Formal methods; Readability; Software engineering; Linguistics","score_opus":0.023913972960793797,"score_gpt":0.27798638223217603,"score_spread":0.25407240927138225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056339801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26605168,0.00082130305,0.66013086,0.012393095,0.008652541,0.00078188133,0.00002573337,0.019332724,0.031810172],"genre_scores_gemma":[0.943608,0.000013106332,0.055345252,0.00039364563,0.00022508593,0.000021397931,0.0000236538,0.000010533399,0.00035935847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881613,0.000024214183,0.00025627908,0.00028979857,0.00043845744,0.00017513207],"domain_scores_gemma":[0.9992318,0.00008309859,0.0001542107,0.00033373956,0.00015188585,0.000045276734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015502787,0.00012348473,0.000084191335,0.00012517766,0.00010160117,0.00023630267,0.0008097877,0.00004744345,0.000044446602],"category_scores_gemma":[0.00012875331,0.0001200389,0.00005156115,0.0001907982,0.00002153577,0.00083267095,0.00015654268,0.00012375774,0.000080406106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052771575,0.0005101693,0.01335153,0.000052327283,0.00020178157,0.00021673561,0.019112803,0.0003577751,0.15570427,0.062003843,0.065903306,0.68253267],"study_design_scores_gemma":[0.0011845432,0.00014656041,0.013005964,0.0001931123,0.00001563069,0.0003257711,0.000048351365,0.9041924,0.047419824,0.021116346,0.011520611,0.0008308869],"about_ca_topic_score_codex":0.00006307394,"about_ca_topic_score_gemma":0.0000068192976,"teacher_disagreement_score":0.90383464,"about_ca_system_score_codex":0.00016737168,"about_ca_system_score_gemma":0.0000072198936,"threshold_uncertainty_score":0.48950446},"labels":[],"label_agreement":null},{"id":"W2056488032","doi":"10.1145/1391984.1391985","title":"Unit-level test adequacy criteria for visual dataflow languages and a testing methodology","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Dataflow; Context (archaeology); Unit testing; Visual programming language; Empirical research; Software engineering; Programming language; Software","score_opus":0.3232977272659157,"score_gpt":0.41639520446411027,"score_spread":0.09309747719819456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056488032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015872458,0.0003192727,0.97847074,0.00019784154,0.0002826361,0.00019282413,0.000037394304,0.004624269,0.0000025681354],"genre_scores_gemma":[0.07256598,0.00006208932,0.9268639,0.00023530642,0.000065070795,0.00010875635,0.000007245993,0.000035765403,0.000055890127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830157,0.00029962536,0.00028596737,0.0005947637,0.00010022213,0.00041784812],"domain_scores_gemma":[0.96762776,0.031476114,0.00007014266,0.00056556414,0.00011473251,0.0001456635],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013894971,0.0002790582,0.00043149004,0.00034561526,0.00033066943,0.000044976918,0.00044083624,0.00020029182,0.00000319793],"category_scores_gemma":[0.021633742,0.00027908024,0.000056709545,0.00036425915,0.00011293839,0.00021160909,0.00005969472,0.00032498728,0.0000013028518],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006858348,0.0002459822,0.0048478665,0.0003812986,0.00014504106,0.00010976783,0.0027438134,0.0012956124,0.010267869,0.0008979223,0.000571897,0.9784244],"study_design_scores_gemma":[0.010434689,0.0148896435,0.120083295,0.0015566432,0.00084529497,0.02888515,0.0004930165,0.607833,0.1213767,0.07241214,0.013196362,0.007994033],"about_ca_topic_score_codex":0.00010405933,"about_ca_topic_score_gemma":0.0000032022858,"teacher_disagreement_score":0.9704303,"about_ca_system_score_codex":0.000017754384,"about_ca_system_score_gemma":0.000055964225,"threshold_uncertainty_score":0.99996614},"labels":[],"label_agreement":null},{"id":"W2056640446","doi":"10.1016/j.infsof.2009.06.006","title":"Using machine learning to refine Category-Partition test specifications and test suites","year":2009,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Dependability; Software engineering; Test Management Approach; Partition (number theory); Test (biology); Context (archaeology); Test strategy; Code coverage; Machine learning; Software testing; Test case; Process (computing); Artificial intelligence; Software; Programming language; Software development; Software construction","score_opus":0.03283553674994307,"score_gpt":0.26684519881008295,"score_spread":0.23400966206013987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056640446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14452791,0.00034407515,0.8231632,0.008797954,0.00006917668,0.00034448245,0.000012919839,0.022511033,0.00022925274],"genre_scores_gemma":[0.7041039,0.000038510567,0.29521742,0.0005801812,0.000010580492,0.0000107569085,0.000013117579,0.000003821748,0.000021742522],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99920785,0.000011327215,0.00028758313,0.00018089911,0.00010869543,0.00020363378],"domain_scores_gemma":[0.9988732,0.00049332343,0.00012389333,0.00028992083,0.00014412048,0.00007554843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020330903,0.0001303865,0.00013853736,0.0005783825,0.0002972215,0.00017657553,0.00023978048,0.00012658483,0.0000036291606],"category_scores_gemma":[0.00527978,0.00012809117,0.000013839097,0.00068474666,0.000063289626,0.0008138804,0.00013503236,0.00020146534,0.000020051839],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038690837,0.00007225179,0.32595202,0.000026630938,0.0000046023306,0.0000045397032,0.0010757247,0.000053145155,0.0011220301,0.020883976,0.0015561966,0.649245],"study_design_scores_gemma":[0.0020016201,0.0035746747,0.3942541,0.00047993328,0.000057038684,0.0021745164,0.00026999903,0.18163371,0.014656398,0.3129463,0.08548566,0.0024660842],"about_ca_topic_score_codex":0.000042837437,"about_ca_topic_score_gemma":0.000006054063,"teacher_disagreement_score":0.64677894,"about_ca_system_score_codex":0.000038670878,"about_ca_system_score_gemma":0.000028984392,"threshold_uncertainty_score":0.63207716},"labels":[],"label_agreement":null},{"id":"W2056904432","doi":"10.1109/issre.2014.14","title":"Multi-objective Construction of an Entire Adequate Test Suite for an EFSM","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Test suite; Computer science; Test (biology); Suite; Extended finite-state machine; Test case; Finite-state machine; Code coverage; Model-based testing; Reliability engineering; Algorithm; Machine learning; Programming language; Engineering; Software","score_opus":0.029913801385492645,"score_gpt":0.2933847128231663,"score_spread":0.26347091143767365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056904432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055651825,0.0000044811013,0.93918824,0.000033584158,0.00016362395,0.0001867025,0.0000035049632,0.004458176,0.00030987823],"genre_scores_gemma":[0.47511804,1.8704715e-7,0.52474135,0.000044145923,0.000025096282,0.000016579272,0.0000024382362,0.000005058114,0.000047125646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991959,0.000051235962,0.00016744992,0.00031272296,0.000107167616,0.00016554366],"domain_scores_gemma":[0.998687,0.0004675326,0.000104623585,0.00048303464,0.00018573643,0.00007207125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039209478,0.000097262404,0.00013208947,0.00009073782,0.00008515411,0.00005982293,0.00038770624,0.000054743174,0.0000025457425],"category_scores_gemma":[0.0005420627,0.00008623638,0.000039611026,0.00015143478,0.00006718571,0.0004239129,0.00006215859,0.00005108411,0.000002688875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016004959,0.00051925896,0.03413683,0.000053773492,0.000017690083,0.0000012830615,0.0018486169,0.00002688302,0.006204867,0.043292683,0.001192386,0.91268975],"study_design_scores_gemma":[0.00073366496,0.0020657165,0.018969359,0.000051555224,0.0000130511835,0.000044580604,0.000043196334,0.8581625,0.04771819,0.07163678,0.00020918893,0.00035217308],"about_ca_topic_score_codex":0.00023646657,"about_ca_topic_score_gemma":0.000027195234,"teacher_disagreement_score":0.91233754,"about_ca_system_score_codex":0.000014239396,"about_ca_system_score_gemma":0.000026018606,"threshold_uncertainty_score":0.35166177},"labels":[],"label_agreement":null},{"id":"W2057272331","doi":"10.1109/issrew.2014.9","title":"Trace Reduction and Pattern Analysis to Assist Debugging in Model-Based Testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TRACE (psycholinguistics); Debugging; Computer science; Root cause; Reduction (mathematics); Test (biology); Model-based testing; Test case; Root cause analysis; Software bug; Data mining; Embedded system; Programming language; Reliability engineering; Machine learning; Software; Engineering","score_opus":0.029121904949418385,"score_gpt":0.26932076576125136,"score_spread":0.24019886081183298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057272331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07178576,0.0000081376365,0.92307526,0.0006909949,0.000023168837,0.000060138613,1.893295e-7,0.0039556287,0.00040073047],"genre_scores_gemma":[0.5914255,6.214471e-8,0.40830672,0.00022716307,0.000009977271,0.000009821805,3.5184624e-7,0.0000038893954,0.000016544007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990306,0.000054735225,0.00018026953,0.0003965634,0.00014061441,0.00019723394],"domain_scores_gemma":[0.9991575,0.00028241318,0.000048072063,0.00037254725,0.00005684819,0.000082659724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005943764,0.00010397131,0.00015666826,0.00044542775,0.000080343154,0.00014609186,0.00025446477,0.000037523405,9.740804e-7],"category_scores_gemma":[0.0004488027,0.0000984685,0.000030470632,0.0012775743,0.000014873163,0.00014938993,0.000086233784,0.00008359626,0.000002130616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017184424,0.000043793407,0.1884843,0.000012456813,0.00001519975,0.0000026280707,0.00029089203,0.0990373,0.00037509148,0.00022597278,0.0005554979,0.71095514],"study_design_scores_gemma":[0.00006751685,0.000033317392,0.030740863,0.000027304271,0.000016446043,0.0000037335485,0.0000014076031,0.9640519,0.0005659231,0.0043531647,0.000006333109,0.00013209599],"about_ca_topic_score_codex":0.0006028522,"about_ca_topic_score_gemma":0.00007946396,"teacher_disagreement_score":0.8650146,"about_ca_system_score_codex":0.000036264515,"about_ca_system_score_gemma":0.000024854557,"threshold_uncertainty_score":0.4015429},"labels":[],"label_agreement":null},{"id":"W2058792175","doi":"10.1016/j.artint.2005.09.002","title":"Finding optimal satisficing strategies for and-or trees","year":2005,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Probabilistic logic; Tree (set theory); Set (abstract data type); Node (physics); Computer science; Outcome (game theory); Satisficing; Class (philosophy); Mathematical optimization; Task (project management); Mathematics; Test (biology); Algorithm; Artificial intelligence; Combinatorics; Mathematical economics","score_opus":0.1111722750895888,"score_gpt":0.3551924202138077,"score_spread":0.2440201451242189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058792175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025787469,0.000090979695,0.9704144,0.0006043756,0.00013032567,0.00015299086,0.0000014713897,0.0025850404,0.00023296509],"genre_scores_gemma":[0.5816385,0.000007863377,0.41808605,0.000092564136,0.00010067169,0.000021498321,4.25616e-7,0.000006025655,0.000046373527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989613,0.000021348418,0.000283408,0.00033671598,0.00011914449,0.00027807715],"domain_scores_gemma":[0.9986823,0.00085809437,0.00007423992,0.0002593611,0.000065765926,0.000060216917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003602173,0.00012726043,0.00012899183,0.00009536944,0.00023077491,0.0003140036,0.00039983474,0.0000515634,0.000015239736],"category_scores_gemma":[0.0004386803,0.000109034314,0.00003829261,0.00021281818,0.000072392104,0.0005480224,0.000114427974,0.00008312765,0.000015671827],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015349053,0.000027932278,0.00012007261,0.000010422661,0.0000051156653,0.0000023870089,0.0017797283,0.0014043787,0.0006412611,0.23692097,0.0008986727,0.7581737],"study_design_scores_gemma":[0.00002079747,0.0002795601,0.00011686592,0.0000755281,0.0000066423804,0.000023770408,0.00022962013,0.6461015,0.04040637,0.31114063,0.0013041927,0.00029456543],"about_ca_topic_score_codex":0.00006946571,"about_ca_topic_score_gemma":0.00012590928,"teacher_disagreement_score":0.75787914,"about_ca_system_score_codex":0.00002326712,"about_ca_system_score_gemma":0.000068810645,"threshold_uncertainty_score":0.444629},"labels":[],"label_agreement":null},{"id":"W2059174184","doi":"10.5555/2666527.2666536","title":"Predicting mutation score using source code and test suite metrics","year":2012,"lang":"en","type":"article","venue":"e-scholar@UOIT (University of Ontario Institute of Technology)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Test suite; Mutation; Computer science; Mutation testing; Suite; Source code; Code (set theory); Process (computing); Test case; Machine learning; Programming language; Set (abstract data type); Biology; Genetics","score_opus":0.030706705246584875,"score_gpt":0.22843711999654606,"score_spread":0.1977304147499612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059174184","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91639316,0.00020932312,0.08106014,0.000089542984,0.0001636082,0.00014191502,0.0000063329603,0.0017582563,0.0001777485],"genre_scores_gemma":[0.4395887,0.0000059129457,0.5603221,0.0000114652985,0.000008084519,2.0428553e-7,0.0000023654065,0.000005346419,0.000055856548],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.998915,0.0000062750096,0.00019769906,0.00031820056,0.00025523346,0.00030757222],"domain_scores_gemma":[0.9988204,0.00002391101,0.0003398032,0.0005176164,0.00020403291,0.00009422753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062092993,0.00016259124,0.00028536443,0.00077370554,0.00046730757,0.000035176057,0.0008430405,0.00026072405,0.00000521481],"category_scores_gemma":[0.00095510954,0.0002027689,0.0000618076,0.0012144103,0.00024271678,0.0020214382,0.0007253321,0.00057867257,0.000002634489],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014705988,0.00025332064,0.757162,0.00009717007,0.00007810632,0.00005147479,0.0044877157,0.00010368289,0.0023367691,0.0026777901,0.00024920618,0.23248811],"study_design_scores_gemma":[0.0034735845,0.0012216641,0.41394874,0.0013799161,0.0005223663,0.0012997311,0.00079483894,0.038059194,0.017201375,0.01254428,0.507658,0.0018963084],"about_ca_topic_score_codex":0.008388579,"about_ca_topic_score_gemma":0.0015099768,"teacher_disagreement_score":0.5074088,"about_ca_system_score_codex":0.0003075257,"about_ca_system_score_gemma":0.00023451919,"threshold_uncertainty_score":0.99821466},"labels":[],"label_agreement":null},{"id":"W2059896025","doi":"10.1145/1218563.1218575","title":"Debugging with control-flow breakpoints","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Debugging; Breakpoint; Control flow; Debugger; Programming language; Guard (computer science)","score_opus":0.0070093457028262305,"score_gpt":0.22456384008184785,"score_spread":0.2175544943790216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059896025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013585165,0.000026432048,0.966345,0.00041975934,0.00006488994,0.000077584766,2.4035947e-7,0.019182168,0.012525423],"genre_scores_gemma":[0.517912,2.8550306e-7,0.4810407,0.0008847066,0.000024499084,0.0000024467495,2.2393424e-7,0.0000057017355,0.00012946388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990321,0.000015823429,0.00014083188,0.0002697096,0.00021574109,0.00032579686],"domain_scores_gemma":[0.998951,0.0003575004,0.000046699264,0.00046223198,0.000082994506,0.000099538614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063531025,0.00011215628,0.00011525489,0.000102892205,0.00009656324,0.000101674144,0.00047565904,0.000037645208,0.000010970487],"category_scores_gemma":[0.00009360209,0.00008052145,0.000027423024,0.00028717262,0.000035085865,0.00024019381,0.00007016759,0.00009362146,0.000037058944],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006362377,0.00016171312,0.07670325,0.000020412554,0.000061951294,0.00044109538,0.0005368775,0.00013350305,0.00031117254,0.028271725,0.054210193,0.8390845],"study_design_scores_gemma":[0.0047960137,0.00146753,0.124489754,0.00042966136,0.00005389718,0.0022898559,0.000019888885,0.65431845,0.017252728,0.18156461,0.010941231,0.0023763923],"about_ca_topic_score_codex":0.00008439581,"about_ca_topic_score_gemma":0.00002201387,"teacher_disagreement_score":0.83670807,"about_ca_system_score_codex":0.00002570598,"about_ca_system_score_gemma":0.000037592305,"threshold_uncertainty_score":0.32835695},"labels":[],"label_agreement":null},{"id":"W2060107892","doi":"10.1109/scam.2010.26","title":"How Good is Static Analysis at Finding Concurrency Bugs?","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Concurrency; Interleaving; Static analysis; Thread (computing); Java; Software bug; Debugging; Spurious relationship; Programming language; Software; Operating system; Parallel computing","score_opus":0.023249236838585617,"score_gpt":0.2784057360787849,"score_spread":0.2551564992401993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060107892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06870677,0.000027584734,0.9174176,0.0023516228,0.00027833105,0.00007927556,0.000003962435,0.008472907,0.0026619644],"genre_scores_gemma":[0.700594,0.0000016796319,0.29666603,0.00037425512,0.000022699933,0.000008086159,0.0000024361807,0.0000050032477,0.0023257905],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989271,0.000025449546,0.0001422706,0.00038772394,0.00025090406,0.0002665074],"domain_scores_gemma":[0.9986059,0.00034673818,0.00009199785,0.00077114394,0.00008020372,0.000104005594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026180618,0.00013169016,0.00018634825,0.00024346595,0.0001563419,0.0003514258,0.00072710245,0.00006262909,0.000105820516],"category_scores_gemma":[0.0002745073,0.000109723136,0.00011414134,0.0009835365,0.000040253213,0.00028899836,0.0002965103,0.00017337153,0.00004556717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018866962,0.00015277178,0.565423,0.000043816395,0.00041521585,0.000046350015,0.0028677196,0.000008832299,0.0030169259,0.046378847,0.22208641,0.1595582],"study_design_scores_gemma":[0.0008361877,0.00033142138,0.058022697,0.0000636198,0.0005576126,0.00010957662,0.000034226116,0.6776014,0.051725533,0.1705562,0.03799743,0.002164101],"about_ca_topic_score_codex":0.00007356236,"about_ca_topic_score_gemma":0.000039020615,"teacher_disagreement_score":0.6775926,"about_ca_system_score_codex":0.000023566285,"about_ca_system_score_gemma":0.00003131009,"threshold_uncertainty_score":0.44743797},"labels":[],"label_agreement":null},{"id":"W2061588280","doi":"10.1109/icst.2014.27","title":"Automated Bug Finding in Video Games: A Case Study for Runtime Monitoring","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Video game; Video game development; Game programming; Runtime verification; Process (computing); Game development tool; Instrumentation (computer programming); Game testing; Game Developer; Software; State (computer science); Sample (material); Programming language; Real-time computing; Game design; Formal verification; Human–computer interaction; Game design document; Game art design; Multimedia","score_opus":0.04248516793564986,"score_gpt":0.33574468143082703,"score_spread":0.29325951349517715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061588280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56498104,0.000008848537,0.41208178,0.000050258568,0.00017728057,0.00034284,2.0096613e-7,0.022205343,0.00015241624],"genre_scores_gemma":[0.7362881,1.5644177e-7,0.26347786,0.0000324275,0.000041916715,0.00009705171,1.5388649e-7,0.00000912234,0.000053223514],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989061,0.00006646549,0.00023712181,0.00037179026,0.00013607382,0.00028247046],"domain_scores_gemma":[0.99851006,0.00083572126,0.00005932771,0.00048232032,0.000057840516,0.000054707656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093063986,0.0001280692,0.00017427684,0.00021571803,0.00011853517,0.00017730771,0.00042728224,0.00004407634,0.0000011891406],"category_scores_gemma":[0.00063691684,0.00011505318,0.000034797107,0.00039048828,0.000010571743,0.00022950683,0.00018546343,0.00008452229,0.0000074903064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000129532355,0.0009048015,0.81833255,0.000092741226,0.000043321947,0.0015829236,0.012253124,0.00045520207,0.0003382317,0.0012816997,0.015999703,0.14870274],"study_design_scores_gemma":[0.0008258257,0.0004973945,0.010590856,0.00012665936,0.000007917399,0.00050050445,0.0002104731,0.9805086,0.0010861341,0.00515313,0.00013990424,0.00035259407],"about_ca_topic_score_codex":0.0009766053,"about_ca_topic_score_gemma":0.0000280791,"teacher_disagreement_score":0.9800534,"about_ca_system_score_codex":0.00004749427,"about_ca_system_score_gemma":0.0000233846,"threshold_uncertainty_score":0.46917325},"labels":[],"label_agreement":null},{"id":"W2063462461","doi":"10.4018/jdm.2002040103","title":"Regression Testing of Database Applications","year":2002,"lang":"en","type":"article","venue":"Journal of Database Management","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Regression testing; Data mining; Control flow graph; Test case; Regression analysis; Database; Machine learning; Theoretical computer science; Programming language; Software; Software system","score_opus":0.06318055350265096,"score_gpt":0.2895761658878142,"score_spread":0.22639561238516326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063462461","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077415083,0.0005366437,0.9949226,0.00037084386,0.000112092435,0.00016627241,0.000015896363,0.0005045116,0.002596992],"genre_scores_gemma":[0.057105616,0.00014509782,0.9424118,0.00013601762,0.00007642803,0.00001055089,0.0000051294446,0.000008052825,0.000101327256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998705,0.000047357284,0.00047531057,0.00018368858,0.00043515742,0.00015345887],"domain_scores_gemma":[0.9980589,0.0002413083,0.0005772461,0.0008601351,0.0001777598,0.000084649466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073328684,0.00010648334,0.00017084858,0.00029547978,0.00008306427,0.0000477734,0.000985686,0.000017434199,0.000016433325],"category_scores_gemma":[0.00022729764,0.00008483296,0.000052844636,0.00057934306,0.00003087666,0.0005056872,0.0005964479,0.00014542988,0.000011742321],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010222969,0.0004707386,0.00302183,0.000467534,0.00009513431,0.00039337995,0.00017154269,0.000070804934,0.0018487443,0.014705564,0.35156333,0.6271812],"study_design_scores_gemma":[0.0067233946,0.0023314198,0.007657664,0.01681953,0.000868717,0.0026780467,0.00026451025,0.3801255,0.033576526,0.052748416,0.49332285,0.0028834448],"about_ca_topic_score_codex":0.0000093681365,"about_ca_topic_score_gemma":2.3046076e-7,"teacher_disagreement_score":0.62429774,"about_ca_system_score_codex":0.00003013513,"about_ca_system_score_gemma":0.000010868291,"threshold_uncertainty_score":0.34593877},"labels":[],"label_agreement":null},{"id":"W2065604113","doi":"10.1109/mra.2008.931632","title":"The robotics experience","year":2009,"lang":"en","type":"article","venue":"IEEE Robotics & Automation Magazine","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Reuse; Robotics; Reusability; Software engineering; Variety (cybernetics); Artificial intelligence; Software; Computer science; Robot; Systems engineering; Engineering; Programming language","score_opus":0.021030628607017297,"score_gpt":0.282433840506703,"score_spread":0.2614032118996857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065604113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006196929,0.00010043584,0.9809029,0.0061636,0.0006407844,0.00015002619,3.615179e-7,0.0103354575,0.0010867022],"genre_scores_gemma":[0.37126228,0.000029066747,0.62728727,0.0007955332,0.00011050127,0.000010081023,0.0000017517169,0.000010243972,0.00049329206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852914,0.000065324486,0.00034909314,0.00030247908,0.00040461076,0.00034936034],"domain_scores_gemma":[0.9982924,0.00035447188,0.00016553658,0.0009101967,0.00018642785,0.00009098759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037500143,0.00017439516,0.00014470861,0.00008267525,0.00040922826,0.00044006092,0.001066338,0.000070578535,0.0000017365875],"category_scores_gemma":[0.00033480066,0.00013304412,0.00005881102,0.0005386824,0.00006931248,0.0004017864,0.000069667854,0.00013577042,0.00012470556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008286749,0.00023846295,0.00093872455,0.000018727416,0.00002068898,0.000051783696,0.0018750234,0.19257145,0.0028105201,0.22107564,0.19259773,0.38779297],"study_design_scores_gemma":[0.00015135409,0.00015040216,0.0082668355,0.00004218832,0.0000067364813,0.000059434347,0.0000029673624,0.90546817,0.0008731634,0.08267014,0.0020269912,0.00028160095],"about_ca_topic_score_codex":0.0000023832638,"about_ca_topic_score_gemma":0.0000020701336,"teacher_disagreement_score":0.71289676,"about_ca_system_score_codex":0.0000587402,"about_ca_system_score_gemma":0.000056429348,"threshold_uncertainty_score":0.54253817},"labels":[],"label_agreement":null},{"id":"W2067531935","doi":"10.1093/comjnl/bxu113","title":"Generalizing the DS-Methods for Testing Non-Deterministic FSMs","year":2014,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Algorithm","score_opus":0.05822499298085235,"score_gpt":0.35446574423089033,"score_spread":0.296240751250038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067531935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011575375,0.00007553258,0.993701,0.002036701,0.0013553458,0.0001607457,2.5074084e-7,0.0012994973,0.00021341968],"genre_scores_gemma":[0.064040124,0.0000022490676,0.9315552,0.002589398,0.0017407093,0.000017365006,2.1840134e-7,0.000018667253,0.00003607463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998337,0.0004673583,0.0003470237,0.00024988438,0.00019148728,0.00040725264],"domain_scores_gemma":[0.9934655,0.005198368,0.0002770156,0.0007531141,0.00021213558,0.00009386552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004638011,0.00018010805,0.00019654159,0.000071633796,0.0011917893,0.00086464075,0.0023377503,0.00004426617,9.61778e-7],"category_scores_gemma":[0.00084967015,0.00009567254,0.00012776595,0.00026320756,0.000084194995,0.000163366,0.00047160444,0.00039315305,0.0000064154037],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002152241,0.0000130244125,0.00022642319,0.000007971212,0.000014602111,0.000003413731,0.0005431917,0.0006589123,0.00020540359,0.0024763234,0.017290289,0.9785583],"study_design_scores_gemma":[0.00015546888,0.00018524697,0.0008372962,0.000065983186,0.000012554028,0.0010382258,0.0000012913957,0.82441354,0.00016526484,0.1679507,0.0050343582,0.0001400748],"about_ca_topic_score_codex":0.000008082893,"about_ca_topic_score_gemma":2.2817812e-7,"teacher_disagreement_score":0.97841823,"about_ca_system_score_codex":0.000030678282,"about_ca_system_score_gemma":0.00006605202,"threshold_uncertainty_score":0.91664004},"labels":[],"label_agreement":null},{"id":"W2067617772","doi":"10.1109/tse.2014.2363479","title":"Instance Generator and Problem Representation to Improve Object Oriented Code Coverage","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Unit testing; Test case; Programming language; Code generation; Java; Code coverage; Object-oriented programming; Data structure; Source code; Generator (circuit theory); Software; Theoretical computer science; Machine learning; Operating system","score_opus":0.009565537506992744,"score_gpt":0.23054314654182123,"score_spread":0.2209776090348285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067617772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024144053,0.000017257884,0.96735996,0.00005623537,0.0005070698,0.0002449994,0.0000110331075,0.007642321,0.000017067829],"genre_scores_gemma":[0.53380543,0.000005414764,0.46584773,0.00014819813,0.00003208351,0.00009117211,7.8061214e-7,0.000020468338,0.000048717662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882424,0.000028907625,0.00020842793,0.00047642,0.00020889666,0.0002531047],"domain_scores_gemma":[0.99895775,0.00029487888,0.000042151107,0.0004843687,0.00007982164,0.00014103063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019314296,0.00018834759,0.00016935474,0.00020368828,0.00014349018,0.000117417105,0.0002299115,0.000067884415,0.0000018263295],"category_scores_gemma":[0.00013412094,0.00020027194,0.00004380495,0.0004937935,0.000012320539,0.0002990924,0.000006658844,0.00019181718,0.000009034404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051242852,0.00022132411,0.0011168185,0.00023028751,0.00009319634,0.000024637071,0.002454906,0.461641,0.018405197,0.0023935335,0.0021465577,0.5112213],"study_design_scores_gemma":[0.0012472892,0.00089105853,0.0014700135,0.00045890428,0.000036352583,0.00008067838,0.000006343374,0.7613114,0.22578558,0.0015115336,0.005852932,0.001347887],"about_ca_topic_score_codex":0.000030665855,"about_ca_topic_score_gemma":0.000005638365,"teacher_disagreement_score":0.5098734,"about_ca_system_score_codex":0.00007021408,"about_ca_system_score_gemma":0.000024712033,"threshold_uncertainty_score":0.8166853},"labels":[],"label_agreement":null},{"id":"W2068493323","doi":"10.1109/tse.2011.56","title":"Size-Constrained Regression Test Case Selection Using Multicriteria Optimization","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Test suite; Test case; Consistency (knowledge bases); Integer programming; Mathematical optimization; Task (project management); Constraint (computer-aided design); Selection (genetic algorithm); Regression testing; Greedy algorithm; Linear programming; Relaxation (psychology); Software; Algorithm; Machine learning; Regression analysis; Artificial intelligence; Software system; Mathematics","score_opus":0.03160363037280706,"score_gpt":0.24695615889016168,"score_spread":0.21535252851735462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068493323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008772391,0.000013017612,0.97777337,0.000006441926,0.0006293928,0.00017567996,0.000007164491,0.012611083,0.000011433218],"genre_scores_gemma":[0.47693112,0.0000019771935,0.52297336,0.000018370474,0.000020831112,0.000018585568,3.6842223e-7,0.000023399038,0.000011983837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987847,0.0000319489,0.000284816,0.00041317128,0.00017195058,0.00031336525],"domain_scores_gemma":[0.99875385,0.00053765066,0.00007838665,0.00038398162,0.00012326697,0.00012289127],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017895587,0.00026364284,0.00018399053,0.00027797977,0.00028029582,0.00009091815,0.00024455853,0.00014069844,0.000042911688],"category_scores_gemma":[0.00029236235,0.0002701113,0.00008852467,0.00061409833,0.000025765688,0.0005289317,0.0000046913055,0.00027736643,0.000005808294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021218713,0.00038791355,0.00037448507,0.0000918373,0.00004832125,0.00060217676,0.0015802417,0.9626136,0.0044101663,0.000047313144,0.00009243377,0.029730335],"study_design_scores_gemma":[0.00023875688,0.00012507578,0.00004332029,0.0001878856,0.00002243677,0.0022464849,0.0000058530536,0.9663855,0.03037051,0.00004205878,0.000008099157,0.00032406126],"about_ca_topic_score_codex":0.00016322042,"about_ca_topic_score_gemma":0.0000033906201,"teacher_disagreement_score":0.46815872,"about_ca_system_score_codex":0.0001245864,"about_ca_system_score_gemma":0.000046923647,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W2069169007","doi":"10.1109/wse.2012.6320526","title":"Visual testing of Graphical User Interfaces: An exploratory study towards systematic definitions and approaches","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical user interface; Computer science; Graphical user interface testing; Human–computer interaction; User interface; Visualization; User interface design; User experience design; Artificial intelligence; Programming language","score_opus":0.22841786623247345,"score_gpt":0.31590808405690346,"score_spread":0.08749021782443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069169007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7430254,0.00012355746,0.2528411,0.00001376105,0.000053861102,0.0003097733,4.7561792e-7,0.0033370794,0.00029501514],"genre_scores_gemma":[0.8066491,5.722494e-7,0.19322819,0.000025500656,0.000014844261,0.00007119106,3.3586596e-7,0.000007464254,0.0000028183526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988186,0.0002400862,0.00031082708,0.0002242077,0.00020577162,0.0002005128],"domain_scores_gemma":[0.99878734,0.0005256124,0.000104719955,0.0003880198,0.00007884497,0.00011543745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011150889,0.00012808283,0.00025212584,0.00015097814,0.000092276925,0.00008799516,0.00033349448,0.000042802087,9.501285e-7],"category_scores_gemma":[0.00062895793,0.00009745264,0.000022259077,0.00038487324,0.00006683467,0.00067867455,0.00027569282,0.00009609408,0.0000020977538],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010091173,0.006564292,0.858505,0.0064849593,0.00017912821,0.000011681753,0.05858422,0.000012736424,0.00036482906,0.056062996,0.0005518432,0.012668226],"study_design_scores_gemma":[0.0036591562,0.016514832,0.3847062,0.015574373,0.0009044004,0.0010397297,0.04844786,0.37266442,0.019578673,0.13145341,0.0000122775355,0.005444674],"about_ca_topic_score_codex":0.00004106555,"about_ca_topic_score_gemma":0.00000546065,"teacher_disagreement_score":0.4737988,"about_ca_system_score_codex":0.000009972296,"about_ca_system_score_gemma":0.00003029435,"threshold_uncertainty_score":0.39740035},"labels":[],"label_agreement":null},{"id":"W2070233995","doi":"10.1145/2678022","title":"Dynamically Instrumenting the QEMU Emulator for Linux Process Trace Generation with the GDB Debugger","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Debugging; TRACE (psycholinguistics); Emulation; Tracing; Operating system; Process (computing); Debugger; Software; Embedded system","score_opus":0.020906165101975738,"score_gpt":0.2672740377382368,"score_spread":0.2463678726362611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070233995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060997456,0.00003434237,0.932567,0.0014320848,0.00053210196,0.00080591295,0.0000023877092,0.0035516077,0.00007712915],"genre_scores_gemma":[0.8943601,6.386631e-7,0.104803875,0.000323701,0.00024311138,0.00017484928,0.0000026044715,0.00003274532,0.000058376703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979584,0.00024800512,0.00040081266,0.00055582385,0.00042861816,0.00040833437],"domain_scores_gemma":[0.9964846,0.0015885979,0.00027540885,0.0013034733,0.00028039422,0.00006754541],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012529808,0.00026691917,0.00024413413,0.000096158816,0.0013505416,0.00062370376,0.0015345514,0.00010049383,6.373817e-7],"category_scores_gemma":[0.00018815213,0.00015493602,0.00009210161,0.0004986538,0.000075588636,0.00021032384,0.000022490549,0.00033096515,0.00000543093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006471374,0.0003326173,0.00027453373,0.00032475527,0.000260861,0.0000032947316,0.0115747,0.5596043,0.00082796806,0.007440759,0.0020769932,0.4172145],"study_design_scores_gemma":[0.00029477084,0.0002526981,0.00004741562,0.00017557024,0.000033991866,0.00008217721,0.000105017665,0.9965221,0.00067715714,0.0012027586,0.00036459006,0.00024174697],"about_ca_topic_score_codex":0.000040839142,"about_ca_topic_score_gemma":0.0000123899135,"teacher_disagreement_score":0.83336264,"about_ca_system_score_codex":0.000065876135,"about_ca_system_score_gemma":0.000076492484,"threshold_uncertainty_score":0.9999496},"labels":[],"label_agreement":null},{"id":"W2070633450","doi":"10.1109/icstw.2013.31","title":"A Method and Tool for Test Optimization for Automotive Controllers","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Automotive industry; Computer science; Test (biology); Automotive engineering; Control engineering; Engineering; Aerospace engineering","score_opus":0.014788650045673982,"score_gpt":0.28235754149414083,"score_spread":0.26756889144846685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070633450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059757636,0.000012015014,0.9933546,0.0014455632,0.000034695986,0.00090313476,0.000002515085,0.003997344,0.00019034118],"genre_scores_gemma":[0.017079044,9.566951e-7,0.981253,0.0008082902,0.000020331885,0.0005413719,0.0000016706142,0.0000066169537,0.00028869105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994772,0.000015191129,0.00010807997,0.0002133688,0.000048022048,0.00013813272],"domain_scores_gemma":[0.99689674,0.0026225855,0.000045498182,0.00015479466,0.000246474,0.00003387484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029680628,0.000072653136,0.000108585744,0.000048112866,0.00008853515,0.00015869293,0.00015880728,0.000037010952,0.0000058234255],"category_scores_gemma":[0.0014608419,0.000058041755,0.000031621556,0.00007575765,0.000013692648,0.00024910472,0.0000459076,0.000020643749,0.0000012311074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016707441,0.0001375497,0.0020509455,0.0000819013,0.0000467194,5.1000484e-7,0.0007063246,0.006338987,0.0002763659,0.03232501,0.26589358,0.6921254],"study_design_scores_gemma":[0.00042698934,0.00017546308,0.00019480631,0.0000080071495,0.0000042981396,0.000003170015,0.0000019434062,0.93361455,0.00043624142,0.064814724,0.00023325217,0.00008654683],"about_ca_topic_score_codex":0.00003140739,"about_ca_topic_score_gemma":3.5241297e-7,"teacher_disagreement_score":0.9272756,"about_ca_system_score_codex":0.000012108842,"about_ca_system_score_gemma":0.000021547441,"threshold_uncertainty_score":0.2366874},"labels":[],"label_agreement":null},{"id":"W2070655751","doi":"10.5555/2819261.2819271","title":"Adaptive random testing by static partitioning","year":2015,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Random testing; Computer science; Overhead (engineering); Point (geometry); Algorithm; Test case; Parallel computing; Distributed computing; Theoretical computer science; Mathematics; Machine learning","score_opus":0.048154716995931886,"score_gpt":0.2663096841822027,"score_spread":0.2181549671862708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070655751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006728416,0.00008558531,0.979495,0.00018272159,0.00009604895,0.00017080456,0.000014994932,0.012831916,0.00039449445],"genre_scores_gemma":[0.49479833,5.633654e-7,0.50502175,0.00009594282,0.000013618531,0.000024960833,0.000008416875,0.000008259076,0.000028158442],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867666,0.000072979834,0.00038356625,0.00026431662,0.0003874543,0.00021500417],"domain_scores_gemma":[0.99588925,0.002790833,0.00031962886,0.00038011442,0.0004993175,0.000120870136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00065711583,0.00014282674,0.00021133694,0.00011300206,0.00009994061,0.00008868914,0.00042600144,0.000055209443,0.0000047869844],"category_scores_gemma":[0.011002823,0.00014113967,0.000036146717,0.0005713544,0.00005607488,0.0005828453,0.000119239085,0.00009659076,0.000045470424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029786579,0.00069501466,0.17230287,0.00017325433,0.00006564439,0.000033014658,0.0050921305,0.0039793504,0.0007130522,0.0032615354,0.48422804,0.3294263],"study_design_scores_gemma":[0.002573427,0.0011964224,0.010068237,0.0007063831,0.00003430478,0.00008410301,0.000058914753,0.7818929,0.0058482476,0.19608495,0.0007038122,0.00074832194],"about_ca_topic_score_codex":0.000082765706,"about_ca_topic_score_gemma":0.0000013017727,"teacher_disagreement_score":0.7779135,"about_ca_system_score_codex":0.00006522544,"about_ca_system_score_gemma":0.00013158402,"threshold_uncertainty_score":0.9973279},"labels":[],"label_agreement":null},{"id":"W2070960202","doi":"10.1109/cec.2010.5586002","title":"A binary Particle Swarm Optimization approach to fault diagnosis in parallel and distributed systems","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Particle swarm optimization; Heuristic; Set (abstract data type); Task (project management); Binary number; Fault (geology); Identification (biology); Distributed computing; Algorithm; Artificial intelligence; Mathematics; Engineering","score_opus":0.02110450445621641,"score_gpt":0.2508811779073411,"score_spread":0.22977667345112468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070960202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09671174,0.000030017929,0.8994405,0.0004318289,0.00007867392,0.00023283862,0.0000018197621,0.0028799714,0.00019258501],"genre_scores_gemma":[0.580318,0.000003325316,0.41942415,0.00007457138,0.00000975785,0.00015000727,0.000003057131,0.0000037343,0.0000134233105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917275,0.00003667033,0.00016462815,0.00030722967,0.00012006571,0.00019863085],"domain_scores_gemma":[0.9993087,0.00016224882,0.000031376945,0.00034313928,0.000046017245,0.00010850505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028666292,0.00009343142,0.00011663088,0.00007128252,0.000058246424,0.00018261567,0.00029486313,0.000059569553,0.0000010212513],"category_scores_gemma":[0.00026818053,0.00008025966,0.000013061505,0.00046839204,0.000021095302,0.00020855854,0.00018209757,0.00010622645,0.000003071431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011712416,0.00062191585,0.22509412,0.00005533138,0.000009179732,0.000019180608,0.0010722838,0.7279997,0.00018910723,0.021826943,0.016199896,0.0069006174],"study_design_scores_gemma":[0.00013800868,0.000048552833,0.005939756,0.000016803215,0.0000014477686,0.0000139136555,0.000009572805,0.9929955,0.000112638285,0.0005159787,0.00008231318,0.00012553154],"about_ca_topic_score_codex":0.00037558484,"about_ca_topic_score_gemma":0.000007889577,"teacher_disagreement_score":0.48360625,"about_ca_system_score_codex":0.000014661174,"about_ca_system_score_gemma":0.000015381514,"threshold_uncertainty_score":0.3272894},"labels":[],"label_agreement":null},{"id":"W2072069604","doi":"10.1109/saner.2015.7081820","title":"JCHARMING: A bug reproduction approach using crash traces and directed model checking","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Crash; Java; Computer science; Field (mathematics); Software; Code (set theory); Model checking; Source code; Software bug; Software engineering; Data science; Programming language; Set (abstract data type)","score_opus":0.15163872696120653,"score_gpt":0.3069914423862612,"score_spread":0.15535271542505466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072069604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10372071,0.0001561386,0.88201016,0.00013443726,0.00007905313,0.00009127733,1.5445667e-7,0.01235467,0.0014533714],"genre_scores_gemma":[0.4516247,0.0000020039024,0.54816747,0.000037199177,0.00003817605,0.000004827146,4.1448095e-7,0.0000062578138,0.0001189853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989183,0.000047433045,0.00014871443,0.0005110594,0.00019367048,0.00018082705],"domain_scores_gemma":[0.9992285,0.000047295427,0.00006784598,0.00044482105,0.00011752786,0.000094048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008671645,0.00011352561,0.0001280412,0.000108055516,0.0001056091,0.00017302785,0.00024177595,0.000051558647,2.877943e-7],"category_scores_gemma":[0.00047893685,0.00010054906,0.000019596533,0.00030714268,0.000035074452,0.0004438126,0.00017808199,0.000094064475,7.840291e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084599094,0.0015781135,0.08084831,0.0004352545,0.00017574626,0.00007120564,0.049294543,0.080140136,0.036188506,0.028583122,0.07982877,0.6427717],"study_design_scores_gemma":[0.00008964096,0.00001747774,0.0001267745,0.000017141114,0.000004955878,0.00010191913,0.0000151253225,0.9772209,0.0021890544,0.02002571,0.000047833633,0.00014347318],"about_ca_topic_score_codex":0.00012858094,"about_ca_topic_score_gemma":6.6205695e-7,"teacher_disagreement_score":0.8970808,"about_ca_system_score_codex":0.000037405993,"about_ca_system_score_gemma":0.000060818307,"threshold_uncertainty_score":0.41002718},"labels":[],"label_agreement":null},{"id":"W2072077040","doi":"","title":"JST: An Automatic Test Generation Tool for Industrial Java Applications with Strings","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Java; Symbolic execution; Scalability; Suite; String (physics); Programming language; Test suite; Pathfinder; Key (lock); Software engineering; Test case; Database; Operating system; Software; Machine learning","score_opus":0.04805541970660984,"score_gpt":0.26503095846209584,"score_spread":0.216975538755486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072077040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021874875,0.000002496436,0.9683537,0.0003734964,0.000030362153,0.00096599164,0.0000015673552,0.00816392,0.00023363208],"genre_scores_gemma":[0.40533295,1.7147313e-7,0.5931918,0.00019739631,0.00014528053,0.000973599,0.000009153548,0.000007471878,0.0001422031],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926656,0.000014021301,0.00016189582,0.00026817812,0.00012881623,0.00016052886],"domain_scores_gemma":[0.99896497,0.00028065988,0.00006941686,0.0004808417,0.00014518443,0.000058931506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017136353,0.00009556222,0.00008892968,0.00006434404,0.000150728,0.00034487143,0.0003927757,0.000059014714,0.000014526892],"category_scores_gemma":[0.00016084136,0.00007307837,0.00001800809,0.00022183737,0.000020197245,0.00057539466,0.000047001016,0.000059946964,0.000024165862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.13833e-7,0.00020787866,0.009787986,0.000015408883,0.0000101936785,4.371672e-7,0.00021526411,0.000054190677,0.0014371547,0.012058633,0.08554961,0.89066243],"study_design_scores_gemma":[0.00051611103,0.00057250605,0.0018463242,0.000021816883,0.000010002196,0.000018627989,0.0000054490147,0.97557545,0.0048188074,0.014820105,0.0014800119,0.0003148171],"about_ca_topic_score_codex":0.0001364352,"about_ca_topic_score_gemma":0.0000050299936,"teacher_disagreement_score":0.9755212,"about_ca_system_score_codex":0.000025765466,"about_ca_system_score_gemma":0.00007936802,"threshold_uncertainty_score":0.33256033},"labels":[],"label_agreement":null},{"id":"W2073900130","doi":"10.5555/2133429.2133588","title":"Engineering a scalable Boolean matching based on EDA SaaS 2.0","year":2010,"lang":"en","type":"article","venue":"International Conference on Computer Aided Design","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Software as a service; Computer science; Scalability; Cloud computing; Overhead (engineering); Software; Distributed computing; Algorithm; Software development; Operating system","score_opus":0.04149444232221811,"score_gpt":0.2732101998238203,"score_spread":0.23171575750160217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073900130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021667585,0.000001198054,0.98734915,0.001447698,0.0017779954,0.00016169122,0.000002523319,0.0044653597,0.002627633],"genre_scores_gemma":[0.51693153,4.5848267e-7,0.481685,0.0011057197,0.00018063444,0.000021304813,0.0000032364064,0.000014007247,0.000058069883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981832,0.00008466617,0.00027881353,0.0005833713,0.0005658675,0.00030410357],"domain_scores_gemma":[0.99785024,0.0010085957,0.00010966313,0.00067146687,0.00022900898,0.00013099646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071303354,0.0002619029,0.00018907187,0.00036669662,0.00010498249,0.00064225576,0.0016318297,0.00010042769,0.00007617463],"category_scores_gemma":[0.00021869756,0.00025323572,0.0000812818,0.00018328585,0.000029267598,0.00030163402,0.00018117401,0.0005403485,0.00017821814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001706216,0.00064103154,0.0006492666,0.00003425415,0.00009489511,0.00027756614,0.0005270977,0.122139595,0.010358043,0.6393322,0.04237861,0.18339686],"study_design_scores_gemma":[0.00027275638,0.00020326424,0.0005232149,0.00018622428,0.0000020806758,0.000023302327,4.7650803e-7,0.9628312,0.0031573265,0.031997744,0.0005234107,0.00027900268],"about_ca_topic_score_codex":0.000043813474,"about_ca_topic_score_gemma":0.0000015886723,"teacher_disagreement_score":0.8406916,"about_ca_system_score_codex":0.000061447034,"about_ca_system_score_gemma":0.00013588699,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W2074184938","doi":"10.5539/cis.v4n2p17","title":"Necessities and Tactics of Tool-Based Software Testing","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Software engineering; System integration testing; Key (lock); Software; Test strategy; Set (abstract data type); Resource (disambiguation); Software development; Acceptance testing; Software construction; Computer security; Operating system; Programming language","score_opus":0.04193299607930647,"score_gpt":0.2424153438950541,"score_spread":0.2004823478157476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074184938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050872847,0.00001535254,0.9473555,0.000024308749,0.00009517558,0.000048829435,8.508549e-7,0.00095473364,0.0006323679],"genre_scores_gemma":[0.5025353,0.0000015436827,0.49719766,0.00025778793,0.0000048472775,0.0000013247563,2.0940531e-7,7.5562406e-7,5.740241e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930716,0.00001027238,0.00021125432,0.0001223545,0.00021433269,0.00013465527],"domain_scores_gemma":[0.9991002,0.00020201628,0.00013102828,0.00022478506,0.00028822705,0.000053757078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050613703,0.00007190627,0.00008589894,0.00022279173,0.00018632102,0.00022181372,0.00039807125,0.000021807937,7.445568e-7],"category_scores_gemma":[0.00034663867,0.00006176531,0.000009398769,0.0005368296,0.00029603974,0.0049012825,0.0002813164,0.00005053843,0.0000012955128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034780155,0.000017664559,0.074989,0.00011493026,0.0000021279427,0.0000010211536,0.007195674,0.000062619096,0.000047535705,0.020358443,0.00037797773,0.89682955],"study_design_scores_gemma":[0.00023185347,0.00033947823,0.18928187,0.00014620672,0.000003523936,0.000052855827,0.000019411746,0.7900061,0.003644173,0.015747167,0.00026914378,0.00025824623],"about_ca_topic_score_codex":0.000021878803,"about_ca_topic_score_gemma":6.161996e-8,"teacher_disagreement_score":0.8965713,"about_ca_system_score_codex":0.000008453916,"about_ca_system_score_gemma":0.00010957897,"threshold_uncertainty_score":0.35533115},"labels":[],"label_agreement":null},{"id":"W2074487274","doi":"10.5555/2819009.2819250","title":"8th international workshop on search-based software testing (SBST 2015)","year":2015,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Oracle; Software engineering; Search-based software engineering; Computer science; Software testing; Software; Construct (python library); Test (biology); Service (business); Set (abstract data type); Software construction; Software development; Systems engineering; Engineering; Programming language","score_opus":0.11723149425156179,"score_gpt":0.32581176964823766,"score_spread":0.20858027539667587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074487274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033639353,0.000025010364,0.980075,0.0016341724,0.0024471502,0.0001596698,0.000024280227,0.0105752,0.0016955534],"genre_scores_gemma":[0.5345514,0.0000026842483,0.46421114,0.00057416304,0.00029422037,0.000049111528,0.000037707923,0.000040115465,0.00023945088],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971674,0.000045612876,0.00038794344,0.00070308655,0.0012450152,0.00045096257],"domain_scores_gemma":[0.9968213,0.0011125187,0.00013249964,0.0006618861,0.0009725229,0.00029929267],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000571895,0.00037367397,0.00024118385,0.00058198796,0.000090826434,0.0005467151,0.0021897266,0.00014122072,0.000044945893],"category_scores_gemma":[0.008270281,0.0003812521,0.000097009775,0.00043214925,0.000050023125,0.0004654969,0.00036171908,0.0005836655,0.00018297337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026062442,0.00096460024,0.051642798,0.00009383663,0.00034225706,0.00074520364,0.0016328694,0.42428663,0.00038661927,0.1061187,0.06521382,0.34831202],"study_design_scores_gemma":[0.00093500677,0.00030359652,0.0030143037,0.001259267,0.000007066578,0.000054010623,0.000021514603,0.98231375,0.0012049172,0.0051291254,0.004892759,0.00086467434],"about_ca_topic_score_codex":0.00004675233,"about_ca_topic_score_gemma":0.0000017467443,"teacher_disagreement_score":0.55802715,"about_ca_system_score_codex":0.00040059106,"about_ca_system_score_gemma":0.000319483,"threshold_uncertainty_score":0.9998639},"labels":[],"label_agreement":null},{"id":"W2077772687","doi":"10.1016/s0950-5849(03)00060-0","title":"UIO sequence based checking sequences for distributed test architectures","year":2003,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Observability; Controllability; Sequence (biology); Sequence diagram; Synchronization (alternating current); Computer science; Current (fluid); Control theory (sociology); Real-time computing; Engineering; Mathematics; Software; Channel (broadcasting); Artificial intelligence; Unified Modeling Language; Computer network; Control (management); Programming language; Electrical engineering","score_opus":0.01946076082708154,"score_gpt":0.2629249510792006,"score_spread":0.24346419025211907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077772687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007574371,0.000076593285,0.97811425,0.0009843468,0.000080962454,0.00026591268,0.000031071257,0.012778049,0.00009445843],"genre_scores_gemma":[0.55582,0.0000032648627,0.44354957,0.0005083829,0.0000043606888,0.00008945494,0.000017692659,0.000004004496,0.0000033006881],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904364,0.000019458843,0.0003046303,0.00020243057,0.00013548158,0.00029432614],"domain_scores_gemma":[0.9986497,0.00055241503,0.00016809492,0.000389336,0.00018355185,0.000056915407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034215915,0.00016030855,0.00016576349,0.00038726896,0.00025773043,0.00016126758,0.0004742065,0.00018316995,0.0000030912302],"category_scores_gemma":[0.005421684,0.00014445548,0.0000377257,0.00057678827,0.00016448574,0.00039420868,0.00007343089,0.00016676083,0.0000052053215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001133148,0.00007518017,0.13315919,0.00025336634,0.000023181547,0.000008074395,0.00072941947,0.00055584573,0.00024681946,0.11886619,0.005041874,0.7410295],"study_design_scores_gemma":[0.0014226763,0.0007231121,0.0033173636,0.0002362307,0.000019009109,0.0004464941,0.000069314505,0.091309614,0.021675969,0.8250959,0.054642756,0.0010415846],"about_ca_topic_score_codex":0.00001232153,"about_ca_topic_score_gemma":0.000002887707,"teacher_disagreement_score":0.73998797,"about_ca_system_score_codex":0.000042326385,"about_ca_system_score_gemma":0.00013078957,"threshold_uncertainty_score":0.6490654},"labels":[],"label_agreement":null},{"id":"W2080458911","doi":"10.1109/pst.2010.5593250","title":"A model-driven penetration test framework for Web applications","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Web application; Software engineering; Web application security; Security testing; Web service; World Wide Web; Web development; Security information and event management; Operating system; Cloud computing security; Cloud computing","score_opus":0.029238329952034868,"score_gpt":0.3038530720129196,"score_spread":0.27461474206088476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080458911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045061618,0.0000034005934,0.988757,0.00079502835,0.0000543982,0.00030970847,0.000003281633,0.008226914,0.0013996647],"genre_scores_gemma":[0.39146444,5.341566e-7,0.6078754,0.00024087164,0.000049727096,0.00028502932,0.0000019727954,0.0000044304898,0.00007758169],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994463,0.0000035347869,0.00010452362,0.00022970111,0.000087193264,0.00012878233],"domain_scores_gemma":[0.9986652,0.00062247104,0.000041054347,0.00051799463,0.00010363353,0.00004961164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011975249,0.00006828109,0.00005879485,0.00004827201,0.00012828989,0.000117070085,0.0004974714,0.00008293163,0.0000040941345],"category_scores_gemma":[0.0003616622,0.0000615043,0.000032362645,0.0001697253,0.000020240823,0.00014922873,0.000060672275,0.0001280179,0.000016409744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.156163e-7,0.000069820235,0.0019646233,0.000006836282,0.0000018028202,1.1392748e-7,0.00006886102,0.00011568868,0.0057428833,0.9460958,0.012662743,0.033270285],"study_design_scores_gemma":[0.000026606433,0.000018739773,0.00012475238,0.000003787797,0.0000012328396,0.0000020404602,2.3308945e-7,0.5716879,0.0005817507,0.42624986,0.0012430457,0.0000600778],"about_ca_topic_score_codex":0.0000055505498,"about_ca_topic_score_gemma":0.000013977188,"teacher_disagreement_score":0.5715722,"about_ca_system_score_codex":0.000007028395,"about_ca_system_score_gemma":0.00006649341,"threshold_uncertainty_score":0.2508073},"labels":[],"label_agreement":null},{"id":"W2080670657","doi":"10.1002/spe.686","title":"Fast dynamic casting","year":2005,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Pointer (user interface); C dynamic memory allocation; Computer science; Modulo; Integer (computer science); Class (philosophy); Arithmetic; Predictability; Base (topology); Theoretical computer science; Algorithm; Programming language; Discrete mathematics; Mathematics; Artificial intelligence; Memory management","score_opus":0.014209689347191417,"score_gpt":0.3035970456289335,"score_spread":0.2893873562817421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080670657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023003666,0.00090257335,0.96448547,0.002380903,0.0001585829,0.00009926632,7.912826e-7,0.008092841,0.00087591546],"genre_scores_gemma":[0.42559633,0.000047304227,0.5729795,0.0012319234,0.000030235105,0.000023325296,4.776761e-7,0.0000076066644,0.00008327434],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987239,0.000054413027,0.00019613086,0.00046036002,0.00024396842,0.00032118565],"domain_scores_gemma":[0.99825287,0.0008951948,0.00012608174,0.00048798288,0.00011646864,0.00012139888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031490394,0.00015455525,0.00012591743,0.00007335934,0.00030580134,0.00029114893,0.00050692406,0.00005918745,0.000007156672],"category_scores_gemma":[0.0031519441,0.00014785375,0.000027330523,0.0002923659,0.00008780063,0.0022586915,0.00033679538,0.00019306428,0.000044759636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000085995725,0.00007497487,0.0022991307,0.00001375225,0.000007234756,0.00005889454,0.016151395,0.000036514553,0.00013999447,0.0013038552,0.0016754,0.97823024],"study_design_scores_gemma":[0.0021490778,0.0014218672,0.011166472,0.00090816064,0.00010588053,0.013144076,0.0058412207,0.4373109,0.0060328543,0.038634446,0.47810918,0.005175861],"about_ca_topic_score_codex":0.000079259924,"about_ca_topic_score_gemma":0.000005359047,"teacher_disagreement_score":0.9730544,"about_ca_system_score_codex":0.000041973057,"about_ca_system_score_gemma":0.000048691934,"threshold_uncertainty_score":0.60293007},"labels":[],"label_agreement":null},{"id":"W2080932040","doi":"10.1145/1356058.1356065","title":"Near-optimal instruction selection on dags","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute of Steel Construction; National Science Foundation","keywords":"Computer science; Selection (genetic algorithm); Directed acyclic graph; Key (lock); Decomposition; Code (set theory); Tree (set theory); Theoretical computer science; Parallel computing; Algorithm; Mathematics; Programming language; Artificial intelligence","score_opus":0.025523420680057217,"score_gpt":0.24694817995428955,"score_spread":0.22142475927423233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080932040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32229006,0.0000029895853,0.6583006,0.00016971843,0.0001557585,0.000042830077,7.04094e-8,0.0143312095,0.0047068093],"genre_scores_gemma":[0.6035106,0.0000014898446,0.3959848,0.0002032281,0.00003295025,0.000003997415,3.2846182e-7,0.000003361248,0.00025921615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994106,0.000019602956,0.000085167165,0.00020934487,0.0001484663,0.00012681902],"domain_scores_gemma":[0.99962765,0.000051367453,0.00002914498,0.00020989384,0.00004517958,0.000036766323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007896304,0.00006961775,0.00005777141,0.000061430255,0.00023932938,0.000055070985,0.00020131304,0.000040851748,0.0000105683075],"category_scores_gemma":[0.00006833212,0.00006148364,0.000024367564,0.00029403155,0.000030912935,0.00021953892,0.000044886056,0.00009345179,0.00007058889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044474524,0.00036206885,0.11326446,0.000016049291,0.0000286441,0.00006784355,0.0019149017,0.0035106693,0.00074573525,0.075892724,0.3258882,0.47826424],"study_design_scores_gemma":[0.00069971697,0.0013285126,0.09224669,0.00004448515,0.000004477263,0.0019876184,0.0000035777537,0.8368698,0.026034871,0.026986182,0.01310462,0.00068945717],"about_ca_topic_score_codex":0.00010207849,"about_ca_topic_score_gemma":0.0000012046938,"teacher_disagreement_score":0.8333591,"about_ca_system_score_codex":0.000032787713,"about_ca_system_score_gemma":0.000044849345,"threshold_uncertainty_score":0.250723},"labels":[],"label_agreement":null},{"id":"W2083965123","doi":"10.1007/s10009-012-0240-3","title":"Model-based testing of software and systems: recent advances and challenges","year":2012,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Software testing; Variety (cybernetics); System integration testing; Software engineering; Automation; Software; Test strategy; Model-based testing; Software performance testing; Software system; Data science; Software construction; Test case; Artificial intelligence; Machine learning; Programming language; Engineering","score_opus":0.09062809914528827,"score_gpt":0.30661703236558707,"score_spread":0.2159889332202988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083965123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015925284,0.021135302,0.95802116,0.0019279114,0.00051650306,0.00020069162,0.000025644296,0.0022286186,0.000018888351],"genre_scores_gemma":[0.5096116,0.0033023262,0.48675454,0.00017333624,0.00007412962,0.000057835783,0.0000019837685,0.000020130792,0.0000040794457],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864644,0.00003330564,0.00039844197,0.000277717,0.0003347118,0.00030939138],"domain_scores_gemma":[0.99767107,0.0012473523,0.00012716666,0.00022888933,0.0006240807,0.00010144336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005585232,0.00020001209,0.00027397892,0.00047802704,0.00012692536,0.00012118292,0.0006612934,0.00018621207,9.31975e-7],"category_scores_gemma":[0.0023903053,0.0001740273,0.000054509088,0.00016487882,0.00014624157,0.00076057663,0.00007102409,0.00028310396,5.955527e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045131434,0.00012596481,0.012044927,0.00012902147,0.0000572957,0.000007597847,0.00013104093,0.00054878334,0.000067086636,0.013220399,0.00009431379,0.97352844],"study_design_scores_gemma":[0.011618991,0.0075732335,0.012909871,0.008920372,0.00033588693,0.007205257,0.00032415424,0.19262375,0.025611538,0.5747255,0.15410574,0.004045667],"about_ca_topic_score_codex":0.0000010342901,"about_ca_topic_score_gemma":5.3752467e-7,"teacher_disagreement_score":0.9694828,"about_ca_system_score_codex":0.000058862694,"about_ca_system_score_gemma":0.00006848658,"threshold_uncertainty_score":0.70966274},"labels":[],"label_agreement":null},{"id":"W2084172672","doi":"10.1016/j.tcs.2011.07.010","title":"Hardness results for covering arrays avoiding forbidden edges and error-locating arrays","year":2011,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Division of Electrical, Communications and Cyber Systems; Natural Sciences and Engineering Research Council of Canada","keywords":"Clique; Enhanced Data Rates for GSM Evolution; Binary number; Reduction (mathematics); Time complexity; Combinatorics; Hardness of approximation; Computer science; Computational complexity theory; Discrete mathematics; Mathematics; Algorithm; Approximation algorithm; Arithmetic; Artificial intelligence; Geometry","score_opus":0.057304972214434674,"score_gpt":0.28066317984675326,"score_spread":0.2233582076323186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084172672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012648468,0.000025485417,0.98053837,0.00021648966,0.00060760207,0.00025685073,0.0000028576003,0.0031106656,0.0025932314],"genre_scores_gemma":[0.54021364,0.0000013511635,0.45953727,0.00014554139,0.000074204276,0.000015484731,3.8128812e-7,0.000008065183,0.000004071187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975154,0.00008285043,0.00036500473,0.0009466435,0.0004040432,0.0006860742],"domain_scores_gemma":[0.997595,0.0009511621,0.00013413878,0.0008164158,0.00024402032,0.00025925622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032768645,0.0002338792,0.00026173855,0.00019364944,0.0009276317,0.00046922732,0.0019225944,0.00006722584,0.000001494829],"category_scores_gemma":[0.0013765176,0.00020356388,0.00005868465,0.0006305939,0.0014646889,0.000752718,0.0010715373,0.00022316653,0.000006126857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027981214,0.000042119398,0.00023654538,0.000036667338,0.000005408736,0.000005393442,0.004804315,0.00003107609,0.0005412711,0.92807895,0.000467568,0.06572269],"study_design_scores_gemma":[0.00029148386,0.00029909826,0.0005169009,0.00016194311,0.000006266848,0.00006068854,0.000015375364,0.43688023,0.017732369,0.5436458,0.000052420633,0.00033744468],"about_ca_topic_score_codex":0.000016487224,"about_ca_topic_score_gemma":5.209479e-7,"teacher_disagreement_score":0.5275652,"about_ca_system_score_codex":0.0000472435,"about_ca_system_score_gemma":0.00009833453,"threshold_uncertainty_score":0.83010936},"labels":[],"label_agreement":null},{"id":"W2084669353","doi":"10.1109/icpc.2013.6613851","title":"Towards generating human-oriented summaries of unit test cases","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Unit testing; Computer science; Java; USable; Test (biology); Code coverage; Code (set theory); Programming language; Test case; Unit (ring theory); Software engineering; Software; Machine learning; World Wide Web; Set (abstract data type)","score_opus":0.042413954737019616,"score_gpt":0.2900342707541397,"score_spread":0.24762031601712006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084669353","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.402135,0.00009024206,0.5782651,0.00040860396,0.00014821778,0.0002539707,0.0000041552626,0.010633729,0.008060975],"genre_scores_gemma":[0.62761873,8.814672e-7,0.3718886,0.00014139366,0.00002425291,0.000016002434,0.0000020133016,0.0000050873946,0.00030303432],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991774,0.000028223089,0.00022877609,0.00020536623,0.000176106,0.00018412636],"domain_scores_gemma":[0.9986647,0.00047554352,0.00008457093,0.0004595634,0.00026066983,0.00005496203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001572472,0.000106028354,0.00013721842,0.000089016336,0.00014037527,0.000117015836,0.00043734343,0.000040249877,0.00004880143],"category_scores_gemma":[0.0010103667,0.00008636786,0.000034694513,0.0003044374,0.000069233174,0.00021982791,0.00025973012,0.00006873007,0.000014104721],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017443258,0.000489869,0.40987387,0.00012688154,0.0000437907,0.00006792142,0.0018038993,0.0000562584,0.03491134,0.17359945,0.18055359,0.19847138],"study_design_scores_gemma":[0.0011435644,0.0025569994,0.09926183,0.0005442048,0.000040692743,0.00039646646,0.00022082929,0.25827456,0.4470607,0.18132506,0.006956384,0.0022187342],"about_ca_topic_score_codex":0.0034465694,"about_ca_topic_score_gemma":0.000028620307,"teacher_disagreement_score":0.41214934,"about_ca_system_score_codex":0.000010623977,"about_ca_system_score_gemma":0.0000472563,"threshold_uncertainty_score":0.52102053},"labels":[],"label_agreement":null},{"id":"W2086037832","doi":"10.1016/j.cor.2007.01.013","title":"Detecting buffer overflow via automatic test input data generation","year":2007,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Buffer overflow; Computer science; Genetic programming; Process (computing); Fitness function; Software; Genetic algorithm; Buffer (optical fiber); Function (biology); Data mining; Real-time computing; Distributed computing; Machine learning; Operating system","score_opus":0.17966519198828013,"score_gpt":0.4136846375907641,"score_spread":0.234019445602484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086037832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028420288,0.00007881373,0.9657669,0.0007174872,0.0003824014,0.00037872043,0.0000037103737,0.0040482683,0.00020339571],"genre_scores_gemma":[0.55082756,0.0000031002555,0.44857517,0.0001729568,0.0003003392,0.000016747876,0.000029994972,0.000014314298,0.000059814185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970186,0.00025599505,0.00043268804,0.00081666565,0.00083046587,0.0006456027],"domain_scores_gemma":[0.9949343,0.0017824684,0.000035213267,0.002481441,0.00057914807,0.00018739168],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0051965467,0.0001763982,0.00017322024,0.0005898966,0.0011472633,0.0011333573,0.0026093868,0.00010526315,0.000011516322],"category_scores_gemma":[0.0024338271,0.0001720594,0.00003440187,0.0014736905,0.000111081376,0.0010623002,0.0018890138,0.0005280934,0.00011140687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015750436,0.00023572412,0.0035319496,0.00003343914,0.000025390746,0.00007727247,0.0012263006,0.0030405773,0.008337192,0.0010922153,0.049898706,0.93249965],"study_design_scores_gemma":[0.0001423921,0.00013564194,0.0020354954,0.000052139134,0.0000025549712,0.00006990004,0.0000053972985,0.9924894,0.0038758,0.00049553334,0.00049901224,0.00019671474],"about_ca_topic_score_codex":0.00032433204,"about_ca_topic_score_gemma":0.00018086887,"teacher_disagreement_score":0.98944885,"about_ca_system_score_codex":0.00017838612,"about_ca_system_score_gemma":0.00023773512,"threshold_uncertainty_score":0.99990356},"labels":[],"label_agreement":null},{"id":"W2086038725","doi":"10.1134/s0361768812040019","title":"FSM-based testing from user defined faults adapted to incremental and mutation testing","year":2012,"lang":"en","type":"article","venue":"Programming and Computer Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test suite; Computer science; Model-based testing; Finite-state machine; Code coverage; Test case; Suite; Fault coverage; Polynomial; State (computer science); Algorithm; Programming language; Mathematics; Software; Engineering; Machine learning","score_opus":0.039164504726991324,"score_gpt":0.25790353807168404,"score_spread":0.21873903334469272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086038725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3114452,0.00019284362,0.6815521,0.00008141699,0.00014236267,0.00023235961,0.0000033441029,0.0063453014,0.0000050638873],"genre_scores_gemma":[0.4788651,1.644604e-7,0.5206428,0.00032521746,0.00010176246,0.000037487516,0.000011255088,0.000014617616,0.0000016159579],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998237,0.00008311273,0.00029621762,0.00056545576,0.00027688476,0.0005413401],"domain_scores_gemma":[0.9974799,0.0015628472,0.00013186467,0.00035107203,0.00016224211,0.0003120355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042708305,0.00028154053,0.0002474615,0.0001585183,0.00035285874,0.00044424113,0.00032908664,0.00008792753,6.505135e-7],"category_scores_gemma":[0.0007748026,0.00027656055,0.00003081955,0.00057354657,0.00003849099,0.00043140427,0.00048235926,0.00017408433,0.000005498847],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000373745,0.000045166045,0.42354092,0.00002220707,0.000008190947,0.000007893522,0.00039755684,0.000023640103,0.000015516256,0.00004862366,0.00012212088,0.5757644],"study_design_scores_gemma":[0.0013429879,0.0010731956,0.70842963,0.0010703154,0.000064134285,0.00021587382,0.000028699369,0.28106114,0.00066967105,0.0030647153,0.0015201183,0.0014595073],"about_ca_topic_score_codex":0.0009424877,"about_ca_topic_score_gemma":0.000006364786,"teacher_disagreement_score":0.57430494,"about_ca_system_score_codex":0.00004283746,"about_ca_system_score_gemma":0.00003227327,"threshold_uncertainty_score":0.99996865},"labels":[],"label_agreement":null},{"id":"W2087097337","doi":"10.1145/1022494.1022539","title":"Relevant empirical testing research","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Software testing; Empirical research; Test strategy; Computer science; Software engineering; Position paper; Software; Software performance testing; Data science; Systems engineering; Engineering; Software construction; Software development; World Wide Web","score_opus":0.1418802265110641,"score_gpt":0.360298768827243,"score_spread":0.21841854231617888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087097337","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15230559,0.00053855294,0.79554826,0.001910319,0.00051349704,0.00031047757,0.000004104388,0.048850533,0.000018646959],"genre_scores_gemma":[0.49734947,0.0000034963239,0.5023221,0.00012197934,0.000119189775,0.000037319423,0.0000021520068,0.00003607828,0.000008232168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970318,0.00006156751,0.0003917247,0.00077718706,0.0007835544,0.0009541708],"domain_scores_gemma":[0.8677852,0.12860273,0.000097956065,0.002560145,0.00059264194,0.0003613456],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013226438,0.00032311023,0.00029742796,0.0004658513,0.0003392611,0.00030246263,0.0023422907,0.00019106784,0.0000037073492],"category_scores_gemma":[0.51872,0.00031856616,0.00009311486,0.0018811274,0.00008217432,0.0004452992,0.0012515525,0.000834657,0.00013110669],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013071227,0.00040856103,0.8555233,0.00034841645,0.0000669108,0.00075452816,0.0027053463,0.0096657025,0.004745583,0.007222175,0.011528017,0.107018374],"study_design_scores_gemma":[0.0029240693,0.002456382,0.7017004,0.004303725,0.000055580553,0.0018212112,0.000021284271,0.0108635565,0.06381981,0.19436197,0.012284757,0.0053872527],"about_ca_topic_score_codex":0.00016810138,"about_ca_topic_score_gemma":0.0000019027215,"teacher_disagreement_score":0.51739734,"about_ca_system_score_codex":0.0002358331,"about_ca_system_score_gemma":0.00024799487,"threshold_uncertainty_score":0.9999266},"labels":[],"label_agreement":null},{"id":"W2088296131","doi":"10.1016/j.scico.2006.04.009","title":"Special issue on Source code analysis and manipulation","year":2006,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Program slicing; Source code; Slicing; Program comprehension; Transformation (genetics); Static program analysis; Code (set theory); Program transformation; Restructuring; Programming language; Program analysis; Software engineering; World Wide Web; Software; Software development; Software system; Set (abstract data type)","score_opus":0.014948064418239062,"score_gpt":0.265467116510335,"score_spread":0.25051905209209596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088296131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040561743,0.000009774971,0.9568263,0.00014592064,0.00024094772,0.00011306893,2.7479575e-7,0.0015030336,0.0005989281],"genre_scores_gemma":[0.45201424,3.3065803e-7,0.54711086,0.000033833967,0.0008025526,0.0000029469677,8.52695e-7,0.0000032761584,0.000031089286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851066,0.000026926738,0.000231555,0.00046611024,0.0004865219,0.00027821216],"domain_scores_gemma":[0.99914664,0.000111270965,0.00014464106,0.0004083185,0.00012844824,0.00006070488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007058124,0.00011374084,0.00017713563,0.0005840203,0.00022338972,0.00036081523,0.0006777714,0.000031817173,0.0000020960147],"category_scores_gemma":[0.000036812664,0.00010496189,0.000056102755,0.0022305471,0.00028205005,0.00036675148,0.00026551777,0.00007193615,0.0000033202027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018327553,0.000056830366,0.016396184,0.000008137984,0.000008607466,0.0000026484552,0.00022662016,0.0019542915,0.000057270307,0.0057285484,0.0011149319,0.9744441],"study_design_scores_gemma":[0.00020166673,0.00037169657,0.12957343,0.00006909992,0.000042589036,0.00001806546,0.000004767428,0.8399377,0.0028128966,0.015139233,0.011456067,0.00037282906],"about_ca_topic_score_codex":0.00015291365,"about_ca_topic_score_gemma":0.000010751222,"teacher_disagreement_score":0.97407126,"about_ca_system_score_codex":0.00002962879,"about_ca_system_score_gemma":0.000036764264,"threshold_uncertainty_score":0.42802218},"labels":[],"label_agreement":null},{"id":"W2088946319","doi":"10.1145/1984642.1984645","title":"Branching and merging","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Branching (polymer chemistry); Computer science; Software; Branching process; Software engineering; Data science; Programming language; Mathematics","score_opus":0.038325349564623884,"score_gpt":0.23013589781330276,"score_spread":0.19181054824867888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088946319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009424168,0.00004959551,0.9550169,0.00006547414,0.000048450784,0.00001866189,1.9643949e-8,0.009177932,0.026198788],"genre_scores_gemma":[0.51068395,0.0000013213445,0.48909947,0.00016326891,0.0000047934086,9.970797e-7,1.4641017e-8,0.0000014337536,0.00004473153],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996923,0.000008943104,0.00004830894,0.00012193299,0.000043736727,0.00008476977],"domain_scores_gemma":[0.99972767,0.00004599154,0.000013019751,0.00017282384,0.000010484474,0.000030041487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012392855,0.000038256407,0.000038774488,0.000036581594,0.000051474944,0.00003492672,0.00017881046,0.000012851609,0.0000064700243],"category_scores_gemma":[0.00004527684,0.000031469433,0.0000083450805,0.00007165797,0.000012039247,0.00017491516,0.00011939629,0.000034375855,0.0000056704466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013590899,0.000030369423,0.051355086,0.000012287319,0.000007647194,0.00002292745,0.0051635737,3.40028e-7,0.00023278562,0.2839252,0.008510732,0.6507377],"study_design_scores_gemma":[0.00017206377,0.00009899363,0.042586558,0.000058375776,0.000003723662,0.00014099381,0.000010180823,0.068146914,0.0072984165,0.88004154,0.0010624743,0.00037975673],"about_ca_topic_score_codex":0.000117638585,"about_ca_topic_score_gemma":0.0000010939875,"teacher_disagreement_score":0.6503579,"about_ca_system_score_codex":0.0000023562397,"about_ca_system_score_gemma":0.000004726188,"threshold_uncertainty_score":0.12832862},"labels":[],"label_agreement":null},{"id":"W2090566883","doi":"10.1109/icsm.2010.5609695","title":"Exploring the impact of context sensitivity on blended analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"Computer science; Scalability; Context (archaeology); Pruning; Call graph; Source code; Sensitivity (control systems); Empirical research; Context model; Object (grammar); Theoretical computer science; Data mining; Artificial intelligence; Database; Programming language; Mathematics; Engineering","score_opus":0.07496066508202304,"score_gpt":0.3072169454212202,"score_spread":0.23225628033919715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090566883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7421521,0.0000015779741,0.2535165,0.0002765174,0.00007544913,0.000046901478,8.67779e-7,0.0023557567,0.0015743378],"genre_scores_gemma":[0.9747624,7.145512e-7,0.02510473,0.00008188099,0.000018358149,0.0000053220415,2.8852438e-7,0.0000029001062,0.00002343648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993878,0.000059256166,0.00010791712,0.00017372037,0.0001436751,0.00012760752],"domain_scores_gemma":[0.99820733,0.0008632542,0.0000585258,0.0007566445,0.00007653558,0.000037708924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005903221,0.00007947071,0.00014249077,0.00013552139,0.00006402056,0.000046410634,0.00030384725,0.000018675215,0.0000084045405],"category_scores_gemma":[0.00034359406,0.00004343438,0.00017926485,0.0006457743,0.00003975249,0.00015850816,0.00009702063,0.00015426321,0.0000063850075],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025485824,0.0003519878,0.15164123,0.000007804079,0.00087310903,0.00003426476,0.0021880113,0.0019801378,0.01341767,0.06487376,0.010266144,0.7543404],"study_design_scores_gemma":[0.00012775668,0.00022792873,0.5880566,0.000013871905,0.000056495937,0.000018251418,0.000011930066,0.36240727,0.039212827,0.009604275,0.00003182661,0.00023092792],"about_ca_topic_score_codex":0.0019226157,"about_ca_topic_score_gemma":0.00009800144,"teacher_disagreement_score":0.75410944,"about_ca_system_score_codex":0.000010575599,"about_ca_system_score_gemma":0.000032582426,"threshold_uncertainty_score":0.29064324},"labels":[],"label_agreement":null},{"id":"W2092198121","doi":"10.1016/j.jss.2012.12.051","title":"A survey of software testing practices in Canada","year":2013,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Software testing; Test (biology); Survey research; Software; Engineering; Computer science; Psychology; Applied psychology","score_opus":0.06050471719038154,"score_gpt":0.2706308278705806,"score_spread":0.2101261106801991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092198121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8908774,0.004114165,0.10374411,0.00011324136,0.00056736736,0.00022550958,0.0000075114935,0.00032917256,0.000021472822],"genre_scores_gemma":[0.89343446,0.000014851549,0.10646033,0.000037919068,0.00002966103,0.0000042667175,3.215849e-7,0.000007731529,0.000010420393],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983648,0.00019483667,0.0007088761,0.00015215616,0.00038332868,0.00019599636],"domain_scores_gemma":[0.9939373,0.0030753973,0.0016663029,0.00025473326,0.0009500952,0.00011617618],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001349842,0.000119747856,0.00039296382,0.00015785698,0.00004843632,0.00012927523,0.0004773212,0.000050042217,0.000002033711],"category_scores_gemma":[0.011380147,0.00009395617,0.00002471042,0.00043036934,0.000021838621,0.00060353015,0.00010855293,0.00021841167,6.81901e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020517903,0.000016464259,0.9744677,0.00011091585,0.000010804043,0.000038958857,0.00012843606,0.00010269352,0.000009777504,0.000008198695,0.0035610497,0.021542976],"study_design_scores_gemma":[0.0002262893,0.00015549226,0.99142605,0.0009114385,0.0000052974806,0.0004271615,0.000059873244,0.0058586965,0.000017202237,0.0006879078,0.00007059934,0.00015398863],"about_ca_topic_score_codex":0.9302604,"about_ca_topic_score_gemma":0.16541986,"teacher_disagreement_score":0.7648406,"about_ca_system_score_codex":0.000119110395,"about_ca_system_score_gemma":0.0011645784,"threshold_uncertainty_score":0.9969474},"labels":[],"label_agreement":null},{"id":"W2092245922","doi":"10.1016/j.infsof.2013.03.004","title":"Graphical user interface (GUI) testing: Systematic mapping and repository","year":2013,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":167,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Graphical user interface testing; Graphical user interface; Computer science; User interface; Software; Interface (matter); Information retrieval; Data mining; Software engineering; User interface design; Programming language; Operating system","score_opus":0.010876144624941233,"score_gpt":0.21512095863092082,"score_spread":0.20424481400597957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092245922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065847084,0.0003449679,0.9139868,0.0008685787,0.00012195069,0.00045646413,4.2184672e-7,0.018120209,0.00025351855],"genre_scores_gemma":[0.70046353,0.000008577076,0.29907918,0.00030054603,0.0000062343156,0.0001091135,6.821765e-7,0.0000049181785,0.00002724103],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899876,0.0000311173,0.0004463728,0.00018128591,0.0001333508,0.0002091277],"domain_scores_gemma":[0.99873865,0.00034295948,0.00019974109,0.00043104935,0.00021823937,0.00006938627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023170197,0.00014579535,0.00022348033,0.0005060312,0.00019230128,0.000322007,0.0003902412,0.00019854895,0.0000013285687],"category_scores_gemma":[0.0017338372,0.00012434777,0.000018771125,0.00054588274,0.00014742544,0.0011831297,0.00038768735,0.00021321164,0.000025984165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006374947,0.00010813912,0.405191,0.014178619,0.0001347352,0.00003192841,0.006435069,0.000017889997,0.0006026089,0.079835124,0.021987423,0.47147107],"study_design_scores_gemma":[0.0023638592,0.0014069148,0.10106883,0.014757302,0.00008532058,0.009974144,0.0012597187,0.22585,0.003659748,0.6306054,0.0057212645,0.0032474818],"about_ca_topic_score_codex":0.000049827322,"about_ca_topic_score_gemma":4.3823565e-7,"teacher_disagreement_score":0.63461643,"about_ca_system_score_codex":0.000020451964,"about_ca_system_score_gemma":0.00002397969,"threshold_uncertainty_score":0.5070755},"labels":[],"label_agreement":null},{"id":"W2095773889","doi":"10.1109/icsme.2014.85","title":"A Web Service Test Generator","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The King's University","funders":"","keywords":"Computer science; Web service; XML; XML validation; Programming language; Information retrieval; Database; Generator (circuit theory); Efficient XML Interchange; World Wide Web","score_opus":0.01603739895257633,"score_gpt":0.23558729255487795,"score_spread":0.21954989360230162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095773889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055431393,0.00001343043,0.9513044,0.0025290085,0.00012519668,0.00004608606,3.5776677e-7,0.025395619,0.015042796],"genre_scores_gemma":[0.4661404,5.4741207e-7,0.52793086,0.005584388,0.00007057289,0.000007789091,3.2239768e-7,0.0000049932623,0.00026010603],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942124,0.000021743075,0.00008674462,0.00020851982,0.000113248585,0.00014850027],"domain_scores_gemma":[0.99899614,0.00031986128,0.000024520865,0.00051763176,0.000079149926,0.000062708496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022041236,0.00007246398,0.00006961078,0.000043015876,0.000063988045,0.00011019969,0.0005894665,0.000031301803,0.000011911212],"category_scores_gemma":[0.00033889624,0.00005914228,0.000017963486,0.0002910236,0.00000769783,0.00012321949,0.00016965451,0.00005092163,0.00019772109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010440026,0.00017450626,0.039197613,0.000036893616,0.000008193875,0.00000950112,0.00030288345,0.000021542392,0.006751805,0.09377753,0.68206733,0.17765114],"study_design_scores_gemma":[0.00018320957,0.00011393187,0.002085691,0.00002291815,0.000002403043,0.000037013695,6.4836894e-7,0.8896612,0.006264069,0.048322022,0.05302027,0.0002866206],"about_ca_topic_score_codex":0.000055439777,"about_ca_topic_score_gemma":0.00001271928,"teacher_disagreement_score":0.8896397,"about_ca_system_score_codex":0.0000087312765,"about_ca_system_score_gemma":0.00003144001,"threshold_uncertainty_score":0.25413707},"labels":[],"label_agreement":null},{"id":"W2095794856","doi":"10.1007/978-1-4471-0719-4_32","title":"On Built-in-Test Classes for Object-Oriented and Component-Based Information Systems","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Testability; Class (philosophy); Object-oriented programming; Software; Software construction; Software development; Component-based software engineering; Programming language; Computer architecture; Software engineering; Engineering; Reliability engineering","score_opus":0.021670964125821573,"score_gpt":0.24998184568840734,"score_spread":0.22831088156258578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095794856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005112726,0.000118188196,0.82384396,0.00016094721,0.0004009465,0.00092309463,0.000027405917,0.0068162903,0.16765808],"genre_scores_gemma":[0.32224438,0.00023519497,0.5504221,0.00629535,0.0005808537,0.0009558136,0.0010054946,0.000283874,0.117976986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987182,0.000011690346,0.00042982402,0.00032932768,0.00028053523,0.00023042106],"domain_scores_gemma":[0.99739474,0.0015690699,0.00024384788,0.0005508056,0.00016815407,0.00007339427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027535995,0.00029231238,0.00033328176,0.000484295,0.00009374069,0.00023503159,0.0003730603,0.0002328439,0.0000030709755],"category_scores_gemma":[0.00029052098,0.00026363658,0.00006176689,0.00007139365,0.000043498778,0.00028681557,0.00009274735,0.0001916763,0.000019671523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024859182,0.000053025484,0.00036525348,0.0002993527,0.000013688326,0.000018259245,0.000065531895,0.00014049765,0.000002687859,0.9402428,0.04373017,0.015043833],"study_design_scores_gemma":[0.0020948127,0.0016898445,0.0003183791,0.0035695916,0.000034139168,0.000114966446,0.0000064264877,0.4915761,0.00009906476,0.11365462,0.38524792,0.0015941213],"about_ca_topic_score_codex":0.00016053345,"about_ca_topic_score_gemma":0.000014693357,"teacher_disagreement_score":0.8265882,"about_ca_system_score_codex":0.00010491122,"about_ca_system_score_gemma":0.000094923926,"threshold_uncertainty_score":0.9999816},"labels":[],"label_agreement":null},{"id":"W2095902286","doi":"10.1109/itng.2009.306","title":"Lessons Learned from a Survey of Web Applications Testing","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; World Wide Web; Software testing; The Internet; Government (linguistics); Web testing; Web page; Web application security; Web application; Data science; Web development; Software; Operating system","score_opus":0.18010079232447723,"score_gpt":0.3500422421938346,"score_spread":0.16994144986935739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095902286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054001585,0.00004702446,0.9809411,0.0010939122,0.000016481035,0.00008909149,0.000007733882,0.007557461,0.0048470423],"genre_scores_gemma":[0.5757651,0.000001676478,0.42403576,0.00014173597,0.0000084073645,0.0000061582737,0.00000315838,0.0000021656167,0.000035904883],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99927986,0.000053439388,0.00016584701,0.00024991765,0.00012450194,0.00012644948],"domain_scores_gemma":[0.9980293,0.001102843,0.00008112031,0.0005784325,0.00016513851,0.00004315729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003787929,0.00007100676,0.00011666327,0.00006035349,0.00006266892,0.00004828569,0.00060552097,0.00003648865,0.0000039518904],"category_scores_gemma":[0.0008450909,0.000064585634,0.000020583546,0.00063566555,0.000020948179,0.000093285,0.000081937025,0.000071242124,0.00001355204],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001461322,0.00011281275,0.035962474,0.0000024581714,0.00000515903,0.0000012588841,0.00007493128,0.000020225058,0.002786123,0.011000406,0.0069372193,0.94309545],"study_design_scores_gemma":[0.00016854938,0.00011997237,0.50880486,0.00004481852,0.0000047950048,0.000004389203,0.0000015654261,0.09947299,0.0032669515,0.38739428,0.00046964653,0.00024720118],"about_ca_topic_score_codex":0.0018625332,"about_ca_topic_score_gemma":0.000039779618,"teacher_disagreement_score":0.94284827,"about_ca_system_score_codex":0.000009629967,"about_ca_system_score_gemma":0.000076601165,"threshold_uncertainty_score":0.28156054},"labels":[],"label_agreement":null},{"id":"W2095974519","doi":"10.1109/tse.2010.32","title":"Assessing, Comparing, and Combining State Machine-Based Testing and Structural Testing: A Series of Experiments","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Test strategy; Non-regression testing; Software performance testing; White-box testing; Machine learning; Reliability engineering; Model-based testing; Software testing; Risk-based testing; Software; Series (stratigraphy); Code coverage; State (computer science); Keyword-driven testing; Software reliability testing; Data mining; Test case; Software quality; Algorithm; Software system; Software development; Engineering; Software construction","score_opus":0.034421962619943035,"score_gpt":0.2701052537879602,"score_spread":0.23568329116801714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095974519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4155685,0.00002696781,0.58125186,0.000005662471,0.00021400055,0.00007138895,0.0000033975757,0.0028515724,0.0000066197476],"genre_scores_gemma":[0.541153,3.908802e-7,0.45879674,0.0000110982855,0.000006207893,0.000012334863,3.704985e-7,0.000016885435,0.000002999709],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998856,0.000021339278,0.00028932514,0.00036100362,0.00020142861,0.0002708962],"domain_scores_gemma":[0.9983659,0.00094946515,0.00011503243,0.00033935095,0.00010727902,0.00012298778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020470443,0.00024985493,0.00026698876,0.00023224167,0.00022766126,0.00025042632,0.0002496095,0.00006804038,0.0000013071053],"category_scores_gemma":[0.00036117324,0.00025757306,0.00003135123,0.00036738446,0.00008655653,0.0005605597,0.000012744822,0.0004367653,3.9382346e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055008608,0.0003231107,0.35792103,0.0010378356,0.00017941963,0.00009353434,0.003386018,0.21025689,0.09151922,0.0002668356,0.00006149194,0.3348996],"study_design_scores_gemma":[0.0004923505,0.00021712035,0.021360083,0.00032918906,0.00001587191,0.00015107448,0.000006315396,0.92426395,0.052387588,0.000353868,0.000008774798,0.0004137967],"about_ca_topic_score_codex":0.00013313748,"about_ca_topic_score_gemma":0.0000057320267,"teacher_disagreement_score":0.7140071,"about_ca_system_score_codex":0.000018509372,"about_ca_system_score_gemma":0.00004971608,"threshold_uncertainty_score":0.99998766},"labels":[],"label_agreement":null},{"id":"W2096226167","doi":"10.1109/issre.2003.1251027","title":"A comprehensive and systematic methodology for client-server class integration testing","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Class (philosophy); Context (archaeology); Client–server model; Data mining; Server; Database; Artificial intelligence; World Wide Web","score_opus":0.16833415468862511,"score_gpt":0.3493839636123504,"score_spread":0.1810498089237253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096226167","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008150831,0.00014638333,0.9862847,0.0005204171,0.00007776663,0.000425883,3.7346052e-7,0.0041416986,0.00025199816],"genre_scores_gemma":[0.2504097,9.1546156e-7,0.7487302,0.00067955523,0.000031280004,0.00007193846,6.6876066e-7,0.000005157701,0.00007062023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999064,0.00015898958,0.0002532158,0.00026834363,0.000088557754,0.00016688756],"domain_scores_gemma":[0.9949986,0.004343927,0.00010677841,0.00029384048,0.00021299595,0.000043888598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006540699,0.0001051919,0.00022820775,0.00008929039,0.00009835634,0.0001017989,0.000252764,0.000055273144,9.648862e-7],"category_scores_gemma":[0.0017817544,0.000080487676,0.000032105712,0.00014724131,0.000028799046,0.00021604265,0.000118165,0.00006389555,0.0000064166447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028575443,0.00021504745,0.00508579,0.011719443,0.00011406206,0.000009890296,0.0047660433,0.00028412938,0.0069363066,0.48333675,0.025714895,0.46178907],"study_design_scores_gemma":[0.0003403494,0.00028126387,0.0009266516,0.0009545488,0.000024782417,0.0001530158,0.000046685447,0.9202358,0.0029044086,0.07357334,0.00029137786,0.00026775087],"about_ca_topic_score_codex":0.000034792865,"about_ca_topic_score_gemma":0.000008998577,"teacher_disagreement_score":0.9199517,"about_ca_system_score_codex":0.000027020535,"about_ca_system_score_gemma":0.00001847636,"threshold_uncertainty_score":0.3282192},"labels":[],"label_agreement":null},{"id":"W2096282282","doi":"10.1109/scam.2005.27","title":"Transforming Embedded Java Code into Custom Tags","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Java; Java applet; Programming language; Java API for XML-based RPC; Real time Java; Business logic; Java annotation; Source code; Code (set theory); Web page; Operating system; World Wide Web; Set (abstract data type)","score_opus":0.011676163790382232,"score_gpt":0.2534006728177438,"score_spread":0.2417245090273616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096282282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073576183,0.000053480693,0.95289683,0.0005826627,0.00011249436,0.00009592619,4.243094e-7,0.018479586,0.020420987],"genre_scores_gemma":[0.52928644,0.0000011497451,0.46961263,0.00029877783,0.000046149482,0.000010637673,0.0000013076792,0.0000075709777,0.000735338],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903065,0.00002164482,0.00019926978,0.00029511168,0.00020132172,0.00025201624],"domain_scores_gemma":[0.99928236,0.00013786407,0.000037101523,0.0004359924,0.00005495996,0.00005172914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023561489,0.00012346268,0.00012283621,0.000099841884,0.00013015661,0.00013243123,0.00060936064,0.000059825248,0.000014492224],"category_scores_gemma":[0.000043184966,0.00010625408,0.000055286167,0.00029674915,0.00003324556,0.00032101106,0.000077272955,0.00009583025,0.000055952434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007509463,0.00022823959,0.006609079,0.00005648558,0.000016049487,0.00009039615,0.0021864385,0.00017114241,0.0058935713,0.23913634,0.38348076,0.362124],"study_design_scores_gemma":[0.0005803885,0.00017785832,0.0012687838,0.00010258019,0.0000123523305,0.00012680628,0.00001765744,0.11126304,0.0914992,0.74761724,0.046421673,0.0009123995],"about_ca_topic_score_codex":0.0009574919,"about_ca_topic_score_gemma":0.000069581314,"teacher_disagreement_score":0.52192885,"about_ca_system_score_codex":0.000033958473,"about_ca_system_score_gemma":0.00004171368,"threshold_uncertainty_score":0.43329158},"labels":[],"label_agreement":null},{"id":"W2096830010","doi":"10.1109/apsec.2003.1254396","title":"Automated test generation from object-oriented specifications of real-time reactive systems","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Oracle; Object-oriented programming; Real-time computing; Domain (mathematical analysis); System testing; Reliability engineering; Software engineering; Programming language; Engineering","score_opus":0.03609809509497559,"score_gpt":0.2620086390616272,"score_spread":0.2259105439666516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096830010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045305785,0.000021270469,0.9161607,0.00023452293,0.00021224385,0.0002615323,0.000020692598,0.030374877,0.007408355],"genre_scores_gemma":[0.61674047,0.000004567499,0.38298097,0.000015263837,0.00005697595,0.00002004069,0.000034897315,0.000007212169,0.00013960918],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990473,0.00003832319,0.00027849243,0.00030269532,0.00020429138,0.0001288984],"domain_scores_gemma":[0.99862,0.00030668065,0.00016190353,0.0006258548,0.0002353775,0.000050202063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015676381,0.00010366015,0.00015161315,0.0000994712,0.000081376165,0.00006646753,0.00032309926,0.000061881285,0.0000070009073],"category_scores_gemma":[0.0002922483,0.0000938337,0.000031876865,0.00045580714,0.000032823675,0.00023511863,0.00006163796,0.00005400297,0.00007809583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008135274,0.001035765,0.0049275327,0.000018715056,0.000085647065,0.000025365562,0.0029473354,0.0040536993,0.67478305,0.20476374,0.10548026,0.0018707265],"study_design_scores_gemma":[0.00049542746,0.00024534922,0.019142155,0.00014757625,0.000018386549,0.000023592995,0.00002295557,0.8415329,0.12609972,0.011572701,0.0003176928,0.00038154723],"about_ca_topic_score_codex":0.0042694523,"about_ca_topic_score_gemma":0.000009067432,"teacher_disagreement_score":0.8374792,"about_ca_system_score_codex":0.000097833356,"about_ca_system_score_gemma":0.000096885546,"threshold_uncertainty_score":0.6454164},"labels":[],"label_agreement":null},{"id":"W2096914257","doi":"10.1109/test.1997.639710","title":"Supervisors for testing non-deterministically specified systems","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); University of Waterloo","funders":"","keywords":"Supervisor; Computer science; Reliability engineering; System testing; Determinism; Software engineering; Engineering","score_opus":0.11584181985453662,"score_gpt":0.2614392815401561,"score_spread":0.1455974616856195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096914257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014135208,0.00003833453,0.970689,0.00022937635,0.0003164387,0.00028145165,0.0000014805692,0.010263777,0.016766645],"genre_scores_gemma":[0.44419044,9.3984704e-7,0.55467767,0.0001683858,0.00010184132,0.000054279782,4.182138e-7,0.000010949695,0.00079510774],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988668,0.000019450037,0.00025495575,0.00036548104,0.00016904785,0.00032425552],"domain_scores_gemma":[0.9978524,0.0012960143,0.00005202125,0.00055286725,0.00014923778,0.00009749395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027238368,0.00013694623,0.00017307576,0.000080504076,0.0001451317,0.00027650472,0.0007192974,0.00005969224,0.000010028308],"category_scores_gemma":[0.0010032685,0.0001176534,0.000049482634,0.00026777864,0.00002913296,0.00015895459,0.00012985975,0.00007173626,0.00006760608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011885987,0.0004657005,0.011106903,0.0004022727,0.00004534329,0.00013787622,0.0015248397,0.0001536358,0.0012593172,0.100898825,0.52632314,0.35767028],"study_design_scores_gemma":[0.00017027545,0.00022841925,0.00041203274,0.00006314793,0.000003979292,0.00006314836,0.0000052465502,0.98870033,0.00019771923,0.007986984,0.0019330296,0.00023569616],"about_ca_topic_score_codex":0.000039386534,"about_ca_topic_score_gemma":4.8025225e-7,"teacher_disagreement_score":0.98854667,"about_ca_system_score_codex":0.00002191602,"about_ca_system_score_gemma":0.000013927715,"threshold_uncertainty_score":0.47977662},"labels":[],"label_agreement":null},{"id":"W2097180485","doi":"10.1109/test.1993.470702","title":"On the design for testability of communication software","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Testability; Computer science; Software engineering; Software; Protocol (science); Communications protocol; Software design; Software testing; Software development; Programming language; Reliability engineering; Engineering; Operating system; Medicine","score_opus":0.10298193677832075,"score_gpt":0.27574761034728895,"score_spread":0.17276567356896821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097180485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008604697,0.000037751866,0.994084,0.0014531284,0.000014261656,0.000239,6.530441e-7,0.0027662618,0.00054449006],"genre_scores_gemma":[0.45546293,0.0000017180804,0.54422104,0.00023205238,0.0000017661864,0.000033869255,1.5260312e-7,0.000002034468,0.000044419285],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995236,0.00008752504,0.0001097218,0.000111141344,0.000088805995,0.00007922614],"domain_scores_gemma":[0.9924803,0.0064239195,0.000052591335,0.0009362272,0.00009301059,0.000013980195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063485693,0.000048872174,0.000061121966,0.00002146176,0.00009891004,0.000026001082,0.0007488883,0.000022574672,0.000017419561],"category_scores_gemma":[0.0024826112,0.000029909454,0.000031348598,0.00012963689,0.000045866946,0.00006322679,0.000079094905,0.00004569412,0.0000051242723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008499881,0.00039058758,0.0025030181,0.00002694577,0.000011695473,2.264785e-7,0.0011703797,0.00027601013,0.00007433262,0.3273401,0.48084798,0.18735021],"study_design_scores_gemma":[0.000083982726,0.00021899663,0.000632112,0.00003248086,0.0000022970873,0.0000016190294,0.000002494474,0.20833984,0.004990684,0.7853195,0.00029092716,0.00008507558],"about_ca_topic_score_codex":0.000016244847,"about_ca_topic_score_gemma":6.050639e-7,"teacher_disagreement_score":0.48055708,"about_ca_system_score_codex":0.000011687546,"about_ca_system_score_gemma":0.0000071053655,"threshold_uncertainty_score":0.29720968},"labels":[],"label_agreement":null},{"id":"W2098174190","doi":"10.5555/2337223.2337449","title":"Locating features in dynamically configured avionics software","year":2012,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Avionics software; Computer science; Avionics; Software construction; Program comprehension; Software system; Software engineering; Software; Static program analysis; Software development; Verification and validation; Software framework; Software sizing; Component-based software engineering; Embedded system; Programming language; Engineering","score_opus":0.02324148763626,"score_gpt":0.2753308825634161,"score_spread":0.2520893949271561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098174190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01326286,0.00012137417,0.97778696,0.00029734985,0.0012106404,0.0001354668,0.000007874937,0.0065115937,0.00066590245],"genre_scores_gemma":[0.6828908,0.000006244159,0.31668383,0.00018103427,0.00009613351,0.00003750403,0.000014209675,0.000019480045,0.000070795635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837005,0.00003042423,0.0003189724,0.00035769842,0.00045805206,0.00046477502],"domain_scores_gemma":[0.9987414,0.0004149031,0.00009812991,0.00041425007,0.00019119833,0.00014015027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036876719,0.0002527802,0.00020208507,0.00033254878,0.000054965967,0.0001981816,0.001072849,0.00013249235,0.000030079085],"category_scores_gemma":[0.0022504271,0.00026202502,0.00006566343,0.00028646085,0.000023858009,0.0005322926,0.00022044292,0.00046374535,0.000040678602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042436553,0.0005782109,0.16239683,0.00013872738,0.00010676277,0.00012710717,0.0032573347,0.012997483,0.000907478,0.6628069,0.003131456,0.15350923],"study_design_scores_gemma":[0.0016003279,0.00029250176,0.25491577,0.0022347837,0.000019589315,0.0003889258,0.00006292458,0.7111242,0.0033131412,0.020575533,0.0028029257,0.0026694005],"about_ca_topic_score_codex":0.00005005944,"about_ca_topic_score_gemma":0.0000053719154,"teacher_disagreement_score":0.6981267,"about_ca_system_score_codex":0.00020906891,"about_ca_system_score_gemma":0.0000745798,"threshold_uncertainty_score":0.9999832},"labels":[],"label_agreement":null},{"id":"W2098272565","doi":"10.1504/ijict.2007.013274","title":"Software testing: a graph theoretic approach","year":2007,"lang":"en","type":"article","venue":"International Journal of Information and Communication Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Control flow graph; Software testing; White-box testing; Software; Path (computing); Graph; Software performance testing; Control flow; Software engineering; Theoretical computer science; Software development; Programming language; Software construction","score_opus":0.014552573438138433,"score_gpt":0.2665073864543589,"score_spread":0.25195481301622047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098272565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053391154,0.0002661447,0.98919606,0.0018561594,0.00011015469,0.00005020998,6.186266e-7,0.0010837587,0.0020977529],"genre_scores_gemma":[0.49426228,0.000078287056,0.50533015,0.0003117715,0.000009011563,0.0000019430388,0.0000020266293,0.000001853664,0.000002705455],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990127,0.00002626845,0.00053773227,0.000055666344,0.0002650241,0.000102625985],"domain_scores_gemma":[0.9976111,0.00031140016,0.0005985188,0.00034623482,0.001090804,0.00004195059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010990517,0.00007677486,0.00010432219,0.0009599087,0.000084848005,0.00013341756,0.0016646539,0.000094326846,0.0000016393612],"category_scores_gemma":[0.0014674737,0.000067132074,0.000033341992,0.00046392993,0.00013682699,0.00097491406,0.00032919607,0.00026523843,0.0000033962772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014346458,0.00004844304,0.005858133,0.0000066865973,0.000028783408,0.0000028904367,0.0005848284,0.00001892967,0.000022782417,0.31517375,0.00093447027,0.67730594],"study_design_scores_gemma":[0.00086227705,0.00024387454,0.0066833757,0.00015910002,0.000010600628,0.0028878096,0.0003298058,0.007676729,0.001356143,0.9697952,0.009750245,0.00024478763],"about_ca_topic_score_codex":0.0000062223407,"about_ca_topic_score_gemma":3.8749897e-7,"teacher_disagreement_score":0.67706114,"about_ca_system_score_codex":0.00004076726,"about_ca_system_score_gemma":0.000052072028,"threshold_uncertainty_score":0.30933687},"labels":[],"label_agreement":null},{"id":"W2098280085","doi":"10.1145/2593069.2602976","title":"Safety Evaluation of Automotive Electronics Using Virtual Prototypes","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Infineon Technologies (Canada)","funders":"","keywords":"Dependability; Automotive electronics; Automotive industry; Electronics; Automotive engineering; Computer science; Functional safety; Reliability engineering; Manufacturing engineering; Engineering; Embedded system; Electrical engineering","score_opus":0.035692471732468395,"score_gpt":0.3091718003874681,"score_spread":0.2734793286549997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098280085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03179609,0.000020856716,0.96338886,0.000054400974,0.00004730897,0.00026515115,1.836909e-7,0.002560496,0.0018666497],"genre_scores_gemma":[0.7388941,4.783711e-7,0.26100844,0.00005482316,0.000014945695,0.000009912346,4.629073e-7,0.000003695674,0.000013113973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901134,0.00016215167,0.00015331482,0.00017776668,0.00036220826,0.0001332261],"domain_scores_gemma":[0.99899065,0.00017364931,0.000084806416,0.00031463397,0.0004130838,0.000023162807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017766407,0.00006694022,0.00009681007,0.000065038905,0.000053692427,0.00002342415,0.000291741,0.000036754936,0.000007970638],"category_scores_gemma":[0.00082863815,0.000057227386,0.000027054553,0.00021036308,0.00002425062,0.00015283386,0.000080114274,0.00005919858,0.0000030761516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013492298,0.00012191245,0.0025420184,0.000016817881,0.000027256208,2.7016304e-7,0.00071536255,0.008463144,0.0013452512,0.1348557,0.0010326733,0.8508661],"study_design_scores_gemma":[0.00013385412,0.00018975596,0.00089068094,0.000022030748,0.000008900059,0.0000038227354,0.0000016109019,0.9204483,0.01266035,0.065474585,0.00009196581,0.000074126714],"about_ca_topic_score_codex":0.00004161205,"about_ca_topic_score_gemma":0.0000035685737,"teacher_disagreement_score":0.91198516,"about_ca_system_score_codex":0.000069625676,"about_ca_system_score_gemma":0.00016045314,"threshold_uncertainty_score":0.23336652},"labels":[],"label_agreement":null},{"id":"W2098647975","doi":"10.1109/compsac.2006.98","title":"A Multi-Agent Framework for Testing Distributed Systems","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Software performance testing; Distributed computing; Software architecture; System integration testing; Software reliability testing; Task (project management); Process (computing); Software system; Software engineering; Software; Software construction; Systems engineering; Operating system; Engineering","score_opus":0.0935818281614061,"score_gpt":0.32300081754675025,"score_spread":0.22941898938534416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098647975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016496012,0.00033287503,0.9615187,0.0001669591,0.0014224051,0.000984132,0.000095837284,0.0351837,0.00013041504],"genre_scores_gemma":[0.061313167,0.0000012737082,0.93741095,0.000098379875,0.00026066354,0.0006323126,0.00009129724,0.000033491673,0.00015844568],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768674,0.00006680198,0.0005226198,0.00095033046,0.00028911544,0.00048437313],"domain_scores_gemma":[0.9955683,0.002055713,0.0003750292,0.001487819,0.00040506065,0.00010807769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005926678,0.00038380196,0.0004480115,0.00013543466,0.00018362609,0.00078930263,0.0017137188,0.000472177,6.291623e-7],"category_scores_gemma":[0.0029526087,0.00034886098,0.00016607785,0.00031271155,0.000033694985,0.000075065676,0.001642736,0.00054943154,0.000008851977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017055501,0.0014156427,0.04504618,0.004817559,0.0003254963,0.0001715639,0.000602839,0.08909828,0.00009532674,0.11644384,0.64352953,0.09843666],"study_design_scores_gemma":[0.00010902424,0.000045065208,0.0011581207,0.00096248265,0.000016286815,0.000015246986,0.0000011491512,0.87070334,0.000040959272,0.12562385,0.0008517888,0.00047267426],"about_ca_topic_score_codex":0.0013515875,"about_ca_topic_score_gemma":0.0000033247202,"teacher_disagreement_score":0.78160506,"about_ca_system_score_codex":0.00016193642,"about_ca_system_score_gemma":0.00017950586,"threshold_uncertainty_score":0.99989635},"labels":[],"label_agreement":null},{"id":"W2098933948","doi":"10.1109/icstw.2010.35","title":"Supporting Test-Driven Development of Graphical User Interfaces Using Agile Interaction Design","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Graphical user interface; Graphical user interface testing; Agile software development; Scripting language; Human–computer interaction; Test (biology); User interface; Test script; Test-driven development; Software engineering; Test Management Approach; Fidelity; Programming language; Test case; User interface design; Software development; Software","score_opus":0.05133768931905014,"score_gpt":0.33723895008860305,"score_spread":0.2859012607695529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098933948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30585596,0.0000017144379,0.69188136,0.000035952504,0.00016668695,0.00006775151,1.1392297e-7,0.0018799838,0.000110500674],"genre_scores_gemma":[0.5008908,1.2063069e-7,0.49905008,0.000026222537,0.0000094418865,0.0000032370883,2.389225e-7,0.000004304798,0.000015537082],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989867,0.00003134055,0.000355374,0.00025055662,0.00017330488,0.0002026824],"domain_scores_gemma":[0.9987742,0.000555584,0.00018548415,0.00030281718,0.00012599233,0.000055947297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051496306,0.0001096412,0.0001328667,0.00016102567,0.00009815843,0.00007978923,0.00047410792,0.000066320405,0.000024954667],"category_scores_gemma":[0.0006212192,0.00009366584,0.000032384432,0.00025190235,0.000042201475,0.00033939324,0.00023805512,0.00021040006,0.0000060346892],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012581764,0.00041324383,0.12469194,0.000057797428,0.000043370936,0.000016695443,0.003959504,0.00029894547,0.7168664,0.0022834013,0.0055089085,0.14584725],"study_design_scores_gemma":[0.00011283307,0.000096976946,0.0030844975,0.00010690363,0.0000060219345,0.00007148502,0.000021542553,0.25894883,0.7310483,0.005830897,0.00040304198,0.0002686532],"about_ca_topic_score_codex":0.00004190673,"about_ca_topic_score_gemma":0.0000124627,"teacher_disagreement_score":0.2586499,"about_ca_system_score_codex":0.000018418543,"about_ca_system_score_gemma":0.000098990415,"threshold_uncertainty_score":0.38195822},"labels":[],"label_agreement":null},{"id":"W2099441126","doi":"10.1109/tse.2003.1214327","title":"General test result checking with log file analysis","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Random testing; Formalism (music); Programming language; Unit testing; Operating system; Software; Test case","score_opus":0.011147187604348262,"score_gpt":0.21500120278407897,"score_spread":0.2038540151797307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099441126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002097336,0.000025344652,0.9867371,0.000015934931,0.0001798991,0.000094306255,0.000039217757,0.010729381,0.00008148545],"genre_scores_gemma":[0.42502555,0.000002955168,0.57461923,0.00005397941,0.000017009888,0.000057096648,0.0000037609568,0.000024115017,0.00019628793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986122,0.000025433988,0.00022932317,0.00047132606,0.0002861109,0.00037560132],"domain_scores_gemma":[0.998276,0.0007479516,0.00005811886,0.0007035306,0.00008917283,0.00012525347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019220928,0.00025286514,0.0002522806,0.0005018831,0.00018447814,0.00013550936,0.00038028887,0.000090588655,0.000079206846],"category_scores_gemma":[0.00021347773,0.00023726885,0.00014364968,0.0018820133,0.000022074026,0.00025673362,0.00000238204,0.00031814177,0.000017399117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066371817,0.00020652633,0.0019165198,0.000035142984,0.0003575011,0.000076666,0.00034380067,0.9820529,0.00021067275,0.00028875063,0.0025879126,0.011916975],"study_design_scores_gemma":[0.0011792077,0.0007925229,0.0062580556,0.00043414772,0.00057739374,0.00031973078,0.000010485471,0.91190934,0.069352135,0.0004664742,0.0062869657,0.002413544],"about_ca_topic_score_codex":0.000041456726,"about_ca_topic_score_gemma":0.000007751677,"teacher_disagreement_score":0.4229282,"about_ca_system_score_codex":0.00008885792,"about_ca_system_score_gemma":0.000053459138,"threshold_uncertainty_score":0.9675543},"labels":[],"label_agreement":null},{"id":"W2099523200","doi":"10.1109/mutation.2006.5","title":"<i>ExMAn</i>: A Generic and Customizable Framework for Experimental Mutation Analysis","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mutation testing; Computer science; Static analysis; Mutation; Software testing; Programming language; Software engineering; Quality assurance; Quality (philosophy); Software; Engineering","score_opus":0.015969552038483013,"score_gpt":0.27566231475820446,"score_spread":0.25969276271972147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099523200","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016197637,0.00021658278,0.9792277,0.0001593007,0.000039251692,0.00010688216,7.56948e-7,0.0035107487,0.0005411119],"genre_scores_gemma":[0.4472716,5.58051e-7,0.5523426,0.00020222005,0.000023789948,0.00003824239,0.000002927928,0.0000032235555,0.00011485403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937665,0.000014374402,0.00011886994,0.00025594086,0.00009139694,0.00014275171],"domain_scores_gemma":[0.9994467,0.00021237718,0.00004601964,0.00023063637,0.000034154673,0.000030136822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012471374,0.00007923051,0.00011523146,0.00013521052,0.000104973384,0.00013848672,0.00016584928,0.000043790413,0.000005358078],"category_scores_gemma":[0.00004080605,0.00007099965,0.00005509894,0.0005085782,0.000018912588,0.000149009,0.00006149179,0.0000303999,0.0000021188016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002784822,0.0005066,0.023413152,0.000042556672,0.00027082328,0.000026510637,0.0011139244,0.0039349077,0.0021755022,0.81659657,0.10803905,0.04385253],"study_design_scores_gemma":[0.00021659311,0.00011216834,0.002062524,0.000008639317,0.00006227403,0.0000141462515,0.000009835724,0.6253351,0.019609304,0.35169315,0.00062075193,0.00025554057],"about_ca_topic_score_codex":0.00025220966,"about_ca_topic_score_gemma":0.0000048048933,"teacher_disagreement_score":0.6214002,"about_ca_system_score_codex":0.000017219776,"about_ca_system_score_gemma":0.000010742818,"threshold_uncertainty_score":0.2895282},"labels":[],"label_agreement":null},{"id":"W2100147370","doi":"10.5381/jot.2009.8.3.a4","title":"Automated State-Based Unit Testing for Aspect-Oriented Programs: A Supporting Framework.","year":2009,"lang":"en","type":"article","venue":"The Journal of Object Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Innovation and Economic Development Trois Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Unit testing; State (computer science); Unit (ring theory); Aspect-oriented programming; Software engineering; Reliability engineering; Programming language; Engineering; Software; Mathematics","score_opus":0.029179515527060974,"score_gpt":0.3179984803389712,"score_spread":0.2888189648119102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100147370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10981477,0.00013728064,0.86982095,0.0033927145,0.00014543971,0.000336261,8.6429367e-7,0.016291114,0.000060604],"genre_scores_gemma":[0.55587643,0.0000011863364,0.4438581,0.00021792362,0.000026580208,0.0000060071043,3.659344e-7,0.000009676657,0.0000037453904],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982302,0.000097898584,0.0006730299,0.00019409768,0.0002800393,0.00052471523],"domain_scores_gemma":[0.9963091,0.0013130642,0.00097235554,0.00061120593,0.0007276748,0.00006658405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019049816,0.00019731549,0.00033788127,0.0005954643,0.00025411235,0.00008336592,0.0015335954,0.0001749775,7.839988e-7],"category_scores_gemma":[0.005736599,0.000136729,0.000094564486,0.0020036795,0.00012903647,0.00016801374,0.000104358536,0.00064757036,0.0000019046123],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016439306,0.0006304385,0.018192206,0.000058474634,0.0001106372,0.00018277369,0.0012403217,0.000769761,0.005870454,0.012148529,0.00576205,0.95487],"study_design_scores_gemma":[0.0011697597,0.009142609,0.0025401223,0.0009635902,0.00008134812,0.001896179,0.000102534796,0.24996209,0.02776017,0.7051573,0.0007308376,0.0004934852],"about_ca_topic_score_codex":0.000009534346,"about_ca_topic_score_gemma":0.0000012691066,"teacher_disagreement_score":0.95437646,"about_ca_system_score_codex":0.00006815291,"about_ca_system_score_gemma":0.0003040626,"threshold_uncertainty_score":0.68676597},"labels":[],"label_agreement":null},{"id":"W2100209048","doi":"","title":"Static And Dynamic Reverse Engineering Techniques for Java Software Systems","year":2019,"lang":"en","type":"book","venue":"Trepo - Institutional Repository of Tampere University","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tekes; University of Victoria","keywords":"Reverse engineering; Computer science; Java; Software engineering; Programming language","score_opus":0.008589263300448567,"score_gpt":0.19626188704935338,"score_spread":0.1876726237489048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100209048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075381354,0.00059330236,0.97646487,0.00006547235,0.0011717192,0.0012383858,0.00020011298,0.006038635,0.0134737175],"genre_scores_gemma":[0.01812653,0.00010988778,0.67134076,0.00005716032,0.00015571852,0.0000149935795,0.00016101266,0.000059910057,0.309974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998528,0.0000335165,0.0003205405,0.0005755196,0.00033777425,0.00020462357],"domain_scores_gemma":[0.99797934,0.00052902405,0.00039809427,0.0006200466,0.0003778786,0.00009561764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021425016,0.000301203,0.0004643475,0.00035396728,0.00030000473,0.00006563491,0.0006576127,0.00030848983,7.473998e-7],"category_scores_gemma":[0.00023144891,0.0003401741,0.00015938196,0.00010071006,0.00020817887,0.0003962432,0.00030759626,0.00025016943,0.000001957625],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004564557,0.00069218077,0.0025186455,0.024924753,0.001967033,0.0032145823,0.0022995928,0.010988518,0.002288051,0.4786044,0.44685954,0.025186239],"study_design_scores_gemma":[0.0012939224,0.0009931369,0.0005555958,0.009316411,0.0004959899,0.0022336082,0.00003922558,0.10529546,0.00067781477,0.007816388,0.86878544,0.0024970255],"about_ca_topic_score_codex":0.00012145859,"about_ca_topic_score_gemma":0.0000015064892,"teacher_disagreement_score":0.47078803,"about_ca_system_score_codex":0.0007151056,"about_ca_system_score_gemma":0.0010660809,"threshold_uncertainty_score":0.99990505},"labels":[],"label_agreement":null},{"id":"W2100485841","doi":"10.1109/infcom.1994.337662","title":"Fault coverage analysis in respect to an FSM specification","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Fault coverage; Test suite; Computer science; Fault tree analysis; Finite-state machine; Fault (geology); Algorithm; Fault model; Class (philosophy); Suite; Code coverage; Minification; Automatic test pattern generation; State (computer science); Test case; Theoretical computer science; Programming language; Reliability engineering; Artificial intelligence; Software; Engineering; Machine learning; Electronic circuit","score_opus":0.04951585261241914,"score_gpt":0.2916565817219161,"score_spread":0.24214072910949697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100485841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043898392,0.000018023931,0.9401098,0.00083258405,0.000031426945,0.00008220469,5.027591e-7,0.004854966,0.01017214],"genre_scores_gemma":[0.77417403,0.000004289675,0.22482273,0.00043185573,0.000018082734,0.000008117823,0.0000010633105,0.0000032281407,0.0005366269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991203,0.00005131096,0.00016015259,0.00034417646,0.00017098329,0.00015308867],"domain_scores_gemma":[0.999016,0.00010403296,0.00003031326,0.0007345216,0.000040985426,0.00007414573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026975677,0.000073375224,0.000114358496,0.00046529504,0.000039353257,0.00013549303,0.000532993,0.00003203556,0.000079302015],"category_scores_gemma":[0.00015219417,0.00006785988,0.00003725272,0.0020418237,0.0000072373,0.0002492149,0.0000731683,0.00006295111,0.000103219274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012110686,0.0007997124,0.23480867,0.000009645838,0.00007875907,0.00011946136,0.0056648664,0.0054365913,0.0009640414,0.0520187,0.14072728,0.55936015],"study_design_scores_gemma":[0.00021216259,0.00024630112,0.24297665,0.000018612167,0.000019204475,0.000009142594,0.000008192637,0.7209924,0.001583429,0.028473552,0.0049681654,0.0004921822],"about_ca_topic_score_codex":0.00023285451,"about_ca_topic_score_gemma":0.0001163413,"teacher_disagreement_score":0.73027563,"about_ca_system_score_codex":0.00005041916,"about_ca_system_score_gemma":0.000004804444,"threshold_uncertainty_score":0.27672458},"labels":[],"label_agreement":null},{"id":"W2100775847","doi":"10.1145/1321631.1321654","title":"Nighthawk","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Software testing; Software","score_opus":0.013701328256595972,"score_gpt":0.2658061073748248,"score_spread":0.2521047791182288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100775847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012698509,0.000008980993,0.90420616,0.0001901321,0.00008590531,0.000018069786,1.4980973e-8,0.017361725,0.07685914],"genre_scores_gemma":[0.48414022,2.2581575e-7,0.51487124,0.0004297177,0.000018105922,4.917092e-7,5.731657e-8,0.0000014943232,0.0005384789],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99959546,0.0000043566056,0.00006646755,0.00011283188,0.00008768792,0.00013316699],"domain_scores_gemma":[0.9995138,0.00013134313,0.000012883085,0.00027716428,0.000024009216,0.000040799663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034478432,0.00003683282,0.000034067125,0.000049387407,0.00003576863,0.000035503228,0.00034388996,0.0000198361,0.00000894265],"category_scores_gemma":[0.000066078435,0.000029200475,0.000015771253,0.00016627985,0.000009397989,0.00009757379,0.00008005686,0.00003598944,0.00006642576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011843221,0.00004074301,0.018281842,0.00000292287,0.0000032972962,0.00005945162,0.00020907387,6.294196e-7,0.0002264951,0.3820401,0.19056278,0.40857148],"study_design_scores_gemma":[0.00015930073,0.00011935194,0.040105626,0.000018093126,0.0000014763891,0.00014258552,0.0000030465535,0.0061039017,0.031163458,0.8901953,0.031618446,0.00036939938],"about_ca_topic_score_codex":0.00002389214,"about_ca_topic_score_gemma":0.0000020806199,"teacher_disagreement_score":0.5081552,"about_ca_system_score_codex":0.000008137928,"about_ca_system_score_gemma":0.000008621368,"threshold_uncertainty_score":0.11907608},"labels":[],"label_agreement":null},{"id":"W2100888697","doi":"10.1109/pccc.1988.10096","title":"Modelling of expressed system behavior towards characterization of the conformance testing problem","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nondeterministic algorithm; Computer science; Set (abstract data type); Conformance testing; Implementation; Characterization (materials science); Programming language; Tree (set theory); Theoretical computer science; Algorithm; Artificial intelligence; Data mining; Mathematics; Standardization; Operating system","score_opus":0.05406417772731281,"score_gpt":0.23563388366252355,"score_spread":0.18156970593521074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100888697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1807347,0.0000046138584,0.81557506,0.00000877056,0.00006207475,0.00018822843,0.0000014197097,0.0013897569,0.002035385],"genre_scores_gemma":[0.6945488,4.4125906e-7,0.30538732,0.000009067692,0.0000032782225,0.000019041654,3.3149743e-7,0.000003834786,0.000027927768],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992264,0.000040441922,0.00029309397,0.00013619936,0.00019146933,0.00011238043],"domain_scores_gemma":[0.99902683,0.00006818735,0.000256537,0.0004083699,0.00022107842,0.000018965744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003092993,0.000075746844,0.00012569074,0.00004334453,0.000055237742,0.00002465245,0.00043331043,0.00003544872,7.0550044e-7],"category_scores_gemma":[0.00008050937,0.00005226965,0.000031734067,0.00035236357,0.000027582102,0.00018762535,0.00007565373,0.000050453473,4.264299e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011456117,0.0005568738,0.12144328,0.0023484838,0.000041129762,0.0000066214147,0.004865457,0.027693622,0.46539336,0.29643738,0.00026611632,0.080936186],"study_design_scores_gemma":[0.000097966935,0.000041141688,0.0015679498,0.00041183995,0.0000080984855,0.000014825054,0.000006776354,0.65612715,0.34063494,0.000956878,0.000022483642,0.00010991578],"about_ca_topic_score_codex":0.00006210211,"about_ca_topic_score_gemma":9.764555e-8,"teacher_disagreement_score":0.6284336,"about_ca_system_score_codex":0.000015441301,"about_ca_system_score_gemma":0.00007387708,"threshold_uncertainty_score":0.21314944},"labels":[],"label_agreement":null},{"id":"W2100942157","doi":"10.1109/csmr.2010.21","title":"Automating Coverage Metrics for Dynamic Web Applications","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Instrumentation (computer programming); Web application; The Internet; Code coverage; Database; Set (abstract data type); Software; Operating system; Programming language","score_opus":0.012044583795526614,"score_gpt":0.2872492392723478,"score_spread":0.27520465547682116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100942157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022202334,0.000012474585,0.9785719,0.00025710624,0.00012343934,0.00026323533,0.000002812608,0.0163115,0.002237311],"genre_scores_gemma":[0.41149405,9.807721e-7,0.58803535,0.00016568102,0.000017454122,0.00013357971,0.0000018876974,0.0000048786533,0.00014612822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939924,0.000006496164,0.00012453456,0.00021418548,0.000103017206,0.00015253275],"domain_scores_gemma":[0.99866235,0.0006602267,0.000054652777,0.0004896798,0.00008673689,0.00004635021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002975678,0.00006938047,0.0000728327,0.00013384751,0.00014564143,0.0001336905,0.0005688614,0.000049482762,0.000004773897],"category_scores_gemma":[0.00041465656,0.000062480125,0.00003916953,0.000496665,0.000015338392,0.00014045609,0.00011048204,0.00010418232,0.000016550475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.790833e-7,0.000069020825,0.0023924152,0.000030985153,0.000007093712,7.066078e-7,0.00006250558,0.000007944865,0.005699652,0.16752854,0.012591649,0.811609],"study_design_scores_gemma":[0.000097718505,0.000025629733,0.00057500124,0.0000050881126,0.0000028764102,0.000011228182,4.801849e-7,0.8694557,0.0006636534,0.12224351,0.006785537,0.0001335769],"about_ca_topic_score_codex":0.0000095405,"about_ca_topic_score_gemma":0.000009259142,"teacher_disagreement_score":0.86944777,"about_ca_system_score_codex":0.000013961169,"about_ca_system_score_gemma":0.00005135134,"threshold_uncertainty_score":0.25478655},"labels":[],"label_agreement":null},{"id":"W2102418068","doi":"10.1109/tse.2002.1049402","title":"Timed Wp-method: testing real-time systems","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Nondeterministic algorithm; Correctness; Timed automaton; Automaton; System under test; Finite-state machine; Fault coverage; Real-time operating system; Test case; Real-time computing; Distributed computing; Algorithm; Theoretical computer science; Embedded system","score_opus":0.026720613989180138,"score_gpt":0.23424799388672066,"score_spread":0.20752737989754053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102418068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007546978,0.00006639904,0.96300083,0.000026515127,0.0007475171,0.00019549172,0.0000070050683,0.034973703,0.00022783395],"genre_scores_gemma":[0.13738368,0.000011506547,0.86172366,0.00003760563,0.00008093422,0.000096782256,6.460476e-7,0.000058854428,0.0006063022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982241,0.000059604845,0.00036458217,0.0005223097,0.00035002895,0.0004793927],"domain_scores_gemma":[0.9972542,0.0016460202,0.00008248465,0.0007287334,0.00011390251,0.00017468091],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037829328,0.00030924246,0.00030829417,0.00037537134,0.0002229118,0.00020478645,0.00062005676,0.00014127986,0.000029776396],"category_scores_gemma":[0.0002562958,0.0003291331,0.000111518166,0.00093613827,0.000017235649,0.00035736192,0.0000062645436,0.00037452354,0.00024628124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004428416,0.0002325413,0.0001208326,0.00018079291,0.00009352344,0.00011755249,0.00060215767,0.8072634,0.0050192205,0.00018391242,0.007396425,0.17878525],"study_design_scores_gemma":[0.00015991944,0.000105897096,0.00006467586,0.00024742965,0.000015061016,0.00016346766,0.0000011417962,0.99474627,0.0037068648,0.000055873366,0.00032635816,0.0004070195],"about_ca_topic_score_codex":0.00010362309,"about_ca_topic_score_gemma":2.3233788e-7,"teacher_disagreement_score":0.18748292,"about_ca_system_score_codex":0.00012789517,"about_ca_system_score_gemma":0.000019975572,"threshold_uncertainty_score":0.9999161},"labels":[],"label_agreement":null},{"id":"W2102816978","doi":"10.1155/2013/420394","title":"Regression Test Reduction for Object-Oriented Software: A Control Call Graph Based Technique and Associated Tool","year":2013,"lang":"en","type":"article","venue":"ISRN Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regression testing; Test suite; Computer science; Test case; Control flow graph; Call graph; Control flow; Test Management Approach; Reduction (mathematics); Graph; Test (biology); Keyword-driven testing; Software regression; Model-based testing; Software; Control (management); Data mining; Regression analysis; Programming language; Artificial intelligence; Machine learning; Theoretical computer science; Software system; Software development; Software quality; Software construction; Mathematics","score_opus":0.006770740737484236,"score_gpt":0.21378199578570348,"score_spread":0.20701125504821924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102816978","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007902584,0.00012073999,0.9693971,0.00015561747,0.0003247115,0.0012472931,0.000020758589,0.020828772,0.0000023737887],"genre_scores_gemma":[0.37738073,0.0000041228186,0.6212512,0.00010820829,0.0000615926,0.0010869984,0.00001752386,0.00004975423,0.000039849583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980753,0.000042982247,0.00039788196,0.00062750955,0.00029061627,0.00056570896],"domain_scores_gemma":[0.99686176,0.0018479994,0.00017584772,0.00059544586,0.00036588983,0.00015308292],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005519305,0.00036758653,0.00036555165,0.0003369372,0.00021876188,0.00020364513,0.0004153794,0.00025894327,0.0000030471967],"category_scores_gemma":[0.00829459,0.00034833793,0.00012161866,0.00061267614,0.000043974243,0.0005298034,0.00010875754,0.0003091891,0.00000433221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000161975,0.0020410642,0.31660816,0.002305539,0.0005887161,0.00014248559,0.0020138677,0.013207825,0.11023391,0.0026361393,0.1864815,0.36357883],"study_design_scores_gemma":[0.0068214,0.0021906854,0.078417785,0.00418459,0.00018136707,0.0003894731,0.000013036739,0.8349686,0.045884144,0.019218124,0.0033704066,0.0043603554],"about_ca_topic_score_codex":0.000089093315,"about_ca_topic_score_gemma":0.0000016244912,"teacher_disagreement_score":0.82176083,"about_ca_system_score_codex":0.0001419207,"about_ca_system_score_gemma":0.00007778759,"threshold_uncertainty_score":0.9998969},"labels":[],"label_agreement":null},{"id":"W2103745340","doi":"10.1109/ase.2002.1115029","title":"Adding value to formal test oracles","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Programming language; Code coverage; Value (mathematics); Test case; Test Management Approach; Keyword-driven testing; Process (computing); Formal verification; Test harness; Software engineering; Software; Theoretical computer science; Software development; Machine learning; Software construction","score_opus":0.03135776340264899,"score_gpt":0.25354025767666805,"score_spread":0.22218249427401907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103745340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019152183,0.000031162836,0.9372322,0.0011051552,0.000103838305,0.00008555392,6.979576e-7,0.019912705,0.039613478],"genre_scores_gemma":[0.4824823,9.870589e-7,0.5157864,0.0011162148,0.00003115045,0.000007669479,1.203462e-7,0.0000043968494,0.0005707636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992491,0.000010611152,0.00011313803,0.00021282368,0.0001504637,0.00026385696],"domain_scores_gemma":[0.99910533,0.000350886,0.000021973417,0.00038757361,0.000038131413,0.00009608751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017351654,0.000082348444,0.00007596757,0.00009194065,0.00011869333,0.00014324197,0.00057344313,0.000028527998,0.000038005455],"category_scores_gemma":[0.00051717274,0.000069986294,0.000027628861,0.0003350774,0.000010054888,0.00038008596,0.0002817703,0.0000602608,0.00034538907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.860484e-7,0.000102808975,0.00796752,0.000007867837,0.0000039740567,0.0000241387,0.00073907664,0.000053396572,0.0002585123,0.06668736,0.43144175,0.492713],"study_design_scores_gemma":[0.00037370526,0.00088264665,0.008857127,0.00020241662,0.000008320184,0.00025490666,0.000014163829,0.8446375,0.012526058,0.05064522,0.08040157,0.0011963561],"about_ca_topic_score_codex":0.000041458137,"about_ca_topic_score_gemma":0.0000014740502,"teacher_disagreement_score":0.8445841,"about_ca_system_score_codex":0.000019390884,"about_ca_system_score_gemma":0.000005824581,"threshold_uncertainty_score":0.4439393},"labels":[],"label_agreement":null},{"id":"W2103792020","doi":"10.1016/j.comnet.2008.11.003","title":"Overcoming controllability problems with fewest channels between testers","year":2008,"lang":"en","type":"article","venue":"Computer Networks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Controllability; Computer science; Port (circuit theory); Sequence (biology); Set (abstract data type); Software deployment; Test (biology); Distributed computing; Mathematics; Engineering","score_opus":0.028572891636590967,"score_gpt":0.22464161361730314,"score_spread":0.19606872198071218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103792020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028497754,0.00013656996,0.9622159,0.0003673908,0.0003939336,0.00035275472,7.666147e-7,0.007892217,0.0001427221],"genre_scores_gemma":[0.76837665,0.0000055982655,0.23034632,0.0005667652,0.00062481075,0.000029634275,0.000004403121,0.000020329422,0.000025493755],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806523,0.00011077666,0.00032816065,0.0006611762,0.00028697256,0.0005476887],"domain_scores_gemma":[0.9978129,0.00077208073,0.00015720926,0.00093131786,0.0001447542,0.00018169844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004050787,0.00028820036,0.0004088665,0.00009521536,0.00032774286,0.0002036549,0.0010247142,0.00012036585,0.0000014671376],"category_scores_gemma":[0.000029631294,0.00023718057,0.00007849345,0.0005093626,0.00015268919,0.00038634043,0.00041463453,0.0003233903,0.00000852145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002195737,0.00017698183,0.74865896,0.000051304825,0.000118298594,0.00018743174,0.0013028483,0.08836968,0.000003534229,0.0006905122,0.034846433,0.12557207],"study_design_scores_gemma":[0.0008572616,0.0005169678,0.06857345,0.00024205477,0.000014001189,0.00024899954,5.2254615e-7,0.92350525,0.00001801822,0.003947337,0.0014875068,0.0005886501],"about_ca_topic_score_codex":0.000051110088,"about_ca_topic_score_gemma":0.0000022218976,"teacher_disagreement_score":0.8351355,"about_ca_system_score_codex":0.000061260376,"about_ca_system_score_gemma":0.000061453786,"threshold_uncertainty_score":0.9671943},"labels":[],"label_agreement":null},{"id":"W2103954365","doi":"10.1109/icsm.2008.4658102","title":"A requirement-based software testing framework: An industrial practice","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); University of Waterloo","funders":"","keywords":"Computer science; Test strategy; Regression testing; Software engineering; Automation; System integration testing; Software testing; Process (computing); Systems engineering; Software; Software development; Software construction; Engineering","score_opus":0.1849764972952483,"score_gpt":0.3331290527394926,"score_spread":0.14815255544424433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103954365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040076706,0.000020534915,0.9654956,0.0008922428,0.000238837,0.00016432909,7.1095366e-7,0.02772888,0.001451188],"genre_scores_gemma":[0.19830768,6.0749056e-7,0.7988492,0.0025900367,0.00016758428,0.000022278642,0.0000018678398,0.000014973572,0.000045782555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981648,0.00016074724,0.00028692436,0.00052107085,0.00047347392,0.00039300526],"domain_scores_gemma":[0.995322,0.0030197473,0.00017287578,0.001000781,0.00031058062,0.00017400525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007311752,0.0001837459,0.0001646315,0.00013398162,0.0003917932,0.00017208616,0.0009528916,0.00017420098,0.000015496214],"category_scores_gemma":[0.020422146,0.00017033954,0.000042467862,0.00081179023,0.00007149104,0.0011251464,0.00019793467,0.00038956333,0.00003293175],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008418791,0.0015992612,0.15223375,0.000033006138,0.000052970852,0.0011909009,0.0017469733,0.00063570705,0.00021242569,0.02282559,0.1214847,0.69790053],"study_design_scores_gemma":[0.005591057,0.008127916,0.011615836,0.0017148949,0.00013562372,0.0037637537,0.000116144656,0.6417927,0.016805762,0.26619405,0.03818127,0.0059609953],"about_ca_topic_score_codex":0.00030234785,"about_ca_topic_score_gemma":0.0000012751996,"teacher_disagreement_score":0.69193953,"about_ca_system_score_codex":0.00006148096,"about_ca_system_score_gemma":0.000376228,"threshold_uncertainty_score":0.98782927},"labels":[],"label_agreement":null},{"id":"W2104487064","doi":"10.1109/wcre.2012.41","title":"Automated Acceptance Testing of JavaScript Web Applications","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"JavaScript; Computer science; Scripting language; Unobtrusive JavaScript; Test script; Web application; World Wide Web; Web testing; Dynamic web page; Web crawler; Web development; Cross-site scripting; Software engineering; Web page; Client-side scripting; Web API; Test case; Programming language; Rich Internet application; Web application security","score_opus":0.04086191583954878,"score_gpt":0.2929715301271169,"score_spread":0.2521096142875681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104487064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030568987,0.00021101683,0.93533987,0.00008277747,0.000096535354,0.00014632878,9.671809e-7,0.044185173,0.016880445],"genre_scores_gemma":[0.51000583,8.067922e-7,0.48979524,0.000081184095,0.000022752813,0.000028103736,3.14956e-7,0.000003496573,0.00006227852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932265,0.00002019425,0.00017330142,0.00014134638,0.00013017026,0.00021233616],"domain_scores_gemma":[0.99895865,0.00027194674,0.00008689504,0.00050789426,0.00010930681,0.000065338085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027677199,0.00007378917,0.00009548468,0.00006851074,0.000063549705,0.000028916676,0.0005441523,0.000033712226,0.0000075080484],"category_scores_gemma":[0.00026779308,0.00006525207,0.00002466377,0.00061693514,0.000030218893,0.0003252549,0.00015445407,0.00005259488,0.00003238397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012337712,0.00040966307,0.324412,0.00008405344,0.000023671206,0.000001122465,0.0005352391,0.000028670427,0.01316989,0.10068894,0.15414289,0.40650266],"study_design_scores_gemma":[0.00034336833,0.00012236864,0.075404115,0.00016267417,0.000020202704,0.00010223989,0.00001559082,0.82440114,0.041836873,0.03362608,0.023187906,0.0007774651],"about_ca_topic_score_codex":0.000034469722,"about_ca_topic_score_gemma":5.453215e-7,"teacher_disagreement_score":0.8243725,"about_ca_system_score_codex":0.000015025383,"about_ca_system_score_gemma":0.00003652328,"threshold_uncertainty_score":0.2660902},"labels":[],"label_agreement":null},{"id":"W2104555990","doi":"10.1109/sera.2007.127","title":"TODD: Test-Oriented Development and Debugging","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Eclipse; Test-driven development; Debugging; Computer science; Software engineering; Software development; Test (biology); Software development process; Software; Software quality; Programming language","score_opus":0.014663742099982372,"score_gpt":0.253548008777659,"score_spread":0.23888426667767662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104555990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028792428,0.00008019908,0.9536279,0.00019100116,0.00007216811,0.000055874036,7.502557e-8,0.012080998,0.0050993785],"genre_scores_gemma":[0.38420582,0.0000012007665,0.6151069,0.000447577,0.000012231228,0.000002458513,2.896434e-7,0.0000036993126,0.00021986727],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992043,0.0000062471026,0.00015848082,0.00024044205,0.00014707293,0.00024350229],"domain_scores_gemma":[0.99914396,0.00044615133,0.000032613763,0.00023596738,0.000048619546,0.00009270102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054216007,0.000089606525,0.000074585245,0.00010656307,0.00012640023,0.00006539619,0.00022925959,0.00003333982,0.0000030199333],"category_scores_gemma":[0.0002723597,0.00007659604,0.0000110727005,0.0002376674,0.00002133044,0.00014531687,0.00021145477,0.000060837097,0.000012470389],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019832848,0.0000721703,0.15241678,0.00001356926,0.000008453033,0.00007583402,0.0010920446,5.0229363e-7,0.00020776404,0.01960467,0.01818666,0.80831957],"study_design_scores_gemma":[0.0010391714,0.0003775216,0.5402104,0.00028823383,0.000010472362,0.000762174,0.000039612987,0.02263587,0.15566887,0.051573094,0.22556953,0.0018250559],"about_ca_topic_score_codex":0.000022522212,"about_ca_topic_score_gemma":0.000008500619,"teacher_disagreement_score":0.80649453,"about_ca_system_score_codex":0.000026603664,"about_ca_system_score_gemma":0.000038651346,"threshold_uncertainty_score":0.3123496},"labels":[],"label_agreement":null},{"id":"W2104619223","doi":"10.1109/dnsr.2004.1344718","title":"PBit - a pattern-based testing framework for iptables","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Firewall (physics); Template; Parameterized complexity; Regression testing; Software; Operating system; Algorithm; Programming language; Software development","score_opus":0.05484419848625403,"score_gpt":0.2950918190262262,"score_spread":0.2402476205399722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104619223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013117683,0.000024228784,0.9808043,0.0012484425,0.00012332053,0.00016585019,0.0000013286842,0.01586823,0.00045248296],"genre_scores_gemma":[0.35606444,1.01241675e-7,0.64221513,0.0016039733,0.000044129283,0.000047578884,6.8755133e-7,0.000008458249,0.000015518372],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910337,0.000011049262,0.00015109355,0.00031182403,0.00013975236,0.00028290504],"domain_scores_gemma":[0.99808973,0.001208574,0.000059275615,0.0004783224,0.00009942727,0.000064681444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023067076,0.00011766036,0.000114442104,0.00007358035,0.00014428227,0.00016910837,0.0005769333,0.00006752612,0.000003844422],"category_scores_gemma":[0.0015036409,0.00010248899,0.000050628892,0.0003243315,0.000022473841,0.0001330772,0.000079180376,0.000093023686,0.000012660727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007838336,0.0003614271,0.04534474,0.00016830693,0.00002288595,0.000042122916,0.00044035778,0.0031093962,0.00029634833,0.2569243,0.012786088,0.68049616],"study_design_scores_gemma":[0.00027195807,0.0001878788,0.0010505251,0.00024482262,0.0000037062823,0.0000099903145,0.0000014632726,0.064980105,0.005513621,0.9271292,0.00036628154,0.00024045707],"about_ca_topic_score_codex":0.0002085454,"about_ca_topic_score_gemma":0.0000036706526,"teacher_disagreement_score":0.6802557,"about_ca_system_score_codex":0.000038514325,"about_ca_system_score_gemma":0.00010909055,"threshold_uncertainty_score":0.41793796},"labels":[],"label_agreement":null},{"id":"W2104785339","doi":"10.1109/issre.2003.1251063","title":"Investigating java type analyses for the receiver-classes testing criterion","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Java; Computer science; Class (philosophy); Context (archaeology); Set (abstract data type); Intersection (aeronautics); Variable (mathematics); Cover (algebra); Hierarchy; Object (grammar); Software; Code coverage; Type (biology); Programming language; Mathematics; Artificial intelligence","score_opus":0.21090173517988733,"score_gpt":0.39278050659782404,"score_spread":0.1818787714179367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104785339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006972337,0.00031797923,0.97551227,0.004128993,0.00019379563,0.00021196576,6.845449e-7,0.010031448,0.00263052],"genre_scores_gemma":[0.28221378,0.0000040474433,0.7160754,0.0012611581,0.00014746445,0.000017503105,7.441762e-7,0.000007974084,0.00027190818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991129,0.00003687601,0.00019887109,0.0002705507,0.00015270003,0.00022811606],"domain_scores_gemma":[0.9962558,0.0028924695,0.00009236967,0.00045021987,0.00025728214,0.000051860443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004578604,0.000116082025,0.00010879247,0.0000659848,0.00034619367,0.000268189,0.00066878216,0.00003897123,0.000005738479],"category_scores_gemma":[0.0045347856,0.00007575552,0.00004216335,0.0005774542,0.00005121012,0.00033319608,0.00016037076,0.000091853726,0.000013779133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024146495,0.000041199164,0.012010706,0.000031487987,0.000031194035,0.0000014928045,0.00063159305,0.00088134944,0.008204262,0.004705063,0.16235194,0.8111073],"study_design_scores_gemma":[0.00012272573,0.00016448437,0.0037900931,0.00010031425,0.000020980651,0.000028610497,0.000016550019,0.9468437,0.011768565,0.025091251,0.011784255,0.00026847413],"about_ca_topic_score_codex":0.00015108837,"about_ca_topic_score_gemma":0.000012473087,"teacher_disagreement_score":0.94596237,"about_ca_system_score_codex":0.000029170018,"about_ca_system_score_gemma":0.00006865493,"threshold_uncertainty_score":0.54288894},"labels":[],"label_agreement":null},{"id":"W2104838677","doi":"10.1002/spe.1017","title":"Grammar‐based test generation with YouGen","year":2010,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Parsing; Grammar; Natural language processing; Compiler; Rule-based machine translation; Programming language; Artificial intelligence; Generator (circuit theory); Context (archaeology); Linguistics; Power (physics)","score_opus":0.01713707136432013,"score_gpt":0.2785418352168769,"score_spread":0.2614047638525568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104838677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05146594,0.00007893929,0.9411528,0.0013705645,0.00023341166,0.0001495097,0.0000013433036,0.0052315528,0.00031590855],"genre_scores_gemma":[0.48035485,0.0000055285423,0.5184958,0.0009974217,0.00006236153,0.00005180592,0.0000021046362,0.0000076112656,0.000022486256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988508,0.00003585339,0.00013912185,0.00045458635,0.0002737198,0.00024592038],"domain_scores_gemma":[0.99788755,0.001047677,0.00012111077,0.00061286177,0.00020675392,0.0001240582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030227183,0.0001537939,0.00010706984,0.00006415628,0.00030846204,0.00038623827,0.00041534854,0.00007454477,0.000007271437],"category_scores_gemma":[0.004186609,0.00012480577,0.000017808377,0.00031100292,0.00013047949,0.001423741,0.000108879,0.0002622458,0.00001147222],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009877362,0.0010448297,0.18227617,0.00007810337,0.00003573206,0.00055587786,0.022429746,0.000059142632,0.024981663,0.011534682,0.0146725895,0.7422327],"study_design_scores_gemma":[0.0054072873,0.0074340575,0.032042176,0.0005166905,0.00024744438,0.010802861,0.0014905316,0.31216452,0.19216786,0.03222683,0.39737046,0.008129275],"about_ca_topic_score_codex":0.00016517712,"about_ca_topic_score_gemma":0.000020095376,"teacher_disagreement_score":0.73410344,"about_ca_system_score_codex":0.000010480696,"about_ca_system_score_gemma":0.00011053318,"threshold_uncertainty_score":0.50894314},"labels":[],"label_agreement":null},{"id":"W2105248826","doi":"10.1109/taicpart.2009.34","title":"Grammar Based Testing of HTML Injection Vulnerabilities in RSS Feeds","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Programming language; XML; Markup language; Rule-based machine translation; Compiler; Code generation; Grammar; Parsing; XHTML; Context (archaeology); Context-free grammar; Syntax; Natural language processing; World Wide Web; Linguistics; Operating system","score_opus":0.028703708936654335,"score_gpt":0.26302400084314165,"score_spread":0.23432029190648732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105248826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16798685,0.000025319374,0.81759894,0.00047799255,0.000090900736,0.00012187708,3.1325894e-7,0.008100929,0.0055968664],"genre_scores_gemma":[0.6403282,1.2787935e-7,0.35943088,0.00018986115,0.000010616196,0.000003576653,2.9307253e-7,0.0000022349275,0.000034186152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991801,0.00005784057,0.00022959893,0.00020746395,0.00015453192,0.00017048023],"domain_scores_gemma":[0.998908,0.00056330673,0.00006438378,0.00034066566,0.00009432443,0.000029351311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005220335,0.00008793106,0.0001293523,0.00021645617,0.000043274053,0.000043210457,0.0003149656,0.000046171415,0.0000033541921],"category_scores_gemma":[0.0010272496,0.00007962787,0.000028557559,0.00072743825,0.00002740748,0.00019070687,0.00003836981,0.00010341067,0.0000014019813],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013619383,0.00043043224,0.36851695,0.000065239845,0.0000037303798,0.000014532819,0.00088417873,0.0024628437,0.0020500699,0.016093154,0.0041188584,0.6053464],"study_design_scores_gemma":[0.00041692058,0.0011717244,0.106798775,0.0002106966,0.0000029044952,0.000025153133,0.000018002462,0.5711723,0.020468548,0.29930058,0.00007061447,0.00034375975],"about_ca_topic_score_codex":0.00072154845,"about_ca_topic_score_gemma":0.000017223694,"teacher_disagreement_score":0.60500264,"about_ca_system_score_codex":0.000037854203,"about_ca_system_score_gemma":0.000058210717,"threshold_uncertainty_score":0.32471302},"labels":[],"label_agreement":null},{"id":"W2105821857","doi":"10.1145/566171.566183","title":"Investigating the use of analysis contracts to support fault isolation in object oriented code","year":2002,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Isolation (microbiology); Computer science; Precondition; Design by contract; Software engineering; Reuse; Object-oriented programming; Software; Instrumentation (computer programming); Code (set theory); Object (grammar); Code reuse; Fault detection and isolation; Reliability engineering; Risk analysis (engineering); Programming language; Software system; Engineering; Software construction; Set (abstract data type); Artificial intelligence","score_opus":0.058524941554268906,"score_gpt":0.2645884942805956,"score_spread":0.2060635527263267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105821857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34518015,0.00005562968,0.650466,0.00033189438,0.00010762939,0.0002186687,0.000012372924,0.0036267827,8.4433816e-7],"genre_scores_gemma":[0.6207497,0.0000026642722,0.3789527,0.0002230334,0.00001714437,0.000025256903,0.000006700449,0.000015136495,0.000007621905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982849,0.00005806359,0.00050211156,0.00041663897,0.00035641209,0.00038192514],"domain_scores_gemma":[0.95669544,0.04151729,0.00018689048,0.0012728493,0.00019319178,0.0001343119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00044576268,0.0002345738,0.00035408558,0.000555594,0.00008268805,0.00012665025,0.0008992489,0.000099043216,0.000009364138],"category_scores_gemma":[0.20693517,0.00020304981,0.00011427866,0.0027759273,0.000033453947,0.0004617983,0.00032059057,0.00025239604,0.000008918428],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001815249,0.00005028855,0.90318054,0.000028368026,0.00007284507,0.000011207465,0.0023150377,0.08051827,0.0008071624,0.0001560047,0.001321896,0.011536583],"study_design_scores_gemma":[0.00035016864,0.00024666375,0.53997403,0.00027539858,0.00011523367,0.00001904862,0.000005560722,0.45184556,0.005059356,0.00019781438,0.0012286239,0.000682539],"about_ca_topic_score_codex":0.0003223195,"about_ca_topic_score_gemma":0.00004550524,"teacher_disagreement_score":0.3713273,"about_ca_system_score_codex":0.000063507,"about_ca_system_score_gemma":0.000026630862,"threshold_uncertainty_score":0.8280131},"labels":[],"label_agreement":null},{"id":"W2106072155","doi":"10.1145/2568225.2568271","title":"Coverage is not strongly correlated with test suite effectiveness","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":398,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Test suite; Suite; Computer science; Proxy (statistics); Test (biology); Confounding; Test case; Statistics; Data mining; Machine learning; Mathematics; Regression analysis; Geology; Geography","score_opus":0.008925411068723877,"score_gpt":0.22585647833183997,"score_spread":0.2169310672631161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106072155","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04433278,0.0000050996296,0.94028234,0.0001525712,0.00008539899,0.00013828512,0.0000014309624,0.010462347,0.0045397356],"genre_scores_gemma":[0.93259454,6.0079515e-7,0.06644562,0.00056809373,0.000019799243,0.000015121234,0.0000013220803,0.000012444587,0.00034244655],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989675,0.00007549429,0.000113978815,0.0003755177,0.00022431696,0.00024313587],"domain_scores_gemma":[0.99745274,0.0016979311,0.000058363472,0.00060922996,0.00010449258,0.00007723255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004132118,0.00015068661,0.00016353626,0.000069374924,0.00010273221,0.00015409032,0.0005177393,0.000058878082,0.000012112603],"category_scores_gemma":[0.0003361534,0.00011052255,0.000031116855,0.00031455889,0.000040423965,0.00022656059,0.00013705583,0.00013597378,0.00006890502],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009665208,0.00047703678,0.7536665,0.00013113783,0.00007387555,0.00007403986,0.00071599014,0.00068952324,0.0014854684,0.033552717,0.03380033,0.1752367],"study_design_scores_gemma":[0.0024693822,0.0032213829,0.4012133,0.0004887831,0.000033355715,0.00021731638,0.0000021458739,0.51588964,0.044861715,0.025795016,0.0044646678,0.0013432974],"about_ca_topic_score_codex":0.00015346128,"about_ca_topic_score_gemma":0.0000034547827,"teacher_disagreement_score":0.8882618,"about_ca_system_score_codex":0.0000299135,"about_ca_system_score_gemma":0.000035918016,"threshold_uncertainty_score":0.4506979},"labels":[],"label_agreement":null},{"id":"W2106459722","doi":"10.48550/arxiv.1212.4123","title":"An Interactive Graph-Based Automation Assistant: A Case Study to Manage the GIPSY's Distributed Multi-tier Run-Time System","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Component (thermodynamics); Distributed computing; Graph; Interconnection; Computer network; Theoretical computer science","score_opus":0.0529443423079787,"score_gpt":0.2240369309263044,"score_spread":0.17109258861832569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106459722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4459616,0.0000029750267,0.5501272,0.000018799601,0.00008951663,0.00031921358,0.000008351632,0.003435717,0.000036658374],"genre_scores_gemma":[0.9890151,1.0723866e-7,0.010822543,0.00007080859,0.000024723817,0.000005034225,0.000005953141,0.0000130866365,0.000042642634],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851894,0.00040407426,0.00015926312,0.00047555316,0.00010479849,0.0003373859],"domain_scores_gemma":[0.99815387,0.00030630917,0.00014359687,0.0010445688,0.0001428038,0.00020883637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061358366,0.00019850527,0.00017575837,0.0002494611,0.00041417227,0.00015511675,0.0008607715,0.00004877121,0.0000036370302],"category_scores_gemma":[0.00007756666,0.000169575,0.000076486736,0.0012478348,0.000045991448,0.00083100016,0.00022117354,0.00015488095,0.000055596403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074562023,0.019588742,0.6875118,0.00037995668,0.0011888618,0.03920143,0.0763533,0.09138416,0.00061012805,0.054722764,0.011198528,0.017114727],"study_design_scores_gemma":[0.0005785504,0.0003108607,0.018811034,0.000065017106,0.00007520447,0.00017168566,0.0016408169,0.9775862,0.000093655246,0.0002620029,0.00005572888,0.0003492625],"about_ca_topic_score_codex":0.00070611737,"about_ca_topic_score_gemma":0.00004727928,"teacher_disagreement_score":0.88620204,"about_ca_system_score_codex":0.00024605246,"about_ca_system_score_gemma":0.000026098227,"threshold_uncertainty_score":0.69150674},"labels":[],"label_agreement":null},{"id":"W2106516749","doi":"10.1109/icdcs.1993.287712","title":"Diagnosis of single transition faults in communicating finite state machines","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Set (abstract data type); Fault (geology); State (computer science); Computer science; Finite-state machine; Simple (philosophy); Finite set; Algorithm; Transition system; Transfer (computing); Transition (genetics); Theoretical computer science; Mathematics; Programming language; Parallel computing","score_opus":0.04608729495696682,"score_gpt":0.2611216801873201,"score_spread":0.21503438523035331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106516749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32159817,0.00042252685,0.6656015,0.0019216673,0.00005485817,0.00017916055,0.0000046136283,0.006225531,0.0039919815],"genre_scores_gemma":[0.77601206,0.000034515742,0.22374684,0.00016664485,0.0000027783724,0.00001276799,8.195667e-7,0.0000038100095,0.000019766841],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993471,0.00007133853,0.0002175863,0.00013746056,0.00010385715,0.00012265325],"domain_scores_gemma":[0.99868745,0.00076190394,0.00006414427,0.00042830448,0.000035587807,0.00002259309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002046462,0.00007025101,0.000116481606,0.000111496156,0.000036115445,0.000022507042,0.00045323573,0.000024540404,0.000013415429],"category_scores_gemma":[0.00019884566,0.00006440608,0.000028396478,0.00033594313,0.000027575634,0.0001867115,0.000087226595,0.000077167184,0.0000048054662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037656955,0.0007943989,0.05135268,0.000069950256,0.000008503466,0.000027029715,0.012555933,0.0015060047,0.00046119592,0.0006820333,0.0037376566,0.9288008],"study_design_scores_gemma":[0.00031218847,0.00016614795,0.00486443,0.00028164865,0.000002411776,0.000011971902,0.00000811542,0.96111125,0.007112756,0.025766287,0.00014120241,0.00022159347],"about_ca_topic_score_codex":0.0005757888,"about_ca_topic_score_gemma":0.00006560329,"teacher_disagreement_score":0.9596052,"about_ca_system_score_codex":0.000014263908,"about_ca_system_score_gemma":0.000002920116,"threshold_uncertainty_score":0.26264036},"labels":[],"label_agreement":null},{"id":"W2107915643","doi":"10.1109/tse.2013.20","title":"Whitening SOA Testing via Event Exposure","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Service (business); Event (particle physics); Service provider; Information leakage; Implementation; Reliability engineering; Test (biology); Leakage (economics); Embedded system; Real-time computing; Computer security; Software engineering; Engineering","score_opus":0.01368091417226672,"score_gpt":0.2104804074451601,"score_spread":0.1967994932728934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107915643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0089212,0.000051241168,0.9679184,0.00005805695,0.00070133974,0.00021591972,0.0000016670341,0.022108048,0.000024102947],"genre_scores_gemma":[0.5407694,0.0000011934638,0.45892203,0.00007491329,0.000037477024,0.00011296919,3.5937015e-7,0.00002859798,0.000053095213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984296,0.000025217896,0.00032068323,0.00045088856,0.0003083632,0.0004652781],"domain_scores_gemma":[0.99832916,0.00065661623,0.00006666555,0.0006296579,0.00015155168,0.00016636183],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019054658,0.0002855054,0.00021183059,0.00028779826,0.00022538145,0.00019971225,0.0005702791,0.000113567236,0.000026464255],"category_scores_gemma":[0.00016375465,0.00029500143,0.00011209611,0.00070440467,0.000017260436,0.000592167,0.000007872244,0.00042814793,0.00012383377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029507032,0.00018047224,0.0015322074,0.0001088519,0.00007256316,0.000038978425,0.0006916134,0.3683423,0.00424746,0.00007326303,0.0015699944,0.6231393],"study_design_scores_gemma":[0.0004221016,0.00039222382,0.004319818,0.00054896536,0.000026075759,0.0002555529,0.0000071691547,0.97284,0.018320836,0.0015096436,0.00026101226,0.0010965714],"about_ca_topic_score_codex":0.00009722731,"about_ca_topic_score_gemma":9.506563e-7,"teacher_disagreement_score":0.6220428,"about_ca_system_score_codex":0.00009579642,"about_ca_system_score_gemma":0.00003625734,"threshold_uncertainty_score":0.99995023},"labels":[],"label_agreement":null},{"id":"W2108367239","doi":"10.1109/hicss.2001.927256","title":"A GUI environment to manipulate FSMs tor testing GUI-based applications in Java","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Java; Graphical user interface; Graphical user interface testing; Programming language; Finite-state machine; Test harness; Representation (politics); Test case; User interface; Software; Software development; User interface design","score_opus":0.03889308573504678,"score_gpt":0.26567195299195556,"score_spread":0.22677886725690877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108367239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006997439,0.000020277243,0.9832077,0.0016909757,0.000017990784,0.0003352975,6.826507e-7,0.0052095377,0.002520122],"genre_scores_gemma":[0.35661,3.0221187e-7,0.64208263,0.0009765397,0.000032178883,0.00012776295,0.0000010402715,0.0000073693636,0.00016217644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998893,0.000023971306,0.00024034375,0.00039530642,0.00018232065,0.00026504498],"domain_scores_gemma":[0.998835,0.0002929721,0.000047151683,0.00069905276,0.000022655666,0.00010315021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028722512,0.00012667158,0.000110511195,0.00014436188,0.0000806965,0.00007809721,0.0006545321,0.00004058438,0.000018285125],"category_scores_gemma":[0.00015458427,0.000117440206,0.000026837586,0.00038906452,0.000015012954,0.00011084465,0.00020924337,0.00007896219,0.00018294065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005830817,0.0007638887,0.13692743,0.000034802113,0.000009972647,0.000022693454,0.00078005006,0.038309462,0.0031878848,0.011868263,0.02862414,0.7794656],"study_design_scores_gemma":[0.0004755243,0.00024594046,0.05677348,0.0001260538,0.000007106603,0.000017145117,0.0000070722003,0.8561764,0.009888225,0.018562807,0.056841157,0.0008791296],"about_ca_topic_score_codex":0.00020081572,"about_ca_topic_score_gemma":0.000017795428,"teacher_disagreement_score":0.8178669,"about_ca_system_score_codex":0.00012426368,"about_ca_system_score_gemma":0.000031751828,"threshold_uncertainty_score":0.47890726},"labels":[],"label_agreement":null},{"id":"W2109277099","doi":"10.1145/2634273","title":"Example-based learning in computer-aided STEM education","year":2014,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ryerson University","keywords":"Computer science; Artificial intelligence; Programming language; Software engineering; Human–computer interaction","score_opus":0.060816836911792134,"score_gpt":0.2971825875912495,"score_spread":0.23636575067945736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109277099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05934882,0.00038696575,0.89255834,0.040996294,0.000320115,0.00041850703,5.139104e-7,0.0042435694,0.0017268892],"genre_scores_gemma":[0.5176248,0.0000029859189,0.48213404,0.00019102334,0.000006589309,0.000017518852,0.0000012326817,0.0000033851077,0.000018431387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897873,0.00049323076,0.00019992952,0.00013307961,0.00010245869,0.000092544695],"domain_scores_gemma":[0.97894,0.0015424746,0.00015252519,0.019248119,0.000096406584,0.000020450967],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00086109305,0.00006384717,0.00009893722,0.000101941085,0.00015019818,0.00004014891,0.020437006,0.000031656105,4.1399437e-7],"category_scores_gemma":[0.0040039956,0.000053577045,0.00004042962,0.00042498813,0.00007249135,0.00009329652,0.0077525843,0.00018595732,0.0000043275763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005772167,0.0006850908,0.2197839,0.000065683744,0.000011735328,8.153025e-8,0.0016682965,0.0049442514,0.00045108522,0.0865754,0.04504704,0.6407617],"study_design_scores_gemma":[0.00026793688,0.00008235868,0.082720466,0.0004217807,0.0000063654925,0.0000045106667,0.00000931503,0.46707016,0.001377061,0.43840152,0.009437427,0.00020110828],"about_ca_topic_score_codex":0.00026479003,"about_ca_topic_score_gemma":0.000021470665,"teacher_disagreement_score":0.64056057,"about_ca_system_score_codex":0.00003445319,"about_ca_system_score_gemma":0.00011923734,"threshold_uncertainty_score":0.9848629},"labels":[],"label_agreement":null},{"id":"W2109780335","doi":"10.1109/infcom.1993.253291","title":"Multiple fault diagnosis for finite state machines","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Chinese Academy of Agricultural Sciences","keywords":"Independence (probability theory); Fault (geology); Computer science; Medical diagnosis; Set (abstract data type); State (computer science); Finite-state machine; Algorithm; Reduction (mathematics); Finite set; Simple (philosophy); Theoretical computer science; Mathematics; Programming language","score_opus":0.04364514317896535,"score_gpt":0.2684246354416706,"score_spread":0.22477949226270527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109780335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025391157,0.0001105389,0.9833048,0.001021381,0.00013708672,0.00018141193,0.000007356126,0.011889005,0.0008093336],"genre_scores_gemma":[0.3786699,0.000024831344,0.6189728,0.00082604046,0.000030494208,0.00017940335,0.0000014408697,0.000009514992,0.0012855944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925196,0.000017430291,0.00013863944,0.00026307782,0.00010918656,0.0002197199],"domain_scores_gemma":[0.9978089,0.0016315631,0.00004148861,0.00039236486,0.000067393376,0.00005833641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013349457,0.000104316234,0.0001031793,0.00007135339,0.00010895143,0.0001193971,0.00049034914,0.00002878661,0.000029789362],"category_scores_gemma":[0.0009245745,0.00008479389,0.000057958987,0.0001767593,0.000017671677,0.00019235596,0.00011537451,0.00005015031,0.000050705185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020817595,0.0001229203,0.040524572,0.000021368654,0.000010377117,0.00001161948,0.00048712513,0.0001976193,0.0000107388905,0.0011504078,0.36134174,0.5961194],"study_design_scores_gemma":[0.00021867784,0.00009237148,0.00065856695,0.000017410503,0.0000020936925,0.000006485577,4.5323924e-7,0.947848,0.00096112577,0.034719057,0.0152988415,0.0001769126],"about_ca_topic_score_codex":0.00011805605,"about_ca_topic_score_gemma":0.000015370688,"teacher_disagreement_score":0.9476504,"about_ca_system_score_codex":0.000011116069,"about_ca_system_score_gemma":0.0000042233896,"threshold_uncertainty_score":0.34577948},"labels":[],"label_agreement":null},{"id":"W2110029287","doi":"10.1109/ecbs.2005.64","title":"Synthesis of C++ Software from Verifiable CSPm Specifications","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Programming language; Formalism (music); Software; Source code; Verifiable secret sharing; Object-oriented programming; Embedded system; Software engineering; Set (abstract data type)","score_opus":0.03881680567377979,"score_gpt":0.24617205225903752,"score_spread":0.20735524658525772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110029287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028004337,0.00008349537,0.98158926,0.0007295388,0.00005646571,0.000054395863,0.000007634318,0.0076275044,0.0070512504],"genre_scores_gemma":[0.31585997,0.000006151203,0.68374795,0.000101107864,0.000038774717,0.00001231658,0.0000012411344,0.0000046582168,0.00022781466],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992893,0.000020498803,0.00018101286,0.0002270446,0.00015204659,0.00013009581],"domain_scores_gemma":[0.99837315,0.00069120165,0.00006546939,0.00075263035,0.00007120378,0.000046368357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012344684,0.00007632725,0.0001191695,0.00006904341,0.000057228455,0.000043900167,0.00068037945,0.00003999133,0.00009306084],"category_scores_gemma":[0.00048499374,0.000069084934,0.000043444656,0.00022911288,0.000031632862,0.00022405546,0.00011037818,0.000050045288,0.00008094641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038803882,0.0002770697,0.013053478,0.000012775359,0.000031661682,0.000002989487,0.00040833454,0.00019454402,0.001064165,0.025980001,0.24029596,0.71867514],"study_design_scores_gemma":[0.00034011094,0.00011465536,0.03358759,0.0002637351,0.000039848368,0.000017977194,0.000022669294,0.087214254,0.57035697,0.21136376,0.09566183,0.0010166198],"about_ca_topic_score_codex":0.00028913727,"about_ca_topic_score_gemma":0.000007025451,"teacher_disagreement_score":0.7176585,"about_ca_system_score_codex":0.000022484797,"about_ca_system_score_gemma":0.0000374203,"threshold_uncertainty_score":0.2817202},"labels":[],"label_agreement":null},{"id":"W2111389084","doi":"10.1109/icc.1996.542187","title":"A test generation tool for specifications in the form of state machines","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Identification (biology); Finite-state machine; Automatic test pattern generation; Heuristic; Minification; Programming language; Test (biology); State (computer science); Test case; Software; Formal specification; Software engineering; Artificial intelligence; Engineering; Machine learning","score_opus":0.10686634083161822,"score_gpt":0.281313890728613,"score_spread":0.1744475498969948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111389084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012462172,0.000026125821,0.98405397,0.0015302858,0.000027993847,0.00021770362,0.000003167282,0.0007853269,0.0008932854],"genre_scores_gemma":[0.63851947,0.000005492709,0.36100584,0.00018803583,0.000020845398,0.00005518205,0.0000013756537,0.0000019952313,0.0002017502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961436,0.000011610905,0.00013129685,0.00009719221,0.00007351835,0.000072003575],"domain_scores_gemma":[0.9991709,0.0004551336,0.000038104426,0.00028424393,0.000045248486,0.000006352651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023534575,0.00003909423,0.000045004275,0.000049142047,0.00004457289,0.000045444704,0.00031459852,0.000011139697,0.000005068256],"category_scores_gemma":[0.00027874598,0.000025074076,0.000019481258,0.00019285406,0.00001157981,0.00011905926,0.000020203519,0.000025296154,0.0000026803123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017479229,0.0005614419,0.03099185,0.00003117188,0.0000055055,0.0000018327665,0.008120277,0.00009687908,0.0029161747,0.096168295,0.30756184,0.553543],"study_design_scores_gemma":[0.000117709315,0.00009132275,0.0067036776,0.0000074394447,0.0000013271343,0.0000064169853,0.0000027234184,0.90057206,0.0021259957,0.08907894,0.0012149211,0.00007747729],"about_ca_topic_score_codex":0.000030769297,"about_ca_topic_score_gemma":0.00002785863,"teacher_disagreement_score":0.90047514,"about_ca_system_score_codex":0.000007378929,"about_ca_system_score_gemma":0.0000051382053,"threshold_uncertainty_score":0.102249116},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"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","score_opus":0.04516024558319632,"score_gpt":0.25357394988629844,"score_spread":0.20841370430310213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111584600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090549774,0.000049612332,0.8972841,0.00018308325,0.00010752066,0.00053192227,0.000008930456,0.010986928,0.00029814022],"genre_scores_gemma":[0.47337148,0.000003107327,0.5263883,0.00009615089,0.000015383539,0.000076873635,0.0000044211783,0.00001359803,0.000030689],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99844545,0.000056993096,0.00029059686,0.00073439995,0.00018151289,0.00029102273],"domain_scores_gemma":[0.9950766,0.0033433703,0.00018554128,0.0008974437,0.00037549902,0.00012155132],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009024243,0.0002079537,0.00018568126,0.00008255292,0.00034507614,0.00009825994,0.00039291842,0.00008361241,0.000002647087],"category_scores_gemma":[0.0084015615,0.00016298954,0.00003429518,0.00035545928,0.00016536728,0.00022571425,0.000064685424,0.00017057738,0.0000043782893],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001802217,0.0015033619,0.36240864,0.00077054097,0.0000318474,0.000012116967,0.0074775824,0.0004601003,0.00041875162,0.00894751,0.006991797,0.6107975],"study_design_scores_gemma":[0.001380897,0.0046967454,0.38658276,0.0010885539,0.000061680636,0.00011713521,0.000054643457,0.10468331,0.0062984596,0.49275807,0.00069672824,0.0015810237],"about_ca_topic_score_codex":0.00019462156,"about_ca_topic_score_gemma":0.0000014272562,"teacher_disagreement_score":0.6092165,"about_ca_system_score_codex":0.000050453356,"about_ca_system_score_gemma":0.00008996765,"threshold_uncertainty_score":0.99995106},"labels":[],"label_agreement":null},{"id":"W2112227385","doi":"10.1109/qsic.2009.30","title":"A Survey of Model-Driven Testing Techniques","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Model-based testing; Non-regression testing; Software reliability testing; Software performance testing; Software engineering; Development testing; Model-driven architecture; Time to market; Software quality; Model-based design; Software development; Software; Reliability engineering; Software construction; Test case; Machine learning; Simulation; Programming language; Engineering","score_opus":0.09180422079795124,"score_gpt":0.3117430841271335,"score_spread":0.21993886332918222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112227385","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036944838,0.000017138462,0.97448635,0.000114566195,0.00001187596,0.0000788388,0.0000011101757,0.014264048,0.0073315618],"genre_scores_gemma":[0.4950365,6.231263e-7,0.5047642,0.00016148693,0.0000035757998,0.0000018967862,4.9643694e-7,0.0000023197674,0.00002889213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919325,0.000044001692,0.00020868823,0.0002241865,0.00016417979,0.00016569422],"domain_scores_gemma":[0.9987631,0.00034623218,0.00008759049,0.00048919965,0.00027078332,0.00004311258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005154515,0.00009415627,0.00014819662,0.000102074126,0.000042251875,0.000038856382,0.0006673105,0.000048104597,8.7237396e-7],"category_scores_gemma":[0.0008922098,0.00008082939,0.000025740408,0.0005428838,0.000022618386,0.0001790557,0.000104902,0.00007546375,0.0000019195452],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040007963,0.0001802027,0.049952313,0.000012823359,0.000006067351,0.0000074215263,0.00021570595,0.000550844,0.004060599,0.01516987,0.020896314,0.90894383],"study_design_scores_gemma":[0.00003880282,0.00019682132,0.036710802,0.000049889248,0.0000013230687,0.000008395413,1.8252248e-7,0.89134437,0.011995698,0.05949776,0.000008783771,0.00014714895],"about_ca_topic_score_codex":0.00038343004,"about_ca_topic_score_gemma":0.0000065900954,"teacher_disagreement_score":0.90879667,"about_ca_system_score_codex":0.000013660724,"about_ca_system_score_gemma":0.00006265209,"threshold_uncertainty_score":0.3296127},"labels":[],"label_agreement":null},{"id":"W2113570371","doi":"10.1109/ccece.2005.1557280","title":"A framework for testing distributed software components","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Component-based software engineering; Software construction; System integration testing; White-box testing; Software reliability testing; Software engineering; Common Object Request Broker Architecture; Test harness; Component (thermodynamics); Regression testing; Embedded system; Software development; Operating system; Software","score_opus":0.05397499011663072,"score_gpt":0.2871375926077368,"score_spread":0.2331626024911061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113570371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019118786,0.00002809127,0.9733324,0.00028878218,0.00013089277,0.0001803105,0.0000117227255,0.02392617,0.00018973976],"genre_scores_gemma":[0.21513787,8.664819e-8,0.7844715,0.00019806772,0.000074458774,0.000043734944,0.000020292888,0.000009481816,0.00004449236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990064,0.000017524355,0.00019666,0.0003182952,0.00015569953,0.00030542206],"domain_scores_gemma":[0.9974037,0.0018724585,0.00007836396,0.0004452359,0.00015061583,0.0000496514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001876711,0.00012705599,0.0001336748,0.000056044788,0.00018957291,0.00016538352,0.0005960732,0.00007453131,0.0000021820917],"category_scores_gemma":[0.0017354039,0.00011430422,0.00005309682,0.00039449678,0.000025411366,0.00014570632,0.00016165523,0.000093026545,0.000010968515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012643533,0.0004335823,0.18758205,0.00010235395,0.000023433915,0.00003098991,0.0000770967,0.00041724514,0.00043719547,0.46990648,0.22796965,0.1130073],"study_design_scores_gemma":[0.00013302201,0.00006185901,0.013470227,0.00007964203,0.0000034754328,0.000016382131,4.5177603e-7,0.06140495,0.0005925506,0.9226555,0.0013725299,0.00020939248],"about_ca_topic_score_codex":0.00021966247,"about_ca_topic_score_gemma":0.0000016257793,"teacher_disagreement_score":0.45274904,"about_ca_system_score_codex":0.000031942538,"about_ca_system_score_gemma":0.000026414467,"threshold_uncertainty_score":0.46611908},"labels":[],"label_agreement":null},{"id":"W2114754963","doi":"10.1109/csmr.2002.995799","title":"C to Java migration experiences","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Java; Computer science; Popularity; Real time Java; Source code; Programming language; Java annotation; Generics in Java; strictfp; Operating system; Software engineering","score_opus":0.022324955203872916,"score_gpt":0.27007970476720605,"score_spread":0.24775474956333313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114754963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040255405,0.000014385149,0.94199467,0.0004555064,0.00012638315,0.000048033744,2.140038e-8,0.006236697,0.010868892],"genre_scores_gemma":[0.5427955,3.1411665e-7,0.45630613,0.00058587454,0.0000055078917,0.000021786676,4.5965933e-8,0.0000012386923,0.00028363074],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99954164,0.000022085667,0.00006874913,0.00016141478,0.000101667094,0.00010443937],"domain_scores_gemma":[0.9995954,0.000059621605,0.000012335768,0.00025160526,0.000030496229,0.000050520383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014819358,0.000045752713,0.00004035292,0.000048451664,0.00005396201,0.000087821674,0.00025493067,0.000015898291,0.000020472597],"category_scores_gemma":[0.00028251525,0.00003682124,0.000013191731,0.0002477169,0.000007665812,0.00014423164,0.000031294498,0.0000201465,0.00006143404],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014915003,0.00009161983,0.01652376,0.0000049742866,0.000004364211,0.00001182485,0.027334092,0.00003160083,0.0009010985,0.33249766,0.52830005,0.09429748],"study_design_scores_gemma":[0.00035596115,0.0009781832,0.0050801937,0.00008752129,0.000004565114,0.00015716311,0.0010368167,0.03402975,0.3439771,0.37832776,0.23441462,0.0015503715],"about_ca_topic_score_codex":0.000046478817,"about_ca_topic_score_gemma":0.000006256541,"teacher_disagreement_score":0.50254005,"about_ca_system_score_codex":0.000008540509,"about_ca_system_score_gemma":0.0000183849,"threshold_uncertainty_score":0.15015265},"labels":[],"label_agreement":null},{"id":"W2114770958","doi":"10.1109/qsic.2007.4385506","title":"An Approach to Integration Testing of Object-Oriented Programs","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture; McMaster University","keywords":"Computer science; Unified Modeling Language; Programming language; Reuse; Object-oriented programming; Test case; Implementation; Software engineering; Object (grammar); Design by contract; Class (philosophy); Component (thermodynamics); Software; Software development; Artificial intelligence; Software construction; Machine learning; Engineering","score_opus":0.04465164295369334,"score_gpt":0.2977340877581621,"score_spread":0.2530824448044688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114770958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030650703,0.0000031935654,0.94941837,0.0000152502525,0.0000506139,0.00018012713,1.0093745e-7,0.008280123,0.011401531],"genre_scores_gemma":[0.4897183,1.9703855e-8,0.51018703,0.000054013588,0.000013524499,0.0000063095326,0.0000014812075,0.0000031875961,0.000016150723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991067,0.000022019743,0.00021121201,0.0002653751,0.00019691058,0.00019774916],"domain_scores_gemma":[0.99904597,0.00013317975,0.00006275575,0.00044418187,0.00022047,0.00009345942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082735525,0.00008515949,0.00009699875,0.00014301979,0.0000498312,0.00005432421,0.00043499458,0.000039548668,3.7053857e-7],"category_scores_gemma":[0.0004608932,0.000069274065,0.00002024718,0.0010014815,0.000020343952,0.00021019134,0.000077686804,0.000068395435,0.0000024345345],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003837772,0.0002751797,0.02032406,0.0000071822333,0.0000023012847,0.0000013647689,0.0010466749,0.000014271004,0.002487515,0.0197917,0.00036978268,0.95567614],"study_design_scores_gemma":[0.00044528113,0.002902239,0.060291998,0.0002901775,0.000012186495,0.00010727549,0.00028820196,0.68086475,0.22436194,0.029076962,0.00042035183,0.00093862496],"about_ca_topic_score_codex":0.00027069234,"about_ca_topic_score_gemma":0.0000068787776,"teacher_disagreement_score":0.9547375,"about_ca_system_score_codex":0.000021761649,"about_ca_system_score_gemma":0.00002646711,"threshold_uncertainty_score":0.28249142},"labels":[],"label_agreement":null},{"id":"W2115479429","doi":"10.1109/issre.2010.39","title":"On the Round Trip Path Testing Strategy","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tree traversal; Traverse; Computer science; Graph traversal; Tree (set theory); State (computer science); Path (computing); Graph; Algorithm; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.04982608621260986,"score_gpt":0.26784749314140166,"score_spread":0.2180214069287918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115479429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2138274,0.000010381438,0.65115064,0.0021240981,0.00050951255,0.00022176445,6.187986e-7,0.026220007,0.10593556],"genre_scores_gemma":[0.82252157,1.2389579e-7,0.17626798,0.0008311292,0.000048386624,0.000009749282,1.3631987e-7,0.0000049437567,0.00031597985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993144,0.000029558376,0.00010294793,0.00021220381,0.00016210848,0.00017876687],"domain_scores_gemma":[0.99741966,0.0017984032,0.00004255238,0.0006351294,0.0000618177,0.00004245023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005033021,0.00008744717,0.000061701576,0.00003388249,0.00017574053,0.00027750636,0.00077004463,0.00004110703,0.000022503016],"category_scores_gemma":[0.0014377577,0.000049799255,0.000023979957,0.00027285848,0.00003309866,0.00011838012,0.00010601319,0.00027442118,0.00005373542],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011917233,0.000061218554,0.0022325728,0.0000028400689,0.0000036812303,0.000014959323,0.000097566866,0.000014764782,0.001443196,0.7701903,0.061926797,0.16401091],"study_design_scores_gemma":[0.00009360085,0.00024092487,0.0042152894,0.000025189449,0.000001973461,0.000053644686,0.000003952576,0.10761324,0.0025765754,0.8842295,0.0007256273,0.00022048109],"about_ca_topic_score_codex":0.00013540109,"about_ca_topic_score_gemma":0.0000071584636,"teacher_disagreement_score":0.6086942,"about_ca_system_score_codex":0.0000066642106,"about_ca_system_score_gemma":0.000049470033,"threshold_uncertainty_score":0.26760003},"labels":[],"label_agreement":null},{"id":"W2115962949","doi":"10.1109/hldvt.2009.5340166","title":"Airwolf-TG: A test generator for assertion-based dynamic verification","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; CMC Microsystems (Canada)","funders":"","keywords":"Assertion; Computer science; Automaton; Generator (circuit theory); Test (biology); Programming language; Key (lock); Test case; Software engineering; Theoretical computer science; Machine learning; Operating system","score_opus":0.014793360935907794,"score_gpt":0.27825829845436,"score_spread":0.26346493751845224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115962949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024946735,0.000025098563,0.9841509,0.0026117433,0.000077470955,0.00020420604,0.0000017026522,0.010102184,0.00033202645],"genre_scores_gemma":[0.5176716,4.5280333e-7,0.4810366,0.0010992619,0.000017592427,0.000035491237,0.0000060518155,0.0000038945673,0.00012907214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925524,0.000013870875,0.00015009742,0.00028987936,0.000118453776,0.000172432],"domain_scores_gemma":[0.998942,0.00033268105,0.00005584514,0.0004885844,0.00012857659,0.000052300195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020814368,0.000096195356,0.000085396685,0.00008096105,0.000118328106,0.0001214763,0.00040790765,0.00005121838,0.0000027565206],"category_scores_gemma":[0.00045416548,0.00008713764,0.00004967072,0.00023557532,0.000010244527,0.00015436848,0.000013017539,0.000043607346,0.0000124059325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018836958,0.00084018137,0.0048437067,0.00004002664,0.000010717895,0.0000057222187,0.00015946278,0.00047218552,0.040135022,0.04224226,0.120849945,0.7903819],"study_design_scores_gemma":[0.00020170653,0.00031544018,0.0056068012,0.00001597543,0.0000035124635,0.0000027803105,5.1824225e-7,0.9498332,0.0130134765,0.029578766,0.0012554,0.00017240776],"about_ca_topic_score_codex":0.000013850656,"about_ca_topic_score_gemma":0.0000035898115,"teacher_disagreement_score":0.949361,"about_ca_system_score_codex":0.000049423223,"about_ca_system_score_gemma":0.00008387179,"threshold_uncertainty_score":0.355337},"labels":[],"label_agreement":null},{"id":"W2115973328","doi":"10.1109/icstw.2014.17","title":"Towards a Taxonomy for Simulink Model Mutations","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Taxonomy (biology); Mutation testing; Mutation; clone (Java method); Programming language; Class (philosophy); Artificial intelligence; Operator (biology); Software engineering; Genetics; Biology; Gene","score_opus":0.0638368369646232,"score_gpt":0.2901242805449788,"score_spread":0.2262874435803556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115973328","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013276747,0.0000036005404,0.9814293,0.0007825731,0.000048854192,0.0001782736,9.492619e-7,0.009025506,0.008398223],"genre_scores_gemma":[0.33244503,1.2748104e-7,0.66651326,0.0006291235,0.000023686689,0.00013546998,0.0000012216713,0.000003808942,0.00024830757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994747,0.000010989423,0.000102498685,0.00019622203,0.00007390135,0.00014170447],"domain_scores_gemma":[0.99919856,0.00029690313,0.000029860872,0.0003370728,0.00008941203,0.000048200054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022414273,0.00006664842,0.000075349235,0.000053071984,0.00008951347,0.00008155255,0.00040061382,0.000031278527,0.0000017945845],"category_scores_gemma":[0.00039168797,0.000057747748,0.00004389371,0.00010159265,0.000016168598,0.00014539323,0.000077080644,0.0000355649,0.0000102809245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018215135,0.00005047525,0.00018813447,0.00001615494,0.0000070223623,3.3462345e-7,0.00019837068,0.0135696,0.000030853833,0.4459757,0.070373915,0.46958762],"study_design_scores_gemma":[0.000067887195,0.000030416515,0.000011508189,0.0000033776735,0.0000014231131,0.0000010710027,3.7006834e-7,0.6938834,0.00029455975,0.30129653,0.004346895,0.00006256035],"about_ca_topic_score_codex":0.000020702077,"about_ca_topic_score_gemma":0.0000015237179,"teacher_disagreement_score":0.6803138,"about_ca_system_score_codex":0.000012416866,"about_ca_system_score_gemma":0.000050846484,"threshold_uncertainty_score":0.23548849},"labels":[],"label_agreement":null},{"id":"W2116368564","doi":"10.1145/1985793.1985870","title":"Automated cross-browser compatibility testing","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compatibility (geochemistry); Computer science; Web browser; Client-side scripting; Emulation; World Wide Web; Backward compatibility; Web-based simulation; Pairwise comparison; Web navigation; Software engineering; Information retrieval; Web page; The Internet; Web API; Operating system; Engineering; Artificial intelligence","score_opus":0.11946833591339981,"score_gpt":0.32342542790760753,"score_spread":0.20395709199420772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116368564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1576886,0.000012119681,0.6194055,0.000030686693,0.00018087342,0.00012481952,5.935973e-7,0.17056994,0.051986832],"genre_scores_gemma":[0.5242279,4.4005805e-8,0.47555664,0.00013810724,0.0000074985924,0.0000045257148,2.4996405e-7,0.0000040612344,0.000060933104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990091,0.000040269722,0.0002130348,0.0003458297,0.00014785142,0.0002439367],"domain_scores_gemma":[0.99866515,0.0002801137,0.00006547882,0.0007273449,0.00018343129,0.000078472665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042339787,0.00011219673,0.000115237934,0.000056770503,0.00012804237,0.00011948594,0.0007575767,0.000049254788,0.000038767725],"category_scores_gemma":[0.0007413682,0.00009359887,0.000031692587,0.00041000595,0.00006653432,0.000334033,0.00028311848,0.000090558264,0.00008923702],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031452096,0.00016630311,0.9475484,0.000019355712,0.000007932865,0.000024620018,0.0007728066,0.000009620508,0.00020867265,0.008610988,0.01577791,0.02685026],"study_design_scores_gemma":[0.00010929658,0.00009283931,0.5505617,0.000023549172,0.0000017251516,0.000032090775,0.0000010428072,0.3794353,0.0050815064,0.064389214,0.000053056563,0.0002186619],"about_ca_topic_score_codex":0.0007095289,"about_ca_topic_score_gemma":0.0000044887315,"teacher_disagreement_score":0.39698666,"about_ca_system_score_codex":0.000022050774,"about_ca_system_score_gemma":0.000040871302,"threshold_uncertainty_score":0.3816851},"labels":[],"label_agreement":null},{"id":"W2117003318","doi":"10.1109/icst.2015.7102595","title":"JSEFT: Automated Javascript Unit Test Generation","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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; Oracle; Programming language; Unit testing; Test case; Document Object Model; Web application; Event (particle physics); Rich Internet application; Operating system; Machine learning; Software; XML","score_opus":0.11660022819717285,"score_gpt":0.3053674336741877,"score_spread":0.18876720547701487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117003318","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005563097,0.000050615345,0.8877135,0.00084686367,0.0003591577,0.0000924677,6.219864e-7,0.09438754,0.010986136],"genre_scores_gemma":[0.51412606,8.1370325e-7,0.4840684,0.00071932026,0.000078067715,0.0000095893865,0.0000045143233,0.0000068572767,0.0009863902],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926174,0.000034250043,0.00013228544,0.00021541507,0.0001974059,0.00015889284],"domain_scores_gemma":[0.9991215,0.00009788921,0.000037353453,0.00045725942,0.00017463975,0.0001113513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034995037,0.00008719871,0.00007915619,0.00008108652,0.000062629915,0.00017752415,0.0004367865,0.000046479625,0.0000054893376],"category_scores_gemma":[0.0007167728,0.00007376208,0.000019087796,0.00033418028,0.000017638191,0.0002985672,0.00013173313,0.000056449593,0.00014864001],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0561628e-7,0.00005408849,0.00763581,0.0000020883574,0.0000031565082,0.000011216047,0.00024386105,0.000055179655,0.0005664038,0.0059132925,0.97361404,0.011900474],"study_design_scores_gemma":[0.00015532566,0.000107629,0.0010503758,0.000007811407,0.00000205025,0.000038307215,0.000002285897,0.97857046,0.004160391,0.009568769,0.006186042,0.00015054592],"about_ca_topic_score_codex":0.00017283806,"about_ca_topic_score_gemma":0.000008302707,"teacher_disagreement_score":0.97851527,"about_ca_system_score_codex":0.00002817068,"about_ca_system_score_gemma":0.00008927297,"threshold_uncertainty_score":0.30079305},"labels":[],"label_agreement":null},{"id":"W2118160504","doi":"10.1109/glocom.1990.116807","title":"A novel approach to protocol test sequence generation","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sequence (biology); Test (biology); Computer science; Finite-state machine; Set (abstract data type); Fault coverage; Test set; Automatic test pattern generation; Theoretical computer science; Fault (geology); Algorithm; Artificial intelligence; Engineering; Programming language","score_opus":0.16318906373876985,"score_gpt":0.312692947955013,"score_spread":0.14950388421624317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118160504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032411852,6.9219845e-7,0.9598462,0.00039892073,0.000022082239,0.013180514,5.166836e-7,0.008438241,0.018080445],"genre_scores_gemma":[0.026635986,4.566859e-8,0.92746145,0.0011474882,0.0000668628,0.043812584,4.777436e-7,0.00000622826,0.0008688686],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991672,0.000011353941,0.00013115916,0.00033451073,0.00018062262,0.00017516752],"domain_scores_gemma":[0.99925554,0.000069302216,0.000030895062,0.00049339735,0.00007091368,0.000079968726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016352281,0.0000933448,0.00007136369,0.00007298451,0.00008793966,0.00017743536,0.0005404009,0.000035562633,0.000010387904],"category_scores_gemma":[0.0003281227,0.000077438686,0.000020204934,0.00040185405,0.000013065146,0.00022305048,0.00013447825,0.000045044762,0.00008577801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014267056,0.0014103879,0.0022456245,0.000048756603,0.000006455394,0.000007534356,0.0013569575,0.00041234004,0.07595988,0.034138773,0.6726616,0.21175024],"study_design_scores_gemma":[0.00012875785,0.00012646387,0.00013262019,0.000011839201,6.8116805e-7,0.000066521985,5.2013235e-7,0.9870101,0.006316232,0.0011661514,0.0048467563,0.00019334846],"about_ca_topic_score_codex":0.000036625683,"about_ca_topic_score_gemma":0.0000010925819,"teacher_disagreement_score":0.9865978,"about_ca_system_score_codex":0.000031472762,"about_ca_system_score_gemma":0.000013379025,"threshold_uncertainty_score":0.3157858},"labels":[],"label_agreement":null},{"id":"W2118304037","doi":"10.1109/issre.2002.1173268","title":"A case study using the round-trip strategy for state-based class testing","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Weighting; Random testing; Finite-state machine; Test case; Test strategy; White-box testing; Unified Modeling Language; Model-based testing; Code coverage; Partition (number theory); Fault coverage; Set (abstract data type); Class (philosophy); Context (archaeology); Path (computing); Algorithm; Machine learning; Programming language; Artificial intelligence; Engineering; Mathematics; Software development; Software","score_opus":0.19123208886540766,"score_gpt":0.3524184528424081,"score_spread":0.16118636397700042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118304037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24726102,0.000014750238,0.74798685,0.000030889572,0.000073536285,0.0005355543,8.002058e-7,0.003831244,0.00026538715],"genre_scores_gemma":[0.6363538,2.6565113e-8,0.3633652,0.00018040069,0.000011991678,0.00004126775,1.2652058e-7,0.000009774553,0.0000374198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986801,0.00017538796,0.00024765517,0.00037170714,0.00018991565,0.00033524586],"domain_scores_gemma":[0.9970138,0.0019397604,0.00010388691,0.00065847597,0.00022144834,0.000062600775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011769023,0.00015980602,0.00014203443,0.00008056653,0.00048149747,0.00044793513,0.00044689234,0.000032213127,0.0000017757415],"category_scores_gemma":[0.0009471071,0.00010777118,0.000047499223,0.00059727865,0.00003484647,0.00018889029,0.000060506212,0.00012025477,0.000001210129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008193214,0.0063730977,0.35270527,0.00032592242,0.00038491393,0.016166942,0.012725243,0.14700447,0.0018503115,0.04370732,0.023203496,0.39547107],"study_design_scores_gemma":[0.0006275575,0.00070481375,0.00008906065,0.000021441198,0.000021174845,0.0018145777,0.00036169536,0.9714291,0.0010325436,0.023479607,0.000105308325,0.00031312375],"about_ca_topic_score_codex":0.0013629443,"about_ca_topic_score_gemma":0.00007701784,"teacher_disagreement_score":0.8244246,"about_ca_system_score_codex":0.00006102459,"about_ca_system_score_gemma":0.00027441685,"threshold_uncertainty_score":0.43947813},"labels":[],"label_agreement":null},{"id":"W2118505540","doi":"10.1109/tools.2000.868956","title":"Specification-based testing for real-time reactive systems","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Test suite; Metric (unit); Formal specification; Set (abstract data type); Test case; Conformance testing; Suite; System testing; Test strategy; White-box testing; Code coverage; Reliability engineering; Programming language; Software system; Software; Engineering; Machine learning","score_opus":0.07573585341304075,"score_gpt":0.2640879782556397,"score_spread":0.18835212484259894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118505540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005470753,0.000024490202,0.94993466,0.0003584289,0.00010777715,0.00032065867,0.0000020398588,0.016818993,0.03188585],"genre_scores_gemma":[0.21669136,5.9701233e-7,0.78167003,0.000089874,0.00008366924,0.0001054566,0.0000020071507,0.000011990767,0.0013450215],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991312,0.00002975166,0.00018243176,0.00031619673,0.00014315969,0.00019727158],"domain_scores_gemma":[0.9971061,0.0019755538,0.00010333215,0.0005402318,0.00021878131,0.0000560452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002912604,0.00010025353,0.00011898212,0.00008561741,0.00012804392,0.00015450348,0.00044213852,0.000043418982,0.000009452316],"category_scores_gemma":[0.00080266676,0.000089483656,0.00003502081,0.00032216436,0.000019822723,0.0001533568,0.00003234512,0.000046614226,0.00009216858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011338819,0.000514217,0.01231277,0.00015412428,0.000038764058,0.000021579302,0.0007093915,0.0013293226,0.012324011,0.061895896,0.8039302,0.106758356],"study_design_scores_gemma":[0.00011565695,0.00010850701,0.00047959684,0.00004789915,0.0000028995044,0.00000854828,0.0000018465978,0.99298173,0.0011302964,0.003960983,0.001007959,0.00015408067],"about_ca_topic_score_codex":0.00016385881,"about_ca_topic_score_gemma":2.6069765e-7,"teacher_disagreement_score":0.9916524,"about_ca_system_score_codex":0.000052435495,"about_ca_system_score_gemma":0.000021768508,"threshold_uncertainty_score":0.36490375},"labels":[],"label_agreement":null},{"id":"W2118553653","doi":"10.1007/3-540-45785-2_27","title":"Expressing Graphical User’s Input for Test Specifications","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Graphical user interface testing; Graphical user interface; Scalability; Human–computer interaction; Graphical model; Software engineering; Programming language; User experience design; User interface design; Artificial intelligence; Operating system","score_opus":0.05880410136687744,"score_gpt":0.27540840828355595,"score_spread":0.2166043069166785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118553653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007682907,0.000307684,0.9919283,0.001177829,0.0008191582,0.00049262925,0.000010788415,0.003522832,0.0017331305],"genre_scores_gemma":[0.04408666,0.000033878303,0.9538403,0.0009776205,0.0005312129,0.000045722267,0.0000058757255,0.000046865312,0.00043184825],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99643284,0.000020739657,0.0005443495,0.0016125853,0.0007207372,0.00066873885],"domain_scores_gemma":[0.9944667,0.0028581338,0.00029608537,0.001854602,0.00034146674,0.00018300212],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072146195,0.00049786584,0.0004665952,0.0009707789,0.0004775957,0.00082365575,0.0035604788,0.00036133657,0.000012708514],"category_scores_gemma":[0.0008677719,0.0004742085,0.00017770611,0.0006975045,0.0007094735,0.00047952298,0.00085454085,0.000699826,0.00002075638],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003047813,0.00012500286,0.0006611654,0.00007057041,0.000010435947,0.00004762133,0.0006220745,0.0017541989,0.00016546006,0.046702642,0.0037766686,0.94606113],"study_design_scores_gemma":[0.00018306935,0.00018484006,0.00021075754,0.0006008763,0.000008570576,0.00008510889,1.8466553e-8,0.30305076,0.0008452667,0.6859322,0.00815917,0.000739369],"about_ca_topic_score_codex":0.000008985944,"about_ca_topic_score_gemma":0.000005468846,"teacher_disagreement_score":0.94532174,"about_ca_system_score_codex":0.00019178154,"about_ca_system_score_gemma":0.00023898279,"threshold_uncertainty_score":0.99977094},"labels":[],"label_agreement":null},{"id":"W2119042529","doi":"10.1109/iscis.2009.5291883","title":"Using a SAT solver to generate checking sequences","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Model checking; Sequence (biology); Boolean satisfiability problem; Computer science; Solver; Finite-state machine; Satisfiability modulo theories; Set (abstract data type); Algorithm; Theoretical computer science; Abstraction model checking; Automaton; Programming language","score_opus":0.09517591476434714,"score_gpt":0.3385833682943744,"score_spread":0.24340745353002727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119042529","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05768766,0.00003390307,0.9315751,0.00084422505,0.00010161093,0.00006530932,1.2966353e-7,0.007821384,0.0018706347],"genre_scores_gemma":[0.46908218,5.018212e-7,0.52841365,0.0023917733,0.000038513288,0.0000010816683,1.2299246e-7,0.0000022316863,0.00006992884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991824,0.000019828378,0.00012201054,0.0002794565,0.00015911815,0.00023721097],"domain_scores_gemma":[0.9994478,0.000038891154,0.000030745494,0.00034531584,0.00005443066,0.00008282115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022888434,0.00009685485,0.000096275115,0.00009682167,0.00011636201,0.00021585273,0.00049334305,0.000032751137,0.0000072116018],"category_scores_gemma":[0.000070920214,0.00008108446,0.00003085695,0.0003166051,0.000010349909,0.0002483663,0.00010200015,0.000056161243,0.000035073903],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009924803,0.00016725768,0.012632806,0.00001781478,0.000026114996,0.00022539537,0.0037760492,0.0052589313,0.12119681,0.068863064,0.07524993,0.7125759],"study_design_scores_gemma":[0.00018859489,0.0003526231,0.004566571,0.00015976837,0.000008768229,0.00018827479,0.000007834895,0.6563909,0.10276213,0.23277143,0.0016916355,0.0009114925],"about_ca_topic_score_codex":0.0001057128,"about_ca_topic_score_gemma":0.0000021871792,"teacher_disagreement_score":0.7116644,"about_ca_system_score_codex":0.00003812228,"about_ca_system_score_gemma":0.000044521195,"threshold_uncertainty_score":0.33065283},"labels":[],"label_agreement":null},{"id":"W2119582290","doi":"10.1002/spe.520","title":"Investigating the use of analysis contracts to improve the testability of object‐oriented code","year":2003,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Testability; Precondition; Software engineering; Reuse; Isolation (microbiology); Design by contract; Programming language; Coding (social sciences); Software; Reliability engineering; Software system; Software construction; Engineering","score_opus":0.04497579318473231,"score_gpt":0.31088651099809034,"score_spread":0.265910717813358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119582290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38584957,0.00017936122,0.6119543,0.00092799985,0.00009747671,0.0003316111,0.0000072609046,0.00061153056,0.00004093022],"genre_scores_gemma":[0.68562335,0.000009358632,0.31342295,0.0008831591,0.0000053329454,0.00004369885,3.5992943e-7,0.000004399456,0.0000073840965],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982135,0.00037723026,0.00040192145,0.00039827143,0.00037014607,0.00023889302],"domain_scores_gemma":[0.98874474,0.009087971,0.00043857482,0.0011170631,0.00050996605,0.00010169091],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001320757,0.00014382224,0.00024476027,0.00007800086,0.00026242412,0.00013327095,0.00055144494,0.000048578808,0.0000022446015],"category_scores_gemma":[0.06437049,0.00008743376,0.00007063071,0.001605084,0.00036146384,0.00087138824,0.000225275,0.00018847862,6.7394194e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000929297,0.00077417033,0.650276,0.00013737155,0.0005704074,0.000018897596,0.21118319,0.0015405904,0.0102670025,0.026839217,0.002285633,0.096014574],"study_design_scores_gemma":[0.002641165,0.004268839,0.30367717,0.00095666206,0.0028712275,0.00055837014,0.025340823,0.083305694,0.3901797,0.060834233,0.12103974,0.0043264045],"about_ca_topic_score_codex":0.0009989283,"about_ca_topic_score_gemma":0.000030459854,"teacher_disagreement_score":0.37991267,"about_ca_system_score_codex":0.00001883998,"about_ca_system_score_gemma":0.00011995842,"threshold_uncertainty_score":0.9435107},"labels":[],"label_agreement":null},{"id":"W2120359737","doi":"10.1109/scam.2008.29","title":"Automated Migration of List Based JSP Web Pages to AJAX","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Ajax; Web page; Computer science; World Wide Web; Static web page; Dynamic web page; Page view; Web application; Web development","score_opus":0.03209367110724004,"score_gpt":0.26569929216042576,"score_spread":0.23360562105318572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120359737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12805846,0.000017502602,0.83006537,0.0018837426,0.00007998318,0.00012484411,0.0000014320249,0.03795377,0.0018148575],"genre_scores_gemma":[0.6019899,0.0000012756881,0.39735785,0.0005143493,0.000007617138,0.000006290908,0.0000011370647,0.0000031013938,0.00011842074],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993473,0.000030734118,0.0001529811,0.00018122031,0.00017082602,0.00011688899],"domain_scores_gemma":[0.9992453,0.00016562923,0.00004602008,0.000384839,0.00010456876,0.00005367505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014733228,0.0000737454,0.00010093477,0.00012443807,0.00006196692,0.000025210218,0.00035141478,0.0000345441,0.000009479569],"category_scores_gemma":[0.00022191647,0.00006277587,0.000031719454,0.00041994874,0.000023534134,0.00010799218,0.000060718616,0.000033939123,0.000018303937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005124267,0.00011614416,0.03131389,0.000019002957,0.000005197508,0.000021070891,0.00040068664,0.0001811545,0.008245293,0.00096446084,0.9509008,0.007827159],"study_design_scores_gemma":[0.00014928011,0.00017798445,0.021013603,0.000046611738,0.0000019867382,0.000016581258,0.000001231936,0.92135483,0.054205783,0.0007606129,0.002105488,0.00016602711],"about_ca_topic_score_codex":0.00030967125,"about_ca_topic_score_gemma":0.00004130946,"teacher_disagreement_score":0.9487953,"about_ca_system_score_codex":0.000014557712,"about_ca_system_score_gemma":0.00007290557,"threshold_uncertainty_score":0.25599256},"labels":[],"label_agreement":null},{"id":"W2121316343","doi":"10.1109/iccd.2006.4380831","title":"Adding Debug Enhancements to Assertion Checkers for Hardware Emulation and Silicon Debug","year":2006,"lang":"en","type":"article","venue":"Proceedings, IEEE International Conference on Computer Design/Proceedings - IEEE International Conference on Computer Design","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Debugging; Emulation; Assertion; Computer science; Background debug mode interface; Hardware emulation; Embedded system; Computer architecture; Software bug; Programming language; Software; Field-programmable gate array; Psychology","score_opus":0.12912903322472305,"score_gpt":0.33324142009886076,"score_spread":0.2041123868741377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121316343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015163554,0.000011128106,0.9691267,0.003237496,0.004234334,0.002024814,0.00003973152,0.0034131624,0.0027490843],"genre_scores_gemma":[0.6014247,0.00003083394,0.3944514,0.0014689537,0.0016114225,0.0005549597,0.000048164555,0.00008429979,0.0003252667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99266016,0.00007138155,0.0014977782,0.002666106,0.001988629,0.0011159106],"domain_scores_gemma":[0.99287105,0.00066076615,0.00103556,0.0004001683,0.004571374,0.000461113],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015432319,0.0012272459,0.00086919597,0.001605111,0.0005947667,0.0038792565,0.0034217804,0.00043140465,0.00005060844],"category_scores_gemma":[0.00023590255,0.0012925896,0.00027615574,0.0006750538,0.0001567518,0.002701647,0.00046766963,0.00068737933,0.00010139227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021796245,0.0016280309,0.0024132705,0.0002875792,0.0007796412,0.000051561896,0.002493696,0.009030985,0.07816322,0.5980316,0.17182025,0.13312054],"study_design_scores_gemma":[0.0015877751,0.0019378772,0.0010117395,0.0013634352,0.00004088457,0.00008813179,0.00002550028,0.91026425,0.034749378,0.046552874,0.0009954927,0.0013826654],"about_ca_topic_score_codex":0.00007954058,"about_ca_topic_score_gemma":0.0000037912785,"teacher_disagreement_score":0.90123326,"about_ca_system_score_codex":0.0007797123,"about_ca_system_score_gemma":0.00027986063,"threshold_uncertainty_score":0.9989524},"labels":[],"label_agreement":null},{"id":"W2121450025","doi":"10.1109/sera.2008.29","title":"Modeling Enhanced Scenarios for Automated Instrumentation","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Traceability; Computer science; Scalability; Software engineering; Instrumentation (computer programming); Model-based testing; Scenario testing; Automation; Focus (optics); Semantics (computer science); Test case; Dominance (genetics); Systems engineering; Programming language; Engineering; Artificial intelligence; Machine learning; Database","score_opus":0.04232699505102225,"score_gpt":0.29299683743677946,"score_spread":0.2506698423857572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121450025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08623723,0.0000051769853,0.8792013,0.00011328161,0.00007933925,0.00013548217,2.6712632e-7,0.033941384,0.000286557],"genre_scores_gemma":[0.5279027,0.0000013919339,0.4718605,0.00015499767,0.000009245581,0.000024688177,0.0000015423043,0.0000031664763,0.000041719457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994307,0.000009669148,0.00012748317,0.00019137072,0.00009945772,0.00014128364],"domain_scores_gemma":[0.9995838,0.000063742,0.000025050891,0.00021270273,0.0000825302,0.000032189906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009384271,0.00006616892,0.000070113165,0.000061952676,0.00015612207,0.00003603836,0.0002517581,0.000031637068,0.0000017041244],"category_scores_gemma":[0.000099905985,0.000060187704,0.000028706385,0.00014663063,0.000010776164,0.00025637163,0.000048402053,0.000030102237,0.000008315618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074687676,0.00061956904,0.00319828,0.00016897684,0.00010048993,0.00003308517,0.012900665,0.29989928,0.029422782,0.040811438,0.14249104,0.47027972],"study_design_scores_gemma":[0.00015682638,0.000046015117,0.000040987954,0.000011074424,9.2070616e-7,0.000013430809,0.0000016917807,0.98567116,0.0070344377,0.0069235256,0.00001445028,0.00008550521],"about_ca_topic_score_codex":0.00006502248,"about_ca_topic_score_gemma":0.0000016858187,"teacher_disagreement_score":0.6857719,"about_ca_system_score_codex":0.000024328936,"about_ca_system_score_gemma":0.000043445863,"threshold_uncertainty_score":0.24543832},"labels":[],"label_agreement":null},{"id":"W2121504314","doi":"10.1145/2642937.2642991","title":"Leveraging existing tests in automated test generation for web applications","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Test suite; Computer science; Web crawler; Crawling; Code coverage; Test (biology); Web testing; Test harness; Random testing; Test Management Approach; Test case; Domain (mathematical analysis); Generator (circuit theory); Software engineering; Event (particle physics); Data mining; Machine learning; Web page; Programming language; World Wide Web; Software; Power (physics); Web development; Software development; Web application security","score_opus":0.060793006232949295,"score_gpt":0.31997880997381783,"score_spread":0.2591858037408685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121504314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004105115,0.000010811982,0.9724594,0.00030362187,0.000041478685,0.00025933958,5.439671e-7,0.020981645,0.0018380942],"genre_scores_gemma":[0.52793914,2.6175005e-7,0.47158766,0.00019224967,0.00005423291,0.0001731809,0.0000030877,0.000005098973,0.000045112323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992519,0.000021802272,0.00018172145,0.0002862342,0.00008277517,0.0001755705],"domain_scores_gemma":[0.998632,0.0008548592,0.000055641765,0.0003434405,0.00008012092,0.00003390316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048047167,0.000081246646,0.000085580796,0.0001182698,0.00012647368,0.0001258574,0.0003149301,0.000037022823,8.8845934e-7],"category_scores_gemma":[0.00089378527,0.000079047066,0.000019387391,0.00032574832,0.0000113300675,0.00014738507,0.00006693566,0.000048719576,0.000008549421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016386471,0.00038041602,0.10075841,0.00011213808,0.000008116989,0.0000025063766,0.00078576803,0.0015809622,0.06699625,0.0931227,0.10001338,0.63623774],"study_design_scores_gemma":[0.00012010518,0.000027360642,0.0028963385,0.000021011387,9.807825e-7,0.000004844397,7.7532314e-7,0.9812879,0.0010333321,0.012872263,0.0016251612,0.000109923145],"about_ca_topic_score_codex":0.00003996296,"about_ca_topic_score_gemma":0.000015381034,"teacher_disagreement_score":0.97970694,"about_ca_system_score_codex":0.000035498517,"about_ca_system_score_gemma":0.0000366145,"threshold_uncertainty_score":0.32234457},"labels":[],"label_agreement":null},{"id":"W2121513851","doi":"10.1007/978-3-319-22689-7_35","title":"Hermes: A Targeted Fuzz Testing Framework","year":2015,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Software security assurance; Fuzz testing; Computer science; Security testing; Test (biology); Software; Test case; Code (set theory); Variety (cybernetics); Buffer overflow; Computer security; Information security; Security information and event management; Security service; Cloud computing security; Artificial intelligence; Programming language; Set (abstract data type); Machine learning; Cloud computing; Operating system","score_opus":0.10195110765609292,"score_gpt":0.32900234293158076,"score_spread":0.22705123527548784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121513851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008975598,0.0006887361,0.80367184,0.00057564507,0.00026069133,0.0002728484,0.000005703289,0.002470368,0.19204517],"genre_scores_gemma":[0.016123751,0.0002466156,0.98220235,0.0008882589,0.000041706604,0.000025229117,0.00001693356,0.000010374952,0.0004448003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818444,0.00003340867,0.00063425873,0.000319685,0.0005530359,0.00027516758],"domain_scores_gemma":[0.9950364,0.0008128329,0.00037594792,0.0027546103,0.00086779497,0.0001523974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017248436,0.00024443585,0.00026324033,0.0009351019,0.00044580438,0.00078591146,0.0043042228,0.00018257703,0.0000030427832],"category_scores_gemma":[0.0008865908,0.00024454197,0.000033215303,0.0008152879,0.00072714774,0.004784951,0.0032986617,0.00063955167,0.000057966598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.275956e-7,0.0000112019625,0.00014524262,0.000019583154,0.0000029707867,7.750529e-7,0.001481204,0.0000923881,4.7533808e-7,0.51316315,0.0028123688,0.48226988],"study_design_scores_gemma":[0.00012829032,0.00008009533,0.00058906333,0.00069037464,0.00000389105,0.000057781686,0.000004177716,0.3934938,0.0000024563521,0.5279137,0.0766055,0.0004308468],"about_ca_topic_score_codex":0.000021164784,"about_ca_topic_score_gemma":0.0000013436578,"teacher_disagreement_score":0.48183903,"about_ca_system_score_codex":0.0001812519,"about_ca_system_score_gemma":0.00056116254,"threshold_uncertainty_score":0.9972132},"labels":[],"label_agreement":null},{"id":"W2122097722","doi":"10.1109/ftcs.1996.534610","title":"A framework for conformance testing of systems communicating through rendezvous","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Conformance testing; Computer science; Rendezvous; Set (abstract data type); Fault (geology); Test case; Fault coverage; Test (biology); System under test; Finite-state machine; Model-based testing; Reliability engineering; System testing; Non-regression testing; Test suite; Code coverage; Algorithm; Programming language; Engineering; Software; Machine learning; Software system; Standardization","score_opus":0.15028303002887528,"score_gpt":0.32538206358263977,"score_spread":0.1750990335537645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122097722","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006653494,0.0005880859,0.9833104,0.0001575987,0.000109697205,0.00020263896,0.0000014210874,0.005976108,0.008988697],"genre_scores_gemma":[0.41531128,0.0000061296137,0.5844614,0.00011161894,0.000017452616,0.0000307301,2.4576875e-7,0.0000056065855,0.000055546876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991039,0.000029896437,0.00032489715,0.0001794908,0.00014390837,0.00021789648],"domain_scores_gemma":[0.9959082,0.0027149487,0.00023578414,0.00093484897,0.00017746729,0.00002877584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033355018,0.00010020141,0.00018896097,0.00003862468,0.00014394862,0.000081250524,0.0010127911,0.00006718525,0.0000020208065],"category_scores_gemma":[0.0018075018,0.00008822277,0.00003996206,0.00035937273,0.000048513157,0.0002449909,0.00022095355,0.00012242942,0.000004657159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025672437,0.00012330593,0.005990635,0.0003253142,0.00002649549,0.0000024815022,0.003487765,0.00028608498,0.00010799612,0.86765486,0.023371972,0.098620534],"study_design_scores_gemma":[0.00013514246,0.00018511245,0.00007673818,0.00055917155,0.000004393739,0.000039343446,0.000024414981,0.87272745,0.00088062603,0.12331998,0.0018515897,0.00019605964],"about_ca_topic_score_codex":0.00017822297,"about_ca_topic_score_gemma":5.13172e-7,"teacher_disagreement_score":0.87244135,"about_ca_system_score_codex":0.000016084485,"about_ca_system_score_gemma":0.00001185528,"threshold_uncertainty_score":0.359762},"labels":[],"label_agreement":null},{"id":"W2122167693","doi":"10.4028/www.scientific.net/amm.241-244.2718","title":"The Quantified Evaluation Method of Project Test Based on Multi-Computing","year":2012,"lang":"en","type":"article","venue":"Applied Mechanics and Materials","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Test (biology); Computer science; Project management; Grid; Project management triangle; Quality (philosophy); Systems engineering; Project planning; Test case; Software; Engineering management; Engineering","score_opus":0.06886701825330585,"score_gpt":0.34737752608012773,"score_spread":0.27851050782682185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122167693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024009943,0.000027770013,0.99594396,0.00004668066,0.00030595047,0.00046937462,0.000003344236,0.00068501144,0.000116924195],"genre_scores_gemma":[0.54702026,0.0000027700455,0.4528359,0.00006951544,0.000026528678,0.000035321744,0.0000017721305,0.000006181295,0.0000017489482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990052,0.00011963863,0.00023534635,0.00020263395,0.00022670528,0.00021049831],"domain_scores_gemma":[0.99826086,0.0010509132,0.00019311646,0.00039302334,0.000071412,0.000030696563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005056602,0.0001094754,0.00015694153,0.000056769455,0.00016637359,0.00010251413,0.0002541694,0.00005429371,0.0000012226781],"category_scores_gemma":[0.0004927195,0.0000746373,0.000018257102,0.00012835315,0.000008470946,0.000048307917,0.00011898899,0.000041873107,0.0000020541622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023181175,0.00018287283,0.000017587867,0.00006362627,0.000012023333,2.436914e-7,0.00054067234,0.000018054821,0.16624719,0.63324916,0.0006119158,0.19903348],"study_design_scores_gemma":[0.0005927137,0.00014170534,0.00025766567,0.00007471086,0.000030684714,0.000005642659,0.000021389094,0.38025728,0.54242355,0.07569629,0.00025306383,0.00024531415],"about_ca_topic_score_codex":0.000031993055,"about_ca_topic_score_gemma":4.73591e-7,"teacher_disagreement_score":0.5575529,"about_ca_system_score_codex":0.000014077062,"about_ca_system_score_gemma":0.000043466345,"threshold_uncertainty_score":0.3043621},"labels":[],"label_agreement":null},{"id":"W2122170536","doi":"10.1109/cmpsac.1997.625060","title":"Natural optimization algorithms for optimal regression testing","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Mathematical optimization; Algorithm; Simulated annealing; Regression testing; Integer programming; Software; Mathematics; Software system","score_opus":0.07023088735804665,"score_gpt":0.2908348467376765,"score_spread":0.22060395937962984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122170536","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001524857,0.0001163433,0.98672396,0.00040051484,0.00021855495,0.00014131857,4.3095025e-7,0.011118169,0.0011282352],"genre_scores_gemma":[0.05165504,0.000002212173,0.9473508,0.00021622253,0.00007434836,0.000026644553,0.0000019786667,0.000009225954,0.00066352024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992142,0.000016608807,0.00014192205,0.00028067746,0.00013858946,0.00020801373],"domain_scores_gemma":[0.9990105,0.00043513856,0.00006511091,0.0002916448,0.00015232731,0.00004528477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016859641,0.0001040807,0.00009130949,0.00007509003,0.00017433208,0.00013594721,0.00039791956,0.000045832792,0.00001055533],"category_scores_gemma":[0.00078660954,0.00008052996,0.000036203066,0.00030220457,0.000016707818,0.00033359748,0.000113974995,0.00007395219,0.0000064953956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035478688,0.000100389785,0.0006482608,0.000025467887,0.000008862123,0.000010817304,0.0003252887,0.023640107,0.00019532692,0.00233896,0.13467976,0.8380232],"study_design_scores_gemma":[0.00012828491,0.00007637133,0.000035427387,0.0000395514,0.0000018331897,0.000028498878,0.0000010534637,0.99729913,0.0006385156,0.0013896214,0.00023443122,0.00012728729],"about_ca_topic_score_codex":0.000010409228,"about_ca_topic_score_gemma":1.05002826e-7,"teacher_disagreement_score":0.97365904,"about_ca_system_score_codex":0.000022480977,"about_ca_system_score_gemma":0.000008101608,"threshold_uncertainty_score":0.32839164},"labels":[],"label_agreement":null},{"id":"W2122175577","doi":"10.1109/iri-05.2005.1506535","title":"A high level design and testing of celestial tracking software with the focus of reusability","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Reusability; Computer science; Constraint (computer-aided design); Dependency (UML); Software; Focus (optics); Process (computing); Partition (number theory); Domain (mathematical analysis); Software engineering; Systems engineering; Programming language; Engineering; Mathematics","score_opus":0.06748813021111748,"score_gpt":0.2572179153920251,"score_spread":0.1897297851809076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122175577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09703928,0.000043875945,0.9008068,0.0004291692,0.0000097380325,0.00014200786,9.862714e-7,0.0014922617,0.00003590642],"genre_scores_gemma":[0.49830425,2.728128e-7,0.50164753,0.000024186886,0.000011020424,0.0000040489044,4.811936e-8,0.000003507295,0.0000051525517],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991101,0.00008050192,0.00021372765,0.00023832968,0.00020435838,0.00015295508],"domain_scores_gemma":[0.99676114,0.0023728719,0.0001531632,0.0004749273,0.00020385456,0.000034048982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007711174,0.000105858635,0.00017149685,0.000033706525,0.000084303865,0.000035764755,0.00046379818,0.000037581503,0.0000015818782],"category_scores_gemma":[0.0011178041,0.00006326325,0.000019691519,0.00030559392,0.000161947,0.00018061597,0.00014932666,0.0000958684,2.7491126e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023968621,0.00010847055,0.040470034,0.000051538656,0.000015444468,0.0000032850562,0.000988221,0.0014244994,0.0013937403,0.0020827148,0.0011702689,0.9522678],"study_design_scores_gemma":[0.0015827713,0.0026817415,0.1921328,0.0007847072,0.00008331146,0.00033722285,0.000046776564,0.15764858,0.5195947,0.12394561,0.00012788261,0.0010338769],"about_ca_topic_score_codex":0.0004962217,"about_ca_topic_score_gemma":0.000020400224,"teacher_disagreement_score":0.9512339,"about_ca_system_score_codex":0.000014211429,"about_ca_system_score_gemma":0.000078900484,"threshold_uncertainty_score":0.25798005},"labels":[],"label_agreement":null},{"id":"W2122260303","doi":"10.1109/rtcsa.1999.811206","title":"Fault coverage in testing real-time systems","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal","funders":"","keywords":"Computer science; Fault coverage; Test suite; Reliability engineering; Fault (geology); Real-time computing; Software quality; Suite; Software fault tolerance; Software; Fault model; System under test; System testing; Test case; Software development; Engineering; Software engineering; Programming language","score_opus":0.025980541671107846,"score_gpt":0.2526553932488752,"score_spread":0.22667485157776734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122260303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037757777,0.0000675929,0.7001639,0.00006107739,0.00023611705,0.00023972917,5.3972997e-7,0.022359341,0.23911396],"genre_scores_gemma":[0.6845529,0.000002497967,0.3144568,0.000080365375,0.0000129206655,0.00001514086,3.1720657e-7,0.00000783156,0.0008712037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990224,0.00009466491,0.00020144408,0.0002770533,0.00015903919,0.00024535082],"domain_scores_gemma":[0.9987838,0.0006543694,0.000052438772,0.00039839084,0.00005876644,0.00005223714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005931046,0.000100882055,0.00013580629,0.000106821026,0.000052620428,0.00015240756,0.00036350705,0.000049235554,0.0000054024513],"category_scores_gemma":[0.0011478035,0.000089732945,0.000018285928,0.0005525826,0.000012399128,0.00019373086,0.00006732764,0.00008658308,0.00007717183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006312976,0.0005433117,0.3410393,0.00019814288,0.000027579612,0.0007826124,0.0014022896,0.0065032784,0.012149146,0.41684225,0.14260432,0.07790146],"study_design_scores_gemma":[0.00081392855,0.00030371602,0.012145546,0.0005288435,0.000004993379,0.000501854,0.000011895689,0.86360955,0.0039078784,0.113753505,0.003277293,0.0011409903],"about_ca_topic_score_codex":0.0008122538,"about_ca_topic_score_gemma":0.0000021245958,"teacher_disagreement_score":0.85710627,"about_ca_system_score_codex":0.000047835634,"about_ca_system_score_gemma":0.000056669916,"threshold_uncertainty_score":0.36592034},"labels":[],"label_agreement":null},{"id":"W2122282651","doi":"10.1109/scam.2002.1134113","title":"Predicate-based dynamic slicing of message passing programs","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Program slicing; Predicate (mathematical logic); Computer science; Slicing; Predicate variable; Computation; Programming language; Algorithm; Theoretical computer science","score_opus":0.016900788852369494,"score_gpt":0.25476644214893224,"score_spread":0.23786565329656273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122282651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00971364,0.000040757648,0.9784804,0.00020244265,0.00006369344,0.00011308189,1.6114961e-7,0.007923666,0.0034621612],"genre_scores_gemma":[0.57335776,3.7774464e-7,0.42645591,0.00013344343,0.0000017949563,0.000008613689,5.736024e-7,0.0000050706735,0.0000364752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990843,0.00006369428,0.00019443853,0.00023858853,0.00021145213,0.00020753218],"domain_scores_gemma":[0.99914503,0.00015560887,0.00009252283,0.0004903463,0.00006261498,0.00005388146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042090032,0.000096670585,0.00012970202,0.00009239437,0.00006486386,0.00006799104,0.00041254857,0.000046100635,0.000005867006],"category_scores_gemma":[0.00022436288,0.00008088843,0.000047158825,0.0003876611,0.000050786795,0.00012397098,0.000049160193,0.00007799943,0.000002481521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009427701,0.0010293907,0.12592366,0.00036737794,0.000057796333,0.000060579066,0.0009837162,0.00043089816,0.005257195,0.07401777,0.012112964,0.7797492],"study_design_scores_gemma":[0.0007485627,0.00051345775,0.004246041,0.0006224548,0.000021604243,0.000045040113,0.00001544033,0.85757786,0.058202457,0.07501677,0.0023175026,0.00067279016],"about_ca_topic_score_codex":0.00006701407,"about_ca_topic_score_gemma":0.0000038978374,"teacher_disagreement_score":0.857147,"about_ca_system_score_codex":0.000025417896,"about_ca_system_score_gemma":0.00007836642,"threshold_uncertainty_score":0.32985342},"labels":[],"label_agreement":null},{"id":"W2122626119","doi":"10.1145/1295074.1295086","title":"Regression test suite reduction using extended dependence analysis","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extended finite-state machine; Test suite; Computer science; Reduction (mathematics); Regression analysis; Set (abstract data type); Finite-state machine; Suite; Test case; Algorithm; Machine learning; Mathematics; Programming language","score_opus":0.03315978076932156,"score_gpt":0.32409144525396816,"score_spread":0.2909316644846466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122626119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03287106,0.00004606011,0.9583492,0.00009475783,0.00012921036,0.00005918125,2.1200036e-7,0.0073603233,0.0010899588],"genre_scores_gemma":[0.55689675,0.0000018832229,0.44281843,0.000049988674,0.00003212278,8.656193e-7,6.921535e-7,0.0000036216916,0.00019563212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987625,0.000027629918,0.00022730598,0.00040121507,0.00030776003,0.00027360246],"domain_scores_gemma":[0.9987273,0.00030091935,0.00011367767,0.0006408741,0.00012667946,0.00009049836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092907384,0.00011746121,0.00014350898,0.0004381999,0.0001743226,0.00011574085,0.00047819767,0.00007011126,0.000012151344],"category_scores_gemma":[0.00041224895,0.000094701914,0.00008384319,0.0019018746,0.000032030468,0.00038520945,0.00016500692,0.00011068099,0.000007943367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000300441,0.000635082,0.24123399,0.000037893544,0.0002469675,0.00030942712,0.0013326958,0.0008824796,0.082703754,0.012741655,0.011054535,0.6487915],"study_design_scores_gemma":[0.00026542792,0.00020062969,0.118458144,0.00014763935,0.00022136452,0.0005477659,0.000037615126,0.68737704,0.13238527,0.05926834,0.00020379182,0.00088700105],"about_ca_topic_score_codex":0.00030813526,"about_ca_topic_score_gemma":0.000016753818,"teacher_disagreement_score":0.6864945,"about_ca_system_score_codex":0.00006940628,"about_ca_system_score_gemma":0.000032609976,"threshold_uncertainty_score":0.3861832},"labels":[],"label_agreement":null},{"id":"W2122715775","doi":"10.1007/s12243-014-0449-0","title":"Integration testing of communicating systems with unknown components","year":2014,"lang":"en","type":"article","venue":"Annals of Telecommunications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Modular design; Reachability; Component (thermodynamics); Model-based testing; TRACE (psycholinguistics); Isolation (microbiology); Model checking; Asynchronous communication; System under test; Inference; Test case; Theoretical computer science; Algorithm; Artificial intelligence; Machine learning; Programming language","score_opus":0.14085710865973636,"score_gpt":0.33044936925932655,"score_spread":0.1895922605995902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122715775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060204446,0.00059367483,0.92246705,0.0018867961,0.00004400533,0.00030474603,0.000004487866,0.0026461328,0.011848687],"genre_scores_gemma":[0.5895855,0.000021418642,0.41030017,0.000049604318,0.000004281157,0.000017307899,0.0000073485858,0.000006231091,0.000008174632],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873656,0.00031894556,0.00046245364,0.00014346867,0.0001853091,0.0001532404],"domain_scores_gemma":[0.99424946,0.0020697631,0.00056186144,0.0023439173,0.0007306963,0.000044313794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009823439,0.00010932049,0.00024406871,0.00014765644,0.00019215175,0.000046616125,0.0021176753,0.000043910728,4.824368e-7],"category_scores_gemma":[0.0011913986,0.000094236915,0.000040054947,0.00061309634,0.00013490394,0.00022925489,0.00042294632,0.00017998228,0.0000018962228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025703115,0.0017454043,0.07522073,0.00040794673,0.00023318388,7.9741517e-7,0.004467167,0.0057589076,0.02105514,0.42564586,0.007899958,0.4575392],"study_design_scores_gemma":[0.00036859105,0.0007856372,0.034224097,0.0023044217,0.000025639349,0.000040823463,0.000058784506,0.91829234,0.018767565,0.02114923,0.0034982956,0.00048459423],"about_ca_topic_score_codex":0.00082651776,"about_ca_topic_score_gemma":0.000019348408,"teacher_disagreement_score":0.9125334,"about_ca_system_score_codex":0.000008056219,"about_ca_system_score_gemma":0.000038842274,"threshold_uncertainty_score":0.3935203},"labels":[],"label_agreement":null},{"id":"W2123039547","doi":"10.1016/j.disc.2011.10.026","title":"Cover starters for covering arrays of strength two","year":2011,"lang":"en","type":"article","venue":"Discrete Mathematics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Carleton University","funders":"","keywords":"Cover (algebra); Mathematics; Combinatorics; Heuristic; Covering space; Upper and lower bounds; Representation (politics); Discrete mathematics; Mathematical optimization; Engineering","score_opus":0.04715693982522598,"score_gpt":0.2780852931107338,"score_spread":0.23092835328550784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123039547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009974373,0.00001096815,0.9843478,0.000014454289,0.00008269677,0.00016983045,0.000011349979,0.0014262696,0.0039622374],"genre_scores_gemma":[0.35477006,0.0000010614818,0.6451298,0.000026545184,0.000010314813,0.000015325193,0.0000013846424,0.000009787803,0.00003571288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992425,0.000010906151,0.00024718023,0.00016646228,0.00015140527,0.00018153414],"domain_scores_gemma":[0.9989422,0.0002678288,0.0001634333,0.00051519857,0.00006630336,0.000045067805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000235616,0.000112967675,0.00018699064,0.000056875586,0.000043779928,0.00003172639,0.0005024334,0.000028600814,0.000009042687],"category_scores_gemma":[0.00020126236,0.00009732294,0.00007775883,0.00010983238,0.000040900075,0.00015670569,0.0001088192,0.00004691325,0.0000066621396],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003661258,0.0006825725,0.0021946984,0.0015378045,0.00020143138,0.000015717565,0.050686322,0.00017500002,0.00217443,0.8938323,0.026078872,0.022384224],"study_design_scores_gemma":[0.0005185025,0.00030334256,0.00010380065,0.0002891335,0.000031940854,0.000011741068,0.00009096779,0.30183172,0.03436921,0.6617922,0.00028700716,0.00037040803],"about_ca_topic_score_codex":0.00001880949,"about_ca_topic_score_gemma":7.1286877e-7,"teacher_disagreement_score":0.3447957,"about_ca_system_score_codex":0.000013486057,"about_ca_system_score_gemma":0.000023943694,"threshold_uncertainty_score":0.39687142},"labels":[],"label_agreement":null},{"id":"W2123203095","doi":"10.1109/issre.1992.285853","title":"Control-flow based testing of Prolog programs","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prolog; Computer science; Control flow; Selection (genetic algorithm); Programming language; Control (management); Data flow diagram; Control flow graph; Test (biology); Artificial intelligence; Database","score_opus":0.033706945543597086,"score_gpt":0.24731288896721035,"score_spread":0.21360594342361328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123203095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029114778,0.00001929595,0.982686,0.00012225438,0.00004992391,0.00018656986,2.295434e-7,0.008516078,0.005508213],"genre_scores_gemma":[0.4891525,2.7927145e-8,0.5106295,0.00017786771,0.000003688186,0.000016578024,1.6736352e-7,0.0000031374316,0.00001654064],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917775,0.00006967131,0.0001773535,0.00021769272,0.00015348998,0.000204039],"domain_scores_gemma":[0.9988352,0.00047015253,0.000082766746,0.0004094979,0.000155298,0.000047102083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054124085,0.000088459245,0.00013489259,0.00005885234,0.000045934026,0.0000433963,0.0003572499,0.000042581185,0.000004611423],"category_scores_gemma":[0.0014385438,0.00007089753,0.000036079105,0.00039184734,0.00004393485,0.00009221315,0.000026917369,0.000067237845,0.000004493643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008927839,0.00054872426,0.5450879,0.000083590196,0.00002218454,0.000027521963,0.00010054556,0.0005503126,0.0009347054,0.037321478,0.005815949,0.40949818],"study_design_scores_gemma":[0.00083751534,0.0007894655,0.0028848315,0.00009842839,0.000009283855,0.000037070182,0.0000011055849,0.9160329,0.012696986,0.06501124,0.0012926554,0.00030847773],"about_ca_topic_score_codex":0.000035941164,"about_ca_topic_score_gemma":9.1198353e-7,"teacher_disagreement_score":0.91548264,"about_ca_system_score_codex":0.000009228489,"about_ca_system_score_gemma":0.00008966207,"threshold_uncertainty_score":0.28911173},"labels":[],"label_agreement":null},{"id":"W2123319826","doi":"10.1007/11569596_93","title":"Generalizing Redundancy Elimination in Checking Sequences","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Redundancy (engineering); Computer science; Prime (order theory); Set (abstract data type); Finite-state machine; Algorithm; Model checking; State (computer science); Discrete mathematics; Theoretical computer science; Combinatorics; Mathematics; Programming language","score_opus":0.03110914949709723,"score_gpt":0.27836388576723836,"score_spread":0.24725473627014113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123319826","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022025021,0.00082225684,0.9925351,0.0010496723,0.0008276392,0.00025094932,9.869789e-7,0.0021007545,0.0021923962],"genre_scores_gemma":[0.27461472,0.000062855695,0.72381926,0.00086309464,0.00041913486,0.000011974306,0.0000027513147,0.000026908394,0.0001792984],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638104,0.000043240776,0.00059804274,0.0014495902,0.00086880993,0.00065926666],"domain_scores_gemma":[0.99783045,0.0004932886,0.0003188382,0.0010694221,0.00018547183,0.00010250819],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014414228,0.0004628759,0.0004482501,0.0013958084,0.00020930012,0.0007708662,0.0027827579,0.0003189348,0.0000060826887],"category_scores_gemma":[0.00031050286,0.0004566474,0.00008978274,0.0008674359,0.00039194393,0.0011590885,0.0008813953,0.0007933189,0.000011912163],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012869934,0.000016011752,0.00035930387,0.000024015799,0.0000022878278,0.00007837194,0.0007946421,0.013621355,0.00010223563,0.014381818,0.000029547988,0.9705891],"study_design_scores_gemma":[0.0001517403,0.00009963126,0.0006528342,0.0013561257,0.0000036165613,0.00011479926,5.950296e-8,0.46077323,0.0018352962,0.5336479,0.0006064525,0.0007583329],"about_ca_topic_score_codex":0.000113774,"about_ca_topic_score_gemma":0.00011775456,"teacher_disagreement_score":0.9698308,"about_ca_system_score_codex":0.0006007292,"about_ca_system_score_gemma":0.00047195452,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W2123723258","doi":"10.1109/qsic.2009.21","title":"Web Traversal with a History Stack","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Hyperlink; Computer science; Web page; Traverse; Tree traversal; Web testing; World Wide Web; HTML5; Web navigation; Web application; Static web page; Information retrieval; Web development; Web application security; Programming language","score_opus":0.017600552813850416,"score_gpt":0.217387154459396,"score_spread":0.19978660164554557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123723258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025215524,0.00008043159,0.8912368,0.0008815164,0.000055571203,0.00006335635,1.3380088e-7,0.021878975,0.08328169],"genre_scores_gemma":[0.5431419,0.0000013169704,0.45364967,0.0016381309,0.00001840253,0.0000017604115,2.0215975e-7,0.0000023850555,0.0015462491],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994593,0.000012268722,0.00006285662,0.0001860694,0.0001388474,0.0001406581],"domain_scores_gemma":[0.99950343,0.00004173904,0.000023093638,0.00034772273,0.000032173888,0.00005185732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008910416,0.000070551134,0.00006722418,0.000054783402,0.000025587668,0.000027886656,0.00035519717,0.000023322373,0.000020162537],"category_scores_gemma":[0.00002139745,0.000052167456,0.000017711269,0.00010174872,0.000020406209,0.00015728308,0.000021616052,0.00006240758,0.000022113365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008371666,0.000084994295,0.0011811394,0.000003607653,0.0000050294034,0.00006573469,0.00044565633,0.000008526733,0.00018496736,0.0633421,0.8516921,0.082977794],"study_design_scores_gemma":[0.002544674,0.00592193,0.03932103,0.00018164348,0.00003071471,0.00064158504,0.000015815214,0.3240694,0.0025959,0.16981946,0.45260918,0.0022486406],"about_ca_topic_score_codex":0.000025390693,"about_ca_topic_score_gemma":0.000002806564,"teacher_disagreement_score":0.5406203,"about_ca_system_score_codex":0.00007579436,"about_ca_system_score_gemma":0.000101359205,"threshold_uncertainty_score":0.2127327},"labels":[],"label_agreement":null},{"id":"W2123742395","doi":"10.1109/hase.2008.8","title":"Mutation-Based Testing of Format String Bugs","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Set (abstract data type); Mutation; Mutation testing; Exploit; Source code; Fuzz testing; String (physics); Programming language; Data mining; Software engineering; Software; Computer security","score_opus":0.05404628711613114,"score_gpt":0.2537613083169688,"score_spread":0.19971502120083767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123742395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08473109,0.000013101613,0.90620786,0.000053554144,0.000034065713,0.0000460805,2.672647e-7,0.006621704,0.002292248],"genre_scores_gemma":[0.54061997,1.5261942e-7,0.45927742,0.000076444965,0.000005486339,0.0000024933881,2.8925015e-7,0.000002239399,0.000015479654],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994142,0.000012934802,0.00016775302,0.00012316692,0.00015775408,0.00012417007],"domain_scores_gemma":[0.99891114,0.0005952825,0.00007691228,0.00026504442,0.00011931059,0.000032289157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014582688,0.000061549494,0.00008257437,0.000091053545,0.00009247103,0.000016927172,0.00031925802,0.000022564078,0.0000027188971],"category_scores_gemma":[0.00052007264,0.000054756827,0.00002546217,0.0003657848,0.000029064575,0.0001884175,0.000059096565,0.00004676633,0.000005421599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009250193,0.00032510384,0.6316602,0.00021085516,0.000025210255,0.00021878691,0.0025584784,0.007065741,0.002009826,0.020935044,0.030002575,0.30497894],"study_design_scores_gemma":[0.00029505114,0.00017683672,0.015948962,0.00010364616,0.0000027740975,0.00014701072,0.000004600708,0.9039286,0.059699036,0.019363053,0.00009480009,0.00023564864],"about_ca_topic_score_codex":0.00014807096,"about_ca_topic_score_gemma":6.8793196e-7,"teacher_disagreement_score":0.89686286,"about_ca_system_score_codex":0.000013272264,"about_ca_system_score_gemma":0.00007758351,"threshold_uncertainty_score":0.22329186},"labels":[],"label_agreement":null},{"id":"W2124177996","doi":"10.1109/ares.2008.46","title":"Fuzzy Belief-Based Supervision","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Continuation; Formalism (music); Fuzzy logic; Fuzzy set; Artificial intelligence; Set (abstract data type); Software; Finite-state machine; Machine learning; Data mining; Algorithm; Programming language","score_opus":0.033630172601859354,"score_gpt":0.24897475747999112,"score_spread":0.21534458487813177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124177996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019472223,0.00005218578,0.94096535,0.00091137254,0.000111041656,0.000058401387,2.2770706e-7,0.023860198,0.0145689985],"genre_scores_gemma":[0.5634712,0.0000023190255,0.4353397,0.0009739471,0.000016395978,0.0000038762773,6.118149e-7,0.000003623992,0.00018837082],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99931026,0.000022423315,0.00010169966,0.00022067352,0.00018502572,0.00015992246],"domain_scores_gemma":[0.9992002,0.00016006545,0.00001856918,0.00050690403,0.00005476937,0.000059466183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013275971,0.00007699561,0.00007628361,0.00007627953,0.00014373082,0.000031714415,0.0005165811,0.000037070877,0.000011795906],"category_scores_gemma":[0.00010473186,0.00006260687,0.000038349266,0.00025094236,0.000029684848,0.00014795102,0.00010610497,0.00006179858,0.00010005466],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008117263,0.0003780131,0.079386525,0.000024431678,0.000009347376,0.00038421623,0.00071382604,0.00014610303,0.0007643568,0.050580967,0.731302,0.13630208],"study_design_scores_gemma":[0.0019354105,0.0012274316,0.09382829,0.00019962575,0.000009231225,0.0009703526,0.000004642182,0.40135345,0.044685848,0.4229551,0.030882346,0.001948261],"about_ca_topic_score_codex":0.0000973277,"about_ca_topic_score_gemma":0.0000011357657,"teacher_disagreement_score":0.70041966,"about_ca_system_score_codex":0.0000134467,"about_ca_system_score_gemma":0.00005350801,"threshold_uncertainty_score":0.2553034},"labels":[],"label_agreement":null},{"id":"W2124559112","doi":"10.1007/s10515-008-0043-7","title":"Parameter reference immutability: formal definition, inference tool, and comparison","year":2008,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Immutability; Correctness; Computer science; Scalability; Component (thermodynamics); Inference; Object (grammar); Programming language; Abstraction; Theoretical computer science; Artificial intelligence","score_opus":0.04144959300512138,"score_gpt":0.2640226251437893,"score_spread":0.22257303213866794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124559112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34209675,0.00014305233,0.6192803,0.000023712242,0.00009468804,0.00008773963,0.0000029296864,0.038249783,0.000021094502],"genre_scores_gemma":[0.5963822,0.000015624095,0.40348348,0.00006151899,0.000009498167,0.000026500042,0.00000879028,0.000009624868,0.0000027393467],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985068,0.000030202735,0.00037113667,0.0004104404,0.00023601028,0.00044545298],"domain_scores_gemma":[0.9979859,0.0011441994,0.00008366991,0.0005647791,0.000118782824,0.00010264184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002445326,0.0002436049,0.00028163393,0.00015709658,0.00022204727,0.000119984026,0.00044134248,0.00013070175,0.000003672734],"category_scores_gemma":[0.0022383432,0.00024618133,0.00003936079,0.00038851175,0.0000625823,0.0008303867,0.00030533684,0.00027562186,0.000011736283],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023858769,0.00048852706,0.841191,0.0007109115,0.00019239652,0.00038560724,0.0070611327,0.011347675,0.0008294973,0.029417887,0.013336695,0.09501481],"study_design_scores_gemma":[0.00030590568,0.00015855081,0.23659754,0.00017295963,0.0000103925,0.00036470633,0.0000032526762,0.7562332,0.0009666732,0.0040150336,0.00050567137,0.00066608563],"about_ca_topic_score_codex":0.0000436265,"about_ca_topic_score_gemma":6.7375663e-7,"teacher_disagreement_score":0.74488556,"about_ca_system_score_codex":0.00004768649,"about_ca_system_score_gemma":0.000059983526,"threshold_uncertainty_score":0.99999905},"labels":[],"label_agreement":null},{"id":"W2124756729","doi":"10.1007/978-3-540-30482-1_12","title":"Formal Models for Web Navigations with Session Control and Browser Cache","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Session (web analytics); Web modeling; Web application security; World Wide Web; Web page; Web service; Web navigation; Web API; Static web page; Cache; Web development; Operating system","score_opus":0.018218756490812737,"score_gpt":0.249842034535426,"score_spread":0.23162327804461327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124756729","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011834078,0.00023505272,0.99604917,0.0006293357,0.00024996026,0.0006334459,0.000011896997,0.001673988,0.00039882847],"genre_scores_gemma":[0.45195484,0.0000056667122,0.54714084,0.0007233339,0.00009205829,0.000029826635,0.0000032255482,0.00002063251,0.000029598097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758464,0.000014881827,0.000306478,0.0010287099,0.00052617845,0.00053909817],"domain_scores_gemma":[0.9979024,0.0007053176,0.00020266767,0.00077916065,0.00026699394,0.00014348184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061989407,0.0003983715,0.00038568585,0.0003877619,0.00040577096,0.00043034228,0.0012654752,0.00020696888,0.0000012230101],"category_scores_gemma":[0.00007511592,0.00030973,0.000065224,0.00028392018,0.00047966972,0.0009563129,0.0004416137,0.00045017633,0.0000013508163],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031352356,0.000045404013,0.00022107206,0.00013073659,0.000021443851,0.000051677856,0.0010373965,0.12603861,0.00009647371,0.08729708,0.00009427871,0.78493446],"study_design_scores_gemma":[0.0004146428,0.00020793515,0.0000347744,0.00054617197,0.000007855561,0.000086719665,2.4520581e-8,0.5209059,0.00012464098,0.47731918,0.00006198025,0.0002901836],"about_ca_topic_score_codex":0.00003064285,"about_ca_topic_score_gemma":0.00002261269,"teacher_disagreement_score":0.7846443,"about_ca_system_score_codex":0.00017338138,"about_ca_system_score_gemma":0.0007164904,"threshold_uncertainty_score":0.9999355},"labels":[],"label_agreement":null},{"id":"W2125172218","doi":"10.1109/infcom.1996.493058","title":"Context independent unique sequences generation for protocol testing","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Context (archaeology); Protocol (science); Geology; Paleontology","score_opus":0.16702740374403804,"score_gpt":0.31924741069067436,"score_spread":0.15222000694663632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125172218","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029791103,0.0000054323286,0.9678216,0.0004531509,0.00006167117,0.020521687,5.7651937e-7,0.0080490215,0.0027889616],"genre_scores_gemma":[0.2235339,1.3618671e-7,0.71580046,0.00064864516,0.000090913934,0.05944345,6.328982e-7,0.0000074453233,0.00047439637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991219,0.000037674043,0.00019360747,0.00030352222,0.00015418968,0.0001890793],"domain_scores_gemma":[0.99906063,0.00030949854,0.00008349379,0.00031151035,0.00018506222,0.000049829545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035245766,0.00010281322,0.000092748436,0.0000650941,0.00016355053,0.00020218844,0.00042317025,0.00005509688,0.000016710459],"category_scores_gemma":[0.0006091703,0.00008461924,0.00003007044,0.00020871783,0.000021768392,0.00030085916,0.00007667084,0.00006683729,0.000012758694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029013445,0.00014742935,0.005827523,0.00006025254,0.000011357476,0.000011815825,0.0006043787,0.000090614805,0.005246445,0.05291598,0.13860278,0.7964785],"study_design_scores_gemma":[0.00028534757,0.00029487454,0.00009603943,0.000039254923,0.0000017318885,0.000039884635,0.0000030260794,0.9432985,0.018198133,0.033364702,0.0041567655,0.00022170643],"about_ca_topic_score_codex":0.000104268605,"about_ca_topic_score_gemma":0.000015380389,"teacher_disagreement_score":0.9432079,"about_ca_system_score_codex":0.00003639395,"about_ca_system_score_gemma":0.000029870556,"threshold_uncertainty_score":0.34506726},"labels":[],"label_agreement":null},{"id":"W2125389711","doi":"10.1109/compsac.2007.11","title":"A Combined Concept Location Method for Java Programs","year":2007,"lang":"en","type":"article","venue":"Proceedings - International Computer Software & Applications Conference","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; Laurentian University","funders":"","keywords":"Debugging; Computer science; Tracing; Java; Profiling (computer programming); Graph; Call graph; Static analysis; Programming language; Software; Source code; Theoretical computer science; Distributed computing","score_opus":0.0300423036523799,"score_gpt":0.31690703169339296,"score_spread":0.28686472804101304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125389711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017606253,0.00003354005,0.98780686,0.001105922,0.00036187124,0.0014431004,0.000009049713,0.008513327,0.0005502664],"genre_scores_gemma":[0.19890405,0.0000031232466,0.7987918,0.0005926362,0.0003366237,0.0011138882,0.00008298391,0.000025573452,0.00014929341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974917,0.000012603037,0.0006091169,0.00091934635,0.0005047088,0.0004625288],"domain_scores_gemma":[0.9953102,0.0005821989,0.00040563606,0.00041956658,0.0031018055,0.00018061268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009427387,0.0003141777,0.0002689549,0.00031542298,0.00030018843,0.00069944316,0.0022989062,0.00014965702,0.0000066389453],"category_scores_gemma":[0.00025765316,0.00033180253,0.00011419097,0.0007740819,0.00010293277,0.00068711926,0.00045157515,0.00023344818,0.000023564573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021804739,0.00020439077,0.0023921279,0.000044128323,0.000046808585,8.211719e-7,0.0006627298,0.000016229129,0.0000750951,0.36899772,0.0056438567,0.6218943],"study_design_scores_gemma":[0.0015782418,0.00067090435,0.0044600246,0.00030539214,0.000044637007,0.00011896584,0.00003983914,0.50340784,0.003777419,0.41904882,0.06534649,0.0012014424],"about_ca_topic_score_codex":0.000042549116,"about_ca_topic_score_gemma":0.0000033028966,"teacher_disagreement_score":0.62069285,"about_ca_system_score_codex":0.00016407213,"about_ca_system_score_gemma":0.00016358576,"threshold_uncertainty_score":0.9999134},"labels":[],"label_agreement":null},{"id":"W2125596330","doi":"10.1109/issre.2005.28","title":"Minimization of Randomized Unit Test Cases","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test (biology); Computer science; Minification; Unit (ring theory); Mathematics; Geology; World Wide Web","score_opus":0.019213582231454827,"score_gpt":0.2543931640386862,"score_spread":0.2351795818072314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125596330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056396327,0.000052268526,0.97958565,0.00017031057,0.00004041361,0.00011690362,6.588618e-7,0.00517272,0.009221456],"genre_scores_gemma":[0.64945954,0.0000015638502,0.35005465,0.00004646121,0.000012916171,0.0000067676096,0.0000016278063,0.0000024075684,0.00041405865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994591,0.000045183864,0.00020272692,0.00010979619,0.00010691057,0.000076273805],"domain_scores_gemma":[0.99738705,0.0021787053,0.00008468906,0.00023389452,0.00010168794,0.000013961163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002665283,0.00005458176,0.00017501443,0.000079244106,0.000027810553,0.000029726732,0.00021642724,0.000023914556,0.000009874615],"category_scores_gemma":[0.0013343068,0.00004187767,0.00004642969,0.00023788375,0.00004568403,0.00009523837,0.000050491424,0.00002159756,0.0000041435105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010235419,0.0010403643,0.1320854,0.000110374676,0.000043762633,0.000099277866,0.00042638712,0.00088600646,0.0008328965,0.52663034,0.28052267,0.056299012],"study_design_scores_gemma":[0.054268803,0.0002312167,0.0081803035,0.00016958488,0.00004980251,0.00020169333,0.000005985547,0.390736,0.053542033,0.49079058,0.0011770902,0.00064690143],"about_ca_topic_score_codex":0.00065970875,"about_ca_topic_score_gemma":0.000005503026,"teacher_disagreement_score":0.6438199,"about_ca_system_score_codex":0.0000040893206,"about_ca_system_score_gemma":0.000021807627,"threshold_uncertainty_score":0.17077218},"labels":[],"label_agreement":null},{"id":"W2125727889","doi":"10.1145/1368088.1368136","title":"Sufficient mutation operators for measuring test effectiveness","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutant; Mutation testing; Test suite; Mutation; Measure (data warehouse); Computer science; Process (computing); Mathematics; Test case; Data mining; Genetics; Biology; Machine learning; Programming language; Gene","score_opus":0.04459589575011752,"score_gpt":0.26666301761281497,"score_spread":0.22206712186269745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125727889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14940275,0.000018902401,0.8436256,0.000042916952,0.00010722476,0.00021380009,4.773085e-7,0.006269137,0.00031918855],"genre_scores_gemma":[0.7854305,6.4284217e-7,0.21437979,0.0000666054,0.000018094475,0.000067216664,7.210958e-7,0.0000056028525,0.000030841493],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934417,0.00002928458,0.000100948695,0.0002368239,0.00013534911,0.00015339431],"domain_scores_gemma":[0.99856704,0.0009861529,0.000026540745,0.00023842734,0.00014081666,0.000041024803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003897777,0.00007824453,0.00008648329,0.00007145019,0.00021272963,0.000047852063,0.0002816533,0.00002801187,9.072599e-7],"category_scores_gemma":[0.0008400108,0.000066748384,0.00003643898,0.00021940026,0.000022157292,0.00016232548,0.0000593292,0.000037453105,0.000008091025],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007287495,0.0025825636,0.58932877,0.00064068177,0.000098226716,0.00036482952,0.009866153,0.008115077,0.0199405,0.08927833,0.049939524,0.2297725],"study_design_scores_gemma":[0.0013272826,0.0012046166,0.15019001,0.00021488834,0.000011454504,0.00052668754,0.000013169132,0.47720364,0.34688413,0.020746479,0.00074839726,0.000929252],"about_ca_topic_score_codex":0.000037730224,"about_ca_topic_score_gemma":9.309523e-7,"teacher_disagreement_score":0.63602775,"about_ca_system_score_codex":0.000041832518,"about_ca_system_score_gemma":0.00005000261,"threshold_uncertainty_score":0.272192},"labels":[],"label_agreement":null},{"id":"W2126024083","doi":"10.1109/pacrim.1995.519425","title":"Hardware techniques for testing software components","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Class (philosophy); Software performance testing; Scheme (mathematics); Software; Software engineering; Object-oriented programming; Unit testing; Software testing; System integration testing; Programming language; Component-based software engineering; Software construction; Embedded system; Software system; Artificial intelligence","score_opus":0.0930962594380544,"score_gpt":0.27308306823971595,"score_spread":0.17998680880166157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126024083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027235423,0.00006934046,0.94699866,0.00041120494,0.000107827545,0.00030793675,0.0000034860911,0.048965268,0.002863908],"genre_scores_gemma":[0.06970847,0.0000020753837,0.92854154,0.0007543594,0.00007060777,0.00012837833,0.0000027186697,0.00001950917,0.000772323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998792,0.000023751363,0.00022612949,0.00041485202,0.0001971064,0.00034615144],"domain_scores_gemma":[0.99819213,0.000815932,0.000082943654,0.000607033,0.0002140354,0.00008791292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023930796,0.00016979306,0.00017228865,0.00012395176,0.00023288434,0.00017605121,0.0008909743,0.00007535181,0.000016752347],"category_scores_gemma":[0.0013036056,0.00015312826,0.000071170616,0.0003459419,0.000032733547,0.00031399287,0.00023658267,0.000099910794,0.000035637848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015348245,0.00012023986,0.008819167,0.000050579827,0.000010672755,0.000011583362,0.0001477024,0.0000030808644,0.0004452506,0.003099811,0.25490993,0.73238045],"study_design_scores_gemma":[0.00081908976,0.0010177096,0.0032805814,0.00060350634,0.000026373562,0.0003075222,0.00000589369,0.62145245,0.029610872,0.24216913,0.098772116,0.0019347338],"about_ca_topic_score_codex":0.000041894145,"about_ca_topic_score_gemma":7.327574e-7,"teacher_disagreement_score":0.73044574,"about_ca_system_score_codex":0.000036169695,"about_ca_system_score_gemma":0.000010285335,"threshold_uncertainty_score":0.62443894},"labels":[],"label_agreement":null},{"id":"W2128209135","doi":"10.1109/sefm.2009.12","title":"Checking Sequence Construction Using Adaptive and Preset Distinguishing Sequences","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Sabancı Üniversitesi","keywords":"Sequence (biology); Computer science; Model checking; Algorithm; State (computer science); Finite-state machine; Theoretical computer science; Biology","score_opus":0.07917394972292258,"score_gpt":0.31378634299328745,"score_spread":0.23461239327036487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128209135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06498828,0.0000953816,0.9262182,0.00026385428,0.00010398182,0.00009100969,8.9041123e-7,0.005879851,0.0023585353],"genre_scores_gemma":[0.5298991,0.0000024511148,0.46993962,0.000121297504,0.000027925642,8.9459473e-7,2.6555512e-7,0.0000019648808,0.0000064558535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990726,0.000042790612,0.00015488557,0.00034505266,0.00017181599,0.0002128368],"domain_scores_gemma":[0.9993615,0.00015605697,0.000093370494,0.00024112522,0.0000837038,0.000064243206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030068602,0.00011660134,0.00011952674,0.00007612904,0.00022615235,0.0002951649,0.00031808752,0.000047434616,0.0000018699398],"category_scores_gemma":[0.00035316136,0.00010433073,0.000020206184,0.00021733576,0.000097009884,0.0006388496,0.000108435765,0.000117792864,9.649389e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010756576,0.00004431248,0.032713685,0.000027371949,0.000020316751,0.000118434706,0.002379149,0.00034207708,0.009531123,0.2476265,0.0010118394,0.70617443],"study_design_scores_gemma":[0.00010812225,0.00015863228,0.0032701937,0.0001980189,0.0000075631187,0.0006215966,0.000038997157,0.585444,0.0047726035,0.40497524,0.00005158846,0.00035346512],"about_ca_topic_score_codex":0.0002767649,"about_ca_topic_score_gemma":0.0000023710006,"teacher_disagreement_score":0.705821,"about_ca_system_score_codex":0.000044151304,"about_ca_system_score_gemma":0.000050069397,"threshold_uncertainty_score":0.42544836},"labels":[],"label_agreement":null},{"id":"W2128416870","doi":"10.1007/s00165-005-0083-8","title":"Constructing checking sequences for distributed testing","year":2006,"lang":"en","type":"article","venue":"Formal Aspects of Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observability; Controllability; Computer science; Sequence (biology); Finite-state machine; Theory of computation; Synchronization (alternating current); Automaton; Model checking; Implementation; State (computer science); Sequence diagram; Observable; Reset (finance); Distributed computing; Programming language; Theoretical computer science; Unified Modeling Language; Mathematics; Software","score_opus":0.023429877115581837,"score_gpt":0.25895384582965925,"score_spread":0.2355239687140774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128416870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11475725,0.000039856488,0.87655646,0.000066219895,0.00018936323,0.00017543494,0.0000072837297,0.0045008077,0.0037073207],"genre_scores_gemma":[0.5444501,5.208078e-8,0.45540604,0.00001371165,0.00011344088,0.0000025994198,0.000005634817,0.00000677139,0.0000016604006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839467,0.000024857676,0.00051076064,0.00031591102,0.00023366055,0.00052015967],"domain_scores_gemma":[0.99766564,0.0012363567,0.00046015842,0.00027818984,0.00031512527,0.000044516557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069038355,0.00017511634,0.0002726592,0.000121321,0.00033674735,0.00014811044,0.0006605496,0.00005937865,5.695072e-7],"category_scores_gemma":[0.00087281567,0.00017216407,0.0000882836,0.000554109,0.00008424164,0.00048408422,0.0003118834,0.00012930202,8.933936e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000090909025,0.00009167643,0.06891271,0.0003108633,0.00003107548,0.000023731815,0.00035893515,0.00614594,0.0015837932,0.67571187,0.00081020006,0.24601012],"study_design_scores_gemma":[0.00032951726,0.00016271832,0.004518934,0.00035341884,0.000009062227,0.00013665449,0.000037495378,0.78234357,0.018319618,0.19343984,0.000038273072,0.0003108952],"about_ca_topic_score_codex":0.00022415727,"about_ca_topic_score_gemma":0.000005875989,"teacher_disagreement_score":0.7761976,"about_ca_system_score_codex":0.000062826686,"about_ca_system_score_gemma":0.000094664145,"threshold_uncertainty_score":0.70206475},"labels":[],"label_agreement":null},{"id":"W2128952545","doi":"10.1109/csmr.2002.995791","title":"A generic worklist algorithm for graph reachability problems in program analysis","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reachability; Computer science; Graph; Reachability problem; Theoretical computer science; Algorithm","score_opus":0.030170705854607422,"score_gpt":0.28858534191547247,"score_spread":0.25841463606086507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128952545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012694253,0.00008796212,0.9896477,0.00009383459,0.000046597324,0.0006178111,9.69153e-7,0.007407805,0.00082790427],"genre_scores_gemma":[0.07249476,0.000003139937,0.9266094,0.00011504582,0.000008106976,0.0006383691,0.0000034718282,0.0000065723175,0.0001211658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867135,0.000084605235,0.00027198615,0.0005033287,0.00014986178,0.00031887207],"domain_scores_gemma":[0.99889326,0.00022018107,0.000067046,0.0006575268,0.00009408271,0.00006787302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097221346,0.00013045277,0.00022554408,0.00033645297,0.00006714726,0.000094768206,0.00043016902,0.000062812825,0.0000033726456],"category_scores_gemma":[0.00024433725,0.00011086979,0.00015563073,0.0030451245,0.000040324638,0.00013588721,0.00005577678,0.00008243872,0.0000012741185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.754978e-7,0.00041356342,0.06469536,0.000016400261,0.000051946336,0.0000022040877,0.00016441873,0.00017496193,0.0000041394937,0.0037644713,0.0015582449,0.92915374],"study_design_scores_gemma":[0.00035132826,0.00032094237,0.013434979,0.000024450817,0.000059043774,0.000009074009,0.0000054479624,0.6946968,0.00023486496,0.28670347,0.0036926565,0.00046696007],"about_ca_topic_score_codex":0.0003460082,"about_ca_topic_score_gemma":0.00012054539,"teacher_disagreement_score":0.92868674,"about_ca_system_score_codex":0.000043810353,"about_ca_system_score_gemma":0.00004330883,"threshold_uncertainty_score":0.45211387},"labels":[],"label_agreement":null},{"id":"W2129272701","doi":"10.5539/cis.v3n1p35","title":"A New Method of Reducing Pair-wise Combinatorial Test Suite","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test suite; Computer science; Combinatorial design; Test (biology); Combinatorial explosion; Combinatorial optimization; Test case; Algorithm; Suite; Combinatorial method; Mathematics; Combinatorics; Machine learning","score_opus":0.012833545615482174,"score_gpt":0.2873989325205463,"score_spread":0.27456538690506416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129272701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059543788,0.0000042064285,0.9907081,0.00022318463,0.0010693998,0.00008877275,8.487217e-7,0.001094002,0.00085707643],"genre_scores_gemma":[0.3165407,0.0000012258291,0.6832172,0.00017184096,0.00006117032,0.0000015827152,5.004944e-7,0.0000013289523,0.0000044373737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989625,0.00001404254,0.00029325287,0.00018079563,0.00036236082,0.00018705115],"domain_scores_gemma":[0.9986072,0.00036945584,0.0001655594,0.00043126682,0.0002785508,0.00014797314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013120138,0.00009021974,0.000121976795,0.00029259903,0.00018282997,0.00039176262,0.0008559511,0.000040979176,0.0000026473933],"category_scores_gemma":[0.0005833972,0.00007861711,0.000024546389,0.00087554666,0.00014344996,0.0051395125,0.00044393266,0.00014398733,0.0000061538162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001512926,0.000016932252,0.0025720042,0.000018401473,0.0000012695781,3.4624742e-7,0.002224087,0.000039183986,0.0015062614,0.07578801,0.006014145,0.91181785],"study_design_scores_gemma":[0.00055553066,0.0002964554,0.020051267,0.00007332346,0.0000038797198,0.00014665395,0.0000040669415,0.8876648,0.02048987,0.061558407,0.008832467,0.0003232692],"about_ca_topic_score_codex":0.00008809312,"about_ca_topic_score_gemma":1.6367781e-7,"teacher_disagreement_score":0.91149455,"about_ca_system_score_codex":0.000010650204,"about_ca_system_score_gemma":0.0002475571,"threshold_uncertainty_score":0.3777776},"labels":[],"label_agreement":null},{"id":"W2129718707","doi":"10.1016/j.infsof.2006.11.002","title":"A state-based approach to integration testing based on UML models","year":2006,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Unified Modeling Language; Computer science; Integration testing; Test case; Class diagram; Reliability engineering; Sequence diagram; Data mining; Software; Software engineering; Programming language; Engineering; Machine learning","score_opus":0.01904630375427704,"score_gpt":0.22558055522803536,"score_spread":0.2065342514737583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129718707","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027678187,0.000008449934,0.97656685,0.00065221905,0.000041666477,0.00026808478,0.0000046691016,0.017942674,0.0017475679],"genre_scores_gemma":[0.49604696,1.4461409e-7,0.5028376,0.0010187977,0.000004649957,0.00006753212,0.000014480432,0.0000044637063,0.000005377579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989631,0.00002104367,0.00033476634,0.00022303076,0.00021448736,0.00024353842],"domain_scores_gemma":[0.9989276,0.0002004066,0.00013342728,0.00045597917,0.00023082006,0.000051782994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027622422,0.00016773243,0.0001512245,0.0009256242,0.00016550033,0.00019015493,0.00040365595,0.00014847958,5.5078465e-7],"category_scores_gemma":[0.0007224776,0.00015256695,0.000023873286,0.0010515954,0.0000538751,0.00066036935,0.00008832583,0.0001896377,0.000015799273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013561234,0.00009124882,0.003367295,0.000031029667,0.0000020759448,0.0000017376045,0.00016910191,0.07236279,0.000014676037,0.02648069,0.0037504958,0.8937153],"study_design_scores_gemma":[0.0002563268,0.0001831853,0.0005385278,0.00005626344,0.000001671318,0.000009399037,0.0000043101813,0.9234101,0.00077075337,0.07425653,0.00032712385,0.00018580996],"about_ca_topic_score_codex":0.00011266388,"about_ca_topic_score_gemma":0.0000032918258,"teacher_disagreement_score":0.8935295,"about_ca_system_score_codex":0.00006384207,"about_ca_system_score_gemma":0.00008715895,"threshold_uncertainty_score":0.62214994},"labels":[],"label_agreement":null},{"id":"W2129772051","doi":"10.1109/ares.2007.49","title":"Automatic Failure Detection with Separation of Concerns","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Session (web analytics); Rotation formalisms in three dimensions; Finite-state machine; Separation of concerns; State (computer science); Software; Reliability engineering; Distributed computing; Programming language; Engineering","score_opus":0.015875870747886055,"score_gpt":0.288597716786828,"score_spread":0.27272184603894195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129772051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08479439,0.000004170609,0.9093198,0.00003733393,0.000025641224,0.0000588452,6.1182455e-8,0.004435676,0.001324048],"genre_scores_gemma":[0.67104703,8.8685674e-8,0.32887685,0.000031050462,0.000009153967,0.0000017268944,1.5429673e-7,0.0000017437897,0.00003219069],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995578,0.000010147092,0.00011032261,0.000106392254,0.00012778062,0.000087570435],"domain_scores_gemma":[0.99951965,0.000115980634,0.000064476495,0.00020707729,0.000069542875,0.00002327986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024471618,0.00004777447,0.000061571496,0.00006368719,0.00003222232,0.000021983738,0.00014744725,0.000027678523,0.0000063159646],"category_scores_gemma":[0.000041086565,0.00003547371,0.000012751171,0.00024304731,0.00002030683,0.00015922876,0.000022867836,0.000036170277,0.0000050553676],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012342233,0.00008611085,0.015800156,0.00006242721,0.000023999723,0.000014493299,0.0014630437,0.00006060996,0.0099089565,0.012297664,0.005346802,0.9549234],"study_design_scores_gemma":[0.00043834318,0.0009469601,0.02510928,0.00012647905,0.0000126712575,0.00013145394,0.000034047145,0.41652298,0.53226125,0.02326209,0.0008025486,0.00035190865],"about_ca_topic_score_codex":0.000071368726,"about_ca_topic_score_gemma":0.00008989596,"teacher_disagreement_score":0.9545715,"about_ca_system_score_codex":0.000016356835,"about_ca_system_score_gemma":0.000018674666,"threshold_uncertainty_score":0.1446576},"labels":[],"label_agreement":null},{"id":"W2130262632","doi":"10.1016/j.tcs.2009.07.057","title":"Covering arrays avoiding forbidden edges","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University; University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Pairwise comparison; Clique; Generalization; Enhanced Data Rates for GSM Evolution; Binary number; Software; Mathematics; Computer science; Algorithm; Theoretical computer science; Combinatorics; Discrete mathematics; Artificial intelligence; Arithmetic; Programming language","score_opus":0.01674969832501048,"score_gpt":0.26296799658636427,"score_spread":0.2462182982613538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130262632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008749225,0.000028258208,0.9780349,0.0012439643,0.00039873767,0.00009986385,2.7271346e-7,0.006782939,0.0046618152],"genre_scores_gemma":[0.6313791,0.0000017670515,0.36763588,0.0008659441,0.00010671673,0.0000019295137,1.3853018e-7,0.0000040045447,0.0000044616468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977327,0.00007498666,0.00023289362,0.00069889467,0.00061251066,0.00064803194],"domain_scores_gemma":[0.9981811,0.00044934067,0.00006313125,0.00091802084,0.00014218841,0.00024622353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018118455,0.0001906083,0.00019561256,0.00021266018,0.00067050074,0.0007038898,0.0027972744,0.00004996977,0.000007609155],"category_scores_gemma":[0.0004454291,0.0001628088,0.00006432024,0.0010843537,0.00088077714,0.0007987612,0.00064882333,0.0002714918,0.000046757228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017048005,0.000026055955,0.00007833748,0.0000027160115,9.618645e-7,0.000011182676,0.0002836821,0.000058887566,0.00062270934,0.8574613,0.00043812898,0.14101438],"study_design_scores_gemma":[0.000077962344,0.00021772174,0.0009509481,0.000051949988,0.0000018111718,0.000066268076,8.368371e-7,0.25710714,0.010352622,0.7308683,0.00008283999,0.00022161593],"about_ca_topic_score_codex":0.0000024080912,"about_ca_topic_score_gemma":4.0359705e-8,"teacher_disagreement_score":0.62262994,"about_ca_system_score_codex":0.00006828618,"about_ca_system_score_gemma":0.00009222609,"threshold_uncertainty_score":0.6787626},"labels":[],"label_agreement":null},{"id":"W2131009004","doi":"10.1002/spe.452","title":"A framework for table driven testing of Java classes","year":2002,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Unit testing; Java; Software portability; Tuple; Class (philosophy); Table (database); Programming language; Integration testing; Interface (matter); Standardization; Software engineering; Class hierarchy; Reuse; Object-oriented programming; Data mining; Operating system; Artificial intelligence; Software; Engineering","score_opus":0.06962558702449549,"score_gpt":0.33178758210427484,"score_spread":0.26216199507977933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131009004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007245558,0.0008334445,0.98798347,0.0005525167,0.00014055321,0.00018563356,0.000002656996,0.0027324269,0.0003237183],"genre_scores_gemma":[0.27404347,0.00004992056,0.72529787,0.00045237585,0.00003640014,0.00007775104,3.1417872e-7,0.000009280457,0.000032627315],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987998,0.00004348678,0.0002447688,0.0004050991,0.00021320299,0.00029361894],"domain_scores_gemma":[0.99247444,0.006387981,0.000250362,0.0004887015,0.00031146567,0.00008704801],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00025185745,0.0001414069,0.00018775223,0.00006757676,0.00023123667,0.00015459933,0.0005055972,0.000088206376,0.0000072690214],"category_scores_gemma":[0.026222989,0.00013460565,0.000032059852,0.00050832203,0.00011270258,0.0012185579,0.0002111712,0.0001494579,0.0000042928746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006028726,0.00081220694,0.07285553,0.00042689312,0.00007039513,0.00007327043,0.056018233,0.00008679315,0.0011866641,0.06400716,0.027638536,0.77676404],"study_design_scores_gemma":[0.0017680902,0.0041352673,0.0030875865,0.0026829063,0.0001691025,0.0015087746,0.003711498,0.23297597,0.025981456,0.5739478,0.14679442,0.0032371518],"about_ca_topic_score_codex":0.000079792146,"about_ca_topic_score_gemma":5.3379966e-7,"teacher_disagreement_score":0.77352685,"about_ca_system_score_codex":0.000015646723,"about_ca_system_score_gemma":0.00003395508,"threshold_uncertainty_score":0.98197955},"labels":[],"label_agreement":null},{"id":"W2131288453","doi":"10.1016/s0140-3664(00)00229-2","title":"Rapid generation of functional tests using MSCs, SDL and TTCN","year":2001,"lang":"en","type":"article","venue":"Computer Communications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.21870477160732624,"score_gpt":0.32048971299808116,"score_spread":0.10178494139075492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131288453","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019238777,0.0010286181,0.97726,0.00074710435,0.000112696536,0.00008727076,0.0000012133999,0.0012850238,0.00023927563],"genre_scores_gemma":[0.4485733,0.00011082827,0.55106086,0.00017021535,0.00005654301,0.0000058102664,0.000008370308,0.0000045556217,0.000009505567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992672,0.00010043359,0.00022019951,0.00018490516,0.00011729158,0.00010995482],"domain_scores_gemma":[0.9979263,0.00030931554,0.000105765605,0.0014428628,0.00016950912,0.000046224126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022501765,0.00008878603,0.00011321588,0.00012540596,0.00025063806,0.00008367423,0.0008071628,0.00004205219,0.0000032193582],"category_scores_gemma":[0.00004924605,0.00009192053,0.000032101223,0.0003486389,0.00010815922,0.0002497711,0.0007587759,0.00010379205,0.0000029247772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004821301,0.00050386274,0.028637711,0.000030021953,0.00006841343,0.000004949072,0.0014849697,0.0019146878,0.004268557,0.07205058,0.032822248,0.8582092],"study_design_scores_gemma":[0.00011989396,0.0000445336,0.010897394,0.000035716843,0.0000066934986,0.0000975215,0.0000012327255,0.97862196,0.00010082478,0.0066546365,0.003305198,0.00011439502],"about_ca_topic_score_codex":0.000051634073,"about_ca_topic_score_gemma":0.0000070478472,"teacher_disagreement_score":0.9767073,"about_ca_system_score_codex":0.00002294171,"about_ca_system_score_gemma":0.00004798361,"threshold_uncertainty_score":0.374841},"labels":[],"label_agreement":null},{"id":"W2132123383","doi":"10.1109/ccece.2004.1345041","title":"Incorporating a contract-based test facility to the GUI framework","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Graphical user interface; Graphical user interface testing; Reuse; Software engineering; Testability; Source code; Object-oriented programming; Software; Code coverage; Code reuse; Test case; User interface; Programming language; Reliability engineering; Engineering; User interface design","score_opus":0.022751505782270087,"score_gpt":0.27067079836287283,"score_spread":0.24791929258060275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132123383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037371898,0.000012541242,0.97381985,0.012228536,0.00009976762,0.00020025513,0.0000033821889,0.009209137,0.0006893328],"genre_scores_gemma":[0.5355795,5.1334858e-8,0.4600082,0.004354818,0.000022904893,0.000021307193,4.6416477e-7,0.0000023354141,0.0000104043875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990101,0.000033227392,0.00019020909,0.00030978277,0.00023335624,0.00022334792],"domain_scores_gemma":[0.9975288,0.0013169729,0.00006289778,0.0008928894,0.00010305762,0.000095414616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006109239,0.00011863987,0.00011076143,0.00004532273,0.00021547271,0.00022741003,0.00095510675,0.00006137051,0.000006809801],"category_scores_gemma":[0.003983397,0.00007694184,0.000043835662,0.000496866,0.00003882331,0.00011536366,0.00017708841,0.00020106438,0.00013101904],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025010166,0.0011429583,0.17312223,0.00006048017,0.000032497966,0.0001512399,0.004244715,0.016571982,0.0009434721,0.31307727,0.07279809,0.41783005],"study_design_scores_gemma":[0.00054712256,0.0006594694,0.024687514,0.00029460393,0.000008513021,0.000037480197,0.000015203518,0.05976473,0.012141624,0.8963342,0.004701362,0.0008082045],"about_ca_topic_score_codex":0.0005104559,"about_ca_topic_score_gemma":0.00004094998,"teacher_disagreement_score":0.5832569,"about_ca_system_score_codex":0.000053869433,"about_ca_system_score_gemma":0.00014524908,"threshold_uncertainty_score":0.47687858},"labels":[],"label_agreement":null},{"id":"W2132409828","doi":"10.1145/2597809.2597823","title":"em-SPADE","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Compiler; Bridge (graph theory); Programming language; Parallel computing; Computer architecture; Embedded system","score_opus":0.011332472989620519,"score_gpt":0.2311082114029438,"score_spread":0.2197757384133233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132409828","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010280185,0.0000064021424,0.9582321,0.00045855367,0.00008220475,0.00001764533,2.247049e-8,0.018789327,0.021385694],"genre_scores_gemma":[0.4871724,2.6756973e-7,0.51143324,0.0009321464,0.000025887442,0.00000246755,9.0762164e-8,0.0000021015592,0.0004313815],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99959725,0.000018380597,0.000055588876,0.000138263,0.00008384765,0.00010669637],"domain_scores_gemma":[0.999415,0.00013700567,0.000014717654,0.00037588913,0.000020556543,0.000036875666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019483561,0.000042677788,0.00004588838,0.000033328855,0.000038652113,0.00007315968,0.00042542655,0.000019551253,0.000008694867],"category_scores_gemma":[0.0002007511,0.000034038818,0.000017320112,0.00010889898,0.000007897442,0.00009247968,0.00010787038,0.000037623584,0.000110014174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.307403e-7,0.000021941052,0.003223512,0.000003871654,0.0000021428423,0.0000020265811,0.00020075518,0.00000505357,0.000074618496,0.28345188,0.21480817,0.4982057],"study_design_scores_gemma":[0.00011947972,0.000114605195,0.0065334872,0.000018610239,0.0000014216306,0.0000298427,0.0000013463158,0.2128658,0.0037544852,0.7378527,0.038455904,0.00025234715],"about_ca_topic_score_codex":0.000019745648,"about_ca_topic_score_gemma":0.0000013968123,"teacher_disagreement_score":0.49795336,"about_ca_system_score_codex":0.0000048357806,"about_ca_system_score_gemma":0.000006843205,"threshold_uncertainty_score":0.14140463},"labels":[],"label_agreement":null},{"id":"W2132430857","doi":"10.1109/icsm.2004.1357874","title":"Context driven slicing based coupling measures","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Program slicing; Slicing; Computer science; Coupling (piping); Context (archaeology); Source code; Software quality; Programming language; Software; Object-oriented programming; Code (set theory); Distributed computing; Software development; Engineering; Computer graphics (images)","score_opus":0.03167786515567414,"score_gpt":0.2563372031324804,"score_spread":0.22465933797680623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132430857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008050135,0.000044552886,0.97451955,0.0009727458,0.00009853811,0.00007189776,1.520146e-7,0.015120505,0.0011219048],"genre_scores_gemma":[0.6589238,5.9704774e-7,0.34001482,0.0010121745,0.00001903356,0.000005755856,2.7834926e-7,0.000005443521,0.000018105355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991927,0.000009122556,0.00013450325,0.00024961875,0.00021321281,0.00020081065],"domain_scores_gemma":[0.9992261,0.00016620447,0.000041339288,0.00041353144,0.000087498825,0.00006532417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025026072,0.00009858404,0.00010817966,0.00008345651,0.00012344355,0.0001232503,0.0005150293,0.0000400678,0.0000042738925],"category_scores_gemma":[0.00022280769,0.00008508947,0.000044385222,0.0002112128,0.000025573998,0.00015929843,0.000081695434,0.00009041724,0.000032583728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026370155,0.0006133884,0.07377301,0.00010346906,0.000088020184,0.0002833752,0.0043660128,0.15927885,0.009139443,0.41492397,0.040303633,0.29710048],"study_design_scores_gemma":[0.0012051403,0.00022877238,0.002508382,0.00035713657,0.000009528228,0.00003663061,0.000021115882,0.84914225,0.051002454,0.09324503,0.0015710776,0.0006724967],"about_ca_topic_score_codex":0.00042720657,"about_ca_topic_score_gemma":0.000026701198,"teacher_disagreement_score":0.6898634,"about_ca_system_score_codex":0.00005145241,"about_ca_system_score_gemma":0.00009430124,"threshold_uncertainty_score":0.3469848},"labels":[],"label_agreement":null},{"id":"W2134274165","doi":"10.1109/aqsdt.1992.205855","title":"SQEngineer: a methodology and tool for specifying and engineering software quality","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Software engineering; Quality (philosophy); Software quality; Computer science; Software quality control; Software; Software quality analyst; Software requirements; Product (mathematics); Software construction; Software development; Programming language","score_opus":0.10247498171315238,"score_gpt":0.33139725545329135,"score_spread":0.22892227374013896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134274165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010954906,0.00029216456,0.9836639,0.000103365455,0.000098966666,0.00013246729,8.662428e-7,0.0046952963,0.00005802966],"genre_scores_gemma":[0.057725128,0.000009512027,0.942,0.00015775555,0.00001786829,0.000026741167,3.375181e-7,0.000008840569,0.000053827036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921304,0.000060990093,0.00016003691,0.0002942595,0.00006474337,0.00020693736],"domain_scores_gemma":[0.9971802,0.0024387925,0.000031375035,0.00025131053,0.000042239237,0.000056070698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012203715,0.00011186848,0.00017497496,0.000077052166,0.000065394226,0.00008217382,0.00012773868,0.00005992507,0.0000018520842],"category_scores_gemma":[0.0038435154,0.00010297986,0.000025388072,0.00011133381,0.000018498673,0.00014331737,0.000078700614,0.000071587645,4.4958674e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000796203,0.000035353485,0.026580783,0.00034240645,0.00004122228,0.000008329631,0.0008917114,0.000102218444,0.0015940961,0.8154629,0.0037119135,0.15122114],"study_design_scores_gemma":[0.0025991183,0.0007059973,0.057680756,0.00023537398,0.000053165226,0.00094632874,0.000043696502,0.13803835,0.021967392,0.7380457,0.03694407,0.0027400695],"about_ca_topic_score_codex":0.00001617267,"about_ca_topic_score_gemma":7.030384e-7,"teacher_disagreement_score":0.14848107,"about_ca_system_score_codex":0.0000117025975,"about_ca_system_score_gemma":0.00001543182,"threshold_uncertainty_score":0.46013245},"labels":[],"label_agreement":null},{"id":"W2134502495","doi":"10.1109/ase.2009.23","title":"Using String Distances for Test Case Prioritisation","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; Computer science; String (physics); Property (philosophy); Code (set theory); Test case; Test (biology); Random testing; Code coverage; Algorithm; Data mining; Theoretical computer science; Machine learning; Programming language; Software; Mathematics","score_opus":0.1170776203460329,"score_gpt":0.3653392665077053,"score_spread":0.2482616461616724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134502495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036431502,0.0001913713,0.9841837,0.0001303496,0.00031733265,0.00041025275,0.000011636756,0.010668049,0.00044413112],"genre_scores_gemma":[0.3408242,0.000005154487,0.65892076,0.000061110666,0.00011492681,0.000022447923,0.0000045755132,0.0000080900845,0.000038772007],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99879706,0.000022835897,0.00026470836,0.0005348767,0.00015378276,0.00022671981],"domain_scores_gemma":[0.99840665,0.00058640307,0.00017991189,0.00062831695,0.00014397893,0.000054721248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036995788,0.00019263614,0.00020627274,0.000113139715,0.00013521705,0.00045624177,0.00053888146,0.00014859014,7.286283e-7],"category_scores_gemma":[0.000570448,0.00019224481,0.00008585857,0.0001215216,0.00001978582,0.00018234315,0.00040650094,0.00019292918,6.355135e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006324554,0.00025144638,0.005582011,0.000700738,0.00003588364,0.0011322005,0.0008525983,0.0024953333,0.00018011214,0.058606327,0.014707566,0.91544944],"study_design_scores_gemma":[0.000110573914,0.0000738605,0.000123869,0.00040846178,0.00001572717,0.0006796712,0.000003813917,0.49301407,0.00058864366,0.50432324,0.00024569957,0.00041237014],"about_ca_topic_score_codex":0.00032620368,"about_ca_topic_score_gemma":0.00002558544,"teacher_disagreement_score":0.9150371,"about_ca_system_score_codex":0.000116855044,"about_ca_system_score_gemma":0.00013212663,"threshold_uncertainty_score":0.7839516},"labels":[],"label_agreement":null},{"id":"W2134872829","doi":"10.1109/csmr.2004.1281420","title":"Source code modularization using lattice of concept slices","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Modular programming; Computer science; Program slicing; Programming language; Code refactoring; Software maintenance; Static program analysis; Slicing; Program analysis; Source code; Modular design; Lattice (music); Theoretical computer science; Software engineering; Software; Software system; Software development","score_opus":0.03697561773179269,"score_gpt":0.2800877208658379,"score_spread":0.2431121031340452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134872829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047145434,0.00003430477,0.9485952,0.00012212001,0.00004652598,0.00004879771,4.0227803e-7,0.003656626,0.00035058742],"genre_scores_gemma":[0.5170497,3.447481e-7,0.48278734,0.000121390825,0.000009782245,6.023196e-7,3.9676797e-7,0.00000308061,0.00002736451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943215,0.000018714403,0.00013614872,0.00016191285,0.00014426211,0.000106808206],"domain_scores_gemma":[0.9994392,0.00007753265,0.00008104346,0.00028951175,0.00008374567,0.00002901087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012553141,0.00006232176,0.00008701874,0.00005579239,0.000055135115,0.00004186028,0.00033680722,0.00003695061,0.0000026820758],"category_scores_gemma":[0.00011737917,0.000056929362,0.000023460534,0.0002588577,0.00003799316,0.00022673148,0.00009703027,0.000041900425,0.0000018856233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010980071,0.0005519891,0.023932137,0.00013965378,0.00007453568,0.000016581233,0.013240332,0.29719537,0.021120697,0.5147469,0.0019353409,0.12703545],"study_design_scores_gemma":[0.00037346547,0.00010836958,0.00084069726,0.00012303765,0.000011206321,0.00003569791,0.000016359296,0.7184913,0.14467835,0.13484931,0.00021114908,0.00026101194],"about_ca_topic_score_codex":0.0003973824,"about_ca_topic_score_gemma":0.000002860702,"teacher_disagreement_score":0.46990424,"about_ca_system_score_codex":0.000021817728,"about_ca_system_score_gemma":0.00004333609,"threshold_uncertainty_score":0.2321512},"labels":[],"label_agreement":null},{"id":"W2135275739","doi":"10.1007/978-3-540-45221-8_22","title":"Towards Automated Support for Deriving Test Data from UML Statecharts","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Automation; Unified Modeling Language; Test case; Programming language; Normalization (sociology); Path (computing); Set (abstract data type); Event (particle physics); Data mining; Software engineering; Software; Machine learning","score_opus":0.04968096074950672,"score_gpt":0.30316102955412755,"score_spread":0.2534800688046208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135275739","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000129666905,0.0001955938,0.9856036,0.0005958552,0.0015303881,0.0005901037,0.00018846069,0.010577665,0.00070542376],"genre_scores_gemma":[0.015266763,0.000021645561,0.9815502,0.0025137172,0.00027237178,0.000024106026,0.0001423129,0.000068551504,0.00014033011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994873,0.000032624965,0.00067780545,0.0025864292,0.0009426525,0.0008875127],"domain_scores_gemma":[0.9930096,0.0020775541,0.00040338695,0.0039471346,0.0003436309,0.00021869219],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016017541,0.00067181926,0.0006746336,0.0006368287,0.00034532495,0.0009428095,0.007350975,0.00040377676,0.000022433327],"category_scores_gemma":[0.0016458903,0.0006410897,0.00010376407,0.0005386778,0.0004523669,0.00086936995,0.002993515,0.0006256827,0.000027865042],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053835756,0.00008768535,0.00044962156,0.000084300525,0.000028085129,0.00016868892,0.00051764515,0.0013405388,0.00014479959,0.001247177,0.014676909,0.98124915],"study_design_scores_gemma":[0.00018809333,0.0001987154,0.00010830749,0.0004021149,0.000012740557,0.00006227405,2.3337684e-8,0.7226633,0.00095991767,0.27029863,0.004389282,0.0007166048],"about_ca_topic_score_codex":0.00010663139,"about_ca_topic_score_gemma":0.000044901106,"teacher_disagreement_score":0.9805326,"about_ca_system_score_codex":0.00025896507,"about_ca_system_score_gemma":0.0009833673,"threshold_uncertainty_score":0.99960405},"labels":[],"label_agreement":null},{"id":"W2135469438","doi":"10.1109/hase.2007.10","title":"Enhanced Traverse of Web Pages","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Traverse; Hyperlink; Computer science; Web testing; Web page; Reliability (semiconductor); Sequence (biology); Web site; Test (biology); World Wide Web; Web navigation; Information retrieval; The Internet; Data mining; Web development; Web application security","score_opus":0.02007141437038364,"score_gpt":0.2660981734370293,"score_spread":0.24602675906664564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135469438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019464808,0.000014726257,0.94757426,0.00006478316,0.00006898604,0.000032142027,1.2780454e-7,0.004944819,0.027835349],"genre_scores_gemma":[0.65864384,0.0000027613335,0.3410576,0.00009065419,0.000008840333,6.1640355e-7,8.467489e-8,0.0000017782199,0.00019385431],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995015,0.000008207849,0.00012313804,0.00012490881,0.000114966875,0.00012722753],"domain_scores_gemma":[0.9993867,0.00019990586,0.000039733004,0.0002929903,0.000046139467,0.000034508274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035518713,0.000049115562,0.00007146694,0.00007044017,0.00001988984,0.000012213288,0.00033377457,0.00002805047,0.00001146478],"category_scores_gemma":[0.000104221304,0.000040852912,0.000028180339,0.00020094449,0.000024573777,0.00008327748,0.00006262167,0.000037909125,0.000011639361],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011079002,0.00017102144,0.0032809188,0.000035471665,0.00001661037,0.000031770076,0.0012241503,0.0000064165442,0.0875436,0.08390112,0.06896661,0.7548112],"study_design_scores_gemma":[0.00023507912,0.00017160465,0.00855253,0.000041817475,0.0000029467717,0.000013287544,0.00001396767,0.0051103276,0.94763786,0.036565382,0.0014434041,0.00021179409],"about_ca_topic_score_codex":0.000018429811,"about_ca_topic_score_gemma":0.0000061602896,"teacher_disagreement_score":0.86009425,"about_ca_system_score_codex":0.000007091189,"about_ca_system_score_gemma":0.000020590871,"threshold_uncertainty_score":0.16659334},"labels":[],"label_agreement":null},{"id":"W2136059906","doi":"10.1109/iceccs.2005.29","title":"Coping with Legacy System Migration Complexity","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Coping (psychology); Computer science; Legacy system; Psychology; Operating system; Software","score_opus":0.03662286275746241,"score_gpt":0.258066197491768,"score_spread":0.2214433347343056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136059906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007540236,0.00001864084,0.96639377,0.0019006775,0.00003515516,0.00007538426,1.3809398e-7,0.0184403,0.005595719],"genre_scores_gemma":[0.5279002,2.0463787e-7,0.47170398,0.0002999482,0.000032593725,0.0000051994616,5.3960264e-7,0.0000025259824,0.000054789445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994102,0.000023162507,0.00010499286,0.00018727136,0.00014474505,0.00012960241],"domain_scores_gemma":[0.9994573,0.00006492756,0.00004312353,0.00033530238,0.000060318336,0.000039004437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014509837,0.00007282471,0.000080894024,0.000047428595,0.00010388353,0.00020255585,0.0002986474,0.000021054777,0.0000028451218],"category_scores_gemma":[0.000017262428,0.00005377519,0.000015468402,0.00017295622,0.000024428531,0.00051923236,0.000057487578,0.000050314193,0.000035290825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009773511,0.000101627214,0.014729079,0.00009639702,0.000019959869,0.000021112925,0.0012462212,0.00033947473,0.00013403269,0.7758793,0.13302027,0.07440271],"study_design_scores_gemma":[0.00056424935,0.00032436184,0.0072207325,0.00032578272,0.000010074392,0.00042120495,0.000038615904,0.9536307,0.007655818,0.008234796,0.020884722,0.00068894017],"about_ca_topic_score_codex":0.00024168844,"about_ca_topic_score_gemma":0.00009076382,"teacher_disagreement_score":0.95329124,"about_ca_system_score_codex":0.00005312324,"about_ca_system_score_gemma":0.000026264439,"threshold_uncertainty_score":0.21928886},"labels":[],"label_agreement":null},{"id":"W2136921053","doi":"10.1109/tse.2010.58","title":"The Effects of Time Constraints on Test Case Prioritization: A Series of Controlled Experiments","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regression testing; Prioritization; Computer science; Context (archaeology); Risk-based testing; Reliability engineering; Process (computing); Software; Regression analysis; Data mining; Risk analysis (engineering); Machine learning; Software development; Engineering; Management science; Software construction","score_opus":0.005484845015205005,"score_gpt":0.2193811498363502,"score_spread":0.21389630482114522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136921053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03091574,0.000032995355,0.9655684,0.000019260504,0.00076848257,0.0003418628,0.000008414631,0.0023229,0.000021933858],"genre_scores_gemma":[0.9067792,0.00000693201,0.09302247,0.000013116885,0.000019064148,0.000086408596,2.8294758e-7,0.000017295186,0.00005519011],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990958,0.000024049954,0.00029137937,0.00019669991,0.00021196008,0.00018010884],"domain_scores_gemma":[0.99574786,0.0034811064,0.000100466656,0.00049156137,0.00011827538,0.000060727532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019214774,0.00016736105,0.00025142677,0.00013032556,0.00015703453,0.000042847478,0.00029726583,0.00007926135,0.0000058163364],"category_scores_gemma":[0.00078194577,0.00013540892,0.000100978454,0.00025795723,0.00010587041,0.00014017551,0.000003675227,0.00024205033,0.0000039673882],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006458235,0.0037602547,0.0010042392,0.0017080426,0.0011307725,0.0018134108,0.0072005093,0.04914959,0.39380094,0.0067457855,0.002264252,0.5307764],"study_design_scores_gemma":[0.0027014995,0.0011912043,0.0001592826,0.00057913846,0.00005098992,0.0009648604,0.000009760905,0.045856323,0.9476696,0.00027825235,0.000082080136,0.0004569596],"about_ca_topic_score_codex":0.000008528981,"about_ca_topic_score_gemma":0.0000014217792,"teacher_disagreement_score":0.8758635,"about_ca_system_score_codex":0.000018553426,"about_ca_system_score_gemma":0.000045998553,"threshold_uncertainty_score":0.55218154},"labels":[],"label_agreement":null},{"id":"W2137519880","doi":"10.1109/ase.2002.1115018","title":"System testing for object-oriented frameworks using hook technology","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test suite; Object-oriented programming; Software engineering; Generator (circuit theory); Suite; Hook; Software bug; Test case; Software; Distributed computing; Embedded system; Programming language; Engineering","score_opus":0.04378043057043085,"score_gpt":0.27130595706913574,"score_spread":0.2275255264987049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137519880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037156208,0.00012796737,0.95686907,0.00025024026,0.00026423452,0.00025710397,7.294664e-7,0.036629118,0.0018858964],"genre_scores_gemma":[0.4009241,2.1385684e-7,0.59879655,0.00012081478,0.000043084263,0.00003207774,1.8837638e-7,0.000010867331,0.00007212276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987767,0.000021059523,0.0002450535,0.00042374444,0.00014491592,0.00038853084],"domain_scores_gemma":[0.99833804,0.0006026312,0.0001109243,0.0006559881,0.00023369373,0.00005870679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023706887,0.00015335859,0.00019015686,0.0002760566,0.00025753278,0.00010361716,0.0006292855,0.00029308166,0.000003226885],"category_scores_gemma":[0.0012698217,0.00014000112,0.000048172602,0.0010967669,0.00004509203,0.00017196704,0.00022200948,0.00026896177,0.000014679001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072560324,0.00031074244,0.036743183,0.00042096176,0.00008209382,0.00011802776,0.0009711694,0.00053953513,0.0032160003,0.39192098,0.050084762,0.5155853],"study_design_scores_gemma":[0.0001386194,0.00013637607,0.000027517463,0.00023885984,0.000006813099,0.00017593495,0.000018548728,0.98376584,0.0016335577,0.013229291,0.00041143293,0.00021718124],"about_ca_topic_score_codex":0.000034548677,"about_ca_topic_score_gemma":5.0881533e-7,"teacher_disagreement_score":0.98322636,"about_ca_system_score_codex":0.00009291712,"about_ca_system_score_gemma":0.000021601547,"threshold_uncertainty_score":0.570908},"labels":[],"label_agreement":null},{"id":"W2138203448","doi":"10.1109/icsecompanion.2007.56","title":"On Sufficiency of Mutants","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mutation; Mutation testing; Computer science; Test suite; Set (abstract data type); Selection (genetic algorithm); Variable (mathematics); Process (computing); Regression analysis; Data mining; Algorithm; Artificial intelligence; Machine learning; Mathematics; Test case; Programming language; Genetics; Biology","score_opus":0.014024968195497286,"score_gpt":0.2740244165764556,"score_spread":0.2599994483809583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138203448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046746936,0.000007854877,0.90975064,0.00005025691,0.00007670546,0.000027977356,1.0702356e-7,0.0041002557,0.039239258],"genre_scores_gemma":[0.8033654,2.8145286e-7,0.19635816,0.0001793999,0.0000054460465,3.0786842e-7,4.615036e-8,0.0000016816358,0.00008925663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99948406,0.000006225945,0.00011154745,0.00012307818,0.00014958413,0.00012552498],"domain_scores_gemma":[0.9992645,0.00032298113,0.000034206176,0.00030968,0.00003863417,0.000029994333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041696973,0.000042630716,0.00005553514,0.00008687174,0.000023335677,0.000010529878,0.0003766491,0.000021314514,0.000007731312],"category_scores_gemma":[0.00023069592,0.000033321536,0.000019453564,0.00026388248,0.000019931193,0.00004904206,0.00005798362,0.000037239166,0.000015209758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000553485,0.00022647026,0.005756732,0.000007866207,0.0000029319579,0.000026667125,0.00035434193,0.0000080600985,0.0008994425,0.7707176,0.013744322,0.20824999],"study_design_scores_gemma":[0.00036169894,0.0013013321,0.048927136,0.00012394703,0.0000031457785,0.00005894737,0.0000099721565,0.022673905,0.1844903,0.7408303,0.00075453153,0.0004647829],"about_ca_topic_score_codex":0.00002897622,"about_ca_topic_score_gemma":0.000001278031,"teacher_disagreement_score":0.7566185,"about_ca_system_score_codex":0.000008237865,"about_ca_system_score_gemma":0.000014234204,"threshold_uncertainty_score":0.13588129},"labels":[],"label_agreement":null},{"id":"W2138693312","doi":"10.1109/agile.2011.23","title":"Rule-Based Exploratory Testing of Graphical User Interfaces","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Graphical user interface testing; Keyword-driven testing; Automation; Graphical user interface; Manual testing; Software engineering; Exploratory research; Test (biology); Software bug; Human–computer interaction; Data mining; User interface; Programming language; Software; User interface design; Software development; Engineering","score_opus":0.08777935105846328,"score_gpt":0.2585833439144655,"score_spread":0.17080399285600223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138693312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16325928,0.00002731007,0.8240151,0.00004865649,0.0000932369,0.00005733402,3.6145627e-7,0.008915864,0.003582902],"genre_scores_gemma":[0.54026693,1.674975e-7,0.45959455,0.00011457472,0.0000049442892,0.0000058152355,9.027874e-8,0.00000402698,0.000008916991],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992296,0.00004443522,0.00019660742,0.00022354508,0.00014934129,0.00015645151],"domain_scores_gemma":[0.99893594,0.0003408564,0.00008062443,0.0004578752,0.00013004156,0.000054674034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030297643,0.00009573424,0.000121613295,0.00013454552,0.00003962651,0.000024298979,0.00065473246,0.000046230434,0.00001545234],"category_scores_gemma":[0.00039134995,0.00007811125,0.000035267003,0.0004109049,0.00007970518,0.00020624734,0.00016093516,0.00008920406,0.000010533049],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026772324,0.0006786619,0.82953703,0.00011901132,0.000035888897,0.000053176016,0.0025848579,0.000017216926,0.005909601,0.04513177,0.01704634,0.09885966],"study_design_scores_gemma":[0.0005306223,0.0008834251,0.03779642,0.00041963172,0.00001557751,0.000023389926,0.00003811843,0.050636433,0.693069,0.21561608,0.00022598598,0.0007453489],"about_ca_topic_score_codex":0.00010768879,"about_ca_topic_score_gemma":0.0000021782243,"teacher_disagreement_score":0.7917406,"about_ca_system_score_codex":0.000006721204,"about_ca_system_score_gemma":0.00004901886,"threshold_uncertainty_score":0.3185284},"labels":[],"label_agreement":null},{"id":"W2139217039","doi":"10.1145/379605.379630","title":"Evaluating explicitly context-sensitive program slicing","year":2001,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Context (archaeology); Computer science; Sensitivity (control systems); Program slicing; Slicing; Programming language; World Wide Web; History; Engineering","score_opus":0.10189528572067504,"score_gpt":0.3893126797833766,"score_spread":0.28741739406270156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139217039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08350421,0.000032719006,0.8690688,0.0006123171,0.00011739332,0.0003308159,1.3981713e-7,0.034137256,0.012196371],"genre_scores_gemma":[0.56789845,0.0000016640964,0.43098378,0.00080088887,0.00003943291,0.00003712398,4.8094296e-7,0.000006721797,0.00023147374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879897,0.00006957432,0.00019310832,0.0003636093,0.0002654928,0.00030924054],"domain_scores_gemma":[0.9988224,0.00039594225,0.000069961636,0.00046472627,0.00017003181,0.00007693716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056726625,0.00012886993,0.00014194324,0.00008640139,0.000153952,0.00018106762,0.00041063465,0.000045193847,0.000008637974],"category_scores_gemma":[0.00047172233,0.00011094111,0.000049949973,0.00039868648,0.000028779676,0.00026794997,0.0001959566,0.00011562419,0.00005451072],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002368441,0.000045699067,0.0019099237,0.0000025648317,0.0000055103933,0.000028551365,0.00049817417,0.000010520099,0.0002863441,0.0059736874,0.0030429638,0.9881937],"study_design_scores_gemma":[0.0005634577,0.0010676135,0.005368965,0.0002056978,0.000012277264,0.00045891068,0.00010763244,0.9304666,0.009719479,0.04825286,0.0030839827,0.0006925439],"about_ca_topic_score_codex":0.0002985689,"about_ca_topic_score_gemma":0.000012109689,"teacher_disagreement_score":0.98750114,"about_ca_system_score_codex":0.000036835943,"about_ca_system_score_gemma":0.000039744653,"threshold_uncertainty_score":0.45240474},"labels":[],"label_agreement":null},{"id":"W2139640569","doi":"10.1109/ccece.1998.682749","title":"Extended TTCN in software testing","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; White-box testing; Integration testing; Non-regression testing; Software reliability testing; Test strategy; System integration testing; Manual testing; Keyword-driven testing; Software performance testing; Test Management Approach; Software engineering; Black-box testing; Unit testing; Regression testing; Development testing; Conformance testing; Model-based testing; Process (computing); Software construction; Software; Test case; Programming language; Software development; Operating system","score_opus":0.05911903413093896,"score_gpt":0.2531458989008313,"score_spread":0.1940268647698923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139640569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047731954,0.00016262036,0.94794333,0.00044925403,0.00011559947,0.00010289509,2.2385571e-7,0.030445023,0.016007869],"genre_scores_gemma":[0.35959992,0.0000013736856,0.6396471,0.000370159,0.000016017728,0.000009801469,1.1276253e-7,0.000005431224,0.00035004973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910545,0.000028665754,0.00016604805,0.00029186517,0.00015097787,0.00025697346],"domain_scores_gemma":[0.99890804,0.0005009611,0.00003623461,0.00045454857,0.00004764318,0.00005258662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020667155,0.00009753096,0.00010291357,0.00013547126,0.000057184385,0.000089603374,0.0005718476,0.000043259777,0.000036757738],"category_scores_gemma":[0.0014019251,0.00008805077,0.000022647819,0.0007553506,0.000019243917,0.0002431638,0.0001808195,0.00011868873,0.00009094067],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.329786e-7,0.00012277938,0.06731248,0.000011157828,0.000002152972,0.000097418546,0.00033712818,0.000023161989,0.000053547697,0.0037081188,0.03772103,0.8906106],"study_design_scores_gemma":[0.00050845795,0.000224183,0.07626025,0.00021022455,0.0000027770707,0.00022595335,0.000005684501,0.6654423,0.001160669,0.25377885,0.0014206975,0.00075998507],"about_ca_topic_score_codex":0.00010493291,"about_ca_topic_score_gemma":0.0000048946063,"teacher_disagreement_score":0.8898506,"about_ca_system_score_codex":0.000028981509,"about_ca_system_score_gemma":0.000010220558,"threshold_uncertainty_score":0.35906062},"labels":[],"label_agreement":null},{"id":"W2140714756","doi":"10.1109/iceccs.2008.17","title":"On Extracting Tests from a Testable Model in the Context of Domain Engineering","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Domain (mathematical analysis); Domain engineering; Computer science; Domain analysis; Domain model; Executable; Model-based testing; Context (archaeology); Test case; Feature-oriented domain analysis; Data mining; Software engineering; Reliability engineering; Software; Software system; Machine learning; Programming language; Domain knowledge; Engineering; Mathematics; Component-based software engineering","score_opus":0.03282684462641823,"score_gpt":0.2453074403543252,"score_spread":0.21248059572790695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140714756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3722126,0.000028961627,0.6247908,0.00014208058,0.00002163127,0.00007039188,8.254334e-7,0.0014930437,0.0012396737],"genre_scores_gemma":[0.63927656,0.0000010733197,0.36047778,0.00021524762,0.000006163763,0.0000074648137,2.5851557e-7,0.0000035553692,0.000011910613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993126,0.000023174445,0.00016245073,0.00017385179,0.00017697155,0.00015097053],"domain_scores_gemma":[0.99769986,0.0018009819,0.00004847836,0.00040568016,0.000024941019,0.000020089283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002992468,0.00008294746,0.000109168555,0.00007549802,0.000045374687,0.0000229133,0.0005225015,0.00003231115,0.0000015550273],"category_scores_gemma":[0.0005047236,0.000058505197,0.000025836644,0.00023937976,0.000016187527,0.00014529278,0.00006148183,0.00013559355,0.0000030258188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065848195,0.0024012232,0.14761105,0.000104046216,0.00006602145,0.00088272267,0.09274289,0.13633311,0.03556496,0.4256936,0.060918715,0.097615816],"study_design_scores_gemma":[0.00016978064,0.000056612855,0.004098727,0.00008683149,8.807772e-7,0.000028033555,0.000027195207,0.94037,0.002667527,0.052345984,0.000023242917,0.0001251858],"about_ca_topic_score_codex":0.0006041082,"about_ca_topic_score_gemma":0.000010471393,"teacher_disagreement_score":0.8040369,"about_ca_system_score_codex":0.000018750552,"about_ca_system_score_gemma":0.000032550244,"threshold_uncertainty_score":0.23857726},"labels":[],"label_agreement":null},{"id":"W2141291123","doi":"10.1145/1108768.1108795","title":"An empirical framework for comparing effectiveness of testing and property-based formal analysis","year":2005,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Debugging; Computer science; Software engineering; Software bug; Formal methods; Software testing; Empirical research; Formal specification; Software; Reliability engineering; Programming language; Engineering; Mathematics","score_opus":0.042738907365135706,"score_gpt":0.30932317573452706,"score_spread":0.26658426836939136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141291123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28136867,0.00007939571,0.71425414,0.00003981349,0.00003950562,0.00020048441,0.000004298284,0.004013329,3.6655248e-7],"genre_scores_gemma":[0.50416386,2.7056228e-7,0.49569678,0.00003243937,0.00003576134,0.000048747825,0.0000050056583,0.00001684922,2.5122972e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984379,0.000058692658,0.00033951513,0.0005056238,0.00022517641,0.00043309655],"domain_scores_gemma":[0.9087674,0.08991007,0.00011866888,0.00086000824,0.00020751933,0.00013634129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009246205,0.0002706444,0.00050737325,0.00037542183,0.00014460529,0.00012211669,0.0008504962,0.0001420346,8.21754e-7],"category_scores_gemma":[0.119153716,0.00022660114,0.0001243627,0.0010409682,0.00004369324,0.0005045788,0.00023415349,0.00020940644,6.755541e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017946471,0.00007585135,0.93854856,0.00030507697,0.00006830469,0.00000165639,0.0001339323,0.035419382,0.0004932426,0.00028582994,0.000010105576,0.024640108],"study_design_scores_gemma":[0.0003322727,0.0003880212,0.42372862,0.00042231203,0.00012503706,0.000008170239,8.6384756e-7,0.56295705,0.010103117,0.0014680894,0.000025914305,0.00044051878],"about_ca_topic_score_codex":0.000050069008,"about_ca_topic_score_gemma":0.0000020301677,"teacher_disagreement_score":0.5275377,"about_ca_system_score_codex":0.000048654885,"about_ca_system_score_gemma":0.000058999976,"threshold_uncertainty_score":0.92405266},"labels":[],"label_agreement":null},{"id":"W2141469470","doi":"10.1109/apaq.2000.883775","title":"Control of nondeterminism in testing distributed multithreaded programs","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Java; Distributed computing; Programming language; Common Object Request Broker Architecture; Test case; Set (abstract data type); System under test; Constraint (computer-aided design); Control (management)","score_opus":0.06328583041465877,"score_gpt":0.2540138546615939,"score_spread":0.1907280242469351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141469470","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021902328,0.00004488117,0.970451,0.00018134633,0.000049536873,0.0002347516,0.0000019102745,0.0062738243,0.0008604175],"genre_scores_gemma":[0.70101476,3.97209e-7,0.29888487,0.000053229007,0.0000066770444,0.000019053665,6.869729e-7,0.0000037914162,0.000016556352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911135,0.000034459776,0.00026273806,0.00022446865,0.00014497376,0.00022198558],"domain_scores_gemma":[0.99901223,0.0004081595,0.000090426394,0.0003654567,0.00007908542,0.000044650355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020445308,0.000097145625,0.00017070955,0.000086601634,0.000026622001,0.000040760373,0.00045646224,0.000048900707,0.000004744553],"category_scores_gemma":[0.0005826784,0.00008346564,0.00003090443,0.00051320577,0.000043297052,0.00013882226,0.000077529876,0.00008859477,0.000007392683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024148164,0.00042509823,0.23455304,0.000027866936,0.0000071929057,0.000055591066,0.00038250233,0.000034922552,0.00065120374,0.0018376319,0.00094945106,0.76107305],"study_design_scores_gemma":[0.0007325862,0.00022412112,0.012197557,0.00011432548,0.000002706354,0.000029545492,0.000002554593,0.9784843,0.0014878667,0.006427068,0.00011156858,0.0001858493],"about_ca_topic_score_codex":0.0001964172,"about_ca_topic_score_gemma":0.0000062536883,"teacher_disagreement_score":0.97844934,"about_ca_system_score_codex":0.000017445773,"about_ca_system_score_gemma":0.000010350913,"threshold_uncertainty_score":0.340363},"labels":[],"label_agreement":null},{"id":"W2142266413","doi":"10.5555/998675.999415","title":"Using simulation to empirically investigate test coverage criteria based on statechart","year":2004,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Code coverage; Class (philosophy); Test (biology); Test case; Reliability engineering; Fault detection and isolation; Test strategy; Data mining; Machine learning; Artificial intelligence; Programming language; Software; Engineering","score_opus":0.08716524489143154,"score_gpt":0.3492094312045713,"score_spread":0.26204418631313975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142266413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021958219,0.0000015959372,0.97172683,0.00075719523,0.00048129025,0.00015367605,0.000024864557,0.004717476,0.00017884382],"genre_scores_gemma":[0.6258753,4.4488976e-7,0.37287217,0.0011485345,0.000052399533,0.000015021629,0.0000089445875,0.000017456003,0.000009715572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849796,0.000015934349,0.0002684999,0.00045211526,0.00050415634,0.00026133287],"domain_scores_gemma":[0.9986233,0.00046455994,0.00007383468,0.00040175216,0.0002714471,0.00016511075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019529044,0.00023706304,0.0001586258,0.00039225322,0.00007476439,0.00032301113,0.0007081759,0.000073068455,0.0000305462],"category_scores_gemma":[0.0027104684,0.00025079228,0.00005241195,0.00031056363,0.000015524529,0.00029321254,0.00012282538,0.00021244698,0.000050603554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009812877,0.000063566426,0.0008558196,0.000009130583,0.0000064164296,0.000032883974,0.00012694861,0.990972,0.0011897857,0.0047133123,0.0001587586,0.0018615989],"study_design_scores_gemma":[0.0002758276,0.00022959721,0.0016166322,0.00047122224,0.0000022459863,0.0000058775213,6.82479e-7,0.98699343,0.0023838093,0.0074065174,0.00030993213,0.0003042188],"about_ca_topic_score_codex":0.00003593791,"about_ca_topic_score_gemma":9.848256e-7,"teacher_disagreement_score":0.6039171,"about_ca_system_score_codex":0.00030034187,"about_ca_system_score_gemma":0.0001488598,"threshold_uncertainty_score":0.99999446},"labels":[],"label_agreement":null},{"id":"W2143742229","doi":"10.5555/2486788.2486974","title":"On extracting unit tests from interactive live programming sessions","year":2013,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Session (web analytics); Unit testing; Cluster analysis; Software testing; Software; Software engineering; Programming language; Machine learning; World Wide Web","score_opus":0.03945455755763936,"score_gpt":0.2990520090276418,"score_spread":0.2595974514700024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143742229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100234486,0.0000123791615,0.8877579,0.00045674434,0.00113001,0.00025829766,0.000011249592,0.009152884,0.0009860247],"genre_scores_gemma":[0.71852255,0.0000023181865,0.28097236,0.00017321126,0.00009695776,0.00011137634,0.0000148936015,0.000020115367,0.000086208456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985043,0.00003014018,0.00026377485,0.00048616156,0.00042285016,0.0002927899],"domain_scores_gemma":[0.997146,0.0018073973,0.00014079387,0.00041584158,0.00036065266,0.0001292848],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000114235845,0.00025754678,0.00017104424,0.0002586302,0.00009961083,0.00053740334,0.0009886523,0.00008924042,0.00021950706],"category_scores_gemma":[0.0028081099,0.00024566738,0.00006839561,0.00018179683,0.000019517447,0.0007361813,0.00023940692,0.00051544234,0.00036010882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048955193,0.00087577687,0.030421909,0.000044824148,0.00040097188,0.00026946905,0.0066481326,0.008295684,0.0034451683,0.13021846,0.00807016,0.81126046],"study_design_scores_gemma":[0.00075517286,0.0005558832,0.045797776,0.0039882506,0.000017081855,0.000064866945,0.00020460968,0.8785866,0.0039034227,0.06259087,0.0019237947,0.0016116945],"about_ca_topic_score_codex":0.0003430884,"about_ca_topic_score_gemma":0.0000034812074,"teacher_disagreement_score":0.8702909,"about_ca_system_score_codex":0.00011892112,"about_ca_system_score_gemma":0.000057404435,"threshold_uncertainty_score":0.9999996},"labels":[],"label_agreement":null},{"id":"W2143791583","doi":"10.1109/apsec.2002.1183004","title":"Quality driven transformation compositions for object oriented migration","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Business process reengineering; Legacy system; Transformation (genetics); Model transformation; Object-oriented programming; Source code; Software engineering; Process (computing); Programming language; Object (grammar); Program transformation; Quality (philosophy); Set (abstract data type); Software system; Software quality; Software development; Software; Artificial intelligence; Engineering","score_opus":0.0352107065189372,"score_gpt":0.3172132540120987,"score_spread":0.2820025474931615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143791583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060040765,0.000005571549,0.98464,0.0005659229,0.000091144495,0.00024590502,0.0000031312807,0.0051688473,0.0032753856],"genre_scores_gemma":[0.53342324,7.95648e-7,0.46632427,0.00015277631,0.000005481633,0.00004310837,0.000012147958,0.000002266798,0.000035917135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993841,0.00006684936,0.00018059535,0.00014563493,0.000106668915,0.00011614416],"domain_scores_gemma":[0.99935806,0.00022841425,0.000045023524,0.0002178144,0.00011766644,0.000033046086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003233201,0.00006429747,0.00007506005,0.000059914473,0.00016065528,0.00006195674,0.00013430449,0.000033937675,0.0000035782734],"category_scores_gemma":[0.00015699619,0.00005809607,0.000049684553,0.0002017974,0.000012345089,0.00032118926,0.000006893855,0.000035654615,0.0000056222043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004241671,0.0000969907,0.001640784,0.000021105008,0.000007971273,2.366523e-7,0.0013661748,0.00008420056,0.0012504562,0.97697824,0.010504216,0.00804538],"study_design_scores_gemma":[0.0015362947,0.0005854919,0.007889582,0.00007470387,0.000020051588,0.000045208362,0.000076375625,0.4145437,0.07693178,0.46707267,0.030411948,0.00081222854],"about_ca_topic_score_codex":0.000052756564,"about_ca_topic_score_gemma":0.00003029906,"teacher_disagreement_score":0.52741915,"about_ca_system_score_codex":0.00002791185,"about_ca_system_score_gemma":0.0000324894,"threshold_uncertainty_score":0.23690888},"labels":[],"label_agreement":null},{"id":"W2144667363","doi":"10.1145/1145735.1145741","title":"Tool support for randomized unit testing","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Java; Unit testing; Class (philosophy); Unit (ring theory); Programming language; Software; Mathematics; Artificial intelligence","score_opus":0.033379706469621157,"score_gpt":0.2757351743738155,"score_spread":0.24235546790419435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144667363","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013368832,0.000010086453,0.96219164,0.00021523147,0.00008975389,0.0003774043,6.7282974e-7,0.015320775,0.02045754],"genre_scores_gemma":[0.14114277,1.1928564e-7,0.8560085,0.00033905572,0.00006890315,0.000114415285,0.0000025049737,0.000007875989,0.0023158488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991547,0.00003546237,0.00024205813,0.00022798934,0.00011915415,0.0002206675],"domain_scores_gemma":[0.99687415,0.0025524676,0.000071300245,0.00033091297,0.0001466289,0.000024542142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009253837,0.00009804732,0.00021228548,0.0000715033,0.000103198494,0.00012504483,0.00040577876,0.00003698398,0.000009035543],"category_scores_gemma":[0.0015152693,0.00007709907,0.00007940358,0.00023789155,0.000035705256,0.00010416641,0.00008873368,0.000044021217,0.000015020895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007947993,0.00016957846,0.009231235,0.00006061055,0.000026009018,0.00002321617,0.00009754897,0.00018190377,0.0004318043,0.5791699,0.2800284,0.12978497],"study_design_scores_gemma":[0.026497366,0.00008966738,0.00043461836,0.000025256097,0.000012515183,0.000042122763,6.0006795e-7,0.28781682,0.0021632963,0.67944384,0.0031617994,0.00031208605],"about_ca_topic_score_codex":0.00021840299,"about_ca_topic_score_gemma":0.000002125219,"teacher_disagreement_score":0.28763494,"about_ca_system_score_codex":0.000009840264,"about_ca_system_score_gemma":0.000055541124,"threshold_uncertainty_score":0.31440085},"labels":[],"label_agreement":null},{"id":"W2144931777","doi":"10.1109/hcc.2002.1046355","title":"A data-flow testing methodology for a dataflow based visual programming language","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Dataflow; Computer science; Programming language; Visual programming language; Visual language; Data flow diagram; High-level programming language; Programming paradigm; Database","score_opus":0.25640698913435905,"score_gpt":0.4144659342470359,"score_spread":0.15805894511267687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144931777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038619875,0.000057687725,0.988161,0.000121668156,0.00013375541,0.00033045295,0.000015789015,0.010414905,0.0003785429],"genre_scores_gemma":[0.011802421,1.3796054e-7,0.98726296,0.0006542791,0.000044131168,0.000085951186,0.000056334746,0.00001811462,0.00007564673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.00024020416,0.00023007403,0.000658539,0.00015550668,0.00041724255],"domain_scores_gemma":[0.9940924,0.0043520276,0.00009012836,0.0012763563,0.000103824954,0.000085262735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026806388,0.00015426343,0.0002056283,0.00011642581,0.00014964827,0.00018087808,0.0012423634,0.00006904172,0.0000069606212],"category_scores_gemma":[0.013469659,0.00013774219,0.000036162266,0.00047818493,0.0000367033,0.00033619226,0.00030513,0.00011084437,0.000006473522],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000674302,0.0001608352,0.0017552442,0.0000714033,0.000017963897,0.000032685406,0.00018087824,0.000054708897,0.00086987315,0.0053554308,0.014682509,0.9768117],"study_design_scores_gemma":[0.00038248082,0.00025059652,0.000039939277,0.000039182356,0.000014780488,0.00006302995,0.00001624904,0.976647,0.003942099,0.0058790627,0.012426094,0.0002994673],"about_ca_topic_score_codex":0.00008453387,"about_ca_topic_score_gemma":0.000014033715,"teacher_disagreement_score":0.9765923,"about_ca_system_score_codex":0.000018992367,"about_ca_system_score_gemma":0.00016130229,"threshold_uncertainty_score":0.9948403},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08413484429999112,"score_gpt":0.2648815431189903,"score_spread":0.18074669881899919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145149095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0458025,0.000106346764,0.9375282,0.000027807388,0.00018786987,0.0003104212,0.0000041162916,0.015486811,0.00054594467],"genre_scores_gemma":[0.51320344,0.0000032658622,0.48671088,0.000022997827,0.00001998205,0.000013243524,0.0000027276828,0.000011049815,0.000012406562],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827534,0.00012220259,0.00041464617,0.00067572395,0.00025118692,0.00026087253],"domain_scores_gemma":[0.9973971,0.00075215305,0.00027050922,0.0009540851,0.0004930947,0.00013300909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094563304,0.00020617987,0.00020435303,0.00011136093,0.0004111127,0.00011467861,0.0004239031,0.00014288144,0.0000014010749],"category_scores_gemma":[0.004143094,0.00017951576,0.00003872257,0.00060351857,0.00011724546,0.0005927942,0.0001847756,0.000172393,0.000004381627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026582828,0.0005799589,0.8201281,0.0011878352,0.0000141636165,0.000024605102,0.004711619,0.0007955329,0.0018947173,0.013030899,0.0009083586,0.15669763],"study_design_scores_gemma":[0.00022535263,0.0001320338,0.073737025,0.00063932355,0.000022274293,0.00012584185,0.000029024925,0.86453813,0.0010828301,0.058967676,0.000034196262,0.0004662886],"about_ca_topic_score_codex":0.0003525542,"about_ca_topic_score_gemma":6.3134104e-7,"teacher_disagreement_score":0.8637426,"about_ca_system_score_codex":0.000129563,"about_ca_system_score_gemma":0.00010569442,"threshold_uncertainty_score":0.73204404},"labels":[],"label_agreement":null},{"id":"W2145733341","doi":"10.1145/2786805.2786858","title":"Assertions are strongly correlated with test suite effectiveness","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; Assertion; Test (biology); Computer science; Suite; Java; Test case; Code coverage; Code (set theory); Unit testing; Programming language; Algorithm; Machine learning; Software; Regression analysis","score_opus":0.029829427367251995,"score_gpt":0.2597681029273936,"score_spread":0.2299386755601416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145733341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04869111,0.000021651538,0.93184876,0.0001972951,0.00010507335,0.00016324355,0.0000011007685,0.015997339,0.0029743963],"genre_scores_gemma":[0.88838005,1.8453761e-7,0.111287124,0.000059868333,0.0000130040235,0.000026375968,0.0000016720437,0.000008917734,0.00022280362],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991595,0.00006187771,0.00009397655,0.00027057974,0.00020543262,0.00020858992],"domain_scores_gemma":[0.9984511,0.0006471912,0.00005980289,0.00046330498,0.0002463234,0.00013228838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003682772,0.0001142475,0.00012289271,0.00007546842,0.0000772631,0.00012877639,0.00042545557,0.000047597132,0.000002123939],"category_scores_gemma":[0.00058428076,0.000082927625,0.000020665406,0.00046374512,0.00003416269,0.00028402224,0.00011130829,0.000118281605,0.000046384197],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019152862,0.0002742446,0.96678406,0.000018011611,0.000022913973,0.000082416715,0.00023798665,0.00070052966,0.000080157304,0.006631892,0.019931685,0.0052169613],"study_design_scores_gemma":[0.0020935312,0.0022334647,0.7202278,0.00052427105,0.000035939545,0.0003983375,0.000053411077,0.22985113,0.00452725,0.03787209,0.0011160121,0.0010667791],"about_ca_topic_score_codex":0.00015380135,"about_ca_topic_score_gemma":0.000019948096,"teacher_disagreement_score":0.83968896,"about_ca_system_score_codex":0.000054936325,"about_ca_system_score_gemma":0.000098866854,"threshold_uncertainty_score":0.33816904},"labels":[],"label_agreement":null},{"id":"W2148177313","doi":"10.1109/iscas.2000.857100","title":"A methodology for validating digital circuits with mutation testing","year":2000,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Verilog; Mutation; Mutation testing; Functional testing; Hardware description language; VHDL; Task (project management); Digital electronics; Theoretical computer science; Computer engineering; Programming language; Reliability engineering; Electronic circuit; Embedded system; Field-programmable gate array; Engineering","score_opus":0.1306905846849651,"score_gpt":0.31829560941346813,"score_spread":0.18760502472850302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148177313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020118585,0.0000056069944,0.964474,0.000100163954,0.00002089715,0.000145127,9.2417844e-7,0.008437551,0.006697112],"genre_scores_gemma":[0.35849696,5.73323e-8,0.64111876,0.00014549232,0.000021605481,0.000027721853,0.0000019205322,0.000006354185,0.00018110414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926436,0.000034254754,0.0001354091,0.0002713561,0.000097215736,0.00019741767],"domain_scores_gemma":[0.99721116,0.0023699347,0.000050829225,0.00022722382,0.00010292016,0.000037945858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003769,0.000086760636,0.00010443239,0.000052040603,0.00011127362,0.00020658823,0.00027363942,0.000031830063,0.000007680263],"category_scores_gemma":[0.0012075346,0.00006877821,0.000020908516,0.0002930606,0.000019973148,0.00040246022,0.000027805812,0.0000480031,0.000008953675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001746953,0.000012238658,0.001389934,0.000007484639,0.000004293664,0.0000056936115,0.0002323565,0.00011031333,0.00006383918,0.0013832678,0.00040878315,0.99638003],"study_design_scores_gemma":[0.001135756,0.0018728112,0.0030623854,0.00021923755,0.00002461601,0.0014688218,0.000038352806,0.4904318,0.011245667,0.48843798,0.0011035231,0.0009590539],"about_ca_topic_score_codex":0.000027703974,"about_ca_topic_score_gemma":0.0000010142346,"teacher_disagreement_score":0.995421,"about_ca_system_score_codex":0.000013420008,"about_ca_system_score_gemma":0.000038813614,"threshold_uncertainty_score":0.2804694},"labels":[],"label_agreement":null},{"id":"W2149695823","doi":"10.1007/s10664-006-9026-0","title":"Empirical evaluation of optimization algorithms when used in goal-oriented automated test data generation techniques","year":2006,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test Management Approach; Computer science; Keyword-driven testing; Test data; Software development; Test harness; Software; Software reliability testing; Automation; Test strategy; Non-regression testing; Data mining; Software construction; Software engineering; Engineering; Programming language","score_opus":0.06930117347575526,"score_gpt":0.3370234376690021,"score_spread":0.26772226419324685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149695823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023737116,0.00011352865,0.9594879,0.00020466899,0.00015120562,0.0003798705,0.000012809566,0.01589891,0.000014003437],"genre_scores_gemma":[0.28893465,0.0000018665515,0.71057355,0.000043479107,0.0001174625,0.00005884009,0.00023976287,0.000025783756,0.0000046083715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747235,0.00012694104,0.00063536945,0.0006465216,0.0007920311,0.0003268057],"domain_scores_gemma":[0.9977652,0.0006679233,0.00015920405,0.0010084735,0.00033026538,0.000068961286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016009898,0.00024243946,0.0002972333,0.0003764406,0.000060230865,0.000090504545,0.0007741569,0.00019236018,0.000008212254],"category_scores_gemma":[0.004106378,0.00024748358,0.000044804056,0.0010644776,0.000028901242,0.0006699534,0.00036161428,0.0002089286,0.0000024096983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003725941,0.00049932185,0.40218502,0.000056213736,0.000016599637,0.000015993315,0.00035537785,0.549433,0.000918107,0.000035283803,0.03208046,0.014400875],"study_design_scores_gemma":[0.00028150438,0.00006412833,0.025896102,0.00008579692,0.000015791678,0.000010141789,7.7046417e-7,0.97015774,0.0026729552,0.00033546623,0.00022148008,0.00025809265],"about_ca_topic_score_codex":0.00018628343,"about_ca_topic_score_gemma":0.000012714499,"teacher_disagreement_score":0.42072475,"about_ca_system_score_codex":0.00025154403,"about_ca_system_score_gemma":0.0001476353,"threshold_uncertainty_score":0.99999774},"labels":[],"label_agreement":null},{"id":"W2151635819","doi":"10.1145/1276958.1277172","title":"Automatic mutation test input data generation via ant colony","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Ant colony optimization algorithms; Mutation; Context (archaeology); Genetic algorithm; Java; Code coverage; Test data; Data mining; Machine learning; Artificial intelligence; Software","score_opus":0.059541612366656615,"score_gpt":0.3142915271483908,"score_spread":0.2547499147817342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151635819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017083276,0.000019066589,0.9714015,0.00031140292,0.00016614892,0.00011291898,0.0000012376953,0.010267392,0.00063703576],"genre_scores_gemma":[0.5041803,5.7556474e-7,0.49533024,0.000340082,0.00006872648,0.0000025733227,0.000023831017,0.000003885746,0.000049773837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990789,0.000021855509,0.00021441917,0.00031335227,0.00020018488,0.0001712519],"domain_scores_gemma":[0.9983753,0.0004928101,0.00007525138,0.0009323946,0.000072480056,0.00005178159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009898989,0.000081778984,0.00007704211,0.00009719279,0.000106432686,0.00013419663,0.00075029425,0.000045368677,0.000010514556],"category_scores_gemma":[0.0007845871,0.0000721352,0.00001134626,0.00031049672,0.000019338077,0.00049265596,0.00027271727,0.00005995757,0.00004701846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.872096e-7,0.0001591945,0.008895942,0.00001841641,0.000007619296,0.00007453882,0.00038339457,0.000024258125,0.0043702545,0.002004207,0.12694208,0.8571195],"study_design_scores_gemma":[0.00006859501,0.00007455061,0.006543418,0.000010861494,0.0000030357396,0.00007165445,9.820931e-7,0.9830382,0.004728157,0.005041384,0.00030863457,0.00011055265],"about_ca_topic_score_codex":0.00013173909,"about_ca_topic_score_gemma":0.000043399887,"teacher_disagreement_score":0.9830139,"about_ca_system_score_codex":0.00003770458,"about_ca_system_score_gemma":0.00004418172,"threshold_uncertainty_score":0.2941588},"labels":[],"label_agreement":null},{"id":"W2152665443","doi":"10.1109/icsm.1990.131335","title":"Non-intrusive tool for software testing and debugging: an actual industrial application example","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Debugging; Computer science; Software engineering; Software; Programming language; Embedded system","score_opus":0.09142306802878755,"score_gpt":0.2741139128491273,"score_spread":0.18269084482033973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152665443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030023156,0.000014996947,0.9597825,0.00017294298,0.000076552475,0.0005094679,0.0000027555686,0.009268594,0.00014904792],"genre_scores_gemma":[0.3954437,6.4455315e-7,0.6038983,0.00030929156,0.00015164139,0.000129247,0.0000034669572,0.000012500724,0.00005122059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880785,0.000020509568,0.00021283665,0.00051583746,0.00015122107,0.0002917735],"domain_scores_gemma":[0.99781686,0.0012966129,0.00010245617,0.00051142776,0.00014492458,0.00012771477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031473243,0.00015971165,0.00015662512,0.00009503552,0.00026432492,0.00024016111,0.000456295,0.00011525548,0.000008839848],"category_scores_gemma":[0.0020417084,0.00014870786,0.000027043096,0.0002835735,0.000039743365,0.0004871832,0.0001710311,0.000119457785,0.0000069370353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000416877,0.00006254411,0.014072524,0.000011823844,0.000007168758,0.0000016903409,0.0005229043,0.0000137757315,0.00023270666,0.000997227,0.01673673,0.9673367],"study_design_scores_gemma":[0.0010642809,0.000757206,0.0030761429,0.000059537866,0.000022321543,0.00008644548,0.000012528036,0.9321689,0.0024956018,0.056346934,0.0031985918,0.00071153534],"about_ca_topic_score_codex":0.00026835848,"about_ca_topic_score_gemma":0.000005411662,"teacher_disagreement_score":0.9666252,"about_ca_system_score_codex":0.000031731535,"about_ca_system_score_gemma":0.00003824783,"threshold_uncertainty_score":0.60641307},"labels":[],"label_agreement":null},{"id":"W2153135840","doi":"10.1109/esem.2007.22","title":"Assessing, Comparing, and Combining Statechart- based testing and Structural testing: An Experiment","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Code coverage; Software testing; Test strategy; Code (set theory); Fault detection and isolation; Fault coverage; Source code; Reliability engineering; Class (philosophy); Test case; Software; Programming language; Machine learning; Artificial intelligence; Set (abstract data type); Engineering","score_opus":0.10540085681696369,"score_gpt":0.35147260285424115,"score_spread":0.24607174603727744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153135840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6286666,0.000052765743,0.36295104,0.000031668173,0.00006006377,0.00009454823,1.884303e-7,0.0068077357,0.0013353942],"genre_scores_gemma":[0.51916784,8.6780176e-8,0.48066324,0.00014070065,0.00001179716,0.0000026077475,7.657782e-7,0.000008269544,0.000004692244],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985141,0.000046587495,0.00028970244,0.00051592337,0.00023174428,0.00040190291],"domain_scores_gemma":[0.9979691,0.0011600897,0.00013274394,0.0003859659,0.0001306119,0.00022151986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000939245,0.00020889816,0.00020633025,0.00015076889,0.000370101,0.00082093285,0.00032263884,0.00005570579,0.0000021029264],"category_scores_gemma":[0.0006619994,0.00018854931,0.0000121612675,0.00032206933,0.000102649276,0.0007479011,0.00028530156,0.0001688714,7.305262e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005255401,0.00005748028,0.8498854,0.00003563422,0.0000070270476,0.0000551105,0.0007958315,0.00007654359,0.0057221926,0.0017346204,0.000272855,0.14135204],"study_design_scores_gemma":[0.00040090884,0.0003370205,0.20280518,0.00011418257,0.0000047992853,0.00012445751,0.00006199003,0.7823241,0.005919834,0.0075151497,0.000022476508,0.00036994356],"about_ca_topic_score_codex":0.00039552292,"about_ca_topic_score_gemma":0.000009360378,"teacher_disagreement_score":0.78224754,"about_ca_system_score_codex":0.000031967887,"about_ca_system_score_gemma":0.000051366347,"threshold_uncertainty_score":0.79162747},"labels":[],"label_agreement":null},{"id":"W2153934195","doi":"10.1145/1068009.1068185","title":"Improving network applications security","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Buffer overflow; Computer science; Program slicing; Dependency graph; Static analysis; Dependency (UML); Call graph; Slicing; Static program analysis; Control flow graph; Exploit; Distributed computing; Data-flow analysis; Software; Graph; Computer security; Data flow diagram; Theoretical computer science; Software engineering; Programming language; Software development; Database","score_opus":0.009514283014754729,"score_gpt":0.24275605342952686,"score_spread":0.23324177041477212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153934195","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010745609,0.000082885126,0.97335696,0.00067412487,0.000029856514,0.000089481444,1.2907726e-7,0.016309455,0.009349643],"genre_scores_gemma":[0.31306177,0.0000013422787,0.685845,0.000711513,0.00020709075,0.000040192393,3.8017183e-7,0.0000030381696,0.00012965487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994581,0.000011581361,0.00009306463,0.00018818842,0.000081645434,0.000167435],"domain_scores_gemma":[0.99935144,0.00009873203,0.000031940344,0.00043760816,0.0000339691,0.000046300775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018836137,0.000055604,0.00005139067,0.000023002032,0.000111739304,0.0000809739,0.0004604636,0.00002784439,0.000008463297],"category_scores_gemma":[0.000028513534,0.00005021265,0.00002292827,0.00022516694,0.00001272782,0.00018115902,0.00016624558,0.00006807437,0.0000713237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.8016433e-7,0.000033186785,0.0015347493,0.0000044679487,0.0000023906,6.371691e-7,0.000091919086,0.00012030709,0.00001866678,0.15098447,0.09707723,0.7501317],"study_design_scores_gemma":[0.000086653534,0.000027718634,0.00045060075,0.000009788119,0.0000028923314,0.000024274548,0.000001000839,0.5131837,0.000708214,0.36772346,0.11752508,0.0002565732],"about_ca_topic_score_codex":0.00004068875,"about_ca_topic_score_gemma":0.000007653966,"teacher_disagreement_score":0.7498751,"about_ca_system_score_codex":0.000018636805,"about_ca_system_score_gemma":0.000020900829,"threshold_uncertainty_score":0.20476124},"labels":[],"label_agreement":null},{"id":"W2155119310","doi":"10.1109/tim.2006.887405","title":"DOS Middleware Instrumentation for Ensuring Reproducibility of Testing Procedures","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Middleware (distributed applications); Distributed computing; Layer (electronics); Operating system; Embedded system","score_opus":0.09772365009063337,"score_gpt":0.3037248750879295,"score_spread":0.20600122499729612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155119310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15796338,0.000018428917,0.840189,0.00012344056,0.00028390333,0.0005567407,0.000004611024,0.00076934736,0.00009119111],"genre_scores_gemma":[0.81001043,0.000004580683,0.18978795,0.00008630374,0.000016086235,0.00007492598,0.0000010970687,0.000008042346,0.000010588761],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983015,0.000035876237,0.0004406177,0.00059402926,0.0004319548,0.00019598882],"domain_scores_gemma":[0.99872726,0.00017406844,0.0001887951,0.00046397003,0.00037414147,0.000071760034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022211222,0.00013911957,0.00014141854,0.0001998537,0.000233557,0.000050282724,0.00014523511,0.000048086593,0.0000018856645],"category_scores_gemma":[0.00028280917,0.00013967788,0.000050682378,0.0003009689,0.00004444982,0.00026994813,0.0000027725528,0.000083391446,6.4613954e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010396702,0.00030802423,0.0043861256,0.00033206274,0.000044106044,6.53586e-7,0.0016068795,0.00035187587,0.037309524,0.0002964784,0.00008950175,0.9551708],"study_design_scores_gemma":[0.0012195845,0.00072665786,0.011757398,0.000360713,0.000037926355,0.000022261549,0.00017526606,0.0043765325,0.97668827,0.0043325694,0.000036199566,0.00026665494],"about_ca_topic_score_codex":0.00007047656,"about_ca_topic_score_gemma":0.00005629426,"teacher_disagreement_score":0.95490414,"about_ca_system_score_codex":0.00014342711,"about_ca_system_score_gemma":0.00009700297,"threshold_uncertainty_score":0.56958985},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07291649913695267,"score_gpt":0.30554752011573033,"score_spread":0.23263102097877766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155388066","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020001836,0.00009917531,0.96895957,0.00093385356,0.00023576576,0.0005860906,0.000041481246,0.009017361,0.00012487387],"genre_scores_gemma":[0.18461071,0.000016579317,0.814645,0.00016344404,0.00015691521,0.00020486566,0.00009233974,0.000018466822,0.000091686125],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979649,0.00012702466,0.00048565672,0.0009225514,0.00021465696,0.00028516588],"domain_scores_gemma":[0.99299747,0.00483635,0.00026337238,0.001105716,0.00065842,0.00013867972],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010273404,0.00022751692,0.00023516612,0.00009744792,0.000591554,0.00020158249,0.00041330294,0.00014497325,0.000007394136],"category_scores_gemma":[0.014852289,0.00021512365,0.00006315443,0.0006720645,0.00009358101,0.00031531148,0.00009457287,0.00016649939,0.000012584791],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003357093,0.00085294986,0.5234631,0.00008308635,0.000032002317,0.0000060220837,0.0018574463,0.00045712004,0.011207268,0.006298813,0.020853627,0.43485504],"study_design_scores_gemma":[0.0008003493,0.00037048108,0.26755366,0.00010814966,0.000058242334,0.00008491831,0.000029396902,0.56032366,0.0032253067,0.14821608,0.01836441,0.00086532417],"about_ca_topic_score_codex":0.0007342249,"about_ca_topic_score_gemma":0.000013870559,"teacher_disagreement_score":0.55986655,"about_ca_system_score_codex":0.0000925909,"about_ca_system_score_gemma":0.000102074075,"threshold_uncertainty_score":0.99344605},"labels":[],"label_agreement":null},{"id":"W2155775985","doi":"10.1109/ecbs.2008.49","title":"Scenario-Based Program Slicing","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Debugging; Program slicing; Slicing; Software engineering; Programming language; Microsoft Visual Studio; Agile software development; XML; Set (abstract data type); Software; Operating system; World Wide Web","score_opus":0.03759731514265637,"score_gpt":0.2735128582192871,"score_spread":0.23591554307663073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155775985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012230464,0.00001873471,0.9280519,0.0005470921,0.00007349874,0.00012946084,6.5441505e-8,0.052905746,0.006043038],"genre_scores_gemma":[0.4528107,5.007619e-7,0.5464558,0.0005703323,0.00001455927,0.000016651162,3.1191374e-7,0.000003597475,0.00012755001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993127,0.000018253275,0.00010158909,0.00021448407,0.00015857234,0.00019438368],"domain_scores_gemma":[0.9993141,0.00011302745,0.000027899807,0.00043413066,0.00005203738,0.0000587648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012322525,0.00007766637,0.00007852074,0.000071877206,0.00015280713,0.000052821106,0.0004596888,0.000032054802,0.0000064360224],"category_scores_gemma":[0.00010859479,0.00006406866,0.000036519676,0.00029950304,0.00003733437,0.00012324101,0.00007920645,0.000072930954,0.000038037633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003959091,0.0004641244,0.08942715,0.000017706776,0.000009491477,0.00021764325,0.0005498257,0.00014492497,0.00013415032,0.010823166,0.1986277,0.6995802],"study_design_scores_gemma":[0.0005158548,0.0006253805,0.02331696,0.00009250009,0.000003847715,0.00026370876,0.0000017608675,0.9330871,0.010041802,0.01394699,0.017439635,0.00066445296],"about_ca_topic_score_codex":0.00012615434,"about_ca_topic_score_gemma":0.0000018431138,"teacher_disagreement_score":0.93294215,"about_ca_system_score_codex":0.000017503944,"about_ca_system_score_gemma":0.000068831185,"threshold_uncertainty_score":0.2612644},"labels":[],"label_agreement":null},{"id":"W2155780123","doi":"10.1145/2371401.2371407","title":"Synthesizing iterators from abstraction functions","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Programming language; Transitive closure; Tuple; Tree traversal; Reachability; Theoretical computer science; Mathematics","score_opus":0.02281374206936714,"score_gpt":0.24553140126461206,"score_spread":0.22271765919524492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155780123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056423,0.000082001185,0.924082,0.00016826122,0.0005075541,0.000035975256,0.000001179441,0.013846352,0.0048536994],"genre_scores_gemma":[0.8004256,8.15787e-7,0.19917217,0.0001717776,0.00013256514,0.000007366116,0.0000018251203,0.0000023501382,0.000085561885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99950653,0.000019202045,0.000089581124,0.00012578847,0.00009647603,0.00016243618],"domain_scores_gemma":[0.99927205,0.00036700722,0.000032567517,0.00023690311,0.000022998132,0.00006847929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014874,0.00006308441,0.000052193263,0.00003770413,0.00009924883,0.00009210641,0.00017568869,0.000035999245,0.00004636847],"category_scores_gemma":[0.00010155648,0.000047480415,0.000027408421,0.0001337687,0.0000062233603,0.00064659346,0.000054693788,0.000069280264,0.00017970066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030026101,0.0002365254,0.21045084,0.0000054405637,0.000033213306,0.0000040780433,0.0009071779,0.000008428495,0.005790096,0.007012188,0.096695155,0.67885387],"study_design_scores_gemma":[0.0003324946,0.00014666792,0.6557132,0.00020861259,0.000058229212,0.0001350892,0.000086605956,0.042839173,0.090454474,0.067548394,0.14073682,0.0017402468],"about_ca_topic_score_codex":0.00021448467,"about_ca_topic_score_gemma":0.0000025582628,"teacher_disagreement_score":0.7440026,"about_ca_system_score_codex":0.000023341632,"about_ca_system_score_gemma":0.000007240842,"threshold_uncertainty_score":0.23097484},"labels":[],"label_agreement":null},{"id":"W2155803905","doi":"10.5555/2663608.2663627","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2012,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Graphical user interface testing; Test (biology); Code coverage; Manual testing; Software engineering; Test harness; Programming language; Reliability engineering; Software; Software development; User interface; Engineering; Software construction; Machine learning","score_opus":0.02530140677214751,"score_gpt":0.27447818259570933,"score_spread":0.24917677582356182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155803905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3622459,0.00072436413,0.5887453,0.0004505986,0.0008362776,0.00057387253,0.00012733405,0.044646498,0.001649868],"genre_scores_gemma":[0.60625327,0.0000049590544,0.39334464,0.00012407255,0.000108394954,0.000023768309,0.000028477507,0.000018752724,0.00009367598],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99818766,0.0000653782,0.00054784975,0.00037028134,0.00040123094,0.0004275854],"domain_scores_gemma":[0.9885282,0.009738054,0.00043093256,0.00085255643,0.0002782403,0.00017200263],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005097098,0.00024699335,0.00031221754,0.0001802799,0.0002003184,0.00012261533,0.00066899887,0.00013321053,0.0000792377],"category_scores_gemma":[0.019455763,0.0002512479,0.00008757023,0.000593097,0.0000902402,0.0009848125,0.0002547714,0.00016256173,0.00018253902],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013928279,0.00034328015,0.91599053,0.00003911203,0.0000121814965,0.000009207142,0.00070601224,0.00000572774,0.0005812125,0.0002140782,0.022200579,0.059896663],"study_design_scores_gemma":[0.0004588318,0.0003843787,0.9590498,0.0005348371,0.00004288073,0.00016729195,0.00002239102,0.01256697,0.010889265,0.013733959,0.0014298025,0.00071955915],"about_ca_topic_score_codex":0.0009794144,"about_ca_topic_score_gemma":0.000017976625,"teacher_disagreement_score":0.24400735,"about_ca_system_score_codex":0.000076181,"about_ca_system_score_gemma":0.00007952058,"threshold_uncertainty_score":0.999994},"labels":[],"label_agreement":null},{"id":"W2156213336","doi":"10.1145/2245276.2231981","title":"Symbolic execution of UML-RT State Machines","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Unified Modeling Language; Symbolic execution; Applications of UML; Modular design; UML tool; Reachability; Finite-state machine; Code generation; Theoretical computer science; Key (lock); Software; Operating system","score_opus":0.01688462853798117,"score_gpt":0.26418489929466593,"score_spread":0.24730027075668476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156213336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064406976,0.00012367772,0.9227916,0.0001582909,0.00018542037,0.000056759625,6.921508e-7,0.0062634903,0.0060130814],"genre_scores_gemma":[0.79882586,0.0000034317727,0.20076929,0.00011170184,0.000028682673,0.00000383333,5.2185635e-7,0.0000034726008,0.000253229],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994464,0.000025560988,0.00012516913,0.00010114266,0.00012520143,0.00017652905],"domain_scores_gemma":[0.99945056,0.00008135151,0.00005160397,0.00031923057,0.00004386856,0.00005335923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027347548,0.00006516662,0.00008748988,0.00007153144,0.000031565072,0.000019348048,0.0002916968,0.000021513317,0.000008613574],"category_scores_gemma":[0.000083292325,0.000051377367,0.00002813296,0.000186908,0.00002127221,0.0002765651,0.000120382305,0.000042211657,0.000020579178],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056211297,0.00028991987,0.34573516,0.000060834078,0.00002127135,0.000002564662,0.0022271008,0.000016963299,0.0024975697,0.12722003,0.060815684,0.46110728],"study_design_scores_gemma":[0.0005608468,0.0003568417,0.40286246,0.00017940793,0.000021297474,0.0001626114,0.000008065583,0.12460699,0.10982307,0.3540546,0.0063363453,0.0010274627],"about_ca_topic_score_codex":0.00021702285,"about_ca_topic_score_gemma":0.0000013723754,"teacher_disagreement_score":0.73441887,"about_ca_system_score_codex":0.000009564858,"about_ca_system_score_gemma":0.000012506092,"threshold_uncertainty_score":0.20951083},"labels":[],"label_agreement":null},{"id":"W2156296121","doi":"10.1109/issre.2007.31","title":"Using Machine Learning to Support Debugging with Tarantula","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Debugging; Computer science; Statement (logic); Ranking (information retrieval); Test (biology); Software bug; Decision tree; Fault (geology); Fault tree analysis; Machine learning; Algorithmic program debugging; Test case; Tree (set theory); Artificial intelligence; Programming language; Reliability engineering; Software; Engineering","score_opus":0.04028565877204957,"score_gpt":0.3031118466118101,"score_spread":0.26282618783976053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156296121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038922396,0.000016240223,0.9450706,0.00012999921,0.000057841502,0.00009301672,1.5762484e-7,0.012989456,0.0027202829],"genre_scores_gemma":[0.47752193,2.1939246e-7,0.52182704,0.0004597327,0.000020486485,0.0000011754537,5.7888616e-7,0.000009648068,0.00015916792],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879956,0.000021866994,0.00017475121,0.00033704276,0.00026012503,0.00040663488],"domain_scores_gemma":[0.9991971,0.00017452509,0.00005208602,0.00035102322,0.00007426747,0.00015098671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082057633,0.0001398957,0.00013459765,0.00021472068,0.00018720771,0.000121501325,0.00045154736,0.000036299,0.000017169026],"category_scores_gemma":[0.00012931591,0.00011000032,0.000027365866,0.0005658355,0.000019229776,0.00021777091,0.0002015568,0.00016210355,0.000024270461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091530324,0.00018284448,0.5309679,0.000054080527,0.000068030065,0.0011310158,0.004210137,0.005116822,0.007486703,0.010938111,0.0059788353,0.43377402],"study_design_scores_gemma":[0.00091381994,0.0020109331,0.010450043,0.00031602432,0.000034582732,0.0018999841,0.000041077743,0.9130669,0.046396114,0.0092637325,0.013812762,0.0017939877],"about_ca_topic_score_codex":0.0005358825,"about_ca_topic_score_gemma":0.00006371414,"teacher_disagreement_score":0.9079501,"about_ca_system_score_codex":0.000046229303,"about_ca_system_score_gemma":0.000053424537,"threshold_uncertainty_score":0.44856828},"labels":[],"label_agreement":null},{"id":"W2157056800","doi":"10.1145/2535838.2535857","title":"Symbolic optimization with SMT solvers","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Satisfiability modulo theories; Programming language; Symbolic execution; Satisfiability; Relation (database); Theoretical computer science; Software; Subtyping; Concolic testing; Data mining","score_opus":0.0058507943220102755,"score_gpt":0.19254675865584875,"score_spread":0.18669596433383848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157056800","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040551554,0.0000029078926,0.97363466,0.00030458567,0.00003765128,0.000037138227,3.3876354e-8,0.011184438,0.014393066],"genre_scores_gemma":[0.325068,6.1116026e-7,0.6743377,0.0004269491,0.0000150625265,0.0000041513435,4.513333e-7,0.0000037892207,0.00014328367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953437,0.000018189401,0.00005792857,0.00016518058,0.000109336695,0.00011501491],"domain_scores_gemma":[0.99947447,0.00008600506,0.000025921116,0.00032941948,0.00004486422,0.00003930481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013493224,0.00005935559,0.000058433212,0.000049777824,0.000057933292,0.000081184495,0.00029790823,0.000022008193,0.000007793046],"category_scores_gemma":[0.00006535051,0.000043015858,0.000011667145,0.000183158,0.000017705874,0.00016059258,0.000054798376,0.000036215853,0.000014033382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000144748,0.00019337266,0.039392557,0.00004317884,0.00003995641,0.000014608103,0.0014880585,0.12832007,0.000073859825,0.39611223,0.14831997,0.28598765],"study_design_scores_gemma":[0.00011179559,0.000109730296,0.0004532817,0.000016926411,0.000001985479,0.000015064173,9.4965105e-7,0.98916423,0.00043186126,0.008719659,0.0008511132,0.00012340181],"about_ca_topic_score_codex":0.000040484516,"about_ca_topic_score_gemma":0.0000014488419,"teacher_disagreement_score":0.86084414,"about_ca_system_score_codex":0.000009100006,"about_ca_system_score_gemma":0.000015913998,"threshold_uncertainty_score":0.17541358},"labels":[],"label_agreement":null},{"id":"W2157325856","doi":"10.1109/tase.2009.20","title":"On Testing 1-Safe Petri Nets","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Petri net; Conformance testing; Model-based testing; Finite-state machine; Programming language; Formal specification; Test case; Context (archaeology); Formal methods; Code coverage; Workflow; Formal verification; Software engineering; Software; Machine learning; Database; Operating system","score_opus":0.033475396034445624,"score_gpt":0.2690563045610275,"score_spread":0.2355809085265819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157325856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004636478,0.000022711369,0.8350137,0.0021700426,0.00012603494,0.00007216333,1.2242288e-7,0.027974578,0.12998419],"genre_scores_gemma":[0.53560096,2.7755615e-7,0.46097767,0.0030906622,0.000021932186,0.0000012627384,1.5894257e-7,0.000002427173,0.00030467322],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992453,0.000018414441,0.00011113628,0.00025043808,0.00017211215,0.00020260269],"domain_scores_gemma":[0.9988389,0.00056204665,0.000035784666,0.00044989598,0.00005250694,0.000060846018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019520143,0.00009077576,0.000080059646,0.00009271745,0.00009109399,0.00010923347,0.00051593914,0.000032060667,0.000007323574],"category_scores_gemma":[0.001027456,0.00007477877,0.00002444102,0.00041960485,0.000009241595,0.00013051128,0.000056472323,0.000096753916,0.000094318566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018337496,0.00008508579,0.0013593116,0.000001820129,0.0000017126406,0.00004014902,0.00006911967,0.00006638785,0.00015963822,0.116931506,0.16433686,0.7169466],"study_design_scores_gemma":[0.00019095856,0.00093423884,0.020109424,0.00009135163,0.0000018469756,0.00007898842,6.4948824e-7,0.11019214,0.0023495082,0.8638352,0.0018503015,0.0003653944],"about_ca_topic_score_codex":0.000023535711,"about_ca_topic_score_gemma":2.590211e-7,"teacher_disagreement_score":0.7469037,"about_ca_system_score_codex":0.000018835017,"about_ca_system_score_gemma":0.000024234501,"threshold_uncertainty_score":0.30493897},"labels":[],"label_agreement":null},{"id":"W2157789678","doi":"10.1109/issre.2005.24","title":"Improving Statechart Testing Criteria Using Data Flow Information","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Dataflow; Unified Modeling Language; Tree (set theory); Data flow diagram; Control flow; Data-flow analysis; Test case; Data mining; Path (computing); Database; Machine learning; Programming language","score_opus":0.07316659845003702,"score_gpt":0.29757673137721696,"score_spread":0.22441013292717993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157789678","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027587567,0.000013554935,0.9835419,0.00006489407,0.00014717733,0.00008199127,0.0000074268905,0.012089225,0.0012950647],"genre_scores_gemma":[0.14217843,1.2801442e-7,0.85752404,0.00018666897,0.000059532944,0.0000022002937,0.000029744246,0.000005197996,0.0000140353695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990697,0.000021365762,0.00026571512,0.00022973696,0.00018135217,0.0002321498],"domain_scores_gemma":[0.99862313,0.00015722388,0.000109466724,0.00094880187,0.00012851345,0.000032888085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005013041,0.00010476234,0.00008813622,0.00011858181,0.00016106485,0.00053147686,0.00096157816,0.000038272818,0.0000046905657],"category_scores_gemma":[0.00054647174,0.00009733559,0.000011830108,0.00036339028,0.000016302693,0.003201365,0.0008000337,0.000077305536,0.000016735072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002681102,0.000048315793,0.005744999,0.000083655425,0.000005412549,0.000014511774,0.00018230388,0.00122602,0.0047893017,0.0020376192,0.06850412,0.9173611],"study_design_scores_gemma":[0.000062563406,0.00001680089,0.00041213792,0.000026790325,0.0000022909446,0.000036549394,0.0000017666173,0.9908908,0.00071723695,0.0071715834,0.00052216905,0.00013928772],"about_ca_topic_score_codex":0.0024949694,"about_ca_topic_score_gemma":0.000006156042,"teacher_disagreement_score":0.9896648,"about_ca_system_score_codex":0.000034125034,"about_ca_system_score_gemma":0.00007142591,"threshold_uncertainty_score":0.51250434},"labels":[],"label_agreement":null},{"id":"W2157827846","doi":"10.1145/1967677.1967693","title":"Software debugging and testing using the abstract diagnosis theory","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Observability; Debugging; Dependency (UML); Controllability; Program slicing; Variable (mathematics); Context (archaeology); Set (abstract data type); Algorithm; Theoretical computer science; Programming language; Mathematics","score_opus":0.12479484147938143,"score_gpt":0.27631308476431243,"score_spread":0.15151824328493102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157827846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05035522,0.00030382955,0.9347367,0.00007377734,0.00010170815,0.00012077667,4.464645e-7,0.011831919,0.0024755946],"genre_scores_gemma":[0.50632346,0.0000026801545,0.49331626,0.00030656607,0.000019112342,0.000011726384,6.4161014e-8,0.000007758146,0.000012388629],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990916,0.00005368471,0.00016459679,0.00029643226,0.00013618871,0.00025745196],"domain_scores_gemma":[0.9972674,0.0020237023,0.00008279807,0.0004908526,0.00007207647,0.00006317108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007871167,0.00013511139,0.00010457133,0.000066808745,0.0003543664,0.00015437318,0.0005970024,0.000044474,0.00001864916],"category_scores_gemma":[0.0014610573,0.000087638036,0.000030281864,0.0002699542,0.00009077654,0.0003245003,0.00035936318,0.00014169353,0.000004746937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002933247,0.000055608092,0.3190759,0.000023596154,0.000023083476,0.000039795093,0.0023589986,0.000010843594,0.00007407435,0.014122096,0.0016730926,0.66253996],"study_design_scores_gemma":[0.00017501484,0.00011375543,0.16730082,0.0002973003,0.000039504917,0.00037308392,0.00006117519,0.042413265,0.0053548645,0.7830605,0.00015410507,0.0006566384],"about_ca_topic_score_codex":0.00040590964,"about_ca_topic_score_gemma":0.0000035249782,"teacher_disagreement_score":0.76893836,"about_ca_system_score_codex":0.000016195841,"about_ca_system_score_gemma":0.000039193896,"threshold_uncertainty_score":0.35737753},"labels":[],"label_agreement":null},{"id":"W2158798798","doi":"10.1145/1368088.1368118","title":"Calysto","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Scalability; Static analysis; Source lines of code; Automation; Static program analysis; Context (archaeology); Software; Software bug; Model checking; Code (set theory); Computer engineering; Programming language; Software development; Database; Set (abstract data type)","score_opus":0.03481987681072068,"score_gpt":0.23643006246479897,"score_spread":0.2016101856540783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158798798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044194,0.000019706156,0.9543152,0.00030211863,0.00005315264,0.000017666782,3.0506403e-8,0.019801663,0.02107108],"genre_scores_gemma":[0.5422674,0.0000015089847,0.45641026,0.00042081357,0.000011426327,0.000002231345,6.648552e-8,0.0000014320576,0.000884847],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996661,0.000007812047,0.00004933847,0.00011029288,0.000080905775,0.00008553695],"domain_scores_gemma":[0.99959385,0.000055735654,0.000009987131,0.00028680312,0.000022038472,0.000031580676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005568577,0.000034303066,0.000039568607,0.00003226493,0.000068348854,0.000012684998,0.00031196664,0.000014869883,0.0000079142765],"category_scores_gemma":[0.00006141039,0.00002742811,0.00001744367,0.00013967695,0.000016434447,0.000092933806,0.00007734033,0.000030046402,0.0000879103],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.020704e-7,0.00004841759,0.027954973,0.0000026845846,0.000004571134,0.00013891037,0.0005086487,0.0000053454614,0.00010880768,0.06476039,0.8576487,0.04881797],"study_design_scores_gemma":[0.00069153274,0.00043998632,0.09208687,0.000049876133,0.0000060537764,0.0037607567,0.0000040472214,0.18466105,0.026944846,0.5803423,0.10952574,0.0014869488],"about_ca_topic_score_codex":0.00005092239,"about_ca_topic_score_gemma":5.2207946e-7,"teacher_disagreement_score":0.74812293,"about_ca_system_score_codex":0.0000066481343,"about_ca_system_score_gemma":0.000017981753,"threshold_uncertainty_score":0.11299384},"labels":[],"label_agreement":null},{"id":"W2160197556","doi":"10.1109/tc.2006.80","title":"Optimizing the length of checking sequences","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Leverhulme Trust","keywords":"Sequence (biology); State (computer science); Set (abstract data type); Algorithm; Finite-state machine; Mathematics; Computer science; Combinatorics","score_opus":0.021365074338475912,"score_gpt":0.24324589287024515,"score_spread":0.22188081853176922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160197556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040098797,0.000039412113,0.991817,0.00045195717,0.00058478385,0.000092608425,0.0000013393825,0.0026909197,0.000312097],"genre_scores_gemma":[0.7150267,0.000003952051,0.2847749,0.00013426764,0.000027359632,0.000008387994,1.6361055e-7,0.000005925484,0.000018395905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990833,0.000057218454,0.00021590918,0.00023725777,0.00022185525,0.00018449638],"domain_scores_gemma":[0.9989073,0.00047174966,0.0000916722,0.00044952214,0.00005392726,0.000025819207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002332699,0.000120937664,0.0001278822,0.00012353518,0.00022236608,0.00008805269,0.00072173175,0.00004024867,0.0000019452518],"category_scores_gemma":[0.0000034283703,0.00009124092,0.000098197226,0.00038486923,0.000091153415,0.00018231272,0.0000043400023,0.00016540712,0.0000042109855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001072086,0.00027364373,0.00012675353,0.000030934352,0.00006268505,0.000019608253,0.0016075053,0.6442675,0.0012327766,0.004339761,0.005367792,0.3426603],"study_design_scores_gemma":[0.00032258886,0.00024368004,0.00030814012,0.0002583339,0.000023748238,0.00007464711,0.000017225642,0.9018099,0.0851272,0.010998863,0.0004234641,0.00039223008],"about_ca_topic_score_codex":0.00031699322,"about_ca_topic_score_gemma":0.000008777031,"teacher_disagreement_score":0.7110168,"about_ca_system_score_codex":0.000032517724,"about_ca_system_score_gemma":0.00003605157,"threshold_uncertainty_score":0.3720697},"labels":[],"label_agreement":null},{"id":"W2160450788","doi":"10.1145/337180.337825","title":"Workshop on standard exchange format (WoSEF) (workshop session)","year":2000,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; World Wide Web","score_opus":0.031036539898250406,"score_gpt":0.2906063153049976,"score_spread":0.2595697754067472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160450788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008516798,0.00026658003,0.84601104,0.004125146,0.00043889048,0.00030596132,0.00000371889,0.035647515,0.10468433],"genre_scores_gemma":[0.40706638,0.0003267306,0.5597798,0.008812352,0.00030835002,0.00008748578,0.000008363944,0.000049812475,0.023560708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984705,0.000054720134,0.00022155321,0.00041560116,0.00042294123,0.00041470458],"domain_scores_gemma":[0.9983584,0.00046629523,0.000048990416,0.00092152826,0.000059277456,0.00014549852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035160052,0.00020697441,0.0001940267,0.00012243504,0.00021772028,0.00026195348,0.00088172196,0.00011553144,0.0008182839],"category_scores_gemma":[0.00013553581,0.00015740759,0.00007824049,0.00048679535,0.00003622098,0.0004821504,0.00017193737,0.00023476695,0.0003814556],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016524815,0.000031787662,0.00007682524,0.0000065168415,0.000003583214,0.000015947266,0.00030592553,0.000030167039,0.0000015687904,0.0017329103,0.2983473,0.69943094],"study_design_scores_gemma":[0.0015493286,0.00074214354,0.0013670619,0.0014251922,0.000019317355,0.00020293848,0.00005766499,0.077130534,0.0030465855,0.14674853,0.76567817,0.0020325533],"about_ca_topic_score_codex":0.000014023638,"about_ca_topic_score_gemma":0.000005545067,"teacher_disagreement_score":0.6973984,"about_ca_system_score_codex":0.00006420513,"about_ca_system_score_gemma":0.000039396386,"threshold_uncertainty_score":0.89596343},"labels":[],"label_agreement":null},{"id":"W2160917074","doi":"10.1142/s0218194013500113","title":"USING TEST ORACLES AND FORMAL SPECIFICATIONS WITH TEST-DRIVEN DEVELOPMENT","year":2013,"lang":"en","type":"article","venue":"International Journal of Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Documentation; Software engineering; Formal specification; Programming language; Test (biology); Formal methods; Test case; Notation; Test Management Approach; Test-driven development; Test suite; Process (computing); Software development; Software; Software construction","score_opus":0.026056357144596323,"score_gpt":0.2394550303039406,"score_spread":0.2133986731593443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160917074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1278666,0.0004666798,0.8705345,0.000072766205,0.0002443467,0.00006092234,0.000001259951,0.0007427751,0.000010156171],"genre_scores_gemma":[0.5026001,0.000018961126,0.49724057,0.0000055926544,0.00010577469,0.000004769939,4.891074e-7,0.000013630059,0.000010143482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991348,0.0000044958047,0.00029286044,0.00015599279,0.00021132281,0.00020057059],"domain_scores_gemma":[0.99848783,0.0006985707,0.000119100565,0.00011706737,0.00043948373,0.00013797643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017438144,0.00017388612,0.0001701038,0.00036062908,0.00006354393,0.0002377561,0.00039064887,0.000047254467,0.000002080709],"category_scores_gemma":[0.0008393768,0.00015090869,0.000028100101,0.0001636231,0.00002019804,0.00077009597,0.00016577663,0.00020583642,0.0000026218788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025473271,0.0009436111,0.3537851,0.00072098116,0.0010636408,0.00042588357,0.011121497,0.13306583,0.025491817,0.005627239,0.0027696756,0.46495923],"study_design_scores_gemma":[0.0007237325,0.00021842637,0.09928853,0.0014504946,0.00002481001,0.0025879776,0.000024571153,0.8877592,0.003177342,0.00017890157,0.003921584,0.0006443926],"about_ca_topic_score_codex":0.0000046075234,"about_ca_topic_score_gemma":6.1027316e-7,"teacher_disagreement_score":0.7546934,"about_ca_system_score_codex":0.00008462579,"about_ca_system_score_gemma":0.000081264014,"threshold_uncertainty_score":0.6153878},"labels":[],"label_agreement":null},{"id":"W2162032875","doi":"10.1109/real.1998.739748","title":"Timed test cases generation based on state characterization technique","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal","funders":"","keywords":"Computer science; Nondeterministic algorithm; Correctness; Test suite; Automaton; Timed automaton; Finite-state machine; Set (abstract data type); System under test; State (computer science); Granularity; Algorithm; Test case; Programming language; Theoretical computer science","score_opus":0.0420348950945121,"score_gpt":0.24113334313612084,"score_spread":0.19909844804160873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162032875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025202539,0.0000029103003,0.98409915,0.00066552317,0.00006551842,0.00021952261,0.0000039577617,0.011193413,0.0012297571],"genre_scores_gemma":[0.7468537,0.0000031002855,0.25087857,0.0013866462,0.000047836398,0.0000860668,0.000019360345,0.000010745844,0.0007139798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919933,0.00004196449,0.0001515366,0.00027656904,0.0001778294,0.00015274694],"domain_scores_gemma":[0.9990884,0.0002758241,0.00006516473,0.00044855208,0.000073167044,0.000048881233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017024452,0.000113030765,0.000083062885,0.00014562545,0.00010515992,0.00014234487,0.00025799175,0.000043892094,0.000061737745],"category_scores_gemma":[0.00038568996,0.00009931971,0.000024949757,0.00030211164,0.000015337075,0.00022846143,0.000036113503,0.000070514376,0.000074867436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007270382,0.001185616,0.010472427,0.000040347928,0.000009212687,0.00022471465,0.00034025768,0.00048503623,0.29059586,0.0020835272,0.1266578,0.5678979],"study_design_scores_gemma":[0.00007421912,0.00023086529,0.0008861456,0.000023283226,0.0000012134757,0.000022891747,6.7502555e-8,0.9055538,0.09186279,0.00045762456,0.00073235354,0.00015474217],"about_ca_topic_score_codex":0.000018862906,"about_ca_topic_score_gemma":0.0000013548131,"teacher_disagreement_score":0.90506876,"about_ca_system_score_codex":0.000035384714,"about_ca_system_score_gemma":0.000014083717,"threshold_uncertainty_score":0.40501404},"labels":[],"label_agreement":null},{"id":"W2163289685","doi":"10.1109/icsm.2002.1167775","title":"Automating impact analysis and regression test selection based on UML designs","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Unified Modeling Language; Regression testing; Selection (genetic algorithm); Test (biology); Regression analysis; Data mining; Programming language; Software engineering; Artificial intelligence; Machine learning; Software; Software development","score_opus":0.02588388994970477,"score_gpt":0.3075896533459878,"score_spread":0.28170576339628306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163289685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025455076,0.000007718044,0.96627295,0.000056484143,0.000016434096,0.00005674849,2.594054e-7,0.0067760376,0.0013583123],"genre_scores_gemma":[0.6156365,4.0406772e-7,0.3842144,0.00010273014,0.000004144526,0.000003780026,5.0362064e-7,0.0000033815518,0.000034118708],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991733,0.00009550049,0.00012188812,0.00028081326,0.00016278395,0.00016572184],"domain_scores_gemma":[0.99879664,0.0007335833,0.00007000822,0.00027758212,0.000051639083,0.00007056337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004726553,0.000113045215,0.00012838528,0.00032916557,0.00016791145,0.00015024836,0.00013252546,0.00004736594,0.000018691939],"category_scores_gemma":[0.0010847065,0.00007894233,0.000060486043,0.0012975745,0.000012721971,0.0001372398,0.000020483518,0.000080792975,0.000003323829],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019617407,0.00009987145,0.9341925,0.000007848954,0.000030782237,0.0000049602736,0.00007111642,0.0012291834,0.001194068,0.0005710341,0.003156422,0.05944028],"study_design_scores_gemma":[0.00007860749,0.00021143354,0.081770316,0.000032037562,0.000022151262,0.000008593113,4.7819674e-7,0.90828276,0.007714846,0.0017577661,0.000005217329,0.000115805255],"about_ca_topic_score_codex":0.00009052583,"about_ca_topic_score_gemma":0.0000051023003,"teacher_disagreement_score":0.9070536,"about_ca_system_score_codex":0.00004780489,"about_ca_system_score_gemma":0.000046101428,"threshold_uncertainty_score":0.32191747},"labels":[],"label_agreement":null},{"id":"W2163844940","doi":"10.1109/ccece.2011.6030533","title":"Integration testing object-oriented software systems: An experiment-driven research approach","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Integration testing; Unit testing; Computer science; Class (philosophy); Process (computing); White-box testing; System integration; Software engineering; System integration testing; Test strategy; Software; Systems engineering; Programming language; Artificial intelligence; Software construction; Software development; Engineering; Database","score_opus":0.24943487068187783,"score_gpt":0.35682480079505396,"score_spread":0.10738993011317613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163844940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009662684,0.000065343374,0.95821553,0.000007859571,0.00018706411,0.00036122344,6.962436e-7,0.017843965,0.013655603],"genre_scores_gemma":[0.42233562,4.8768555e-7,0.57735497,0.000021302616,0.00003493317,0.00011455252,0.0000042834045,0.000012824485,0.00012101814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976779,0.00035554788,0.00029866348,0.00065248803,0.0005470347,0.0004683201],"domain_scores_gemma":[0.9976704,0.0003830315,0.000084289924,0.0010441047,0.0006557845,0.0001623557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013143017,0.00017648417,0.00017537961,0.00032627795,0.00035638292,0.00026235302,0.0010827726,0.00010576508,0.000006481376],"category_scores_gemma":[0.0013022496,0.00014608871,0.00003294539,0.0010541113,0.000089989786,0.000777454,0.00037788425,0.00030376075,0.000029560531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008854634,0.0042835935,0.09184897,0.0003658363,0.00012320446,0.00019228105,0.10451184,0.0003226907,0.016674515,0.42705953,0.06728996,0.28723902],"study_design_scores_gemma":[0.00035849796,0.0013858256,0.0031423112,0.0003155897,0.000007209382,0.00015853689,0.0012812616,0.96158886,0.015782773,0.01497557,0.00024453798,0.0007590279],"about_ca_topic_score_codex":0.0019835192,"about_ca_topic_score_gemma":0.000004723816,"teacher_disagreement_score":0.96126616,"about_ca_system_score_codex":0.00010412819,"about_ca_system_score_gemma":0.000108267006,"threshold_uncertainty_score":0.5957325},"labels":[],"label_agreement":null},{"id":"W2164188174","doi":"10.1109/compsac.2005.151","title":"Testing the Semantics of W3C XML Schema","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; XML Schema Editor; XML Schema (W3C); RELAX NG; Document Structure Description; XML validation; Streaming XML; Efficient XML Interchange; XML; Programming language; Information retrieval; World Wide Web; XML Signature","score_opus":0.031104465118838128,"score_gpt":0.2450003664756878,"score_spread":0.21389590135684966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164188174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023771279,0.00003820771,0.94681615,0.0008604273,0.000058343143,0.00006696015,1.8767246e-7,0.0064573605,0.02193106],"genre_scores_gemma":[0.53671086,1.1986425e-7,0.46305352,0.00009622125,0.000020439313,0.0000017094956,9.2951346e-8,0.0000026685661,0.000114358205],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943626,0.000018124987,0.00014310979,0.00012967738,0.00014769338,0.00012510821],"domain_scores_gemma":[0.9988466,0.000548311,0.00006810552,0.00044779445,0.00007604109,0.000013161402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027152253,0.00006159659,0.00007278031,0.000026951731,0.00007075746,0.000044505752,0.00053573615,0.000024414725,0.0000037637624],"category_scores_gemma":[0.00036865883,0.000038782426,0.000025228333,0.0003759869,0.00004578725,0.00007489454,0.00021865961,0.00005824206,0.000010645601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016357743,0.00019797,0.245961,0.000057406276,0.000013560672,0.00002160426,0.00025293848,0.00038332609,0.0103566265,0.28096542,0.33600116,0.12578736],"study_design_scores_gemma":[0.00018122603,0.00012774998,0.08026059,0.00012023307,0.0000113634715,0.00011068137,0.0000046105833,0.29544872,0.060766127,0.55999297,0.0026182379,0.00035750642],"about_ca_topic_score_codex":0.0004513655,"about_ca_topic_score_gemma":0.0000035365845,"teacher_disagreement_score":0.5129396,"about_ca_system_score_codex":0.0000063298025,"about_ca_system_score_gemma":0.000019742192,"threshold_uncertainty_score":0.15815014},"labels":[],"label_agreement":null},{"id":"W2164209468","doi":"10.1109/enabl.2001.953386","title":"SCENTOR: scenario-based testing of e-business applications","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software engineering; Extreme programming; Schedule; Pace; Task (project management); Business requirements; Black-box testing; Software development; Software; Business process; Systems engineering; Software development process; Software construction; Programming language; Operating system; Engineering","score_opus":0.05492985228936814,"score_gpt":0.24851425001435307,"score_spread":0.19358439772498492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164209468","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039127993,0.00007582736,0.9833267,0.0003716994,0.000031447486,0.000121695346,5.5625515e-7,0.0077203754,0.007960416],"genre_scores_gemma":[0.4457932,7.5368735e-7,0.5539144,0.00016485127,0.000016607712,0.000023904284,3.915997e-7,0.0000044189997,0.00008146083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992914,0.000015587932,0.0001711498,0.00021125532,0.00016168163,0.0001489332],"domain_scores_gemma":[0.9987693,0.00029752968,0.00008226681,0.0005590755,0.00024673154,0.00004511206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013423954,0.0000789375,0.000098403005,0.000101670914,0.00008219409,0.00004653562,0.0005630013,0.000032461066,0.000019663456],"category_scores_gemma":[0.00027945542,0.00007098706,0.00002415748,0.0009992839,0.000041489333,0.00011356527,0.00008578667,0.00005161783,0.00002868693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000145948,0.00068926,0.102528945,0.00016418596,0.000011142392,0.0000066990315,0.00017812356,0.0008143277,0.0016061594,0.017382016,0.05241487,0.82420284],"study_design_scores_gemma":[0.0002756053,0.000069262496,0.009352445,0.0001628156,0.0000075242106,0.000016952787,0.0000013561266,0.9652481,0.0060508386,0.013357237,0.0051245405,0.0003332994],"about_ca_topic_score_codex":0.00009324298,"about_ca_topic_score_gemma":0.0000011083273,"teacher_disagreement_score":0.9644338,"about_ca_system_score_codex":0.000017092303,"about_ca_system_score_gemma":0.00002748553,"threshold_uncertainty_score":0.2894768},"labels":[],"label_agreement":null},{"id":"W2164551036","doi":"10.1109/sew.2003.1270746","title":"Software verification and validation within the (rational) unified process","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Software verification; Verification and validation; Process (computing); Software engineering; Unified Process; Functional verification; Verification; Formal verification; Software; Programming language; Unified Modeling Language; Software construction; Software development; Engineering","score_opus":0.024221883433120418,"score_gpt":0.2688568003011636,"score_spread":0.24463491686804317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164551036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035239868,0.000021109028,0.957838,0.0021547477,0.000053395313,0.000119343764,2.8437714e-7,0.0043339333,0.00023930045],"genre_scores_gemma":[0.74517727,0.0000012902841,0.25443637,0.0003037765,0.00001478827,0.000021087933,0.0000032379278,0.000003025166,0.000039134695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999468,0.000020527836,0.000107861706,0.00018314272,0.00015282059,0.000067644534],"domain_scores_gemma":[0.9994396,0.000101142694,0.0000597038,0.00027471592,0.00010131645,0.000023542965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028143488,0.000059869282,0.000041462703,0.000033811735,0.00017671016,0.00015182972,0.00027475646,0.000028714918,0.0000012030844],"category_scores_gemma":[0.0003106675,0.000039874936,0.000009165965,0.0002182054,0.00003462998,0.00030330065,0.00003994743,0.00005672965,0.0000065229506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007845072,0.00010264763,0.008770369,0.000044559227,0.000014671278,0.000003121383,0.0058190417,0.004582058,0.00044822422,0.9415487,0.002204785,0.03645397],"study_design_scores_gemma":[0.00018254995,0.00005256743,0.008016383,0.000030864867,0.000004139885,0.000034467554,0.000023277094,0.009401374,0.01831001,0.96372116,0.00007336032,0.00014987684],"about_ca_topic_score_codex":0.00004357492,"about_ca_topic_score_gemma":0.0000036271203,"teacher_disagreement_score":0.7099374,"about_ca_system_score_codex":0.000018428593,"about_ca_system_score_gemma":0.000076394484,"threshold_uncertainty_score":0.16260527},"labels":[],"label_agreement":null},{"id":"W2164617101","doi":"10.1145/1082983.1083247","title":"Dynamic analysis of java applications for multithreaded antipatterns","year":2005,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Java; Tracing; Programming language; TRACE (psycholinguistics); Scalability; Model checking; Formal methods; Java Modeling Language; Formal specification; Software engineering; Eclipse; Java annotation; Real time Java; Operating system","score_opus":0.018557714815639687,"score_gpt":0.2824922130252833,"score_spread":0.26393449820964365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164617101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029521827,0.00021513461,0.9623083,0.00022391576,0.000062152205,0.00031976664,0.000052917203,0.0072953957,5.823129e-7],"genre_scores_gemma":[0.51285344,0.000004559798,0.4868804,0.0000493055,0.000022322018,0.00013728588,0.000028848486,0.000016875063,0.000006963189],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998642,0.000010563355,0.0003739255,0.00044520706,0.00020227683,0.0003260186],"domain_scores_gemma":[0.9746915,0.02361208,0.00014483312,0.0012920799,0.00017389802,0.00008556945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00022901855,0.00022228733,0.00037922393,0.00057207845,0.000078798206,0.000056882294,0.0012573319,0.00010170793,0.0000049654823],"category_scores_gemma":[0.022977289,0.00023289396,0.00023349143,0.0011921088,0.00002770072,0.00023187348,0.00023104103,0.00011283937,0.000006307282],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011050592,0.0003780822,0.68108207,0.0003880753,0.001087263,0.000003484482,0.0011588986,0.04756724,0.0060828514,0.0017943659,0.0009789607,0.2594677],"study_design_scores_gemma":[0.0007232051,0.00017829495,0.36988297,0.0001826234,0.00074222754,0.000014213939,0.00000365933,0.60046875,0.021178463,0.0010173677,0.004333412,0.0012747983],"about_ca_topic_score_codex":0.000040553212,"about_ca_topic_score_gemma":0.000011606162,"teacher_disagreement_score":0.5529015,"about_ca_system_score_codex":0.00005564809,"about_ca_system_score_gemma":0.00003404329,"threshold_uncertainty_score":0.98525256},"labels":[],"label_agreement":null},{"id":"W2164968206","doi":"10.1109/icst.2012.111","title":"Generating Checking Sequences for Nondeterministic Finite State Machines","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Nondeterministic algorithm; Finite-state machine; Computer science; Sequence (biology); Model checking; Deterministic finite automaton; Theoretical computer science; Generalization; State (computer science); Automaton; Class (philosophy); Algorithm; Fault coverage; Programming language; Mathematics; Artificial intelligence","score_opus":0.048602551238794436,"score_gpt":0.3108628382386156,"score_spread":0.2622602869998212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164968206","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013097147,0.000101519785,0.97989833,0.00011480101,0.00032082046,0.00012194346,0.0000023108382,0.0057367804,0.0006063273],"genre_scores_gemma":[0.47133416,0.0000011360295,0.52796173,0.0003598322,0.00010198849,0.000031321244,0.0000012368181,0.000006345215,0.00020223431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909335,0.000028046177,0.00018596077,0.00020726526,0.00012282333,0.00036255803],"domain_scores_gemma":[0.99874747,0.0007415927,0.00008001033,0.0002924565,0.000057616202,0.00008086253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005278794,0.000121024,0.00011794635,0.000067011795,0.00019382003,0.0001775572,0.0004202499,0.000029281202,0.000004845827],"category_scores_gemma":[0.00055413076,0.00009719732,0.000045956123,0.00014015373,0.000024458614,0.0004145834,0.00013015013,0.000058764097,0.000009550978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075018593,0.00013999938,0.056335427,0.00016609534,0.000037044036,0.00002185699,0.0045967745,0.001121334,0.0031259195,0.018329915,0.013700917,0.90241724],"study_design_scores_gemma":[0.000106061205,0.00008255911,0.00046150212,0.000038734906,0.0000051241987,0.000049483053,0.000003105563,0.9618844,0.003565463,0.032560144,0.00095705595,0.00028636408],"about_ca_topic_score_codex":0.000050512095,"about_ca_topic_score_gemma":0.0000031974018,"teacher_disagreement_score":0.9607631,"about_ca_system_score_codex":0.000017119404,"about_ca_system_score_gemma":0.000031635067,"threshold_uncertainty_score":0.39635918},"labels":[],"label_agreement":null},{"id":"W2165679316","doi":"10.1109/icst.2008.18","title":"A Three-Tiered Testing Strategy for Cookies","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Scalability; Test suite; Random testing; Grammar; Suite; Reliability (semiconductor); Artificial intelligence; Test case; Machine learning; Database","score_opus":0.15301318136428213,"score_gpt":0.2990189896137123,"score_spread":0.14600580824943019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165679316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041234964,0.000049282724,0.9758802,0.00012566669,0.000062310006,0.00015111704,7.9981675e-7,0.014915731,0.004691395],"genre_scores_gemma":[0.40303946,5.0793517e-7,0.5966019,0.00014320815,0.00003244553,0.0000294964,5.044033e-7,0.000005548638,0.00014689624],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992759,0.000007465676,0.00013946269,0.00024888502,0.00011498572,0.00021326485],"domain_scores_gemma":[0.9988001,0.0006111466,0.00004640286,0.00035146147,0.00014037664,0.000050492345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015488948,0.00009679406,0.000109836714,0.000057671838,0.0002237743,0.00006394624,0.00045933638,0.000038818882,0.0000023574637],"category_scores_gemma":[0.0005396601,0.000082225684,0.000036791065,0.0002470671,0.000044570545,0.00018326245,0.00009044919,0.0000533126,0.000009099615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000148051595,0.00019387213,0.06410253,0.00006778157,0.00003497013,0.0000884442,0.000524449,0.00027681084,0.0006865352,0.14797036,0.39302784,0.3930116],"study_design_scores_gemma":[0.00036752355,0.00049397995,0.011056444,0.000043514785,0.0000041670487,0.0002989186,0.0000036290237,0.4155843,0.0024908378,0.56846005,0.0007907853,0.00040582384],"about_ca_topic_score_codex":0.00016587078,"about_ca_topic_score_gemma":0.000008890321,"teacher_disagreement_score":0.4204897,"about_ca_system_score_codex":0.000013547716,"about_ca_system_score_gemma":0.00008439708,"threshold_uncertainty_score":0.3353066},"labels":[],"label_agreement":null},{"id":"W2166103344","doi":"10.1109/ccece.1999.807212","title":"Formal test requirements for component interactions","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Integration testing; Concurrency; Unit testing; Component (thermodynamics); Model-based testing; Formal methods; Conformance testing; Test case; Formal specification; Test (biology); Software engineering; Programming language; Reliability engineering; Software; Machine learning; Engineering; Standardization","score_opus":0.05891314489628981,"score_gpt":0.32213162065631656,"score_spread":0.26321847576002677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166103344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007952652,0.000007401047,0.98216504,0.00025815534,0.0002571708,0.00014357117,9.675474e-7,0.0049529597,0.011419473],"genre_scores_gemma":[0.47225505,4.638296e-7,0.52683115,0.00031991678,0.000012148833,0.000041680996,0.0000010945148,0.0000036971276,0.00053481513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994075,0.000012143968,0.00013075677,0.00016370283,0.00008815952,0.00019778237],"domain_scores_gemma":[0.99914634,0.0004131378,0.000038717793,0.00029016685,0.00006579335,0.000045846602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022785149,0.00006789796,0.000064410306,0.00005616928,0.0001441986,0.00007885288,0.0002653975,0.000015945685,0.000012676174],"category_scores_gemma":[0.00045326957,0.00005904751,0.0000397798,0.00010766373,0.000011265443,0.0004010304,0.00006084557,0.00004206811,0.000015980875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054688853,0.0006534478,0.018410292,0.00003495014,0.000027728644,0.0000057722714,0.00037066668,0.000018988723,0.001827881,0.50973994,0.3888026,0.08010227],"study_design_scores_gemma":[0.001471467,0.00092148967,0.0045578433,0.0001419569,0.000019967945,0.00022256143,0.000022693832,0.18004109,0.05325126,0.43791896,0.32046232,0.00096839824],"about_ca_topic_score_codex":0.000013782063,"about_ca_topic_score_gemma":0.0000025611068,"teacher_disagreement_score":0.47145978,"about_ca_system_score_codex":0.000029676154,"about_ca_system_score_gemma":0.000022463128,"threshold_uncertainty_score":0.24078876},"labels":[],"label_agreement":null},{"id":"W2166881673","doi":"10.1109/snpd.2009.55","title":"A Tool Suite for Java Program Tracing and Feature Location","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"Algoma University","keywords":"Suite; Java; Debugging; Computer science; Programmer; Tracing; Programming language; Feature (linguistics); TRACE (psycholinguistics); Source code; Call graph; Focus (optics); Operating system","score_opus":0.016399273823345044,"score_gpt":0.291218842187196,"score_spread":0.27481956836385096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166881673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007373678,0.000099790814,0.9785114,0.0021792932,0.000031206328,0.00037424816,2.0776815e-7,0.011036393,0.00039377983],"genre_scores_gemma":[0.42981973,8.01256e-7,0.5695592,0.0003982156,0.000020496187,0.00002362408,7.512171e-7,0.0000018753957,0.00017529764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953896,0.000007551985,0.00006634311,0.00019025287,0.0000671266,0.00012975543],"domain_scores_gemma":[0.99958724,0.000096177835,0.000025369223,0.00019206457,0.00007125789,0.000027885411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001696481,0.00006356825,0.0000626891,0.0000411024,0.00007355355,0.0001629181,0.00015265551,0.000041488074,2.6453614e-7],"category_scores_gemma":[0.00015609968,0.00005220986,0.00001678105,0.00016742034,0.000009038659,0.00013601525,0.000020001347,0.00004424229,7.654014e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017746809,0.000028756436,0.0003454307,0.000010835355,0.0000010601813,7.255347e-7,0.00014585356,0.0000033608646,0.00006384943,0.006909137,0.014976951,0.97751224],"study_design_scores_gemma":[0.00074592617,0.0019604706,0.04247275,0.00022861271,0.000016535167,0.00015537243,0.000009093702,0.5787782,0.005992443,0.3598468,0.009090994,0.0007027944],"about_ca_topic_score_codex":0.0000058456358,"about_ca_topic_score_gemma":0.0000011910579,"teacher_disagreement_score":0.97680944,"about_ca_system_score_codex":0.000009601162,"about_ca_system_score_gemma":0.000017208502,"threshold_uncertainty_score":0.21290563},"labels":[],"label_agreement":null},{"id":"W2166906534","doi":"10.1109/infcom.1993.253243","title":"A unified approach to protocol test sequence generation","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Executable; Extended finite-state machine; Computer science; Constraint satisfaction problem; Sequence (biology); Theoretical computer science; Control flow; Finite-state machine; Control flow graph; Constraint (computer-aided design); Algorithm; Data flow diagram; Construct (python library); Graph; Data-flow analysis; Data mining; Programming language; Artificial intelligence; Mathematics; Database","score_opus":0.14543768759567544,"score_gpt":0.30963796361751794,"score_spread":0.1642002760218425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166906534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075169744,8.615552e-7,0.9424853,0.00045588677,0.00002298459,0.014619445,3.2157777e-7,0.010193679,0.03214639],"genre_scores_gemma":[0.06901249,8.217849e-8,0.887433,0.0010672186,0.00006114177,0.041052204,6.2989204e-7,0.000006502245,0.0013667617],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991596,0.000025459633,0.00013428714,0.00032869948,0.00017535024,0.00017664272],"domain_scores_gemma":[0.9992046,0.00007560457,0.000031052426,0.00053295,0.00007216931,0.000083673076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017853004,0.00009398665,0.00007393678,0.000079422,0.00009308933,0.00017944773,0.0005470399,0.000037641905,0.000013665656],"category_scores_gemma":[0.00031082492,0.00007793412,0.000019433443,0.00045197573,0.000013647475,0.00020911284,0.00012345196,0.000047091213,0.000106503976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001651447,0.00068108685,0.0023189164,0.000041679014,0.000005438637,0.000013809051,0.0012411891,0.00028967852,0.01218964,0.04587084,0.7534091,0.18393701],"study_design_scores_gemma":[0.00013090404,0.00017065865,0.00013752388,0.000013090394,8.750309e-7,0.00004145402,9.013331e-7,0.9811134,0.0069117355,0.004202877,0.0070462455,0.00023034828],"about_ca_topic_score_codex":0.000029463752,"about_ca_topic_score_gemma":0.0000010354756,"teacher_disagreement_score":0.9808237,"about_ca_system_score_codex":0.00003117865,"about_ca_system_score_gemma":0.000014353625,"threshold_uncertainty_score":0.31780612},"labels":[],"label_agreement":null},{"id":"W2167505893","doi":"10.1109/tr.2009.2034288","title":"A Novel Evolutionary Approach for Adaptive Random Testing","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Random testing; Sobol sequence; Computer science; Evolutionary algorithm; Test strategy; Generality; Orthogonal array testing; Mathematical optimization; Random search; Algorithm; Test case; Monte Carlo method; Mathematics; Machine learning; Statistics","score_opus":0.04507286624197506,"score_gpt":0.2673688255707413,"score_spread":0.22229595932876625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167505893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005000791,0.000014290488,0.99102384,0.00031633643,0.00017871718,0.0006498778,0.000026160646,0.0065259202,0.00076478336],"genre_scores_gemma":[0.48350394,5.075814e-7,0.516199,0.00014641261,0.00001921198,0.00010533499,7.3243126e-7,0.0000041432772,0.000020722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853235,0.00005799517,0.0002796961,0.0006048005,0.00023051514,0.00029463795],"domain_scores_gemma":[0.99755675,0.0013098578,0.00007514937,0.0007049003,0.00026113397,0.00009218715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061453483,0.00018554533,0.00021553482,0.0001129803,0.00036114437,0.00005182027,0.00046496702,0.00010281963,0.000001229599],"category_scores_gemma":[0.00025086105,0.00017242141,0.00016119676,0.00051327667,0.0000557665,0.00025336412,0.0000016065749,0.00024584765,0.000002688752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070373615,0.005174879,0.00013871143,0.00008905062,0.000053257503,0.0000033290096,0.0006532292,0.24048014,0.0025138308,0.0019961053,0.004208668,0.74398506],"study_design_scores_gemma":[0.0010142126,0.00067639234,0.0015166543,0.000035799334,0.000017710374,0.000031276093,0.0000036882977,0.9618256,0.0015985386,0.032966148,0.000050455048,0.00026351312],"about_ca_topic_score_codex":0.00005162876,"about_ca_topic_score_gemma":8.1391744e-7,"teacher_disagreement_score":0.74372154,"about_ca_system_score_codex":0.00013369141,"about_ca_system_score_gemma":0.00010636937,"threshold_uncertainty_score":0.7031141},"labels":[],"label_agreement":null},{"id":"W2167680630","doi":"10.1145/2491404.2491406","title":"Efficiency of subtype test in object oriented languages with generics","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Programming language; Test (biology); Semantics (computer science); Typing; Object-oriented programming","score_opus":0.008265875011669218,"score_gpt":0.23454597693097187,"score_spread":0.22628010191930265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167680630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4200076,0.00008037119,0.5683693,0.0002303419,0.000038030128,0.00019978132,5.1471113e-7,0.0043232273,0.0067508044],"genre_scores_gemma":[0.7457407,0.000001493174,0.2540411,0.000101751815,0.0000056978492,0.000010178154,4.2005203e-7,0.0000039005013,0.00009477273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993772,0.000016564309,0.00012714304,0.000179399,0.00014505349,0.00015465161],"domain_scores_gemma":[0.99925876,0.00020895337,0.00005186093,0.00035390118,0.00009648625,0.000030034393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012381902,0.0000746447,0.00010292948,0.00011182784,0.000018790217,0.000027633716,0.0003478018,0.0000271967,0.000013454746],"category_scores_gemma":[0.00028887318,0.00005117653,0.000012979144,0.00068151066,0.000035559184,0.00012817305,0.000087221204,0.00005634418,0.000014526359],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040894142,0.00052597845,0.9367462,0.0000490207,0.0000071531454,0.00004113632,0.0014416841,0.0001021498,0.004857732,0.005866805,0.013432719,0.03692536],"study_design_scores_gemma":[0.0015243642,0.0035447218,0.63420635,0.00043253,0.000012654119,0.00016040805,0.00022318479,0.25645095,0.08921662,0.0124087185,0.000459713,0.0013597687],"about_ca_topic_score_codex":0.0009224358,"about_ca_topic_score_gemma":0.00003165361,"teacher_disagreement_score":0.3257331,"about_ca_system_score_codex":0.000013141368,"about_ca_system_score_gemma":0.000044979213,"threshold_uncertainty_score":0.20869184},"labels":[],"label_agreement":null},{"id":"W2167924718","doi":"10.1109/compsac.2008.123","title":"Mutation-Based Testing of Buffer Overflow Vulnerabilities","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Buffer overflow; Computer science; Vulnerability (computing); Secure coding; Fuzz testing; Vulnerability management; Set (abstract data type); Software; Vulnerability assessment; Computer security; Software security assurance; Programming language; Information security","score_opus":0.04601465034739637,"score_gpt":0.2578013310027019,"score_spread":0.21178668065530554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167924718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11245611,0.000022816615,0.8764903,0.00012765448,0.0000612349,0.00006066366,6.796687e-7,0.006879873,0.0039006914],"genre_scores_gemma":[0.55544955,1.29532e-7,0.44430912,0.00013798181,0.000009784915,0.0000054527927,4.055623e-7,0.0000030843541,0.00008451647],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928313,0.000034561854,0.00017932866,0.00018055548,0.00019200417,0.00013042598],"domain_scores_gemma":[0.9978654,0.0014462688,0.00006182839,0.0003743255,0.00021854565,0.00003365842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018554696,0.000078346835,0.000109909524,0.00008197939,0.00009983795,0.000017997376,0.000314793,0.000029590896,0.000011878286],"category_scores_gemma":[0.0015440645,0.00006754182,0.000029629795,0.00035748523,0.00007563615,0.0001422417,0.00005089634,0.000058044712,0.0000058376477],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001010831,0.00039285497,0.8670331,0.00016471703,0.000022596998,0.0001228475,0.0020881358,0.005023767,0.0017628408,0.017593624,0.04516557,0.06061982],"study_design_scores_gemma":[0.00035477383,0.0003388543,0.04753272,0.00009611772,0.000004134788,0.00011923127,0.0000072549465,0.84408826,0.05054451,0.056396443,0.0001632847,0.00035440142],"about_ca_topic_score_codex":0.0003580922,"about_ca_topic_score_gemma":0.0000015444222,"teacher_disagreement_score":0.8390645,"about_ca_system_score_codex":0.000015813606,"about_ca_system_score_gemma":0.00013054967,"threshold_uncertainty_score":0.27542755},"labels":[],"label_agreement":null},{"id":"W2169207812","doi":"10.1109/qsic.2006.46","title":"Optimal Synchronizable Test Sequence from Test Segments","year":2006,"lang":"en","type":"article","venue":"Proceedings of the ... International Conference on Quality Software/Proceedings","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Controllability; Computer science; Sequence (biology); Test (biology); Conformance testing; Context (archaeology); System under test; Test case; Machine learning; Mathematics","score_opus":0.05284735757345193,"score_gpt":0.3021675926522371,"score_spread":0.24932023507878515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169207812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9169059,0.000066636654,0.012710827,0.007746677,0.0011232474,0.0009489583,0.0003411137,0.009661438,0.050495204],"genre_scores_gemma":[0.85982543,0.000012215512,0.13826363,0.00054976594,0.00025247256,0.000075638556,0.000012351222,0.000038668968,0.0009698092],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954396,0.0000070481933,0.0009996749,0.0011485071,0.0017365478,0.0006686042],"domain_scores_gemma":[0.9947691,0.00085142377,0.0012108518,0.0003459771,0.0026628505,0.00015980276],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011220925,0.0005297039,0.00051284605,0.00025335536,0.0004329647,0.0010361763,0.0049772807,0.00023052107,0.000065428096],"category_scores_gemma":[0.004926254,0.00044892335,0.0002286803,0.00072537275,0.0003334056,0.0014632478,0.0013862211,0.00047428775,0.000048737547],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005433892,0.0009420842,0.6853598,0.00016820952,0.00007951692,0.0000027974027,0.0006697045,0.000018869541,0.05751185,0.21215937,0.040548846,0.0024846585],"study_design_scores_gemma":[0.0020305598,0.00095956144,0.1255786,0.0030886347,0.00009739687,0.00010736577,0.00036959324,0.028921265,0.28363124,0.55036944,0.0023665603,0.0024797672],"about_ca_topic_score_codex":0.0009993087,"about_ca_topic_score_gemma":0.0000063570465,"teacher_disagreement_score":0.55978113,"about_ca_system_score_codex":0.0003985445,"about_ca_system_score_gemma":0.00016445258,"threshold_uncertainty_score":0.9997963},"labels":[],"label_agreement":null},{"id":"W2169461503","doi":"10.1109/apsec.1994.465263","title":"Automated class testing: methods and experience","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Oracle; Computer science; Class (philosophy); Object (grammar); Contrast (vision); Programming language; Test (biology); Theoretical computer science; Artificial intelligence","score_opus":0.094927932525324,"score_gpt":0.3667322613879026,"score_spread":0.2718043288625786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169461503","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056042345,0.00014790686,0.91134393,0.00038684308,0.00008608834,0.00006050482,9.2957606e-8,0.0685058,0.013864594],"genre_scores_gemma":[0.25773653,0.0000024463277,0.7416161,0.0003872987,0.000009123214,0.000010773771,4.3373177e-8,0.0000042303163,0.00023346132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992054,0.00006830989,0.00012902837,0.00030219406,0.00010462092,0.00019046044],"domain_scores_gemma":[0.9987537,0.0006691815,0.00003835084,0.000403594,0.000055301276,0.00007986882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002602716,0.000095072886,0.00009854356,0.0000648843,0.00010657285,0.00014913703,0.00040279847,0.000041374195,0.000015881857],"category_scores_gemma":[0.0010156236,0.000079075544,0.000013522033,0.00042423245,0.000057868903,0.00022929879,0.00022501154,0.00006765459,0.00001545929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7997804e-7,0.00006681685,0.011795138,0.000013298184,0.0000058095,0.000030425897,0.0023956785,0.0000072643065,0.0024188966,0.011236167,0.07963139,0.89239866],"study_design_scores_gemma":[0.0000535199,0.000050910945,0.0020455,0.000014190633,0.00000104597,0.000099607154,0.0000035871997,0.9852721,0.0024587377,0.008193156,0.0016696885,0.0001379183],"about_ca_topic_score_codex":0.000042637635,"about_ca_topic_score_gemma":2.558179e-7,"teacher_disagreement_score":0.9852649,"about_ca_system_score_codex":0.000010720427,"about_ca_system_score_gemma":0.000005726253,"threshold_uncertainty_score":0.3224607},"labels":[],"label_agreement":null},{"id":"W2170327261","doi":"10.1109/ccece.1997.614838","title":"The event-flow technique for selecting test cases for object-oriented programs","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Event (particle physics); Test (biology); Flow (mathematics); Mathematics","score_opus":0.03880748932803603,"score_gpt":0.2857414402070478,"score_spread":0.24693395087901177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170327261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000108187436,0.00010374201,0.98579174,0.00070657214,0.00014177813,0.001752482,0.000002978509,0.011045262,0.00034724508],"genre_scores_gemma":[0.16024864,0.000004788487,0.83586514,0.00016536235,0.000089415094,0.0025721719,0.0000030525118,0.000020288135,0.001031172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987244,0.00002648184,0.0002510613,0.00037909482,0.00015291305,0.00046603824],"domain_scores_gemma":[0.995317,0.0037216002,0.0001060343,0.0005170839,0.00027541048,0.00006287551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006689457,0.00016186334,0.0001331631,0.00005735196,0.0007383864,0.00026125665,0.00063618005,0.00007039207,0.0000017657363],"category_scores_gemma":[0.003415577,0.00011014654,0.000113179194,0.00044914882,0.000044541383,0.00016085785,0.00011036582,0.00009973421,0.0000030965098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012429568,0.000412757,0.0041235085,0.00007627666,0.000029152654,0.000007718422,0.00044990974,0.000011421906,0.0009507331,0.010363945,0.16831037,0.81525177],"study_design_scores_gemma":[0.00063549436,0.0028967808,0.00006319758,0.00019204969,0.000023828281,0.0004588976,0.00003114192,0.8064016,0.045840807,0.052177265,0.0905363,0.00074265635],"about_ca_topic_score_codex":0.000035983863,"about_ca_topic_score_gemma":0.000023115614,"teacher_disagreement_score":0.8145091,"about_ca_system_score_codex":0.000045560173,"about_ca_system_score_gemma":0.000030908916,"threshold_uncertainty_score":0.5679146},"labels":[],"label_agreement":null},{"id":"W2170644445","doi":"10.1109/wcre.2008.27","title":"Data Model Reverse Engineering in Migrating a Legacy System to Java","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Java; Programming language; Programmer; Legacy system; Reverse engineering; Coding (social sciences); Software engineering; Data modeling; Software","score_opus":0.07230785660745945,"score_gpt":0.2711514458224755,"score_spread":0.19884358921501608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170644445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043631718,0.00001608046,0.9459863,0.00018489653,0.000048440248,0.00010367065,0.0000014276634,0.009396244,0.0006312224],"genre_scores_gemma":[0.46572107,4.471835e-7,0.5340819,0.00010616332,0.000013185381,0.000006922839,0.0000010424196,0.000005077208,0.00006424847],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990445,0.0000141845485,0.00019479076,0.00037410276,0.00015638597,0.00021604734],"domain_scores_gemma":[0.99863565,0.00011211586,0.000025993744,0.0011238664,0.000028958184,0.0000733872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003413193,0.00009940624,0.00012483446,0.00015470223,0.00005379862,0.000071625334,0.0011933591,0.000032225256,4.186679e-7],"category_scores_gemma":[0.000359309,0.00009435877,0.000014959966,0.0004290971,0.0000053456806,0.00063557824,0.00067127467,0.00009488653,0.000017991157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011294165,0.00019234477,0.015169027,0.0003371365,0.000023892535,0.0013237529,0.0078079244,0.27979672,0.0012075024,0.05167312,0.62259376,0.019863555],"study_design_scores_gemma":[0.00006944957,0.000014247038,0.00016836723,0.00012566856,6.2212166e-7,0.00011054385,0.0000060271414,0.9990264,0.000121027275,0.000071402,0.00016051902,0.00012569112],"about_ca_topic_score_codex":0.00053182483,"about_ca_topic_score_gemma":0.000019918056,"teacher_disagreement_score":0.7192297,"about_ca_system_score_codex":0.000055496374,"about_ca_system_score_gemma":0.00005414911,"threshold_uncertainty_score":0.3847839},"labels":[],"label_agreement":null},{"id":"W2171074827","doi":"10.1145/2687148.2687151","title":"Verifying security patches","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Correctness; Credence; Sketch; Semantics (computer science); Set (abstract data type); Program analysis; Computer security; Nothing; Programming language; Theoretical computer science; Algorithm; Machine learning","score_opus":0.011135649131328113,"score_gpt":0.2292289484173727,"score_spread":0.2180932992860446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171074827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005582052,0.00001588388,0.9595575,0.00036899597,0.00010295397,0.000024216417,5.5785026e-8,0.017216932,0.017131409],"genre_scores_gemma":[0.71829176,6.817944e-7,0.28114253,0.00047982854,0.000027630664,0.0000029528555,1.3942697e-7,0.0000024456497,0.0000520579],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995103,0.000028590624,0.00006993457,0.00016795032,0.00009653066,0.00012668746],"domain_scores_gemma":[0.9993575,0.00017866881,0.000020629324,0.0003775766,0.000025460746,0.00004016197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000277546,0.000055514054,0.00006175611,0.000030982414,0.00006174271,0.00008057846,0.00040824804,0.000027271377,0.0000055613773],"category_scores_gemma":[0.00021970154,0.00004637591,0.000022622493,0.000114646864,0.000013755208,0.00013909389,0.00014574251,0.000058372603,0.000042721746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013857774,0.00006901194,0.03346958,0.000029131472,0.000007326955,0.000006349398,0.0015220647,0.000007055458,0.00018289193,0.2902309,0.11584221,0.5586321],"study_design_scores_gemma":[0.00009348673,0.00007137159,0.002793586,0.000022850116,0.0000014211021,0.000015428766,0.0000021158457,0.16037318,0.0045957603,0.8170413,0.014772054,0.00021747718],"about_ca_topic_score_codex":0.00008665673,"about_ca_topic_score_gemma":0.0000021444669,"teacher_disagreement_score":0.71270967,"about_ca_system_score_codex":0.000009095956,"about_ca_system_score_gemma":0.0000091258225,"threshold_uncertainty_score":0.18911546},"labels":[],"label_agreement":null},{"id":"W2171131535","doi":"10.1109/step.2005.30","title":"TETE: A Non-Invasive Unit Testing Framework for Source Transformation","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Unit testing; Computer science; Eclipse; Programming language; Transformation (genetics); Debugging; Model transformation; Software engineering; Simple (philosophy); Test-driven development; Test (biology); Program transformation; Grammar; Software development; Artificial intelligence; Software","score_opus":0.0467537272594929,"score_gpt":0.2946937454766724,"score_spread":0.24794001821717948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171131535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031123373,0.000013652362,0.9827884,0.0013145322,0.00005416547,0.00026291647,8.4478756e-7,0.009987074,0.0024660854],"genre_scores_gemma":[0.34199017,7.2443703e-7,0.6570028,0.00076725206,0.00008447943,0.00004401863,0.0000011278983,0.00000772345,0.00010172927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916637,0.00001502078,0.00019916674,0.00022187877,0.00014252457,0.0002550668],"domain_scores_gemma":[0.9975886,0.0017969294,0.00006756016,0.00033670795,0.0001456179,0.00006462545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029083082,0.00011673836,0.000108979366,0.000094822884,0.00018769517,0.00014148462,0.00048492255,0.00008160843,0.000003860008],"category_scores_gemma":[0.001284178,0.00010453738,0.00004951757,0.000386072,0.000019919566,0.00042665063,0.000047962836,0.000119439435,0.000027020415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049728687,0.00006325759,0.0017647872,0.000062003026,0.000010720756,0.0000011518232,0.0032142368,0.0008362695,0.00027033073,0.045653366,0.0072940527,0.94082487],"study_design_scores_gemma":[0.00032944878,0.00026854925,0.000603453,0.0002711419,0.00001030655,0.000041210846,0.000032016647,0.72524035,0.017071245,0.24888515,0.0068282797,0.00041881582],"about_ca_topic_score_codex":0.000033382035,"about_ca_topic_score_gemma":0.0000053353274,"teacher_disagreement_score":0.940406,"about_ca_system_score_codex":0.000026352245,"about_ca_system_score_gemma":0.000068913134,"threshold_uncertainty_score":0.42629105},"labels":[],"label_agreement":null},{"id":"W2171274571","doi":"10.1109/csmr.2005.10","title":"An XML-Based Framework for Language Neutral Program Representation and Generic Analysis","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Programming language; XML; Source code; Program comprehension; XML validation; XML framework; Document Structure Description; Efficient XML Interchange; Representation (politics); XML Schema Editor; Streaming XML; Program analysis; Static program analysis; Software development; Software; World Wide Web; Software system","score_opus":0.030951523715071736,"score_gpt":0.3701001120251534,"score_spread":0.33914858831008166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171274571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08214092,0.00004118875,0.9095,0.0006224886,0.0000199386,0.0001879016,8.7412434e-7,0.0074335854,0.00005309037],"genre_scores_gemma":[0.4459899,4.691204e-7,0.55345935,0.0004310895,0.000039665636,0.000055011256,0.000006505892,0.0000032841308,0.000014716296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993162,0.000030320354,0.00011078124,0.0003089826,0.000081063525,0.00015265364],"domain_scores_gemma":[0.99917376,0.000211153,0.000044970282,0.00046046477,0.000042738382,0.000066910034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016093263,0.00007603435,0.00010579325,0.00014259803,0.00007274475,0.00018997896,0.00024837334,0.000049230806,0.0000035432136],"category_scores_gemma":[0.00009190899,0.00006596388,0.00005887143,0.00062895747,0.000019659887,0.00020218424,0.000026160675,0.000046966208,0.0000010896717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007725362,0.00021391916,0.021748012,0.000011529447,0.000052608386,0.0000040338605,0.0007231425,0.002605881,0.00016285025,0.012159493,0.0016902547,0.9606205],"study_design_scores_gemma":[0.00009503563,0.00016706534,0.008547821,0.0000044650014,0.000043337383,0.0000021614983,0.000007192033,0.97497356,0.003782432,0.012126779,0.00012670686,0.000123426],"about_ca_topic_score_codex":0.00010105484,"about_ca_topic_score_gemma":0.000030507768,"teacher_disagreement_score":0.9723677,"about_ca_system_score_codex":0.000011452502,"about_ca_system_score_gemma":0.000014559861,"threshold_uncertainty_score":0.2689929},"labels":[],"label_agreement":null},{"id":"W2171494278","doi":"","title":"Software testing by active learning for commercial games","year":2005,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Computer science; Correctness; Video game; Context (archaeology); Software engineering; Software performance testing; Artificial intelligence; White-box testing; Software; Active learning (machine learning); Machine learning; Human–computer interaction; Software construction; Software system; Multimedia; Programming language","score_opus":0.16779529998615517,"score_gpt":0.36722164474622604,"score_spread":0.19942634476007087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171494278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014629374,0.000020456033,0.9905042,0.0019440001,0.0001419034,0.00024210646,0.000017422375,0.003142001,0.0025249417],"genre_scores_gemma":[0.7733667,0.0000028308086,0.22544648,0.00075152604,0.00019100559,0.000085426065,0.000016819284,0.000012460418,0.00012674308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981986,0.00007444854,0.00035199957,0.0005054307,0.00053920614,0.00033029445],"domain_scores_gemma":[0.99621195,0.0022247692,0.00018207487,0.00019298804,0.001096351,0.00009185479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054920255,0.0001975351,0.00017751707,0.00015614353,0.00041960992,0.0002746581,0.00074435456,0.000104854145,0.000038534996],"category_scores_gemma":[0.0063814204,0.00020445742,0.000079228994,0.00038840843,0.00009354356,0.00039473362,0.00010627808,0.00032857675,0.0000902721],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020273139,0.00009055308,0.0001461742,0.0000043072314,0.000006952087,3.965962e-7,0.00020694309,0.0012085706,0.0003215058,0.117777295,0.004473443,0.87574357],"study_design_scores_gemma":[0.000047469046,0.00035738107,0.00048915605,0.00009350755,0.000005122787,0.000004809984,0.00002556935,0.5101072,0.036864243,0.44774458,0.0038421573,0.00041875514],"about_ca_topic_score_codex":0.000030121491,"about_ca_topic_score_gemma":0.000011510942,"teacher_disagreement_score":0.87532485,"about_ca_system_score_codex":0.00013969191,"about_ca_system_score_gemma":0.00024974957,"threshold_uncertainty_score":0.83375317},"labels":[],"label_agreement":null},{"id":"W2174629870","doi":"","title":"Fault model-driven test derivation from finite state models: annotated bibliography","year":2001,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Test suite; Fault coverage; Fault model; Automaton; Stuck-at fault; Conformance testing; Finite-state machine; Fault (geology); Equivalence (formal languages); TRACE (psycholinguistics); Equivalence relation; Algorithm; Fault injection; Fault detection and isolation; Theoretical computer science; Test case; Programming language; Software; Mathematics; Discrete mathematics; Artificial intelligence; Standardization; Engineering","score_opus":0.029094367605719408,"score_gpt":0.2628401739598293,"score_spread":0.23374580635410988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174629870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036940843,0.000100894664,0.95761967,0.0006499912,0.0002593261,0.00019748839,0.000008378703,0.004199838,0.000023574385],"genre_scores_gemma":[0.51863426,0.00006447168,0.4803816,0.0008601605,0.000035627014,0.000010669933,0.0000039805177,0.000008857472,3.6520402e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970534,0.000059436115,0.0003997892,0.0011181118,0.00070517,0.00066411553],"domain_scores_gemma":[0.99690014,0.001356894,0.00016316939,0.0010853229,0.00033578888,0.0001586908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052819203,0.00030386823,0.0002593087,0.003580925,0.00029226416,0.0007429894,0.0023534617,0.00010071591,0.000001664846],"category_scores_gemma":[0.0003596458,0.0002789405,0.00007235144,0.01782674,0.00029365954,0.0017047636,0.0006575925,0.0003427606,0.000007950575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033051076,0.00006378464,0.011121063,0.0000026545597,0.0000025673044,0.00003675135,0.0006637115,0.82761467,0.00039540208,0.000028223725,0.00017055594,0.15989733],"study_design_scores_gemma":[0.00014763327,0.00007093228,0.0017320438,0.00006678249,0.0000015664491,0.000015814034,5.539014e-8,0.7019229,0.0012827697,0.29449588,0.000011414877,0.0002522458],"about_ca_topic_score_codex":0.00042485193,"about_ca_topic_score_gemma":0.000047267607,"teacher_disagreement_score":0.48169342,"about_ca_system_score_codex":0.00006124622,"about_ca_system_score_gemma":0.00015582412,"threshold_uncertainty_score":0.99996626},"labels":[],"label_agreement":null},{"id":"W2182335636","doi":"10.4018/978-1-60960-747-0.ch002","title":"Exceptions for Dependability","year":2011,"lang":"en","type":"book-chapter","venue":"Advances in computer and electrical engineering book series","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Correctness; Dependability; Mathematical proof; Computer science; Masking (illustration); Rollback; Programming language; Theoretical computer science; Software engineering; Database transaction; Mathematics","score_opus":0.011504289668309088,"score_gpt":0.22498159509788404,"score_spread":0.21347730542957497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182335636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030667302,0.0086085405,0.98359954,0.00004569633,0.00028411622,0.00026207702,0.0000046142136,0.0030145706,0.004177771],"genre_scores_gemma":[0.0017769288,0.0058929985,0.9820819,0.00024719536,0.0003484023,0.00013881421,0.000012064131,0.000077069664,0.009424628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986749,0.0000068935024,0.0003129296,0.00055637857,0.00012033707,0.0003285129],"domain_scores_gemma":[0.9989464,0.00043097453,0.00007239972,0.00040033783,0.000062812716,0.000087067776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014193585,0.00032445462,0.00039052774,0.00021511155,0.000075143835,0.000072421164,0.00042142448,0.00018908673,0.000004513669],"category_scores_gemma":[0.000059854647,0.0003266491,0.00009022954,0.00006935701,0.00006045661,0.00078995986,0.00018950705,0.00032782723,0.0000024614258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016385036,0.000024228937,0.00007249829,0.00019078837,0.000019767716,0.000016323573,0.00011911647,0.0006540918,0.0000025672891,0.6150424,0.0011708593,0.382671],"study_design_scores_gemma":[0.0001965128,0.000557547,0.00014346564,0.00026307342,0.000013447564,0.00009531684,4.708485e-8,0.05825265,0.000053984386,0.5422097,0.3975069,0.00070736016],"about_ca_topic_score_codex":0.0000036443957,"about_ca_topic_score_gemma":0.0000026042926,"teacher_disagreement_score":0.39633605,"about_ca_system_score_codex":0.000063836706,"about_ca_system_score_gemma":0.000039462677,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W2202321577","doi":"10.1007/978-3-642-28891-3_6","title":"Symbolic Execution of Communicating and Hierarchically Composed UML-RT State Machines","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Reachability; Unified Modeling Language; Modular design; Programming language; Reuse; Symbolic execution; Finite-state machine; State (computer science); Theoretical computer science; Software","score_opus":0.019748807224966396,"score_gpt":0.2626622974765419,"score_spread":0.24291349025157552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2202321577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011355917,0.0014302791,0.9942578,0.00034728,0.0003003055,0.0002716252,0.0000055018454,0.0013744081,0.00087719545],"genre_scores_gemma":[0.46215814,0.00009229292,0.5372976,0.0003292646,0.00007080294,0.0000043551645,0.0000036163879,0.000020455263,0.000023480792],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973336,0.00008647595,0.0005999771,0.0008086888,0.0006471841,0.0005241112],"domain_scores_gemma":[0.996262,0.001306864,0.00044483942,0.0015964421,0.00022302869,0.00016683782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001369277,0.00042518202,0.00058759854,0.00065960735,0.00025496536,0.00023015555,0.0027403599,0.00020157734,0.0000027055307],"category_scores_gemma":[0.00022864284,0.0003840715,0.00008111468,0.0004177474,0.0010848548,0.0003715927,0.0022617136,0.00082576746,0.000003377998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004395983,0.000030065949,0.001278615,0.00006981,0.000007988121,0.0000074095656,0.0012944019,0.00049072277,0.00035784804,0.006688568,0.000014539601,0.98975563],"study_design_scores_gemma":[0.00021090059,0.00019260978,0.0024648572,0.0009777445,0.0000101142705,0.00012908677,3.541499e-8,0.4096173,0.0011109086,0.5845227,0.00016552594,0.0005981974],"about_ca_topic_score_codex":0.0001422231,"about_ca_topic_score_gemma":0.000023406925,"teacher_disagreement_score":0.98915744,"about_ca_system_score_codex":0.00009455926,"about_ca_system_score_gemma":0.00022597893,"threshold_uncertainty_score":0.9998611},"labels":[],"label_agreement":null},{"id":"W2205665593","doi":"","title":"The case for system testing with swift hierarchical VM fork","year":2014,"lang":"en","type":"article","venue":"IEEE International Conference on Cloud Computing Technology and Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Fork (system call); Computer science; Test suite; Cloud computing; Operating system; Unit testing; Virtual machine; Software performance testing; White-box testing; Suite; Embedded system; Software; Test case; Software system; Software construction","score_opus":0.04916953759013115,"score_gpt":0.3087123122288789,"score_spread":0.25954277463874775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2205665593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15049198,0.000009383091,0.83967334,0.0035411308,0.00078585546,0.00018393762,0.0000013457884,0.0035891137,0.0017239103],"genre_scores_gemma":[0.8309649,7.0363245e-7,0.16875191,0.00013331322,0.00009891375,0.000024453564,1.9221503e-7,0.0000062063086,0.000019409352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983164,0.000042659074,0.00025426672,0.00065174163,0.00031609143,0.0004188482],"domain_scores_gemma":[0.9968282,0.00174321,0.00018816124,0.0005486397,0.00061014004,0.00008167242],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017312544,0.00017207798,0.00015704642,0.0003442949,0.0015988008,0.00052831083,0.0020814813,0.00009087583,1.6204669e-7],"category_scores_gemma":[0.0015340331,0.000116097915,0.000024096682,0.0008486801,0.0010781512,0.00013690334,0.0003710203,0.00032544555,0.000002847291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008957142,0.000011784677,0.0010599048,0.0000065642257,0.0000053422655,0.00003460089,0.000048152197,0.00005496609,0.00014042786,0.8768552,0.000085601336,0.12168852],"study_design_scores_gemma":[0.00020344427,0.00042610426,0.00015938234,0.00021196075,0.0000031258512,0.00238906,0.000028489492,0.8025137,0.0009231604,0.19275598,0.0002138499,0.00017169218],"about_ca_topic_score_codex":0.0000228189,"about_ca_topic_score_gemma":0.000008578262,"teacher_disagreement_score":0.80245876,"about_ca_system_score_codex":0.00006273786,"about_ca_system_score_gemma":0.00017783267,"threshold_uncertainty_score":0.99970096},"labels":[],"label_agreement":null},{"id":"W2243603742","doi":"10.1109/ase.2015.23","title":"Synthesizing Web Element Locators (T)","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Mitacs; Intel Corporation","keywords":"JavaScript; Computer science; Document Object Model; Web application; Element (criminal law); Code (set theory); Web service; Web page; World Wide Web; Programming language; Set (abstract data type)","score_opus":0.04862106141560102,"score_gpt":0.26953980481618445,"score_spread":0.22091874340058343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2243603742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026419396,0.00007982533,0.95579004,0.00077984075,0.00018539252,0.00006207387,1.4206621e-7,0.016638767,0.023822006],"genre_scores_gemma":[0.60344034,9.0456734e-7,0.39588988,0.00041588323,0.000025527424,0.0000074347736,1.46831e-7,0.0000036714446,0.0002162312],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993031,0.000026065967,0.0001093524,0.00019142362,0.00019854681,0.00017149284],"domain_scores_gemma":[0.9992784,0.00010294882,0.00002925623,0.0004148075,0.00006071914,0.000113819144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045139785,0.00007236783,0.00007219441,0.0000692118,0.000038204107,0.00008797977,0.00051667844,0.000024210376,0.0000065743357],"category_scores_gemma":[0.00026401348,0.00005922019,0.000021263362,0.00020635541,0.000014527806,0.00015902477,0.00019154212,0.00004744578,0.00012770118],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023242546,0.000089616886,0.016888384,0.000010090205,0.000013600436,0.00003351438,0.00047928875,0.000043613385,0.000103480954,0.084988125,0.7415619,0.15578605],"study_design_scores_gemma":[0.0007033655,0.00049891084,0.00094510714,0.00015514538,0.00001321588,0.00014358346,0.00007817057,0.4907629,0.02391616,0.32362708,0.15798068,0.0011757013],"about_ca_topic_score_codex":0.00006243764,"about_ca_topic_score_gemma":0.0000026976393,"teacher_disagreement_score":0.60079837,"about_ca_system_score_codex":0.000046813042,"about_ca_system_score_gemma":0.00009652717,"threshold_uncertainty_score":0.24149293},"labels":[],"label_agreement":null},{"id":"W2246639849","doi":"10.1109/ase.2015.26","title":"Generating Fixtures for JavaScript Unit Testing (T)","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"JavaScript; Unobtrusive JavaScript; Computer science; Document Object Model; Unit testing; Test fixture; Fixture; Test case; Programming language; Web application; Rich Internet application; Operating system; Web page; Machine learning; World Wide Web; Software","score_opus":0.1726648636456591,"score_gpt":0.31919885295152883,"score_spread":0.14653398930586972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246639849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032303922,0.00008763893,0.97859174,0.00030385173,0.00021983928,0.00012665623,5.7118814e-7,0.013227521,0.0042118123],"genre_scores_gemma":[0.10667122,1.3338956e-7,0.89168084,0.0009672087,0.0001370508,0.00003348571,0.0000013668838,0.000009188489,0.0004994813],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918926,0.000026609876,0.00015179993,0.00025082403,0.00015129968,0.00023021422],"domain_scores_gemma":[0.998694,0.0004877315,0.00005313567,0.00037057677,0.00028707803,0.00010748761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056181656,0.00010020854,0.00009956494,0.00006305955,0.00012610602,0.0002001341,0.0005203703,0.000041555068,0.0000010500554],"category_scores_gemma":[0.0029920253,0.00008408079,0.000029459678,0.0002635354,0.00001596809,0.00021333559,0.0001632382,0.00006291367,0.000008541428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033973565,0.00005356583,0.012736109,0.000026250453,0.000013493657,0.000011391787,0.0007993402,0.0009345707,0.0011483644,0.028683512,0.57659215,0.37899783],"study_design_scores_gemma":[0.00023571785,0.00018200546,0.000117394964,0.000028806073,0.0000034737466,0.000038803835,0.000009938833,0.88398826,0.0029329387,0.1053621,0.0068749874,0.00022554696],"about_ca_topic_score_codex":0.00012802784,"about_ca_topic_score_gemma":0.00000413567,"teacher_disagreement_score":0.8830537,"about_ca_system_score_codex":0.000019196255,"about_ca_system_score_gemma":0.00010059377,"threshold_uncertainty_score":0.35819498},"labels":[],"label_agreement":null},{"id":"W2247591691","doi":"10.1109/ase.2015.102","title":"GRT: An Automated Test Generator Using Orchestrated Program Analysis","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generator (circuit theory); Computer science; Test (biology); Automatic test equipment; Engineering; Reliability engineering; Power (physics)","score_opus":0.1083915520828959,"score_gpt":0.37862138673583295,"score_spread":0.27022983465293704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247591691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23168315,0.000024668654,0.6321306,0.00009786826,0.00007904178,0.00019866944,0.0000016787596,0.13520254,0.00058175856],"genre_scores_gemma":[0.45785376,1.5670936e-7,0.5419543,0.00011392652,0.000024872294,0.000011027608,0.0000070078536,0.0000070272145,0.000027931648],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870044,0.00008259298,0.00023229701,0.0004226068,0.00026919093,0.00029284882],"domain_scores_gemma":[0.9984914,0.00008939942,0.00008412282,0.00073906983,0.00031427073,0.0002817372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048357612,0.00015586884,0.00020149158,0.0002768009,0.00009267444,0.00031791333,0.00065741007,0.000082074395,0.0000041378808],"category_scores_gemma":[0.00035695444,0.00013089634,0.0000582831,0.0026947756,0.00003859926,0.00045076123,0.00013124081,0.00008446327,0.00001325829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015799824,0.0041961363,0.7474844,0.000041741812,0.00085614517,0.00046336235,0.0025382338,0.01719894,0.0074797086,0.0056691905,0.078151524,0.13590485],"study_design_scores_gemma":[0.000095115836,0.00022730484,0.002891234,0.0000048244624,0.000052308977,0.000021743412,0.000003994169,0.9931416,0.001711415,0.0015551801,0.00009175891,0.00020352728],"about_ca_topic_score_codex":0.00061585614,"about_ca_topic_score_gemma":0.000026642638,"teacher_disagreement_score":0.9759427,"about_ca_system_score_codex":0.00006503815,"about_ca_system_score_gemma":0.0002206986,"threshold_uncertainty_score":0.5337798},"labels":[],"label_agreement":null},{"id":"W2271850540","doi":"10.1145/2789209","title":"Test Case Prioritization Using Extended Digraphs","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regression testing; Test case; Test suite; Digraph; Model-based testing; Machine learning; Prioritization; Data mining; Test (biology); Hidden Markov model; Fault detection and isolation; Artificial intelligence; Reliability engineering; Software; Regression analysis; Software development","score_opus":0.15832191192600087,"score_gpt":0.3445707515609084,"score_spread":0.18624883963490751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271850540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01071556,0.00020699885,0.98207814,0.00007110158,0.00045176258,0.000098269535,0.0000044798085,0.006370334,0.000003349034],"genre_scores_gemma":[0.18744797,0.000014091406,0.81238496,0.00007509612,0.000025845966,0.000016937898,9.2142284e-7,0.00001795322,0.000016250517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893683,0.0001308564,0.00019575054,0.00036286475,0.00011901479,0.0002547112],"domain_scores_gemma":[0.9963054,0.0027879884,0.00004630916,0.00057909393,0.00010629598,0.00017489932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076398224,0.00017821371,0.00021421656,0.00030616767,0.00013677994,0.00005865407,0.00026926686,0.00013354626,0.0000012950677],"category_scores_gemma":[0.0044877157,0.00018280285,0.000048302074,0.00043939424,0.000037851754,0.00020964176,0.000023769377,0.00023519326,0.0000017653983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003353971,0.00033727312,0.002589054,0.00014688638,0.00011482696,0.0014484108,0.0035078977,0.053712863,0.0012936757,0.0021610924,0.0003763495,0.93427813],"study_design_scores_gemma":[0.00289408,0.0022091265,0.0020484044,0.00043547497,0.0002654431,0.057590727,0.00017156136,0.82499737,0.016171195,0.08820202,0.0025033401,0.0025112594],"about_ca_topic_score_codex":0.00009683441,"about_ca_topic_score_gemma":0.0000023124078,"teacher_disagreement_score":0.93176687,"about_ca_system_score_codex":0.000045255398,"about_ca_system_score_gemma":0.000055512326,"threshold_uncertainty_score":0.74544835},"labels":[],"label_agreement":null},{"id":"W2277501150","doi":"10.1109/issrew.2015.7392048","title":"Getting more in less: The power of single/error annotations in category partition","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Pairwise comparison; Partition (number theory); Computer science; Basis (linear algebra); Process (computing); Function (biology); Algorithm; Data mining; Theoretical computer science; Mathematics; Artificial intelligence; Programming language","score_opus":0.08382940141853011,"score_gpt":0.3080654015788923,"score_spread":0.22423600016036216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277501150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69154537,0.00011302372,0.29665878,0.004678967,0.0001288298,0.00019027512,6.726971e-7,0.0021898176,0.004494261],"genre_scores_gemma":[0.94716984,2.7638336e-7,0.052490253,0.0002911629,0.0000059972035,0.000014855439,8.0952344e-7,0.0000032699509,0.000023525705],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993604,0.000060426104,0.00018884595,0.00013227835,0.00013508437,0.00012299074],"domain_scores_gemma":[0.99937975,0.00019249672,0.000059151458,0.0002693676,0.00007537618,0.000023871258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005563375,0.00005367859,0.00007526914,0.000113036556,0.000021892207,0.000029974168,0.0002901247,0.000029047309,0.0000012031845],"category_scores_gemma":[0.00045877713,0.00003890932,0.000014980316,0.0004346945,0.000039994316,0.00020008454,0.000082752646,0.00007724457,0.0000026109233],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029418085,0.0015913228,0.5634634,0.00007843553,0.000018601397,0.00011539675,0.14370757,0.010599002,0.004038332,0.09886642,0.08239063,0.09510145],"study_design_scores_gemma":[0.0011876154,0.00043922,0.20903693,0.0004207583,0.00000689066,0.00005202983,0.0044036703,0.28401938,0.0116986325,0.48754615,0.00047918537,0.0007095385],"about_ca_topic_score_codex":0.0006970328,"about_ca_topic_score_gemma":0.00016478024,"teacher_disagreement_score":0.38867974,"about_ca_system_score_codex":0.000036528298,"about_ca_system_score_gemma":0.00005547105,"threshold_uncertainty_score":0.1586676},"labels":[],"label_agreement":null},{"id":"W2279957488","doi":"10.1109/issrew.2015.7392039","title":"An analysis and extension of Category partition testing for constrained systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Software testing; Software performance testing; System testing; Integration testing; White-box testing; Test strategy; Non-regression testing; Extension (predicate logic); Model-based testing; Software reliability testing; Task (project management); Keyword-driven testing; Partition (number theory); System integration testing; Software; Software system; Software engineering; Test case; Programming language; Machine learning; Software construction; Mathematics; Engineering; Systems engineering","score_opus":0.07935491540892278,"score_gpt":0.30696917360457493,"score_spread":0.22761425819565215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279957488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06506126,0.000040571478,0.9324628,0.000028358822,0.000037378486,0.00009913883,0.0000012773045,0.0020984733,0.00017073196],"genre_scores_gemma":[0.67035824,1.6308844e-7,0.32959425,0.000018373505,0.00000931846,0.000009033971,0.00000238829,0.0000018934423,0.0000063124958],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942815,0.000035738634,0.00015439127,0.00019382825,0.00009630738,0.00009158095],"domain_scores_gemma":[0.9989492,0.0002994078,0.000082556166,0.0002743712,0.00031782623,0.00007662114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006411506,0.000054812906,0.00013944994,0.00012814032,0.00003683428,0.00005749203,0.00012376146,0.000029591325,1.9239178e-7],"category_scores_gemma":[0.0005293742,0.0000454475,0.000020285044,0.00035291386,0.000034441124,0.00016852868,0.000029993931,0.000019364721,2.2691697e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004516106,0.0004484513,0.66517425,0.00034071846,0.0002822603,0.000021253969,0.0026304126,0.008078039,0.019487707,0.12766568,0.009420989,0.16640507],"study_design_scores_gemma":[0.00012005377,0.00027844144,0.005455235,0.000017400549,0.00004010224,0.000012719647,0.00003170856,0.97733504,0.0010587751,0.015567675,0.000005910943,0.00007694889],"about_ca_topic_score_codex":0.00060949865,"about_ca_topic_score_gemma":0.000006306885,"teacher_disagreement_score":0.969257,"about_ca_system_score_codex":0.000009479036,"about_ca_system_score_gemma":0.00003758989,"threshold_uncertainty_score":0.18532953},"labels":[],"label_agreement":null},{"id":"W2284923418","doi":"10.1007/978-3-642-38171-3_29","title":"Constraint-Based Fitness Function for Search-Based Software Testing","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Arity; Computer science; Fitness function; Software; Statement (logic); Constraint (computer-aided design); Function (biology); Theoretical computer science; Programming language; Machine learning; Mathematics","score_opus":0.044692900339624184,"score_gpt":0.26765899978498825,"score_spread":0.22296609944536405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284923418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032907865,0.00011295186,0.99102885,0.00051355315,0.0011191749,0.0009598145,0.000014824428,0.005887329,0.00033058794],"genre_scores_gemma":[0.069128014,5.3069556e-7,0.9280446,0.0022882444,0.0002996598,0.000081981896,0.000017182136,0.000057529196,0.00008221576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957154,0.000047818554,0.0005705634,0.0017889057,0.0009633266,0.0009139967],"domain_scores_gemma":[0.99190307,0.004974201,0.00032923592,0.001548087,0.001016104,0.0002293226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013967514,0.00064436905,0.00056769716,0.0009989042,0.00050255615,0.00086607574,0.002778652,0.00042352526,0.000021013679],"category_scores_gemma":[0.0015893677,0.00060709985,0.00018204491,0.0007711508,0.0010573408,0.00043150742,0.00051721407,0.0007757376,0.000031786636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007635892,0.000030423522,0.00032918295,0.0001422527,0.00000613777,0.000018494573,0.000048841666,0.05049022,0.00004932821,0.0021426692,0.0002539246,0.9464809],"study_design_scores_gemma":[0.00033902706,0.00043458742,0.00012919323,0.0008917985,0.0000104011615,0.000020762824,2.5238316e-8,0.77181715,0.0010064133,0.22441003,0.0002879152,0.0006527171],"about_ca_topic_score_codex":0.000064647946,"about_ca_topic_score_gemma":0.000009687006,"teacher_disagreement_score":0.9458282,"about_ca_system_score_codex":0.00032870282,"about_ca_system_score_gemma":0.0017424583,"threshold_uncertainty_score":0.999638},"labels":[],"label_agreement":null},{"id":"W2294018077","doi":"10.1109/hase.2016.45","title":"An Extension of Category Partition Testing for Highly Constrained Systems","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Extension (predicate logic); Partition (number theory); White-box testing; Set (abstract data type); Base (topology); Black-box testing; Mathematical optimization; Software; Theoretical computer science; Algorithm; Programming language; Mathematics; Software system; Software construction","score_opus":0.0531951948667412,"score_gpt":0.284574951903722,"score_spread":0.2313797570369808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294018077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019223832,0.000018472601,0.97429925,0.00015252327,0.00014208989,0.00016814421,0.000002726042,0.0056485655,0.00034437596],"genre_scores_gemma":[0.71552074,3.2577555e-7,0.284357,0.000033291508,0.000026942664,0.000023016979,7.4341904e-7,0.00000438739,0.00003355082],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992783,0.00003548263,0.00020209196,0.00023169385,0.00010495106,0.00014748734],"domain_scores_gemma":[0.9983722,0.0007921344,0.00010720787,0.00039913016,0.000278501,0.000050826267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004449687,0.00007154457,0.00011549263,0.000063330306,0.000055611064,0.000035869492,0.0002531958,0.000040318228,9.804334e-7],"category_scores_gemma":[0.0006107307,0.00004511307,0.000023292798,0.00012092288,0.000045335262,0.0002618002,0.00003233975,0.000017353184,0.0000025652107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017860993,0.00019056545,0.012106965,0.00015422433,0.000013846571,0.000008401616,0.00018134229,0.00006518297,0.39043272,0.27128193,0.015759777,0.30978718],"study_design_scores_gemma":[0.0014594165,0.0030652557,0.00936016,0.0011641431,0.000024251432,0.00016496824,0.000027074464,0.5232814,0.14360845,0.3166199,0.00042763088,0.00079735275],"about_ca_topic_score_codex":0.0001158752,"about_ca_topic_score_gemma":0.0000010033579,"teacher_disagreement_score":0.69629693,"about_ca_system_score_codex":0.000014998996,"about_ca_system_score_gemma":0.000047631987,"threshold_uncertainty_score":0.18396576},"labels":[],"label_agreement":null},{"id":"W2296668858","doi":"10.1007/978-3-319-25945-1_2","title":"Using Multiple Adaptive Distinguishing Sequences for Checking Sequence Generation","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sequence (biology); Identification (biology); State (computer science); Computer science; Construct (python library); Model checking; Finite-state machine; Algorithm; Programming language","score_opus":0.2198040413080693,"score_gpt":0.3446613266231766,"score_spread":0.12485728531510731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296668858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012984693,0.0004492459,0.99466527,0.00012807861,0.0015426173,0.00058656617,0.000013550023,0.0021460708,0.00033874935],"genre_scores_gemma":[0.28509295,0.0000036960978,0.71382356,0.00025437685,0.0007358387,0.000017380227,0.00000829316,0.000032002306,0.000031884076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961099,0.00004522284,0.0005581391,0.0016554634,0.00093243486,0.00069886405],"domain_scores_gemma":[0.9962951,0.0011128514,0.0005082884,0.0010439383,0.0008612079,0.00017860207],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020396588,0.00054515287,0.000528638,0.0005882852,0.0005247388,0.000869039,0.0025763237,0.00031947833,0.0000013817602],"category_scores_gemma":[0.001929168,0.0005239097,0.00012294948,0.0005145759,0.0005402301,0.00088177575,0.00092370354,0.00056827633,0.000002944984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000091626725,0.000023728118,0.0003417025,0.000063501524,0.000016028616,0.000078013865,0.0017289516,0.124416724,0.0016290515,0.013652663,0.0001599408,0.85788053],"study_design_scores_gemma":[0.00011229932,0.0001118615,0.00000389967,0.00046050266,0.000006923251,0.0000638516,9.0313804e-8,0.7139368,0.0010812198,0.28361455,0.00013844244,0.0004695397],"about_ca_topic_score_codex":0.00019649944,"about_ca_topic_score_gemma":0.00007845159,"teacher_disagreement_score":0.85741097,"about_ca_system_score_codex":0.00083166634,"about_ca_system_score_gemma":0.0011183805,"threshold_uncertainty_score":0.9997212},"labels":[],"label_agreement":null},{"id":"W2300062158","doi":"10.11575/prism/30915","title":"An Exploratory Study of Automated GUI Testing: Goals, Issues, and Best Practices","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Test suite; Suite; Computer science; Graphical user interface testing; Software engineering; Keyword-driven testing; Best practice; Test (biology); Test strategy; Graphical user interface; Human–computer interaction; Test case; Programming language; User experience design; Machine learning; Software; Software development; Software construction","score_opus":0.15756735840381086,"score_gpt":0.4042491749741715,"score_spread":0.24668181657036065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300062158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932477,0.00006824637,0.0033400054,0.00010825236,0.00006635633,0.00038489135,0.0000011265988,0.0008039099,0.0019795494],"genre_scores_gemma":[0.65970075,9.1265014e-7,0.34019074,0.000017945331,0.000019352163,0.000012452446,7.1869164e-7,0.00000676205,0.000050367733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875003,0.00024504238,0.0002401975,0.00042554724,0.00019204842,0.00014715652],"domain_scores_gemma":[0.9980495,0.0005117477,0.00040242076,0.0007883464,0.00016294155,0.00008506729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012563409,0.000119283366,0.00020151191,0.00007537654,0.00011666685,0.0004474427,0.0012087931,0.000042816857,0.000008183913],"category_scores_gemma":[0.0018448352,0.00010731402,0.0000075535904,0.0002977224,0.00004014059,0.0009915566,0.0005542405,0.00008183496,0.000023160841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019271774,0.0033086932,0.117572464,0.000030125919,0.000040516203,0.000045946184,0.017895032,0.000051548574,0.0030285208,0.0001064826,0.007656227,0.8502452],"study_design_scores_gemma":[0.0033421589,0.022495592,0.036744267,0.00079710165,0.00016804316,0.00019193467,0.003164859,0.8694422,0.018872404,0.006893744,0.035902023,0.0019856363],"about_ca_topic_score_codex":0.00083533226,"about_ca_topic_score_gemma":0.00008994684,"teacher_disagreement_score":0.86939067,"about_ca_system_score_codex":0.000008119964,"about_ca_system_score_gemma":0.000056921697,"threshold_uncertainty_score":0.43761387},"labels":[],"label_agreement":null},{"id":"W2316535507","doi":"10.2316/p.2010.676-055","title":"Is Iterative Deepening Search a Complete and Optimal Algorithm for Java PathFinder?","year":2010,"lang":"en","type":"article","venue":"Parallel and Distributed Computing and Networks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pathfinder; Computer science; Java; Algorithm; Iterative method; Parallel computing; Operating system; World Wide Web","score_opus":0.024177024768679133,"score_gpt":0.2810436833405228,"score_spread":0.2568666585718437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316535507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049939934,0.0005913546,0.9477091,0.00029626847,0.00011682178,0.00020433411,0.000033367585,0.0010881311,0.000020723142],"genre_scores_gemma":[0.5734983,0.000024177905,0.4261276,0.00018890719,0.00010516197,0.0000092321125,0.000032281914,0.000007986165,0.0000063109355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855584,0.00005330287,0.00023389867,0.00057435513,0.00012495325,0.00045767947],"domain_scores_gemma":[0.9985671,0.0007914157,0.00008493703,0.00023438984,0.000120284625,0.0002018537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005132113,0.0002265773,0.00027626223,0.00005788328,0.0006581091,0.00049603643,0.00023798122,0.00013727983,0.0000010853194],"category_scores_gemma":[0.000056012395,0.00020689677,0.00004192225,0.00017235025,0.0001437136,0.0001330051,0.00042051208,0.00038729183,4.394646e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035035508,0.0000723333,0.009849011,0.000052953208,0.00007638052,0.000028586132,0.002291855,0.0024942812,0.000058236965,0.004834369,0.0058412547,0.9743657],"study_design_scores_gemma":[0.00058555586,0.00014965006,0.00407693,0.000059413458,0.0000107809,0.00014200919,0.000018754194,0.9891248,0.000014048843,0.005192135,0.00035809365,0.00026782556],"about_ca_topic_score_codex":0.00004624312,"about_ca_topic_score_gemma":0.000001881256,"teacher_disagreement_score":0.9866305,"about_ca_system_score_codex":0.0000069029966,"about_ca_system_score_gemma":0.000022034843,"threshold_uncertainty_score":0.8437006},"labels":[],"label_agreement":null},{"id":"W2338921896","doi":"10.1109/tse.2016.2550441","title":"Test Case Prioritization Using Lexicographical Ordering","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Lexicographical order; Computer science; Prioritization; Test case; Heuristic; Fault detection and isolation; Data mining; Fault (geology); Greedy algorithm; Reliability engineering; Algorithm; Machine learning; Artificial intelligence; Mathematics","score_opus":0.019273459654922546,"score_gpt":0.24197271955170754,"score_spread":0.222699259896785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338921896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018500047,0.000024818211,0.96633416,0.000046167726,0.0005136677,0.00011671352,0.000007909,0.014452951,0.0000035522803],"genre_scores_gemma":[0.60701513,0.0000062924605,0.3928621,0.000025657077,0.000033790653,0.00001789551,1.2734827e-7,0.000025639352,0.000013317511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879205,0.000018473218,0.00024205967,0.00039764063,0.00021204702,0.00033771186],"domain_scores_gemma":[0.998401,0.00085035065,0.0000450084,0.0004894144,0.00008656037,0.00012767561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016254083,0.00021808156,0.00015901873,0.00036877795,0.00021173108,0.00009784812,0.00028294526,0.00011145231,0.000008113502],"category_scores_gemma":[0.00023002432,0.00018770038,0.00009472026,0.0006898784,0.00002898266,0.00047199894,0.000005465999,0.00018784057,0.000010234169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021278427,0.00071272196,0.005199355,0.00025710734,0.00015742872,0.0032247526,0.00074743584,0.17088322,0.030534383,0.0012446897,0.0004944878,0.7865231],"study_design_scores_gemma":[0.0013789337,0.0004942214,0.00057632534,0.0015723244,0.000072134775,0.010808501,0.000006633864,0.89081824,0.09013486,0.001591827,0.0006207446,0.0019252474],"about_ca_topic_score_codex":0.000028650204,"about_ca_topic_score_gemma":0.0000027582341,"teacher_disagreement_score":0.7845979,"about_ca_system_score_codex":0.00010765193,"about_ca_system_score_gemma":0.00003971222,"threshold_uncertainty_score":0.7654199},"labels":[],"label_agreement":null},{"id":"W2339904014","doi":"10.1109/tse.2015.2487958","title":"Black-Box String Test Case Generation through a Multi-Objective Optimization","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; String (physics); Random testing; Algorithm; Test case; Test (biology); Test functions for optimization; String searching algorithm; Optimization problem; Mathematics; Machine learning; Programming language; Data structure","score_opus":0.04811254978416045,"score_gpt":0.26542024025866834,"score_spread":0.21730769047450788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339904014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027636876,0.000042203043,0.9840673,0.000026532172,0.0007053272,0.00022773117,0.000011442869,0.012146566,0.000009198238],"genre_scores_gemma":[0.43853045,0.0000049377613,0.5612647,0.000040078245,0.000056884262,0.00004543451,0.0000020539023,0.00002643044,0.000029058368],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986895,0.000032753116,0.00026536235,0.00045551523,0.00025734637,0.00029957684],"domain_scores_gemma":[0.9987298,0.00034767817,0.00006687228,0.0005027488,0.00020951593,0.0001433804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021838259,0.0002563001,0.00018294873,0.00022315276,0.00018400104,0.00017185116,0.00026723213,0.00012393433,0.0000034683728],"category_scores_gemma":[0.00035014094,0.00028064253,0.00007762456,0.0006292525,0.000024582321,0.0008005912,0.000006314716,0.00030124254,0.00001701103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018691752,0.000094859715,0.00003558516,0.000011102399,0.000014984043,0.0001345162,0.0011685713,0.9941374,0.00008376681,0.000033138742,0.0002672359,0.0040169437],"study_design_scores_gemma":[0.00040074054,0.00014083023,0.000007511355,0.00006437729,0.000015940568,0.0005409279,0.000019022693,0.9832106,0.015189109,0.000047492536,0.00004100749,0.0003224051],"about_ca_topic_score_codex":0.0001126115,"about_ca_topic_score_gemma":0.000010465583,"teacher_disagreement_score":0.43576676,"about_ca_system_score_codex":0.0002429898,"about_ca_system_score_gemma":0.00008270187,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W2343554492","doi":"","title":"Formal Approaches to Software Testing: Third International Workshop on Formal Approaches to Testing of Software: Fates 2003: Montreal, Quebec, Canada, October 6th, 2003: Revised Papers (LECTURE NOTES IN COMPUTER SCIENCE)","year":2004,"lang":"en","type":"book","venue":"Springer eBooks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software testing; Software engineering; Computer science; Formal methods; Library science; Software; Programming language","score_opus":0.0779619741570228,"score_gpt":0.23216008431352803,"score_spread":0.15419811015650522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343554492","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001217839,0.00022569664,0.9643543,0.0005150206,0.0012592244,0.0025648188,0.00006036037,0.00451186,0.025290921],"genre_scores_gemma":[0.029071389,0.0000015529511,0.9603808,0.0015695877,0.0005702492,0.00026229926,0.000042966967,0.00016259786,0.007938578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930499,0.00008021012,0.0012773541,0.0020150149,0.0018551336,0.0017223514],"domain_scores_gemma":[0.9946912,0.0014263641,0.00072104856,0.0016321938,0.0009469028,0.00058230077],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013999721,0.0011513404,0.0011319227,0.0013486618,0.00048332167,0.0006125326,0.0036933292,0.00050211255,0.0000049090677],"category_scores_gemma":[0.007006769,0.0010976333,0.00015348554,0.0017157492,0.00037033926,0.0005265602,0.0021347401,0.0012568914,0.000008583297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008113242,0.00015645889,0.004763694,0.00041775402,0.00010110156,0.00013371959,0.0026187198,0.051559363,0.000025665537,0.0014706259,0.0052038585,0.9334679],"study_design_scores_gemma":[0.016094754,0.007830767,0.13117194,0.14053625,0.0011429987,0.0013919519,0.00018300889,0.40392745,0.030327046,0.14939438,0.07233974,0.0456597],"about_ca_topic_score_codex":0.07088228,"about_ca_topic_score_gemma":0.109140344,"teacher_disagreement_score":0.8878082,"about_ca_system_score_codex":0.0027446032,"about_ca_system_score_gemma":0.01132961,"threshold_uncertainty_score":0.99914736},"labels":[],"label_agreement":null},{"id":"W2363564475","doi":"","title":"Designing and implementing crawler-based Web test generation system","year":2014,"lang":"en","type":"article","venue":"Journal of Suzhou University of Science and Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Web crawler; Test (biology); Web testing; Automation; Web application; Test Management Approach; Computer science; Test harness; Test case; Software engineering; World Wide Web; Engineering; Web page; Web development; Web application security; Operating system; Machine learning; Software","score_opus":0.01438619461874731,"score_gpt":0.21097078333201505,"score_spread":0.19658458871326773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363564475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4786655,0.00005925227,0.51978356,0.000909631,0.000046465604,0.000034506615,3.0022213e-7,0.00038453547,0.00011624066],"genre_scores_gemma":[0.77607,0.0000075455823,0.22389361,0.000015196477,0.000009698636,2.7895249e-8,2.757153e-8,0.0000011923172,0.0000027037522],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993292,0.000017851055,0.00013783431,0.00014819276,0.00021552798,0.000151365],"domain_scores_gemma":[0.9989298,0.00013682464,0.00028309238,0.00013801637,0.00046145095,0.00005078904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015515365,0.000054788085,0.00013481984,0.0006882698,0.00037238243,0.000045629167,0.00051337056,0.000048212136,3.793986e-7],"category_scores_gemma":[0.00041130313,0.000052917894,0.0000143097795,0.00070887926,0.00063432084,0.00040145742,0.00019424286,0.000098429475,1.9399651e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000082080805,0.000086943386,0.15595655,0.00010910577,0.000015892314,0.00006762058,0.0006551459,0.000033968372,0.5923539,0.031390462,0.0018140281,0.21750817],"study_design_scores_gemma":[0.0021648423,0.0027215905,0.0063067186,0.0007437002,0.000070984024,0.0010913175,0.0018978096,0.75056005,0.22171141,0.0094091045,0.0028017,0.0005208023],"about_ca_topic_score_codex":0.000013862852,"about_ca_topic_score_gemma":0.0000037455914,"teacher_disagreement_score":0.7505261,"about_ca_system_score_codex":0.000041285293,"about_ca_system_score_gemma":0.00017912769,"threshold_uncertainty_score":0.2864102},"labels":[],"label_agreement":null},{"id":"W2368534069","doi":"","title":"Functional Test Platform Research Based on Model Driven Technology","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Test (biology)","score_opus":0.06005169548088268,"score_gpt":0.3248242107119926,"score_spread":0.2647725152311099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2368534069","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000164129,0.000018832437,0.98292917,0.00740924,0.000008680085,0.00043239153,0.0000043463856,0.007490188,0.0015429943],"genre_scores_gemma":[0.24208191,0.0000013846177,0.756134,0.0012926698,0.000071227696,0.000297205,0.000011121033,0.000008955339,0.00010152119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985284,0.000015888258,0.00020412827,0.00057572447,0.00030422924,0.00037163068],"domain_scores_gemma":[0.9982935,0.0003914309,0.000051617175,0.00091282476,0.0002672843,0.000083308056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028981332,0.00014819663,0.00012473922,0.0006583575,0.00044036098,0.00014364884,0.0011917796,0.00013090229,0.0000029736373],"category_scores_gemma":[0.000011783312,0.00014612921,0.000051651954,0.0013055439,0.00010722166,0.00013008811,0.00018090877,0.00039891573,0.0001810288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048577476,0.00087882805,0.0005428094,0.000008936683,0.0000057209722,0.0000045896654,0.00007957551,0.0149335535,0.0046259505,0.15653813,0.17877282,0.6436042],"study_design_scores_gemma":[0.00015339693,0.00014859499,0.00059809326,0.000026395532,0.0000015030231,0.000013893839,5.835179e-7,0.7174577,0.0021815703,0.26398036,0.01528336,0.00015452207],"about_ca_topic_score_codex":0.000002667549,"about_ca_topic_score_gemma":4.904923e-7,"teacher_disagreement_score":0.7025242,"about_ca_system_score_codex":0.00010579663,"about_ca_system_score_gemma":0.0001380647,"threshold_uncertainty_score":0.5958976},"labels":[],"label_agreement":null},{"id":"W2371137413","doi":"","title":"A Designing Method for Function Combination Testing Based on Orthogonal Chart","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Chart; Test strategy; Software reliability testing; Software; Manual testing; Black-box testing; Keyword-driven testing; White-box testing; Reliability engineering; Test (biology); Function (biology); Non-regression testing; Software testing; Software engineering; Test Management Approach; Risk-based testing; Software construction; Software development; Programming language; Statistics; Mathematics","score_opus":0.032306658540416935,"score_gpt":0.3048874524493184,"score_spread":0.2725807939089015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2371137413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007229839,0.000012153907,0.9930095,0.00032704507,0.00003642932,0.0008725901,0.00000273468,0.0053127334,0.0003545141],"genre_scores_gemma":[0.030114405,1.062857e-7,0.9675542,0.0015547965,0.00014185134,0.00056970416,0.000025327528,0.000018520836,0.000021063224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987339,0.0000384179,0.00027741713,0.0004936864,0.00016495875,0.0002916317],"domain_scores_gemma":[0.9971955,0.001908081,0.00014363548,0.0003975517,0.00027905885,0.00007618185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001232693,0.00015632888,0.0001283913,0.00026120528,0.0003813692,0.0001358699,0.00046039355,0.000074808224,0.0000010082899],"category_scores_gemma":[0.000022053197,0.00016494682,0.00006864357,0.00066351955,0.000017749357,0.000131419,0.000070317896,0.0001261205,0.000015996073],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010085031,0.00018441038,0.0006445723,0.0000239092,0.000007367352,6.7554225e-7,0.00006017638,0.00051900215,0.0077408752,0.01794441,0.0041371207,0.9687274],"study_design_scores_gemma":[0.0006643838,0.0003865029,0.0047989264,0.00008888567,0.000018792814,0.000021236192,0.0000024438527,0.86858594,0.01745623,0.07203345,0.035542164,0.00040105922],"about_ca_topic_score_codex":0.000007359333,"about_ca_topic_score_gemma":9.472202e-7,"teacher_disagreement_score":0.96832633,"about_ca_system_score_codex":0.00006945805,"about_ca_system_score_gemma":0.000059841666,"threshold_uncertainty_score":0.6726336},"labels":[],"label_agreement":null},{"id":"W2382790792","doi":"","title":"Design of an Automatic Test Case Generator for Embedded C Compilers","year":2010,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Compiler; Programming language; Correctness; Generator (circuit theory); Semantics (computer science); Syntax; Algorithm; Artificial intelligence","score_opus":0.02220176430816151,"score_gpt":0.2852982312793528,"score_spread":0.26309646697119127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2382790792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007609118,0.000010488826,0.98736846,0.00013184815,0.000027499202,0.0010076337,0.000014973196,0.0038145438,0.000015444599],"genre_scores_gemma":[0.09929093,3.7972643e-7,0.899542,0.0003175138,0.000064358224,0.00075031567,0.000011291475,0.000015907972,0.000007323601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990584,0.000036477064,0.00027791213,0.00036127065,0.000080900834,0.0001849983],"domain_scores_gemma":[0.99801916,0.00079590344,0.00013725944,0.0007671946,0.00018635501,0.00009412595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036625232,0.00013669961,0.00016300505,0.00011466404,0.00017166749,0.00011829686,0.000769155,0.00006864922,0.000002298175],"category_scores_gemma":[0.000010595197,0.00013600425,0.000049254366,0.00027147305,0.00005637743,0.00018587282,0.000120935096,0.00012008888,0.000007276201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014654719,0.0008051456,0.00015137956,0.00008978103,0.000024948173,0.000021257389,0.0012676071,0.0005622794,0.18417206,0.009406757,0.01596554,0.7875318],"study_design_scores_gemma":[0.00030497287,0.00014790522,0.00009510384,0.000015311316,0.000013305078,0.00093165395,0.0000032984965,0.94238794,0.03514194,0.015681494,0.005011936,0.0002651248],"about_ca_topic_score_codex":0.000016445809,"about_ca_topic_score_gemma":0.000004674879,"teacher_disagreement_score":0.9418257,"about_ca_system_score_codex":0.000011454995,"about_ca_system_score_gemma":0.00009231552,"threshold_uncertainty_score":0.55460924},"labels":[],"label_agreement":null},{"id":"W2389797271","doi":"","title":"State-Based Class Testing Research","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Computer science; System integration testing; Software reliability testing; Class (philosophy); Software performance testing; Non-regression testing; Software quality; Class diagram; State (computer science); Software engineering; Unit testing; Software construction; Software; Reliability engineering; Software development; Programming language; Unified Modeling Language; Engineering; Artificial intelligence","score_opus":0.24520556701404095,"score_gpt":0.354585413518932,"score_spread":0.10937984650489108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2389797271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048942724,0.00007134825,0.90549654,0.0021058542,0.00009089306,0.00013527654,4.148726e-7,0.028598575,0.058606803],"genre_scores_gemma":[0.5159714,5.610378e-7,0.4827739,0.00036901995,0.000018938861,0.000012164036,1.281453e-7,0.0000062706217,0.00084755174],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863154,0.00011329018,0.00013605096,0.0003133417,0.00041755082,0.00038821087],"domain_scores_gemma":[0.9972024,0.0017868016,0.000025946207,0.00062880665,0.0002674569,0.00008856971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096994924,0.0000790601,0.00007807202,0.00019542314,0.00020707933,0.00022221963,0.0007946402,0.000034340403,0.000036701043],"category_scores_gemma":[0.0016203495,0.000067798996,0.000021684871,0.00105409,0.000062148436,0.00016049642,0.00019388988,0.00022483947,0.00025193984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013496726,0.00016955091,0.019335657,0.000021878568,0.0000040477303,0.00008569014,0.00028455653,0.00018355016,0.0003676462,0.007383293,0.5026723,0.4694905],"study_design_scores_gemma":[0.000113900925,0.00015850681,0.0008761662,0.000040376963,4.5141957e-7,0.000011071606,0.0000011808788,0.94097316,0.0025080896,0.051317405,0.003847423,0.0001522918],"about_ca_topic_score_codex":0.00015998025,"about_ca_topic_score_gemma":0.0000030506346,"teacher_disagreement_score":0.9407896,"about_ca_system_score_codex":0.00004248534,"about_ca_system_score_gemma":0.000035220295,"threshold_uncertainty_score":0.32382607},"labels":[],"label_agreement":null},{"id":"W2394617872","doi":"10.1016/b978-0-12-408094-2.00005-9","title":"Test Cost-Effectiveness and Defect Density: A Case Study on the Android Platform","year":2013,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Orta Doğu Teknik Üniversitesi","keywords":"Android (operating system); Code coverage; Computer science; Replicate; Engineering; Embedded system; Operating system; Software; Statistics; Mathematics","score_opus":0.04311971506019773,"score_gpt":0.2986792452720685,"score_spread":0.2555595302118708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394617872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11957901,0.0074751475,0.75936586,0.00047988482,0.0040990636,0.016938,0.0000260538,0.017514441,0.07452256],"genre_scores_gemma":[0.9758385,0.00019354129,0.02239064,0.0005990049,0.00010859527,0.0002635629,0.0000021549918,0.00006294041,0.00054105476],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982603,0.00007478671,0.0002861212,0.00079370715,0.0002932496,0.0002918128],"domain_scores_gemma":[0.99103594,0.0076719415,0.00019798095,0.0009325804,0.00008179391,0.00007974585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006287504,0.0004361218,0.0004613935,0.00023514165,0.0002112365,0.0002366473,0.00072984287,0.00012967171,0.0000018198671],"category_scores_gemma":[0.00018329325,0.00031964068,0.00008039941,0.00011221887,0.000148581,0.0004003506,0.00060467643,0.00055736443,0.000019761157],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018403922,0.0002215197,0.008981132,0.00010400728,0.000075908094,0.008057377,0.0011001811,0.000186683,0.0000011094519,0.030715844,0.001744287,0.94879353],"study_design_scores_gemma":[0.0043253643,0.009217306,0.009344531,0.0066459845,0.00018424311,0.023446552,0.00016971305,0.053637296,0.00012842439,0.863348,0.024830772,0.0047218315],"about_ca_topic_score_codex":0.000093089606,"about_ca_topic_score_gemma":0.00007914969,"teacher_disagreement_score":0.9440717,"about_ca_system_score_codex":0.00012453026,"about_ca_system_score_gemma":0.000038766175,"threshold_uncertainty_score":0.99992555},"labels":[],"label_agreement":null},{"id":"W2397104696","doi":"10.1016/bs.adcom.2014.12.003","title":"Advances in Testing JavaScript-Based Web Applications","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Unobtrusive JavaScript; JavaScript; Computer science; Scripting language; Web application; Programming language; Oracle; Unit testing; Test script; Web testing; Software engineering; Rich Internet application; World Wide Web; Dynamic web page; Test case; Web development; Web service; Web application security; Software","score_opus":0.04193320955251735,"score_gpt":0.2981805410131842,"score_spread":0.25624733146066686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397104696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014594153,0.0247,0.8143862,0.00014851957,0.00071606546,0.0005862633,0.000009496129,0.0052386154,0.15421341],"genre_scores_gemma":[0.0033104713,0.0011231817,0.99272096,0.0006173708,0.00024054728,0.00024078958,0.000026910639,0.00007887801,0.0016409046],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99727416,0.000046574598,0.00066959707,0.0010419484,0.0004969422,0.00047075946],"domain_scores_gemma":[0.9967842,0.0013517984,0.0004046192,0.0011167342,0.00020883651,0.00013380013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005415065,0.00049316965,0.000576487,0.00071596866,0.000081662736,0.00011350665,0.0018531994,0.0002195751,0.0000027824767],"category_scores_gemma":[0.00019226849,0.000533045,0.00009039533,0.00046523256,0.00016725743,0.00092350494,0.00040394734,0.0006242363,0.000035128713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051924267,0.000050252995,0.0011132187,0.000135471,0.0000036834183,0.00008101441,0.000053041877,0.011918105,0.0000012746895,0.047304,0.0027224713,0.93661225],"study_design_scores_gemma":[0.00038059358,0.000111680594,0.000020042751,0.0013400294,0.000005002103,0.000019771116,0.0000010802922,0.1111487,0.000004719195,0.36072764,0.5255998,0.0006409776],"about_ca_topic_score_codex":0.000019757746,"about_ca_topic_score_gemma":0.00008023482,"teacher_disagreement_score":0.9359713,"about_ca_system_score_codex":0.00033439358,"about_ca_system_score_gemma":0.00034743312,"threshold_uncertainty_score":0.9997121},"labels":[],"label_agreement":null},{"id":"W2398007991","doi":"","title":"Machine Learning-based Software Testing: Towards a Classification Framework.","year":2011,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of New Brunswick","funders":"","keywords":"Computer science; Software testing; Software engineering; Software reliability testing; System integration testing; Software performance testing; Test strategy; Machine learning; Regression testing; Software construction; Artificial intelligence; Software; Software development; Programming language","score_opus":0.04277672093902538,"score_gpt":0.23928308148803581,"score_spread":0.19650636054901044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398007991","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027437909,0.0018260723,0.9636774,0.000020435684,0.0005458347,0.00016824741,0.0000038824146,0.03091418,0.000100174184],"genre_scores_gemma":[0.3824558,0.0000119417,0.6172392,0.000018834755,0.0000931303,0.0000664706,0.0000060329403,0.00006956106,0.00003906152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979811,0.000038332197,0.0003981254,0.0007092945,0.0002371604,0.0006360133],"domain_scores_gemma":[0.9976616,0.0010424084,0.00010309489,0.0006857949,0.00020590305,0.00030121714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005037499,0.0005015711,0.00038254057,0.0004799,0.0001852585,0.00015680373,0.0007229474,0.00026758705,0.000007838891],"category_scores_gemma":[0.007695975,0.0005280166,0.000103870625,0.0010058231,0.000037971393,0.0003103868,0.00028069204,0.00080955797,0.000023292552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051951374,0.0009965007,0.20079428,0.0035049852,0.00036891224,0.00030190867,0.011644215,0.0790767,0.0011384139,0.028428413,0.0014625629,0.67223114],"study_design_scores_gemma":[0.00024614338,0.00019563209,0.015971133,0.0005758166,0.000022798846,0.000058871014,0.0000031574837,0.9776449,0.0008449057,0.001033312,0.0026285315,0.0007747842],"about_ca_topic_score_codex":0.000049790524,"about_ca_topic_score_gemma":9.2080006e-7,"teacher_disagreement_score":0.8985682,"about_ca_system_score_codex":0.000101091406,"about_ca_system_score_gemma":0.000121676385,"threshold_uncertainty_score":0.9997171},"labels":[],"label_agreement":null},{"id":"W2398142207","doi":"","title":"Diagnosing new faults using mutants and prior faults.","year":2011,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Reliability engineering; Engineering","score_opus":0.09920225159013185,"score_gpt":0.2892741667797259,"score_spread":0.19007191518959404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398142207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094101205,0.000044264154,0.90055543,0.0000624574,0.0006586194,0.00009134788,0.0000041144563,0.004153699,0.00032887774],"genre_scores_gemma":[0.59043235,0.000010088929,0.40937123,0.00007572807,0.000060231843,0.000005185683,0.0000012840928,0.000013266341,0.000030674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988248,0.000012558527,0.0002260843,0.00040239329,0.00029097288,0.00024323212],"domain_scores_gemma":[0.9991745,0.0001821593,0.00008523487,0.00029037741,0.00012782129,0.00013991428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013369508,0.0002038682,0.00015820647,0.00021956001,0.00007003023,0.00010641632,0.0006572232,0.00007570695,0.000026410258],"category_scores_gemma":[0.0008339886,0.00020908676,0.000039069644,0.00014917052,0.000022461476,0.00044282695,0.00023276174,0.0001940864,0.000011705613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008188162,0.00034469733,0.11048745,0.000120277786,0.00028024975,0.0006326154,0.011764894,0.001966966,0.0025568544,0.1847018,0.0016704543,0.68539184],"study_design_scores_gemma":[0.0009053315,0.00026864666,0.05211078,0.0016501629,0.000020606938,0.00037004857,0.000026700955,0.908156,0.009844648,0.024665415,0.0007118323,0.0012698465],"about_ca_topic_score_codex":0.00017885074,"about_ca_topic_score_gemma":0.0000021641117,"teacher_disagreement_score":0.906189,"about_ca_system_score_codex":0.00007131616,"about_ca_system_score_gemma":0.00007773842,"threshold_uncertainty_score":0.8526311},"labels":[],"label_agreement":null},{"id":"W2401010683","doi":"","title":"Change-driven Incremental Symbolic Execution of Evolving State Machines.","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Symbolic execution; State (computer science); Programming language","score_opus":0.06153845280612907,"score_gpt":0.2896852166668992,"score_spread":0.22814676386077015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401010683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13330954,0.00026198695,0.8466549,0.00045993668,0.00036429722,0.0003049466,0.0000034578084,0.012136285,0.006504653],"genre_scores_gemma":[0.8176413,0.0000027121448,0.18211481,0.00014696663,0.000028234672,0.000011737091,0.0000017848408,0.00000518604,0.000047282836],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924254,0.000039055078,0.0001543435,0.00017746394,0.00023443867,0.00015216936],"domain_scores_gemma":[0.9993601,0.00004952067,0.00007594872,0.0003167841,0.0001187162,0.00007896128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003022851,0.000084145824,0.0001131954,0.000110966175,0.000031637628,0.000040481023,0.00040785235,0.00002505036,0.0000061007163],"category_scores_gemma":[0.00012682032,0.00007247674,0.000027286518,0.00023621887,0.000026150115,0.0003603493,0.0002762354,0.000054891214,0.000013320033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026711212,0.0004620973,0.37794924,0.00011773412,0.00006571119,0.000051197967,0.016299376,0.00008136624,0.005823139,0.017662378,0.21041293,0.3710481],"study_design_scores_gemma":[0.00062751176,0.00042543467,0.032754045,0.00015707016,0.000009491402,0.00005834363,0.000022799906,0.8710248,0.015974633,0.078182645,0.00031256463,0.0004506722],"about_ca_topic_score_codex":0.0013577986,"about_ca_topic_score_gemma":0.000014049719,"teacher_disagreement_score":0.8709434,"about_ca_system_score_codex":0.000047133526,"about_ca_system_score_gemma":0.000036953617,"threshold_uncertainty_score":0.29555157},"labels":[],"label_agreement":null},{"id":"W2401568214","doi":"","title":"Combining static analysis and targeted symbolic execution for scalable bug-finding in application binaries","year":2016,"lang":"en","type":"article","venue":"Computer Science and Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Symbolic execution; Computer science; Concolic testing; Program analysis; Static analysis; Statement (logic); Programming language; Pruning; Process (computing); Program slicing; Scalability; Code (set theory); Debugging; Software; Operating system","score_opus":0.009698424595459712,"score_gpt":0.2327454978405086,"score_spread":0.22304707324504888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401568214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1887185,0.00008394691,0.809449,0.00011053388,0.00008331757,0.0001437,0.0000011062572,0.0014092507,6.1848476e-7],"genre_scores_gemma":[0.61021465,0.0000082941815,0.38968378,0.00003517921,0.000013423004,0.000037316182,7.2202175e-7,0.0000046886803,0.0000019859624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987053,0.000014352311,0.0002044044,0.0005132507,0.00021322152,0.00034943403],"domain_scores_gemma":[0.9987367,0.000679037,0.00006087861,0.00029551305,0.00012724184,0.00010066299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010522921,0.00013733662,0.00020747368,0.00076757686,0.00030618528,0.000222774,0.0003879239,0.0000417172,1.4860262e-7],"category_scores_gemma":[0.00060299644,0.00011334217,0.000025597878,0.0017579886,0.000112388065,0.0007577514,0.00033916577,0.00005700262,4.1342366e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069755033,0.000059496386,0.32081005,0.00018273033,0.000058654,0.000007855931,0.003910672,0.005956926,0.005811926,0.015361304,0.00016303989,0.6476704],"study_design_scores_gemma":[0.00021936558,0.00006159708,0.06885753,0.000116838935,0.000013873152,0.000008271134,0.0000024187777,0.92506653,0.0013155412,0.0040645734,0.00005807992,0.00021540598],"about_ca_topic_score_codex":0.000035077668,"about_ca_topic_score_gemma":0.0000024830288,"teacher_disagreement_score":0.9191096,"about_ca_system_score_codex":0.000078207144,"about_ca_system_score_gemma":0.000056267225,"threshold_uncertainty_score":0.46219593},"labels":[],"label_agreement":null},{"id":"W2401952677","doi":"","title":"Empirical Analysis for Investigating the Effect of Control Flow Dependencies on Testability of Classes.","year":2011,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Testability; Computer science; Control flow; Data-flow analysis; Reliability engineering; Data flow diagram; Programming language; Engineering; Database","score_opus":0.025811940340620704,"score_gpt":0.25466925489641645,"score_spread":0.22885731455579575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401952677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17626043,0.00040968435,0.8211564,0.000008060564,0.00014271945,0.00022464702,0.000008726383,0.0017773573,0.000011975501],"genre_scores_gemma":[0.78103715,0.0000019166007,0.21884014,0.000004542976,0.000028874485,0.000065622415,0.0000012655614,0.00001785626,0.0000026586085],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988062,0.000050063558,0.00037468923,0.00032711113,0.0001563646,0.0002855947],"domain_scores_gemma":[0.9941549,0.005002611,0.00010197533,0.00052389666,0.00012171744,0.0000949046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010443678,0.0002553629,0.0005024742,0.00029548284,0.00006530414,0.0000244743,0.00045686006,0.00010101343,9.211783e-7],"category_scores_gemma":[0.0056995866,0.00018906084,0.00020457598,0.0007898862,0.000058849888,0.00010374139,0.00010882038,0.00021054709,3.7753176e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004276016,0.00012093871,0.8225171,0.002066786,0.0009391348,0.000003996933,0.0054234415,0.14464636,0.0011104419,0.0014422054,0.0002252436,0.021461597],"study_design_scores_gemma":[0.0003882545,0.00056929205,0.058526512,0.00020335143,0.00018864048,0.000005313094,0.0000040183536,0.9261976,0.013397705,0.0002116336,0.000044475943,0.00026323143],"about_ca_topic_score_codex":0.000017394463,"about_ca_topic_score_gemma":0.0000019079143,"teacher_disagreement_score":0.78155124,"about_ca_system_score_codex":0.00003130042,"about_ca_system_score_gemma":0.000035454388,"threshold_uncertainty_score":0.7709677},"labels":[],"label_agreement":null},{"id":"W2408469942","doi":"10.1002/smr.1789","title":"A bug reproduction approach based on directed model checking and crash traces","year":2016,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Crash; Computer science; Java; Slicing; Programming language; Model checking; Task (project management); Program slicing; Open source; Debugging; Software; World Wide Web","score_opus":0.01984930774373265,"score_gpt":0.2571976485383381,"score_spread":0.23734834079460546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408469942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049941044,0.00045302906,0.94714177,0.00085423945,0.00009132594,0.00006793791,0.0000011786661,0.0014061823,0.00004327512],"genre_scores_gemma":[0.76255745,0.000031880896,0.23719192,0.00009663902,0.00007309691,0.000004508265,1.9427361e-7,0.0000075829353,0.000036732577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989053,0.000048452956,0.00028582008,0.00030201412,0.0003066973,0.00015172506],"domain_scores_gemma":[0.9987547,0.00017946296,0.0003161451,0.0002015694,0.0004512772,0.000096848526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007748035,0.00012750788,0.00018310321,0.0002282258,0.00015120643,0.00008731267,0.00021148361,0.0000739103,8.155279e-7],"category_scores_gemma":[0.0015492906,0.00008331886,0.000037773123,0.00025749407,0.000064272506,0.0005912022,0.00003378768,0.00014349284,3.4224882e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034848403,0.00076359586,0.18202545,0.00071504293,0.000073066316,0.000027540396,0.002600557,0.007575001,0.0013603418,0.0014572507,0.013150509,0.78990316],"study_design_scores_gemma":[0.0018680145,0.0008173952,0.052867897,0.0015626576,0.00005052062,0.00079602585,0.00002980961,0.80761003,0.0020497516,0.13149731,0.00022227949,0.0006282939],"about_ca_topic_score_codex":0.0000027210485,"about_ca_topic_score_gemma":2.3592321e-7,"teacher_disagreement_score":0.80003506,"about_ca_system_score_codex":0.000054220094,"about_ca_system_score_gemma":0.000122369,"threshold_uncertainty_score":0.33976445},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02512928207923182,"score_gpt":0.25991368093417877,"score_spread":0.23478439885494695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461407631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5501346,0.00031900458,0.4361752,0.0015228908,0.00023062665,0.0005999396,0.00001925774,0.010783203,0.00021528397],"genre_scores_gemma":[0.74813664,0.000035932982,0.2515905,0.0000995043,0.000024891955,0.000036647565,0.0000017732972,0.000011297164,0.0000628204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982302,0.00012675597,0.00039106605,0.0007185573,0.0002251409,0.000308287],"domain_scores_gemma":[0.9944291,0.0043637524,0.00015102168,0.0008578129,0.000066982095,0.00013134786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009180242,0.00018708984,0.00018170635,0.000111350724,0.00017683029,0.000073004376,0.00037493042,0.00010277154,0.000003838044],"category_scores_gemma":[0.021620242,0.00014324764,0.00003234283,0.00035179956,0.00018260283,0.00036759113,0.00018984168,0.00014596601,0.00002054876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005126714,0.00014634035,0.563756,0.000031202086,0.0000013230953,0.000023772809,0.00013167475,0.0000023958376,0.0016283767,0.00011523919,0.00036488016,0.4337937],"study_design_scores_gemma":[0.00060799374,0.00028475976,0.97283983,0.0004605944,0.000007802855,0.00015752301,0.000008868476,0.0026526884,0.0013076002,0.01956175,0.0015865638,0.00052399625],"about_ca_topic_score_codex":0.00013654062,"about_ca_topic_score_gemma":0.0000023668174,"teacher_disagreement_score":0.4332697,"about_ca_system_score_codex":0.00013633772,"about_ca_system_score_gemma":0.00006676585,"threshold_uncertainty_score":0.9866211},"labels":[],"label_agreement":null},{"id":"W2462043969","doi":"10.22215/etd/2011-09481","title":"A UML/MARTE model analysis approach for detection of concurrency faults","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Computer science; Concurrency; Unified Modeling Language; Programming language; Software","score_opus":0.039956633023581635,"score_gpt":0.2926322019118875,"score_spread":0.25267556888830583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2462043969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015858178,0.00008245714,0.9886402,0.0000014384447,0.00013238016,0.00032826242,0.000010914525,0.0034887895,0.0057297605],"genre_scores_gemma":[0.4908771,0.000005569317,0.5066811,0.000010374497,0.00001466628,0.00016629584,0.00019998164,0.000013395483,0.0020315682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865556,0.000025373,0.0003843119,0.0005291297,0.00021564536,0.0001899797],"domain_scores_gemma":[0.99843824,0.000097851196,0.00038509414,0.000634112,0.0003946851,0.000050020157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027204392,0.00022035863,0.00043442837,0.0005622128,0.00007252854,0.00003075945,0.0006755511,0.00024537992,0.0000020140951],"category_scores_gemma":[0.00014557868,0.00020018422,0.00033973518,0.00075545604,0.000015496631,0.00014819598,0.000037060545,0.00013058851,9.4855324e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025961772,0.0011534685,0.0017862017,0.0024307042,0.0027558645,0.0000020651682,0.010432465,0.0044103074,0.0031658646,0.028751193,0.0077561103,0.9370961],"study_design_scores_gemma":[0.00009908883,0.00009180858,0.00020978869,0.000024483335,0.00030419818,6.992592e-7,0.000007980998,0.9710138,0.008283011,0.019727213,0.000006651196,0.00023126356],"about_ca_topic_score_codex":0.00028436215,"about_ca_topic_score_gemma":0.000057401598,"teacher_disagreement_score":0.9666035,"about_ca_system_score_codex":0.000020472147,"about_ca_system_score_gemma":0.000092818875,"threshold_uncertainty_score":0.8163276},"labels":[],"label_agreement":null},{"id":"W2479336862","doi":"10.1109/snpd.2016.7515953","title":"A comparative study on black-box testing with open source applications","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Black box; Open source software; Computer science; Open source; White-box testing; Non-regression testing; Software; Software performance testing; Software testing; Software reliability testing; Reliability engineering; Software engineering; Operating system; Software quality; Software development; Software construction; Engineering; Artificial intelligence","score_opus":0.094093447487158,"score_gpt":0.3420626282076523,"score_spread":0.24796918072049431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479336862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010274915,0.0000016709603,0.96301645,0.00045056987,0.0000075118833,0.00085571595,5.2331177e-7,0.0072277086,0.018164918],"genre_scores_gemma":[0.707178,6.034412e-8,0.2916252,0.00018218422,0.00001501788,0.00022569955,1.1728518e-7,0.0000063457605,0.0007673738],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903184,0.0000580144,0.00013028987,0.00042251035,0.00018424117,0.00017310414],"domain_scores_gemma":[0.9979372,0.0010272765,0.00007902962,0.0007607591,0.00012992485,0.000065792636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026702607,0.00012164815,0.0001552996,0.0000627201,0.0001674952,0.00022690478,0.0013365491,0.000017495948,0.0000043096866],"category_scores_gemma":[0.00009110298,0.00006506127,0.000011314024,0.0004461679,0.000060154885,0.00024095637,0.00048322466,0.000060740145,0.00012361594],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007882266,0.00430476,0.30286705,0.000016381917,0.00017046568,0.000037830032,0.013147077,0.00020544085,0.0011002591,0.05552569,0.082379706,0.5401665],"study_design_scores_gemma":[0.018238045,0.043107,0.3474734,0.0037282074,0.00020202703,0.0004119148,0.0035150223,0.093163624,0.04327579,0.39001128,0.048111454,0.008762201],"about_ca_topic_score_codex":0.00011755752,"about_ca_topic_score_gemma":0.00001265683,"teacher_disagreement_score":0.69690305,"about_ca_system_score_codex":0.00003000195,"about_ca_system_score_gemma":0.00005404193,"threshold_uncertainty_score":0.26531217},"labels":[],"label_agreement":null},{"id":"W2480723093","doi":"10.1007/b136676","title":"Testing of Communicating Systems","year":2005,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Tomsk State University; Tsinghua University; Georg-August-Universität Göttingen; Ohio State University; Universidad Complutense de Madrid; University of Ottawa","keywords":"Computer science","score_opus":0.03524634707782208,"score_gpt":0.27733617445007575,"score_spread":0.24208982737225365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2480723093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059620346,0.0012996844,0.9906977,0.000119523174,0.00067035685,0.000294497,0.0000024253359,0.003055226,0.003800959],"genre_scores_gemma":[0.11891562,0.000007649656,0.8803574,0.0002448732,0.00031535488,0.000012806012,0.0000022336687,0.00002718713,0.00011688246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966059,0.000109969325,0.00077781576,0.0009983226,0.00090173626,0.0006063065],"domain_scores_gemma":[0.9924386,0.0036895233,0.0006869412,0.002603007,0.00047024005,0.00011169349],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0020549842,0.00041277928,0.0006490298,0.0008006208,0.00023249967,0.00040155998,0.006475878,0.00027569092,9.0345975e-7],"category_scores_gemma":[0.0013983656,0.0003900327,0.00008638699,0.0016765543,0.0006471329,0.0004078424,0.0024970649,0.00087439374,0.000007368325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3248244e-7,0.00003796776,0.0008286055,0.00013405547,0.00000589628,0.000017064425,0.00058739283,0.031094735,0.00008540823,0.001224748,0.00038792772,0.96559536],"study_design_scores_gemma":[0.000111246765,0.00014479426,0.00021989267,0.002400149,0.0000055777205,0.00013091059,4.99261e-8,0.91809106,0.00050316093,0.07729492,0.0005841789,0.00051407923],"about_ca_topic_score_codex":0.0001422979,"about_ca_topic_score_gemma":0.000007953538,"teacher_disagreement_score":0.9650813,"about_ca_system_score_codex":0.0004017927,"about_ca_system_score_gemma":0.0012584039,"threshold_uncertainty_score":0.99985516},"labels":[],"label_agreement":null},{"id":"W2485697085","doi":"10.1109/icst.2016.32","title":"Atrina: Inferring Unit Oracles from GUI Test Cases","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Intel Corporation","keywords":"JavaScript; Computer science; Unit testing; Leverage (statistics); Programming language; Assertion; Test suite; Test case; Software testing; Code (set theory); Artificial intelligence; Software; Machine learning","score_opus":0.048376541193908905,"score_gpt":0.2788364857413657,"score_spread":0.2304599445474568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485697085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1242079,0.00008893983,0.84374714,0.0012867657,0.00015627676,0.00007537694,0.000007034779,0.026787711,0.0036428343],"genre_scores_gemma":[0.76433533,0.0000072642233,0.23485373,0.00022566812,0.00006339235,0.0000048013235,4.760878e-7,0.000007657034,0.0005016997],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916303,0.00002507376,0.00015269613,0.00029806522,0.00015007808,0.00021106811],"domain_scores_gemma":[0.9964463,0.0027033198,0.000050722865,0.00064617075,0.00007613832,0.00007731503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014320307,0.000114990595,0.00011021139,0.000080072416,0.000091544556,0.000110729685,0.00067238,0.000045570752,0.000048463837],"category_scores_gemma":[0.0016799036,0.00007183031,0.000035554312,0.00020512739,0.00003843608,0.00034431566,0.0003870887,0.00004931312,0.00017869868],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018850828,0.000062762716,0.64915836,0.0000044352823,0.000009410468,0.00016101582,0.00009605585,7.766394e-7,0.0011543019,0.010825587,0.029976347,0.30854908],"study_design_scores_gemma":[0.0013267001,0.0008123124,0.31264323,0.0009947672,0.000031343123,0.00043768514,0.000020526264,0.0058139693,0.086181656,0.53698003,0.052795485,0.0019622592],"about_ca_topic_score_codex":0.0012245941,"about_ca_topic_score_gemma":0.000058406284,"teacher_disagreement_score":0.6401274,"about_ca_system_score_codex":0.00002340214,"about_ca_system_score_gemma":0.000056331613,"threshold_uncertainty_score":0.2929155},"labels":[],"label_agreement":null},{"id":"W2512737610","doi":"","title":"Global Applications of Array-Based Techniques II Posters","year":2015,"lang":"en","type":"article","venue":"2015 AGU Fall Meeting","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.026468031843469682,"score_gpt":0.292040474495669,"score_spread":0.2655724426521993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512737610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008061279,0.00019296767,0.97105706,0.00078159827,0.00008839894,0.0002937206,0.0000061278374,0.009114539,0.010404308],"genre_scores_gemma":[0.45230198,7.072136e-7,0.5473365,0.00023182192,0.000042407624,0.00005736768,0.0000030917283,0.0000074509817,0.000018683513],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872994,0.000063787396,0.00029579937,0.00032407066,0.00033710286,0.00024927728],"domain_scores_gemma":[0.9985084,0.00012552843,0.00021512435,0.00068572717,0.0003263929,0.00013883895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080867414,0.00014527456,0.00018517103,0.000101591424,0.000108412,0.00005507417,0.00091354206,0.000082205544,2.4928514e-7],"category_scores_gemma":[0.00038721756,0.00014034093,0.000060439583,0.0005423772,0.00006657526,0.00016048789,0.00024371853,0.00008078569,0.000007981804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048443577,0.0008298273,0.41025835,0.00023776591,0.0000675096,0.000021524196,0.002513262,0.00048948615,0.0046911296,0.017733572,0.26531202,0.29779708],"study_design_scores_gemma":[0.0033268803,0.0039174496,0.007502158,0.003056791,0.00017130525,0.00028775402,0.00031225366,0.08127,0.19712871,0.5615272,0.13674289,0.0047566346],"about_ca_topic_score_codex":0.0011129748,"about_ca_topic_score_gemma":0.000047393696,"teacher_disagreement_score":0.5437936,"about_ca_system_score_codex":0.000092555405,"about_ca_system_score_gemma":0.00017865941,"threshold_uncertainty_score":0.5722937},"labels":[],"label_agreement":null},{"id":"W2516023085","doi":"10.4204/eptcs.224.6","title":"Fault Localization in Web Applications via Model Finding","year":2016,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Satisfiability; Programming language; Focus (optics); Set (abstract data type); Object (grammar); Fault (geology); Theoretical computer science; Specification language; Fault model; Algorithm; Artificial intelligence; Engineering","score_opus":0.007970434223973321,"score_gpt":0.2536372894738852,"score_spread":0.2456668552499119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516023085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060684457,0.000027204254,0.98982453,0.0009298065,0.000042072184,0.00028346828,2.926706e-7,0.0018565515,0.00096763886],"genre_scores_gemma":[0.8815783,0.00001735633,0.11794954,0.00030239185,0.00003532292,0.00010170711,1.6394957e-7,0.000009993171,0.000005190058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973168,0.000018219733,0.00034836223,0.00087494525,0.0005007575,0.00094095],"domain_scores_gemma":[0.99906695,0.00021029892,0.00008854309,0.00033916289,0.00017635859,0.00011866135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018962696,0.00018569981,0.00018301279,0.00057038077,0.00019327935,0.00021442345,0.0021337087,0.00008386642,0.0000024816657],"category_scores_gemma":[0.00026371126,0.00014144472,0.000032314612,0.0026003153,0.0007817745,0.00096174603,0.0006124806,0.00025771724,0.000013424961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028760721,0.00004619813,0.0011125997,0.0000056653953,6.0373145e-7,8.602293e-7,0.00016972343,0.00036937304,0.0011539689,0.9284916,0.00006158477,0.06858494],"study_design_scores_gemma":[0.000120692224,0.000049496393,0.000048057627,0.000058843445,5.323981e-7,0.000013182759,3.2721087e-7,0.5258858,0.001734207,0.47193503,0.00003259727,0.00012117443],"about_ca_topic_score_codex":0.0000023338491,"about_ca_topic_score_gemma":0.000001977707,"teacher_disagreement_score":0.8755099,"about_ca_system_score_codex":0.0005398862,"about_ca_system_score_gemma":0.00032773483,"threshold_uncertainty_score":0.5767948},"labels":[],"label_agreement":null},{"id":"W2517343942","doi":"10.1145/2975961.2975962","title":"Mining timed regular expressions from system traces","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Debugging; Computer science; Rotation formalisms in three dimensions; Event (particle physics); Anomaly (physics); Anomaly detection; Programming language; Temporal logic; Real-time computing; Data mining","score_opus":0.019495748284716483,"score_gpt":0.23320831570258288,"score_spread":0.2137125674178664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517343942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024481032,0.000077545286,0.94819707,0.00071402226,0.00017313716,0.000056989633,0.0000017325142,0.02293772,0.003360729],"genre_scores_gemma":[0.5175595,8.2016146e-7,0.48164788,0.000051036903,0.000039007296,0.000012185837,2.8138174e-7,0.0000050564863,0.00068417075],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914795,0.000052309086,0.00014855315,0.00030376983,0.00017214642,0.00017524662],"domain_scores_gemma":[0.9984997,0.0006847798,0.00005667289,0.00064381113,0.000038200422,0.00007682699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017485533,0.000092014394,0.00011406683,0.0000551366,0.000095012605,0.00007292509,0.00064407237,0.00005199335,0.00002239415],"category_scores_gemma":[0.00015308592,0.00005216113,0.000036375863,0.00011311424,0.000024768522,0.00024691212,0.0001753311,0.000029397344,0.000071416085],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008096271,0.00008088888,0.009116388,0.000024761797,0.000041136464,0.00010024739,0.0014314215,0.0000022851132,0.048417587,0.024557734,0.35498038,0.56123906],"study_design_scores_gemma":[0.002961231,0.0005369336,0.020499364,0.010021668,0.000069464826,0.00025066527,0.00033989636,0.15807642,0.61447114,0.15824163,0.03129166,0.0032399376],"about_ca_topic_score_codex":0.000076710145,"about_ca_topic_score_gemma":0.0000011914603,"teacher_disagreement_score":0.56605357,"about_ca_system_score_codex":0.000026283096,"about_ca_system_score_gemma":0.000023643634,"threshold_uncertainty_score":0.21270691},"labels":[],"label_agreement":null},{"id":"W2519113869","doi":"10.1109/ivsw.2016.7566604","title":"Revision debug with non-linear version history in regression verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Bottleneck; Preprocessor; Ranking (information retrieval); Regression testing; Software bug; Correctness; Graph; Software engineering; Programming language; Theoretical computer science; Embedded system; Information retrieval; Software system","score_opus":0.02317134808403726,"score_gpt":0.25303797536745515,"score_spread":0.2298666272834179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519113869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025800327,0.00010731708,0.9675357,0.0007647703,0.00013196867,0.00011450467,1.421559e-7,0.003768286,0.0017769944],"genre_scores_gemma":[0.67176014,0.000024452771,0.32718217,0.00020429931,0.000019746652,0.000006098215,8.70784e-7,0.000007393456,0.00079481956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999215,0.00003719908,0.00012871476,0.00030355778,0.00018233157,0.0001331786],"domain_scores_gemma":[0.99915415,0.00013584617,0.00006703123,0.0005384474,0.00006091592,0.000043583477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028610305,0.00008817343,0.00009020705,0.00012849727,0.00003413199,0.00001015531,0.000348501,0.000051041254,0.000016354186],"category_scores_gemma":[0.00012609598,0.000046459354,0.00001702209,0.00016840966,0.000028523373,0.0003402516,0.000087475346,0.000055287113,0.00006841543],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089477355,0.00014369024,0.027764084,0.000036505076,0.0000027816723,0.00004219559,0.0005167327,0.0000074198883,0.0069187125,0.0020227153,0.3423823,0.6200734],"study_design_scores_gemma":[0.007292205,0.0029217673,0.07557239,0.011252598,0.00002567219,0.00018328008,0.00002989499,0.21612106,0.08977498,0.019146753,0.57480747,0.0028719397],"about_ca_topic_score_codex":0.00005242744,"about_ca_topic_score_gemma":0.0000018752643,"teacher_disagreement_score":0.6459598,"about_ca_system_score_codex":0.00022876528,"about_ca_system_score_gemma":0.00007164181,"threshold_uncertainty_score":0.18945575},"labels":[],"label_agreement":null},{"id":"W2521099350","doi":"10.1007/s11219-016-9340-8","title":"An empirical study on the effects of code visibility on program testability","year":2016,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities","keywords":"Testability; Visibility; Computer science; Code coverage; Artifact (error); Code (set theory); Software; Software quality; Software engineering; Software metric; Programming language; Software development; Reliability engineering; Engineering; Artificial intelligence; Set (abstract data type)","score_opus":0.06644119961895152,"score_gpt":0.4136435348790582,"score_spread":0.3472023352601067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521099350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7852594,0.000012217798,0.20879549,0.0012085388,0.00025563463,0.0006927643,0.0000057821962,0.003752549,0.000017619375],"genre_scores_gemma":[0.9632718,0.0000015146484,0.036106028,0.00045536555,0.000088276414,0.00005459535,2.6602578e-7,0.000014861058,0.0000073036285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945282,0.0027310932,0.00072116626,0.00061069394,0.0009982913,0.00041058907],"domain_scores_gemma":[0.9846166,0.012283374,0.00042236169,0.002040383,0.0004003301,0.00023700426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068087303,0.00026096494,0.0003901827,0.00010261777,0.00036655657,0.00018908732,0.0016808811,0.000099957106,0.000009249187],"category_scores_gemma":[0.019795487,0.0001273579,0.00018477562,0.000392445,0.00023645915,0.00030462997,0.0001842068,0.0005245456,0.000011539339],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067623245,0.004386267,0.7518306,0.00003611468,0.000027928736,0.000019707903,0.0014092292,0.0000012115349,0.0001281693,0.0003431398,0.0017934047,0.2399566],"study_design_scores_gemma":[0.00068074977,0.009271407,0.8872189,0.00026956806,0.00001338168,0.00002897989,0.000039543396,0.00007038843,0.0020785022,0.09997556,0.0000796896,0.00027333232],"about_ca_topic_score_codex":0.000025670737,"about_ca_topic_score_gemma":0.000006919623,"teacher_disagreement_score":0.23968327,"about_ca_system_score_codex":0.00016050144,"about_ca_system_score_gemma":0.00019084204,"threshold_uncertainty_score":0.9884612},"labels":[],"label_agreement":null},{"id":"W2528843943","doi":"","title":"Towards a formalization of viewpoints testing","year":2002,"lang":"en","type":"article","venue":"Kent Academic Repository (University of Kent)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Viewpoints; Computer science","score_opus":0.03945148300212559,"score_gpt":0.21778578672480411,"score_spread":0.17833430372267853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528843943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39574766,0.0010673252,0.57737195,0.00040569267,0.000429421,0.00035839458,0.0000027384565,0.004062768,0.020554064],"genre_scores_gemma":[0.90449923,0.00007533257,0.09482163,0.000035205325,0.00002600455,3.1550653e-7,8.7484034e-7,0.0000058228497,0.0005355611],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989755,0.000063049214,0.00023175894,0.00024222286,0.00031930633,0.00016816052],"domain_scores_gemma":[0.99890804,0.000117168136,0.00038376913,0.00034726234,0.0001735736,0.000070170536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024665828,0.000101633064,0.00018910442,0.00013476271,0.00014988233,0.000010728654,0.00087233674,0.00012675786,0.000010276607],"category_scores_gemma":[0.00016978692,0.000120370605,0.000076389435,0.00045949378,0.00009227922,0.0005008677,0.00024163214,0.00018998902,0.0000056776807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051487274,0.0005833502,0.43573382,0.0009979021,0.00019375717,0.00021280276,0.02375822,0.0005782338,0.042106062,0.011462089,0.18191756,0.3024047],"study_design_scores_gemma":[0.0021350929,0.0010184635,0.11501669,0.0026562617,0.00018935755,0.0005563919,0.00034989612,0.79112804,0.05643383,0.023285436,0.005892806,0.0013377601],"about_ca_topic_score_codex":0.00014608052,"about_ca_topic_score_gemma":3.1554833e-7,"teacher_disagreement_score":0.79054976,"about_ca_system_score_codex":0.000066758475,"about_ca_system_score_gemma":0.000035643505,"threshold_uncertainty_score":0.49085706},"labels":[],"label_agreement":null},{"id":"W2535681473","doi":"10.1109/mutation.2006.10","title":"Mutation Operators for Concurrent Java (J2SE 5.0)","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Concurrency; Java; Programming language; Java concurrency; Operating system; Semaphore; Real time Java","score_opus":0.0165711930763524,"score_gpt":0.27212979571160767,"score_spread":0.25555860263525526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2535681473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00474806,0.000041471987,0.9854017,0.00031295497,0.00024889264,0.0001572422,0.0000011335312,0.0076232897,0.0014652446],"genre_scores_gemma":[0.63166374,3.3913508e-7,0.3676842,0.00020241183,0.00005369726,0.00004021733,0.000004860961,0.000004381169,0.00034615336],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994544,0.000012351456,0.00012288912,0.0001875268,0.00008982212,0.00013304822],"domain_scores_gemma":[0.99950826,0.0001571358,0.000031169493,0.0001908444,0.000087132925,0.000025449008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014956492,0.000067118664,0.00006521577,0.000049252343,0.00007490453,0.00010871153,0.0002476667,0.000026624331,0.0000041307158],"category_scores_gemma":[0.00008297707,0.000056518173,0.000031896896,0.00012770706,0.000014098846,0.00015755497,0.00004365598,0.000027899157,0.000013898083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016414508,0.00010001585,0.0029616894,0.000019609202,0.0000049326036,0.000006942371,0.00013492149,0.000121712445,0.00024756268,0.3477556,0.44617182,0.20247354],"study_design_scores_gemma":[0.0009688252,0.00041379198,0.0048253206,0.000058368503,0.000011303242,0.000056720808,0.000005914409,0.5467756,0.03799754,0.3704988,0.037701894,0.00068596896],"about_ca_topic_score_codex":0.00013299855,"about_ca_topic_score_gemma":0.000006544504,"teacher_disagreement_score":0.6269157,"about_ca_system_score_codex":0.000019909177,"about_ca_system_score_gemma":0.000028717272,"threshold_uncertainty_score":0.23047441},"labels":[],"label_agreement":null},{"id":"W2544310856","doi":"10.1109/icm.2011.6177404","title":"Performance analysis of constraint solvers for coverage directed test generation","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Constraint (computer-aided design); Test (biology); Mathematics","score_opus":0.05718253183475186,"score_gpt":0.25378960447336724,"score_spread":0.19660707263861538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544310856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08165315,0.0000046608848,0.9117167,0.0000136193885,0.000048248105,0.00009428028,0.000005063172,0.002991319,0.003472993],"genre_scores_gemma":[0.64724404,0.0000027262595,0.35263842,0.000051083865,0.0000061868363,0.000010613092,0.000005052775,0.000001953021,0.000039911167],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994637,0.000009832532,0.00016065282,0.000172077,0.00008689648,0.0001068609],"domain_scores_gemma":[0.9992648,0.00020703337,0.00008015581,0.00028213093,0.00013775573,0.000028128545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020088899,0.00006445829,0.00013396543,0.00017412046,0.000051491978,0.000018665325,0.00023611811,0.000030519714,0.000023980654],"category_scores_gemma":[0.00019969883,0.00005561568,0.0000697915,0.0005134359,0.000033719527,0.00014108555,0.00003695811,0.000024291361,0.0000010586323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001972162,0.00058253313,0.6581987,0.00007552332,0.0007802918,0.000004327711,0.0038169066,0.0006343272,0.012129601,0.01930273,0.03144593,0.27300936],"study_design_scores_gemma":[0.0000881548,0.00013552328,0.027731884,0.0000057434045,0.00006808846,0.0000011570152,0.0000012483432,0.9464689,0.024682174,0.0006933671,0.000031001087,0.00009274103],"about_ca_topic_score_codex":0.00008202688,"about_ca_topic_score_gemma":0.000009991799,"teacher_disagreement_score":0.9458346,"about_ca_system_score_codex":0.000013680223,"about_ca_system_score_gemma":0.000031596483,"threshold_uncertainty_score":0.22679417},"labels":[],"label_agreement":null},{"id":"W2546974490","doi":"10.1016/bs.adcom.2017.09.003","title":"Optimizing the Symbolic Execution of Evolving Rhapsody Statecharts","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Programming language; Symbolic execution; The Symbolic; Psychology; Software; Psychoanalysis","score_opus":0.019843225956895267,"score_gpt":0.2774101269308896,"score_spread":0.2575669009739944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546974490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010434738,0.008272738,0.8968671,0.00022002541,0.0014409343,0.00036779506,0.0000053513845,0.0023650227,0.09045063],"genre_scores_gemma":[0.07776401,0.004179913,0.90934503,0.00038988312,0.00031946984,0.000045136592,0.000015441974,0.00009938163,0.007841745],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982968,0.0000337819,0.0004542064,0.0005498014,0.0003682376,0.0002971627],"domain_scores_gemma":[0.9969866,0.00065672945,0.0006879968,0.0014932113,0.0001278483,0.00004756833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047704068,0.00032316768,0.00044442795,0.00026224385,0.00020512573,0.00015729459,0.0022802877,0.0001495089,0.000003832326],"category_scores_gemma":[0.00011146105,0.00026783254,0.00012682608,0.00004844945,0.00023037256,0.0007081756,0.0007256304,0.00043367024,0.0000061997107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011086118,0.000038278544,0.00014935617,0.00024701378,0.000053545158,0.0001256245,0.0021249785,0.0037927916,0.000015809646,0.21018547,0.009692369,0.7735637],"study_design_scores_gemma":[0.0003583499,0.00022175357,0.00011926648,0.004950727,0.000026124351,0.0000766549,0.000004963981,0.15287855,0.00020534213,0.7574133,0.08280583,0.00093909184],"about_ca_topic_score_codex":0.000034666307,"about_ca_topic_score_gemma":0.000011259461,"teacher_disagreement_score":0.7726246,"about_ca_system_score_codex":0.000096772616,"about_ca_system_score_gemma":0.00007668269,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W2548701964","doi":"10.1145/2994291.2994294","title":"PredSym: estimating software testing budget for a bug-free release","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Overfitting; Symbolic execution; Regression testing; Software; Code (set theory); Software performance testing; Code coverage; Software bug; Concolic testing; Software testing; Programming language; Software engineering; Machine learning; Software system; Software construction; Artificial neural network","score_opus":0.0332152410180936,"score_gpt":0.2673196379326332,"score_spread":0.2341043969145396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548701964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015607841,0.000026848404,0.9665644,0.0012898233,0.00022763858,0.00029495687,0.000008706147,0.029464604,0.0005622404],"genre_scores_gemma":[0.050874677,3.8197626e-7,0.9477662,0.00045820573,0.00015071407,0.00014124713,9.501465e-7,0.000026170193,0.0005814732],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840194,0.00003417817,0.00030698394,0.0005520746,0.00023663646,0.00046816928],"domain_scores_gemma":[0.9943554,0.00383608,0.00014529719,0.0012355144,0.00028352847,0.00014418812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00053120725,0.0001998815,0.00018959575,0.00010974096,0.00024183818,0.00015971875,0.0014026728,0.000076707176,0.0000064201],"category_scores_gemma":[0.02267628,0.00013450481,0.000075201075,0.0003250094,0.000048711852,0.00047113196,0.00057394046,0.00007236715,0.000023927389],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008295007,0.00006706833,0.014669507,0.000078861005,0.000013737415,0.000015186599,0.00013888495,0.000034730467,0.00071837415,0.0055132876,0.16911791,0.80962414],"study_design_scores_gemma":[0.001104009,0.00044268597,0.0012737897,0.00070522557,0.00001501111,0.000114142305,0.000001918573,0.23324414,0.0041844686,0.75676686,0.0014614229,0.0006863291],"about_ca_topic_score_codex":0.00006157749,"about_ca_topic_score_gemma":0.0000025266636,"teacher_disagreement_score":0.80893785,"about_ca_system_score_codex":0.000055652283,"about_ca_system_score_gemma":0.0001153948,"threshold_uncertainty_score":0.9855561},"labels":[],"label_agreement":null},{"id":"W2549749398","doi":"10.14288/1.0319084","title":"A study of the influence of assertions and mutants on test suite effectiveness","year":2016,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Suite; Test suite; Test (biology); Computer science; Biology; Test case; History; Archaeology","score_opus":0.009772553224793704,"score_gpt":0.1978724058906307,"score_spread":0.188099852665837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549749398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979131,0.000006598085,0.0015188886,0.000025003956,0.000022478816,0.00021445245,0.000019265528,0.00024156086,0.00003865405],"genre_scores_gemma":[0.9992767,0.000004294877,0.00068788993,0.0000062755425,0.0000015948783,5.990542e-7,5.650893e-8,0.0000030062404,0.000019600566],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99933416,0.0000941122,0.00008131627,0.00021664692,0.00018321183,0.00009055217],"domain_scores_gemma":[0.99858034,0.00068581227,0.00013013858,0.0003971291,0.00017538446,0.00003121629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023846934,0.000027484619,0.00015042526,0.000034678564,0.000111645895,0.00001990522,0.00053332123,0.000032922333,7.5752394e-7],"category_scores_gemma":[0.0003789047,0.000053026193,0.000033701926,0.000316865,0.00018642764,0.00019638106,0.00027629995,0.000045019333,4.9980196e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035689882,0.0003674889,0.83929825,0.00003546729,0.000013391503,0.0000162495,0.0003012927,0.0000059414724,0.0022107712,0.0000056725007,0.00007622799,0.15766568],"study_design_scores_gemma":[0.00049019506,0.00039803574,0.9969168,0.0005857575,0.000010010134,0.000017856592,0.00004497856,0.0000427973,0.00004534083,0.001385923,0.0000010177946,0.00006131318],"about_ca_topic_score_codex":0.01836198,"about_ca_topic_score_gemma":0.011316946,"teacher_disagreement_score":0.15761852,"about_ca_system_score_codex":0.000020222116,"about_ca_system_score_gemma":0.00003804385,"threshold_uncertainty_score":0.98817486},"labels":[],"label_agreement":null},{"id":"W2549903643","doi":"10.1109/hldvt.2016.7748249","title":"Accelerating assertion assessment using GPUs","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University; CMC Microsystems (Canada)","funders":"","keywords":"Assertion; Correctness; Computer science; Parallelism (grammar); Key (lock); Programming language; Formal verification; Parallel computing; Theoretical computer science; Operating system","score_opus":0.07412440821616174,"score_gpt":0.3391528525172591,"score_spread":0.26502844430109734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549903643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043344,0.0000054119537,0.94459534,0.00051135005,0.00013706076,0.00004875732,1.1381467e-7,0.008338952,0.003018996],"genre_scores_gemma":[0.5050201,5.629442e-7,0.49474257,0.000119393255,0.000023546205,0.0000032257897,6.475053e-8,0.0000031495752,0.000087390275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927557,0.000035950205,0.00013345333,0.00022356618,0.0001613237,0.00017016381],"domain_scores_gemma":[0.9993088,0.00018882027,0.00005405999,0.000342041,0.00006384835,0.000042403994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982581,0.00007467913,0.00007073353,0.000058681264,0.00010870339,0.00013567775,0.0003337622,0.000032130632,0.000016528742],"category_scores_gemma":[0.00011782176,0.000046016045,0.000026424917,0.00014573256,0.000011456063,0.00047642292,0.0001557146,0.00003967547,0.000011291232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013369198,0.00007383983,0.06546112,0.000008874146,0.000012244181,0.000015286012,0.000091431924,0.000014552552,0.09928645,0.08204514,0.0073324856,0.7456572],"study_design_scores_gemma":[0.000744663,0.00027289154,0.053863805,0.0004206817,0.00001116,0.00015077536,0.000006356747,0.60362077,0.079012364,0.25985163,0.0011178473,0.00092706067],"about_ca_topic_score_codex":0.00005693657,"about_ca_topic_score_gemma":0.0000014987054,"teacher_disagreement_score":0.7447302,"about_ca_system_score_codex":0.00007565566,"about_ca_system_score_gemma":0.00005609135,"threshold_uncertainty_score":0.18764798},"labels":[],"label_agreement":null},{"id":"W2550120381","doi":"10.48550/arxiv.1611.01855","title":"Neuro-Symbolic Program Synthesis","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Correctness; Computer science; Construct (python library); Program synthesis; Set (abstract data type); Representation (politics); Artificial neural network; Domain (mathematical analysis); Task (project management); String (physics); Theoretical computer science; Regular expression; Algorithm; Artificial intelligence; Programming language; Mathematics","score_opus":0.06483697021880241,"score_gpt":0.18710201138523988,"score_spread":0.12226504116643747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550120381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11555325,0.000010357631,0.8623358,0.00051756715,0.00014287402,0.000165901,0.0000017039486,0.018444693,0.0028278665],"genre_scores_gemma":[0.9824035,0.000016815124,0.016863437,0.00012905565,0.000026613938,0.0000023634952,1.1204345e-7,0.00000999783,0.0005480882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990078,0.00006966562,0.00008397154,0.0004977114,0.0000559267,0.0002848999],"domain_scores_gemma":[0.9984072,0.0006050533,0.000060970142,0.0007453828,0.00006531374,0.00011612319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014097715,0.00012721485,0.000120259494,0.00013340605,0.00011002254,0.00005198935,0.000990942,0.000057219037,0.000014355021],"category_scores_gemma":[0.00037390742,0.00010129722,0.000075868185,0.0005535071,0.000081932616,0.00037757045,0.0002697953,0.00006300011,0.00015361395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025459382,0.00040039574,0.07438581,0.00002376182,0.00005075348,0.0007508154,0.00012433022,0.00012548374,0.00063616753,0.36627197,0.02110923,0.53609586],"study_design_scores_gemma":[0.001424251,0.0008415693,0.043350637,0.00048361043,0.00010784721,0.00015692745,0.000012050784,0.20056726,0.0123643195,0.70753783,0.031025039,0.0021286744],"about_ca_topic_score_codex":0.00002924522,"about_ca_topic_score_gemma":0.0000022519243,"teacher_disagreement_score":0.86685026,"about_ca_system_score_codex":0.000046654386,"about_ca_system_score_gemma":0.000038409722,"threshold_uncertainty_score":0.4130781},"labels":[],"label_agreement":null},{"id":"W2562367443","doi":"10.22360/summersim.2016.scsc.019","title":"On Simulation-based Metrics that Characterize the Behavior of RTL Errors","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Debugging; Debugger; Process (computing); Pruning; Software bug; Programming language; Reliability engineering; Software","score_opus":0.06359309796219473,"score_gpt":0.29865548424512556,"score_spread":0.23506238628293083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562367443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063302554,0.0000046490522,0.9326355,0.0007897985,0.000118838376,0.00015788358,0.0000029260323,0.0027801227,0.0002077692],"genre_scores_gemma":[0.96264243,5.260736e-7,0.03669722,0.00049493316,0.000009762145,0.00002865587,4.8234034e-7,0.000005683763,0.00012030746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992709,0.000042308526,0.0001289078,0.00017342095,0.00026332945,0.00012110794],"domain_scores_gemma":[0.99569815,0.0034581975,0.000102419435,0.0006104679,0.000099891826,0.00003086673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002946224,0.000081436636,0.00009018036,0.00012429648,0.000056943565,0.000029985247,0.0005878718,0.00003680728,0.000024662122],"category_scores_gemma":[0.0009766342,0.000038067592,0.00004557193,0.0004055546,0.00004298195,0.00010731567,0.00006596719,0.00004189334,0.000014549178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002671305,0.0005042994,0.15331128,0.000019322171,0.000018640998,0.000013732015,0.00025069155,0.0006982478,0.0030814367,0.02836249,0.006342259,0.8073709],"study_design_scores_gemma":[0.001426595,0.0011131426,0.37404433,0.00037475378,0.000052052706,0.000005906132,0.0000050295566,0.39036664,0.18587595,0.043069318,0.0027070974,0.000959159],"about_ca_topic_score_codex":0.000031657688,"about_ca_topic_score_gemma":8.493757e-7,"teacher_disagreement_score":0.89933985,"about_ca_system_score_codex":0.000020631718,"about_ca_system_score_gemma":0.000036320624,"threshold_uncertainty_score":0.15523513},"labels":[],"label_agreement":null},{"id":"W2584970301","doi":"10.1109/icosst.2016.7838329","title":"Safe regression test suite optimization: A review","year":2016,"lang":"en","type":"review","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Test suite; Regression testing; Computer science; Suite; Reduction (mathematics); Test case; Fuzzy logic; Machine learning; Artificial intelligence; Regression analysis; Mathematics; Software","score_opus":0.057840892821870986,"score_gpt":0.36391140119092785,"score_spread":0.30607050836905686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584970301","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.023601e-12,0.5926791,0.39466238,0.00023533897,0.0001270992,0.00036809203,0.0000031524082,0.0075097405,0.0044150962],"genre_scores_gemma":[1.1860588e-9,0.6567783,0.34008834,0.00042677752,0.00008207283,0.00009832774,0.00001059161,0.00002390658,0.0024917312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977988,0.00017096862,0.00067847467,0.0007150679,0.0003319487,0.00030472022],"domain_scores_gemma":[0.9958017,0.0016669587,0.0005045058,0.0017496425,0.00015023953,0.00012693935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065544917,0.00044956512,0.0013575312,0.00017949136,0.000109560206,0.00013084339,0.0018580991,0.00022092443,0.00018846455],"category_scores_gemma":[0.0019508951,0.00023703926,0.00036549772,0.0007681108,0.000035839043,0.0002466643,0.00064036204,0.00021904979,0.00041202526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6143933e-8,0.0000101134265,4.0487402e-7,0.010486007,0.000004644437,0.0000093111985,8.9567544e-7,6.5718105e-8,1.0996686e-9,0.00027125943,0.19400236,0.7952149],"study_design_scores_gemma":[0.00001854088,0.000022984052,2.3597945e-8,0.2774892,0.000043425993,0.00013264055,6.6650254e-9,0.00015816561,9.1645546e-8,0.0003684581,0.72149867,0.0002678042],"about_ca_topic_score_codex":0.0000027256767,"about_ca_topic_score_gemma":9.9155535e-8,"teacher_disagreement_score":0.7949471,"about_ca_system_score_codex":0.00008751667,"about_ca_system_score_gemma":0.0002983585,"threshold_uncertainty_score":0.96661806},"labels":[],"label_agreement":null},{"id":"W2587858343","doi":"10.1109/aspdac.2017.7858329","title":"An extensible perceptron framework for revision RTL debug automation","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Leverage (statistics); Perceptron; Algorithmic program debugging; Cluster analysis; Automation; Machine learning; Data mining; Artificial intelligence; Programming language; Artificial neural network; Engineering","score_opus":0.04757200302978046,"score_gpt":0.37120749215319254,"score_spread":0.3236354891234121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587858343","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046325494,0.000028028197,0.98190635,0.00096519006,0.00022082761,0.00019303386,5.41948e-7,0.011483635,0.00056981645],"genre_scores_gemma":[0.3897407,0.000005023418,0.60982686,0.00026080845,0.000071690025,0.000011929777,0.0000014383867,0.0000067963356,0.000074728174],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913853,0.00002560817,0.00014060568,0.00034528392,0.0001511511,0.00019881346],"domain_scores_gemma":[0.99784386,0.00019379947,0.0001249828,0.0016325554,0.00013210671,0.00007269557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045163726,0.00010227189,0.000119930235,0.000056202418,0.0006243877,0.0006902836,0.0011076435,0.00009366985,0.000011258104],"category_scores_gemma":[0.0010667966,0.00008555424,0.0000505388,0.000047311976,0.00003044757,0.0008546334,0.00014102535,0.00007830479,0.000024738914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005378716,0.00007357267,0.0032110445,0.00002930614,0.000003852219,0.0000017624078,0.00042802515,0.0000085667625,0.0003437831,0.15325573,0.029537108,0.8131019],"study_design_scores_gemma":[0.00012208046,0.00031976105,0.020765861,0.00017098073,0.0000051599036,0.000010438634,0.0000041316325,0.36798134,0.0012802699,0.6064895,0.0026135747,0.00023691154],"about_ca_topic_score_codex":0.00007083089,"about_ca_topic_score_gemma":0.0000024185783,"teacher_disagreement_score":0.81286496,"about_ca_system_score_codex":0.00002430561,"about_ca_system_score_gemma":0.000029305636,"threshold_uncertainty_score":0.6656421},"labels":[],"label_agreement":null},{"id":"W2592345979","doi":"10.1109/access.2017.2676161","title":"Patch-Related Vulnerability Detection Based on Symbolic Execution","year":2017,"lang":"en","type":"article","venue":"IEEE Access","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Buffer overflow; Software bug; Symbolic execution; Fuzz testing; Memory safety; Software; Software security assurance; Memory leak; Security bug; Vulnerability (computing); Append; Malware; Static analysis; Operating system; Computer security; Programming language; Memory management; Cloud computing","score_opus":0.04551933161146442,"score_gpt":0.3414228419462515,"score_spread":0.29590351033478707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592345979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33391938,0.000005654582,0.65557337,0.00044467367,0.0011079691,0.0001715395,0.0000011988778,0.0069984733,0.0017777471],"genre_scores_gemma":[0.9958852,0.0000010901546,0.0037171831,0.00025321648,0.000064969885,0.00003965816,8.941537e-7,0.000009584755,0.000028204662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884844,0.00009172254,0.00018097494,0.00042504785,0.00024086879,0.00021294029],"domain_scores_gemma":[0.99779654,0.00019802239,0.00019598904,0.0016416602,0.00010027841,0.00006752707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053528044,0.00013339425,0.00013383852,0.00010585296,0.00067146466,0.0007712042,0.0016775201,0.00010689272,0.0000049800383],"category_scores_gemma":[0.0006415009,0.00012208312,0.000060419687,0.00015038121,0.000065040476,0.0008140289,0.00013918095,0.00020649114,0.000029082605],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054443946,0.00044902,0.13344191,0.00007058652,0.000023018916,0.000050636754,0.00028919688,0.0018716761,0.0029479687,0.001151494,0.0073751267,0.8522749],"study_design_scores_gemma":[0.0004370938,0.00018516336,0.25467587,0.00011936871,0.000009082636,0.000009353339,4.131787e-7,0.5804465,0.08137075,0.082204714,0.00017333686,0.00036837286],"about_ca_topic_score_codex":0.0009453658,"about_ca_topic_score_gemma":0.00003036914,"teacher_disagreement_score":0.85190654,"about_ca_system_score_codex":0.00007158828,"about_ca_system_score_gemma":0.000039487117,"threshold_uncertainty_score":0.743674},"labels":[],"label_agreement":null},{"id":"W2593244908","doi":"10.1145/2700529","title":"Automated Bug Finding in Video Games","year":2017,"lang":"en","type":"article","venue":"Computers in entertainment","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Video game; Video game development; Game development tool; Video game design; Game Developer; Instrumentation (computer programming); Process (computing); Sequential game; Game programming; State (computer science); Sample (material); Game testing; Game design; Event (particle physics); Programming language; Human–computer interaction; Game design document; Game theory; Game art design; Multimedia","score_opus":0.025209883546195373,"score_gpt":0.3043409565355983,"score_spread":0.27913107298940293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593244908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3711192,0.00012592386,0.6099061,0.0024393853,0.0019124212,0.00048661476,0.0000012114534,0.012403082,0.0016061066],"genre_scores_gemma":[0.8483681,0.000008765384,0.15120491,0.00033306982,0.000025567662,0.000031070278,0.0000010653592,0.000008825328,0.000018606812],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985584,0.0000688859,0.0003067693,0.00046257905,0.00022157919,0.00038175535],"domain_scores_gemma":[0.99846137,0.00019756854,0.00015483401,0.0011042464,0.00001736628,0.000064639105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048994785,0.00017204617,0.0002192105,0.00026902565,0.00014889751,0.00039292325,0.0018430877,0.000059723603,0.0000018895498],"category_scores_gemma":[0.00016886197,0.0001724282,0.000049169994,0.00012492537,0.000057083296,0.00034292857,0.00091539056,0.00016509292,0.000012580804],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001551833,0.00042422087,0.78314495,0.00006568479,0.000022487504,0.0007424142,0.0038699731,0.0012244644,0.00012368915,0.003927208,0.029678995,0.17676038],"study_design_scores_gemma":[0.00078796427,0.000089194524,0.26092696,0.0007316438,0.000001559403,0.000023571381,0.0000076080955,0.72260827,0.00036290623,0.013601576,0.00054389006,0.00031487053],"about_ca_topic_score_codex":0.00022826019,"about_ca_topic_score_gemma":0.0000256728,"teacher_disagreement_score":0.72138375,"about_ca_system_score_codex":0.00022512193,"about_ca_system_score_gemma":0.00002856246,"threshold_uncertainty_score":0.7031418},"labels":[],"label_agreement":null},{"id":"W2598381280","doi":"10.1145/3066862.3066867","title":"Fun and games at IEEE WCCI 2016, Vancouver, Canada","year":2017,"lang":"en","type":"article","venue":"ACM SIGEVOlution","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"Champion; Competition (biology); Artificial intelligence; Media studies; Psychology; Operations research; Computer science; Sociology; Engineering; Political science; Law","score_opus":0.017929992714591437,"score_gpt":0.24133561414956178,"score_spread":0.22340562143497034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598381280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6173448,0.003520904,0.34395075,0.004157144,0.012096036,0.0005885566,0.000020870177,0.012862067,0.0054588756],"genre_scores_gemma":[0.9636424,0.00003265796,0.03427019,0.00019151405,0.00006871297,0.00000980007,8.660656e-7,0.000006971922,0.0017768523],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9991582,0.000023386387,0.00010947059,0.00029254184,0.00019332553,0.00022308077],"domain_scores_gemma":[0.99824023,0.0001722902,0.00012821166,0.0013317706,0.00006142603,0.0000660628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001653808,0.00010496675,0.00010483221,0.000032656044,0.0006122094,0.00011048183,0.0009341587,0.00005094443,0.0000033241047],"category_scores_gemma":[0.00086525595,0.00009880806,0.000018684806,0.000039254966,0.0000605848,0.0003513187,0.0005499814,0.000076019125,0.0000069876232],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032236253,0.000008692675,0.02600752,0.000009441751,0.0000056681156,0.000013715759,0.000061291925,0.000006424819,0.00022785552,0.0002946516,0.9292007,0.04416082],"study_design_scores_gemma":[0.0012301119,0.00032214104,0.5410993,0.00035853736,0.00003833085,0.00011263729,0.000012761599,0.061924465,0.010349327,0.17325568,0.20974737,0.0015493026],"about_ca_topic_score_codex":0.2713554,"about_ca_topic_score_gemma":0.25919148,"teacher_disagreement_score":0.71945333,"about_ca_system_score_codex":0.00018755175,"about_ca_system_score_gemma":0.00021308518,"threshold_uncertainty_score":0.75432634},"labels":[],"label_agreement":null},{"id":"W2598672795","doi":"10.1007/978-3-662-54494-5_2","title":"Bordeaux: A Tool for Thinking Outside the Box","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Negation; Extension (predicate logic); Meaning (existential); Programming language; Algorithm; Theoretical computer science","score_opus":0.02714208637281054,"score_gpt":0.28431637315416347,"score_spread":0.25717428678135296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598672795","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005209331,0.00037197658,0.9896156,0.0026389582,0.0017904759,0.00069781137,0.000005140841,0.0026810481,0.002193736],"genre_scores_gemma":[0.029558515,0.000019511102,0.9656289,0.0033626175,0.00074598077,0.00005509886,0.0000029045568,0.00004584754,0.0005806099],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965101,0.00002850995,0.00044258742,0.0014014388,0.0008987414,0.0007186185],"domain_scores_gemma":[0.993872,0.0021276863,0.00047233386,0.003117835,0.00032256066,0.00008758533],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0022809124,0.0005120956,0.00047878912,0.00038948536,0.0012717034,0.0019213083,0.008406824,0.000298448,0.0000028904678],"category_scores_gemma":[0.0011370655,0.00036536664,0.00020731603,0.00015992047,0.00079992064,0.0005272474,0.0020933794,0.0007801795,0.000013818188],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042155866,0.000012375435,0.00011679743,0.000035785844,0.000010907961,0.000033021726,0.00092253124,0.0011158378,0.000010255077,0.036078442,0.0010698154,0.96059],"study_design_scores_gemma":[0.00012985991,0.000117696676,0.00009543908,0.00050226215,0.00000874407,0.00007069801,1.9611564e-8,0.12434556,0.00027693165,0.8671624,0.00679449,0.0004958882],"about_ca_topic_score_codex":0.00005773173,"about_ca_topic_score_gemma":0.00003759136,"teacher_disagreement_score":0.96009415,"about_ca_system_score_codex":0.00018098611,"about_ca_system_score_gemma":0.0006143261,"threshold_uncertainty_score":0.99987984},"labels":[],"label_agreement":null},{"id":"W2598705408","doi":"10.1007/978-3-319-55792-2_4","title":"Focusing Learning-Based Testing Away from Known Weaknesses","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Strengths and weaknesses; Similarity (geometry); Artificial intelligence; Adversary; Machine learning; Extension (predicate logic); Test (biology); Measure (data warehouse); Similarity measure; Theoretical computer science; Data mining; Computer security; Programming language","score_opus":0.03557945597157287,"score_gpt":0.27079144967597146,"score_spread":0.2352119937043986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598705408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009311325,0.00049762294,0.988058,0.0004872121,0.0014767059,0.00025452953,0.0000040676555,0.005783243,0.0033455393],"genre_scores_gemma":[0.24657238,0.0000058743562,0.75188315,0.0005428139,0.00072924973,0.000009807264,0.0000062611393,0.000058414633,0.00019208486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954252,0.00006288669,0.0005524363,0.0020619554,0.0010677455,0.00082973286],"domain_scores_gemma":[0.99255174,0.0035339235,0.00073105696,0.0024821006,0.00049620285,0.00020500096],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011737227,0.000722505,0.0007104115,0.00082290504,0.0011002185,0.0019197807,0.005343126,0.00043336977,0.000012276231],"category_scores_gemma":[0.0028448147,0.0006822058,0.00015070244,0.0003697803,0.00090285786,0.0006834713,0.0018241368,0.0014265386,0.000043889595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033398244,0.000024001998,0.0019227216,0.000034019096,0.000008110805,0.0001677299,0.00023401182,0.025212536,0.00009721011,0.00042347616,0.00007081826,0.971802],"study_design_scores_gemma":[0.00020873261,0.00019192854,0.0005427221,0.002145315,0.000012823265,0.00003955289,2.2733971e-8,0.631481,0.0019172848,0.36071664,0.0017807131,0.00096325396],"about_ca_topic_score_codex":0.00043553117,"about_ca_topic_score_gemma":0.00006197192,"teacher_disagreement_score":0.9708388,"about_ca_system_score_codex":0.0002840577,"about_ca_system_score_gemma":0.0011558414,"threshold_uncertainty_score":0.9995629},"labels":[],"label_agreement":null},{"id":"W2607146905","doi":"10.1002/smr.1868","title":"Extending Category Partition's <scp>B</scp>ase <scp>C</scp>hoice criterion to better support constraints","year":2017,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partition (number theory); Base (topology); Computer science; Set (abstract data type); Mathematical optimization; Mathematics; Combinatorics; Programming language","score_opus":0.025064019517953475,"score_gpt":0.30153339368785353,"score_spread":0.2764693741699001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607146905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2406752,0.00042698922,0.7558828,0.0006198185,0.0007458808,0.0001620645,0.000011770285,0.0010953582,0.00038014993],"genre_scores_gemma":[0.92277604,0.00003809172,0.07555138,0.0009861655,0.00035868614,0.00001499032,0.0000030331396,0.000022473781,0.0002491242],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99789894,0.000082299106,0.0005815859,0.00040281346,0.000562775,0.00047158537],"domain_scores_gemma":[0.99660313,0.00078509236,0.0008609723,0.0005056132,0.00081650657,0.00042870644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011948368,0.00026400376,0.00036545825,0.0003531067,0.0008195993,0.0007802215,0.001019877,0.00015510207,0.000008247791],"category_scores_gemma":[0.008016624,0.00024149033,0.00011245974,0.00021566845,0.00023132266,0.0017764344,0.00025074536,0.000409858,0.000025570407],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024784586,0.0004907125,0.4072035,0.0007941485,0.00015916346,0.00087301666,0.010184908,0.0001271174,0.001049537,0.001882096,0.4155387,0.16167232],"study_design_scores_gemma":[0.0040031294,0.003181976,0.6287723,0.0037285862,0.00029325543,0.010300967,0.0010791828,0.0050843754,0.00759147,0.27665028,0.058443934,0.00087054976],"about_ca_topic_score_codex":0.000024062869,"about_ca_topic_score_gemma":0.0000033685535,"teacher_disagreement_score":0.68210083,"about_ca_system_score_codex":0.00010156219,"about_ca_system_score_gemma":0.00029150266,"threshold_uncertainty_score":0.984769},"labels":[],"label_agreement":null},{"id":"W2607355777","doi":"","title":"Requirement-based Software Testing With the UML: A Systematic Mapping Study","year":2012,"lang":"en","type":"article","venue":"International Conference on Software Engineering Advances","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Software testing; Unified Modeling Language; Software engineering; Software performance testing; Applications of UML; Software; Reliability engineering; Programming language; Software development; Software construction; Engineering","score_opus":0.0600898824269571,"score_gpt":0.2875042514738007,"score_spread":0.22741436904684362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607355777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008386446,0.00026440778,0.9824914,0.0002606123,0.00070847716,0.0005340132,0.0000029169512,0.0072531477,0.00009861196],"genre_scores_gemma":[0.67805666,0.0000014233452,0.3213784,0.00014539668,0.000092988405,0.0002673932,0.0000022433603,0.000021452433,0.000034007426],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979626,0.00007813715,0.00034338536,0.00039312808,0.00079530285,0.0004274739],"domain_scores_gemma":[0.99722403,0.0014249897,0.00024147939,0.0006361225,0.0003683249,0.000105051375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007389257,0.00031089617,0.00027596403,0.00022644253,0.00019263935,0.00031693067,0.0013653781,0.000041078078,0.0000070095803],"category_scores_gemma":[0.0027821478,0.00021000825,0.000052011987,0.00047329438,0.000039806062,0.0007744153,0.00016229598,0.00027377685,0.000020700476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012513039,0.0028327357,0.71571887,0.0078107575,0.001065666,0.00028368583,0.011452853,0.10035802,0.00034287508,0.04434196,0.002439645,0.11322782],"study_design_scores_gemma":[0.0037390068,0.003075465,0.0761885,0.041671414,0.00023022144,0.00044377343,0.0014002632,0.8602283,0.0014663654,0.0037338056,0.0028379445,0.0049849446],"about_ca_topic_score_codex":0.000017840046,"about_ca_topic_score_gemma":0.0000024754108,"teacher_disagreement_score":0.7598703,"about_ca_system_score_codex":0.00012342651,"about_ca_system_score_gemma":0.00007287819,"threshold_uncertainty_score":0.85638875},"labels":[],"label_agreement":null},{"id":"W2611833875","doi":"","title":"Verification of Modular Systems with Unknown Components Combining Testing and Inference","year":2012,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Modular design; Computer science; Component (thermodynamics); TRACE (psycholinguistics); Reachability; Construct (python library); Model checking; Model-based testing; Isolation (microbiology); Inference; Theoretical computer science; Algorithm; Test case; Programming language; Artificial intelligence; Machine learning","score_opus":0.03582087525383267,"score_gpt":0.2392506539911267,"score_spread":0.203429778737294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611833875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14905405,0.0009572597,0.84395945,0.0004162662,0.00013972087,0.000369461,0.000009005349,0.0021509188,0.0029438878],"genre_scores_gemma":[0.66377383,0.000040046478,0.33598697,0.000009457902,0.000007011429,0.000042270585,0.000035714726,0.000018231021,0.0000864737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961038,0.0020193916,0.00049425906,0.00065480504,0.00043006314,0.0002976672],"domain_scores_gemma":[0.9916839,0.0031163096,0.00083705696,0.002143887,0.0020682989,0.00015052767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004017355,0.00029096208,0.00040371707,0.00019329056,0.00023593706,0.0004107835,0.0014133314,0.0001913719,0.0000013155134],"category_scores_gemma":[0.0024339156,0.00028502298,0.000047756253,0.0004250854,0.00022051958,0.00024960862,0.0015875807,0.0004557139,0.0000026950158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028271246,0.0020292832,0.28975457,0.0030327812,0.0003310435,0.000016211001,0.029837243,0.002742632,0.016285215,0.45954064,0.00053574523,0.19586639],"study_design_scores_gemma":[0.00059776445,0.000003057983,0.058992732,0.011967467,0.00007165281,0.000059331847,0.000024173021,0.8968625,0.013488014,0.016627615,0.00038410586,0.00092159706],"about_ca_topic_score_codex":0.0022890193,"about_ca_topic_score_gemma":0.000026020756,"teacher_disagreement_score":0.89411986,"about_ca_system_score_codex":0.00005980307,"about_ca_system_score_gemma":0.00016813955,"threshold_uncertainty_score":0.9999602},"labels":[],"label_agreement":null},{"id":"W2615727104","doi":"","title":"Successful Implementation of Protocol V","year":2006,"lang":"en","type":"article","venue":"JMU Scholoraly Commons (James Madison University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mine action; Protocol (science); Computer science; Computer network; Political science; Medicine; Law","score_opus":0.012324386388021514,"score_gpt":0.2732457354490791,"score_spread":0.2609213490610576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615727104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26864147,0.000042425232,0.6073199,0.003517136,0.00028225742,0.03784107,0.000052189487,0.020759743,0.061543804],"genre_scores_gemma":[0.91205966,9.4656787e-7,0.0867925,0.00006439399,0.00003833929,0.00039941183,0.000011399542,0.000014684065,0.0006186792],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887675,0.00011887824,0.00022901192,0.00031286333,0.00021792103,0.00024456822],"domain_scores_gemma":[0.9988582,0.00010124791,0.00024283196,0.0006043345,0.00013367635,0.00005971225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018814014,0.00014646768,0.0001888501,0.00048657876,0.00015732856,0.000091261725,0.0010759522,0.00006987634,0.000019923058],"category_scores_gemma":[0.000019110763,0.00015745574,0.000089846835,0.0010878679,0.00008346843,0.0007518644,0.00033999674,0.00015131808,0.000010346118],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044375236,0.00036370955,0.72837454,0.000064085856,0.00003122666,0.000100929785,0.0002971672,0.00007496302,0.0003865975,0.08829339,0.09727168,0.08469732],"study_design_scores_gemma":[0.005761871,0.0014437938,0.39223588,0.00024916045,0.00008844851,0.0000533261,0.00058008917,0.004560525,0.028289812,0.059512697,0.5055036,0.0017207912],"about_ca_topic_score_codex":0.0020859912,"about_ca_topic_score_gemma":0.00019852756,"teacher_disagreement_score":0.6434182,"about_ca_system_score_codex":0.000085028674,"about_ca_system_score_gemma":0.000082623315,"threshold_uncertainty_score":0.6420859},"labels":[],"label_agreement":null},{"id":"W2620742065","doi":"10.1109/icse-c.2017.6","title":"JSDeodorant: Class-Awareness for JavaScript Programs","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Namespace; JavaScript; Computer science; Programming language; Inheritance (genetic algorithm); Callback; Class (philosophy); Modular design; Eclipse; Unobtrusive JavaScript; Software engineering; Object-oriented programming; Object (grammar); Common Object Request Broker Architecture; World Wide Web; Operating system; Artificial intelligence; Rich Internet application","score_opus":0.09250601432181466,"score_gpt":0.3382746358746273,"score_spread":0.24576862155281265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620742065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019366902,0.000029686717,0.9776313,0.001369325,0.00049352495,0.00032557893,9.962259e-7,0.01298462,0.005228286],"genre_scores_gemma":[0.5307354,0.0000016360028,0.46788305,0.00024133705,0.000073352516,0.000119505865,0.000001925702,0.0000102821705,0.0009335372],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990268,0.000013638431,0.00014322443,0.00036493575,0.00015640899,0.00029502917],"domain_scores_gemma":[0.9980535,0.00010714069,0.000112483685,0.0015084102,0.00014321572,0.00007527063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037527026,0.00012224467,0.0001489206,0.000043791897,0.0006642804,0.0009078102,0.0018963848,0.00006484653,0.0000022671304],"category_scores_gemma":[0.0004077439,0.0000995137,0.00008302924,0.000051185296,0.00007204995,0.00048694553,0.0003266863,0.00006076402,0.000017655826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053075114,0.000082065126,0.0185381,0.00003266175,0.000012010509,0.0000074220916,0.0001351381,8.109192e-7,0.000044068664,0.06267519,0.055862226,0.862605],"study_design_scores_gemma":[0.0013693685,0.0006344358,0.011298553,0.00022412508,0.000021282696,0.00006408803,0.000007711094,0.24305639,0.0077514853,0.58434874,0.15020035,0.0010234924],"about_ca_topic_score_codex":0.00027522544,"about_ca_topic_score_gemma":0.000022691764,"teacher_disagreement_score":0.8615815,"about_ca_system_score_codex":0.000016808492,"about_ca_system_score_gemma":0.00005939657,"threshold_uncertainty_score":0.87540346},"labels":[],"label_agreement":null},{"id":"W270596444","doi":"10.1007/978-3-319-17040-4_14","title":"A Formal Approach to Verify Completeness and Detect Anomalies in Firewall Security Policies","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Security policy; Automaton; Firewall (physics); Completeness (order theory); Computer security model; Computer security; Formalism (music); Formal methods; Theoretical computer science; Software engineering; Spacetime","score_opus":0.03820750955614092,"score_gpt":0.26836447362602334,"score_spread":0.23015696406988242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W270596444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021113106,0.00065179565,0.99240416,0.0002944826,0.00035090328,0.00046136463,0.0000072726734,0.001542142,0.0021765379],"genre_scores_gemma":[0.5293907,0.000011816097,0.46947688,0.00091424305,0.00013007496,0.00002257909,0.000002679367,0.000024783529,0.000026256259],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649024,0.000050555285,0.0004771203,0.0013608838,0.00078473054,0.00083647243],"domain_scores_gemma":[0.99774253,0.0004761128,0.00016952942,0.0011314807,0.00021990543,0.000260449],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014750382,0.0005417508,0.0006563461,0.0011438314,0.00020327639,0.0005834954,0.0026041728,0.00030955704,9.898341e-7],"category_scores_gemma":[0.00030038407,0.000501499,0.00006490828,0.0008079962,0.00057456107,0.0006099581,0.0027282748,0.0006904649,0.000005429388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000326001,0.00009965027,0.0025149176,0.0002606327,0.00001454123,0.00012141366,0.019730717,0.0076596015,0.000039668288,0.018128647,0.00047687296,0.95092076],"study_design_scores_gemma":[0.0002967579,0.00034144917,0.0015707327,0.00050954573,0.000004701273,0.00025249558,3.6161927e-7,0.46254537,0.0001695517,0.53230184,0.0010682131,0.00093895284],"about_ca_topic_score_codex":0.00038380057,"about_ca_topic_score_gemma":0.00015043996,"teacher_disagreement_score":0.9499818,"about_ca_system_score_codex":0.00029184058,"about_ca_system_score_gemma":0.00038219104,"threshold_uncertainty_score":0.99974364},"labels":[],"label_agreement":null},{"id":"W2733241474","doi":"10.5555/3105427.3105430","title":"Searching for behavioural bugs with stateful test oracles in web crawlers","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Stateful firewall; Computer science; Crawling; Web crawler; World Wide Web; Web application; Software engineering; Computer security","score_opus":0.0564857498765327,"score_gpt":0.3196836482819782,"score_spread":0.2631978984054455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733241474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5136449,0.00001703727,0.47157678,0.0033036342,0.00010674585,0.0004953309,0.000006903643,0.008491044,0.0023576277],"genre_scores_gemma":[0.64349884,9.586644e-7,0.35621294,0.000070265145,0.000010612879,0.000027656339,8.313291e-7,0.000007825175,0.0001700961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991189,0.00001529175,0.00012182059,0.0002891167,0.00015863452,0.00029619472],"domain_scores_gemma":[0.99863446,0.00044529524,0.000080458354,0.0006961358,0.00008391929,0.000059725597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041374494,0.000106400425,0.000118360054,0.00009943892,0.0003213676,0.0005615539,0.0010137412,0.00003190397,0.0000017503619],"category_scores_gemma":[0.00060434954,0.00008032464,0.00002239553,0.00007908911,0.00007792509,0.00053216575,0.00022591744,0.00011472939,0.0000042712836],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013716335,0.00011172394,0.9153178,0.000025407924,0.0000047201474,0.000050761624,0.0005680968,0.000016270867,0.0003010058,0.0035236888,0.0049634194,0.07510339],"study_design_scores_gemma":[0.0025790033,0.0015159977,0.60310054,0.00060081284,0.000015329102,0.00010911614,0.00006883348,0.31039596,0.009255712,0.06963693,0.0014815655,0.0012402181],"about_ca_topic_score_codex":0.0010855816,"about_ca_topic_score_gemma":0.00050119247,"teacher_disagreement_score":0.31221727,"about_ca_system_score_codex":0.00003092464,"about_ca_system_score_gemma":0.00010624362,"threshold_uncertainty_score":0.5415078},"labels":[],"label_agreement":null},{"id":"W2733392061","doi":"10.5555/3105427.3105436","title":"JTeXpert at the SBST 2017 tool competition","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Test suite; Unit testing; Suite; CONTEST; Computer science; Java; Programming language; Software; Code (set theory); Competition (biology); Software testing; Source code; Test (biology); Test case; Artificial intelligence; Software engineering; Set (abstract data type); Machine learning","score_opus":0.040837899822264774,"score_gpt":0.29927517210164556,"score_spread":0.2584372722793808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733392061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016270153,0.0001284807,0.8337937,0.015128564,0.0008246846,0.00022727439,0.0000017008314,0.01349475,0.120130695],"genre_scores_gemma":[0.9123426,0.000011531668,0.07996479,0.0013346864,0.00009519191,0.000022401955,0.000001278712,0.0000058347136,0.0062217056],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939144,0.000021792319,0.000087216344,0.00020070726,0.0001534961,0.00014536496],"domain_scores_gemma":[0.9980389,0.00014461472,0.0000803223,0.0016641992,0.00004491755,0.000027035188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026872545,0.00007395589,0.00006671012,0.000017819491,0.0010770524,0.00047962947,0.0014726667,0.00003136805,0.000040987266],"category_scores_gemma":[0.0002739489,0.000045021687,0.000038982347,0.000024280069,0.00009832374,0.00028477365,0.0006571814,0.00006120744,0.00024652347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029495359,0.000034857967,0.0089817075,0.00000565066,0.000007555218,0.000014985815,0.00031224737,0.0000028492195,0.00040874432,0.10825205,0.81558055,0.06639585],"study_design_scores_gemma":[0.0008715911,0.00027946528,0.2652351,0.00022142514,0.000013407725,0.0003576297,0.000012840958,0.0860344,0.024440084,0.33782014,0.283441,0.0012729036],"about_ca_topic_score_codex":0.00023163366,"about_ca_topic_score_gemma":0.000032192223,"teacher_disagreement_score":0.89607245,"about_ca_system_score_codex":0.000026855496,"about_ca_system_score_gemma":0.000016703887,"threshold_uncertainty_score":0.82839257},"labels":[],"label_agreement":null},{"id":"W2733860488","doi":"","title":"Expected time to detection of interaction faults","year":2013,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Econometrics; Statistics","score_opus":0.012411871599337737,"score_gpt":0.2533188563413243,"score_spread":0.24090698474198655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733860488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7303887,0.000053312502,0.26168364,0.00016653717,0.006339225,0.0003483408,3.3345137e-7,0.0005925913,0.000427333],"genre_scores_gemma":[0.9381013,0.0000019008107,0.061473276,0.00002024294,0.0003787521,0.0000030327344,1.7140573e-7,0.000015597214,0.0000057537763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807286,0.00009131117,0.0009323208,0.0001868971,0.0004969385,0.00021966686],"domain_scores_gemma":[0.99676645,0.00083334005,0.0009821292,0.00029652033,0.00095309387,0.00016848926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008477231,0.00019339207,0.00052051607,0.0003274785,0.00012550528,0.00017956685,0.00057106063,0.00010642842,0.0000072500693],"category_scores_gemma":[0.0011444127,0.00017288313,0.00011565986,0.0004789551,0.000030835516,0.0004526368,0.00029917705,0.00027836426,0.000017104483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034623008,0.004524646,0.00080575474,0.0009829703,0.0006457519,0.00006782954,0.018515788,0.00032803445,0.20024121,0.44895512,0.013588163,0.31099853],"study_design_scores_gemma":[0.0020419979,0.0024132552,0.00046116172,0.00080066005,0.000042724114,0.00024310335,0.00008284039,0.06444595,0.029560925,0.8991741,0.0003019649,0.00043132526],"about_ca_topic_score_codex":0.000028775143,"about_ca_topic_score_gemma":6.4520506e-8,"teacher_disagreement_score":0.45021898,"about_ca_system_score_codex":0.00007021004,"about_ca_system_score_gemma":0.000057159665,"threshold_uncertainty_score":0.7049969},"labels":[],"label_agreement":null},{"id":"W2736040703","doi":"10.1145/3092703.3098229","title":"SealTest: a simple library for test sequence generation","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Simple (philosophy); Computer science; Sequence (biology); Test (biology); Chemistry","score_opus":0.11375339780369222,"score_gpt":0.3372430159476951,"score_spread":0.22348961814400292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736040703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030140216,0.000015640691,0.9792137,0.0031057484,0.00012751405,0.00019550753,0.000008392706,0.011550889,0.0027685864],"genre_scores_gemma":[0.4483712,0.000002415581,0.5501793,0.0006949714,0.00013038638,0.000041005453,0.000007316773,0.0000073524775,0.00056605285],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993709,0.000008933375,0.00010432811,0.00026042762,0.000085963555,0.00016949006],"domain_scores_gemma":[0.9985761,0.00030734346,0.000086458094,0.00092884287,0.00004342668,0.00005780376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014697679,0.00007784703,0.000075232376,0.000032669308,0.0005145338,0.0007724975,0.001019126,0.000037099093,0.0000064280157],"category_scores_gemma":[0.0009562595,0.000067401255,0.000032408007,0.00004278612,0.00003261841,0.001124994,0.00024433108,0.00003058754,0.000012256371],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011096098,0.000059772057,0.04991463,0.00002363413,0.0000043302393,0.000008561647,0.000102846236,0.000008119121,0.0033468958,0.047284964,0.7378718,0.16137332],"study_design_scores_gemma":[0.00019478895,0.00021084626,0.00505944,0.000021159914,0.0000030002989,0.000022756174,5.373702e-7,0.7088249,0.028346438,0.2420855,0.014958827,0.0002718308],"about_ca_topic_score_codex":0.000038710834,"about_ca_topic_score_gemma":0.000004599494,"teacher_disagreement_score":0.722913,"about_ca_system_score_codex":0.000009102643,"about_ca_system_score_gemma":0.00007369274,"threshold_uncertainty_score":0.7449211},"labels":[],"label_agreement":null},{"id":"W2740565296","doi":"10.1145/3106237.3106258","title":"QTEP: quality-aware test case prioritization","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code coverage; Computer science; Source code; Software quality; Leverage (statistics); Test case; Test suite; Code (set theory); Code review; Reliability engineering; Software; Programming language; Software development; Set (abstract data type); Engineering","score_opus":0.05778218964391741,"score_gpt":0.36462649522235946,"score_spread":0.30684430557844206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740565296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005114618,0.000013023208,0.974626,0.0011101334,0.00017626352,0.00008714039,0.0000018508837,0.011716772,0.0071541755],"genre_scores_gemma":[0.80005306,0.0000017314325,0.19903837,0.00023224279,0.000051283274,0.0000068118625,8.4498123e-7,0.0000053122753,0.00061035494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99927455,0.00002598515,0.00014710386,0.00025740467,0.00013989244,0.00015508223],"domain_scores_gemma":[0.99809384,0.00032991942,0.000116923205,0.0012813387,0.000114325725,0.00006364595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037010037,0.000083991785,0.00009245145,0.000041956726,0.00060009945,0.0005996401,0.00077114586,0.000047682475,0.000007692422],"category_scores_gemma":[0.0017101826,0.00007482505,0.000029437511,0.000059325706,0.000042399475,0.0005019312,0.00031445108,0.000070278875,0.000037419442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023299983,0.00025285484,0.28386286,0.00007535436,0.000012975894,0.0027158149,0.0007862179,0.0000044161497,0.00021438322,0.1013431,0.10519856,0.50553113],"study_design_scores_gemma":[0.0016653358,0.00064215803,0.18896995,0.00037958173,0.000027637363,0.010542865,0.000054135595,0.26211855,0.012663724,0.5090991,0.011285616,0.002551315],"about_ca_topic_score_codex":0.0008512137,"about_ca_topic_score_gemma":0.00004984654,"teacher_disagreement_score":0.79493845,"about_ca_system_score_codex":0.000019207744,"about_ca_system_score_gemma":0.000035930134,"threshold_uncertainty_score":0.5782343},"labels":[],"label_agreement":null},{"id":"W2741328617","doi":"10.1145/3106237.3106274","title":"Better test cases for better automated program repair","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Metric (unit); Artificial intelligence; Benchmark (surveying); Test (biology); Machine learning; Software bug; Pattern recognition (psychology); Data mining; Software; Programming language; Engineering","score_opus":0.044205879285435255,"score_gpt":0.34301408199295436,"score_spread":0.2988082027075191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741328617","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020127796,0.000024739858,0.111760005,0.009821402,0.00045345153,0.0011496987,0.00000896188,0.8526846,0.003969321],"genre_scores_gemma":[0.14643033,3.479909e-7,0.8512427,0.0015764808,0.00009914507,0.00021937993,0.000002456325,0.000012934085,0.00041618888],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900126,0.0000126894065,0.00016754013,0.0003815381,0.00013280605,0.0003041333],"domain_scores_gemma":[0.99769896,0.00059602666,0.00011268107,0.0014086489,0.000116263334,0.00006740628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025076198,0.00013628707,0.00013780654,0.000053961463,0.0004880643,0.00059112016,0.0010160946,0.0000678399,0.0000053711087],"category_scores_gemma":[0.0015682994,0.000108317676,0.00010211466,0.00005320075,0.000073516065,0.00039187958,0.00030479726,0.00006688286,0.000026346495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012808165,0.00009917173,0.058227345,0.000018405959,0.000008991991,0.000044923505,0.000028616787,1.6752048e-7,0.000014537459,0.00022226527,0.84454554,0.09678876],"study_design_scores_gemma":[0.00033480066,0.0006621883,0.050580416,0.000078988756,0.000013251267,0.0001397533,6.7321366e-7,0.9022577,0.0012567213,0.016150698,0.028102625,0.00042218034],"about_ca_topic_score_codex":0.00015654947,"about_ca_topic_score_gemma":0.000010379369,"teacher_disagreement_score":0.90225756,"about_ca_system_score_codex":0.000016742262,"about_ca_system_score_gemma":0.000028910697,"threshold_uncertainty_score":0.57001853},"labels":[],"label_agreement":null},{"id":"W2747184587","doi":"10.1016/bs.adcom.2017.06.002","title":"Testing the Control-Flow, Data-Flow, and Time Aspects of Communication Systems: A Survey","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Extended finite-state machine; Computer science; Conformance testing; Finite-state machine; Standardization; Data flow diagram; Software; Deterministic finite automaton; Database; Programming language; Operating system","score_opus":0.05862950462809106,"score_gpt":0.29601633582158937,"score_spread":0.23738683119349832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747184587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015807353,0.036302965,0.86966515,0.00041354293,0.0011259655,0.001258788,0.000280067,0.0032459663,0.08769173],"genre_scores_gemma":[0.10465187,0.0019968725,0.89036626,0.00033972747,0.00023921928,0.00004138477,0.0002764362,0.00011117842,0.0019770814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981174,0.00021966237,0.0005106474,0.0006159828,0.00031351205,0.00022281373],"domain_scores_gemma":[0.98826504,0.0068295305,0.00086783565,0.0037746562,0.0002140061,0.000048951293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020616944,0.000302969,0.0005826429,0.00014588133,0.00022700847,0.0002616249,0.004382195,0.00013704189,7.23328e-7],"category_scores_gemma":[0.001007807,0.00024584774,0.0000351747,0.00006024609,0.00037072896,0.00069437583,0.0016790879,0.0003963892,0.0000056437593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037864906,0.00006865212,0.0036549924,0.000359603,0.00018009401,0.00008111726,0.0004763133,0.01274713,0.0000037715315,0.0852486,0.014911215,0.88223064],"study_design_scores_gemma":[0.0003140483,0.000096268224,0.0012056183,0.0022838195,0.000020099891,0.000056565907,5.489009e-7,0.90350765,5.975947e-7,0.08190032,0.0102616185,0.00035286008],"about_ca_topic_score_codex":0.0003250851,"about_ca_topic_score_gemma":0.00007191107,"teacher_disagreement_score":0.8907605,"about_ca_system_score_codex":0.000046818473,"about_ca_system_score_gemma":0.00010471185,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W2754010186","doi":"10.1109/compsac.2017.138","title":"How Does GUI Testing Exercise Application Logic Functionality?","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Programming language; Graphical user interface; Graphical user interface testing; Keyword-driven testing; Regression testing; Code coverage; Software; White-box testing; Software engineering; User interface; Software system; Software construction; User interface design","score_opus":0.05614546730983575,"score_gpt":0.28686183270118853,"score_spread":0.2307163653913528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754010186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007988733,0.000021447464,0.9780654,0.0043304004,0.00017730602,0.00012751672,5.3457717e-7,0.010320436,0.0061580944],"genre_scores_gemma":[0.5395921,0.0000013833717,0.4590941,0.00017393511,0.00006829669,0.000042090465,8.373368e-7,0.0000041400867,0.0010230936],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991821,0.000013299179,0.00010002713,0.00035364064,0.0001838873,0.00016706664],"domain_scores_gemma":[0.998055,0.0002276218,0.00015235637,0.0013452742,0.0001650032,0.000054780074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032144482,0.00009976814,0.00009941902,0.000041832332,0.00057984947,0.00093744276,0.0011317756,0.000048788144,0.0000027338715],"category_scores_gemma":[0.0014098794,0.00006797851,0.00003189363,0.0000845557,0.000058191268,0.000604409,0.00036461945,0.00007336736,0.000024785704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022009328,0.00006247681,0.07124065,0.000027832046,0.0000053918297,0.000006420878,0.00005693768,0.0000064824935,0.0005634398,0.08675423,0.016317401,0.82495654],"study_design_scores_gemma":[0.0001227231,0.000040720508,0.048783638,0.000061014485,0.0000066636385,0.000017916103,0.000004212931,0.05398852,0.0021688761,0.89169234,0.0028267873,0.00028660736],"about_ca_topic_score_codex":0.00021637874,"about_ca_topic_score_gemma":0.0000055287037,"teacher_disagreement_score":0.82466996,"about_ca_system_score_codex":0.00001979388,"about_ca_system_score_gemma":0.000025802467,"threshold_uncertainty_score":0.9039782},"labels":[],"label_agreement":null},{"id":"W2755609451","doi":"10.1109/compsac.2017.221","title":"State-Based Tests Suites Automatic Generation Tool (STAGE-1)","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Test suite; Tree traversal; Graph traversal; Automation; Test case; Random testing; Code coverage; Model-based testing; Test Management Approach; Graph; Test (biology); Finite-state machine; State (computer science); Keyword-driven testing; Software; Theoretical computer science; Programming language; Machine learning; Software system; Software construction; Engineering","score_opus":0.04925087200966932,"score_gpt":0.3073691148616308,"score_spread":0.2581182428519615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755609451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1464861,0.000012612012,0.83790827,0.0007895499,0.00018720972,0.00013505045,0.0000012857462,0.013554219,0.0009256961],"genre_scores_gemma":[0.5937945,4.7781947e-7,0.40511408,0.00033900863,0.000028884246,0.000015694979,0.0000016174708,0.00000569823,0.0007000073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991258,0.000031477943,0.00016453835,0.00027403366,0.00020433463,0.00019983143],"domain_scores_gemma":[0.99813676,0.00027416646,0.00013483879,0.0013168717,0.00008814356,0.000049234048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036322663,0.00011212601,0.0001058571,0.00006969449,0.00043612867,0.0010095827,0.00097506726,0.00003532502,0.000024811312],"category_scores_gemma":[0.0013478177,0.00009406506,0.000035691755,0.000063168496,0.000043449454,0.0005193193,0.00016555344,0.00006235309,0.000056090863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002061168,0.00018013023,0.1629685,0.000071826384,0.000016718664,0.00006877686,0.00027999515,0.00034350486,0.0041384706,0.013027897,0.11164798,0.7072541],"study_design_scores_gemma":[0.00016023929,0.00007176212,0.039720424,0.000027948076,0.0000020502002,0.0000035100907,2.5330118e-7,0.93639594,0.014145258,0.008843555,0.0004268618,0.00020219135],"about_ca_topic_score_codex":0.00021507112,"about_ca_topic_score_gemma":0.000030693365,"teacher_disagreement_score":0.93605244,"about_ca_system_score_codex":0.000028007162,"about_ca_system_score_gemma":0.00009533203,"threshold_uncertainty_score":0.9735429},"labels":[],"label_agreement":null},{"id":"W2756297985","doi":"10.1007/978-3-319-67549-7_1","title":"Fragility-Oriented Testing with Model Execution and Reinforcement Learning","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Fragility; Reinforcement learning; Computer science; Reinforcement; Stress testing (software); Artificial intelligence; Engineering; Operating system; Structural engineering","score_opus":0.02738793666073401,"score_gpt":0.2561419108886857,"score_spread":0.22875397422795168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756297985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014526381,0.00011537572,0.99340844,0.00017146755,0.00019620243,0.0002751556,5.3579964e-7,0.0022964915,0.0033910768],"genre_scores_gemma":[0.33712578,0.000009243464,0.66225374,0.00022575795,0.00007759874,0.000008737505,0.0000022226,0.000020416905,0.00027650007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970455,0.000021601563,0.0003389196,0.001309072,0.00076714787,0.0005177149],"domain_scores_gemma":[0.99725854,0.00052800967,0.000414188,0.0012958854,0.00035715252,0.00014622066],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009920612,0.000441553,0.00039136037,0.00046489414,0.00077797694,0.00065067236,0.0015740861,0.00020933384,0.0000010366533],"category_scores_gemma":[0.0006910508,0.00037551677,0.00003972461,0.00020161005,0.0007136731,0.0006208598,0.0013230311,0.0008881683,0.0000028619386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007951231,0.000011683498,0.0012391824,0.000054687516,0.000007691666,0.000058349426,0.00077981746,0.3378693,0.00003597067,0.0060620653,0.00001828109,0.653855],"study_design_scores_gemma":[0.0001394432,0.00025211571,0.0001234307,0.0007870019,0.000006047778,0.00008201097,2.9769508e-8,0.8520257,0.00015073338,0.14592917,0.00009994812,0.00040436417],"about_ca_topic_score_codex":0.00007290976,"about_ca_topic_score_gemma":0.000012035928,"teacher_disagreement_score":0.65345067,"about_ca_system_score_codex":0.00018958193,"about_ca_system_score_gemma":0.00041565913,"threshold_uncertainty_score":0.9998697},"labels":[],"label_agreement":null},{"id":"W2760129307","doi":"10.1007/978-0-387-35516-0_20","title":"Erratum to: Testing of Communicating Systems","year":2017,"lang":"en","type":"erratum","venue":"IFIP advances in information and communication technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Library science; World Wide Web","score_opus":0.022167174185329402,"score_gpt":0.3033675095037852,"score_spread":0.2812003353184558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760129307","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021209777,0.13474773,0.34353387,0.006810871,0.009538965,0.0027225595,0.000054704604,0.020304905,0.4820743],"genre_scores_gemma":[0.15063517,0.02333469,0.8226654,0.00045826446,0.000057929457,0.0007433317,0.00018526451,0.000043597607,0.0018763487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981732,0.00011491394,0.0009912121,0.00022187598,0.00023658584,0.00026221888],"domain_scores_gemma":[0.99352413,0.00047762765,0.0015598569,0.003908362,0.000480302,0.000049708924],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008860821,0.0002483707,0.00050786865,0.0011935456,0.00036179504,0.00025867665,0.0047971094,0.00052743184,4.6799764e-7],"category_scores_gemma":[0.003406477,0.00026219685,0.00003079132,0.0008375553,0.00029919395,0.0018657505,0.0022969123,0.0011336813,0.000008511686],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004602304,0.000041059437,0.0019038373,0.0005237927,0.000012015858,9.171254e-7,0.001123056,0.00014428807,0.0000031154743,0.09695145,0.094680235,0.8046116],"study_design_scores_gemma":[0.00026944303,0.00016084724,0.00025933774,0.0038221614,0.000007697124,0.000059075082,0.00021263145,0.035047606,0.000044037675,0.10791476,0.8516849,0.00051744835],"about_ca_topic_score_codex":0.00021516676,"about_ca_topic_score_gemma":0.000040412666,"teacher_disagreement_score":0.8040942,"about_ca_system_score_codex":0.00008418751,"about_ca_system_score_gemma":0.00015919069,"threshold_uncertainty_score":0.999983},"labels":[],"label_agreement":null},{"id":"W2760492644","doi":"10.1080/10556788.2019.1692344","title":"mts: a light framework for parallelizing tree search codes","year":2019,"lang":"en","type":"preprint","venue":"Optimization methods & software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Japan Society for the Promotion of Science","keywords":"Computer science; Backtracking; Enumeration; Satisfiability; Debugging; Search tree; Parallel computing; Vertex (graph theory); Theoretical computer science; Branch and bound; Search algorithm; Algorithm; Graph; Programming language; Discrete mathematics; Mathematics","score_opus":0.0714005721263264,"score_gpt":0.40162440456002696,"score_spread":0.33022383243370057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760492644","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000065440936,0.0011729297,0.97879916,0.0010560013,0.00140877,0.0013988055,0.000033238168,0.01593336,0.00019119073],"genre_scores_gemma":[0.00014890256,0.00018782943,0.9976665,0.00062854233,0.0002687142,0.0005451979,0.00014218176,0.00012000469,0.00029217824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956126,0.0008915589,0.0007199845,0.0015536926,0.0005376637,0.0006844703],"domain_scores_gemma":[0.99031436,0.005696697,0.00051333604,0.0024356202,0.00084869494,0.0001913066],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029953076,0.000606189,0.0008696755,0.00043527217,0.00033880217,0.0008831605,0.0024766629,0.00095633004,0.000026139956],"category_scores_gemma":[0.008078913,0.0006074924,0.00038196545,0.0006342307,0.0000617115,0.00031934687,0.0020697438,0.0010568228,0.000013792391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002637981,0.000092261704,0.0009452505,0.00066654163,0.000103159386,0.0000056015842,0.0013005967,0.7556555,0.000006975278,0.0075377338,0.009641236,0.22401875],"study_design_scores_gemma":[0.00022339246,0.000102547216,0.000043639102,0.0009603516,0.00005097028,0.000009673669,0.000009206802,0.7527859,0.0005723734,0.24270868,0.0017823374,0.00075088674],"about_ca_topic_score_codex":0.0000339855,"about_ca_topic_score_gemma":8.9539867e-7,"teacher_disagreement_score":0.23517096,"about_ca_system_score_codex":0.0001883518,"about_ca_system_score_gemma":0.0004910196,"threshold_uncertainty_score":0.99963766},"labels":[],"label_agreement":null},{"id":"W2767601065","doi":"10.1109/icsme.2017.21","title":"SimPact: Impact Analysis for Simulink Models","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; General Motors of Canada","keywords":"Computer science; Process (computing); Set (abstract data type); Reliability engineering; Model-based testing; Software engineering; Test case; Machine learning; Engineering; Programming language","score_opus":0.08757853160803547,"score_gpt":0.37799711569846617,"score_spread":0.2904185840904307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767601065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040459377,0.000015413054,0.9870587,0.00047694167,0.000047512804,0.00011143035,0.0000046394484,0.005531912,0.002707518],"genre_scores_gemma":[0.678174,0.0000012309076,0.32146063,0.00012509817,0.000027398017,0.00000953587,0.0000014912614,0.0000047909048,0.00019580599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991671,0.00001093958,0.0001314569,0.0002951675,0.00013592567,0.00025941533],"domain_scores_gemma":[0.9976948,0.00032521962,0.00012394118,0.0016305761,0.00011668681,0.00010878225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036161792,0.00011679218,0.0002013014,0.0001511061,0.0004031532,0.0006672248,0.0014415977,0.000052877516,0.000009227217],"category_scores_gemma":[0.0005322748,0.000086151675,0.00028090356,0.00016429783,0.00003057141,0.0007172724,0.00022390511,0.000051563424,0.0000074331197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048897306,0.00036027317,0.24015959,0.00004442242,0.0020822803,0.000031462954,0.0014931853,0.16301848,0.000120775454,0.08939412,0.1440756,0.3591709],"study_design_scores_gemma":[0.00008552447,0.00005588266,0.0057437406,0.0000033789033,0.000034309993,0.0000010173578,3.0614612e-7,0.7858643,0.00013717952,0.20790733,0.000058044145,0.00010896254],"about_ca_topic_score_codex":0.00039176937,"about_ca_topic_score_gemma":0.000011831028,"teacher_disagreement_score":0.67412806,"about_ca_system_score_codex":0.000029709827,"about_ca_system_score_gemma":0.000045876684,"threshold_uncertainty_score":0.6434064},"labels":[],"label_agreement":null},{"id":"W2768693575","doi":"10.1109/issre.2017.34","title":"On FSM-Based Testing: An Empirical Study: Complete Round-Trip Versus Transition Trees","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Transition (genetics); Software testing; Empirical research; Programming language; Statistics; Mathematics; Chemistry; Software","score_opus":0.1997591464537318,"score_gpt":0.38378440311105216,"score_spread":0.18402525665732036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768693575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37999514,0.0000030293922,0.60121495,0.0014604083,0.00033922322,0.00030283644,0.0000026906444,0.01331173,0.0033699644],"genre_scores_gemma":[0.8563579,6.094094e-8,0.14299567,0.0005252135,0.00006271658,0.00002075197,0.000003009642,0.000011848039,0.000022865748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845266,0.00012928103,0.00020153202,0.0005526505,0.00038630978,0.00027757284],"domain_scores_gemma":[0.99699825,0.0009958693,0.00011817939,0.0016323065,0.00012234497,0.00013306478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004889932,0.0001921323,0.00020259572,0.000119543605,0.00077168655,0.000763782,0.0013760974,0.00006298064,0.000007557111],"category_scores_gemma":[0.0009165776,0.00016453653,0.00005690837,0.0001552548,0.00007878526,0.00045209183,0.00009500064,0.00016729756,0.0000287086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015209215,0.013600413,0.4217429,0.00007359738,0.00019217769,0.0010011044,0.0069793137,0.004272912,0.0010251343,0.012152555,0.07031486,0.4671241],"study_design_scores_gemma":[0.0035055273,0.008716818,0.27888846,0.00007433582,0.000030391579,0.000011475037,0.000025286608,0.6830477,0.0003570487,0.024423005,0.0002451217,0.0006747802],"about_ca_topic_score_codex":0.00064385775,"about_ca_topic_score_gemma":0.00013001818,"teacher_disagreement_score":0.67877483,"about_ca_system_score_codex":0.000054879903,"about_ca_system_score_gemma":0.00007757116,"threshold_uncertainty_score":0.7365168},"labels":[],"label_agreement":null},{"id":"W2770530563","doi":"10.1109/issrew.2017.51","title":"Finite State Machine Testing Complete Round-Trip Versus Transition Trees: On the Road of Finding the Most Effective Criterion","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Tree traversal; Finite-state machine; Computer science; Graph traversal; Cover (algebra); Tree (set theory); Random testing; Algorithm; Transition (genetics); Test case; Mathematics; Machine learning; Engineering","score_opus":0.08251322982207974,"score_gpt":0.3089630976320257,"score_spread":0.22644986780994592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770530563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15036641,0.000044812532,0.836463,0.0039114556,0.0004947545,0.00074382545,0.000027292117,0.0031264701,0.004821998],"genre_scores_gemma":[0.9811038,0.0000028439615,0.018456938,0.00031942077,0.000037498754,0.000033601536,0.0000026119972,0.000010531815,0.000032777156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879855,0.00019823309,0.00021536543,0.00028874792,0.00027242952,0.00022667619],"domain_scores_gemma":[0.99370444,0.0048272093,0.0002535288,0.0010610991,0.00012067067,0.00003305025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00098434,0.00016589843,0.0001699896,0.000069435635,0.0010910818,0.00042158176,0.0011861682,0.00003526437,0.000004166253],"category_scores_gemma":[0.0022899641,0.000092361974,0.00006619264,0.00020715583,0.00014489479,0.00029811752,0.00018287009,0.0002191587,0.000008017218],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003349643,0.00021528939,0.003121342,0.00006790267,0.00012270796,0.000056896723,0.007923548,0.0027878336,0.0033745463,0.008349112,0.0030948948,0.97055095],"study_design_scores_gemma":[0.000891181,0.0011460066,0.039062485,0.00040649163,0.000024790037,0.000019251218,0.000027756607,0.934623,0.0036314712,0.019740622,0.00012641327,0.00030055552],"about_ca_topic_score_codex":0.0019720776,"about_ca_topic_score_gemma":0.000078840414,"teacher_disagreement_score":0.9702504,"about_ca_system_score_codex":0.00004302086,"about_ca_system_score_gemma":0.000025169442,"threshold_uncertainty_score":0.839183},"labels":[],"label_agreement":null},{"id":"W2787734695","doi":"10.22215/etd/2017-12062","title":"Towards Efficient Instrumentation for Reverse-Engineering Object Oriented Software through Static and Dynamic Analyses","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Instrumentation (computer programming); Computer science; Static analysis; Overhead (engineering); Reverse engineering; Source code; C dynamic memory allocation; Software; Dynamic program analysis; Static program analysis; Context (archaeology); Program analysis; Software development; Programming language; Memory management","score_opus":0.03285469019548842,"score_gpt":0.35459371719772287,"score_spread":0.32173902700223445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787734695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017695451,0.00020361715,0.9750242,0.000058301892,0.0008082882,0.00059842446,0.00002329433,0.005267963,0.00032041964],"genre_scores_gemma":[0.09790554,0.000051160623,0.9000185,0.00007729374,0.000027354752,0.00018651912,0.0005197768,0.000046551653,0.0011673234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839264,0.000022937938,0.0003397272,0.0006291157,0.00031664266,0.00029892547],"domain_scores_gemma":[0.99842465,0.00027569174,0.0003433114,0.00065485126,0.00023730734,0.000064193926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022434362,0.0003391749,0.000377569,0.00023419815,0.000308223,0.0003602471,0.00053872215,0.00017195965,0.000004157985],"category_scores_gemma":[0.0011807546,0.00031444675,0.00011051702,0.00019560757,0.000023634057,0.00032008585,0.00006775035,0.00016928201,0.0000023086027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016321625,0.00042407872,0.00090386707,0.007069264,0.00091536186,0.00005732966,0.019740641,0.0055126618,0.0017219436,0.012765019,0.025280923,0.9254457],"study_design_scores_gemma":[0.001338622,0.00059974816,0.007704377,0.0022663076,0.00034829727,0.00003646109,0.00033434885,0.954794,0.007119598,0.022264604,0.0013742174,0.0018194022],"about_ca_topic_score_codex":0.0004054269,"about_ca_topic_score_gemma":0.000046126752,"teacher_disagreement_score":0.94928133,"about_ca_system_score_codex":0.00012437117,"about_ca_system_score_gemma":0.00017834225,"threshold_uncertainty_score":0.99993074},"labels":[],"label_agreement":null},{"id":"W2790194976","doi":"10.1016/bs.adcom.2018.01.001","title":"Model-Based Test Cases Reuse and Optimization","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reuse; Reusability; Computer science; Redundancy (engineering); Test case; Reliability engineering; Model-based testing; Test (biology); Regression testing; Test Management Approach; Engineering; Machine learning; Software; Programming language; Software development; Software construction","score_opus":0.026656270361618307,"score_gpt":0.2734850027060155,"score_spread":0.2468287323443972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790194976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000061022906,0.0013955646,0.98802763,0.00015128603,0.00030186557,0.00016646484,0.0000071130885,0.0031582152,0.0067857653],"genre_scores_gemma":[0.0018372093,0.00047351507,0.99528563,0.00059848925,0.000088423076,0.000010898044,0.000012082549,0.000035538338,0.0016581927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986219,0.000014311327,0.00029117614,0.00064858445,0.00020883491,0.00021518981],"domain_scores_gemma":[0.99749225,0.0011438475,0.0002019495,0.0009857265,0.00010322719,0.000073013165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001629083,0.00030297096,0.00029276375,0.00029177518,0.000082157014,0.00011874645,0.0009754077,0.00015901568,0.000004394045],"category_scores_gemma":[0.00028876704,0.00031346138,0.000045492794,0.000081529324,0.00017655439,0.00044147437,0.00047060938,0.00020324193,0.000005269451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001552469,0.000071282004,0.000448973,0.000197474,0.0000134835645,0.00031679566,0.00033506934,0.80175304,8.957081e-7,0.017100409,0.024832446,0.1549146],"study_design_scores_gemma":[0.00014189411,0.00016418169,0.0000022161732,0.0005921763,0.0000051837355,0.00003533555,1.5565213e-7,0.881283,0.00000722121,0.111667074,0.0057761297,0.0003254441],"about_ca_topic_score_codex":0.0000056005238,"about_ca_topic_score_gemma":0.0000075238418,"teacher_disagreement_score":0.15458916,"about_ca_system_score_codex":0.000075685966,"about_ca_system_score_gemma":0.00008160581,"threshold_uncertainty_score":0.99993175},"labels":[],"label_agreement":null},{"id":"W2790715424","doi":"10.1007/s10515-018-0232-y","title":"Black-box tree test case generation through diversity","year":2018,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Tree (set theory); Test case; Test (biology); Set (abstract data type); Black box; Algorithm; Random testing; Mathematics; Machine learning; Artificial intelligence","score_opus":0.024780093582989115,"score_gpt":0.24827839461829362,"score_spread":0.22349830103530452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790715424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10022294,0.000037214628,0.820481,0.000050180628,0.0004101592,0.00010309079,0.0000036722627,0.07863259,0.00005917672],"genre_scores_gemma":[0.58981925,0.0000021553421,0.4098664,0.000100215126,0.00016442942,0.0000061134624,0.0000043834566,0.00001681542,0.000020214638],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874765,0.000021635142,0.00020967014,0.00042717316,0.00022529624,0.00036855924],"domain_scores_gemma":[0.9986628,0.00037978453,0.00006757017,0.000632346,0.00016590129,0.00009155339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020274629,0.00022331112,0.0001715598,0.00012348556,0.00042545985,0.0001533915,0.00053632824,0.00012149793,0.000007464953],"category_scores_gemma":[0.0013066332,0.00023530607,0.000057065976,0.00056857365,0.00005842005,0.0005890034,0.0006281171,0.00014754797,0.000080592756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001677609,0.000998516,0.113341175,0.0005412513,0.00047224114,0.017421136,0.051145274,0.024479058,0.01270544,0.0074882084,0.64639056,0.12500036],"study_design_scores_gemma":[0.00019412544,0.000150428,0.0019189245,0.00006297441,0.000013764333,0.0009924727,0.0000045349457,0.98838925,0.0069488194,0.0004615184,0.0004582352,0.00040494534],"about_ca_topic_score_codex":0.00019719641,"about_ca_topic_score_gemma":0.000012208891,"teacher_disagreement_score":0.9639102,"about_ca_system_score_codex":0.00009435335,"about_ca_system_score_gemma":0.00003278951,"threshold_uncertainty_score":0.9595503},"labels":[],"label_agreement":null},{"id":"W2794522096","doi":"10.1145/3180155.3180203","title":"Fine-grained test minimization","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Test suite; Computer science; Test (biology); Code coverage; Test case; Test Management Approach; Minification; Test harness; Reliability engineering; Automatic test pattern generation; Test script; Test method; System under test; Algorithm; Model-based testing; Software; Programming language; Machine learning; Statistics; Mathematics; Software system; Engineering","score_opus":0.01795446925922184,"score_gpt":0.25962416323773274,"score_spread":0.2416696939785109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794522096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008239579,0.0000051693287,0.9675618,0.0009638936,0.00011372478,0.000042249227,2.4871161e-7,0.014868744,0.015620202],"genre_scores_gemma":[0.4668216,2.1966905e-7,0.5317798,0.0004248321,0.00008064616,0.0000037957004,7.3476144e-7,0.0000033248045,0.0008850346],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951774,0.0000105954805,0.00008649498,0.0001735132,0.000093337985,0.00011830097],"domain_scores_gemma":[0.99925613,0.00022261024,0.00002725741,0.00035272446,0.000106018255,0.000035258698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104173436,0.00005675224,0.000049427435,0.00005626255,0.00007724166,0.00007460835,0.00036556003,0.000027298745,0.000032082793],"category_scores_gemma":[0.00073371606,0.00004696107,0.000015943757,0.0002915232,0.000035848727,0.00013745531,0.00010325076,0.000026837512,0.000124472],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014382726,0.00008495341,0.023779461,0.000005118877,0.0000036233128,0.0000056292374,0.00038326325,0.0000015726673,0.00041017396,0.028194055,0.826002,0.121128686],"study_design_scores_gemma":[0.000510751,0.001089848,0.023790278,0.00007260731,0.000006927913,0.00008001875,0.0000029369594,0.6031397,0.035129834,0.29919973,0.03626167,0.0007156885],"about_ca_topic_score_codex":0.000024243473,"about_ca_topic_score_gemma":0.000007935861,"teacher_disagreement_score":0.7897404,"about_ca_system_score_codex":0.000008646198,"about_ca_system_score_gemma":0.000022082333,"threshold_uncertainty_score":0.19150169},"labels":[],"label_agreement":null},{"id":"W2795612311","doi":"10.1109/saner.2018.8330200","title":"Clustering support for inadequate test suite reduction","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Test suite; Cluster analysis; Regression testing; Computer science; Test (biology); Reduction (mathematics); Reliability engineering; Test case; Code coverage; Data mining; Test Management Approach; Suite; Automatic test pattern generation; Machine learning; Regression analysis; Engineering; Software; Programming language; Mathematics; Software system","score_opus":0.03564268704330998,"score_gpt":0.29757460533931246,"score_spread":0.2619319182960025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795612311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010243314,0.0000027012304,0.9843581,0.0005476838,0.00038022306,0.00014013765,7.450815e-7,0.009943454,0.0036026754],"genre_scores_gemma":[0.43950084,5.5567995e-7,0.5586186,0.00020287554,0.00018370948,0.000024117571,0.0000011958377,0.0000067334217,0.0014613591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992966,0.000008394987,0.00013371206,0.00025646808,0.000092408285,0.0002123898],"domain_scores_gemma":[0.99924254,0.00016574297,0.000046104506,0.00036802114,0.00012894638,0.00004867019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032187017,0.00007858187,0.0000751398,0.000076006036,0.00013985508,0.00011107276,0.00037056176,0.00003776243,0.000011914845],"category_scores_gemma":[0.00034290535,0.00007071733,0.000030714265,0.00018221275,0.000042372314,0.00025831102,0.00014555288,0.000039295395,0.000046044934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013733053,0.000112781185,0.002727862,0.000054843866,0.000012284803,0.000005592349,0.0011220514,0.0000079249085,0.0047671027,0.008808257,0.34868738,0.63368016],"study_design_scores_gemma":[0.00073304714,0.00303188,0.0032532846,0.00010756518,0.000015258482,0.00047611544,0.00001523545,0.6937565,0.0944368,0.16216621,0.041093167,0.0009149139],"about_ca_topic_score_codex":0.000046788704,"about_ca_topic_score_gemma":0.000005600664,"teacher_disagreement_score":0.6937486,"about_ca_system_score_codex":0.000026319747,"about_ca_system_score_gemma":0.000034318116,"threshold_uncertainty_score":0.2883769},"labels":[],"label_agreement":null},{"id":"W2796271057","doi":"10.1007/978-3-319-89363-1_13","title":"Iterative Generation of Diverse Models for Testing Specifications of DSL Tools","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Emberi Eroforrások Minisztériuma","keywords":"Computer science; Digital subscriber line; Test suite; Programming language; Iterative refinement; Model-based testing; Domain-specific language; Set (abstract data type); Generator (circuit theory); Suite; Software engineering; Context (archaeology); Graph; Code generation; Theoretical computer science; Test case; Algorithm; Machine learning","score_opus":0.19838911353524138,"score_gpt":0.30393732370412346,"score_spread":0.10554821016888208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796271057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016624434,0.000084088875,0.99752647,0.000074982556,0.0004460318,0.00046259223,0.000027691245,0.00051378505,0.00069811445],"genre_scores_gemma":[0.14370818,0.0000044732965,0.85583204,0.000094559895,0.00027069685,0.000014800262,0.000008017273,0.0000144456835,0.00005275164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997848,0.000022648652,0.00055302243,0.0008215834,0.00048400453,0.00027074866],"domain_scores_gemma":[0.9956918,0.0015234973,0.0005494011,0.0009901401,0.0011872813,0.000057876303],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000749655,0.00027148266,0.00039932015,0.00055127474,0.00017234209,0.00017562194,0.0016356509,0.00016784214,0.0000041453336],"category_scores_gemma":[0.00072459574,0.0002550006,0.00009468732,0.0005012056,0.000587753,0.0006170378,0.00052932993,0.00019092667,0.0000017696921],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007797785,0.00007178277,0.00012214124,0.000119176446,0.000019682442,0.0000046568753,0.0038748619,0.061565783,0.0028163346,0.050920717,0.00056087517,0.8799162],"study_design_scores_gemma":[0.00007364922,0.0001954428,0.000017762155,0.000286718,0.0000053811386,0.0000064731685,7.553267e-8,0.6185697,0.0077555655,0.3728752,0.000033841894,0.0001801779],"about_ca_topic_score_codex":0.000015692302,"about_ca_topic_score_gemma":0.0000071932545,"teacher_disagreement_score":0.879736,"about_ca_system_score_codex":0.000104410006,"about_ca_system_score_gemma":0.00036101238,"threshold_uncertainty_score":0.9999902},"labels":[],"label_agreement":null},{"id":"W2798496775","doi":"10.23919/date.2018.8342261","title":"Suspect set prediction in RTL bug hunting","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Algorithmic program debugging; Probabilistic logic; Set (abstract data type); Software bug; Representation (politics); Programming language; Graph; Theoretical computer science; Artificial intelligence; Software","score_opus":0.026260762018551712,"score_gpt":0.2771563603785227,"score_spread":0.250895598359971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798496775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08888572,0.000014812466,0.85454226,0.0004716604,0.00036644985,0.00010319123,6.476663e-7,0.021256609,0.034358684],"genre_scores_gemma":[0.82261544,5.1645196e-7,0.17676714,0.00021063906,0.000113520146,0.0000052771984,6.0796896e-7,0.000004017139,0.00028284735],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993097,0.000027163745,0.00013178124,0.00023230788,0.000119947574,0.0001790901],"domain_scores_gemma":[0.99945503,0.000106073094,0.00003166759,0.00032526668,0.000053176456,0.000028808143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039364924,0.00006408888,0.00006687081,0.00011868886,0.0000666954,0.000082471386,0.00034056578,0.00003755333,0.000026356267],"category_scores_gemma":[0.00022972171,0.000057621448,0.000016857659,0.00038320254,0.000030803076,0.00023573694,0.00014976438,0.00007546248,0.00007921396],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052958717,0.000079139216,0.71093446,0.000015847176,0.000007148633,0.000024848006,0.0020718363,0.000009612408,0.0005958337,0.020895166,0.18538393,0.0799769],"study_design_scores_gemma":[0.00055881985,0.0006182967,0.25653064,0.00022386333,0.000004425375,0.00010884935,0.00002642847,0.47865835,0.020107225,0.23589501,0.006705118,0.00056298636],"about_ca_topic_score_codex":0.0003753034,"about_ca_topic_score_gemma":0.00006272759,"teacher_disagreement_score":0.7337297,"about_ca_system_score_codex":0.00003152755,"about_ca_system_score_gemma":0.00002357243,"threshold_uncertainty_score":0.23497345},"labels":[],"label_agreement":null},{"id":"W2803276064","doi":"10.1145/3183440.3183470","title":"VISUFLOW","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.014934488957384216,"score_gpt":0.26813717810419996,"score_spread":0.25320268914681576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803276064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001279103,0.0000051866455,0.9374169,0.00037218703,0.00012868433,0.000017435299,2.8979258e-8,0.019823313,0.04095714],"genre_scores_gemma":[0.46916178,1.9235722e-7,0.52965194,0.00069453596,0.000058560916,0.0000015066815,4.3419046e-8,0.0000015618643,0.00042988828],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99966186,0.000007641972,0.00004476189,0.00012174695,0.00006839737,0.00009561003],"domain_scores_gemma":[0.9995561,0.00004534443,0.000010129946,0.00031349112,0.000046590892,0.0000283237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000097756776,0.000034403074,0.000031661715,0.000031193755,0.00005285839,0.000054551187,0.00037367648,0.000015296002,0.000029275063],"category_scores_gemma":[0.00007336081,0.000027203167,0.000012333613,0.00014813605,0.000027730783,0.000105985535,0.00011023642,0.000021950937,0.0003116393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.3280364e-7,0.000027236727,0.0038921488,0.0000018407379,0.0000030264293,0.0000058442097,0.00024284013,1.2165016e-7,0.0002200332,0.13147481,0.55831695,0.30581445],"study_design_scores_gemma":[0.00016147149,0.00045812514,0.0069793877,0.000026767293,0.000001847448,0.00007478505,0.0000013961932,0.1349759,0.033961747,0.75821966,0.06476,0.00037893577],"about_ca_topic_score_codex":0.000021867178,"about_ca_topic_score_gemma":0.0000011979823,"teacher_disagreement_score":0.6267448,"about_ca_system_score_codex":0.000005084141,"about_ca_system_score_gemma":0.000011758806,"threshold_uncertainty_score":0.40055966},"labels":[],"label_agreement":null},{"id":"W2804918785","doi":"10.7939/r3pr7n043","title":"Diversity-Based Automated Test Case Generation","year":2015,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alberta Innovates","keywords":"Test (biology); Diversity (politics); Computer science; Biology; Political science; Ecology","score_opus":0.031491472263569346,"score_gpt":0.2089218540776135,"score_spread":0.17743038181404414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804918785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7374492,0.0000524656,0.220146,0.004175348,0.0002765254,0.0002459666,0.000006945073,0.02526163,0.012385898],"genre_scores_gemma":[0.81709224,7.6174337e-7,0.1821229,0.00022395876,0.00001536718,4.6476522e-8,0.000012470351,0.000004498521,0.00052776205],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945855,0.00004628313,0.000064568965,0.00019392652,0.000126667,0.000110005974],"domain_scores_gemma":[0.99913555,0.00029135752,0.00007002731,0.0003331914,0.00004914988,0.00012070154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000066794084,0.000077513214,0.000096278774,0.00013235664,0.0002938909,0.000027902795,0.0005241957,0.000056894372,0.000015028654],"category_scores_gemma":[0.00011100547,0.00009087333,0.000039459464,0.0002981188,0.000054444597,0.0009210781,0.0009018862,0.00005494564,0.000017112485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020262514,0.00028278172,0.15527551,0.000027088554,0.000024044351,0.002391964,0.011164032,0.00053338846,0.000055881606,0.0031164223,0.82512546,0.001983139],"study_design_scores_gemma":[0.00072977215,0.00024908507,0.0010619479,0.000035952173,0.000017742392,0.00020691862,0.000064125015,0.98938185,0.0015860392,0.0015801684,0.004817694,0.00026872277],"about_ca_topic_score_codex":0.002456352,"about_ca_topic_score_gemma":0.000059264774,"teacher_disagreement_score":0.98884845,"about_ca_system_score_codex":0.000019170024,"about_ca_system_score_gemma":0.00014406997,"threshold_uncertainty_score":0.3713286},"labels":[],"label_agreement":null},{"id":"W2806092147","doi":"10.1007/s10270-018-0680-7","title":"Static slicing of Use Case Maps requirements models","year":2018,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"King Fahd University of Petroleum and Minerals","keywords":"Slicing; Computer science; Computer graphics (images)","score_opus":0.12165666343186207,"score_gpt":0.3041852905049325,"score_spread":0.1825286270730704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806092147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07751603,0.00018055885,0.9150139,0.00002055959,0.0005315949,0.000308968,0.000011785255,0.0063529676,0.000063629384],"genre_scores_gemma":[0.67018867,0.0000036323624,0.32955402,0.00008625729,0.000074291995,0.000024443632,0.0000027355327,0.000027349599,0.00003863039],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747276,0.0001466747,0.00078444806,0.00059149857,0.0005184548,0.00048615792],"domain_scores_gemma":[0.9973539,0.00036715993,0.00030701447,0.001208228,0.00062361296,0.00014007305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009581697,0.00026519597,0.00040355703,0.00026847905,0.0002776246,0.00026508348,0.00069866766,0.00011008333,0.0000010385734],"category_scores_gemma":[0.00054505095,0.00025385365,0.00008982661,0.00044354307,0.00006552441,0.0014682504,0.00036010717,0.00015233093,0.0000112950975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006645488,0.00042168796,0.013362941,0.0020887386,0.00033731465,0.0021015063,0.022486933,0.8633221,0.0005770834,0.03392444,0.011996588,0.049314212],"study_design_scores_gemma":[0.00017824404,0.00011663395,0.0000017486648,0.0007282763,0.000016070519,0.00061872986,0.000049117112,0.97481674,0.00007824075,0.02309814,0.000028560724,0.00026948022],"about_ca_topic_score_codex":0.004048091,"about_ca_topic_score_gemma":0.00001789478,"teacher_disagreement_score":0.59267265,"about_ca_system_score_codex":0.000108473076,"about_ca_system_score_gemma":0.00011284629,"threshold_uncertainty_score":0.99999136},"labels":[],"label_agreement":null},{"id":"W2807011628","doi":"10.1007/978-3-319-92997-2_13","title":"Life Sciences-Inspired Test Case Similarity Measures for Search-Based, FSM-Based Software Testing","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Test suite; Computer science; Suite; Intuition; Diversity (politics); Machine learning; Fault detection and isolation; Random testing; Software; Test case; Test (biology); Artificial intelligence; Data mining; Software engineering; Programming language; Psychology","score_opus":0.08310386132228398,"score_gpt":0.3036598676674446,"score_spread":0.22055600634516065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807011628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014200792,0.0002962076,0.9897206,0.0010457935,0.0009158549,0.0010734971,0.00005458772,0.006515954,0.00023553339],"genre_scores_gemma":[0.12445888,0.0000016254165,0.86986464,0.004925391,0.00058695086,0.000054188204,0.0000071631375,0.0000737475,0.000027410233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925481,0.000100974525,0.00088496733,0.0030405582,0.0019021898,0.0015232195],"domain_scores_gemma":[0.9833686,0.011612364,0.00051346014,0.0022492264,0.0016168524,0.0006394953],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0048567043,0.0009823428,0.00086578244,0.001611112,0.0018301071,0.0012171128,0.005287217,0.00056640693,0.000012312679],"category_scores_gemma":[0.019400414,0.00091255415,0.00027884232,0.0019124758,0.003421009,0.0006101944,0.0012607027,0.0010299955,0.00002000873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003206159,0.00028478837,0.007076959,0.0005154076,0.000023694587,0.0015785978,0.0005519968,0.095027834,0.00009005048,0.0009395837,0.002644101,0.89123493],"study_design_scores_gemma":[0.00045811824,0.001200317,0.0000662699,0.0011026567,0.000020026597,0.00039412666,9.836817e-8,0.8666967,0.0016564515,0.12685181,0.00042455827,0.00112887],"about_ca_topic_score_codex":0.00020016287,"about_ca_topic_score_gemma":0.000104595674,"teacher_disagreement_score":0.8901061,"about_ca_system_score_codex":0.00048771314,"about_ca_system_score_gemma":0.006121699,"threshold_uncertainty_score":0.9998197},"labels":[],"label_agreement":null},{"id":"W2808023677","doi":"10.1145/3183519.3183551","title":"Evaluating specification-level MC/DC criterion in model-based testing of safety critical systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Microsoft (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Code coverage; Certification; Reliability engineering; Model-based testing; Process (computing); White-box testing; Software; Software engineering; Software system; Test case; Programming language; Software construction; Engineering","score_opus":0.2588067781531558,"score_gpt":0.40762558216868033,"score_spread":0.14881880401552455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808023677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015136139,0.000030291967,0.979403,0.00025060758,0.000162532,0.00014734267,0.000002825475,0.002482155,0.0023850603],"genre_scores_gemma":[0.51745164,1.3393577e-7,0.4824126,0.00006300886,0.000037971786,0.000010427066,6.902415e-7,0.0000057744423,0.000017732395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832547,0.00012830262,0.00052832405,0.0003900998,0.0003715923,0.00025622195],"domain_scores_gemma":[0.9968695,0.0016773834,0.00010840486,0.0006577954,0.000626425,0.000060477978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016692745,0.00012382177,0.00019529313,0.0001867327,0.00011227181,0.00009467175,0.00056447624,0.00006820349,0.0000055100545],"category_scores_gemma":[0.00498873,0.00011639546,0.000029637667,0.0005908395,0.00012027037,0.00022890918,0.00012762916,0.00010762088,0.000009991122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015759814,0.0015460298,0.11315118,0.0014828022,0.000029193687,0.000040482002,0.0050791744,0.07775831,0.072246954,0.32052428,0.0107479,0.3972361],"study_design_scores_gemma":[0.00014062195,0.0001527156,0.0030444427,0.00032196537,0.0000026841449,0.0000071857494,0.0000054540683,0.9810396,0.003612095,0.0115284715,0.000007568623,0.00013720806],"about_ca_topic_score_codex":0.00026985767,"about_ca_topic_score_gemma":0.000005393244,"teacher_disagreement_score":0.9032813,"about_ca_system_score_codex":0.00007508229,"about_ca_system_score_gemma":0.00017303962,"threshold_uncertainty_score":0.5972336},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.033805008270209574,"score_gpt":0.28879608613740154,"score_spread":0.254991077867192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809981234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45325324,0.00008767116,0.5252904,0.00029232076,0.00017165196,0.0005097213,0.000008175788,0.019831605,0.0005551884],"genre_scores_gemma":[0.624447,0.0000020355706,0.37528732,0.00013805326,0.000045345976,0.000040938274,0.00001029075,0.000011471501,0.00001751686],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787563,0.00027136545,0.0005006887,0.0006619146,0.0003997045,0.00029068592],"domain_scores_gemma":[0.9952805,0.0022356766,0.00037691428,0.0010822135,0.00091984967,0.00010485825],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017636828,0.00023218367,0.00024368387,0.00011812059,0.0004341105,0.00014539718,0.0006659018,0.000158467,0.0000011841654],"category_scores_gemma":[0.015660029,0.00016901582,0.000062636434,0.0011242189,0.00060256314,0.00022704934,0.00015941178,0.00021237879,0.0000070869874],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028340512,0.0015668614,0.79991406,0.0007867217,0.000041919702,0.0000032282176,0.004518598,0.00070470106,0.007510026,0.0013641166,0.043706942,0.13985448],"study_design_scores_gemma":[0.0002232311,0.00029149026,0.31080624,0.000080668025,0.000017104152,0.000016864497,0.000016216107,0.6807459,0.0025955704,0.0043788934,0.00070303486,0.00012479036],"about_ca_topic_score_codex":0.00032062488,"about_ca_topic_score_gemma":0.0000049222926,"teacher_disagreement_score":0.6800412,"about_ca_system_score_codex":0.000057545072,"about_ca_system_score_gemma":0.00032530635,"threshold_uncertainty_score":0.9926315},"labels":[],"label_agreement":null},{"id":"W2810463508","doi":"10.1109/mtv.2017.19","title":"Dynamic Exerciser Template Weighting in x86 Processor Verification","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; x86; Template; Weighting; Functional verification; Embedded system; Computer engineering; Theoretical computer science; Formal verification; Software; Operating system; Programming language","score_opus":0.021446376472997554,"score_gpt":0.3025776588844818,"score_spread":0.2811312824114842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810463508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18237877,0.000050301733,0.79297894,0.0018135809,0.00023858555,0.0002488802,4.5662418e-7,0.010217559,0.012072912],"genre_scores_gemma":[0.74108386,0.0000045989327,0.2585118,0.0000517342,0.000006490969,0.0000223119,5.3733584e-7,0.000004942066,0.0003137045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926126,0.00001327676,0.00014745623,0.00028518942,0.000119120086,0.00017371205],"domain_scores_gemma":[0.9988852,0.000058205573,0.000117875985,0.0008585664,0.00004805073,0.00003207764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033785126,0.00008073322,0.00009347308,0.00008267107,0.00024055493,0.00033207005,0.0010521031,0.00004595047,0.0000039541824],"category_scores_gemma":[0.00031513677,0.00007073649,0.000018261482,0.000091690104,0.000027239843,0.0005807515,0.0001847978,0.00008686772,0.000035429868],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016444616,0.00022153182,0.22906318,0.00013424424,0.000009022097,0.00006914452,0.0019194032,0.000045185956,0.0027892205,0.01896604,0.008426529,0.7383401],"study_design_scores_gemma":[0.0003880783,0.00005508452,0.27146342,0.00029723617,0.0000032727096,0.000025021889,0.0000067820033,0.5861363,0.0074348636,0.13303882,0.0006771668,0.00047396752],"about_ca_topic_score_codex":0.00019193692,"about_ca_topic_score_gemma":0.00003216946,"teacher_disagreement_score":0.7378661,"about_ca_system_score_codex":0.000032211858,"about_ca_system_score_gemma":0.000032013868,"threshold_uncertainty_score":0.3202159},"labels":[],"label_agreement":null},{"id":"W2810772136","doi":"10.5539/mas.v12n7p99","title":"Using Artificial Bee Colony Algorithm for Test Data Generation and Path Testing Coverage","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Traverse; Keyword-driven testing; White-box testing; Automation; Software; Path (computing); Code coverage; Heuristic; Artificial bee colony algorithm; Test strategy; Data mining; Software development; Artificial intelligence; Software construction; Programming language; Engineering","score_opus":0.18411092876477508,"score_gpt":0.33815538343728446,"score_spread":0.15404445467250938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810772136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008640448,0.000014696809,0.98909086,0.000052739637,0.00013295394,0.0002995213,0.000021866581,0.0015421449,0.00020478836],"genre_scores_gemma":[0.47043216,3.3411314e-7,0.5292043,0.00016291923,0.000176885,0.000012021543,0.0000027173173,0.000005955439,0.0000026972316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814665,0.000010534728,0.00020046448,0.0009116851,0.0003527648,0.00037792374],"domain_scores_gemma":[0.99843997,0.00037346984,0.000115760406,0.0007562769,0.00021628354,0.00009825448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014067369,0.00013419443,0.00012628647,0.00010892671,0.0010408409,0.00064030883,0.001300939,0.000045791738,4.2954116e-7],"category_scores_gemma":[0.00085534755,0.00013158045,0.000009163102,0.00062185136,0.00044455993,0.0006018765,0.0008964837,0.000074793476,0.0000027206208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011448154,0.000036241498,0.00021473634,0.0000044596877,0.0000011009208,0.0000013033855,0.00023167349,0.000032838576,0.37239772,0.0018952141,0.00047097373,0.6247126],"study_design_scores_gemma":[0.000077208526,0.000082844526,0.00013462409,0.000012077234,0.00000403684,0.000016704327,0.0000010813201,0.9159051,0.0113473255,0.07220877,0.00004789392,0.00016232584],"about_ca_topic_score_codex":0.00004135415,"about_ca_topic_score_gemma":0.000004679112,"teacher_disagreement_score":0.9158723,"about_ca_system_score_codex":0.000054171258,"about_ca_system_score_gemma":0.00025824446,"threshold_uncertainty_score":0.80054116},"labels":[],"label_agreement":null},{"id":"W2867457158","doi":"10.1145/3213846.3213847","title":"Safe and sound program analysis with Flix","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sound (geography); Acoustics; Physics","score_opus":0.016017412333590296,"score_gpt":0.28403457255650233,"score_spread":0.26801716022291205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2867457158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032512534,0.000016901853,0.950149,0.00018169153,0.000015866159,0.00007543447,1.3446278e-7,0.009879443,0.007169017],"genre_scores_gemma":[0.49742007,3.873481e-7,0.50231457,0.00012604464,0.000015484746,0.0000071512954,2.5827762e-7,0.0000018337843,0.00011417828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994263,0.000013735646,0.00006984327,0.00024044995,0.00011354023,0.0001361291],"domain_scores_gemma":[0.9994016,0.000069801106,0.00002771265,0.00036821418,0.000078895995,0.000053744956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013987579,0.00006819502,0.00009305578,0.00011351956,0.00009356119,0.0001338096,0.00023370486,0.000022233407,0.000010131282],"category_scores_gemma":[0.000033299733,0.00004550674,0.000019512261,0.00077162246,0.000100678546,0.00012763853,0.000104622944,0.000034360924,0.000010371374],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009364639,0.00013214456,0.46318585,0.000009959478,0.00026727983,0.000016756961,0.00075122976,0.0000035056266,0.000010294203,0.017981548,0.010307255,0.5073248],"study_design_scores_gemma":[0.00064160733,0.0041879914,0.21725707,0.00004711693,0.00038396113,0.00017444976,0.000017814495,0.53813225,0.0016783198,0.22392717,0.012380349,0.0011718996],"about_ca_topic_score_codex":0.000104052975,"about_ca_topic_score_gemma":0.000066526714,"teacher_disagreement_score":0.53812873,"about_ca_system_score_codex":0.0000060699995,"about_ca_system_score_gemma":0.000011746957,"threshold_uncertainty_score":0.18557109},"labels":[],"label_agreement":null},{"id":"W2884350287","doi":"10.1109/icstw.2018.00037","title":"Test Automation - Automation of What?","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Automation; Software deployment; Computer science; Test (biology); Software engineering; Software; Engineering; Programming language","score_opus":0.017588103902229337,"score_gpt":0.2754708383392292,"score_spread":0.2578827344369999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884350287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009188306,0.000013815801,0.9742254,0.0003862501,0.00017137614,0.000059059123,1.6193131e-7,0.012231933,0.0037236933],"genre_scores_gemma":[0.56821877,0.000001496481,0.4315442,0.000114041715,0.00002769315,0.0000029777916,5.323511e-7,0.0000019706233,0.00008827956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994808,0.000016000682,0.0001460475,0.00013059763,0.0001407617,0.00008582127],"domain_scores_gemma":[0.99918973,0.00021523773,0.000079205216,0.0003407794,0.00015268884,0.000022349284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022965235,0.000050661405,0.00006330902,0.00008451924,0.00004766159,0.000112381225,0.000300666,0.000032321528,0.000022664182],"category_scores_gemma":[0.00036600296,0.0000436824,0.000018290573,0.0002754843,0.00004093689,0.00086247857,0.00007650138,0.000023332947,0.00008149764],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013164542,0.00014122683,0.009046693,0.000034380995,0.000007098064,0.0000014678631,0.0014820185,0.000005456184,0.003454668,0.046534225,0.0874602,0.85183126],"study_design_scores_gemma":[0.00011490821,0.00034533115,0.03081473,0.00013523836,0.0000029861521,0.000016501304,0.000007690899,0.8022617,0.0603377,0.10530234,0.00050620025,0.00015468962],"about_ca_topic_score_codex":0.000029646197,"about_ca_topic_score_gemma":0.0000018073309,"teacher_disagreement_score":0.8516766,"about_ca_system_score_codex":0.0000134854445,"about_ca_system_score_gemma":0.000022021995,"threshold_uncertainty_score":0.17813165},"labels":[],"label_agreement":null},{"id":"W2886792510","doi":"10.1109/qrs.2018.00056","title":"Avoiding the Familiar to Speed Up Test Case Reduction","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Test suite; Reduction (mathematics); Computer science; Debugging; Fuzz testing; Compiler; Test case; Test (biology); Process (computing); Programming language; Algorithm; Suite; Parallel computing; Computer engineering; Software; Machine learning; Mathematics","score_opus":0.0372376855372135,"score_gpt":0.293992681587254,"score_spread":0.2567549960500405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886792510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087816685,0.000010241455,0.88698345,0.0028079846,0.0009848252,0.00019757624,5.213013e-7,0.013732335,0.007466387],"genre_scores_gemma":[0.8550051,8.8592583e-7,0.14295319,0.00063359115,0.00024382594,0.000004615374,1.1494777e-7,0.000005716326,0.0011529548],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927765,0.00005239939,0.00011099276,0.0002540263,0.00012400014,0.00018090925],"domain_scores_gemma":[0.99885464,0.000379468,0.000028914725,0.000559919,0.000114752824,0.00006228234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065341534,0.00008095087,0.000059477832,0.00006470737,0.0005098408,0.0001509958,0.00046131545,0.000028408569,0.000007660965],"category_scores_gemma":[0.0011773134,0.000053148407,0.000023964327,0.00044158395,0.000051270225,0.00015146272,0.00021400927,0.00011780144,0.00018982032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050394165,0.000066191176,0.00082732947,0.000006905922,0.000009267559,0.00025044623,0.0071275854,0.000011209526,0.008107261,0.012166636,0.6937402,0.27768195],"study_design_scores_gemma":[0.0006849321,0.002352486,0.003162941,0.00033337783,0.000039948856,0.058829755,0.0011436489,0.30152893,0.3858622,0.19673437,0.047313057,0.0020143525],"about_ca_topic_score_codex":0.00045896994,"about_ca_topic_score_gemma":0.000011607878,"teacher_disagreement_score":0.76718843,"about_ca_system_score_codex":0.000028527107,"about_ca_system_score_gemma":0.000022125134,"threshold_uncertainty_score":0.39213347},"labels":[],"label_agreement":null},{"id":"W2895807070","doi":"10.1145/3273934.3273944","title":"An Improvement to Test Case Failure Prediction in the Context of Test Case Prioritization","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Toronto Metropolitan University","funders":"","keywords":"Computer science; Test (biology); Test suite; Ranking (information retrieval); Context (archaeology); Test plan; Machine learning; Test case; A priori and a posteriori; Scale (ratio); Predictive modelling; Data mining; Logistic regression; Reliability (semiconductor); Plan (archaeology); Artificial intelligence; Reliability engineering; Regression analysis; Statistics; Engineering","score_opus":0.014813174640073286,"score_gpt":0.27506018310741376,"score_spread":0.26024700846734045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895807070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4228825,0.000005306745,0.5724485,0.0011240788,0.00010433468,0.000571868,0.00001639037,0.0025832127,0.00026382058],"genre_scores_gemma":[0.91668993,2.2523318e-7,0.08255574,0.00062936556,0.00006820186,0.00003163752,0.0000017779416,0.000004807799,0.00001829965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921054,0.000038065064,0.00021971075,0.0002426582,0.0001493849,0.00013966573],"domain_scores_gemma":[0.99871355,0.00042322127,0.000059605998,0.00055545743,0.00019794259,0.00005024364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005142694,0.000085312,0.000079908605,0.00010518903,0.0001084841,0.00009269456,0.0003121805,0.000041834515,0.0000050062954],"category_scores_gemma":[0.00065536285,0.000061264196,0.000015091468,0.00046032114,0.00003367746,0.00025190212,0.00007264859,0.00006401203,0.00000608803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017492812,0.0030678548,0.19144356,0.00010492885,0.000014886891,0.0073263845,0.040279523,0.000037491125,0.02161501,0.008042913,0.1069675,0.6210825],"study_design_scores_gemma":[0.0021437267,0.030971726,0.014787196,0.0004445594,0.00004770959,0.054841302,0.004714524,0.750606,0.12195901,0.014959762,0.0032634202,0.0012610449],"about_ca_topic_score_codex":0.0019755578,"about_ca_topic_score_gemma":0.002086782,"teacher_disagreement_score":0.7505685,"about_ca_system_score_codex":0.000034134056,"about_ca_system_score_gemma":0.000035826255,"threshold_uncertainty_score":0.29864654},"labels":[],"label_agreement":null},{"id":"W2896097868","doi":"10.1109/modre.2018.00007","title":"Modelling and Testing Requirements via Executable Abstract State Machines","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Eiffel; Computer science; Executable; Programming language; Formal specification; Notation; Software engineering; Object-oriented programming; Mathematics","score_opus":0.07012389338083574,"score_gpt":0.29371774342755136,"score_spread":0.22359385004671561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896097868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04527556,0.000038331997,0.9412392,0.000063111016,0.0000897905,0.00006581055,3.9146852e-7,0.0066052503,0.0066225557],"genre_scores_gemma":[0.50640386,0.0000015320682,0.49327433,0.00011842603,0.00003059767,0.0000026346484,2.1589345e-7,0.000005873134,0.0001624921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990766,0.000012272997,0.00017630272,0.00032102797,0.000158041,0.00025577564],"domain_scores_gemma":[0.9992188,0.00018933705,0.00006656955,0.00032898225,0.00012365621,0.00007263452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035435535,0.000116150266,0.000100678364,0.00007274479,0.00019920016,0.00019628202,0.0003222582,0.000026351488,0.0000067280967],"category_scores_gemma":[0.00010823437,0.000098523255,0.000013036106,0.0002175856,0.000051658677,0.00044441532,0.00022822786,0.00007016816,0.000020483481],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001288248,0.00013879016,0.04620884,0.000084111365,0.00003571558,0.00005166298,0.0014686108,0.004406254,0.0040551033,0.0021455907,0.010451139,0.9309413],"study_design_scores_gemma":[0.00006016753,0.00007245534,0.0005185048,0.000039324797,0.000001546013,0.000023401655,4.7825176e-7,0.89601564,0.001997264,0.10104491,0.00009629008,0.00012999726],"about_ca_topic_score_codex":0.0009707885,"about_ca_topic_score_gemma":0.0000037402124,"teacher_disagreement_score":0.9308113,"about_ca_system_score_codex":0.000013816975,"about_ca_system_score_gemma":0.000020113228,"threshold_uncertainty_score":0.40176618},"labels":[],"label_agreement":null},{"id":"W2898893292","doi":"10.1145/3236024.3236063","title":"Visual web test repair","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Focus (optics); Regression testing; Workflow; Pipeline (software); Test (biology); Test case; Artificial intelligence; Machine learning; Database; Software; Programming language; Regression analysis; Software development","score_opus":0.01627182758737435,"score_gpt":0.28774382715051855,"score_spread":0.2714719995631442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898893292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010230165,0.000023962022,0.70461047,0.0008189284,0.00038074644,0.000093814946,4.298925e-7,0.21294422,0.07089725],"genre_scores_gemma":[0.5223593,5.4710733e-7,0.4758363,0.0007767985,0.00011485642,0.0000035447747,1.39717e-7,0.0000039030197,0.0009046078],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936676,0.00001363687,0.00009601465,0.00023415679,0.00012425495,0.00016515434],"domain_scores_gemma":[0.99916375,0.00025382757,0.00002343702,0.00041839023,0.0000879811,0.000052601234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020908461,0.00006778034,0.000061607534,0.00005692549,0.00009301574,0.000066818175,0.0004020948,0.000032480875,0.000035358986],"category_scores_gemma":[0.00050593505,0.00005517462,0.000035144563,0.00026254993,0.00005693755,0.00014933638,0.00020924787,0.000047143665,0.0003448114],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.7816215e-7,0.00009058701,0.037049334,0.0000037830569,0.000004030653,0.00001286042,0.00011740871,6.993481e-8,0.00033941827,0.009272696,0.9241017,0.029007217],"study_design_scores_gemma":[0.00024035531,0.0013963652,0.013781625,0.000054401822,0.000004736996,0.000121553276,0.000003087815,0.8455605,0.010370492,0.068180665,0.05976222,0.0005239822],"about_ca_topic_score_codex":0.000033704295,"about_ca_topic_score_gemma":0.000005361521,"teacher_disagreement_score":0.8643395,"about_ca_system_score_codex":0.000012427375,"about_ca_system_score_gemma":0.000044321496,"threshold_uncertainty_score":0.44319677},"labels":[],"label_agreement":null},{"id":"W2900453375","doi":"10.1109/icsme.2018.00016","title":"Test Re-Prioritization in Continuous Testing Environments","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Prioritization; Scalability; Reliability engineering; Set (abstract data type); Regression testing; Test case; Test strategy; Software deployment; Test (biology); Risk-based testing; Data mining; Software; Machine learning; Software system; Engineering","score_opus":0.026343412774647586,"score_gpt":0.25770566259295047,"score_spread":0.2313622498183029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900453375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0139056565,0.000015737227,0.9629787,0.00017469443,0.000114229675,0.00011529227,3.2291592e-7,0.005790155,0.016905218],"genre_scores_gemma":[0.5737464,6.6615627e-7,0.4257234,0.0002591199,0.000042005748,0.0000052843434,3.95378e-7,0.000004606395,0.00021811355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992235,0.00002309647,0.00016403304,0.0002626563,0.00013511626,0.00019162065],"domain_scores_gemma":[0.99916565,0.0003735439,0.000049072914,0.0003455564,0.00002927589,0.00003692584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027042927,0.00007983987,0.000083897954,0.00008790096,0.000069191716,0.00007666593,0.00037070672,0.000040946274,0.000009677348],"category_scores_gemma":[0.0014801682,0.00007670507,0.000010696338,0.00038059082,0.000047120084,0.00020938615,0.00016211935,0.00006309337,0.00007889889],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011301037,0.00013404532,0.8032096,0.000005187301,0.0000017474985,0.00002544808,0.00040441324,0.00000389442,0.0024169423,0.0019555062,0.010259068,0.18158302],"study_design_scores_gemma":[0.0010983874,0.0013708039,0.43551883,0.00040417147,0.000006689231,0.000097669945,0.000024599263,0.3974857,0.032914132,0.12188345,0.008066225,0.001129332],"about_ca_topic_score_codex":0.00013122139,"about_ca_topic_score_gemma":0.000012493892,"teacher_disagreement_score":0.55984074,"about_ca_system_score_codex":0.000037493755,"about_ca_system_score_gemma":0.000017876995,"threshold_uncertainty_score":0.3127942},"labels":[],"label_agreement":null},{"id":"W2901173357","doi":"10.1007/978-3-030-03592-1_2","title":"Executable Counterexamples in Software Model Checking","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Executable; Computer science; Programming language; Counterexample; Model checking; Software; Software engineering; Operating system; Discrete mathematics","score_opus":0.035696260353724835,"score_gpt":0.2674783825539967,"score_spread":0.23178212220027186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901173357","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001448689,0.00034047777,0.99381375,0.00016455042,0.0006934138,0.00030872345,0.0000054111465,0.0033624426,0.0011663756],"genre_scores_gemma":[0.06647915,0.00002526568,0.9315435,0.0012801222,0.0002581927,0.000016704524,0.000004288911,0.000053082444,0.00033967674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99557525,0.000029127012,0.00062641694,0.0018642277,0.0009774895,0.00092749036],"domain_scores_gemma":[0.9966715,0.0007374576,0.0002997903,0.0018348931,0.00030591185,0.00015045407],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013768121,0.0006213535,0.0006404444,0.001231019,0.00023501918,0.00069566193,0.0042117457,0.00041735222,0.000018217814],"category_scores_gemma":[0.00046603347,0.00060226046,0.0001117907,0.00075944973,0.00069866114,0.0007453921,0.0019940876,0.00087591534,0.00003671942],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014347892,0.00009985879,0.0023037698,0.00017178,0.000015633372,0.00027873757,0.004505068,0.11509475,0.00007611208,0.008523581,0.0015905628,0.8673258],"study_design_scores_gemma":[0.00009813344,0.00006542865,0.000044007356,0.0007458025,0.0000022152,0.00004483413,2.7819585e-8,0.53756016,0.0002526261,0.46051928,0.00021842672,0.00044904623],"about_ca_topic_score_codex":0.00010267462,"about_ca_topic_score_gemma":0.000105143925,"teacher_disagreement_score":0.8668767,"about_ca_system_score_codex":0.00050389755,"about_ca_system_score_gemma":0.00078035815,"threshold_uncertainty_score":0.99964285},"labels":[],"label_agreement":null},{"id":"W2903495827","doi":"10.1016/j.jss.2020.110542","title":"On testing machine learning programs","year":2020,"lang":"en","type":"preprint","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Transformative learning; Domain (mathematical analysis); Witness; Software engineering; Field (mathematics); Reliability (semiconductor); Software testing; Artificial intelligence; Software; Data science; Machine learning; Psychology","score_opus":0.06147200893269984,"score_gpt":0.2724679788593244,"score_spread":0.21099596992662456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903495827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017899252,0.0062672542,0.96754587,0.0004973031,0.0016866898,0.0003727702,0.000004863089,0.005600942,0.00012503794],"genre_scores_gemma":[0.7025432,0.00005101614,0.2967846,0.00010161243,0.0004260333,0.000010970088,0.0000029058385,0.00003274649,0.00004691419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980137,0.00016795562,0.0006917481,0.00036890284,0.00053030375,0.0002274158],"domain_scores_gemma":[0.9970079,0.0007802194,0.001224614,0.00034297843,0.00043115087,0.00021312606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009253661,0.0002875628,0.0006390171,0.00019614906,0.00015283641,0.0006982565,0.0008109428,0.000206636,4.5253364e-7],"category_scores_gemma":[0.0031676637,0.0002243303,0.00013796033,0.00021434364,0.000031711497,0.00013856312,0.0007192428,0.0015474664,0.000002437921],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006749393,0.00031561704,0.18101163,0.0044397796,0.0004241014,0.0023130076,0.0039035152,0.010890778,0.000045631623,0.0036141868,0.014356641,0.7786176],"study_design_scores_gemma":[0.0022330245,0.010691413,0.008934781,0.04980529,0.00029022078,0.008464132,0.00010961923,0.6414126,0.000065901404,0.26201072,0.012722575,0.003259729],"about_ca_topic_score_codex":0.00014350531,"about_ca_topic_score_gemma":5.172283e-7,"teacher_disagreement_score":0.7753579,"about_ca_system_score_codex":0.000061999956,"about_ca_system_score_gemma":0.00017190176,"threshold_uncertainty_score":0.9147924},"labels":[],"label_agreement":null},{"id":"W2906640661","doi":"10.1016/bs.adcom.2018.10.005","title":"Three Open Problems in the Context of E2E Web Testing and a Vision: NEONATE","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automation; Computer science; Web testing; Cohesion (chemistry); Web application; Software engineering; Context (archaeology); Web standards; Quality (philosophy); Web modeling; Data science; Web service; Web development; World Wide Web; Web application security; Engineering","score_opus":0.040664011614605776,"score_gpt":0.30901489416049815,"score_spread":0.2683508825458924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906640661","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011059532,0.022337439,0.75989467,0.00207676,0.0023230077,0.0051969667,0.00002884222,0.004422945,0.20261343],"genre_scores_gemma":[0.06621944,0.00058207475,0.9309294,0.0014518374,0.00014919916,0.00007415156,0.0000044247763,0.000055056367,0.0005344102],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983085,0.000044097134,0.0004963972,0.00062257267,0.00028486375,0.00024359471],"domain_scores_gemma":[0.9965216,0.0021875552,0.0003785043,0.0007668947,0.0001084986,0.000036984686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009025972,0.0002869804,0.000453883,0.0002290269,0.00006958922,0.00019889927,0.002656232,0.00012058381,0.0000028018574],"category_scores_gemma":[0.0001421423,0.00022056291,0.000040217932,0.0002050737,0.00028154388,0.0005656326,0.0014263183,0.00035305644,0.0000034795883],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009327706,0.000037511614,0.002554906,0.00016467829,0.000011373734,0.000070062655,0.0015520067,0.00013454031,0.0000024008039,0.036487617,0.0048542866,0.9541213],"study_design_scores_gemma":[0.000564435,0.0006289296,0.0004663859,0.0047241296,0.0000062716044,0.00010167227,0.0000075483385,0.06826795,0.0000044974236,0.88706356,0.03769666,0.00046794972],"about_ca_topic_score_codex":0.00018277734,"about_ca_topic_score_gemma":0.00041865042,"teacher_disagreement_score":0.95365334,"about_ca_system_score_codex":0.00004050509,"about_ca_system_score_gemma":0.0000834636,"threshold_uncertainty_score":0.8994295},"labels":[],"label_agreement":null},{"id":"W2909649608","doi":"","title":"Upper bounds on the sizes of variable strength covering arrays using the Lov\\'{a}sz local lemma","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Hypergraph; Mathematics; Lemma (botany); Combinatorics; Upper and lower bounds; Logarithm; Generalization; Clique; Variable (mathematics); Row; Discrete mathematics; Spiral (railway); Logarithmic spiral; Algorithm; Computer science; Geometry; Mathematical analysis","score_opus":0.0798147617837113,"score_gpt":0.20125222415357577,"score_spread":0.12143746236986447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909649608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18925506,0.00003740561,0.8068968,0.00008959645,0.00043427528,0.00023931015,0.000009552141,0.0010993201,0.0019386691],"genre_scores_gemma":[0.9881907,0.000021142378,0.011241427,0.00017243944,0.000057624806,8.245398e-7,0.0000025406616,0.000022095699,0.00029121788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982523,0.00021496862,0.00022177969,0.0007678519,0.00018200446,0.00036110915],"domain_scores_gemma":[0.99605054,0.0012751659,0.00035124097,0.002097336,0.00016450927,0.00006121934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006396671,0.0003200773,0.00033542656,0.00014564679,0.00028898116,0.00018050849,0.0027046765,0.00022151384,0.000016246495],"category_scores_gemma":[0.00017359812,0.00023269044,0.00019087015,0.00055240607,0.00027474915,0.00018671247,0.0020756829,0.0007426426,0.000015339681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003291575,0.000109420456,0.007613656,0.00011459153,0.00011307896,0.000045094366,0.0004461836,0.7681411,0.00007075156,0.22080427,0.0019174444,0.0005914752],"study_design_scores_gemma":[0.00015407044,0.00007969843,0.00028332046,0.00042157984,0.000057469926,0.000007137515,0.00005633678,0.8966483,0.0008595479,0.10077371,0.0003183014,0.0003405198],"about_ca_topic_score_codex":0.0007944599,"about_ca_topic_score_gemma":0.0000053494155,"teacher_disagreement_score":0.79893565,"about_ca_system_score_codex":0.00020300272,"about_ca_system_score_gemma":0.00033874894,"threshold_uncertainty_score":0.948884},"labels":[],"label_agreement":null},{"id":"W2912088669","doi":"","title":"Proceedings of the 6th International Workshop on Constraints in Software Testing, Verification, and Analysis","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Software testing; Computer science; Software engineering; Software verification; Software; Systems engineering; Programming language; Software construction; Engineering; Software development","score_opus":0.021075756774194165,"score_gpt":0.2534182041734346,"score_spread":0.23234244739924043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912088669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11092032,0.0000066730768,0.8756826,0.0014000275,0.0000901961,0.00013335665,0.0000012746606,0.0019638946,0.009801654],"genre_scores_gemma":[0.8069367,6.03005e-7,0.19275011,0.0002306391,0.000007865232,0.000005818751,3.657947e-7,0.0000021176604,0.00006578822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99938035,0.000010882544,0.00015347727,0.0002111307,0.0001639715,0.000080206955],"domain_scores_gemma":[0.99912375,0.0004224299,0.000101113095,0.00017823534,0.0001524238,0.000022019862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035757272,0.00006248539,0.00009377423,0.00016770158,0.000036114678,0.00006249324,0.0005044067,0.00003081631,0.0000040785703],"category_scores_gemma":[0.0024177176,0.000043782566,0.000025851625,0.0008297593,0.00008769775,0.000091825576,0.00012147447,0.000074631454,7.8930054e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013615518,0.000035462235,0.88831395,0.0000053370836,0.00001841739,1.2115632e-7,0.00021132606,0.000057449757,0.00006943767,0.017641691,0.0012913608,0.09235406],"study_design_scores_gemma":[0.00016493503,0.00003750451,0.8521495,0.00014067611,0.00001815759,0.000006337901,0.000011715649,0.10813445,0.0010273218,0.038009327,0.0001571803,0.00014293668],"about_ca_topic_score_codex":0.000027504087,"about_ca_topic_score_gemma":0.0000035137546,"teacher_disagreement_score":0.6960164,"about_ca_system_score_codex":0.000014843715,"about_ca_system_score_gemma":0.000014754522,"threshold_uncertainty_score":0.28944084},"labels":[],"label_agreement":null},{"id":"W2912170833","doi":"10.1002/spe.404","title":"Exploiting exceptions","year":2001,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Purdue University","keywords":"Bytecode; Java bytecode; Programming language; Computer science; Java; Compiler; Program optimization; Interpretation (philosophy); Optimizing compiler; Abstract interpretation; Code (set theory); Parallel computing; Operating system; Real time Java; Java annotation","score_opus":0.0296799226284058,"score_gpt":0.3130142890524758,"score_spread":0.28333436642407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912170833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03965839,0.00041815458,0.94804335,0.0015041701,0.0001645771,0.00008398152,3.612181e-7,0.008549576,0.0015774434],"genre_scores_gemma":[0.50022733,0.00021789937,0.49787244,0.0014528646,0.000059524544,0.00005902252,6.225186e-7,0.000008099753,0.00010217152],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988419,0.00006157955,0.00017399428,0.00040795506,0.00022406454,0.0002905379],"domain_scores_gemma":[0.998227,0.00093529146,0.00010187521,0.00048863504,0.00012633893,0.00012087117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002925327,0.00013036616,0.00010832066,0.0000761412,0.00038114426,0.00029287656,0.00044303734,0.000051700044,0.000014653188],"category_scores_gemma":[0.0036713248,0.00012613609,0.00002805906,0.00040141947,0.00008657051,0.0022892854,0.00028057833,0.00015699,0.000040530416],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025748905,0.00023628867,0.059762217,0.000022433005,0.000018454683,0.00039611038,0.037939817,0.000010509576,0.00037951284,0.016181054,0.009686286,0.8753416],"study_design_scores_gemma":[0.0014945337,0.0010919143,0.025198162,0.00062903576,0.000074179996,0.013762647,0.00969374,0.01321818,0.00276754,0.22400874,0.7044832,0.0035781001],"about_ca_topic_score_codex":0.000117321026,"about_ca_topic_score_gemma":0.0000012380984,"teacher_disagreement_score":0.87176347,"about_ca_system_score_codex":0.000020869233,"about_ca_system_score_gemma":0.000035294728,"threshold_uncertainty_score":0.51436806},"labels":[],"label_agreement":null},{"id":"W2912187704","doi":"10.1007/3-540-45324-5_109","title":"Humboldt Heroes","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; League; Quarter (Canadian coin); Code (set theory); Operations research; Programming language; History; Engineering; Archaeology; Physics","score_opus":0.023497611520950187,"score_gpt":0.2601918604175893,"score_spread":0.2366942488966391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912187704","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025938496,0.00048064234,0.97846234,0.00060702965,0.0012730295,0.00024131211,0.0000016994748,0.0055725644,0.013335438],"genre_scores_gemma":[0.06943122,0.000076984616,0.9264593,0.002274126,0.00065967836,0.00001345731,0.0000033803744,0.000058538444,0.001023316],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961137,0.000028927463,0.00048150923,0.0016352244,0.000986338,0.0007543016],"domain_scores_gemma":[0.99658203,0.0007298617,0.00025640277,0.002005162,0.00023721157,0.00018930928],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008908914,0.00056446897,0.00054978643,0.0008924595,0.00027893367,0.00067231664,0.004409973,0.0003551415,0.000026604324],"category_scores_gemma":[0.00025043957,0.0005168619,0.0001403369,0.0007317366,0.0006258251,0.00050060643,0.0015920149,0.0008443161,0.00008416364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016165208,0.000021750417,0.00024580353,0.000019848245,0.0000059858403,0.00019304403,0.00030469353,0.0015107793,0.000015986161,0.013810021,0.0005444786,0.983326],"study_design_scores_gemma":[0.00012229738,0.00015622345,0.00011382841,0.00050553464,0.0000050725343,0.0002313058,1.5178628e-8,0.099638574,0.00044256766,0.8931824,0.0048573334,0.0007448701],"about_ca_topic_score_codex":0.000053475058,"about_ca_topic_score_gemma":0.00002314078,"teacher_disagreement_score":0.98258114,"about_ca_system_score_codex":0.00026164314,"about_ca_system_score_gemma":0.00043557698,"threshold_uncertainty_score":0.9997283},"labels":[],"label_agreement":null},{"id":"W2913009888","doi":"","title":"Proceedings of the 7th International Workshop on Automation of Software Test","year":2012,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Automation; Theme (computing); Scope (computer science); Test (biology); Software engineering; Software testing; Computer science; Selection (genetic algorithm); Engineering management; Diversity (politics); Software; Engineering; World Wide Web; Operating system; Programming language; Political science; Artificial intelligence","score_opus":0.030262160215990375,"score_gpt":0.26951956315226727,"score_spread":0.2392574029362769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913009888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10120556,0.000032044285,0.88729197,0.0008732114,0.0032167376,0.00030418116,0.0000422027,0.0042325417,0.0028015878],"genre_scores_gemma":[0.8683327,0.0000055050723,0.13127431,0.00008395191,0.00012402452,0.000025009233,0.000004252507,0.000014295258,0.0001359716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998536,0.000007345158,0.00034517926,0.00022699898,0.00067760056,0.00020687215],"domain_scores_gemma":[0.9983509,0.000560665,0.00027090416,0.00026145508,0.0004954935,0.000060556282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028472257,0.00018100192,0.00016335874,0.00024997917,0.000040317213,0.00007350321,0.0014058183,0.0000840871,0.000033196247],"category_scores_gemma":[0.0040566702,0.00014855569,0.00009484,0.0002817369,0.00003942091,0.00047344092,0.00026760675,0.00023270516,0.000011311657],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049630406,0.0010576585,0.45056304,0.00019431656,0.00024165737,0.0000031297848,0.0031540836,0.0048639686,0.005962355,0.44256425,0.012010439,0.07933547],"study_design_scores_gemma":[0.0014152427,0.00050454686,0.49588645,0.0069898646,0.000047941812,0.000114480325,0.000109522945,0.37251312,0.10072465,0.015657552,0.0044025765,0.0016340386],"about_ca_topic_score_codex":0.000006629213,"about_ca_topic_score_gemma":1.9837837e-7,"teacher_disagreement_score":0.7671271,"about_ca_system_score_codex":0.00010460101,"about_ca_system_score_gemma":0.000037983682,"threshold_uncertainty_score":0.6057925},"labels":[],"label_agreement":null},{"id":"W2913486937","doi":"","title":"Proceedings of the 19th IFIP TC6/WG6.1 international conference, and 7th international conference on Testing of Software and Communicating Systems","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Software; Computer science; Library science; Software engineering; Engineering; Operating system","score_opus":0.07168205796549357,"score_gpt":0.29696386027347144,"score_spread":0.22528180230797787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913486937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6005321,0.00015828453,0.26938805,0.0015039727,0.00079909,0.00069117144,0.000022080334,0.0034091799,0.12349608],"genre_scores_gemma":[0.8155632,0.000011465802,0.18422656,0.00006026711,0.000020031273,0.0000049578543,8.3562145e-7,0.000005385055,0.00010727483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998858,0.000016974438,0.0003764651,0.00024582984,0.00035850142,0.00014425037],"domain_scores_gemma":[0.9979395,0.000676882,0.00037817226,0.00025025287,0.00070748763,0.00004765835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008415871,0.00012461413,0.00017215194,0.00010784549,0.000099573546,0.00015563068,0.0011659118,0.000057138073,0.0000035615053],"category_scores_gemma":[0.0010761068,0.00009132024,0.000022463768,0.00020670808,0.00020007158,0.00021143314,0.0007679004,0.00017975784,3.107211e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017791444,0.00010913251,0.45993218,0.00014188474,0.00004968968,0.0000015280809,0.0018358943,0.0000068000295,0.0034829576,0.4673334,0.0010607806,0.06602794],"study_design_scores_gemma":[0.0014514073,0.00066129613,0.2314154,0.0057272245,0.000035520723,0.0003997045,0.0014327457,0.6543602,0.0177649,0.085157864,0.00065672287,0.0009370291],"about_ca_topic_score_codex":0.00024475376,"about_ca_topic_score_gemma":0.000005745844,"teacher_disagreement_score":0.6543534,"about_ca_system_score_codex":0.000023900518,"about_ca_system_score_gemma":0.000046154706,"threshold_uncertainty_score":0.37239313},"labels":[],"label_agreement":null},{"id":"W2913811733","doi":"","title":"Proceedings of the Eighth International Workshop on Search-Based Software Testing","year":2015,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Search-based software engineering; Software engineering; Computer science; Software development; Software metric; Software construction; Process (computing); Software; Metric (unit); Systems engineering; Engineering; Programming language","score_opus":0.09293096580281542,"score_gpt":0.2918747485365626,"score_spread":0.1989437827337472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913811733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04628688,0.00001739667,0.93766934,0.0019603295,0.0026174318,0.00030796594,0.000025488778,0.00704603,0.004069158],"genre_scores_gemma":[0.7140496,9.55832e-7,0.28538212,0.00025096742,0.00012852089,0.000029359613,0.0000043182617,0.000022103917,0.0001320694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978993,0.00001429944,0.00032110472,0.00042909884,0.0010707342,0.00026544617],"domain_scores_gemma":[0.9976039,0.00058925955,0.00016527475,0.0003420039,0.0011727273,0.00012684177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004195054,0.00024070198,0.00017802308,0.0003072341,0.000064842934,0.00024792604,0.002259873,0.00009214647,0.000013212462],"category_scores_gemma":[0.0066686147,0.00019567304,0.000090391935,0.00046306496,0.000057502795,0.00031337596,0.0003773153,0.0004141707,0.000017395665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024926697,0.0010497605,0.2385356,0.00021102268,0.00036717692,0.00008348969,0.0029514257,0.14905486,0.0022593148,0.42191,0.030248608,0.15307951],"study_design_scores_gemma":[0.0011270432,0.00035917718,0.016112048,0.0032192417,0.00001275352,0.00005555525,0.000048028105,0.94974744,0.013971576,0.012244253,0.00223801,0.0008648828],"about_ca_topic_score_codex":0.00002149017,"about_ca_topic_score_gemma":5.291845e-7,"teacher_disagreement_score":0.80069256,"about_ca_system_score_codex":0.0002149393,"about_ca_system_score_gemma":0.00020546425,"threshold_uncertainty_score":0.79834366},"labels":[],"label_agreement":null},{"id":"W2913863212","doi":"10.1007/s11219-019-9440-3","title":"Fault model-driven testing from FSM with symbolic inputs","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Finite-state machine; Test suite; Computer science; Symbolic execution; Implementation; Fault model; Fault injection; Fault (geology); Set (abstract data type); Model-based testing; Theoretical computer science; Fault coverage; Process (computing); Constraint (computer-aided design); Algorithm; Programming language; Test case; Software; Engineering; Machine learning","score_opus":0.044427028615976964,"score_gpt":0.29178708709886186,"score_spread":0.2473600584828849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913863212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2594619,0.000066193825,0.7339607,0.00035395383,0.0002013466,0.00011996136,0.00000895074,0.005599815,0.00022715944],"genre_scores_gemma":[0.44114226,0.0000026078558,0.557918,0.0007083543,0.000112934744,0.0000049695677,0.0000030705096,0.000022149408,0.00008561619],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972501,0.0002435857,0.0005736787,0.0005675721,0.00081597746,0.00054910354],"domain_scores_gemma":[0.9965021,0.0012550928,0.00048187244,0.0009599077,0.0005167761,0.0002842793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009903419,0.00030289314,0.00042815384,0.00016579518,0.0003306573,0.0005436343,0.0014245835,0.00014090714,0.000017560295],"category_scores_gemma":[0.0012744962,0.00024250304,0.00011184451,0.0005173126,0.000065036285,0.0007943929,0.0003204677,0.0007953312,0.000096253956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057787183,0.00026200223,0.8400493,0.0000853286,0.00015699827,0.00016843906,0.005117735,0.020790711,0.00091144023,0.002108641,0.008331842,0.12195974],"study_design_scores_gemma":[0.002792967,0.0010302863,0.07412617,0.0019408294,0.00006784285,0.0015512967,0.000058289013,0.46693456,0.0012853334,0.44698933,0.00080492254,0.0024181642],"about_ca_topic_score_codex":0.00022309586,"about_ca_topic_score_gemma":0.000008632122,"teacher_disagreement_score":0.76592314,"about_ca_system_score_codex":0.00012761014,"about_ca_system_score_gemma":0.00039172356,"threshold_uncertainty_score":0.9888987},"labels":[],"label_agreement":null},{"id":"W2916083331","doi":"","title":"Advances in Debug Automation for a Modern Verification Environment","year":2013,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Debugging; Automation; Software engineering; Computer science; Systems engineering; Engineering; Programming language","score_opus":0.012658475127772163,"score_gpt":0.24800232028868463,"score_spread":0.23534384516091247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916083331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015382186,0.002571364,0.96930224,0.00016798878,0.00021370486,0.0008021799,0.000005947952,0.0018968254,0.009657575],"genre_scores_gemma":[0.572442,0.0014059012,0.42312413,0.000009239135,0.000018442042,0.0000138144505,0.00016929423,0.000017176264,0.0027999957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921405,0.000030024043,0.00010468064,0.00032918944,0.00017800015,0.00014404852],"domain_scores_gemma":[0.9991585,0.00008391442,0.00027713602,0.0003808978,0.000063142994,0.000036422134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012451145,0.00013434819,0.00020342156,0.00007081119,0.00008070956,0.00001975481,0.00053517974,0.00015472833,0.00013777474],"category_scores_gemma":[0.000031886855,0.00017593386,0.00006955599,0.0000421387,0.000019152769,0.0009369191,0.00004099326,0.000064765765,0.000008069284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034039524,0.0000897076,0.00011086371,0.00021515413,0.000010172651,0.0000012288571,0.013338055,0.0001377521,0.00042180237,0.0017046006,0.0010265808,0.98291004],"study_design_scores_gemma":[0.0012256202,0.0005369094,0.18571502,0.0007800124,0.00007358135,0.0000024282872,0.0022543925,0.77978635,0.0007792445,0.024297563,0.0034973146,0.0010515464],"about_ca_topic_score_codex":0.012793035,"about_ca_topic_score_gemma":0.0051687863,"teacher_disagreement_score":0.9818585,"about_ca_system_score_codex":0.00029784956,"about_ca_system_score_gemma":0.000055958957,"threshold_uncertainty_score":0.99378085},"labels":[],"label_agreement":null},{"id":"W2921594963","doi":"10.1007/s10664-019-09691-z","title":"Assessing and optimizing the performance impact of the just-in-time configuration parameters - a case study on PyPy","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reliability engineering; Engineering","score_opus":0.03857829876151698,"score_gpt":0.31762281544977644,"score_spread":0.27904451668825947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921594963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443092,0.000018731827,0.054346547,0.00006328975,0.000088111636,0.00030148958,3.3024673e-7,0.00086412946,0.000008206014],"genre_scores_gemma":[0.9747898,5.8592025e-7,0.025110982,0.00005632575,0.000010820415,0.0000140304455,1.8730746e-7,0.000011881539,0.0000054168004],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990417,0.000067883935,0.00021184793,0.00024487555,0.00022751144,0.00020619239],"domain_scores_gemma":[0.99827296,0.0011114659,0.00007682936,0.00046877694,0.000030147121,0.000039820778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046900133,0.00015028419,0.00017761947,0.000080324884,0.00008700611,0.0001822538,0.0003890549,0.000046313893,0.0000019744189],"category_scores_gemma":[0.00041703467,0.00008760655,0.000060855305,0.00038180602,0.000022245771,0.00025604726,0.00016436717,0.00026564233,0.0000033553224],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004739222,0.000093976276,0.88528943,0.00002981778,0.000023786308,0.00006369573,0.002827263,0.10625539,0.00016441752,0.000005297981,0.00011892341,0.0051232544],"study_design_scores_gemma":[0.0003556462,0.00044929126,0.5760097,0.00025118177,0.000011346584,0.00037207198,0.00007373088,0.421539,0.00066739327,0.000021245132,0.000008579959,0.00024085162],"about_ca_topic_score_codex":0.00010229798,"about_ca_topic_score_gemma":3.899007e-7,"teacher_disagreement_score":0.3152836,"about_ca_system_score_codex":0.00006319125,"about_ca_system_score_gemma":0.00003300023,"threshold_uncertainty_score":0.35724917},"labels":[],"label_agreement":null},{"id":"W2922606767","doi":"10.1109/icpc.2019.00020","title":"An Empirical Study on Practicality of Specification Mining Algorithms on a Real-World Application","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Computer science; Program comprehension; Context (archaeology); Implementation; Inference; Programming language; Abstraction; Set (abstract data type); Software engineering; Root cause; Software; Algorithm; Artificial intelligence; Software system; Reliability engineering","score_opus":0.12292230898323768,"score_gpt":0.42842618468842586,"score_spread":0.30550387570518817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922606767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056491055,0.0000023628731,0.92636496,0.00070088357,0.00024428722,0.001292305,0.000004662823,0.0063699265,0.008529563],"genre_scores_gemma":[0.730559,0.0000021852393,0.2689442,0.00015685287,0.000091867754,0.00013296733,0.000019031555,0.00001636062,0.00007755881],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969396,0.0003657252,0.0005705396,0.0012199801,0.00067779556,0.00022633234],"domain_scores_gemma":[0.99468535,0.0011276611,0.00056859176,0.003280599,0.00024267979,0.00009509183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016572556,0.00027731122,0.00041049987,0.0003337589,0.000068431604,0.00015500996,0.0013304716,0.00018231709,0.000004176152],"category_scores_gemma":[0.00032583336,0.00024467005,0.000080331796,0.00040906144,0.00003731866,0.00013815993,0.0005511274,0.00053900736,0.000036910766],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021003792,0.017233642,0.53672135,0.00026403682,0.00016320286,0.00002041603,0.008676137,0.002816312,0.0001937397,0.030062119,0.028340086,0.37529892],"study_design_scores_gemma":[0.0003503941,0.0022194427,0.5607446,0.00024045078,0.00004005024,0.0000031792763,0.000101355676,0.40010014,0.001527214,0.033590287,0.00034918447,0.00073368463],"about_ca_topic_score_codex":0.000576819,"about_ca_topic_score_gemma":0.000016528356,"teacher_disagreement_score":0.6740679,"about_ca_system_score_codex":0.00016343262,"about_ca_system_score_gemma":0.00015161907,"threshold_uncertainty_score":0.9977355},"labels":[],"label_agreement":null},{"id":"W2925127136","doi":"10.1007/s11219-018-9437-3","title":"Testing self-healing cyber-physical systems under uncertainty: a fragility-oriented approach","year":2019,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Horizon 2020 Framework Programme; Norges Forskningsråd","keywords":"Fragility; Reliability engineering; Normality; Computer science; Reliability (semiconductor); Cyber-physical system; Data mining; Engineering; Mathematics; Statistics","score_opus":0.04131213216160864,"score_gpt":0.308153895772097,"score_spread":0.2668417636104884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925127136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21311186,0.00017364582,0.7741698,0.00015068882,0.00084860914,0.0003105159,0.0000051896413,0.010832998,0.00039670884],"genre_scores_gemma":[0.58691055,0.0000018153796,0.41231173,0.0002931548,0.0003736795,0.000017163364,0.000005159036,0.000031651965,0.000055101584],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99538696,0.0009014855,0.0008913888,0.0008112765,0.0011672477,0.0008416513],"domain_scores_gemma":[0.99428785,0.0027273868,0.00063981104,0.0011773148,0.0007771322,0.00039050935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003802481,0.00040220807,0.000663919,0.00023173142,0.0005845209,0.00073767983,0.0013195105,0.00019108345,0.000004268882],"category_scores_gemma":[0.0022772837,0.00035102514,0.00024452718,0.0010427161,0.00007362645,0.00069643214,0.0004087612,0.0012085594,0.000060556613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014381425,0.0041809757,0.630176,0.0023238119,0.0009155284,0.00022480747,0.022047073,0.11945642,0.00080433587,0.11492485,0.013513778,0.091288574],"study_design_scores_gemma":[0.0023535057,0.0008946191,0.030888643,0.0011911432,0.000096226795,0.0029468029,0.0007637883,0.7796924,0.00007792472,0.17641795,0.0022806728,0.002396305],"about_ca_topic_score_codex":0.00042737403,"about_ca_topic_score_gemma":9.0758897e-7,"teacher_disagreement_score":0.660236,"about_ca_system_score_codex":0.00040904977,"about_ca_system_score_gemma":0.00047121508,"threshold_uncertainty_score":0.9998942},"labels":[],"label_agreement":null},{"id":"W2930178786","doi":"","title":"PySnippet: Accelerating Exploratory Data Analysis in Jupyter Notebook through Facilitated Access to Example Code.","year":2019,"lang":"en","type":"article","venue":"EDBT/ICDT Workshops","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Code (set theory); Exploratory analysis; Computer security; Exploratory data analysis; Programming language; Data science; Data mining","score_opus":0.17585169340228715,"score_gpt":0.3512547445601635,"score_spread":0.17540305115787633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930178786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1391755,0.00023811926,0.84943455,0.0011082606,0.00056436897,0.0007441602,0.000038959723,0.006952994,0.0017430595],"genre_scores_gemma":[0.7799036,0.000012182259,0.21737707,0.0019771592,0.000095054085,0.000090210044,0.00008856834,0.000038960825,0.0004172244],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640757,0.00021823127,0.0006275183,0.0015206019,0.00052877126,0.0006973111],"domain_scores_gemma":[0.9948867,0.00093663274,0.00017147158,0.0037057863,0.0001407602,0.00015864379],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011179764,0.00036143363,0.0005808618,0.0005276263,0.00016171546,0.0009095437,0.004727193,0.00016138783,0.000097519594],"category_scores_gemma":[0.00045009164,0.000349717,0.00010290519,0.003510675,0.000046576366,0.00271843,0.0030900233,0.00043485683,0.00023851357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010060019,0.00059126195,0.56750184,0.0001593974,0.00064081635,0.00025644564,0.027283123,0.022102652,0.0010657032,0.0016526695,0.24105698,0.13758852],"study_design_scores_gemma":[0.0024746424,0.00044133214,0.1155529,0.0014145431,0.00029108181,0.000037247577,0.00060541776,0.78798985,0.005803525,0.023511317,0.057016622,0.004861487],"about_ca_topic_score_codex":0.0007513239,"about_ca_topic_score_gemma":0.00042165443,"teacher_disagreement_score":0.7658872,"about_ca_system_score_codex":0.000112614674,"about_ca_system_score_gemma":0.00013481181,"threshold_uncertainty_score":0.99989545},"labels":[],"label_agreement":null},{"id":"W2932065239","doi":"10.1007/978-3-030-16722-6_24","title":": Priority Aware Test Case Reduction","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reduction (mathematics); Test case; Debugging; Code coverage; Test (biology); Abstract syntax tree; Programming language; Queue; Priority queue; Process (computing); Set (abstract data type); Software; Reliability engineering; Machine learning; Parsing","score_opus":0.020987685690595698,"score_gpt":0.26446983885645753,"score_spread":0.24348215316586183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2932065239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010929722,0.00020383012,0.9907758,0.00047082134,0.002251943,0.00042727744,0.000005987431,0.0042348076,0.0015202133],"genre_scores_gemma":[0.35891548,0.000020834615,0.6391354,0.00053009967,0.0006267694,0.000008802666,0.000004338587,0.000048509286,0.0007097248],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99633354,0.000031199186,0.00047149853,0.0017449083,0.0007962835,0.0006225484],"domain_scores_gemma":[0.9960145,0.0010144563,0.0003132763,0.0021464531,0.000347571,0.00016374861],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009940685,0.0005330715,0.00049472635,0.00079132227,0.0003223451,0.0005821961,0.0024553505,0.000401128,0.000010502899],"category_scores_gemma":[0.0004209557,0.00050489453,0.00012865181,0.00066068897,0.00048460276,0.0006126887,0.0014043176,0.0010209137,0.00007658088],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021097762,0.000043542306,0.00039192953,0.000068436326,0.0000058967958,0.0013076346,0.000515862,0.0020060895,0.00004402295,0.0030976841,0.00042968063,0.9920871],"study_design_scores_gemma":[0.00027363765,0.00049568526,0.00015794979,0.0010000769,0.000015584475,0.014064793,1.04561835e-7,0.4465648,0.00125735,0.5332011,0.0015042109,0.0014647243],"about_ca_topic_score_codex":0.000111458176,"about_ca_topic_score_gemma":0.000025381674,"teacher_disagreement_score":0.9906224,"about_ca_system_score_codex":0.00040985152,"about_ca_system_score_gemma":0.0008978705,"threshold_uncertainty_score":0.99974024},"labels":[],"label_agreement":null},{"id":"W2942132945","doi":"10.1007/978-3-030-10543-3_13","title":"Evaluation and Application of Two Fuzzing Approaches for Security Testing of IoT Applications","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Fuzz testing; Computer science; Software quality; Software security assurance; Software bug; Software; Software reliability testing; Software quality assurance; Software metric; Security testing; Code coverage; Leverage (statistics); Software testing; Reliability engineering; Software engineering; Software development; Computer security; Machine learning; Operating system; Engineering; Information security","score_opus":0.10769492292998101,"score_gpt":0.318746074156001,"score_spread":0.21105115122601997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942132945","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029111401,0.0004166635,0.93424547,0.000026510408,0.000018307874,0.001695701,0.000010119868,0.0009919351,0.06256619],"genre_scores_gemma":[0.13542238,0.000007255389,0.8630742,0.000019528421,0.000059916998,0.0003607821,0.000027847991,0.0000271535,0.0010009533],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987103,0.000018113542,0.00038371238,0.00044099387,0.00034413938,0.000102773934],"domain_scores_gemma":[0.99720603,0.0008657822,0.000569216,0.00067318743,0.0006563895,0.000029381115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312689,0.00016616115,0.00028791497,0.000157447,0.00005544124,0.00002848466,0.00038116073,0.00013213471,0.0000012176092],"category_scores_gemma":[0.00021665232,0.00016473673,0.000058567515,0.000079352205,0.00006826081,0.0000811396,0.00016782788,0.000099387864,0.0000013769971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.756343e-7,0.000015022635,0.00014172756,0.00023347883,0.000016924134,1.0268042e-8,0.00007350635,0.00006719798,0.00007037337,0.46827745,0.00009201412,0.53101134],"study_design_scores_gemma":[0.00012272934,0.000051618248,0.00002629055,0.00011364264,0.000058013855,0.0000028037362,0.0000013328605,0.39241198,0.0004252493,0.60606706,0.00058676087,0.00013249075],"about_ca_topic_score_codex":0.000045975285,"about_ca_topic_score_gemma":0.0000046626715,"teacher_disagreement_score":0.53087884,"about_ca_system_score_codex":0.000038105733,"about_ca_system_score_gemma":0.00015565912,"threshold_uncertainty_score":0.6717769},"labels":[],"label_agreement":null},{"id":"W2948233389","doi":"10.1007/978-3-030-27455-9_10","title":"Revisiting Hyper-Parameter Tuning for Search-Based Test Data Generation","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Metric (unit); Replicate; Heuristic; Computer science; Baseline (sea); Software; Performance metric; Minor (academic); Space (punctuation); Machine learning; Artificial intelligence; Mathematics; Statistics; Engineering","score_opus":0.10774043282988424,"score_gpt":0.338558522507848,"score_spread":0.23081808967796377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948233389","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031633112,0.00022769118,0.9900155,0.0016168638,0.0015607438,0.000830434,0.000028056513,0.0025524914,0.0000049119935],"genre_scores_gemma":[0.44976276,0.000002577875,0.5486687,0.0009821662,0.000486328,0.000025226254,0.000054392596,0.000017390495,4.6232637e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951863,0.00013579191,0.00053038273,0.0025628041,0.00080356473,0.00078110024],"domain_scores_gemma":[0.9898111,0.004850256,0.0002798582,0.0045135287,0.00042163554,0.0001236027],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0037943022,0.00043269567,0.00048742065,0.00066825974,0.00034098816,0.001806975,0.0076889326,0.0002689332,0.0000012942847],"category_scores_gemma":[0.005104656,0.00040955198,0.00009606963,0.0011446106,0.00027234596,0.000663816,0.006752377,0.0008930711,0.0000068780964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020818877,0.00003831836,0.006524108,0.00017402731,0.0000036781707,0.000006986098,0.00022857964,0.29289812,0.0008393793,0.00003237216,0.00017274628,0.69907963],"study_design_scores_gemma":[0.00016980815,0.0000977124,0.00037465512,0.0006934525,0.000006661329,0.000015167858,4.8271126e-8,0.9807246,0.003925843,0.013460666,0.00004552987,0.00048587786],"about_ca_topic_score_codex":0.00010480513,"about_ca_topic_score_gemma":0.0000068787012,"teacher_disagreement_score":0.69859374,"about_ca_system_score_codex":0.00024036475,"about_ca_system_score_gemma":0.001199547,"threshold_uncertainty_score":0.9998356},"labels":[],"label_agreement":null},{"id":"W2950434324","doi":"10.82308/1356","title":"On testing concurrent systems through contexts of queues","year":2006,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; McGill University; Microsoft Research","keywords":"Asynchronous communication; Computer science; Queue; Atomicity; Fork–join queue; Distributed computing; Queue management system; Programming language; Computer network","score_opus":0.032207299057107355,"score_gpt":0.2550858479032864,"score_spread":0.22287854884617908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950434324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85931903,0.001344532,0.003158144,0.00007307604,0.0027865262,0.0013111164,0.00032135003,0.024283608,0.10740263],"genre_scores_gemma":[0.97207785,0.000006362029,0.027400816,0.00018728002,0.000042074007,0.00005828767,0.0000075044954,0.000047995232,0.00017181672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966908,0.0003230262,0.0008289592,0.0008327449,0.00072407856,0.00060036476],"domain_scores_gemma":[0.9958941,0.0019118119,0.0005387186,0.0010335688,0.0004961303,0.0001257216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095492305,0.00042457352,0.0005471874,0.00019528074,0.0005499928,0.00014577016,0.0012306893,0.00019585862,0.0000046927394],"category_scores_gemma":[0.0020833092,0.00040349123,0.00015313544,0.0007853688,0.00012005715,0.0007798579,0.00037572335,0.000514422,0.000064989996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007869244,0.00023633032,0.0004410427,0.00010670427,0.000023343466,0.00004791826,0.0000045593306,0.00036320044,0.0042091412,0.91723806,0.00019206588,0.07712977],"study_design_scores_gemma":[0.0014707962,0.001199769,0.0019977035,0.0023694716,0.0000536984,0.00023260195,0.000010723709,0.009239515,0.10364926,0.8632934,0.014874032,0.0016090325],"about_ca_topic_score_codex":0.0021564662,"about_ca_topic_score_gemma":0.000025874031,"teacher_disagreement_score":0.11275885,"about_ca_system_score_codex":0.00025715356,"about_ca_system_score_gemma":0.00003835361,"threshold_uncertainty_score":0.9998417},"labels":[],"label_agreement":null},{"id":"W2951101154","doi":"10.1109/icstw.2019.00029","title":"Using Imprecise Test Oracles Modelled by FSM","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Oracle; Nondeterministic algorithm; Computer science; Context (archaeology); Finite-state machine; Conformance testing; Set (abstract data type); Test case; Theoretical computer science; Algorithm; Machine learning; Programming language","score_opus":0.027730293977826826,"score_gpt":0.27313344330657946,"score_spread":0.24540314932875262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951101154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055678986,0.00007404525,0.92784816,0.00012514582,0.00012187764,0.00012371874,0.0000013559044,0.010516766,0.005509941],"genre_scores_gemma":[0.5360222,0.000002020894,0.4627354,0.00023720045,0.000012086284,0.0000026392602,6.4291646e-7,0.000008269535,0.0009795566],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991453,0.000018331279,0.00014091154,0.0003105647,0.00017050577,0.00021435176],"domain_scores_gemma":[0.99887604,0.0003517048,0.000049294333,0.0006016337,0.000059375616,0.0000619583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018713211,0.00011016419,0.0001263466,0.00006133123,0.000060572234,0.00013762692,0.0006079732,0.00005302432,0.000031765838],"category_scores_gemma":[0.00012517489,0.00009263414,0.000038352824,0.00022466229,0.000015480273,0.0003063253,0.0002447055,0.00008069485,0.0001268565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014790076,0.000736149,0.13013597,0.000088634006,0.000041940184,0.00003170309,0.0010239378,0.0026602917,0.07771545,0.017343257,0.59437144,0.17583643],"study_design_scores_gemma":[0.0001332252,0.000054674012,0.00006946889,0.000026510561,0.0000020934722,0.000016604396,0.0000012104299,0.96890223,0.0057090726,0.024052957,0.0008421489,0.00018978427],"about_ca_topic_score_codex":0.00019436116,"about_ca_topic_score_gemma":6.6049597e-7,"teacher_disagreement_score":0.96624196,"about_ca_system_score_codex":0.000027534392,"about_ca_system_score_gemma":0.000038246722,"threshold_uncertainty_score":0.37775105},"labels":[],"label_agreement":null},{"id":"W2952903800","doi":"10.1109/icst.2019.00019","title":"BugsJS: a Benchmark of JavaScript Bugs","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"JavaScript; Unobtrusive JavaScript; Computer science; Benchmark (surveying); Programming language; Test case; Software bug; Unit testing; Rich Internet application; Operating system; Database; Software; Machine learning","score_opus":0.004992930306730839,"score_gpt":0.20213004230445228,"score_spread":0.19713711199772144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952903800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07177263,0.00017385061,0.8034472,0.00052005,0.0006268471,0.00024785928,9.780554e-7,0.013594849,0.10961574],"genre_scores_gemma":[0.675952,0.0000018749266,0.32252392,0.0002777603,0.000010572793,0.0000033683887,4.2464643e-7,0.000003838832,0.0012262354],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992791,0.000019867866,0.00015444089,0.00021581168,0.0001820731,0.00014874265],"domain_scores_gemma":[0.99902314,0.00015015702,0.00005727322,0.00065849215,0.00007230979,0.000038651575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023337938,0.00007520448,0.00012828337,0.000081447346,0.00001817591,0.000032045944,0.0006472999,0.000037968468,0.000080915226],"category_scores_gemma":[0.0000950806,0.00006206841,0.000049926017,0.00025610466,0.000019506533,0.000178754,0.00019817639,0.00005767579,0.000099071585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009027037,0.00024563144,0.17166631,0.00013945882,0.00004434886,0.000012764735,0.0012486605,0.000025211835,0.00544961,0.3021294,0.39566785,0.12336176],"study_design_scores_gemma":[0.0013267015,0.0014814534,0.051346406,0.00048681002,0.000020301442,0.00013784658,0.000036916674,0.13053845,0.0793455,0.694615,0.039224893,0.0014397156],"about_ca_topic_score_codex":0.00015306911,"about_ca_topic_score_gemma":9.568513e-7,"teacher_disagreement_score":0.6041794,"about_ca_system_score_codex":0.000010559447,"about_ca_system_score_gemma":0.000035794987,"threshold_uncertainty_score":0.2531076},"labels":[],"label_agreement":null},{"id":"W2953988581","doi":"10.1109/icse-companion.2019.00095","title":"Supervised Tie Breaking in Test Case Prioritization","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Prioritization; Test (biology); Test case; Code coverage; Rank (graph theory); Data mining; Code (set theory); Cover (algebra); Reliability engineering; Machine learning; Software; Engineering; Mathematics; Programming language; Regression analysis","score_opus":0.011334825375838005,"score_gpt":0.2420150815609072,"score_spread":0.2306802561850692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953988581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3829471,0.000042393694,0.5902582,0.00039810827,0.00021566969,0.00029424703,6.6574785e-7,0.01354191,0.012301748],"genre_scores_gemma":[0.83617634,5.5652157e-7,0.16340773,0.00023222993,0.000012173259,0.000004346861,6.7679287e-7,0.0000048221946,0.00016113075],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994027,0.000018851035,0.00012423264,0.00021375368,0.00009618691,0.00014429995],"domain_scores_gemma":[0.99923253,0.00032845975,0.000023131352,0.0003487219,0.000039342245,0.000027814991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020643858,0.00006548382,0.00007742754,0.00010880538,0.000031975134,0.000088888264,0.00023839188,0.00003738146,0.000017664355],"category_scores_gemma":[0.00019621864,0.000060988903,0.000015569327,0.00035286235,0.0000073175524,0.00027023788,0.000108532295,0.000064951884,0.000059063168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016174671,0.0001371684,0.7808908,0.00004455859,0.000002411444,0.0010532739,0.00094417017,0.000049338836,0.0008094914,0.012380686,0.004005348,0.1996811],"study_design_scores_gemma":[0.00090482726,0.00025571886,0.033088773,0.0002485373,0.0000031467157,0.0034785941,0.000028980177,0.9171303,0.0036111095,0.039760813,0.0008352531,0.00065396074],"about_ca_topic_score_codex":0.00046379346,"about_ca_topic_score_gemma":0.0000320689,"teacher_disagreement_score":0.91708094,"about_ca_system_score_codex":0.000030125748,"about_ca_system_score_gemma":0.000032507294,"threshold_uncertainty_score":0.24870554},"labels":[],"label_agreement":null},{"id":"W2954796040","doi":"10.1109/tse.2019.2925345","title":"What's Wrong with My Benchmark Results? Studying Bad Practices in JMH Benchmarks","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Vetenskapsrådet","keywords":"Java; Computer science; Benchmark (surveying); Software engineering; Open source; Statement (logic); Best practice; Empirical research; Software; Programming language; Data science","score_opus":0.01793363133666667,"score_gpt":0.24993281964352593,"score_spread":0.23199918830685926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954796040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07382603,0.00013755471,0.91898364,0.00012460083,0.0012392648,0.000403094,0.0000040830682,0.005169,0.000112709764],"genre_scores_gemma":[0.7595155,0.00004607663,0.24012844,0.000070411836,0.000031204567,0.00008155946,0.0000032838204,0.000034878965,0.00008862618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777657,0.00005941518,0.00041833645,0.000764256,0.0004694482,0.00051200186],"domain_scores_gemma":[0.99717367,0.0014398847,0.00021930505,0.00095664285,0.00008918594,0.0001213108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006560662,0.0003459589,0.00031979464,0.00052756886,0.00012421641,0.00047787308,0.00071298686,0.00013945073,0.000022664757],"category_scores_gemma":[0.000204238,0.0003313332,0.000080642465,0.0010221279,0.000022384744,0.0025142143,0.000011149674,0.0007238356,0.000027365028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002215205,0.0006896333,0.008703062,0.00029622167,0.00018809148,0.000253799,0.005541131,0.86862385,0.00041417946,0.00022428493,0.00085291464,0.113991335],"study_design_scores_gemma":[0.007951595,0.0036970542,0.030886423,0.011039438,0.00016141414,0.0006243855,0.0008534196,0.91278416,0.020804906,0.00079292286,0.0049359966,0.0054682964],"about_ca_topic_score_codex":0.0001317928,"about_ca_topic_score_gemma":0.000036293364,"teacher_disagreement_score":0.6856895,"about_ca_system_score_codex":0.00016528962,"about_ca_system_score_gemma":0.000091458634,"threshold_uncertainty_score":0.9999139},"labels":[],"label_agreement":null},{"id":"W2955338589","doi":"10.22215/etd/2018-13266","title":"FSM Testing Based on Transition Trees and Complete Round Trip Paths Testing Criteria","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Tree traversal; Random testing; Test suite; Algorithm; Tree (set theory); Computer science; Finite-state machine; Test case; Fault tree analysis; Mathematics; Engineering; Machine learning; Combinatorics; Reliability engineering","score_opus":0.06657820508724317,"score_gpt":0.3033449460471787,"score_spread":0.23676674095993555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955338589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05515832,0.00014253103,0.8753693,0.0003162498,0.0013333616,0.00094565103,0.000041417377,0.03267113,0.034022007],"genre_scores_gemma":[0.32426685,6.838709e-7,0.67452145,0.00054924295,0.00019438578,0.00004800314,0.00013544601,0.00004506367,0.00023888807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771893,0.00012436899,0.00046459417,0.00089824205,0.0004198404,0.00037404345],"domain_scores_gemma":[0.9966273,0.001897974,0.00028249068,0.0006430332,0.00042706,0.00012214457],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060076715,0.00045648936,0.0004214865,0.00037363401,0.00042084808,0.0006315889,0.0005706516,0.00026092134,0.000012810625],"category_scores_gemma":[0.0017816906,0.0004294913,0.00007228065,0.00062467845,0.000053570828,0.00028649997,0.000039869872,0.00030874892,0.000013470658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021668665,0.0006309065,0.0023302054,0.0015179267,0.000076017575,0.0002463037,0.0047806874,0.00011885125,0.012584751,0.0027976208,0.030023415,0.94467664],"study_design_scores_gemma":[0.00054467225,0.0013618567,0.0145414965,0.0024571985,0.00004957541,0.000045830973,0.000035982186,0.9470071,0.0010394972,0.03172287,0.00019974711,0.0009941402],"about_ca_topic_score_codex":0.00043909936,"about_ca_topic_score_gemma":0.00006522318,"teacher_disagreement_score":0.94688827,"about_ca_system_score_codex":0.000059959657,"about_ca_system_score_gemma":0.00015066088,"threshold_uncertainty_score":0.9998157},"labels":[],"label_agreement":null},{"id":"W2955364532","doi":"10.1109/icse-seip.2019.00031","title":"Improving Test Effectiveness Using Test Executions History: An Industrial Experience Report","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Test (biology); Test Management Approach; Test strategy; Regression testing; Integration testing; Prioritization; Software engineering; Selection (genetic algorithm); System integration testing; Test case; Risk-based testing; Software; Reliability engineering; Software quality; Software development; Process management; Machine learning; Engineering; Software construction","score_opus":0.0682729781571386,"score_gpt":0.2945401461666829,"score_spread":0.22626716800954427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955364532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4645027,0.000025026748,0.52307117,0.000022285412,0.001021036,0.00033926213,9.551785e-7,0.009722459,0.0012951379],"genre_scores_gemma":[0.86580473,1.8556257e-7,0.13375488,0.00006846987,0.00009614269,0.00002805893,0.0000019715092,0.000014274836,0.00023131374],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984578,0.000073017574,0.00025699227,0.00064194825,0.0002657699,0.00030448838],"domain_scores_gemma":[0.99740106,0.0010528923,0.00017121565,0.0011165894,0.00013705973,0.0001212108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068576256,0.00017253048,0.00019699546,0.0001353308,0.0001401626,0.00012677893,0.0007063788,0.000118704884,0.000023574074],"category_scores_gemma":[0.00243067,0.00016280795,0.00004978952,0.0003304384,0.000066622364,0.000900196,0.00028238265,0.00018946531,0.00001645847],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007049261,0.00044776697,0.8881969,0.000034139037,0.0000070497313,0.00024846313,0.0010656014,0.00007823862,0.08690126,0.0018047635,0.0025447123,0.018664049],"study_design_scores_gemma":[0.0021573359,0.0025836066,0.058047757,0.0007603262,0.000048910308,0.00420463,0.00013520842,0.84611815,0.06814205,0.0067491126,0.007942585,0.0031103017],"about_ca_topic_score_codex":0.0016182269,"about_ca_topic_score_gemma":0.000004071426,"teacher_disagreement_score":0.84603995,"about_ca_system_score_codex":0.00043321252,"about_ca_system_score_gemma":0.0003515922,"threshold_uncertainty_score":0.6639115},"labels":[],"label_agreement":null},{"id":"W2955925687","doi":"10.1109/icse.2019.00031","title":"Mining Historical Test Logs to Predict Bugs and Localize Faults in the Test Logs","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Flagging; Fault (geology); Product (mathematics); Data mining; Test data; Software; Reliability engineering; Engineering; Mathematics; Software engineering","score_opus":0.016333578780329608,"score_gpt":0.2420664346322286,"score_spread":0.225732855851899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955925687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3090145,0.00043128015,0.6241236,0.020350471,0.0009449947,0.0015377733,0.0000053666986,0.018230388,0.025361631],"genre_scores_gemma":[0.87045723,0.0000027675237,0.1260328,0.0023267793,0.00004211523,0.000023702456,4.873035e-7,0.00000892935,0.0011051821],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871725,0.000045963912,0.000221858,0.00044390984,0.0002747561,0.0002962532],"domain_scores_gemma":[0.99586713,0.0033245368,0.00004549883,0.0006245449,0.000047532725,0.00009073496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006076462,0.00014719919,0.00017612522,0.00012271492,0.000062955194,0.000102296275,0.0008471625,0.000076112774,0.0000066790017],"category_scores_gemma":[0.0019806242,0.00009987742,0.00002620115,0.0004938775,0.000029681094,0.0001552443,0.00031525563,0.00016076575,0.00004840118],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004063507,0.00018116683,0.7937019,0.000022290877,0.0000025026204,0.000042924643,0.0021849922,0.000016767432,0.00013003472,0.00081809715,0.1726805,0.030214798],"study_design_scores_gemma":[0.0027004967,0.00663476,0.50777036,0.0009619997,0.00003275414,0.0010252759,0.00026291388,0.2979538,0.0012031546,0.04427424,0.13464855,0.0025317057],"about_ca_topic_score_codex":0.0006970458,"about_ca_topic_score_gemma":0.000031553063,"teacher_disagreement_score":0.56144273,"about_ca_system_score_codex":0.00011561133,"about_ca_system_score_gemma":0.000042508087,"threshold_uncertainty_score":0.40728828},"labels":[],"label_agreement":null},{"id":"W2960484385","doi":"10.1145/3356773.3356801","title":"The State and Future of Genetic Improvement","year":2019,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Engineering and Physical Sciences Research Council","keywords":"Maintainability; Session (web analytics); State (computer science); Software; Software development","score_opus":0.006067583557949196,"score_gpt":0.20652276807165942,"score_spread":0.20045518451371022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960484385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80939615,0.0036154718,0.18035248,0.00050395995,0.0008425353,0.00036996772,0.0000061004707,0.004910514,0.0000028241036],"genre_scores_gemma":[0.72978383,0.0001262096,0.2699072,0.000057580055,0.000057489022,0.000017013792,6.8849147e-7,0.000018112321,0.000031863547],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99898344,0.000012318503,0.0002350007,0.0002805019,0.0002118249,0.00027689282],"domain_scores_gemma":[0.98258954,0.016169297,0.0000916023,0.0010063411,0.000079364276,0.000063842774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00022618187,0.00017023759,0.00016520117,0.00006822271,0.00007175068,0.00009331445,0.0008843581,0.000051035277,0.0000029077378],"category_scores_gemma":[0.008953884,0.00012751378,0.000044959284,0.00020969739,0.000027576389,0.00012328998,0.00048048203,0.000139863,0.000009341683],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055280148,0.000023626462,0.38305563,0.00018090251,0.000039142116,0.000006422904,0.0006263403,0.0004028304,0.0020242776,0.00086162286,0.0007668312,0.61200684],"study_design_scores_gemma":[0.0008773252,0.0010768897,0.9289859,0.0003562528,0.000030464065,0.00008183635,0.000013871207,0.012482004,0.025534013,0.01265967,0.016591363,0.0013103941],"about_ca_topic_score_codex":0.00003139494,"about_ca_topic_score_gemma":7.6243083e-7,"teacher_disagreement_score":0.61069643,"about_ca_system_score_codex":0.000018601619,"about_ca_system_score_gemma":0.000030556028,"threshold_uncertainty_score":0.9993941},"labels":[],"label_agreement":null},{"id":"W2964374341","doi":"10.1007/978-3-030-28423-7_9","title":"Mutant Accuracy Testing for Assessing the Implementation of Numerical Algorithms","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Implementation; Computer science; MATLAB; Algorithm; Regression testing; Process (computing); Mutation; Software; Software development; Programming language","score_opus":0.0439389944210681,"score_gpt":0.3484687972418413,"score_spread":0.30452980282077324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964374341","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011002786,0.00010050008,0.99685097,0.0004441252,0.0007903815,0.0006396226,0.0000058649835,0.00085405825,0.00020444582],"genre_scores_gemma":[0.2230105,0.0000020221319,0.77629673,0.00045351894,0.00018552957,0.000014339201,0.0000029157245,0.00002218295,0.000012242409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973727,0.00003475153,0.0005547466,0.00089827436,0.0006804485,0.00045911086],"domain_scores_gemma":[0.99237895,0.0054757693,0.0006062942,0.0010476678,0.00043470075,0.00005661686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014115212,0.00032876572,0.00040207154,0.00033734573,0.0002649834,0.0004981074,0.0024966658,0.00014256504,0.0000031347972],"category_scores_gemma":[0.00083972636,0.00024093708,0.00011038088,0.0005772704,0.00029049578,0.00050268625,0.00084289344,0.00041149725,0.0000028309096],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.6195023e-7,0.000008751511,0.0007838173,0.000039015056,0.0000053222825,0.0000034237185,0.0003622708,0.0016730035,0.00013426733,0.0021409206,0.000030520074,0.99481815],"study_design_scores_gemma":[0.00018460372,0.00023683457,0.0009564937,0.00044964286,0.000011579764,0.00006352602,3.8050936e-7,0.7377296,0.002588332,0.25719336,0.00019526815,0.00039037174],"about_ca_topic_score_codex":0.000084014806,"about_ca_topic_score_gemma":0.0000037800362,"teacher_disagreement_score":0.99442774,"about_ca_system_score_codex":0.0001570782,"about_ca_system_score_gemma":0.0008993324,"threshold_uncertainty_score":0.9825129},"labels":[],"label_agreement":null},{"id":"W2967858513","doi":"10.1145/3338906.3338908","title":"Concolic testing for models of state-based systems","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Concolic testing; Computer science; White-box testing; Model-based testing; Symbolic execution; Test case; Integration testing; System under test; Benchmark (surveying); Keyword-driven testing; Random testing; Unified Modeling Language; Manual testing; Test strategy; Code coverage; Non-regression testing; Unit testing; Context (archaeology); System testing; Regression testing; Software; Software engineering; Programming language; Software system; Machine learning; Software construction","score_opus":0.057612966011510496,"score_gpt":0.27455193970213226,"score_spread":0.21693897369062176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967858513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01799664,0.00003161335,0.9742485,0.000031751977,0.00012994521,0.0003805849,0.000002686164,0.0048562256,0.0023220521],"genre_scores_gemma":[0.61537194,5.900105e-8,0.3843923,0.00006927577,0.0000061679284,0.000025048248,4.5660252e-7,0.000005064522,0.00012971173],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992945,0.000019892626,0.00019528378,0.00019723512,0.00013252845,0.00016057004],"domain_scores_gemma":[0.9980988,0.001128998,0.00010559873,0.00040653834,0.0002252698,0.00003478998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003523683,0.00007454294,0.00015708072,0.00007052929,0.000025681546,0.00005210178,0.00040707094,0.000028457798,8.6486966e-7],"category_scores_gemma":[0.00017990917,0.00006280458,0.00003332287,0.00020251924,0.000013663932,0.00015037761,0.000055487417,0.00003293992,0.000004822995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007114222,0.0005459207,0.11976298,0.0029919858,0.000092146474,0.00001082956,0.0014838657,0.35792345,0.020030618,0.31682247,0.055677556,0.12458703],"study_design_scores_gemma":[0.00019917934,0.00021256528,0.00007251902,0.00008973184,0.0000013660211,0.0000020995703,0.000001495849,0.96413916,0.0036432552,0.03148832,0.00006277514,0.0000875209],"about_ca_topic_score_codex":0.00029432445,"about_ca_topic_score_gemma":5.945259e-7,"teacher_disagreement_score":0.6062157,"about_ca_system_score_codex":0.000019095329,"about_ca_system_score_gemma":0.00010792948,"threshold_uncertainty_score":0.25610965},"labels":[],"label_agreement":null},{"id":"W2972465897","doi":"10.1007/s10009-019-00530-6","title":"Diversity of graph models and graph generators in mutation testing","year":2019,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Emberi Eroforrások Minisztériuma; Natural Sciences and Engineering Research Council of Canada; Magyar Tudományos Akadémia; Budapesti Műszaki és Gazdaságtudományi Egyetem","keywords":"Computer science; Test suite; Predicate abstraction; Random testing; Graph; Model-based testing; Theoretical computer science; Predicate (mathematical logic); Software quality; Programming language; Test case; Software; Software engineering; Model checking; Machine learning; Software development","score_opus":0.03993430915760716,"score_gpt":0.26907315315342245,"score_spread":0.2291388439958153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972465897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48339877,0.000045145644,0.5152939,0.00027012968,0.00019311,0.000113332244,0.0000067595242,0.000665189,0.000013688547],"genre_scores_gemma":[0.8154672,0.000020953203,0.18432042,0.00015157784,0.000014873396,0.000011130752,0.0000018351494,0.000008557595,0.0000035046755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887997,0.000024669256,0.00032867678,0.0002738771,0.00030790397,0.00018490401],"domain_scores_gemma":[0.9987747,0.0005012092,0.000086703854,0.00018100493,0.00041790018,0.000038469992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036219976,0.00013529176,0.00019973585,0.0009920273,0.00013698587,0.00006986558,0.00082330266,0.00015470001,0.000001952164],"category_scores_gemma":[0.00043704588,0.00012893345,0.0000791834,0.00043560535,0.0000721038,0.00066955003,0.00018063115,0.00028861928,9.666547e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017769878,0.00034334042,0.39057514,0.000055316723,0.00020421397,0.00015991004,0.0012351669,0.007601483,0.0012036558,0.123929776,0.00023009289,0.4742842],"study_design_scores_gemma":[0.0016964156,0.00074553915,0.009124073,0.00032797255,0.000013837129,0.0004183487,0.00002264969,0.013364053,0.0071607754,0.9667837,0.000043233686,0.00029939305],"about_ca_topic_score_codex":0.000016430917,"about_ca_topic_score_gemma":0.000003757841,"teacher_disagreement_score":0.84285396,"about_ca_system_score_codex":0.000054897468,"about_ca_system_score_gemma":0.000044137545,"threshold_uncertainty_score":0.5257754},"labels":[],"label_agreement":null},{"id":"W2977837980","doi":"10.1109/qrs.2019.00049","title":"Fault Detection in Timed FSM with Timeouts by SAT-Solving","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Scalability; Implementation; Lift (data mining); Finite-state machine; Fault injection; Fault detection and isolation; Constraint (computer-aided design); Model checking; Fault coverage; Distributed computing; Embedded system; Real-time computing; Programming language; Software; Data mining; Artificial intelligence; Actuator","score_opus":0.0050325935670965626,"score_gpt":0.20667492671879337,"score_spread":0.2016423331516968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977837980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21601422,0.000037671838,0.76723033,0.0001761412,0.00010348702,0.00020225992,3.0564905e-7,0.009639626,0.00659597],"genre_scores_gemma":[0.8786281,6.7150637e-7,0.11987093,0.00021890158,0.000008218203,0.000009690057,8.8124324e-7,0.000007799303,0.0012548047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992033,0.000027538841,0.0001132332,0.0002930042,0.00016508688,0.00019779337],"domain_scores_gemma":[0.99936724,0.00014211501,0.000041310712,0.0003754348,0.000035295645,0.00003863434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020268092,0.00009569811,0.0001039372,0.000097928845,0.000032431835,0.0000832428,0.00032075774,0.00005091262,0.000018631214],"category_scores_gemma":[0.000053871056,0.00007503905,0.000015866859,0.00033381762,0.000012176263,0.0002601175,0.000088119035,0.00011573417,0.00017368855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052330168,0.000283079,0.23585352,0.00007215222,0.00003247187,0.00005358085,0.0016098107,0.00027960265,0.033913486,0.0011667104,0.053087175,0.6735961],"study_design_scores_gemma":[0.0015965839,0.0011367447,0.033062592,0.00036363263,0.000007813133,0.00016355162,0.00001588883,0.8157157,0.13079014,0.012333802,0.0035906117,0.0012229694],"about_ca_topic_score_codex":0.00033772376,"about_ca_topic_score_gemma":0.0000350454,"teacher_disagreement_score":0.81543607,"about_ca_system_score_codex":0.000043206892,"about_ca_system_score_gemma":0.000022667298,"threshold_uncertainty_score":0.30600038},"labels":[],"label_agreement":null},{"id":"W2978909621","doi":"10.1109/qrs.2019.00055","title":"Efficient Generation of Test Data with Extended Cardinality Constraints","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Cardinality (data modeling); Computer science; Theoretical computer science; Extension (predicate logic); Translation (biology); Graph; Algorithm; Programming language; Data mining","score_opus":0.05952479385163361,"score_gpt":0.28876779762455956,"score_spread":0.22924300377292595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978909621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10461644,0.000013514919,0.8895101,0.000088565146,0.00007043219,0.00014495855,0.000008565005,0.0020558895,0.0034915318],"genre_scores_gemma":[0.7047914,1.6890512e-7,0.2951042,0.000044916742,0.000010020373,0.000001441444,0.000005902112,0.0000022384581,0.000039697396],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992348,0.000024810817,0.0001249975,0.0003090752,0.00020275073,0.00010358713],"domain_scores_gemma":[0.99835575,0.00018319585,0.000064333595,0.0012678772,0.00009877834,0.000030075491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040252312,0.00006621767,0.00010865008,0.00003550651,0.000025121495,0.000037023932,0.00064508995,0.000022594211,0.000014632158],"category_scores_gemma":[0.00016138874,0.00004765465,0.000012381274,0.000161187,0.000059462076,0.00007601664,0.0002514576,0.000043251617,0.000012156532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002143537,0.0012224008,0.5068702,0.00019724245,0.00010398332,0.000040452218,0.00086599024,0.0034589928,0.01902378,0.073143825,0.044235673,0.35081604],"study_design_scores_gemma":[0.0002557716,0.0002932206,0.017786209,0.00004648315,0.0000071607096,0.00004955837,0.0000050738167,0.9743056,0.0060721,0.00092387997,0.0000803772,0.00017455568],"about_ca_topic_score_codex":0.00007490299,"about_ca_topic_score_gemma":0.000002731334,"teacher_disagreement_score":0.9708466,"about_ca_system_score_codex":0.000011050202,"about_ca_system_score_gemma":0.000072513096,"threshold_uncertainty_score":0.19433002},"labels":[],"label_agreement":null},{"id":"W2979344318","doi":"10.1007/978-3-030-31280-0_7","title":"Multiple Mutation Testing for Timed Finite State Machine with Timed Guards and Timeouts","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Finite-state machine; Process (computing); State (computer science); Test suite; Fault (geology); Mutation; Domain (mathematical analysis); Enumeration; Theoretical computer science; Fault injection; Model checking; Algorithm; Test case; Programming language; Software; Mathematics; Machine learning","score_opus":0.01965444124293541,"score_gpt":0.245311961391384,"score_spread":0.2256575201484486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979344318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022832768,0.00019875358,0.995708,0.0001833715,0.00031185435,0.000837555,0.000020036603,0.0021027497,0.00040933344],"genre_scores_gemma":[0.11597831,0.0000031610964,0.8829193,0.0005567756,0.00009391554,0.000022390068,0.00001586112,0.00004745667,0.00036282503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969926,0.000027237045,0.00039977542,0.0014022959,0.0006168787,0.00056124],"domain_scores_gemma":[0.9937981,0.004349529,0.00035462374,0.00094584207,0.00042235412,0.00012958232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008971731,0.00050053775,0.00049162377,0.00060261646,0.0002463526,0.0005016203,0.0012940026,0.00018236741,0.0000022732747],"category_scores_gemma":[0.0009830432,0.0004155098,0.000054574877,0.0004698645,0.0003757482,0.00042139506,0.0006196207,0.00045959855,0.000011913869],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025227497,0.000020628087,0.0014269938,0.000108477994,0.000015564872,0.000080523605,0.00058016053,0.02684114,0.00006286579,0.0002564404,0.00005704503,0.9705249],"study_design_scores_gemma":[0.00047801613,0.0006040887,0.00032905684,0.00060290727,0.000010311122,0.0001577819,2.0807562e-8,0.90213996,0.00050967553,0.094492115,0.00014190003,0.00053413725],"about_ca_topic_score_codex":0.000085569525,"about_ca_topic_score_gemma":0.000054018656,"teacher_disagreement_score":0.9699908,"about_ca_system_score_codex":0.00013698127,"about_ca_system_score_gemma":0.00050986843,"threshold_uncertainty_score":0.99982965},"labels":[],"label_agreement":null},{"id":"W2987704219","doi":"10.1145/3356773.3356810","title":"Workshop Summary","year":2019,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software engineering; Software testing; Event (particle physics); Engineering management; Engineering; Library science; Software; Computer science; Programming language","score_opus":0.015181600319348384,"score_gpt":0.23504206514700132,"score_spread":0.21986046482765292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987704219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14692768,0.0011891995,0.77865803,0.00070540875,0.0017978761,0.00042130816,0.000006318111,0.07025093,0.000043219097],"genre_scores_gemma":[0.5742274,0.0000087095505,0.4252145,0.000239106,0.00008035465,0.00002298034,0.000006477136,0.000037979076,0.00016248877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823505,0.000022183245,0.00027455663,0.00058953784,0.00034086974,0.0005377856],"domain_scores_gemma":[0.94508797,0.052365407,0.000086116015,0.0021906972,0.0001035953,0.00016619907],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031050242,0.00031341062,0.00029404263,0.0002297328,0.000074189826,0.00019065445,0.002035742,0.00015790107,0.0000285636],"category_scores_gemma":[0.09301708,0.00031702616,0.000120553115,0.00062068773,0.000019367266,0.0005080043,0.00084944296,0.00034214827,0.00029608601],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000676408,0.00008111329,0.90213615,0.00018992773,0.000049578222,0.0000644009,0.00047441997,0.0017338585,0.00093476265,0.002824519,0.024718339,0.0667862],"study_design_scores_gemma":[0.0031575714,0.0010718999,0.7979361,0.004454044,0.00010858112,0.0007035083,0.00001977579,0.04993338,0.031331174,0.02134199,0.0806951,0.009246871],"about_ca_topic_score_codex":0.000025078818,"about_ca_topic_score_gemma":5.644876e-7,"teacher_disagreement_score":0.42729974,"about_ca_system_score_codex":0.00006346144,"about_ca_system_score_gemma":0.00005580295,"threshold_uncertainty_score":0.9999282},"labels":[],"label_agreement":null},{"id":"W2987942974","doi":"10.48550/arxiv.1911.07444","title":"A Code Injection Method for Rapid Docker Image Building","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Code (set theory); Image (mathematics); Computer science; Operating system; Programming language; Artificial intelligence","score_opus":0.08449209376665238,"score_gpt":0.25005849032487165,"score_spread":0.16556639655821925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987942974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006169886,0.00004099972,0.98465,0.00009205716,0.0008119173,0.00055679964,0.000019942576,0.0069900774,0.00066832674],"genre_scores_gemma":[0.37821752,0.000019378314,0.6209709,0.00012268449,0.00008113748,0.000004717747,0.000008997343,0.000025141768,0.00054951943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793124,0.00016740857,0.0001968195,0.0012484743,0.00008480349,0.00037122413],"domain_scores_gemma":[0.9972798,0.00068849605,0.00029686562,0.0013664215,0.00026848196,0.00009992818],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076888985,0.00031288844,0.00036595942,0.00037781746,0.0001747549,0.0002013606,0.0015597262,0.00031538517,0.0000067703595],"category_scores_gemma":[0.00027811588,0.0003636836,0.00027878577,0.00045841886,0.000045906614,0.00035975498,0.0015983252,0.0004809364,0.000024475265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032071068,0.000565677,0.008620992,0.0017889733,0.0007204561,0.00042347485,0.0017503382,0.38747022,0.0019584903,0.4015443,0.12170031,0.073136084],"study_design_scores_gemma":[0.00027433792,0.0000998894,0.0001145236,0.00013338342,0.00004848779,0.000014126562,0.0000049081063,0.7543625,0.0007980131,0.24259456,0.0011641895,0.0003910857],"about_ca_topic_score_codex":0.00022330528,"about_ca_topic_score_gemma":0.0000056815065,"teacher_disagreement_score":0.37204763,"about_ca_system_score_codex":0.00022972973,"about_ca_system_score_gemma":0.00018175159,"threshold_uncertainty_score":0.9998815},"labels":[],"label_agreement":null},{"id":"W2989862949","doi":"10.1109/models.2019.00-12","title":"Towards System-Level Testing with Coverage Guarantees for Autonomous Vehicles","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Test suite; Domain (mathematical analysis); Safety assurance; Geospatial analysis; Component (thermodynamics); Suite; Abstraction; Graph; Context (archaeology); Field (mathematics); Distributed computing; Test case; Software engineering; Reliability engineering; Theoretical computer science; Machine learning; Engineering","score_opus":0.036738859316262244,"score_gpt":0.24882340102546516,"score_spread":0.2120845417092029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989862949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03729326,0.0000306481,0.9376978,0.00015727358,0.00014448773,0.00042049092,0.000005376365,0.016069265,0.008181366],"genre_scores_gemma":[0.53978205,1.567855e-7,0.45962498,0.00014004947,0.000022679078,0.000032941865,8.632672e-7,0.000010792791,0.00038552532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988806,0.00002141865,0.00019093776,0.00040554666,0.00020187945,0.00029960193],"domain_scores_gemma":[0.9985233,0.0005863242,0.00009479447,0.0005599063,0.00018355188,0.000052144846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035769842,0.00016170688,0.0002109323,0.00008151153,0.00011235424,0.00021265492,0.00064451835,0.000053530803,0.0000022934457],"category_scores_gemma":[0.00017624571,0.00011784181,0.00004320625,0.0002565407,0.000020950376,0.00026894244,0.00013706821,0.00007500007,0.000032328222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008211792,0.00023557308,0.10106218,0.001388441,0.00012640905,0.000082879575,0.0012447871,0.0013052666,0.002530057,0.24375203,0.02133964,0.6268506],"study_design_scores_gemma":[0.0016994505,0.0019131007,0.020172933,0.0011144949,0.000026680282,0.00049740577,0.000043779073,0.9342243,0.010813862,0.026346903,0.001965825,0.0011812807],"about_ca_topic_score_codex":0.00027352376,"about_ca_topic_score_gemma":0.000003358718,"teacher_disagreement_score":0.932919,"about_ca_system_score_codex":0.00006536041,"about_ca_system_score_gemma":0.00015378659,"threshold_uncertainty_score":0.48054495},"labels":[],"label_agreement":null},{"id":"W2990853981","doi":"10.1109/models-c.2019.00008","title":"Querying Automotive System Models and Safety Artifacts with MMINT and Viatra","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Traceability; Computer science; Automotive industry; Domain (mathematical analysis); Software engineering; Hazard and operability study; Systems engineering; Engineering","score_opus":0.010829436579208016,"score_gpt":0.2034567904169108,"score_spread":0.1926273538377028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990853981","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11616125,0.000047334594,0.8720454,0.0001939817,0.000042380627,0.00019174692,4.693874e-7,0.006811822,0.0045056483],"genre_scores_gemma":[0.783204,0.000002678164,0.21656105,0.00011015328,0.000006375604,0.0000045631564,2.0924612e-7,0.000005955872,0.00010496921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999201,0.000029163823,0.000117715,0.00034071947,0.000137158,0.00017422631],"domain_scores_gemma":[0.9993169,0.00018073643,0.000049031183,0.00030820657,0.00006590265,0.00007922448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024442316,0.000114294606,0.00015011622,0.000059316055,0.0000757739,0.00014123094,0.00015451133,0.000039633167,0.0000011112091],"category_scores_gemma":[0.000017950935,0.000081049315,0.000011384434,0.00011060249,0.000028911412,0.0003953592,0.00015364622,0.00007703387,0.000007170967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011276532,0.00013485595,0.12644954,0.0010062227,0.00014802073,0.00014698981,0.010839015,0.003436792,0.00043410299,0.67961943,0.0025585506,0.17511371],"study_design_scores_gemma":[0.00034751618,0.00028354107,0.0070734276,0.00039708757,0.000008403371,0.00027046757,0.00007367333,0.9752617,0.00091933424,0.015005554,0.00004155791,0.00031775856],"about_ca_topic_score_codex":0.00014535703,"about_ca_topic_score_gemma":0.0000058713003,"teacher_disagreement_score":0.9718249,"about_ca_system_score_codex":0.000030216164,"about_ca_system_score_gemma":0.000030072077,"threshold_uncertainty_score":0.3305095},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03641849049665075,"score_gpt":0.2574023251371866,"score_spread":0.22098383464053584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994711059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7547442,0.00008471105,0.23526841,0.00038113023,0.00016791717,0.0005106825,0.0000030206397,0.008630551,0.00020937761],"genre_scores_gemma":[0.50786984,0.0000014617078,0.4917551,0.00028268035,0.0000131211345,0.000045170735,0.0000012303383,0.000012219283,0.000019204748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997443,0.00021551858,0.0006381865,0.00093896553,0.00034719243,0.00041714573],"domain_scores_gemma":[0.99470073,0.0033361125,0.00019749338,0.001136562,0.0004458889,0.00018323639],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002001292,0.00027230816,0.0003881939,0.00027132416,0.00022338553,0.00023293273,0.0006089333,0.00012298918,0.0000038561643],"category_scores_gemma":[0.024946714,0.00025259287,0.000046260135,0.0014874926,0.000105920924,0.00032764202,0.00035318424,0.00030406215,0.000045181037],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007048522,0.000078500525,0.88073,0.00023353094,0.000006837165,0.000006950198,0.0012438924,0.0015692114,0.0038560685,0.00022167045,0.00023586607,0.111810446],"study_design_scores_gemma":[0.0003309694,0.00023742297,0.7676047,0.00041724675,0.000012669134,0.000049865535,0.000046804143,0.20910786,0.0012360069,0.02008365,0.0002381691,0.00063465076],"about_ca_topic_score_codex":0.0004311439,"about_ca_topic_score_gemma":0.000011888509,"teacher_disagreement_score":0.25648668,"about_ca_system_score_codex":0.00014585207,"about_ca_system_score_gemma":0.0002463042,"threshold_uncertainty_score":0.9999926},"labels":[],"label_agreement":null},{"id":"W3000541349","doi":"10.1109/ase.2019.00132","title":"mCUTE: A Model-Level Concolic Unit Testing Engine for UML State Machines","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Concolic testing; Computer science; Unified Modeling Language; Model-based testing; Applications of UML; Finite-state machine; Programming language; Embedded system; Software; Symbolic execution; Test case","score_opus":0.09458609736607745,"score_gpt":0.30561833662574867,"score_spread":0.2110322392596712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000541349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01910992,0.000022386823,0.96686405,0.00027105602,0.00012348911,0.00036378644,0.000011825972,0.011113585,0.0021198767],"genre_scores_gemma":[0.30637097,7.6482405e-7,0.6903853,0.00054056867,0.000024162227,0.00004019293,0.0000027751767,0.000016009946,0.0026192837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888545,0.000019495003,0.00021790747,0.00037041033,0.00016616729,0.00034056313],"domain_scores_gemma":[0.99827653,0.0007828411,0.00008113282,0.00055984367,0.00021602504,0.00008363761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038199854,0.0001696452,0.00019522152,0.00011939023,0.00008994985,0.00013227478,0.0006904228,0.00004594199,0.000005481252],"category_scores_gemma":[0.000459859,0.0001432717,0.00005015001,0.00036800787,0.000018046363,0.00027373395,0.00023044445,0.000105052655,0.000034196997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025111347,0.00016550231,0.032208852,0.00023074773,0.00005229854,0.000012748769,0.0010555065,0.038080163,0.0018325727,0.030015793,0.043028437,0.8532923],"study_design_scores_gemma":[0.00027152017,0.00012459348,0.00049041386,0.000040160874,0.0000030779722,0.000016428305,6.348356e-7,0.93109643,0.0006123589,0.0667887,0.00034918194,0.00020647075],"about_ca_topic_score_codex":0.00017771962,"about_ca_topic_score_gemma":0.0000065872573,"teacher_disagreement_score":0.8930163,"about_ca_system_score_codex":0.000024301762,"about_ca_system_score_gemma":0.00011596253,"threshold_uncertainty_score":0.584245},"labels":[],"label_agreement":null},{"id":"W3004099993","doi":"10.1145/2499370.2462168","title":"Dynamic determinacy analysis","year":2013,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Static analysis; Programming language; JavaScript; Soundness; Determinacy; Program analysis; Functional programming; Leverage (statistics); Source code; Scalability; Theoretical computer science; Operating system; Artificial intelligence","score_opus":0.014623327021583827,"score_gpt":0.2669698366788959,"score_spread":0.2523465096573121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004099993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5483116,0.00020543754,0.43200195,0.0018229353,0.00025101352,0.0002437019,0.000003042766,0.015357362,0.0018029984],"genre_scores_gemma":[0.69096047,0.0000021393962,0.3086038,0.00027885937,0.000011387727,0.000018420622,0.0000034048783,0.00000509248,0.000116431846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898475,0.000044160824,0.000175346,0.00034229545,0.00019353948,0.0002598999],"domain_scores_gemma":[0.9977479,0.0007345052,0.00010206521,0.0012582878,0.00007139637,0.000085875225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016162063,0.00012909525,0.00018258936,0.00025601356,0.00010305503,0.0003218251,0.0017428516,0.000053101852,0.000052455274],"category_scores_gemma":[0.00057043385,0.00010982728,0.000085820626,0.000766006,0.000034354885,0.0005294134,0.00038605568,0.00009339131,0.0002948805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045396655,0.00020493219,0.35981765,0.00007220017,0.000573984,0.000119860975,0.002205783,0.0005020872,0.0007218871,0.0018752421,0.03933586,0.594566],"study_design_scores_gemma":[0.00014986082,0.00013508649,0.2869634,0.000032879798,0.00018742312,0.000018896675,0.0000129846085,0.63646746,0.00047282493,0.074385285,0.0006209712,0.00055289356],"about_ca_topic_score_codex":0.00059493474,"about_ca_topic_score_gemma":0.000042407835,"teacher_disagreement_score":0.6359654,"about_ca_system_score_codex":0.000020585538,"about_ca_system_score_gemma":0.00001845244,"threshold_uncertainty_score":0.44786263},"labels":[],"label_agreement":null},{"id":"W3004493192","doi":"10.1016/j.jss.2020.110542","title":"On testing machine learning programs","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":198,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Transformative learning; Domain (mathematical analysis); Software testing; Software engineering; Test strategy; Field (mathematics); Software; Witness; Data science; Artificial intelligence; Machine learning; Psychology","score_opus":0.027723359479573075,"score_gpt":0.23802568780602595,"score_spread":0.21030232832645288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004493192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013824329,0.00032091525,0.93358266,0.005797466,0.00006663262,0.0004934,0.0000030689714,0.044884533,0.0010270197],"genre_scores_gemma":[0.5403733,0.000008199279,0.45474166,0.0045179916,0.00008211557,0.00016181495,0.0000071725626,0.00004429712,0.000063437845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973204,0.00018221469,0.00042589768,0.0007830232,0.00049561716,0.0007928479],"domain_scores_gemma":[0.99773663,0.0005628861,0.00024617842,0.0008289374,0.00014435868,0.000481016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006225286,0.00039663893,0.00035702268,0.0002407508,0.0003784891,0.0004866751,0.0014478175,0.0001923467,0.000008407723],"category_scores_gemma":[0.0030842745,0.00038554874,0.00013792998,0.0014089906,0.00006685615,0.00037356952,0.0005781389,0.000893072,0.000053955253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059255424,0.00036173963,0.13468115,0.000081529455,0.000043919485,0.0003630303,0.00092074595,0.004382005,0.0021622824,0.071548976,0.007626771,0.7777686],"study_design_scores_gemma":[0.0002777474,0.0010241602,0.0030281853,0.00011551501,0.000009612141,0.00010866036,0.000004947976,0.9702724,0.002385322,0.020466767,0.001792184,0.0005145049],"about_ca_topic_score_codex":0.002345767,"about_ca_topic_score_gemma":0.0000608046,"teacher_disagreement_score":0.9658904,"about_ca_system_score_codex":0.00016802884,"about_ca_system_score_gemma":0.0001408759,"threshold_uncertainty_score":0.99985963},"labels":[],"label_agreement":null},{"id":"W3006547141","doi":"10.1109/issre.2019.00018","title":"Engineering a Better Fuzzer with Synergically Integrated Optimizations","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Block (permutation group theory); Granularity; Scheduling (production processes); Knapsack problem; Parallel computing; Algorithm; Mathematical optimization; Operating system; Software","score_opus":0.0037741349157259852,"score_gpt":0.17514663970216207,"score_spread":0.1713725047864361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006547141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008853699,0.0000048186166,0.97621787,0.00047504963,0.000050379465,0.00007938185,2.434003e-7,0.010448632,0.0038699466],"genre_scores_gemma":[0.25605604,4.0118783e-7,0.74284565,0.0004274732,0.00000794576,0.000009808374,0.000001466866,0.000007455787,0.0006437656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994359,0.0000088853,0.00008595627,0.00021031014,0.000112643684,0.00014631994],"domain_scores_gemma":[0.9993803,0.00010683661,0.000020076735,0.000377099,0.00007199825,0.000043681885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000074697564,0.00008902639,0.00008449366,0.000079833495,0.000024485664,0.00010959547,0.00034656227,0.00003271762,0.000063016414],"category_scores_gemma":[0.000040418636,0.00006022793,0.00001865175,0.0003588659,0.000008106875,0.00019219352,0.00007873181,0.00008779014,0.00009186711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004067308,0.0005824849,0.13847779,0.00015045542,0.00029247047,0.00024520617,0.001798017,0.247427,0.0033790187,0.3386092,0.17813449,0.09086322],"study_design_scores_gemma":[0.00018183603,0.00011341975,0.0013302477,0.00007609104,0.0000035462604,0.00004795352,0.0000014791203,0.9931956,0.0005884436,0.0011657813,0.003040511,0.0002550801],"about_ca_topic_score_codex":0.000021686681,"about_ca_topic_score_gemma":6.6530873e-7,"teacher_disagreement_score":0.7457686,"about_ca_system_score_codex":0.000015157993,"about_ca_system_score_gemma":0.00002756564,"threshold_uncertainty_score":0.24560237},"labels":[],"label_agreement":null},{"id":"W3011348730","doi":"10.1109/ibf50092.2020.9034821","title":"Exploring the Differences between Plausible and Correct Patches at Fine-Grained Level","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Correctness; Abstraction; Invariant (physics); Test case; Programming language; Artificial intelligence; Machine learning; Mathematics","score_opus":0.3754039426601999,"score_gpt":0.2731418934620426,"score_spread":0.10226204919815729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011348730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58479476,0.000042957778,0.40103245,0.007188696,0.000086119435,0.00010814445,0.0000031885033,0.006351166,0.00039254283],"genre_scores_gemma":[0.93486804,0.0000075310604,0.0643864,0.00048238866,0.000085441265,0.000022081816,7.867262e-7,0.0000059237022,0.00014142957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991931,0.000041867628,0.00012967458,0.00028983614,0.0001642124,0.00018136545],"domain_scores_gemma":[0.99871176,0.0009194188,0.000041755695,0.00021225926,0.00002434859,0.000090425965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016878865,0.00011868008,0.00014540243,0.000026357777,0.00021533927,0.00014063319,0.00054632104,0.000021260767,0.0000068120517],"category_scores_gemma":[0.0003183723,0.00007165051,0.000028653421,0.0002351307,0.000049724124,0.00021721677,0.0005633791,0.000099856865,0.000012499026],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059463796,0.000011102071,0.8009944,0.000026027154,0.00002286126,0.0000072638545,0.005336017,0.0000033845859,0.00020948477,0.002182017,0.027394028,0.16380748],"study_design_scores_gemma":[0.00043013148,0.00054567965,0.90910196,0.000115832205,0.000026907874,0.000026149819,0.000097015174,0.047351643,0.016357549,0.022997582,0.002190262,0.00075928814],"about_ca_topic_score_codex":0.00018779776,"about_ca_topic_score_gemma":0.000026345471,"teacher_disagreement_score":0.35007328,"about_ca_system_score_codex":0.000010884364,"about_ca_system_score_gemma":0.000019057377,"threshold_uncertainty_score":0.2921823},"labels":[],"label_agreement":null},{"id":"W3013054130","doi":"10.1002/smr.415","title":"Regression test suite reduction based on SDL models of system requirements","year":2009,"lang":"en","type":"article","venue":"Journal of Software Maintenance and Evolution Research and Practice","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test suite; Regression testing; Computer science; Suite; Regression analysis; Reduction (mathematics); Test (biology); Set (abstract data type); Test case; Regression; Programming language; Data mining; Statistics; Machine learning; Mathematics; Software; Software development","score_opus":0.08214894951886607,"score_gpt":0.37058079961742646,"score_spread":0.28843185009856037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013054130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008697136,0.0013497537,0.98307586,0.0052266303,0.0001885194,0.00022257603,0.0000036213191,0.00042696914,0.0008089138],"genre_scores_gemma":[0.8617837,0.0002728574,0.13772662,0.00008603098,0.000061255436,0.0000022962925,5.205927e-7,0.000005078749,0.00006163531],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977718,0.00042111473,0.00041930913,0.00023657645,0.0008603636,0.0002908324],"domain_scores_gemma":[0.99453175,0.0027572983,0.00052308216,0.0003039938,0.0017231364,0.000160765],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006132571,0.0001149213,0.000216117,0.00042427029,0.0002602185,0.00012225482,0.0002983703,0.00008224279,5.312569e-7],"category_scores_gemma":[0.009147967,0.0000841034,0.000041614632,0.00050837034,0.00012148464,0.0014793848,0.00006819927,0.00045040762,9.749336e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014817647,0.0053358222,0.019843843,0.0023230459,0.00020315875,0.0015334935,0.0034021575,0.0046441257,0.014317389,0.09067608,0.24194868,0.60095453],"study_design_scores_gemma":[0.0067229937,0.039427582,0.04783391,0.028411664,0.00012999059,0.012827068,0.0017921365,0.411547,0.0038000103,0.44104162,0.005189029,0.0012769749],"about_ca_topic_score_codex":0.000045625937,"about_ca_topic_score_gemma":2.8345738e-7,"teacher_disagreement_score":0.8530866,"about_ca_system_score_codex":0.00017140295,"about_ca_system_score_gemma":0.0001912172,"threshold_uncertainty_score":0.9991984},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01937952920259313,"score_gpt":0.2572724153819903,"score_spread":0.2378928861793972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013655954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4071725,0.000054395514,0.58806074,0.00011540234,0.000034394398,0.00011615948,0.000010982271,0.004406615,0.000028808592],"genre_scores_gemma":[0.8353387,0.0000047557355,0.16456345,0.000039681803,0.000005933712,0.000009539333,0.000005903872,0.0000072614794,0.000024780464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886286,0.0000750759,0.00037848795,0.0003899701,0.000102669735,0.00019090525],"domain_scores_gemma":[0.9978559,0.0013469597,0.00012968562,0.00044336656,0.00015958372,0.00006451261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001241302,0.00012769033,0.00017047602,0.00013914544,0.00014784058,0.000060747214,0.00016119127,0.00006681889,4.1818248e-7],"category_scores_gemma":[0.0020752957,0.000109974084,0.000025610096,0.00061478675,0.00020314983,0.00028849873,0.00006322138,0.00015185826,5.8377856e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037908394,0.00045624166,0.7707582,0.00030824143,0.0000128546435,0.0000047334092,0.0052740173,0.0011326972,0.003989526,0.0004088314,0.00045020794,0.21716653],"study_design_scores_gemma":[0.00031227717,0.00013051937,0.872484,0.00017741801,0.0000069535768,0.000043270804,0.000081899314,0.10380101,0.0014406458,0.0211267,0.00012997494,0.00026530167],"about_ca_topic_score_codex":0.00031383842,"about_ca_topic_score_gemma":0.00003433544,"teacher_disagreement_score":0.4281662,"about_ca_system_score_codex":0.000035946614,"about_ca_system_score_gemma":0.00005275707,"threshold_uncertainty_score":0.4484613},"labels":[],"label_agreement":null},{"id":"W3021368500","doi":"10.1145/2858965.2814297","title":"SATCheck: SAT-directed stateless model checking for SC and TSO","year":2015,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Model checking; Scalability; Programming language; Stateless protocol; Parallel computing; Memory model; Thread (computing); Concurrency; Shared memory; Operating system","score_opus":0.10695654727802961,"score_gpt":0.3183851898259565,"score_spread":0.21142864254792687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021368500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37687233,0.0004715393,0.6066134,0.00096436124,0.0002693398,0.00035669882,0.000018006587,0.013939302,0.0004950204],"genre_scores_gemma":[0.5433893,0.0000032846488,0.45628443,0.00019597814,0.000039229384,0.000018869061,0.0000063873003,0.0000112724265,0.00005120786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988459,0.000035318408,0.00018901186,0.0004013396,0.00021461604,0.00031385815],"domain_scores_gemma":[0.9981991,0.0007321479,0.00011519159,0.0006331167,0.00016246199,0.00015800027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056102005,0.00016290588,0.00020251244,0.000095333184,0.000120591714,0.00024936727,0.000865521,0.000076105716,5.242788e-7],"category_scores_gemma":[0.0015545377,0.00014746535,0.000028964929,0.00017754555,0.000048826445,0.0003913017,0.00037388864,0.000099953664,0.000005137708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033088826,0.00057010644,0.14272352,0.00070855615,0.00025428194,0.00014105257,0.041339368,0.0107887015,0.0023929775,0.016272536,0.28678572,0.49769232],"study_design_scores_gemma":[0.0004991692,0.0001718322,0.0014493805,0.000084996966,0.000018202854,0.000015549567,0.00003165859,0.8874641,0.0018135055,0.107468165,0.0006284845,0.00035494156],"about_ca_topic_score_codex":0.000148434,"about_ca_topic_score_gemma":0.000026944794,"teacher_disagreement_score":0.8766754,"about_ca_system_score_codex":0.000028763123,"about_ca_system_score_gemma":0.000106889,"threshold_uncertainty_score":0.60134625},"labels":[],"label_agreement":null},{"id":"W3025363231","doi":"10.1039/d0sc01232g","title":"Demonstration of the utility of DOS-derived fragment libraries for rapid hit derivatisation in a multidirectional fashion","year":2020,"lang":"en","type":"article","venue":"Chemical Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"Biotechnology and Biological Sciences Research Council; Novartis Pharma; Medical Research Council; Ministero dello Sviluppo Economico; Innovative Medicines Initiative; Royal Society; Ontario Ministry of Economic Development and Innovation; Diamond Light Source; Wellcome Trust; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Department of Biochemistry, University of Cambridge; AbbVie; European Federation of Pharmaceutical Industries and Associations; Merck KGaA; Meso Scale Diagnostics; Engineering and Physical Sciences Research Council; AstraZeneca; Takeda Pharmaceuticals U.S.A.; University of Warwick; Pfizer","keywords":"Fragment (logic); Computer science; Chemistry; Programming language","score_opus":0.038923748058163746,"score_gpt":0.25441191038409106,"score_spread":0.21548816232592732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025363231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55180776,0.000011036256,0.4466018,0.0010704909,0.000040533483,0.00015328197,0.0000014651997,0.00022638883,0.00008723545],"genre_scores_gemma":[0.87011385,7.13369e-7,0.12977502,0.0000853583,0.000009016078,0.000013787049,6.3033895e-7,0.0000012174002,4.134978e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992022,0.000019991578,0.00019854259,0.000220712,0.0002554602,0.00010312155],"domain_scores_gemma":[0.9993543,0.00024749723,0.0001120682,0.0001624238,0.000087481785,0.00003620089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029961625,0.00005078196,0.000085677966,0.000027012975,0.00004853825,0.000025150192,0.00054378697,0.000030596606,0.0000024207047],"category_scores_gemma":[0.0013322787,0.000038475286,0.000032273303,0.00068094884,0.00033469885,0.00029230322,0.00016456594,0.000052837102,1.2405569e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011929604,0.00005569896,0.032568567,0.000036995745,0.0000012237457,6.539259e-8,0.0010353078,0.000012604116,0.9250371,0.0045946096,0.00032970516,0.036316197],"study_design_scores_gemma":[0.000098694865,0.00002556599,0.04273931,0.000025693183,9.295954e-7,5.482093e-7,0.0000061389637,0.108466916,0.8367979,0.011788424,0.000007342006,0.000042547184],"about_ca_topic_score_codex":0.000012555964,"about_ca_topic_score_gemma":5.839193e-7,"teacher_disagreement_score":0.3183061,"about_ca_system_score_codex":0.000020877425,"about_ca_system_score_gemma":0.00014713279,"threshold_uncertainty_score":0.15949583},"labels":[],"label_agreement":null},{"id":"W3029402327","doi":"10.1145/2578855.2535857","title":"Symbolic optimization with SMT solvers","year":2014,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Satisfiability modulo theories; Symbolic execution; Programming language; Satisfiability; Set (abstract data type); Function (biology); Software; Theoretical computer science; Algorithm","score_opus":0.012830927648873825,"score_gpt":0.2239901630927133,"score_spread":0.21115923544383947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029402327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01001013,0.000022798538,0.9793479,0.00064865506,0.000119570024,0.000078298195,5.782185e-7,0.006908721,0.0028633515],"genre_scores_gemma":[0.5304784,0.0000014587529,0.46908402,0.00034819363,0.00004241918,0.0000055482806,0.0000028412908,0.0000069737116,0.000030118666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991769,0.00004493695,0.00010619077,0.00027527107,0.00019529914,0.00020135712],"domain_scores_gemma":[0.9984659,0.00054611475,0.00008769751,0.0007764141,0.000059029826,0.00006484133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022513374,0.00011360774,0.00011501825,0.00008365572,0.0001156402,0.00017279814,0.0009850543,0.0000444966,0.000006767318],"category_scores_gemma":[0.0005252382,0.00008922053,0.000018654955,0.0002319461,0.000038215938,0.000321724,0.00016042124,0.000078484445,0.000025673222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009423465,0.00043952203,0.21524064,0.00028396244,0.00018175883,0.00010470438,0.008341495,0.317078,0.00025488102,0.06256419,0.09541269,0.30000392],"study_design_scores_gemma":[0.00048940943,0.00052426057,0.0056700003,0.00015753861,0.000028644097,0.000040516836,0.000012364257,0.972555,0.001149508,0.015683664,0.0031077953,0.000581346],"about_ca_topic_score_codex":0.0000831682,"about_ca_topic_score_gemma":0.000007359663,"teacher_disagreement_score":0.6554769,"about_ca_system_score_codex":0.000012375846,"about_ca_system_score_gemma":0.00002476,"threshold_uncertainty_score":0.36383078},"labels":[],"label_agreement":null},{"id":"W3043367330","doi":"10.1145/3395363.3397386","title":"Automated repair of feature interaction failures in automated driving systems","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"H2020 European Research Council; 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; European Commission","keywords":"Computer science; Feature (linguistics); Reliability engineering; Distributed computing; Embedded system; Artificial intelligence; Engineering","score_opus":0.020375712857958212,"score_gpt":0.2789408929585433,"score_spread":0.2585651801005851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043367330","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13067105,0.0001990024,0.28028223,0.003890494,0.0006425151,0.00054696994,0.0000018610414,0.58174664,0.0020192417],"genre_scores_gemma":[0.8782377,0.0000012099487,0.12155924,0.00013945947,0.000019159728,0.000009342517,0.0000016782146,0.00000758988,0.000024617735],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902964,0.000089694666,0.00026167935,0.00028893715,0.0001736673,0.00015636953],"domain_scores_gemma":[0.9992323,0.00020472376,0.00012386455,0.00030078285,0.00007974353,0.00005859626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020701745,0.00011136786,0.00019950235,0.00013516142,0.00002873345,0.0000780226,0.00038913358,0.00008305871,0.0000023587456],"category_scores_gemma":[0.00048183417,0.00009678594,0.00004982181,0.00069067307,0.000015461763,0.0003200903,0.00016149733,0.00014487791,0.000008109886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018367178,0.00015519858,0.11180985,0.0004371271,0.000059797512,0.00013912341,0.0035299151,0.006270595,0.006232218,0.006404949,0.861878,0.0030648962],"study_design_scores_gemma":[0.00009315058,0.0000745715,0.009255744,0.00019591577,0.0000020457267,0.000018342707,0.000022715185,0.9886697,0.0009929374,0.00009443388,0.00047372133,0.0001067352],"about_ca_topic_score_codex":0.00046219878,"about_ca_topic_score_gemma":0.000011610236,"teacher_disagreement_score":0.9823991,"about_ca_system_score_codex":0.000037554197,"about_ca_system_score_gemma":0.000035632496,"threshold_uncertainty_score":0.3946816},"labels":[],"label_agreement":null},{"id":"W3043761819","doi":"10.1145/3395363.3397369","title":"CoCoNuT: combining context-aware neural translation models using ensemble for program repair","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":329,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Facebook","keywords":"Computer science; Context (archaeology); Machine translation; Artificial intelligence; Programming language; Machine learning; Software engineering; Natural language processing","score_opus":0.1833401154001179,"score_gpt":0.3325084569739183,"score_spread":0.14916834157380038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043761819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028817153,0.00007764616,0.93915576,0.0010763579,0.00007386635,0.0006532814,0.0000015671859,0.055848114,0.00023168769],"genre_scores_gemma":[0.5110445,3.9716912e-7,0.48801485,0.0008539909,0.000024750248,0.00004303488,0.0000027716994,0.000009462401,0.0000062627714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989389,0.000037135167,0.0002394886,0.00038522933,0.00014843674,0.00025076533],"domain_scores_gemma":[0.9991911,0.0002672384,0.00007263412,0.0002475728,0.00011755547,0.00010388262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001805115,0.0001366371,0.00017989398,0.000041105446,0.00015799959,0.0001380927,0.00033244395,0.00006354201,0.0000014306218],"category_scores_gemma":[0.00007683725,0.00013005386,0.00011754206,0.00023283149,0.000025641213,0.0004916535,0.00006444344,0.000093993454,0.0000010847081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006990842,0.00019775427,0.0013012077,0.00022220974,0.00005415046,0.000022190288,0.005685476,0.01064379,0.0005098095,0.022739634,0.030177288,0.92837656],"study_design_scores_gemma":[0.00033415726,0.0002931858,0.000007047338,0.000029291888,0.000008178854,0.000009978152,0.000014233561,0.98166174,0.00055687607,0.016622946,0.00029367598,0.00016869517],"about_ca_topic_score_codex":0.00006914186,"about_ca_topic_score_gemma":0.0000033621147,"teacher_disagreement_score":0.97101796,"about_ca_system_score_codex":0.000017179113,"about_ca_system_score_gemma":0.00004839165,"threshold_uncertainty_score":0.53034425},"labels":[],"label_agreement":null},{"id":"W306569659","doi":"10.1016/b978-0-12-800160-8.00002-4","title":"Automated Extraction of GUI Models for Testing","year":2014,"lang":"en","type":"book-chapter","venue":"Advances in computers","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graphical user interface; Software engineering; Process (computing); Graphical user interface testing; Domain (mathematical analysis); Model-based testing; Process modeling; Software; Data mining; User interface; Test case; Machine learning; Programming language; Work in process; User interface design; Engineering","score_opus":0.044030852554028777,"score_gpt":0.3119502890067512,"score_spread":0.2679194364527224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W306569659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000033777023,0.0007279704,0.9665978,0.000035116616,0.0007368164,0.0002977635,0.0000047672315,0.008356263,0.02324011],"genre_scores_gemma":[0.0070624338,0.00007393746,0.9912059,0.00011870433,0.00010566066,0.000027079774,0.000009390742,0.000039309005,0.0013576112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844384,0.000018829665,0.0005241199,0.0005425927,0.00023055874,0.00024006599],"domain_scores_gemma":[0.99645835,0.0021275338,0.0005440027,0.0006126205,0.00021253996,0.00004492533],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003647704,0.0002792831,0.00044595462,0.00031513683,0.00005431818,0.000042911335,0.0008609435,0.00017928779,5.371918e-7],"category_scores_gemma":[0.00018552394,0.00029583694,0.000099963705,0.00010309065,0.00006781118,0.0004228853,0.0001970288,0.00019945292,0.000002084194],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009523179,0.000023031234,0.000041813968,0.0003375022,0.000017749988,0.000011718233,0.00009956424,0.07192902,0.000014941258,0.2164632,0.006158631,0.7048933],"study_design_scores_gemma":[0.000117695214,0.00011075093,0.00000469125,0.00076839054,0.0000048652832,0.000015426456,1.2992002e-7,0.6326748,0.00002759286,0.35742852,0.008643383,0.00020372882],"about_ca_topic_score_codex":0.00001437488,"about_ca_topic_score_gemma":0.0000032422654,"teacher_disagreement_score":0.70468956,"about_ca_system_score_codex":0.0000800966,"about_ca_system_score_gemma":0.000059951944,"threshold_uncertainty_score":0.9999494},"labels":[],"label_agreement":null},{"id":"W3081900038","doi":"","title":"Unit Test Effort Prioritization Using Combined Datasets and Deep Learning: A Cross-Systems Validation.","year":2020,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Prioritization; Computer science; Test (biology); Artificial intelligence; Unit (ring theory); Unit testing; Cross-validation; Machine learning; Data mining; Engineering; Software; Mathematics","score_opus":0.02080212164416674,"score_gpt":0.25420117283484395,"score_spread":0.23339905119067722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081900038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062054146,0.0021961075,0.92552805,0.000021796206,0.00030197657,0.00019346878,0.000011248915,0.009686483,0.000006698947],"genre_scores_gemma":[0.8192527,0.0000474566,0.18035409,0.000013133561,0.00018138226,0.00002255799,0.000051482464,0.000062081075,0.000015066119],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861854,0.000019380155,0.00032731288,0.00050434144,0.00016586347,0.00036454486],"domain_scores_gemma":[0.99866426,0.00060098234,0.000071930604,0.0002751167,0.000107151594,0.00028054108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029113854,0.0003189926,0.0002992546,0.00018675141,0.00018705438,0.00048065078,0.00030928513,0.00012753492,9.867213e-7],"category_scores_gemma":[0.0025163959,0.000359098,0.00003434238,0.00058987946,0.000025848587,0.0004922376,0.00033453188,0.0003407148,0.000004382228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013112623,0.00011493908,0.34513563,0.0028615238,0.00013138916,0.000093253744,0.0036681585,0.6250912,0.0029654421,0.004174596,0.0004653782,0.015285374],"study_design_scores_gemma":[0.00033370827,0.00011037328,0.0053642564,0.00021036383,0.00001590699,0.00006531958,0.0000043088935,0.99058294,0.00041876736,0.00002885345,0.0024437448,0.0004214507],"about_ca_topic_score_codex":0.000013784646,"about_ca_topic_score_gemma":2.2096314e-7,"teacher_disagreement_score":0.7571986,"about_ca_system_score_codex":0.000039885366,"about_ca_system_score_gemma":0.000039393963,"threshold_uncertainty_score":0.9998861},"labels":[],"label_agreement":null},{"id":"W3082254096","doi":"","title":"Using Deep Learning Classifiers to Identify Candidate Classes for Unit Testing in Object-Oriented Systems.","year":2020,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Unit testing; Object (grammar); Machine learning; Unit (ring theory); Pattern recognition (psychology); Mathematics; Programming language; Software","score_opus":0.04895468532458588,"score_gpt":0.29476299749057217,"score_spread":0.24580831216598628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082254096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06853569,0.0011334127,0.9210114,0.000028480985,0.0005767043,0.00036735513,0.0000035417404,0.008330649,0.0000127820185],"genre_scores_gemma":[0.59110135,0.000005711712,0.4085442,0.000020719224,0.00016547675,0.00008123994,0.000003913102,0.00006662956,0.000010729938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980112,0.000035624988,0.00044459093,0.0006556543,0.00017047656,0.000682488],"domain_scores_gemma":[0.9979,0.0012090295,0.00007519578,0.00027039417,0.00017171426,0.0003736416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045810879,0.0003908664,0.0004413453,0.0004886304,0.00015380212,0.00026330995,0.00043241508,0.00014270541,3.9580257e-7],"category_scores_gemma":[0.006690995,0.00045044132,0.00006289975,0.0015672465,0.000013339548,0.00032357045,0.0003104098,0.00046071285,0.0000040429513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010999484,0.000026555936,0.024552274,0.0012549042,0.000049255144,0.00004387849,0.0032702875,0.95416623,0.0046696207,0.0010324566,0.00015453297,0.010768993],"study_design_scores_gemma":[0.00032534794,0.00011981476,0.002401984,0.0006838463,0.000014244674,0.000030294475,0.00003902174,0.9929015,0.00036632264,0.000017702698,0.002572371,0.0005275595],"about_ca_topic_score_codex":0.000063394466,"about_ca_topic_score_gemma":0.0000035179116,"teacher_disagreement_score":0.52256566,"about_ca_system_score_codex":0.00013743468,"about_ca_system_score_gemma":0.00008237657,"threshold_uncertainty_score":0.9997947},"labels":[],"label_agreement":null},{"id":"W3088428890","doi":"10.1145/3387940.3392218","title":"Double Cycle Hybrid Testing of Hybrid Distributed IoT System","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Reliability (semiconductor); Automation; Embedded system; Variety (cybernetics); Internet of Things; Network packet; Packet loss; Software; Reliability engineering; Computer network; Engineering; Operating system","score_opus":0.04061316968890568,"score_gpt":0.24544651359270597,"score_spread":0.20483334390380029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088428890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054127097,0.000033460085,0.9225051,0.0005012828,0.00008848664,0.00013607004,0.000012703055,0.01997161,0.0026241823],"genre_scores_gemma":[0.74202776,1.5856597e-7,0.257752,0.00015277401,0.000039204482,0.000007051591,0.0000035936728,0.000008332112,0.000009156346],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987939,0.00003103998,0.00031736467,0.00036373409,0.00024810756,0.00024582908],"domain_scores_gemma":[0.9987771,0.00030997858,0.00014406703,0.00046880846,0.00015951527,0.00014056836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022220727,0.0001364371,0.00023242671,0.00004315096,0.000084647305,0.00008375648,0.00083035463,0.000016824686,0.0000037891975],"category_scores_gemma":[0.00041062685,0.00012208447,0.000056359007,0.00048257358,0.00003300153,0.000120645454,0.0003674705,0.00010571136,0.000028238921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019870073,0.0008188239,0.14457832,0.0035690363,0.0002895082,0.0020576774,0.0015838908,0.012014195,0.0148634445,0.13753793,0.47588357,0.20660488],"study_design_scores_gemma":[0.00044880837,0.00020372793,0.0004792505,0.00016802269,0.000009963074,0.00018447214,0.000007935276,0.8844185,0.11042474,0.0029135067,0.00044850243,0.00029258922],"about_ca_topic_score_codex":0.00026536259,"about_ca_topic_score_gemma":2.5575602e-7,"teacher_disagreement_score":0.8724043,"about_ca_system_score_codex":0.00003395241,"about_ca_system_score_gemma":0.000061465704,"threshold_uncertainty_score":0.497846},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05055143313862166,"score_gpt":0.23784943200647207,"score_spread":0.18729799886785042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092453472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.124593884,0.00054497825,0.8630589,0.0019847378,0.00013086564,0.00056961796,0.000009754038,0.008673445,0.00043377094],"genre_scores_gemma":[0.54054844,0.000010078064,0.45913547,0.00024750977,0.000019037556,0.000025943158,0.0000021795634,0.0000056964336,0.0000056553286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986395,0.000085982894,0.00035745735,0.0005738101,0.00017191388,0.00017132537],"domain_scores_gemma":[0.9980181,0.00083582854,0.00019820414,0.00052324944,0.00025544318,0.00016916887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511987,0.00015355772,0.00022766028,0.00004720159,0.00014149604,0.00007274273,0.0003338023,0.00008280217,0.0000032313762],"category_scores_gemma":[0.008090468,0.00014215313,0.00003347906,0.00045286145,0.00021070485,0.0002230042,0.00021912188,0.00016038513,0.0000022264348],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017914788,0.000119171025,0.7038515,0.00057644106,0.000013297227,0.0000033010003,0.0015688188,0.000034944882,0.0009246173,0.001602984,0.0066559464,0.28463104],"study_design_scores_gemma":[0.0012397835,0.001254531,0.759297,0.00050596613,0.00007543569,0.000098193894,0.00009084362,0.145851,0.0037990736,0.06938388,0.01696659,0.0014377114],"about_ca_topic_score_codex":0.00013743389,"about_ca_topic_score_gemma":4.4565866e-7,"teacher_disagreement_score":0.41595456,"about_ca_system_score_codex":0.000017798677,"about_ca_system_score_gemma":0.00007726569,"threshold_uncertainty_score":0.9685631},"labels":[],"label_agreement":null},{"id":"W3095252018","doi":"10.1109/tse.2021.3070549","title":"Reinforcement Learning for Test Case Prioritization","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Queen's University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Reinforcement learning; Computer science; Prioritization; Context (archaeology); Ranking (information retrieval); Regression testing; Machine learning; Test case; Bidding; Test (biology); Adaptation (eye); Artificial intelligence; Regression analysis; Engineering; Software; Software system","score_opus":0.019405390937673923,"score_gpt":0.25133358157887337,"score_spread":0.23192819064119943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095252018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009662138,0.00010934956,0.9789068,0.00003232632,0.0016179542,0.00052673684,0.000010167544,0.017824037,0.00000639891],"genre_scores_gemma":[0.5118025,0.000025860561,0.48749316,0.00003799506,0.00007391062,0.00038161458,0.000017519917,0.00005288286,0.00011459076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815655,0.00002627015,0.00042456918,0.0007222977,0.00028146713,0.0003888541],"domain_scores_gemma":[0.9974702,0.0012057008,0.00013694944,0.0007876446,0.0002737464,0.0001257651],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027971953,0.00040505698,0.00034925021,0.0003505857,0.00029504395,0.00041895334,0.0004526643,0.000312039,0.000007068882],"category_scores_gemma":[0.00055009633,0.00049132016,0.00025328132,0.0003406516,0.000013890816,0.00023618543,0.000025362599,0.0009365158,0.0000034346178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018879435,0.00005046839,0.000024018467,0.00031751653,0.00003930995,0.00018955272,0.00033159647,0.9781109,0.000041155236,0.000021226426,0.00016539617,0.020706972],"study_design_scores_gemma":[0.00023898251,0.00016361572,0.000013585759,0.0008316787,0.000051582192,0.0005545792,0.000007934848,0.98980665,0.007290993,0.00012805358,0.00028533803,0.00062700803],"about_ca_topic_score_codex":0.000052491887,"about_ca_topic_score_gemma":0.00000390789,"teacher_disagreement_score":0.51083624,"about_ca_system_score_codex":0.00024925589,"about_ca_system_score_gemma":0.00016847205,"threshold_uncertainty_score":0.99975383},"labels":[],"label_agreement":null},{"id":"W3096465442","doi":"10.1002/spe.2929","title":"Root causing, detecting, and fixing flaky tests: State of the art and future roadmap","year":2020,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Guelph; University of Guelph-Humber","funders":"","keywords":"Pace; Root cause; Software deployment; Test (biology); Field (mathematics); Computer science; Root (linguistics); Engineering; Data science; Software; Engineering management; Software engineering; Operations management","score_opus":0.016750706809614355,"score_gpt":0.2725751747409247,"score_spread":0.2558244679313103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096465442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7290197,0.004796202,0.24890308,0.012844456,0.00036894315,0.0003966815,0.00000455329,0.0034457152,0.00022067675],"genre_scores_gemma":[0.8479337,0.00019615536,0.1498688,0.0018584101,0.00009132215,0.000017033704,2.5735395e-7,0.000012845154,0.000021487967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987867,0.0000920899,0.000212847,0.00045092378,0.00023709121,0.00022038943],"domain_scores_gemma":[0.9984086,0.00075774593,0.00023420282,0.0003521668,0.00011215088,0.00013513016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028091526,0.00016422024,0.00017200861,0.0000330297,0.0003235217,0.0002284659,0.0002804992,0.000051298422,0.000001721511],"category_scores_gemma":[0.0034405908,0.00012503068,0.000022985865,0.00033994243,0.0001869742,0.0009898989,0.0005747635,0.00024920015,9.980786e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009147711,0.00009781788,0.15304798,0.00032077704,0.000050507766,0.00013111834,0.16631764,0.000018285502,0.0027416018,0.0006072491,0.0058572832,0.67071825],"study_design_scores_gemma":[0.0042874287,0.0045609665,0.2358156,0.0025493165,0.00037364973,0.00879459,0.015262559,0.04469772,0.0950712,0.05660688,0.5258419,0.006138196],"about_ca_topic_score_codex":0.000085637774,"about_ca_topic_score_gemma":0.000011083939,"teacher_disagreement_score":0.66458005,"about_ca_system_score_codex":0.000010360991,"about_ca_system_score_gemma":0.000052184114,"threshold_uncertainty_score":0.50986034},"labels":[],"label_agreement":null},{"id":"W3097853154","doi":"10.1109/icsme46990.2020.00047","title":"A Cost-Effective Approach for Hyper-Parameter Tuning in Search-based Test Case Generation","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Metric (unit); Computer science; Heuristic; Fine-tuning; Class (philosophy); Domain (mathematical analysis); Selection (genetic algorithm); Mathematical optimization; Test case; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.15115330699758797,"score_gpt":0.32558085003198906,"score_spread":0.17442754303440108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097853154","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010662935,0.000011967836,0.98410195,0.00063100347,0.00002069623,0.00127779,0.000002647248,0.0031248226,0.00016619894],"genre_scores_gemma":[0.49489206,8.790999e-8,0.5036924,0.0009712229,0.000031985786,0.0003962961,0.0000048614725,0.000006040459,0.0000050471563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907976,0.00007332459,0.00013687725,0.00038931682,0.00011203672,0.00020866649],"domain_scores_gemma":[0.9983401,0.0012392508,0.000027976394,0.00022861178,0.000076986194,0.00008711834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003525971,0.00010693124,0.00012835198,0.0000904187,0.000084659296,0.00013631667,0.00023980532,0.000050175346,0.000001465709],"category_scores_gemma":[0.0013032709,0.000095511474,0.00004125058,0.00037798073,0.000025334395,0.00017036157,0.00008008943,0.00012054727,0.000002861563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055917437,0.00070609734,0.031039972,0.00024751917,0.000022501172,0.0006552439,0.0054881093,0.024081204,0.008801142,0.0026755908,0.02362923,0.9025975],"study_design_scores_gemma":[0.00033966097,0.00026676108,0.00007483195,0.0000085526235,0.0000022637719,0.000068838395,0.000007638011,0.9909418,0.0078263655,0.00025311855,0.00008162834,0.00012853449],"about_ca_topic_score_codex":0.00013265412,"about_ca_topic_score_gemma":0.0000071135405,"teacher_disagreement_score":0.9668606,"about_ca_system_score_codex":0.000047592064,"about_ca_system_score_gemma":0.000052734697,"threshold_uncertainty_score":0.3894845},"labels":[],"label_agreement":null},{"id":"W3098557859","doi":"10.1145/3368089.3409757","title":"ARDiff: scaling program equivalence checking via iterative abstraction and refinement of common code","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Equivalence (formal languages); Symbolic execution; Computer science; Symbolic trajectory evaluation; Abstraction; Programming language; Program analysis; Formal equivalence checking; Abstraction model checking; Model checking; Theoretical computer science; Symbolic data analysis; Static analysis; Algorithm; Mathematics; Discrete mathematics; Software","score_opus":0.05157918219343462,"score_gpt":0.31744576279154774,"score_spread":0.26586658059811313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098557859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082157694,0.00005936438,0.9103379,0.00091255014,0.000044869757,0.00020334075,0.000001137561,0.0051110047,0.001172131],"genre_scores_gemma":[0.67127985,0.000003952957,0.32848,0.00020046793,0.000015589942,0.000010793158,9.1054426e-7,0.0000032420126,0.00000520682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999223,0.000027035843,0.0002080914,0.0002490835,0.00016699075,0.00012580509],"domain_scores_gemma":[0.9994532,0.00013247538,0.00011040842,0.00017965405,0.0000613378,0.00006295204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018761924,0.0000893864,0.00013770763,0.000033007873,0.00006452346,0.000082453786,0.00021984785,0.000031877033,0.0000044427197],"category_scores_gemma":[0.00009282629,0.00007824679,0.000025553887,0.00017045386,0.00003876,0.0001962944,0.00018337264,0.00009795789,0.0000016907492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000134894035,0.00016797532,0.01154193,0.00018082611,0.000022383034,0.00001298526,0.003898865,0.00010798979,0.0063361074,0.0017413809,0.002685364,0.9732907],"study_design_scores_gemma":[0.0004199176,0.00096730894,0.018890178,0.00038838215,0.000019012465,0.000039347593,0.000038236816,0.87445223,0.08896014,0.013879079,0.0014971665,0.00044902283],"about_ca_topic_score_codex":0.00006300687,"about_ca_topic_score_gemma":0.0000022612937,"teacher_disagreement_score":0.9728417,"about_ca_system_score_codex":0.00001510764,"about_ca_system_score_gemma":0.0000110432875,"threshold_uncertainty_score":0.31908116},"labels":[],"label_agreement":null},{"id":"W3100648313","doi":"10.1145/3412452.3423571","title":"Comparing transition trees test suites effectiveness for different mutation operators","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mutation testing; Computer science; Mutation; Fault tree analysis; Test case; Process (computing); Test strategy; Tree (set theory); Fault (geology); Reliability engineering; Data mining; Artificial intelligence; Machine learning; Engineering; Mathematics; Programming language; Biology","score_opus":0.040456044367176924,"score_gpt":0.27180922118318696,"score_spread":0.23135317681601003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100648313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23752353,0.000013960584,0.7563027,0.000652392,0.000033837245,0.00023132382,0.0000011083284,0.0052080825,0.000033027092],"genre_scores_gemma":[0.94117284,5.7549164e-7,0.0582709,0.0004252424,0.000038152582,0.00007454959,0.000007837678,0.000007655563,0.000002226355],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999346,0.000041999505,0.00012095549,0.00026075318,0.00009975964,0.0001305357],"domain_scores_gemma":[0.9979034,0.0018161546,0.000027905926,0.00012570005,0.00006209532,0.00006472212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001265759,0.000104514256,0.00014743995,0.00003907704,0.00010086955,0.00013569558,0.00024307244,0.000029690016,0.0000016089875],"category_scores_gemma":[0.0004973489,0.0000855471,0.000048643367,0.00016142818,0.000014219626,0.0002082961,0.000033501125,0.00004645468,0.000003310699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018782157,0.0010923096,0.6683373,0.0012556324,0.00013105088,0.000044037333,0.015704013,0.004920401,0.06435244,0.04488218,0.015004382,0.18408844],"study_design_scores_gemma":[0.00061788043,0.0006149994,0.0879724,0.00008682125,0.000012067547,0.0000066551133,0.000013034642,0.80680776,0.09685051,0.0067103533,0.00004186782,0.00026568226],"about_ca_topic_score_codex":0.000024934487,"about_ca_topic_score_gemma":0.0000053757485,"teacher_disagreement_score":0.80188733,"about_ca_system_score_codex":0.000022481801,"about_ca_system_score_gemma":0.00001258197,"threshold_uncertainty_score":0.34885097},"labels":[],"label_agreement":null},{"id":"W3102206389","doi":"10.1145/3419604.3419628","title":"Test Generation Tool for Modified Condition/Decision Coverage","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Traceability; Model-based testing; Integration testing; Code coverage; Test strategy; White-box testing; Dataflow; Extended finite-state machine; Non-regression testing; Keyword-driven testing; Manual testing; Reliability engineering; Software performance testing; Test case; Software; Finite-state machine; Software system; Algorithm; Software engineering; Programming language; Engineering; Software construction; Machine learning","score_opus":0.05601324452544399,"score_gpt":0.29192293129835284,"score_spread":0.23590968677290886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102206389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040334533,0.000008841586,0.98722446,0.001557319,0.00010131339,0.00021245242,0.0000073598585,0.006328423,0.000526359],"genre_scores_gemma":[0.5797835,0.0000013821575,0.41713324,0.0028602448,0.00011179563,0.00003085747,0.000012040175,0.000004595866,0.00006236964],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993238,0.000010596529,0.00015020368,0.0002658996,0.00013555576,0.000113960064],"domain_scores_gemma":[0.9989659,0.00062019035,0.00004093005,0.00022883587,0.000093059,0.000051037674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013158658,0.00007713106,0.00008508384,0.00002908297,0.00011208138,0.00017090199,0.0002965977,0.000040110262,0.000011332347],"category_scores_gemma":[0.0011609985,0.00006744842,0.000040263683,0.00014505991,0.000009224846,0.00026706903,0.000073853,0.00004160189,0.000026802902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000093616345,0.00006745995,0.0007058927,0.000017014798,0.0000056803274,0.000005894993,0.00023666855,0.00096195616,0.0061566653,0.060461204,0.7717786,0.1595936],"study_design_scores_gemma":[0.00030489868,0.0002150412,0.00027240388,0.000007851647,0.0000024087008,0.0000041409926,3.1229342e-7,0.9194783,0.009408762,0.0675896,0.0025715455,0.00014474265],"about_ca_topic_score_codex":0.00000483701,"about_ca_topic_score_gemma":4.1551172e-7,"teacher_disagreement_score":0.91851634,"about_ca_system_score_codex":0.000015287076,"about_ca_system_score_gemma":0.000031102176,"threshold_uncertainty_score":0.27504665},"labels":[],"label_agreement":null},{"id":"W3105178636","doi":"10.1145/3368089.3409737","title":"Mining assumptions for software components using machine learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; European Commission; H2020 European Research Council; Université du Luxembourg","keywords":"Computer science; Component (thermodynamics); Set (abstract data type); Machine learning; Test case; Software; Decision tree; Process (computing); Tree (set theory); Artificial intelligence; Component-based software engineering; Software system; Data mining; Programming language; Mathematics","score_opus":0.12612852738100291,"score_gpt":0.3063556652720434,"score_spread":0.18022713789104047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105178636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016119987,0.000050364764,0.9685885,0.0007881653,0.00007787167,0.00012558239,0.0000020770708,0.014181971,0.00006550752],"genre_scores_gemma":[0.23981057,8.469775e-7,0.7592965,0.00077185774,0.000048445414,0.000009133564,0.0000069822318,0.000012040532,0.000043618038],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991356,0.000035000357,0.00016534243,0.00030574444,0.00013921128,0.00021908148],"domain_scores_gemma":[0.9991723,0.0003967387,0.00007082561,0.00018280775,0.00006834446,0.000109019944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016052835,0.000112913556,0.00013858653,0.000055562243,0.0002780269,0.00012828366,0.00044051433,0.000041064963,0.000008582319],"category_scores_gemma":[0.0007685176,0.0001086854,0.00006395984,0.00022148545,0.000016541862,0.00020894855,0.00022767289,0.000110517234,0.000009693519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006135956,0.00032546942,0.7080017,0.00044116977,0.00018862913,0.00007043831,0.007612887,0.014458291,0.0188802,0.011999512,0.050181754,0.1877786],"study_design_scores_gemma":[0.00017617333,0.00008496084,0.0004947719,0.000030016812,0.000006598956,0.000011525092,0.0000037753687,0.99379355,0.000704459,0.0018221368,0.002705482,0.00016653337],"about_ca_topic_score_codex":0.000064379674,"about_ca_topic_score_gemma":0.000001404808,"teacher_disagreement_score":0.97933525,"about_ca_system_score_codex":0.000021258435,"about_ca_system_score_gemma":0.000025117663,"threshold_uncertainty_score":0.4432062},"labels":[],"label_agreement":null},{"id":"W3108741386","doi":"10.1145/3417564.3417575","title":"Genetic Improvement @ ICSE 2020","year":2020,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Engineering and Physical Sciences Research Council","keywords":"Coronavirus disease 2019 (COVID-19); Face (sociological concept); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); The Internet; Personal account; Software; Computer science; Pandemic; World Wide Web; Sociology; Medicine; Art; Virology; Operating system; Social science","score_opus":0.01721808277170105,"score_gpt":0.22137228675128495,"score_spread":0.2041542039795839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108741386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061980985,0.0005078146,0.90484804,0.0019279313,0.00035028433,0.000227588,0.000007393322,0.030147724,0.0000022599145],"genre_scores_gemma":[0.53521115,0.00001114778,0.46353757,0.0009928851,0.00017533325,0.000032026677,0.0000029490118,0.000032637938,0.0000043048103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981472,0.000016896363,0.00034095667,0.0006478354,0.00035249794,0.000494599],"domain_scores_gemma":[0.9846844,0.013557417,0.00009808511,0.0012095561,0.000104778395,0.0003457407],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013672022,0.0003308963,0.000278257,0.00007960382,0.00009850582,0.00018739168,0.001867941,0.00010956123,0.00001385592],"category_scores_gemma":[0.09986586,0.000342258,0.000113746384,0.0005829753,0.000023038883,0.0002589435,0.000928098,0.00029118228,0.00009579074],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017776818,0.00016118778,0.68661296,0.00059716415,0.00013780707,0.000472732,0.002461141,0.005545963,0.010343251,0.00094633666,0.04248727,0.2502164],"study_design_scores_gemma":[0.0026830204,0.003395949,0.72470003,0.00079782965,0.00015722132,0.0003184169,0.000011016077,0.14683445,0.08010011,0.0073600276,0.027020024,0.0066218833],"about_ca_topic_score_codex":0.0000310388,"about_ca_topic_score_gemma":3.8175392e-7,"teacher_disagreement_score":0.47323015,"about_ca_system_score_codex":0.00004837807,"about_ca_system_score_gemma":0.00006225243,"threshold_uncertainty_score":0.99990296},"labels":[],"label_agreement":null},{"id":"W3110815134","doi":"10.5381/jot.2021.20.3.a9","title":"Fixing Multiple Type Errors in Model Transformations with Alternative Oracles to Test Cases.","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Object Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Heuristics; Transformation (genetics); Computer science; Type I and type II errors; Type (biology); Model transformation; Algorithm; Selection (genetic algorithm); Space (punctuation); Artificial intelligence; Theoretical computer science; Machine learning; Mathematics; Statistics","score_opus":0.03467816425871621,"score_gpt":0.29206771445440244,"score_spread":0.2573895501956862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110815134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42825744,0.0002824391,0.5676533,0.0025572383,0.00012561647,0.00019127292,0.000003485533,0.0008923153,0.000036889982],"genre_scores_gemma":[0.7382626,0.00007469582,0.26151353,0.0001028119,0.000017128965,0.0000103340135,7.0598605e-7,0.000013335104,0.000004827749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986775,0.00008191222,0.0004968063,0.0002120794,0.0002735194,0.000258204],"domain_scores_gemma":[0.9975679,0.0007795173,0.00042913784,0.0006819905,0.00049081125,0.000050665305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072539964,0.00021499577,0.00040508207,0.00094543246,0.00009633576,0.00007885804,0.001840044,0.00020746447,0.0000010617902],"category_scores_gemma":[0.0016917159,0.00014581518,0.00006228543,0.0010644237,0.00007940898,0.00019359465,0.00063709787,0.0013182862,0.0000015664774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018284316,0.0007972009,0.019063264,0.0001712497,0.00025545474,0.0017636893,0.027452752,0.8924215,0.0019180062,0.0007786717,0.0018800879,0.05331529],"study_design_scores_gemma":[0.00094530825,0.0022337013,0.0009691126,0.0034054036,0.00011201597,0.0072681187,0.00085179275,0.8768795,0.026313916,0.08011347,0.00007370886,0.00083392597],"about_ca_topic_score_codex":0.00021045964,"about_ca_topic_score_gemma":0.00040272577,"teacher_disagreement_score":0.3100052,"about_ca_system_score_codex":0.00015614423,"about_ca_system_score_gemma":0.0005111387,"threshold_uncertainty_score":0.594617},"labels":[],"label_agreement":null},{"id":"W3118132313","doi":"10.1109/ictai50040.2020.00091","title":"Decision Support for Combining Security Mechanisms using Exploratory Evolutionary Testing","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Decision support system; Artificial intelligence","score_opus":0.0980905697129831,"score_gpt":0.3002942782632393,"score_spread":0.20220370855025618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118132313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028597293,0.000024453357,0.9851982,0.000236951,0.00020744768,0.00019986025,0.000002642849,0.0109798135,0.00029087227],"genre_scores_gemma":[0.35047403,2.7822682e-7,0.6484027,0.0010496051,0.000042374668,0.000015011345,0.0000017901765,0.0000112502685,0.0000029747202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987145,0.00003390471,0.00026464355,0.0004507859,0.00025758904,0.00027856935],"domain_scores_gemma":[0.99826044,0.00096259743,0.00009917892,0.00031122722,0.00021123269,0.00015533013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000426783,0.00014490316,0.00017089113,0.00006946774,0.0002686373,0.000105827115,0.00058912946,0.000066597284,0.0000074304726],"category_scores_gemma":[0.0016788322,0.00014279767,0.00006116263,0.00044957298,0.000021619584,0.00048600693,0.0004192215,0.00011430099,0.000011982427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015682206,0.00061052357,0.014550474,0.00046053127,0.00010136879,0.00026455693,0.011383342,0.0029992596,0.029052546,0.37642947,0.3054037,0.2585874],"study_design_scores_gemma":[0.00017147277,0.00021150876,0.000038228733,0.00004029593,0.0000041663393,0.000022334494,0.00001598251,0.7028486,0.0016660308,0.29460257,0.00021215637,0.00016664425],"about_ca_topic_score_codex":0.000013587519,"about_ca_topic_score_gemma":3.4618554e-7,"teacher_disagreement_score":0.6998493,"about_ca_system_score_codex":0.0000474038,"about_ca_system_score_gemma":0.00015583642,"threshold_uncertainty_score":0.582312},"labels":[],"label_agreement":null},{"id":"W3119230199","doi":"10.1109/tse.2021.3107680","title":"Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results in the Space Domain","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 European Research Council; Natural Sciences and Engineering Research Council of Canada; European Commission; European Space Agency","keywords":"Computer science; Context (archaeology); Software construction; Software; Software system; Scalability; Software reliability testing; Software engineering; Verification and validation; Avionics software; Domain (mathematical analysis); Reliability engineering; Engineering; Operating system","score_opus":0.02396113930530181,"score_gpt":0.25378680370064594,"score_spread":0.22982566439534413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119230199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012811318,0.00020634384,0.98235655,0.00022445951,0.0006319852,0.00052745896,0.0000875925,0.0031490691,0.0000052466503],"genre_scores_gemma":[0.69276565,0.000014734346,0.30658734,0.000019091589,0.000050674964,0.00050682185,0.00002132935,0.000019992076,0.000014378484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998118,0.00011499242,0.00040771932,0.000696519,0.00030875838,0.00035404565],"domain_scores_gemma":[0.99692243,0.0018744927,0.00012354572,0.0008842532,0.00012760749,0.000067638146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086566753,0.0003018857,0.0004274985,0.0005958977,0.00021929205,0.00048867695,0.0005114279,0.00019865364,2.9386982e-7],"category_scores_gemma":[0.00022569558,0.00027982105,0.00025203946,0.0011791447,0.000028914747,0.00018746415,0.000019317627,0.00064122933,8.4191606e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006284068,0.00009484717,0.00002503226,0.00014389768,0.00015815705,0.000017917306,0.002094254,0.9954139,0.000014106357,0.00029452948,0.00015343743,0.0015836462],"study_design_scores_gemma":[0.00030047158,0.00006670413,0.00062650803,0.00042550344,0.000219137,0.0000332255,0.00007402532,0.99661446,0.00024575982,0.00091184705,0.00008188339,0.000400455],"about_ca_topic_score_codex":0.0003467092,"about_ca_topic_score_gemma":0.00004951529,"teacher_disagreement_score":0.67995435,"about_ca_system_score_codex":0.00015393771,"about_ca_system_score_gemma":0.00009135601,"threshold_uncertainty_score":0.99996537},"labels":[],"label_agreement":null},{"id":"W31287713","doi":"10.1007/978-3-642-31753-8_18","title":"JSART: JavaScript Assertion-Based Regression Testing","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"JavaScript; Unobtrusive JavaScript; Computer science; Programming language; Correctness; Regression testing; Assertion; Rich Internet application; Source code; Test case; Web application; Data mining; Artificial intelligence; Machine learning; Operating system; Regression analysis; Software; Software development","score_opus":0.04071869676340591,"score_gpt":0.2725068548380246,"score_spread":0.23178815807461872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W31287713","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051013245,0.00086127565,0.9892651,0.00044699048,0.0015938181,0.00029430736,0.00000194399,0.0053085955,0.0021769847],"genre_scores_gemma":[0.22759762,0.0000044959006,0.7703619,0.0013886618,0.00045957006,0.000013570308,0.0000043062428,0.000044233864,0.00012564649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580634,0.000057299818,0.0005753616,0.0014776961,0.0011836815,0.0008996491],"domain_scores_gemma":[0.99455035,0.0023625016,0.00043676113,0.001948145,0.0004408953,0.00026134268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015977477,0.0006398462,0.0005376496,0.00096612755,0.00043436943,0.0005771111,0.0032611047,0.0004161267,0.000013894593],"category_scores_gemma":[0.001428755,0.00054552057,0.00013979364,0.0009072398,0.0004710951,0.0006716503,0.001059239,0.0009818422,0.0000578338],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003062336,0.000041435123,0.0024581093,0.000048503898,0.0000036715994,0.00005236653,0.00018688379,0.0033582433,0.00018673319,0.0016683264,0.00031791907,0.9916747],"study_design_scores_gemma":[0.00024782695,0.00021912374,0.00094345724,0.0019034145,0.000012910598,0.000105079984,1.8516443e-8,0.69269145,0.0033379467,0.298132,0.0013278314,0.001078955],"about_ca_topic_score_codex":0.000045639892,"about_ca_topic_score_gemma":0.0000075251774,"teacher_disagreement_score":0.9905958,"about_ca_system_score_codex":0.00034915737,"about_ca_system_score_gemma":0.0007269879,"threshold_uncertainty_score":0.99969965},"labels":[],"label_agreement":null},{"id":"W3131260619","doi":"10.1109/sbst52555.2021.00010","title":"Data Driven Testing of Cyber Physical Systems","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Testbed; Computer science; Python (programming language); Cyber-physical system; Thermostat; Software deployment; Software; Task (project management); Software engineering; Domain (mathematical analysis); Implementation; Distributed computing; Systems engineering; Engineering; Programming language","score_opus":0.1260824671765509,"score_gpt":0.32881512688358794,"score_spread":0.20273265970703705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131260619","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015036099,0.00021876743,0.9676425,0.00009225277,0.00069574977,0.00021865615,0.000034517056,0.012055547,0.00400594],"genre_scores_gemma":[0.4718224,0.0000018999954,0.5278895,0.000023747381,0.00013204939,0.000012832963,0.000043331864,0.0000117333675,0.00006247805],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808747,0.00010323848,0.00032826705,0.00089009065,0.00038244348,0.00020846607],"domain_scores_gemma":[0.99439865,0.00090753776,0.00027734393,0.0040455605,0.00030763063,0.00006324471],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003845995,0.00021190578,0.000453596,0.000082758976,0.000041788848,0.00033608824,0.003822822,0.00013356765,0.0000014050287],"category_scores_gemma":[0.0012785022,0.00018917426,0.000064340944,0.00029214352,0.00004571246,0.00020152144,0.012140743,0.00040482922,0.0000045622824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008647844,0.0030823394,0.08453166,0.008364294,0.0010998129,0.000981291,0.006746668,0.039843403,0.0034754337,0.053828735,0.44539437,0.35264334],"study_design_scores_gemma":[0.0000378791,0.00002242455,0.00054729177,0.0008881238,0.000017021412,0.000027437176,0.0000058474643,0.9925475,0.00029170176,0.005250332,0.00011332553,0.00025110366],"about_ca_topic_score_codex":0.0010661114,"about_ca_topic_score_gemma":0.00000398873,"teacher_disagreement_score":0.95270413,"about_ca_system_score_codex":0.000028437951,"about_ca_system_score_gemma":0.00030243312,"threshold_uncertainty_score":0.9958489},"labels":[],"label_agreement":null},{"id":"W3135281973","doi":"10.32628/cseit1949168","title":"Impact of Automation on the Test Insertion","year":2019,"lang":"en","type":"article","venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Automation; Test (biology); Computer science; Engineering; Geology; Mechanical engineering","score_opus":0.02411700522098179,"score_gpt":0.32688362792859393,"score_spread":0.3027666227076121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135281973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7917794,0.000008677395,0.20566817,0.0015055143,0.00073983544,0.00009329054,8.378566e-7,0.00015590734,0.000048379963],"genre_scores_gemma":[0.96492755,0.000007218965,0.035025887,0.000015273945,0.000017971903,0.000002420768,2.8472158e-7,0.0000014184421,0.0000019467325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828947,0.000021648731,0.00038612675,0.00012020348,0.0009990641,0.00018347752],"domain_scores_gemma":[0.9975713,0.0005709992,0.00020193621,0.00028401168,0.001333776,0.000037985028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044528614,0.000060871716,0.000092786206,0.0038177094,0.0000777008,0.00048245085,0.001733909,0.00004284362,0.00000233702],"category_scores_gemma":[0.0013822588,0.000040538067,0.0000323911,0.0023239413,0.00028870662,0.0025168515,0.0003295855,0.00031269022,0.000009115459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002667174,0.0002376159,0.058581147,0.00003736011,0.000034669953,0.000011188256,0.0018138835,0.07843284,0.017900126,0.15972501,0.0018652941,0.6813342],"study_design_scores_gemma":[0.00018089979,0.0004830111,0.03865498,0.00021403546,2.7864363e-7,0.00009048745,0.000008146864,0.94531685,0.004422725,0.010401735,0.00017066016,0.00005617002],"about_ca_topic_score_codex":0.000008225491,"about_ca_topic_score_gemma":9.1901214e-8,"teacher_disagreement_score":0.86688405,"about_ca_system_score_codex":0.00017658394,"about_ca_system_score_gemma":0.00024824956,"threshold_uncertainty_score":0.46522847},"labels":[],"label_agreement":null},{"id":"W3142089163","doi":"10.1109/ase.2004.1342761","title":"Using a genetic algorithm and formal concept analysis to generate branch coverage test data automatically","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pointer (user interface); Algorithm; Pairwise comparison; Test suite; Theoretical computer science; Programming language; Artificial intelligence; Test case; Machine learning","score_opus":0.04303292143597743,"score_gpt":0.30504203559225707,"score_spread":0.26200911415627964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142089163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01706717,0.00006610654,0.97900075,0.00021711188,0.000042578853,0.00012905021,0.000020729509,0.003377709,0.00007880385],"genre_scores_gemma":[0.28536686,0.0000026926052,0.7138003,0.000767863,0.000030189716,0.000003293721,0.0000069140224,0.000006383865,0.000015490048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864537,0.000024787616,0.00025057347,0.00052161724,0.00023358295,0.00032404487],"domain_scores_gemma":[0.9984078,0.00020412041,0.000053068336,0.001092978,0.00007331575,0.00016871204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026626512,0.00014943187,0.0002239233,0.00018690208,0.00016026304,0.00036336153,0.0008977594,0.000047934835,0.000007254646],"category_scores_gemma":[0.0002679329,0.00013179966,0.00003382943,0.0009867827,0.000041289364,0.000508077,0.0009998963,0.00007065058,0.000007167113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022528861,0.00019907556,0.0074655185,0.000020584155,0.0002751929,0.00012231804,0.0010627691,0.035111763,0.000428737,0.001832707,0.0023475853,0.9511315],"study_design_scores_gemma":[0.00020632011,0.00009070685,0.009379288,0.000017929473,0.000072918054,0.00007267626,8.0212556e-7,0.9784165,0.0005109128,0.010962534,0.000040735544,0.00022869797],"about_ca_topic_score_codex":0.00050603726,"about_ca_topic_score_gemma":0.00001127634,"teacher_disagreement_score":0.9509028,"about_ca_system_score_codex":0.000036937585,"about_ca_system_score_gemma":0.000096927906,"threshold_uncertainty_score":0.5374635},"labels":[],"label_agreement":null},{"id":"W3143871025","doi":"10.1007/s00165-005-0082-8","title":"A formal approach to property testing in causally consistent distributed traces","year":2006,"lang":"en","type":"article","venue":"Formal Aspects of Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"TRACE (psycholinguistics); Computer science; Theory of computation; Property (philosophy); Automaton; Consistency (knowledge bases); Model checking; Causality (physics); Theoretical computer science; Programming language; Property testing; Event (particle physics); Relation (database); Algorithm; Data mining; Artificial intelligence","score_opus":0.025169513752820116,"score_gpt":0.2376320665976636,"score_spread":0.21246255284484347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143871025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19102545,0.000036559817,0.79145706,0.000106990396,0.000078785306,0.0003538027,0.0000037392465,0.002861337,0.01407629],"genre_scores_gemma":[0.6329649,7.3478965e-8,0.36691347,0.00004602492,0.000046859488,0.000007129185,0.000005398577,0.000008471523,0.000007645207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785686,0.000050563303,0.0006298592,0.0003966742,0.00035687131,0.0007091478],"domain_scores_gemma":[0.9987735,0.0003211389,0.00023884953,0.0003739231,0.00020558317,0.00008701509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008574694,0.00021910957,0.00034031173,0.00023337085,0.00018254624,0.00013756799,0.0007665604,0.000066745204,3.5488546e-7],"category_scores_gemma":[0.0004353143,0.00016873458,0.00006590178,0.0010208457,0.000048585865,0.0006072557,0.00061006186,0.00021098966,0.0000031595812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011850707,0.0030836733,0.16590106,0.0011102728,0.0000779394,0.0002664288,0.0057505257,0.18875061,0.0030038105,0.28051013,0.0064336136,0.3449934],"study_design_scores_gemma":[0.00056057173,0.00041333435,0.09690414,0.00041655469,0.0000070499955,0.00018844158,0.000033315682,0.8861846,0.0025714447,0.012121594,0.00011515354,0.00048382833],"about_ca_topic_score_codex":0.0008261823,"about_ca_topic_score_gemma":0.00002539712,"teacher_disagreement_score":0.69743395,"about_ca_system_score_codex":0.00008140303,"about_ca_system_score_gemma":0.00012001086,"threshold_uncertainty_score":0.68807966},"labels":[],"label_agreement":null},{"id":"W3149550336","doi":"10.1109/raise.2012.6227969","title":"Predicting mutation score using source code and test suite metrics","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Test suite; Computer science; Mutation; Mutation testing; Source code; Suite; Code coverage; Test case; Process (computing); Code (set theory); Reliability engineering; Programming language; Machine learning; Software; Set (abstract data type); Engineering; Biology; Genetics","score_opus":0.05832407227421543,"score_gpt":0.2908110474789894,"score_spread":0.23248697520477396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149550336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29416743,0.00014340844,0.70057636,0.000036482114,0.00007160262,0.000053049444,5.0533674e-7,0.004755454,0.00019573917],"genre_scores_gemma":[0.6381158,0.0000012709514,0.3616805,0.00010612295,0.00004797394,0.0000016089788,4.5280976e-7,0.0000055464616,0.000040686322],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992926,0.000023287692,0.00012591384,0.00016597584,0.000162544,0.00022966244],"domain_scores_gemma":[0.99848604,0.0010867035,0.00006862651,0.00021038642,0.000058486425,0.00008973206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050191977,0.00008178357,0.000078580764,0.0001462501,0.00014472759,0.0001334126,0.00018020283,0.000041661755,0.0000014256053],"category_scores_gemma":[0.0019199137,0.00007318757,0.000015059707,0.00047968607,0.000024862411,0.0005183896,0.00017871098,0.000076954115,0.0000027590859],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.4291288e-7,0.000020057607,0.97056323,0.000009497922,0.0000020960829,0.0000012888777,0.00047070152,0.000020082745,0.00014092134,0.0005031577,0.00033917758,0.027929561],"study_design_scores_gemma":[0.0001386402,0.00006953335,0.06651471,0.000065068714,0.000013992538,0.0002712967,0.000020311285,0.92620534,0.0032025925,0.0029990238,0.0002531169,0.0002463777],"about_ca_topic_score_codex":0.00015351112,"about_ca_topic_score_gemma":0.0000022017662,"teacher_disagreement_score":0.92618525,"about_ca_system_score_codex":0.000027369768,"about_ca_system_score_gemma":0.000016830423,"threshold_uncertainty_score":0.29845026},"labels":[],"label_agreement":null},{"id":"W3150233949","doi":"10.1109/date.2012.6176548","title":"Non-solution implications using reverse domination in a modern SAT-based debugging environment","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Debugging; Pruning; Satisfiability modulo theories; Leverage (statistics); Bottleneck; Solver; Speedup; Parallel computing; Algorithmic program debugging; Theoretical computer science; Programming language; Embedded system; Artificial intelligence","score_opus":0.03952488856495533,"score_gpt":0.2789340241394563,"score_spread":0.23940913557450094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150233949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039976127,0.000039677187,0.95727134,0.0004830578,0.00004876437,0.00015774716,6.486668e-7,0.0017886834,0.00023398528],"genre_scores_gemma":[0.5818297,8.8849123e-7,0.41794547,0.00017156576,0.000014985632,0.000021987245,0.000002678749,0.0000046120313,0.000008077562],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917185,0.00003524784,0.00017661882,0.00021180774,0.00013225217,0.00027221095],"domain_scores_gemma":[0.99932665,0.000102570484,0.00007082157,0.00041759064,0.000018218263,0.000064148015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045843792,0.00009520859,0.00008546642,0.00018017071,0.00010275891,0.00003906746,0.00023498808,0.000051445088,0.0000045120214],"category_scores_gemma":[0.000050841427,0.000096266325,0.000031398526,0.00022085237,0.000019954081,0.00047834637,0.00009678495,0.00007617756,0.000016604961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015044073,0.0011282892,0.4878083,0.00006656692,0.000018251329,0.0000054464276,0.0033999374,0.014659949,0.05033875,0.008803524,0.0066709877,0.42708498],"study_design_scores_gemma":[0.00016866754,0.000012712717,0.04531188,0.000034140907,0.00000461214,0.000007961933,0.0000026532484,0.9451415,0.001961569,0.0071217287,0.00008295368,0.0001496087],"about_ca_topic_score_codex":0.00022459477,"about_ca_topic_score_gemma":0.0000048921493,"teacher_disagreement_score":0.93048155,"about_ca_system_score_codex":0.00026001516,"about_ca_system_score_gemma":0.000039343246,"threshold_uncertainty_score":0.3925627},"labels":[],"label_agreement":null},{"id":"W3155466149","doi":"10.1109/sp40001.2021.00109","title":"StochFuzz: Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic Rewriting","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Rewriting; Probabilistic logic; Soundness; Binary translation; Programming language; Binary number; Static analysis; Process (computing); Algorithm; Artificial intelligence; Software","score_opus":0.016390658772891135,"score_gpt":0.26720851668917894,"score_spread":0.2508178579162878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155466149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21997152,0.0007709643,0.7771077,0.00015702579,0.000039032704,0.0003170217,0.0000055452083,0.001311483,0.00031968957],"genre_scores_gemma":[0.91960007,0.000006240742,0.08020352,0.00011058396,0.000010903235,0.000025669297,0.0000029930611,0.000006659656,0.000033360815],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910396,0.00006789151,0.0001704951,0.00032580792,0.0001543907,0.00017743175],"domain_scores_gemma":[0.9987345,0.00081812515,0.0000778266,0.00020647972,0.00010022807,0.00006286981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030019003,0.00011550862,0.00017974348,0.0000619352,0.00014853501,0.00015421638,0.00013212414,0.000043672564,0.000002712839],"category_scores_gemma":[0.00059162424,0.0001123167,0.000018422246,0.00020867666,0.00011045291,0.00023756128,0.00041241822,0.000099921985,3.9211565e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007758031,0.00045990007,0.07211079,0.0005486735,0.00025090782,0.00016559154,0.0055546807,0.00006680697,0.06753534,0.07722909,0.014846613,0.76115406],"study_design_scores_gemma":[0.006470867,0.0029231682,0.025312772,0.0019494647,0.0001884743,0.0021256278,0.0026854484,0.27953732,0.23777209,0.43751824,0.00046759626,0.0030489229],"about_ca_topic_score_codex":0.00013517354,"about_ca_topic_score_gemma":0.000010851959,"teacher_disagreement_score":0.7581051,"about_ca_system_score_codex":0.000024744473,"about_ca_system_score_gemma":0.000029391404,"threshold_uncertainty_score":0.45801422},"labels":[],"label_agreement":null},{"id":"W3157242654","doi":"10.22215/etd/2017-11952","title":"An Analysis and Extension of Category Partition Testing in the Presence of Constraints","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Constraint (computer-aided design); Partition (number theory); Set (abstract data type); Domain (mathematical analysis); Extension (predicate logic); Base (topology); Test suite; White-box testing; Completeness (order theory); Test case; Programming language; Mathematics; Software; Machine learning; Software development","score_opus":0.042013065491432446,"score_gpt":0.3265260541144748,"score_spread":0.2845129886230423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157242654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8699073,0.00015828131,0.12307173,0.000036812395,0.0000985067,0.00031937,0.000004876888,0.0008773811,0.0055256984],"genre_scores_gemma":[0.9541438,0.000007484513,0.04576813,0.000009959513,0.000005427817,0.000008790205,0.000025077594,0.0000030312744,0.000028269074],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990785,0.000098873745,0.00025728042,0.00026777168,0.00020723244,0.00009035144],"domain_scores_gemma":[0.99803555,0.0005909009,0.00040148816,0.0007418262,0.00021065075,0.000019575386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078993296,0.00009556943,0.00023459946,0.00025113745,0.00006340417,0.00005950409,0.0006130096,0.0000862578,0.0000022800527],"category_scores_gemma":[0.0010978851,0.00006834549,0.0000366352,0.0003350023,0.00009946054,0.00018087254,0.000023731149,0.0001040232,1.3060479e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023624005,0.0003452158,0.34168157,0.0005239643,0.00010577393,0.000037902522,0.010252862,0.00018867616,0.008797788,0.008387153,0.0004780533,0.6291774],"study_design_scores_gemma":[0.0000805308,0.00015684073,0.86973315,0.00038401125,0.000114949966,0.000008586025,0.00022558759,0.09014118,0.0068297856,0.032150578,9.462641e-7,0.00017383655],"about_ca_topic_score_codex":0.002135506,"about_ca_topic_score_gemma":0.0004050678,"teacher_disagreement_score":0.6290036,"about_ca_system_score_codex":0.0000047656313,"about_ca_system_score_gemma":0.0000620659,"threshold_uncertainty_score":0.32282603},"labels":[],"label_agreement":null},{"id":"W3160700180","doi":"10.1109/icse43902.2021.00138","title":"Automatic Unit Test Generation for Machine Learning Libraries: How Far Are We?","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Unit testing; Test suite; Machine learning; Computer science; Artificial intelligence; Test (biology); Test Management Approach; Code coverage; Unit (ring theory); Test set; Set (abstract data type); Software; Quality (philosophy); Test case; Software development; Programming language; Software construction","score_opus":0.06743097283882477,"score_gpt":0.2686211446901192,"score_spread":0.20119017185129445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160700180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012845855,0.0003545523,0.9755098,0.009056669,0.00010859099,0.0001054362,0.0000025682516,0.013352048,0.00022575667],"genre_scores_gemma":[0.15665166,0.000019151597,0.8393217,0.00086098915,0.0000852755,0.000039310846,0.000024397597,0.000014803531,0.0029827433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992205,0.00005071065,0.00012308046,0.00029414162,0.00013272408,0.00017884524],"domain_scores_gemma":[0.99859935,0.0007661906,0.00008311722,0.00036798118,0.00013130427,0.000052028194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017373388,0.00011164823,0.00013110129,0.000063503474,0.00022989653,0.00056421995,0.00031285908,0.00005265874,0.000024021794],"category_scores_gemma":[0.0018436547,0.00009983285,0.000045944238,0.0003305615,0.00001634206,0.00053492555,0.00016546914,0.000104103936,0.0000064664587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002481868,0.00036308082,0.070531026,0.0004149179,0.00006592466,0.00011792237,0.0017867208,0.00057626754,0.006387762,0.0871675,0.2927419,0.5398445],"study_design_scores_gemma":[0.00011368222,0.00007176192,0.00030758284,0.00004539838,0.0000046762325,0.000026161364,0.0000128873835,0.966528,0.0068604546,0.013105862,0.012774376,0.00014916471],"about_ca_topic_score_codex":0.000011108675,"about_ca_topic_score_gemma":0.000010456101,"teacher_disagreement_score":0.96595174,"about_ca_system_score_codex":0.000013961665,"about_ca_system_score_gemma":0.00008650944,"threshold_uncertainty_score":0.5440786},"labels":[],"label_agreement":null},{"id":"W3160705248","doi":"10.1145/3249769","title":"Session details: Session 48: formal specification and verification testbench generation","year":2006,"lang":"en","type":"article","venue":"Design Automation Conference","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Session (web analytics); Computer science; Programming language; Formal verification; Formal specification; Formal methods; Functional verification; Software engineering; Computer architecture; World Wide Web","score_opus":0.0665673360729413,"score_gpt":0.2736821927955757,"score_spread":0.2071148567226344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160705248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018530263,0.000062637606,0.9753072,0.0004015263,0.0001628977,0.00031701097,0.0000012012904,0.0047170776,0.00050015544],"genre_scores_gemma":[0.6606206,0.0000139383155,0.33907568,0.00004657582,0.00006881115,0.00005051547,0.00004048262,0.0000070452734,0.000076324824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849755,0.00017774754,0.00036727072,0.0004318156,0.00030994232,0.0002157077],"domain_scores_gemma":[0.99878347,0.00016562841,0.00026318073,0.00044816692,0.0002837045,0.000055825614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065275526,0.00016827974,0.00013152233,0.0001798453,0.00033085363,0.0004654032,0.0003060788,0.00011741829,0.000014723358],"category_scores_gemma":[0.0001723311,0.00015886404,0.000022415095,0.0003446047,0.000041405325,0.0015710962,0.00007150986,0.00010089784,0.000042555464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012986427,0.0001859476,0.0042110644,0.00005971972,0.000006877489,0.0000052609707,0.0008256025,0.0008631925,0.19303024,0.1328371,0.032162983,0.63579905],"study_design_scores_gemma":[0.00016781964,0.000049289683,0.03348364,0.000057436413,0.0000053579265,0.000021731592,0.0000048732068,0.90794754,0.032871664,0.024919573,0.00026005096,0.00021100711],"about_ca_topic_score_codex":0.00005308692,"about_ca_topic_score_gemma":0.0000031025324,"teacher_disagreement_score":0.90708435,"about_ca_system_score_codex":0.00006771692,"about_ca_system_score_gemma":0.00011046785,"threshold_uncertainty_score":0.64782876},"labels":[],"label_agreement":null},{"id":"W3161421710","doi":"10.1007/978-3-030-74296-6_32","title":"Automated Repair of Layout Bugs in Web Pages with Linear Programming","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Solver; Integer programming; Container (type theory); Linear programming; Web page; State (computer science); Programming language; Parallel computing; Algorithm; World Wide Web; Engineering","score_opus":0.019652387797870846,"score_gpt":0.2611711895946186,"score_spread":0.24151880179674776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161421710","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007735237,0.0004679183,0.98873776,0.00024157138,0.00029253305,0.00035297126,0.0000022980475,0.008631525,0.0004999057],"genre_scores_gemma":[0.17404275,0.000019112955,0.82548803,0.00023481871,0.00008431064,0.000013123004,0.0000040158516,0.00003141787,0.00008244899],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650764,0.00005489133,0.00059300184,0.0013752121,0.0008874851,0.0005817559],"domain_scores_gemma":[0.9970687,0.0006088891,0.00034846985,0.001460741,0.00040614308,0.00010707423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010641196,0.00046401634,0.00066150614,0.00092623086,0.00010068493,0.00022673186,0.002018148,0.00029436965,0.0000037392592],"category_scores_gemma":[0.0002972275,0.00039250063,0.00011702685,0.0013519461,0.00059266086,0.00033664334,0.0010798745,0.00072263775,0.0000030411168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018753424,0.0002008607,0.007888875,0.00038482016,0.000040100538,0.0013958897,0.0025320658,0.02666566,0.0001475086,0.0036653567,0.00025235265,0.95680773],"study_design_scores_gemma":[0.00028078395,0.0004095583,0.00050245924,0.0031170116,0.000009155109,0.00017425639,2.2408476e-7,0.9747446,0.0013370189,0.018307285,0.00042482553,0.0006927915],"about_ca_topic_score_codex":0.0000570972,"about_ca_topic_score_gemma":0.00016565679,"teacher_disagreement_score":0.95611495,"about_ca_system_score_codex":0.00017091901,"about_ca_system_score_gemma":0.00093596545,"threshold_uncertainty_score":0.9998527},"labels":[],"label_agreement":null},{"id":"W3163160051","doi":"10.1145/2637365.2517225","title":"On the simplicity of synthesizing linked data structure operations","year":2013,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Simplicity; Data structure; Code (set theory); Simple (philosophy); Code generation; Programming language; Algorithm; Theoretical computer science; Parallel computing; Set (abstract data type); Operating system","score_opus":0.06814676140076811,"score_gpt":0.28931906523018935,"score_spread":0.22117230382942124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163160051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90690356,0.000075084055,0.079360396,0.00872606,0.0002275077,0.000490249,0.00006496181,0.0035692486,0.00058291975],"genre_scores_gemma":[0.8724882,0.0000012210594,0.12675224,0.0006904916,0.000037120473,0.0000069945077,0.000008982223,0.000005424104,0.000009313429],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916,0.00007593475,0.00016099324,0.00027160568,0.00018698564,0.00014446834],"domain_scores_gemma":[0.99399227,0.0033097162,0.00007621385,0.0025114908,0.0000753816,0.00003494087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023652565,0.00009878368,0.00011224608,0.000044261447,0.00016970144,0.00020217281,0.0034950026,0.00004762765,0.0000389572],"category_scores_gemma":[0.003989763,0.000060483508,0.000017094113,0.00017032005,0.00004975337,0.00040255042,0.00078326126,0.0001396863,0.000023699495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019537321,0.00045439185,0.029142788,0.00022866424,0.00027070392,0.000021789938,0.007290622,0.0068902546,0.029543033,0.25946575,0.40695208,0.25972039],"study_design_scores_gemma":[0.00019272539,0.00025925066,0.04366876,0.00031741484,0.00004026354,0.000018153618,0.000058981663,0.61472315,0.015941622,0.32350022,0.0006787084,0.0006007834],"about_ca_topic_score_codex":0.0006281657,"about_ca_topic_score_gemma":0.000038569593,"teacher_disagreement_score":0.60783285,"about_ca_system_score_codex":0.0000069566963,"about_ca_system_score_gemma":0.000030337895,"threshold_uncertainty_score":0.64946425},"labels":[],"label_agreement":null},{"id":"W3163537710","doi":"10.1145/3249746","title":"Session details: Session 25: the test bin","year":2006,"lang":"en","type":"article","venue":"Design Automation Conference","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Session (web analytics); Computer science; Test (biology); Bin; World Wide Web; Programming language","score_opus":0.04490146855196091,"score_gpt":0.27352533837223153,"score_spread":0.2286238698202706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163537710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018030321,0.00004097049,0.98468786,0.0013236075,0.00014928413,0.0002479275,0.000001168194,0.0104584,0.0012877289],"genre_scores_gemma":[0.7218296,0.0000034639068,0.27762493,0.00020065006,0.00004187158,0.000044598324,0.0000033493143,0.000007682338,0.00024382537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985596,0.00022569826,0.00028734189,0.00033650346,0.00035466108,0.00023619016],"domain_scores_gemma":[0.99735826,0.0015569727,0.00019747637,0.00063312205,0.00020977831,0.000044407552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007193517,0.00016433984,0.00012926849,0.00010980829,0.00033926129,0.000450149,0.00086000963,0.000086180575,0.000023825862],"category_scores_gemma":[0.0007171541,0.00011068938,0.000038366128,0.0004778104,0.000059367707,0.0004944283,0.00014630573,0.00014527756,0.00011087651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009624981,0.00043385182,0.014427111,0.000069789676,0.000012987063,0.000043938933,0.0013796057,0.0012419249,0.032717522,0.092358224,0.3016802,0.5556252],"study_design_scores_gemma":[0.0001454849,0.00007389523,0.019656258,0.00015398982,0.000005335331,0.000031184085,0.0000054901266,0.84888667,0.013177511,0.116764575,0.00087636866,0.00022323629],"about_ca_topic_score_codex":0.000105928135,"about_ca_topic_score_gemma":0.0000035504765,"teacher_disagreement_score":0.84764475,"about_ca_system_score_codex":0.000044114302,"about_ca_system_score_gemma":0.00016323033,"threshold_uncertainty_score":0.45137823},"labels":[],"label_agreement":null},{"id":"W3163597827","doi":"10.1109/icse43902.2021.00019","title":"Studying Test Annotation Maintenance in the Wild","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Annotation; Computer science; Java; Fixture; Test (biology); Empirical research; Test case; Software engineering; Artificial intelligence; Machine learning; Programming language; Engineering","score_opus":0.031171318486716636,"score_gpt":0.2705429677314099,"score_spread":0.23937164924469326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163597827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013674344,0.00007732683,0.96910465,0.0058205244,0.00008904737,0.0000916103,2.4783742e-7,0.0035590946,0.007583183],"genre_scores_gemma":[0.81928587,0.0000032303706,0.17856246,0.0019529221,0.00001354748,0.000012000214,4.4467112e-7,0.0000020276495,0.00016752968],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994369,0.000049798346,0.00009476171,0.00016874571,0.0001302515,0.000119522985],"domain_scores_gemma":[0.99888307,0.00067338656,0.00002261537,0.00035077476,0.00005912449,0.00001104924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038928835,0.00004680663,0.000048992268,0.000030417808,0.000057114998,0.00012590013,0.0003894151,0.000015265421,0.0000018591542],"category_scores_gemma":[0.0009337039,0.000031212556,0.00001486181,0.00049365556,0.000011485469,0.00014518504,0.00008791951,0.00008045552,0.000008869969],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016730976,0.0005233741,0.34818506,0.000024792373,0.0000064321985,0.0005825881,0.008452396,0.000095148265,0.00061803916,0.10631871,0.16997826,0.36521354],"study_design_scores_gemma":[0.0006768928,0.00022635082,0.391855,0.00030437816,0.0000058873256,0.00046920936,0.0005563044,0.1978102,0.004026967,0.3956896,0.0077589415,0.0006202835],"about_ca_topic_score_codex":0.000054692806,"about_ca_topic_score_gemma":0.00002691464,"teacher_disagreement_score":0.8056115,"about_ca_system_score_codex":0.0000141339715,"about_ca_system_score_gemma":0.000032837357,"threshold_uncertainty_score":0.12728111},"labels":[],"label_agreement":null},{"id":"W3169794909","doi":"10.1109/icstw52544.2021.00040","title":"Test Sequence Generation with Cayley Graphs","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Test suite; Computer science; Sequence (biology); Graph; Theoretical computer science; Set (abstract data type); Metric (unit); Finite-state machine; Algorithm; Test case; Programming language; Engineering; Machine learning","score_opus":0.04702509873227484,"score_gpt":0.26444477978923137,"score_spread":0.21741968105695653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169794909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011848409,0.000048700727,0.97412294,0.0007619624,0.00006596388,0.000040711962,5.894932e-7,0.00835518,0.0047555314],"genre_scores_gemma":[0.5033057,0.000003393714,0.49577075,0.0005496798,0.000016788033,0.000006765826,0.0000023631515,0.0000031853433,0.00034140324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937075,0.000019741628,0.000076807795,0.00026499238,0.00014462986,0.00012305503],"domain_scores_gemma":[0.9992107,0.00012328416,0.000024829635,0.0004488482,0.00014946135,0.00004288408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009743497,0.00006872043,0.000060813632,0.000034655026,0.00008186561,0.00014798522,0.0002316551,0.000024388422,0.000009979019],"category_scores_gemma":[0.00018602649,0.000053196676,0.000015929634,0.00040093012,0.000021550504,0.00020567015,0.000072458824,0.000039993523,0.0000137404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030424335,0.0004228117,0.17433317,0.00004160699,0.000037950147,0.001540142,0.0010768271,0.00023364468,0.13902181,0.28211743,0.15684472,0.24432684],"study_design_scores_gemma":[0.00045478102,0.00048900396,0.00511267,0.000121081335,0.000014111747,0.0023334865,0.000010507349,0.2692583,0.58555573,0.13312857,0.0025781519,0.0009435796],"about_ca_topic_score_codex":0.000044596025,"about_ca_topic_score_gemma":0.000030221021,"teacher_disagreement_score":0.49145728,"about_ca_system_score_codex":0.000014275085,"about_ca_system_score_gemma":0.00010204174,"threshold_uncertainty_score":0.21692975},"labels":[],"label_agreement":null},{"id":"W3173275515","doi":"","title":"RIFF: Reduced Instruction Footprint for Coverage-Guided Fuzzing.","year":2021,"lang":"en","type":"article","venue":"USENIX Annual Technical Conference","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Footprint; Operating system; Software; Geography","score_opus":0.0541948968657504,"score_gpt":0.3114097351044024,"score_spread":0.257214838238652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173275515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032478664,0.000048429287,0.9508169,0.0017711354,0.0004445929,0.00034789348,0.000027192591,0.011558574,0.0025066151],"genre_scores_gemma":[0.67876834,0.000015509677,0.32054687,0.00027777452,0.00007816771,0.00008430827,0.000011588659,0.000015271073,0.00020215227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978531,0.00008956423,0.00045582897,0.0008145803,0.0003433013,0.0004436374],"domain_scores_gemma":[0.9972845,0.00046625236,0.00015506493,0.0010498327,0.0008804008,0.00016396995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004164819,0.00024697045,0.0003266901,0.00011185218,0.00021488969,0.00028632197,0.0009589194,0.00023094064,0.000011181735],"category_scores_gemma":[0.0023297055,0.0002484615,0.00015405467,0.0005251933,0.00010259629,0.0002886437,0.0005894877,0.00034136206,0.0000133110425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000489212,0.0003511376,0.00085714925,0.00011782137,0.000040779738,0.000114847724,0.00056325376,0.000033927383,0.04203949,0.4609851,0.038438436,0.45640916],"study_design_scores_gemma":[0.0017426964,0.0006701181,0.005839807,0.00036767815,0.00004138772,0.0010444387,0.000035449666,0.009491085,0.16940497,0.7686665,0.04128272,0.0014131286],"about_ca_topic_score_codex":0.000036432448,"about_ca_topic_score_gemma":0.000010465513,"teacher_disagreement_score":0.6462897,"about_ca_system_score_codex":0.00008832805,"about_ca_system_score_gemma":0.00036869262,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W3173309977","doi":"10.1109/msr52588.2021.00084","title":"EqBench: A Dataset of Equivalent and Non-equivalent Program Pairs","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Education","keywords":"Equivalence (formal languages); Computer science; Formal equivalence checking; Programming language; Java; Benchmark (surveying); Model checking; Program analysis; String (physics); Theoretical computer science; Algorithm; Arithmetic; Discrete mathematics; Mathematics","score_opus":0.033712847771385834,"score_gpt":0.3087434225400677,"score_spread":0.27503057476868187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173309977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021898529,0.00072787335,0.96050686,0.0013505127,0.0003068423,0.0005526216,0.00019154383,0.011030182,0.0034350592],"genre_scores_gemma":[0.33557484,0.000033145112,0.6639231,0.0002481893,0.000018277397,0.000026251833,0.000100263715,0.000006287839,0.00006965608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894273,0.00003643755,0.00022618212,0.0003569959,0.00022593758,0.00021170918],"domain_scores_gemma":[0.9988756,0.00015887701,0.00007043198,0.0007272538,0.00007909484,0.00008872418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029370663,0.000108089014,0.00015938893,0.000054464243,0.000048265283,0.00009095032,0.00039714715,0.000040119496,0.000025670246],"category_scores_gemma":[0.00013719943,0.00009201054,0.000028221715,0.00025103975,0.00006061227,0.00016612577,0.0007358704,0.000073223404,0.0000058362853],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005709437,0.000770416,0.01481304,0.00027490815,0.0000483473,0.00019761409,0.00044848892,0.0000066149164,0.0011100332,0.009159806,0.44413832,0.5290267],"study_design_scores_gemma":[0.003767454,0.00545374,0.057178635,0.0015920646,0.0001892604,0.0015590941,0.00021679977,0.37065637,0.15738283,0.17319559,0.2251049,0.0037032855],"about_ca_topic_score_codex":0.0000839485,"about_ca_topic_score_gemma":0.00000554617,"teacher_disagreement_score":0.52532345,"about_ca_system_score_codex":0.000011691841,"about_ca_system_score_gemma":0.000077291275,"threshold_uncertainty_score":0.37520808},"labels":[],"label_agreement":null},{"id":"W3174050238","doi":"10.1109/icccs52626.2021.9449249","title":"Automatic Generation of Parallel Java Programs and their Validation using Combinatorial Testing Suites","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Stem Cell Network","keywords":"Computer science; Executable; Java; Correctness; Programming language; Test suite; Parallel computing; Thread (computing); Suite; Multi-core processor; Operating system; Test case","score_opus":0.179823003380709,"score_gpt":0.3190231130519308,"score_spread":0.13920010967122182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174050238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23358734,0.00036966367,0.7629885,0.00039224597,0.0011989931,0.0003192105,0.000006573305,0.0006675828,0.00046984875],"genre_scores_gemma":[0.8525417,0.00006406321,0.14709567,0.000046841393,0.00014563602,0.00003180096,0.000048020986,0.000009462831,0.000016802533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826473,0.00038524333,0.0005203507,0.00037817404,0.00030683554,0.00014466343],"domain_scores_gemma":[0.9973973,0.0005391693,0.00037620627,0.00065858767,0.00096303195,0.000065690736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057061313,0.00019131956,0.0002774787,0.0001424975,0.00020051702,0.0006871693,0.0006177478,0.00008796843,0.00000523451],"category_scores_gemma":[0.00014175332,0.0001798469,0.000040075047,0.00026428406,0.00007680791,0.00037922343,0.0003448622,0.00016050905,0.0000019129106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018151086,0.0006899164,0.02464941,0.00023553836,0.00029281992,0.00001365108,0.004173492,0.0029879166,0.011952826,0.5307711,0.0010784236,0.4231368],"study_design_scores_gemma":[0.0003277621,0.00009953124,0.0005166903,0.00055048993,0.000007612224,0.00008117431,0.00004553973,0.9875118,0.001314513,0.009295623,0.00006693133,0.00018233071],"about_ca_topic_score_codex":0.00016991391,"about_ca_topic_score_gemma":0.000004761767,"teacher_disagreement_score":0.9845239,"about_ca_system_score_codex":0.000050902298,"about_ca_system_score_gemma":0.00013143406,"threshold_uncertainty_score":0.7333944},"labels":[],"label_agreement":null},{"id":"W3178329914","doi":"10.1145/3460319.3464824","title":"Log-based slicing for system-level test cases","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Computer science; Slicing; Regression testing; Program slicing; Test (biology); Test suite; Test Management Approach; Test case; Test harness; System under test; Code coverage; Reliability engineering; Test script; White-box testing; Software; Programming language; Software system; Machine learning; Regression analysis; Engineering; Software construction","score_opus":0.07594283484011646,"score_gpt":0.2931907843325324,"score_spread":0.2172479494924159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178329914","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011903272,0.000052152973,0.984472,0.00053681503,0.00016205302,0.00010634259,0.000005578717,0.012374995,0.0010997404],"genre_scores_gemma":[0.4864314,1.6346357e-7,0.5125787,0.00055748527,0.0000330283,0.000028222465,0.0000026062519,0.0000059975814,0.00036235384],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991806,0.000021467833,0.00015627786,0.00030798186,0.00012465644,0.0002089903],"domain_scores_gemma":[0.99678373,0.002387129,0.0000456079,0.0005168079,0.00021003911,0.000056688557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002270738,0.00009771113,0.00013180355,0.00005603578,0.00013435323,0.00014700406,0.00033524487,0.000042480966,0.0000042422703],"category_scores_gemma":[0.0016759578,0.0000863161,0.000060924875,0.00025267416,0.000014173713,0.00009476476,0.0000969538,0.000046304565,0.000009098814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015481513,0.00086724135,0.11075534,0.001415277,0.00006178752,0.0018946055,0.00047155216,0.00059414207,0.004978314,0.13869835,0.59299624,0.14725165],"study_design_scores_gemma":[0.00091297954,0.0005367296,0.0021681476,0.0007995555,0.000028657347,0.0011328078,0.000049171118,0.85724616,0.121531114,0.0098728,0.0048643546,0.00085749844],"about_ca_topic_score_codex":0.0001631689,"about_ca_topic_score_gemma":0.000022839193,"teacher_disagreement_score":0.856652,"about_ca_system_score_codex":0.00004519925,"about_ca_system_score_gemma":0.00015730316,"threshold_uncertainty_score":0.35198683},"labels":[],"label_agreement":null},{"id":"W3195549714","doi":"10.1145/3468264.3473123","title":"Slicer4J: a dynamic slicer for Java","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Java; Program slicing; Call graph; Debugging; Programming language; Slicing; Java annotation; Control flow graph; Real time Java; Multithreading; Thread (computing); Java concurrency; Speculative multithreading; Static analysis; Scala; Control flow; strictfp; Data-flow analysis; TRACE (psycholinguistics); Data flow diagram; Database","score_opus":0.016872314729178182,"score_gpt":0.2906664266073143,"score_spread":0.2737941118781361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195549714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008115103,0.000095566866,0.98084813,0.0032382892,0.0001754198,0.00008474912,0.0000011612917,0.010012851,0.004732292],"genre_scores_gemma":[0.11079895,0.0000048401444,0.8833415,0.0017880084,0.000028164808,0.000044167424,0.0000032431087,0.0000091469465,0.0039820205],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992817,0.00001781137,0.00009743354,0.0003015947,0.00010574305,0.00019568416],"domain_scores_gemma":[0.99895126,0.00030275906,0.000028165045,0.0005234647,0.00014376671,0.000050576564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015670943,0.00007969906,0.000095342024,0.00004178259,0.00008028034,0.00012711219,0.00039121925,0.000041906278,0.000018308876],"category_scores_gemma":[0.0002871167,0.00007205749,0.000063275715,0.00024130823,0.000011741909,0.00013868054,0.00017262812,0.000050339397,0.000029712579],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047614685,0.00015509967,0.0012255212,0.00006479367,0.000036250276,0.000054245178,0.00048334256,0.000016334723,0.0021835794,0.13978916,0.47058538,0.38540152],"study_design_scores_gemma":[0.00060841086,0.00016400243,0.0019179073,0.00007091242,0.000014443657,0.00021446028,0.000013838239,0.4853029,0.013590536,0.36844587,0.12903607,0.00062062434],"about_ca_topic_score_codex":0.000018533177,"about_ca_topic_score_gemma":0.000013066122,"teacher_disagreement_score":0.48528656,"about_ca_system_score_codex":0.000024213914,"about_ca_system_score_gemma":0.00008081448,"threshold_uncertainty_score":0.29384193},"labels":[],"label_agreement":null},{"id":"W3195614596","doi":"10.1145/3468264.3473930","title":"Quantifying no-fault-found test failures to prioritize inspection of flaky tests at Ericsson","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reliability engineering; Fault (geology); Test (biology); Fault coverage; Work (physics); Software; Computer science; Software testing; Engineering; Embedded system; Operating system; Electrical engineering; Geology; Mechanical engineering; Seismology","score_opus":0.039810804368580484,"score_gpt":0.308410739023143,"score_spread":0.2685999346545625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195614596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2608125,0.00027047488,0.69787234,0.0026260272,0.0011051366,0.0003759207,0.000006554378,0.027814992,0.0091160415],"genre_scores_gemma":[0.5825407,0.000005334114,0.41659126,0.0002475882,0.000055768058,0.0000089620935,0.0000016672428,0.000009893339,0.0005388283],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986294,0.0000397313,0.00028649461,0.00046692058,0.0003180891,0.00025935812],"domain_scores_gemma":[0.9978652,0.0007815461,0.000093990224,0.0007180376,0.00043894464,0.00010226017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025449792,0.00014797066,0.00020699804,0.0001281549,0.00016935763,0.00015014531,0.0004575533,0.00007163964,0.000019436702],"category_scores_gemma":[0.0030984273,0.00014298562,0.00006372945,0.0008452566,0.000033619068,0.00023631653,0.00054030033,0.00010530917,0.0001093605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025514186,0.00069882616,0.4312366,0.0003064131,0.000049566403,0.0002513678,0.0018328829,0.00016708569,0.27312765,0.018036768,0.21757433,0.05669304],"study_design_scores_gemma":[0.0011457191,0.0015880766,0.34701186,0.001132932,0.000041625855,0.00077181845,0.000081506965,0.06514236,0.5171142,0.023669463,0.04028363,0.0020168112],"about_ca_topic_score_codex":0.00037315476,"about_ca_topic_score_gemma":0.00031277534,"teacher_disagreement_score":0.3217282,"about_ca_system_score_codex":0.000105799336,"about_ca_system_score_gemma":0.00009640923,"threshold_uncertainty_score":0.58307844},"labels":[],"label_agreement":null},{"id":"W3196239222","doi":"10.1145/3468264.3468591","title":"A comprehensive study of deep learning compiler bugs","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Compiler; Computer science; Programming language; Boosting (machine learning); Deep learning; Context (archaeology); Code (set theory); Code generation; Parallel computing; Artificial intelligence; Operating system","score_opus":0.03173090442745961,"score_gpt":0.28398372578950304,"score_spread":0.2522528213620434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196239222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.330675,0.00014115851,0.6591977,0.00009361526,0.000110275156,0.00011171005,1.0964873e-7,0.0065272213,0.0031432242],"genre_scores_gemma":[0.8362119,0.0000018697843,0.16348784,0.00013965709,0.000010246356,0.00000532713,6.100282e-7,0.0000048348475,0.00013769124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910223,0.0001231756,0.00017738513,0.0002602906,0.00020275512,0.00013415245],"domain_scores_gemma":[0.99880207,0.0003762879,0.000064182976,0.00042760532,0.0002909381,0.000038942097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007800895,0.0000830554,0.000171662,0.00005736224,0.00007637463,0.0000512642,0.00034575237,0.00002566531,0.000023726356],"category_scores_gemma":[0.00013997185,0.00007575578,0.000034503697,0.0003802598,0.000019561918,0.00009115512,0.00038505648,0.00012727677,0.000011964207],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020620442,0.0043235715,0.44035718,0.00015776126,0.00026392218,0.00075277354,0.029674945,0.003232036,0.005186387,0.016740933,0.017563783,0.48172608],"study_design_scores_gemma":[0.003602179,0.003839559,0.37780145,0.00021667125,0.00006194551,0.00044725672,0.004212062,0.53534085,0.019956632,0.04398524,0.008983401,0.0015527882],"about_ca_topic_score_codex":0.00010154811,"about_ca_topic_score_gemma":0.000009364899,"teacher_disagreement_score":0.5321088,"about_ca_system_score_codex":0.000009669976,"about_ca_system_score_gemma":0.000022640692,"threshold_uncertainty_score":0.30892313},"labels":[],"label_agreement":null},{"id":"W3196351123","doi":"","title":"Leveraging Documentation to Test Deep Learning Library Functions","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Fuzz testing; Constraint (computer-aided design); Code (set theory); Artificial intelligence; Software bug; Machine learning; Data mining; Software; Programming language; Set (abstract data type)","score_opus":0.05306870260441219,"score_gpt":0.19408058708966935,"score_spread":0.14101188448525717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196351123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10529635,0.000051261442,0.8828303,0.00021276432,0.00039352424,0.00015696582,0.0000015162647,0.009276674,0.0017806343],"genre_scores_gemma":[0.93782437,0.000040212813,0.05966212,0.00027326352,0.000071076145,0.000002838132,0.000041647225,0.000024120085,0.0020603759],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983162,0.00012823495,0.00016589301,0.0010082796,0.00009342428,0.00028792807],"domain_scores_gemma":[0.99833447,0.00041633425,0.00014797098,0.0008240048,0.00010725778,0.0001699352],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015260217,0.00024432372,0.00021345838,0.00035483576,0.00029620258,0.0006281957,0.0010203173,0.00015439626,0.00006088403],"category_scores_gemma":[0.00025812484,0.00031574166,0.0001313383,0.00094757305,0.000024025585,0.00088099233,0.0024652549,0.00061848306,0.000085719366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016012411,0.00033190745,0.1693174,0.00015013295,0.00012664692,0.0011752472,0.0034302762,0.7804075,0.00012695524,0.007421239,0.0094085,0.028088216],"study_design_scores_gemma":[0.00037473167,0.00022899592,0.009485544,0.00069500844,0.00009595306,0.000032740656,0.000336779,0.93966234,0.00070159166,0.04500953,0.0020817253,0.0012950865],"about_ca_topic_score_codex":0.0001433494,"about_ca_topic_score_gemma":0.0000074359964,"teacher_disagreement_score":0.832528,"about_ca_system_score_codex":0.00013528246,"about_ca_system_score_gemma":0.00015683992,"threshold_uncertainty_score":0.9999295},"labels":[],"label_agreement":null},{"id":"W3196600806","doi":"","title":"Finding Counterexamples of Temporal Logic properties in Software Implementations via Greybox Fuzzing","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Computer science; Model checking; Liveness; Programming language; Counterexample; Temporal logic; Stateful firewall; Software; Property (philosophy); Linear temporal logic; Implementation; Theoretical computer science; Mathematics; Computer security","score_opus":0.1810027213860887,"score_gpt":0.23743890492983932,"score_spread":0.05643618354375063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196600806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36597714,0.00013539227,0.63204074,0.00002809894,0.00014744641,0.00018816935,0.000009074168,0.0014193399,0.00005461468],"genre_scores_gemma":[0.9290522,0.00003668571,0.07076201,0.00004016179,0.000017627379,0.0000032939693,0.000025810166,0.000014993576,0.000047275345],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826264,0.00015393761,0.00034668457,0.000802541,0.00011586464,0.00031833167],"domain_scores_gemma":[0.9983048,0.00021809869,0.00034744412,0.0008442097,0.00022066919,0.00006477535],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034723314,0.00026544268,0.00038572896,0.0004263476,0.00012489551,0.00013287968,0.0012178705,0.00017183757,0.000013720621],"category_scores_gemma":[0.00019623895,0.00029560065,0.00014496845,0.000662984,0.00010041087,0.00037923577,0.0018556089,0.00039702395,0.0000027547403],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029362936,0.00043563283,0.9182431,0.0011672094,0.00016443942,0.0009416061,0.0044773933,0.050317626,0.00036286013,0.017955957,0.0005796984,0.0053250897],"study_design_scores_gemma":[0.0017267049,0.0003765273,0.05921515,0.006108101,0.00018587774,0.00008036657,0.0011292784,0.5273611,0.004261152,0.39661667,0.00012757666,0.0028115143],"about_ca_topic_score_codex":0.0020339016,"about_ca_topic_score_gemma":0.00049192266,"teacher_disagreement_score":0.859028,"about_ca_system_score_codex":0.00021524633,"about_ca_system_score_gemma":0.00030663097,"threshold_uncertainty_score":0.99994963},"labels":[],"label_agreement":null},{"id":"W3197204261","doi":"10.5281/zenodo.5346846","title":"Mapping breakpoint types: an exploratory study","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Breakpoint; Computer science; Cartography; Computational biology; Geography; Biology; Genetics; Chromosomal translocation","score_opus":0.0637448935379894,"score_gpt":0.27887108849297804,"score_spread":0.21512619495498864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197204261","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049475825,0.00039059884,0.07824496,0.00044932906,0.0009732734,0.0017662923,0.8652984,0.047865234,0.0045171794],"genre_scores_gemma":[0.0014519447,0.000068335976,0.0052059027,0.00031888747,0.00031220095,2.411992e-7,0.9914571,0.0010886259,0.00009673109],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967538,0.00093987514,0.00035425427,0.00094196753,0.00060410093,0.0004059861],"domain_scores_gemma":[0.9965651,0.000058818285,0.00019738487,0.0021845666,0.0007682191,0.00022591196],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013665226,0.00027372208,0.00028891177,0.00047469177,0.0017332111,0.002360284,0.0039067566,0.00013370917,0.0014454586],"category_scores_gemma":[0.0011052494,0.0002968645,0.00006187631,0.0010005856,0.00008066865,0.00047768827,0.004683518,0.0005995745,0.0035647312],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035427227,0.00035779324,4.2790677e-7,0.000053235577,0.000032751173,0.00013087384,0.0011466694,0.000004466398,0.000014781163,0.00003827528,0.9739358,0.024281373],"study_design_scores_gemma":[0.00018211505,0.00041861486,0.000025398771,0.00010155205,0.000011737252,0.00015336082,0.00024674434,0.0002891136,0.00001346474,0.00028241734,0.99794596,0.00032952527],"about_ca_topic_score_codex":0.00005272928,"about_ca_topic_score_gemma":0.0000017865875,"teacher_disagreement_score":0.12615876,"about_ca_system_score_codex":0.00016734962,"about_ca_system_score_gemma":0.000019261146,"threshold_uncertainty_score":0.9999483},"labels":[],"label_agreement":null},{"id":"W3197206692","doi":"10.1109/tse.2021.3107680","title":"Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results in the Space Domain","year":2022,"lang":"en","type":"article","venue":"Open Repository and Bibliography (University of Luxembourg)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"H2020 European Research Council; Natural Sciences and Engineering Research Council of Canada; European Commission; European Space Agency","keywords":"Computer science; Scalability; Cyber-physical system; Domain (mathematical analysis); Space (punctuation); Domain analysis; Theoretical computer science; Distributed computing; Computer security; Programming language; Operating system; Software; Software development","score_opus":0.024208405854101948,"score_gpt":0.24324409481134837,"score_spread":0.21903568895724643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197206692","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5899094,0.0008200186,0.40065244,0.0020060511,0.0001606209,0.0015631597,0.000087141736,0.00059858523,0.0042026215],"genre_scores_gemma":[0.9779566,0.000026949654,0.0219047,0.000018938697,0.000010346763,0.000011539931,0.0000068371523,0.0000021331655,0.0000619315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99899673,0.00028047487,0.0001124477,0.0002917589,0.00018425724,0.00013432639],"domain_scores_gemma":[0.99902385,0.00042966966,0.00015852612,0.00028886696,0.000060471302,0.000038609494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012277726,0.000070547285,0.00017814491,0.003500212,0.0010345781,0.00023962768,0.00065800385,0.000024916888,3.511499e-7],"category_scores_gemma":[0.000003747204,0.00006811818,0.00009442107,0.011491545,0.00010223809,0.0004122947,0.0004646411,0.00009262421,5.0892385e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011007463,0.0022876444,0.60390466,0.00041418336,0.0018405095,0.00064653065,0.040025443,0.0072308825,0.0009949106,0.14061902,0.19545494,0.005480519],"study_design_scores_gemma":[0.0054738987,0.0026373288,0.649353,0.0002015716,0.0011549239,0.0005199954,0.02059735,0.21502915,0.00010838068,0.088502616,0.015139254,0.0012824904],"about_ca_topic_score_codex":0.002970182,"about_ca_topic_score_gemma":0.00002728236,"teacher_disagreement_score":0.38804725,"about_ca_system_score_codex":0.00000943023,"about_ca_system_score_gemma":0.000022799013,"threshold_uncertainty_score":0.7957243},"labels":[],"label_agreement":null},{"id":"W3201392238","doi":"10.1007/s10270-021-00918-6","title":"Automated generation of consistent models using qualitative abstractions and exploration strategies","year":2021,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Nemzeti Kutatási, Fejlesztési és Innovaciós Alap; Natural Sciences and Engineering Research Council of Canada; National Research, Development and Innovation Office; Innovációs és Technológiai Minisztérium; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal","keywords":"Computer science; Solver; Scalability; Key (lock); Context (archaeology); Graph; Consistency (knowledge bases); Theoretical computer science; Programming language; Artificial intelligence","score_opus":0.2661288694789344,"score_gpt":0.37461296274791683,"score_spread":0.10848409326898245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201392238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08039703,0.0009171417,0.9132063,0.000039149338,0.00025555937,0.00014132806,0.0000072322505,0.0050088717,0.000027427179],"genre_scores_gemma":[0.6743682,0.000017710036,0.32552728,0.000009816704,0.0000308124,0.000018257591,0.000012607344,0.0000099277495,0.000005391101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984381,0.00022838806,0.0005278391,0.00036891992,0.00026971538,0.00016700254],"domain_scores_gemma":[0.9984558,0.00023441404,0.00022011372,0.00035968106,0.000675266,0.000054730986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005419503,0.00014811405,0.00025094935,0.00012147332,0.0002110171,0.0003220037,0.00012692717,0.00009015137,4.0611602e-7],"category_scores_gemma":[0.00019745197,0.00015371952,0.00004691767,0.0002323859,0.000032398097,0.0015012051,0.000084841304,0.00009743377,6.1115475e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011944267,0.00002460237,0.000019599229,0.00009530459,0.000023192755,0.0000058853,0.006654504,0.9799371,0.0024012171,0.0101722125,0.00007805367,0.0005871737],"study_design_scores_gemma":[0.000095517345,0.000020811864,0.000001382191,0.0002203973,0.000015247401,0.000059146678,0.0023898236,0.96438414,0.0004012694,0.03225904,0.0000012001985,0.00015202082],"about_ca_topic_score_codex":0.0006580517,"about_ca_topic_score_gemma":0.000013737683,"teacher_disagreement_score":0.59397113,"about_ca_system_score_codex":0.000064929016,"about_ca_system_score_gemma":0.00031578954,"threshold_uncertainty_score":0.62685},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02022802077216418,"score_gpt":0.24044934009781616,"score_spread":0.22022131932565198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207636857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51943827,0.00024883018,0.47778985,0.00018138725,0.0000809946,0.00012013571,0.000005788275,0.0020752547,0.000059524788],"genre_scores_gemma":[0.64260423,0.00003921373,0.3572326,0.000055684584,0.000011148833,0.000010686182,0.000008495219,0.000005668596,0.000032248878],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987197,0.00009393516,0.00035433102,0.00049428793,0.00017758865,0.00016017054],"domain_scores_gemma":[0.99797016,0.0006885423,0.00019949874,0.000579562,0.00048739443,0.000074854215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007053636,0.00013362714,0.00017419337,0.000059036487,0.00024365824,0.000113113936,0.00017449155,0.00006722315,0.000002223478],"category_scores_gemma":[0.0035113932,0.00012826225,0.00002296494,0.00044751746,0.0001336393,0.00036737171,0.00019679168,0.00015816758,0.0000011128177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010294186,0.00008814393,0.4916123,0.00038675862,0.0000038230337,0.0000028275679,0.0006835577,0.00021086747,0.0015464773,0.00007788542,0.0000908866,0.5052862],"study_design_scores_gemma":[0.00034531287,0.00021780662,0.5767328,0.00021187906,0.000015017811,0.00009899086,0.000010020012,0.3983274,0.012983621,0.010556875,0.0001501467,0.00035008727],"about_ca_topic_score_codex":0.00013587145,"about_ca_topic_score_gemma":0.0000038548988,"teacher_disagreement_score":0.5049361,"about_ca_system_score_codex":0.000031143707,"about_ca_system_score_gemma":0.000121214776,"threshold_uncertainty_score":0.52303827},"labels":[],"label_agreement":null},{"id":"W3210529140","doi":"10.1109/tse.2022.3171295","title":"Fragment-Based Test Generation for Web Apps","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test (biology); Fragment (logic); Web application; Software engineering; World Wide Web; Programming language; Operating system; Database","score_opus":0.02069671311464428,"score_gpt":0.22918178894011498,"score_spread":0.2084850758254707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210529140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021078545,0.000035857276,0.98451185,0.00010485379,0.0009673039,0.00028447594,0.00005666354,0.011927365,0.000003746349],"genre_scores_gemma":[0.5577673,8.8620624e-7,0.44125667,0.00018911545,0.000045818848,0.0006641675,0.000006082714,0.00002569854,0.000044280227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889433,0.000019755676,0.00019318453,0.00036475464,0.00026665122,0.0002613314],"domain_scores_gemma":[0.9987232,0.00066484726,0.000043756536,0.00044764293,0.000051359493,0.00006919736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024698972,0.00017046345,0.00013096134,0.00026761222,0.00045077648,0.00008096191,0.0004173471,0.000043087857,0.000021530612],"category_scores_gemma":[0.00008934701,0.0002019623,0.00011228192,0.00042657956,0.000008635104,0.00014526414,0.0000046496043,0.00024336163,0.0000050370813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050663434,0.00018683152,0.00006045072,0.000031536132,0.0000150268515,0.000005624101,0.00008571456,0.961644,0.004111909,0.00010901402,0.0047398745,0.029004982],"study_design_scores_gemma":[0.00033060065,0.00026691685,0.000019530937,0.000019086428,0.000009984565,0.0000133036265,0.0000015494318,0.9780799,0.017379943,0.00007442651,0.0035495353,0.00025518396],"about_ca_topic_score_codex":0.0000073601605,"about_ca_topic_score_gemma":9.851653e-7,"teacher_disagreement_score":0.5556594,"about_ca_system_score_codex":0.00016827886,"about_ca_system_score_gemma":0.00008569514,"threshold_uncertainty_score":0.8235784},"labels":[],"label_agreement":null},{"id":"W3212114119","doi":"10.1109/models50736.2021.00018","title":"Efficient Replay-based Regression Testing for Distributed Reactive Systems in the Context of Model-driven Development","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regression testing; Computer science; Context (archaeology); Overhead (engineering); Timestamp; Distributed computing; Regression; Software; Data mining; Machine learning; Software system; Real-time computing; Programming language","score_opus":0.06536512290365601,"score_gpt":0.2960268156135097,"score_spread":0.23066169270985368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212114119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051236942,0.000049203372,0.94705594,0.00021463011,0.00005411997,0.00031079687,0.0000073029964,0.00094332336,0.0001277174],"genre_scores_gemma":[0.6287446,6.4411694e-8,0.37107617,0.00008179528,0.0000040693612,0.000072518575,0.00000969259,0.0000035154346,0.0000076080896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885267,0.000092456015,0.0003214583,0.00030762012,0.0002457923,0.00018002847],"domain_scores_gemma":[0.99728847,0.0016549574,0.00016584281,0.00047625395,0.00038704943,0.000027456337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006974555,0.00010585263,0.00017586316,0.000059119935,0.00009983232,0.00005709805,0.00041585168,0.000046668094,1.6905048e-7],"category_scores_gemma":[0.0013550805,0.00006787361,0.000034902478,0.00045767904,0.00002250014,0.000032839907,0.00010083367,0.000083440755,4.3379936e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015568247,0.0022356848,0.03335794,0.00088232034,0.00007637845,0.00019976796,0.01784869,0.72497237,0.020298872,0.047040556,0.024693377,0.12823837],"study_design_scores_gemma":[0.00025236575,0.000044592478,0.00054092414,0.00043579075,0.0000025613592,0.00001062966,0.00009586389,0.98267967,0.015313092,0.00045749595,0.00007063081,0.00009638457],"about_ca_topic_score_codex":0.00008209087,"about_ca_topic_score_gemma":0.0000066937987,"teacher_disagreement_score":0.5775076,"about_ca_system_score_codex":0.00008207422,"about_ca_system_score_gemma":0.00033687666,"threshold_uncertainty_score":0.27678055},"labels":[],"label_agreement":null},{"id":"W3212458632","doi":"10.5281/zenodo.3871016","title":"deferred correction software","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Software; Programming language","score_opus":0.05506760616288969,"score_gpt":0.24727118751585697,"score_spread":0.19220358135296728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212458632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007878204,0.000037651098,0.9477887,0.0016606221,0.00018721652,0.0001807049,0.000011896708,0.03489574,0.014449629],"genre_scores_gemma":[0.9190514,0.00002267058,0.07693188,0.0019213349,0.00027930032,6.948644e-8,0.00033073587,0.0011283868,0.00033424486],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877393,0.00016372104,0.0001544186,0.00039760448,0.00027083227,0.00023947719],"domain_scores_gemma":[0.99898446,0.00004758614,0.00006853386,0.0004000904,0.0003202767,0.00017903915],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003025197,0.00010263705,0.00009794878,0.00010008486,0.0012269645,0.0008301102,0.0014007102,0.000046355988,0.00064415915],"category_scores_gemma":[0.0023791497,0.0001106035,0.000039931718,0.000683997,0.00005201154,0.00032195364,0.0012121475,0.00021114579,0.0033342415],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009042033,0.00002880679,0.000012415642,0.000014321322,0.0000071884465,0.000009481573,0.0009135317,0.000038329526,0.00025501964,0.0010317293,0.6746354,0.32304475],"study_design_scores_gemma":[0.0002313419,0.0003335451,0.00045830788,0.000028255909,0.0000049402506,0.00014707663,0.000022152562,0.02177615,0.00072543474,0.0021060687,0.97394484,0.00022187414],"about_ca_topic_score_codex":0.000008573161,"about_ca_topic_score_gemma":2.9061452e-8,"teacher_disagreement_score":0.91826355,"about_ca_system_score_codex":0.000059327118,"about_ca_system_score_gemma":0.0000034471695,"threshold_uncertainty_score":0.99744177},"labels":[],"label_agreement":null},{"id":"W3215130818","doi":"10.1109/icsme52107.2021.00028","title":"Interactive Patch Filtering as Debugging Aid","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Correctness; Process (computing); Plug-in; Software engineering; Recall; Software bug; Precision and recall; Eclipse; Programming language; Human–computer interaction; Machine learning; Software","score_opus":0.016013490395001127,"score_gpt":0.27598801298719805,"score_spread":0.25997452259219694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215130818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008881267,0.000044711385,0.9523499,0.0009366558,0.0002631766,0.00003604716,3.176976e-7,0.013882258,0.023605658],"genre_scores_gemma":[0.5988984,0.0000029440407,0.39911518,0.0011299731,0.000033879936,0.000015137987,0.0000010493552,0.0000072632724,0.0007961934],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991082,0.00004344242,0.00013534068,0.00034475685,0.00015211543,0.00021612082],"domain_scores_gemma":[0.9989548,0.00031768502,0.000039846247,0.0005086844,0.00011277789,0.00006623136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013324332,0.00010410872,0.000111295725,0.000058569618,0.00009348578,0.00022929972,0.00041889676,0.00003454273,0.000110545785],"category_scores_gemma":[0.00045294213,0.00009824762,0.000051036794,0.00028571172,0.000013183744,0.00038376224,0.0005072667,0.00013049513,0.000114347815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014538306,0.00029945103,0.021258004,0.00006706869,0.00011733973,0.001976366,0.0044092913,0.00006572438,0.008562318,0.07767222,0.11320048,0.7723572],"study_design_scores_gemma":[0.00046034023,0.00018084428,0.0024640327,0.00040963254,0.000013359075,0.001379022,0.000076868855,0.13466148,0.40563515,0.4356337,0.01816401,0.000921591],"about_ca_topic_score_codex":0.00020422055,"about_ca_topic_score_gemma":0.000009445176,"teacher_disagreement_score":0.7714356,"about_ca_system_score_codex":0.000037386173,"about_ca_system_score_gemma":0.000086843225,"threshold_uncertainty_score":0.4006422},"labels":[],"label_agreement":null},{"id":"W3216180498","doi":"10.1109/icsme52107.2021.00026","title":"Mining Historical Test Failures to Dynamically Batch Tests to Save CI Resources","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Weighting; Metric (unit); Batch processing; Test case; Constant (computer programming); Test (biology); Machine learning; Programming language; Operations management; Engineering","score_opus":0.017222032460242877,"score_gpt":0.25771211069511063,"score_spread":0.24049007823486776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216180498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03617683,0.0000787919,0.9060878,0.035900958,0.00031889626,0.00016833634,0.0000021072533,0.015047539,0.006218697],"genre_scores_gemma":[0.28257605,4.906063e-7,0.7113521,0.0030810013,0.00008117026,0.00002244545,9.2396556e-7,0.000013962391,0.0028718517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982184,0.000052491858,0.0002735976,0.00067328743,0.0003869746,0.00039523072],"domain_scores_gemma":[0.99712425,0.0014361414,0.000040931805,0.00083292974,0.00023093606,0.00033481224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027060776,0.00018001387,0.00022446596,0.00016154307,0.00013931865,0.0002841689,0.000914292,0.00007866266,0.000026631526],"category_scores_gemma":[0.0048750564,0.00016631266,0.00006211333,0.0009823113,0.000014005806,0.00010930791,0.0008084114,0.0001319596,0.00012054766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061093274,0.00024346617,0.04539261,0.000021211175,0.000013048067,0.00038172366,0.0025685877,0.00008087666,0.00493711,0.0029209938,0.83187944,0.11155485],"study_design_scores_gemma":[0.0006076609,0.0020696789,0.07470988,0.00071883993,0.000033549786,0.000696435,0.00012605559,0.045508835,0.013480033,0.026823387,0.83234084,0.0028848073],"about_ca_topic_score_codex":0.00034072524,"about_ca_topic_score_gemma":0.00016902923,"teacher_disagreement_score":0.24639922,"about_ca_system_score_codex":0.00028128555,"about_ca_system_score_gemma":0.00009829146,"threshold_uncertainty_score":0.67820334},"labels":[],"label_agreement":null},{"id":"W3216603549","doi":"10.1109/icsme52107.2021.00023","title":"Mutation Analysis for Assessing End-to-End Web Tests","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Mutation testing; Source code; Web testing; Code coverage; Test case; Web application; Programmer; Web server; Suite; Static analysis; Web page; World Wide Web; Mutation; Software engineering; The Internet; Operating system; Web application security; Programming language; Web development; Software; Machine learning; Regression analysis","score_opus":0.0408933321761317,"score_gpt":0.3334186079602007,"score_spread":0.29252527578406895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216603549","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012857777,0.000026476328,0.97935677,0.000987696,0.00008394387,0.00006710432,0.0000016443415,0.005102254,0.0015163397],"genre_scores_gemma":[0.49667484,2.841576e-7,0.5026399,0.0004300317,0.000018009569,0.000014925407,0.000006101954,0.0000033232122,0.00021262748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911535,0.000035630314,0.00015239947,0.0003488592,0.00017249184,0.00017530024],"domain_scores_gemma":[0.99853456,0.00069493556,0.000046840174,0.00042119328,0.00023449697,0.000067999565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031304732,0.000080952144,0.0001379295,0.00021812963,0.00011517475,0.00040231406,0.00026760195,0.00003505314,0.00002381555],"category_scores_gemma":[0.0008314044,0.00007640587,0.000093682065,0.0015292768,0.00000907425,0.00027501615,0.0001163536,0.00004286794,0.000009609202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036207248,0.00024266001,0.10661271,0.00005631515,0.00037540402,0.00016888125,0.0009966979,0.0022337888,0.007310654,0.02066144,0.051066335,0.8102715],"study_design_scores_gemma":[0.00025311083,0.00008472812,0.06315935,0.00004914102,0.00016939398,0.000055430926,0.00002483958,0.85431683,0.023993349,0.054455176,0.0029589261,0.00047970243],"about_ca_topic_score_codex":0.000041257896,"about_ca_topic_score_gemma":0.000046097066,"teacher_disagreement_score":0.8520831,"about_ca_system_score_codex":0.000031977743,"about_ca_system_score_gemma":0.00012943974,"threshold_uncertainty_score":0.3879524},"labels":[],"label_agreement":null},{"id":"W329547450","doi":"10.1007/978-3-319-00804-2_3","title":"Observations on Software Testing and Its Optimization","year":2013,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Software testing; Software reliability testing; Computer science; Regression testing; System integration testing; Test strategy; Software; Coding (social sciences); Software construction; Non-regression testing; Software engineering; Software performance testing; Software development; Programming language; Mathematics","score_opus":0.24303127799320062,"score_gpt":0.35238518618001113,"score_spread":0.10935390818681051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W329547450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015862941,0.00217582,0.9835262,0.0003580436,0.00037275138,0.00040262353,0.000009345117,0.0024909517,0.010648456],"genre_scores_gemma":[0.0044620787,0.0003336353,0.98736376,0.0005460459,0.00008415185,0.00006806156,0.000014217413,0.000032477365,0.0070955763],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829125,0.000026147793,0.0004861957,0.0006242556,0.00036925945,0.00020290239],"domain_scores_gemma":[0.99451303,0.004068497,0.0002554275,0.00027080698,0.00084031676,0.000051929692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024179298,0.0003234089,0.000325446,0.0003044594,0.00021631867,0.00010121955,0.0004970832,0.0001359221,0.000014341471],"category_scores_gemma":[0.0027693938,0.0003245654,0.000040158215,0.00019848706,0.00014004271,0.0002444792,0.00047724904,0.00034073807,0.00005546835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014631336,0.000017928045,0.00012607715,0.00008141276,0.00003699986,0.000017680533,0.0003300133,0.5926911,7.35257e-8,0.37038654,0.002795009,0.033515695],"study_design_scores_gemma":[0.00002118539,0.00007723652,0.00009939781,0.00077548024,0.000004762678,0.0000146029515,0.0000034094373,0.4671664,0.0000028710588,0.5314803,0.00011801673,0.00023633399],"about_ca_topic_score_codex":0.0000094679635,"about_ca_topic_score_gemma":0.000001815665,"teacher_disagreement_score":0.16109376,"about_ca_system_score_codex":0.00014131509,"about_ca_system_score_gemma":0.000087453605,"threshold_uncertainty_score":0.99992067},"labels":[],"label_agreement":null},{"id":"W33337023","doi":"10.1007/978-0-387-35497-2_25","title":"Test Generation for CEFSM Combining Specification and Fault Coverage","year":2002,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"European Commission; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Nondeterministic algorithm; Computer science; Fault coverage; Reliability engineering; Code coverage; Cover (algebra); Fault (geology); Algorithm; Programming language; Engineering","score_opus":0.023605522039051273,"score_gpt":0.2605515167815273,"score_spread":0.23694599474247605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W33337023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000096577714,0.016991692,0.8643093,0.003388643,0.00021180256,0.0013370445,0.000035409594,0.005547579,0.10808192],"genre_scores_gemma":[0.24963953,0.15327474,0.58594,0.0014077444,0.00008256509,0.0008743281,0.0007018614,0.0000668975,0.008012316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988865,0.00001558189,0.00058609265,0.0002381183,0.00012675994,0.0001469422],"domain_scores_gemma":[0.99792,0.0004117736,0.00053586066,0.00090107886,0.00020028335,0.00003103119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030172127,0.00020911283,0.00024533973,0.0006639168,0.00023099377,0.00016440672,0.00061482406,0.00037082811,0.0000045442785],"category_scores_gemma":[0.0003581968,0.00023115815,0.000024888084,0.00013772669,0.00017894003,0.0015247958,0.0002825596,0.0003516317,0.000009531065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001539048,0.000008490953,0.00009079077,0.000031870797,0.0000023274108,1.2801759e-7,0.00018652665,0.000011185118,0.0000043812483,0.5539142,0.0006504001,0.44509816],"study_design_scores_gemma":[0.0004369659,0.00012430774,0.00003173842,0.0001965304,0.0000060601624,0.000032466243,0.000014757384,0.051288377,0.00009848456,0.5478621,0.39959607,0.00031212257],"about_ca_topic_score_codex":0.0000032448263,"about_ca_topic_score_gemma":0.000007826526,"teacher_disagreement_score":0.44478604,"about_ca_system_score_codex":0.00007415005,"about_ca_system_score_gemma":0.000022013404,"threshold_uncertainty_score":0.9426356},"labels":[],"label_agreement":null},{"id":"W35884834","doi":"10.22215/etd/2009-10147","title":"An open framework for the specification and execution of a testable requirements model","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","score_opus":0.09014579382382956,"score_gpt":0.38785753413183016,"score_spread":0.2977117403080006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W35884834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00058447075,0.00013417285,0.9956696,0.00016189455,0.00008033141,0.00075459725,0.0000035352439,0.0009843789,0.0016270269],"genre_scores_gemma":[0.123695664,0.000052525196,0.87522286,0.000112717615,0.000024948487,0.00012076783,0.00007598909,0.000011073572,0.0006834342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991206,0.000019863326,0.00023027837,0.00034079046,0.00016772388,0.00012077658],"domain_scores_gemma":[0.99851495,0.0002819539,0.00024606255,0.0007292035,0.0001973536,0.000030492745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046548157,0.00012397722,0.00015698573,0.00006607337,0.00015448514,0.00028369974,0.0012491654,0.00013972557,0.0000012751204],"category_scores_gemma":[0.00023216508,0.00009138975,0.000022837874,0.0001584919,0.000014090745,0.00041462018,0.000055197375,0.000095351155,3.6987691e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008311915,0.0002737892,0.00013267239,0.00013339802,0.000027415495,3.0738934e-7,0.0019762442,0.0003189083,0.0012853425,0.5284051,0.02401845,0.4433453],"study_design_scores_gemma":[0.00006569689,0.00016970739,0.0014818059,0.00016297783,0.000015402948,6.481771e-7,0.000024918858,0.30498526,0.0020296962,0.69087315,0.00007182442,0.000118920616],"about_ca_topic_score_codex":0.00014133476,"about_ca_topic_score_gemma":0.000020557909,"teacher_disagreement_score":0.44322637,"about_ca_system_score_codex":0.000022293798,"about_ca_system_score_gemma":0.00008484917,"threshold_uncertainty_score":0.37267658},"labels":[],"label_agreement":null},{"id":"W37109407","doi":"10.3390/life13040878","title":"An Ontology-based Software Test Generation Framework.","year":2010,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; U.S. Department of Veterans Affairs","keywords":"Computer science; Test Management Approach; Software engineering; Test harness; Test case; Test (biology); Keyword-driven testing; Code coverage; Test suite; Manual testing; System under test; Reliability engineering; Software; Software development; Software construction; Programming language; Machine learning; Engineering","score_opus":0.010886739021814421,"score_gpt":0.24339811035775683,"score_spread":0.2325113713359424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37109407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0382163,0.00042726804,0.9371327,0.00004501202,0.00149184,0.00013894173,0.000005697942,0.022534084,0.000008132521],"genre_scores_gemma":[0.43296134,0.0000032772834,0.5665233,0.00003618866,0.0003597914,0.000047560457,0.0000097883185,0.0000477242,0.000011048363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825114,0.000018500925,0.00031241798,0.0006756968,0.00018193561,0.0005602895],"domain_scores_gemma":[0.9972929,0.001230182,0.00005930501,0.0009416252,0.0001455111,0.00033051913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000428642,0.00042242618,0.00031728434,0.00037963278,0.00017986547,0.00028204365,0.00070193387,0.00035728634,0.000006610702],"category_scores_gemma":[0.004794539,0.00045329932,0.000078329474,0.000490129,0.000036049067,0.0004502308,0.00013542258,0.0008681339,0.0000149473335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016153232,0.001568145,0.16533518,0.0015683604,0.00020406571,0.00029048813,0.0054123336,0.13507588,0.10915847,0.04295636,0.007343447,0.5310711],"study_design_scores_gemma":[0.00021211317,0.00015179113,0.0045662154,0.00015169189,0.000013373722,0.00007479777,0.0000010635777,0.9856149,0.0057147196,0.0004807113,0.002325157,0.000693472],"about_ca_topic_score_codex":0.000012835467,"about_ca_topic_score_gemma":0.000009385467,"teacher_disagreement_score":0.850539,"about_ca_system_score_codex":0.000045250523,"about_ca_system_score_gemma":0.00010213435,"threshold_uncertainty_score":0.99979186},"labels":[],"label_agreement":null},{"id":"W39437227","doi":"","title":"Model-Based Testing of Distributed Systems","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Correctness; Computer science; Reliability (semiconductor); Reliability engineering; Quality (philosophy); Engineering; Algorithm","score_opus":0.07862109517659838,"score_gpt":0.26056696555696235,"score_spread":0.18194587038036397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W39437227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01419403,0.000030600128,0.97568166,0.000039917883,0.000045409746,0.00006206525,0.0000028705633,0.008777523,0.0011659127],"genre_scores_gemma":[0.5934884,1.709656e-7,0.40644035,0.000030092098,0.000005647555,0.000005090966,0.0000011154688,0.0000028423353,0.000026275504],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931145,0.000020990412,0.00018343485,0.00017126063,0.00017163232,0.00014121218],"domain_scores_gemma":[0.99894506,0.00034037916,0.00007899605,0.00042523496,0.00016565264,0.000044691114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016047516,0.00007455575,0.00012394041,0.000059892853,0.00007554297,0.000019322024,0.0004356435,0.0000334875,4.849499e-7],"category_scores_gemma":[0.00043190757,0.00006324271,0.000027639306,0.00038699957,0.000040960498,0.000092353315,0.00007308049,0.000049946837,0.0000029102234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010264313,0.00049396383,0.30720866,0.0002665605,0.000028284774,0.00012973907,0.00042300907,0.52937,0.0028246897,0.03512294,0.1108333,0.013288601],"study_design_scores_gemma":[0.00007061677,0.000038725662,0.00084972277,0.000039335144,0.0000011185524,0.000026347518,3.726106e-7,0.99484766,0.0014769163,0.0025468501,0.00002206255,0.00008026082],"about_ca_topic_score_codex":0.00015676003,"about_ca_topic_score_gemma":2.4578102e-7,"teacher_disagreement_score":0.5792944,"about_ca_system_score_codex":0.000017274911,"about_ca_system_score_gemma":0.000105109546,"threshold_uncertainty_score":0.2578963},"labels":[],"label_agreement":null},{"id":"W40826477","doi":"10.1007/978-0-387-35516-0_2","title":"Structural Coverage for Lotos","year":2000,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.010793855260251348,"score_gpt":0.2619111293880397,"score_spread":0.25111727412778834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W40826477","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012112764,0.023449682,0.47149602,0.0028685834,0.00028960814,0.0019310568,0.00005954885,0.014802227,0.48498213],"genre_scores_gemma":[0.15299122,0.09623477,0.73427254,0.0031587926,0.00005720444,0.0010925331,0.00062332273,0.00008042493,0.011489188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990845,0.000011040949,0.00047995805,0.00016606173,0.00010743073,0.00015102552],"domain_scores_gemma":[0.998307,0.0002099608,0.00033771194,0.0010128304,0.000108185974,0.00002433685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015980995,0.0001886741,0.00023372659,0.0006188254,0.00014911355,0.0000932447,0.001094915,0.00034569568,0.000012508577],"category_scores_gemma":[0.000096032374,0.00019508251,0.00003566782,0.00011230488,0.00016794784,0.001377461,0.0002813037,0.00035550588,0.000015240508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003685163,0.0000012549574,0.000018967774,0.00001754284,0.0000017903598,1.1283321e-7,0.000067645386,0.000014927558,7.229955e-8,0.5047217,0.00018602249,0.49496627],"study_design_scores_gemma":[0.00016860232,0.00004081278,0.000008017388,0.00009707991,0.0000018472524,0.00001690495,0.0000028678585,0.003360004,0.000012846923,0.63119596,0.36495063,0.00014442325],"about_ca_topic_score_codex":0.000004819871,"about_ca_topic_score_gemma":0.000009321662,"teacher_disagreement_score":0.49482185,"about_ca_system_score_codex":0.000058908303,"about_ca_system_score_gemma":0.000041318137,"threshold_uncertainty_score":0.7955234},"labels":[],"label_agreement":null},{"id":"W4104734","doi":"10.1007/978-3-642-39742-4_26","title":"A Multi-objective Genetic Algorithm for Generating Test Suites from Extended Finite State Machines","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Computer science; Test suite; Finite-state machine; Genetic algorithm; Similarity (geometry); Algorithm; Set (abstract data type); State (computer science); Test (biology); Suite; Test case; Artificial intelligence; Machine learning; Programming language","score_opus":0.020592682319030896,"score_gpt":0.2616508539926293,"score_spread":0.2410581716735984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4104734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008716168,0.0008752508,0.99398875,0.00011580235,0.0010159225,0.0009331975,0.000094061994,0.0028434787,0.00004634968],"genre_scores_gemma":[0.00632364,0.00002767613,0.9915872,0.0010143523,0.00054703216,0.0001137266,0.000020406354,0.00007274708,0.00029318134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955425,0.000048295922,0.00069355656,0.0021509717,0.00070514,0.0008594845],"domain_scores_gemma":[0.98871243,0.008568959,0.0004740979,0.0014523894,0.000587172,0.00020492257],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006093111,0.0007848838,0.0006989356,0.00071584806,0.00045335232,0.0011292059,0.003025545,0.00030357507,0.000013284328],"category_scores_gemma":[0.0018315183,0.0007027862,0.00018558998,0.00047073496,0.00049065985,0.0004942969,0.0012832469,0.00068329956,0.000030185667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001191534,0.000040842704,0.00020919001,0.000016482523,0.000011396902,0.000048453006,0.00060726126,0.005511181,0.00019025498,0.000037307414,0.000084404455,0.993242],"study_design_scores_gemma":[0.0002743693,0.00022850462,0.0006097455,0.00032283162,0.00000963973,0.000036812584,4.043368e-8,0.8111836,0.000931026,0.18562578,0.00007925001,0.00069842604],"about_ca_topic_score_codex":0.00043626444,"about_ca_topic_score_gemma":0.00007198584,"teacher_disagreement_score":0.99254364,"about_ca_system_score_codex":0.00023247108,"about_ca_system_score_gemma":0.00045831813,"threshold_uncertainty_score":0.99990773},"labels":[],"label_agreement":null},{"id":"W413907436","doi":"10.1016/j.scico.2014.09.005","title":"Crawl-based analysis of web applications: Prospects and challenges","year":2014,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sketch; Web crawler; Computer science; Crawling; World Wide Web; Web application; Web testing; Field (mathematics); Data science; Web service; Web application security; Web development","score_opus":0.022321936001959024,"score_gpt":0.26792613935501,"score_spread":0.24560420335305094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W413907436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011074082,0.0003893869,0.9866874,0.00025496705,0.000040138304,0.00021508512,4.1264678e-7,0.0012384319,0.000100068064],"genre_scores_gemma":[0.522514,0.000008022269,0.47742313,0.000018262308,0.000011320764,0.00002225302,3.2113414e-7,0.0000021440994,5.4116776e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859405,0.00003576947,0.00025760685,0.00046303772,0.00041517944,0.00023435763],"domain_scores_gemma":[0.99848056,0.000260964,0.00022201966,0.0006609803,0.0002930554,0.00008241238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013811117,0.00010455299,0.0002625971,0.0006931104,0.000119807824,0.00011623021,0.000996332,0.000030672825,3.4597588e-7],"category_scores_gemma":[0.00009088942,0.000093378156,0.000056142675,0.0024082947,0.000517823,0.0002517718,0.00027814115,0.000054621127,4.5041128e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.069662e-7,0.00007444132,0.0044546984,0.00007983835,0.000019212868,2.2204057e-7,0.00021589897,0.00024282698,0.0002431247,0.028979337,0.000008500266,0.9656811],"study_design_scores_gemma":[0.00012647502,0.00026002858,0.012341147,0.00006962482,0.000044383,0.000002347116,0.0000035294763,0.97421837,0.0024850366,0.009225173,0.001061964,0.00016191414],"about_ca_topic_score_codex":0.0000126740915,"about_ca_topic_score_gemma":0.0000025585537,"teacher_disagreement_score":0.97397554,"about_ca_system_score_codex":0.000013789218,"about_ca_system_score_gemma":0.00010083039,"threshold_uncertainty_score":0.38078508},"labels":[],"label_agreement":null},{"id":"W41990731","doi":"","title":"Knowledge-based Software Test Generation.","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Test Management Approach; Computer science; Test harness; Keyword-driven testing; Test (biology); Test script; Software engineering; Manual testing; Test case; Unit testing; System under test; Ontology; White-box testing; Reliability engineering; Software; Software construction; Software development; Programming language; Machine learning; Engineering","score_opus":0.03646622812087495,"score_gpt":0.2826508291638791,"score_spread":0.24618460104300416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W41990731","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034428874,0.00009964121,0.9720407,0.0011219111,0.00010152013,0.00006375091,4.1087682e-7,0.022630628,0.003597125],"genre_scores_gemma":[0.3529005,5.932487e-7,0.64483327,0.0017397645,0.000081310034,0.0000053661893,0.0000020171246,0.0000035436287,0.00043364067],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992893,0.000020201593,0.00012820883,0.00026770655,0.000118108364,0.00017648676],"domain_scores_gemma":[0.99897903,0.00028830065,0.000030910003,0.0005211429,0.00011236106,0.000068266316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001646267,0.00010170854,0.00008509558,0.00009069717,0.00012190905,0.00015213298,0.00051625044,0.000045646342,0.00001445306],"category_scores_gemma":[0.0006167516,0.00008715375,0.000039318355,0.0003248076,0.000014880238,0.00017126818,0.000040425006,0.00006795144,0.00009749597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.6822194e-7,0.00028882074,0.004985915,0.0000044889844,0.0000018899419,0.000011357623,0.00009696018,0.0000863014,0.00069346564,0.010101644,0.50654954,0.47717902],"study_design_scores_gemma":[0.0005126389,0.000778565,0.011621683,0.00006342681,0.0000070619767,0.00003759917,7.2735907e-7,0.84367245,0.03466742,0.093559094,0.014299405,0.0007799383],"about_ca_topic_score_codex":0.000007469279,"about_ca_topic_score_gemma":0.0000023352138,"teacher_disagreement_score":0.84358615,"about_ca_system_score_codex":0.000026594964,"about_ca_system_score_gemma":0.00009219813,"threshold_uncertainty_score":0.35540265},"labels":[],"label_agreement":null},{"id":"W4200053401","doi":"10.1109/models-c53483.2021.00095","title":"MRegTest: A Replay-Based Regression Testing Tool for Distributed UML-RT Models","year":2021,"lang":"en","type":"article","venue":"2021 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regression testing; Semantics (computer science); Model-based testing; Process (computing); Set (abstract data type); Unified Modeling Language; Timestamp; Regression analysis; Data mining; Test case; Programming language; Machine learning; Real-time computing; Software; Software system","score_opus":0.11174798614387775,"score_gpt":0.32266939813125173,"score_spread":0.21092141198737396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200053401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017075447,0.00020847547,0.979092,0.00042195982,0.0005630722,0.00031992033,0.00016719023,0.0017884686,0.00036346918],"genre_scores_gemma":[0.7815547,0.000021095793,0.21778549,0.000069667185,0.00013143718,0.0001448369,0.0001494884,0.00003382254,0.00010945564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757695,0.00007028061,0.0005281769,0.00084786664,0.0005750066,0.00040169669],"domain_scores_gemma":[0.99721825,0.00060737354,0.00021852239,0.0009015104,0.0009069513,0.00014737165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003904018,0.00038963225,0.00044984775,0.00021852576,0.00018046617,0.0006056244,0.0009586842,0.00016437836,0.0000035522442],"category_scores_gemma":[0.00052379805,0.0003688384,0.00012545862,0.00026037832,0.000029488896,0.0005828793,0.0002845924,0.00029856781,0.0000024939486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012504125,0.000067043664,0.00005638913,0.00008860609,0.000034173656,0.000040043837,0.00020441395,0.9024786,0.0023373968,0.091783814,0.0008272647,0.0020697445],"study_design_scores_gemma":[0.0004964363,0.000078917976,0.000025276902,0.0013360361,0.000013447096,0.00006554939,0.000029584688,0.9793513,0.0005070469,0.017636836,0.000035682915,0.00042391932],"about_ca_topic_score_codex":0.00007434615,"about_ca_topic_score_gemma":0.0000029139137,"teacher_disagreement_score":0.7644793,"about_ca_system_score_codex":0.00014549308,"about_ca_system_score_gemma":0.00021525005,"threshold_uncertainty_score":0.9998764},"labels":[],"label_agreement":null},{"id":"W4200439617","doi":"10.18280/ijsse.110606","title":"Qualitative Analysis of State/Event Fault Trees Based on Interface Automata","year":2021,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China","keywords":"Automaton; Computer science; Interface (matter); Fault tree analysis; Semantics (computer science); Event (particle physics); Theoretical computer science; Tree (set theory); Set (abstract data type); Process (computing); State (computer science); Finite-state machine; Algorithm; Programming language; Mathematics; Reliability engineering; Engineering","score_opus":0.013979296515769313,"score_gpt":0.3259175296679685,"score_spread":0.3119382331521992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200439617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058656808,0.00016198133,0.9397525,0.00095646584,0.00022733929,0.000016288266,0.000021667245,0.00016386344,0.000043078482],"genre_scores_gemma":[0.9536214,0.000059525013,0.04622562,0.000060649385,0.000019590143,4.1219727e-7,0.0000033243355,0.0000037620916,0.0000057009447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893904,0.000058477053,0.00040297513,0.00011916126,0.00039975758,0.0000805783],"domain_scores_gemma":[0.9984991,0.0006663211,0.00021352938,0.00013600831,0.00043314256,0.00005189463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005674305,0.000087006905,0.00023235146,0.00038797525,0.000017069868,0.000052558946,0.00037284254,0.00002796475,0.0000060998404],"category_scores_gemma":[0.000531339,0.00008067037,0.0001283164,0.00033594744,0.000017056977,0.00018042733,0.00009137514,0.00015305079,2.3639241e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018526109,0.00040272047,0.00094781443,0.00005362145,0.0021483458,0.00027968752,0.024780678,0.9342878,0.0013362432,0.009693387,0.00035265955,0.025531784],"study_design_scores_gemma":[0.000314256,0.00010583763,0.0030462923,0.00024193914,0.00004414091,0.000033267017,0.00007603477,0.98906773,0.004377258,0.0022411158,0.00035477622,0.000097355514],"about_ca_topic_score_codex":0.000014474363,"about_ca_topic_score_gemma":0.0000050660788,"teacher_disagreement_score":0.89496464,"about_ca_system_score_codex":0.000055585107,"about_ca_system_score_gemma":0.00005349318,"threshold_uncertainty_score":0.3289642},"labels":[],"label_agreement":null},{"id":"W4205529760","doi":"10.1145/3502297","title":"Automated, Cost-effective, and Update-driven App Testing","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Centre National de la Recherche Scientifique; European Commission","keywords":"Computer science; Dependability; Oracle; Code coverage; Random testing; Android (operating system); Model-based testing; Test case; Cyclomatic complexity; Automation; Source code; Code (set theory); Test suite; Random oracle; Set (abstract data type); Software engineering; Distributed computing; Programming language; Machine learning; Software; Operating system; Encryption","score_opus":0.07249387697246641,"score_gpt":0.3145700562029212,"score_spread":0.24207617923045482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205529760","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072882213,0.00020533559,0.9714318,0.00017480724,0.00037602562,0.0003398768,0.00001107915,0.020168627,0.000004215806],"genre_scores_gemma":[0.13223872,0.000017789174,0.8669199,0.00022624858,0.000014770749,0.0005412533,0.000002128078,0.000023875284,0.000015324778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858165,0.00031597016,0.00018080814,0.00048065453,0.00013519713,0.00030570023],"domain_scores_gemma":[0.9937447,0.0055480124,0.00005342846,0.0005027465,0.00004240261,0.000108744985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362151,0.00019869095,0.00026246958,0.00029861947,0.00043262777,0.00005062777,0.0004202733,0.00007643141,0.000005814848],"category_scores_gemma":[0.0018799568,0.00021458021,0.000039991533,0.00048199054,0.0000453842,0.00012440058,0.00011068765,0.0004797727,0.000001913093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016301023,0.00006181917,0.001283349,0.000058806545,0.00005839098,0.00004247413,0.00051478035,0.072244704,0.00047880557,0.0005569091,0.00033100988,0.92435265],"study_design_scores_gemma":[0.0011216921,0.0012141243,0.008178595,0.00009766944,0.00008809091,0.0026213862,0.00003709484,0.96314836,0.002003675,0.008555774,0.01187808,0.0010554666],"about_ca_topic_score_codex":0.00004707457,"about_ca_topic_score_gemma":6.966669e-7,"teacher_disagreement_score":0.92329717,"about_ca_system_score_codex":0.000054292526,"about_ca_system_score_gemma":0.000027992406,"threshold_uncertainty_score":0.8750327},"labels":[],"label_agreement":null},{"id":"W4213240734","doi":"10.2197/ipsjjip.30.155","title":"Automatic Optimize-time Validation for Binary Optimizers","year":2022,"lang":"en","type":"article","venue":"Journal of Information Processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Binary number; Compatibility (geochemistry); Code (set theory); Binary code; Code coverage; Program optimization; Source code; Dead code; Redundant code; Programming language; Code generation; Set (abstract data type); Operating system; Software; Arithmetic","score_opus":0.01353373715607724,"score_gpt":0.2568205463823833,"score_spread":0.24328680922630602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213240734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005405689,0.000055565855,0.992204,0.00077920145,0.00019213036,0.00013617081,0.0000017009928,0.0010016935,0.00022385835],"genre_scores_gemma":[0.12986287,0.0000016835756,0.8696832,0.00036725504,0.000030341542,0.000024085426,0.000006254357,0.0000051464135,0.000019132747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987886,0.00004227799,0.000596447,0.000054929802,0.00038920838,0.000128514],"domain_scores_gemma":[0.9982639,0.00016099191,0.001038398,0.00012164186,0.00036932557,0.000045758305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013725343,0.00007910096,0.00014699061,0.00038710027,0.00039112926,0.0003050638,0.00053254905,0.000023225917,0.000020038735],"category_scores_gemma":[0.0004035665,0.000072368726,0.00007495679,0.00038366157,0.00001233926,0.0037626831,0.000118418575,0.00014534169,0.0000031133004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006167477,0.00009563615,0.0000783818,0.0002516328,0.000029086594,0.0000054567026,0.005789625,0.1650135,0.00020853445,0.0004897791,0.06346024,0.7645165],"study_design_scores_gemma":[0.00044553287,0.00025888448,0.000033989818,0.00007432785,0.000010472963,0.000255722,0.000064845066,0.99130464,0.0004994277,0.005424316,0.0015234543,0.00010437518],"about_ca_topic_score_codex":8.180123e-7,"about_ca_topic_score_gemma":1.8654744e-9,"teacher_disagreement_score":0.82629114,"about_ca_system_score_codex":0.00012732323,"about_ca_system_score_gemma":0.00026168596,"threshold_uncertainty_score":0.30082896},"labels":[],"label_agreement":null},{"id":"W4213241976","doi":"10.1109/ms.2021.3133805","title":"AI-Driven Development Is Here: Should You Worry?","year":2022,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Worry; Computer science; Software development; Software engineering; Software; Psychology; Operating system","score_opus":0.04386800979763472,"score_gpt":0.2825543218158692,"score_spread":0.23868631201823448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213241976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015032331,0.00026851197,0.9566484,0.002419504,0.0013185185,0.0002642859,0.000015116065,0.023866953,0.00016634527],"genre_scores_gemma":[0.34066457,0.00000358328,0.6458098,0.011922281,0.0001018832,0.0002565562,0.0000102491,0.00004477234,0.001186257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788016,0.0000827567,0.00029184617,0.0006175535,0.0006770866,0.00045058475],"domain_scores_gemma":[0.99860144,0.00018353855,0.00010741836,0.0008788513,0.00009855404,0.00013019198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003402022,0.00022759767,0.00021158204,0.00016996564,0.0010742941,0.00011906829,0.0016035893,0.00006530103,0.00010869074],"category_scores_gemma":[0.00011992831,0.00023912238,0.000090645364,0.00066284946,0.000036491638,0.00022139418,0.0011584057,0.00044313536,0.00008188005],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011380922,0.00022504585,0.05021281,0.00004408132,0.000053431104,0.000203288,0.008154227,0.0006443717,0.000058953017,0.00044131672,0.69294995,0.24700111],"study_design_scores_gemma":[0.0009736913,0.0005124,0.005729577,0.00016811452,0.000027581238,0.0004243765,0.00007001084,0.014122391,0.008387082,0.05334812,0.9139939,0.0022427528],"about_ca_topic_score_codex":0.00004911565,"about_ca_topic_score_gemma":0.000003092998,"teacher_disagreement_score":0.32563224,"about_ca_system_score_codex":0.00022120413,"about_ca_system_score_gemma":0.00027984194,"threshold_uncertainty_score":0.9751128},"labels":[],"label_agreement":null},{"id":"W4214654833","doi":"10.26226/morressier.5ada8a0ed462b8029238e544","title":"The Value Of A Specimen Tracking Tool And Beyond","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Tracking (education); Computer science; Psychology; Machine learning","score_opus":0.02511246415375651,"score_gpt":0.2778520837146284,"score_spread":0.2527396195608719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214654833","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02207066,0.00060604274,0.9532684,0.0010125872,0.00062261015,0.00032846225,0.0000027714095,0.006269711,0.015818734],"genre_scores_gemma":[0.32851437,0.000060120095,0.67077005,0.00019640334,0.00013409332,0.000017730594,7.6720573e-7,0.000011525633,0.00029491918],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895304,0.000054528737,0.00024472998,0.0003641427,0.00021733236,0.00016625159],"domain_scores_gemma":[0.99806535,0.0006333661,0.00016739294,0.000981097,0.00012243628,0.000030377656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000780217,0.00014178641,0.00017855121,0.00005474546,0.00012246674,0.0002854372,0.0010962154,0.00010840829,0.0000031381153],"category_scores_gemma":[0.0003351281,0.00009260996,0.000053868767,0.00008612638,0.00014319221,0.00007110957,0.0019997216,0.00021090069,0.0000029626685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010703932,0.000081458194,0.006876534,0.00019951214,0.00011438503,0.000013879006,0.002634229,0.000025065832,0.00012977894,0.26612327,0.13406977,0.58972144],"study_design_scores_gemma":[0.00006831842,0.00008400473,0.0050366824,0.00016371408,0.000011068225,0.000021959799,0.0000041162193,0.03729831,0.0029694887,0.95259666,0.001503702,0.00024196309],"about_ca_topic_score_codex":0.00008874604,"about_ca_topic_score_gemma":0.0000026394282,"teacher_disagreement_score":0.6864734,"about_ca_system_score_codex":0.000017180266,"about_ca_system_score_gemma":0.000082194194,"threshold_uncertainty_score":0.37765244},"labels":[],"label_agreement":null},{"id":"W4220798833","doi":"10.18280/isi.270106","title":"Automatic Generation and Optimization of Combinatorial Test Cases from UML Activity Diagram Using Particle Swarm Optimization","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Activity diagram; Test case; Particle swarm optimization; Computer science; Model-based testing; Unified Modeling Language; Process (computing); Automation; Test Management Approach; Combinatorial explosion; Test (biology); Software; Algorithm; Data mining; Software system; Programming language; Machine learning; Mathematics; Engineering; Regression analysis","score_opus":0.02835137652987759,"score_gpt":0.24920017531039684,"score_spread":0.22084879878051925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220798833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3642309,0.000026203625,0.6343739,0.000015337546,0.00022221918,0.00017485848,0.000016224676,0.00092330726,0.000017045397],"genre_scores_gemma":[0.75973034,0.000004888599,0.24009869,0.00003080005,0.00003010057,0.000043100834,0.0000551819,0.000006311173,5.9178245e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988449,0.00013433992,0.00040519392,0.00015151716,0.00030911082,0.00015494443],"domain_scores_gemma":[0.99881697,0.00025094065,0.00044087286,0.0002667547,0.000176293,0.000048152335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041066375,0.00012639599,0.00017157668,0.00014502658,0.00048503053,0.00024710552,0.00019516337,0.00005096312,0.000014054216],"category_scores_gemma":[0.00090400066,0.00014005834,0.000029877543,0.000496833,0.000059706246,0.0025473987,0.00021391718,0.0000887435,6.3624674e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008091708,0.00007984502,0.0031676984,0.0000509485,0.000011273844,0.000001788844,0.0023583595,0.8895659,0.00033097068,0.0004792461,0.0000962109,0.10384969],"study_design_scores_gemma":[0.0002913572,0.00017906983,0.000656596,0.0000326424,0.000015145125,0.00003207203,0.000024513709,0.9929933,0.0038858613,0.0017397504,0.0000032362987,0.00014646212],"about_ca_topic_score_codex":0.0005485687,"about_ca_topic_score_gemma":0.0000015951128,"teacher_disagreement_score":0.39549944,"about_ca_system_score_codex":0.00022327375,"about_ca_system_score_gemma":0.00009147777,"threshold_uncertainty_score":0.57114136},"labels":[],"label_agreement":null},{"id":"W4220988444","doi":"10.1109/tse.2022.3162236","title":"Selecting Context-Sensitivity Modularly for Accelerating Object-Sensitive Pointer Analysis","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Notation; Pointer (user interface); Pointer analysis; Computer science; Programming language; Context (archaeology); Theoretical computer science; Algorithm; Mathematics; Static analysis; Artificial intelligence; Arithmetic","score_opus":0.019674976284096056,"score_gpt":0.23646358962900285,"score_spread":0.2167886133449068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220988444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021482667,0.000018374518,0.96770424,0.000060557257,0.00055070873,0.00031351403,0.000049555376,0.009813218,0.0000071437416],"genre_scores_gemma":[0.71195114,5.121418e-7,0.28753114,0.00019619116,0.000034082357,0.0002041038,0.000004278137,0.00003329066,0.000045280656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981111,0.00011013428,0.00032653863,0.0006366282,0.00035092584,0.0004646567],"domain_scores_gemma":[0.99742925,0.0016846262,0.00010695165,0.0005068705,0.00017238336,0.00009992841],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007416776,0.00028510086,0.00037403352,0.00068533595,0.0008214379,0.0001916408,0.0003301386,0.00006322111,0.000010263335],"category_scores_gemma":[0.00021709535,0.00034029369,0.00037850672,0.0015829928,0.000015346637,0.00035905882,0.000016655373,0.0005622719,0.000002613913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026305324,0.00012107625,0.00023086359,0.000029891891,0.00050264143,0.000042195516,0.0014772565,0.95542675,0.0012255823,0.00017881367,0.00027327365,0.040465336],"study_design_scores_gemma":[0.00034493566,0.00021126826,0.00027586476,0.000028918583,0.00013086456,0.00008385177,0.000041112708,0.97710735,0.021124657,0.00011200938,0.00009492811,0.0004442389],"about_ca_topic_score_codex":0.00013262611,"about_ca_topic_score_gemma":0.000023528637,"teacher_disagreement_score":0.69046843,"about_ca_system_score_codex":0.00028150692,"about_ca_system_score_gemma":0.000059904567,"threshold_uncertainty_score":0.99990493},"labels":[],"label_agreement":null},{"id":"W4225425474","doi":"10.3389/feduc.2022.853578","title":"Using Content Coding and Automatic Item Generation to Improve Test Security","year":2022,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Coding (social sciences); Scalability; Item bank; Process (computing); Data mining; Item response theory; Database","score_opus":0.04183309971773125,"score_gpt":0.2869789934573029,"score_spread":0.24514589373957163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225425474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.427594,0.00023291325,0.56789577,0.0005670426,0.0024715587,0.00030099056,0.0000021082194,0.00088520907,0.00005038195],"genre_scores_gemma":[0.60638463,0.0000018947569,0.39312837,0.00032548886,0.000048973627,0.00007782604,0.0000030857598,0.0000042996144,0.000025431085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929136,0.00006216854,0.00015208957,0.00024215797,0.00013023076,0.000121986726],"domain_scores_gemma":[0.99956274,0.00006964067,0.000068416964,0.00021321056,0.000040097857,0.000045874505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003694181,0.00006842709,0.00008763158,0.00021007776,0.00018601473,0.00009374252,0.00019220136,0.000018684605,0.0000018016015],"category_scores_gemma":[0.0004140159,0.000079648475,0.000011798991,0.0003223546,0.000010398412,0.00019047777,0.00014714804,0.000093364295,3.4958393e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034642028,0.00046588952,0.30483422,0.00007083547,0.000009147523,0.0000032631,0.013502842,0.00032150108,0.00776818,0.0019831532,0.15295896,0.51807857],"study_design_scores_gemma":[0.00008760216,0.00007865659,0.00689093,0.000029917655,0.0000038795743,0.00001632893,0.00031180793,0.98126835,0.0007619265,0.009966576,0.00043873498,0.00014530192],"about_ca_topic_score_codex":0.00017752302,"about_ca_topic_score_gemma":0.0000025582872,"teacher_disagreement_score":0.98094684,"about_ca_system_score_codex":0.000334138,"about_ca_system_score_gemma":0.00014606673,"threshold_uncertainty_score":0.32479703},"labels":[],"label_agreement":null},{"id":"W4225845951","doi":"10.1109/qrs-c55045.2021.00080","title":"Boosting Grey-box Fuzzing for Connected Autonomous Vehicle Systems","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ross Video (Canada); Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Fuzz testing; Computer science; Software; Automotive industry; Symbolic execution; Concolic testing; Code coverage; Vulnerability (computing); Process (computing); Computer security; Embedded system; Artificial intelligence; Programming language; Engineering","score_opus":0.07344966310209487,"score_gpt":0.33783700142671286,"score_spread":0.26438733832461797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225845951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.334845,0.00030613647,0.64814335,0.003989374,0.0041735037,0.0008985683,0.00034450108,0.0053720674,0.0019275172],"genre_scores_gemma":[0.95923156,0.00006200201,0.039391715,0.0005997203,0.00028806625,0.00011238792,0.00013159902,0.00002680546,0.00015615334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956801,0.0006399939,0.001011093,0.0013664032,0.0007852667,0.00051713013],"domain_scores_gemma":[0.9933154,0.0026986413,0.00044477303,0.001026046,0.0022686126,0.0002465355],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019866698,0.00042293442,0.0006583012,0.00016820939,0.00049110706,0.0011468809,0.0010654606,0.0002654866,0.000053922195],"category_scores_gemma":[0.0048513524,0.00045051315,0.00021577212,0.00036976472,0.00017860938,0.0005712604,0.00048046515,0.00055342814,0.00002492501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015704657,0.0012589673,0.030889846,0.00088827865,0.00021296869,0.000062796375,0.0042973626,0.0006492081,0.0015471674,0.926272,0.005743445,0.028020952],"study_design_scores_gemma":[0.0026380625,0.0006237619,0.010666596,0.0015779714,0.000058077043,0.00020413061,0.0007912226,0.54613477,0.005911364,0.4217144,0.007589118,0.002090559],"about_ca_topic_score_codex":0.0005850642,"about_ca_topic_score_gemma":0.00006155275,"teacher_disagreement_score":0.62438655,"about_ca_system_score_codex":0.00025408313,"about_ca_system_score_gemma":0.00041372384,"threshold_uncertainty_score":0.99989},"labels":[],"label_agreement":null},{"id":"W4226139682","doi":"10.5281/zenodo.6415365","title":"Scalable and Accurate Test Case Prioritization in Continuous Integration Contexts","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Prioritization; Scalability; Test (biology); Computer science; Biology; Engineering; Database; Ecology; Process management","score_opus":0.028062328126160885,"score_gpt":0.2553470633048817,"score_spread":0.22728473517872083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226139682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17412032,0.0005121786,0.7609312,0.0032685439,0.00037149288,0.0020075971,0.00021599428,0.028565113,0.030007571],"genre_scores_gemma":[0.9948009,0.0000131283905,0.0045215497,0.00014328212,0.000020215673,2.1817623e-7,0.0001267009,0.00020657502,0.00016741692],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876344,0.0002896594,0.0001939346,0.00034029406,0.00020653513,0.0002061441],"domain_scores_gemma":[0.99920774,0.00010451427,0.00008408542,0.00030582194,0.00022829282,0.000069531554],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008692246,0.00008884451,0.00010035041,0.00024600513,0.0016415304,0.0007386112,0.0005786678,0.000025695837,0.0003031353],"category_scores_gemma":[0.0014122778,0.000100252706,0.000014353933,0.0007147479,0.000055125227,0.00037895233,0.001331461,0.00023126877,0.00008997277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026737644,0.0003111182,0.000292287,0.000039787046,0.000009023207,0.00074838416,0.0044910884,0.00014957927,0.002075504,0.01489642,0.12338997,0.8535701],"study_design_scores_gemma":[0.0029490113,0.0024677804,0.0057647927,0.0001919228,0.00001967698,0.022002157,0.001008144,0.24401173,0.0017525733,0.023662714,0.69497967,0.0011898017],"about_ca_topic_score_codex":0.00007478494,"about_ca_topic_score_gemma":0.0000011215039,"teacher_disagreement_score":0.8523803,"about_ca_system_score_codex":0.00012988677,"about_ca_system_score_gemma":0.000004732559,"threshold_uncertainty_score":0.99965817},"labels":[],"label_agreement":null},{"id":"W4226176814","doi":"10.1007/978-3-030-99527-0_19","title":"Automatic Repair for Network Programs","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Debugging; Modular design; Reuse; Abstraction; Set (abstract data type); Domain (mathematical analysis); Symbolic execution; Task (project management); Programming language; Software; Software engineering; Distributed computing; Embedded system; Systems engineering","score_opus":0.02667669564335165,"score_gpt":0.2650263496974982,"score_spread":0.23834965405414657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226176814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013143335,0.0004437074,0.98220587,0.0004096299,0.0018513788,0.0009774088,0.0000026218106,0.013115752,0.00098048],"genre_scores_gemma":[0.0071623344,0.000009860425,0.99057555,0.0012922046,0.00052253145,0.00016792382,0.000010380384,0.000050372397,0.00020882925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606,0.000040621315,0.0005477078,0.0015956147,0.000895103,0.0008609558],"domain_scores_gemma":[0.996201,0.0012985367,0.0003369953,0.0018339092,0.00018696676,0.00014258915],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001900121,0.00049303495,0.00054146786,0.00046926196,0.00056633423,0.00045312635,0.0036071257,0.00022091754,0.000025453945],"category_scores_gemma":[0.0003008198,0.0004709446,0.0002695676,0.0007838422,0.00039351408,0.00036260483,0.0019143322,0.0006899435,0.000008195686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000203482,0.000025206104,0.0001371841,0.00006661921,0.000010089024,0.000037196834,0.00024931153,0.005845368,6.159247e-7,0.020351993,0.0010857397,0.97218865],"study_design_scores_gemma":[0.00008472868,0.00029839834,0.000024241945,0.00026022622,0.000006217636,0.00005755316,9.183897e-9,0.52286774,0.000008752194,0.4664484,0.009557915,0.0003858459],"about_ca_topic_score_codex":0.000023612874,"about_ca_topic_score_gemma":0.000012749789,"teacher_disagreement_score":0.9718028,"about_ca_system_score_codex":0.0003601394,"about_ca_system_score_gemma":0.00056675513,"threshold_uncertainty_score":0.9997742},"labels":[],"label_agreement":null},{"id":"W4226466002","doi":"10.1109/qrs54544.2021.00093","title":"MINTS: Unsupervised Temporal Specifications Miner","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 21st International Conference on Software Quality, Reliability and Security (QRS)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Correctness; Computer science; Debugging; Task (project management); Finite-state machine; Scalability; Frame (networking); Software; State (computer science); Trie; Software bug; Software system; Artificial intelligence; Programming language; Data structure; Engineering; Database; Systems engineering","score_opus":0.10583280632417456,"score_gpt":0.34160529800087,"score_spread":0.2357724916766954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226466002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40136823,0.0004151687,0.52641046,0.03800658,0.004964688,0.00098605,0.00078117015,0.008023242,0.019044405],"genre_scores_gemma":[0.918654,0.00023520958,0.07834878,0.0013177736,0.000257179,0.00007159985,0.00018018586,0.000021283171,0.0009139547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961213,0.00052292855,0.0007968613,0.0012755813,0.0009010931,0.0003822579],"domain_scores_gemma":[0.99555457,0.0010368119,0.00023693804,0.0014185075,0.0014956987,0.00025748266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012454136,0.00036439172,0.0004521011,0.00016626061,0.00027574168,0.00064305397,0.0012392136,0.00023888022,0.0005097736],"category_scores_gemma":[0.0030449005,0.00036953454,0.00019815241,0.00046324808,0.00027157555,0.0005498744,0.00045026492,0.0005499446,0.00010317806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011431859,0.002703737,0.11658213,0.00031804232,0.00018768155,0.00014084284,0.0056962627,0.0000424138,0.00073562935,0.8077672,0.023597732,0.04211399],"study_design_scores_gemma":[0.0015968403,0.00033127778,0.029756969,0.0006098012,0.000041615225,0.00014020501,0.0006032791,0.024352323,0.0046452438,0.905537,0.030546082,0.001839338],"about_ca_topic_score_codex":0.00041341467,"about_ca_topic_score_gemma":0.00012913396,"teacher_disagreement_score":0.5172858,"about_ca_system_score_codex":0.00015010883,"about_ca_system_score_gemma":0.00039474486,"threshold_uncertainty_score":0.99987566},"labels":[],"label_agreement":null},{"id":"W4229062148","doi":"10.1016/j.infsof.2022.106936","title":"A search-based framework for automatic generation of testing environments for cyber–physical systems","year":2022,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Cyber-physical system; Drone; Computer science; Robot; Software; Virtual machine; Physical system; Distributed computing; Human–computer interaction; Systems engineering; Embedded system; Real-time computing; Artificial intelligence; Engineering; Operating system","score_opus":0.03980151792648982,"score_gpt":0.2772495253795939,"score_spread":0.2374480074531041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229062148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03911917,0.000034353292,0.9568685,0.00026890927,0.00010335069,0.00062218466,0.000028839397,0.0029502944,0.0000043816885],"genre_scores_gemma":[0.48465088,3.3545905e-7,0.51465976,0.000098183446,0.000010907267,0.00055255205,0.00002061499,0.000004415554,0.0000023811301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918175,0.000025307656,0.0002965029,0.00013990508,0.00018088522,0.00017563716],"domain_scores_gemma":[0.9986447,0.0007416138,0.00020979985,0.00029861816,0.00007788939,0.00002735759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003563794,0.000095215924,0.00016759936,0.0003205594,0.0003065432,0.00005388463,0.00034045457,0.00008107425,8.2638263e-7],"category_scores_gemma":[0.0013006591,0.00009770704,0.000034780325,0.00034665485,0.00006454587,0.00026587394,0.00017091437,0.0001256511,9.808259e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015246976,0.00015606362,0.006157513,0.00047776857,0.00003105485,8.124202e-7,0.0014602827,0.012647645,0.0003975674,0.16344331,0.00207107,0.81314164],"study_design_scores_gemma":[0.0002962734,0.0005361246,0.00011467007,0.000031017335,0.000006275423,0.000013077484,0.000032894684,0.9498301,0.0010347088,0.04698183,0.0010090325,0.00011400342],"about_ca_topic_score_codex":0.0000104320025,"about_ca_topic_score_gemma":9.9173846e-8,"teacher_disagreement_score":0.9371824,"about_ca_system_score_codex":0.00005981167,"about_ca_system_score_gemma":0.00006690847,"threshold_uncertainty_score":0.39843774},"labels":[],"label_agreement":null},{"id":"W4230318508","doi":"10.22215/etd/2010-08842","title":"Method and tool support for refinement of test suites","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Test (biology); Computer science; Geology","score_opus":0.017882349998801794,"score_gpt":0.33241269764019243,"score_spread":0.31453034764139065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230318508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034896762,0.00008596277,0.9851511,0.00015481356,0.00040473376,0.0006060868,0.000024429331,0.0047022076,0.005380995],"genre_scores_gemma":[0.005818758,0.000007817996,0.98568046,0.000086799475,0.00003081569,0.000094217794,0.0001034519,0.0000144202195,0.00816328],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990805,0.00001102423,0.0002766152,0.0003330614,0.0001556083,0.00014320012],"domain_scores_gemma":[0.996809,0.0023300673,0.00019535233,0.00041118555,0.0002208428,0.00003354107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054713746,0.00015302289,0.00024547064,0.00012974968,0.00004913024,0.00006238117,0.00040452246,0.00017733382,0.000018880492],"category_scores_gemma":[0.0016368338,0.00012958112,0.00005870775,0.00009960216,0.000012230742,0.000072311406,0.000058675967,0.00012605709,0.0000010662733],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015685697,0.00016235773,0.0050244867,0.00084255333,0.00003609301,0.0000029454397,0.00081997935,2.3751332e-7,0.008797613,0.027425937,0.08770788,0.8691642],"study_design_scores_gemma":[0.0013767123,0.0034220326,0.043686245,0.0008413516,0.0002460859,0.00007819556,0.00005788964,0.013272186,0.47845572,0.3901334,0.06598198,0.0024481965],"about_ca_topic_score_codex":0.00008350613,"about_ca_topic_score_gemma":0.000049079557,"teacher_disagreement_score":0.866716,"about_ca_system_score_codex":0.0000068487743,"about_ca_system_score_gemma":0.00010214532,"threshold_uncertainty_score":0.52841645},"labels":[],"label_agreement":null},{"id":"W4231515836","doi":"10.1109/jcdl.2017.7991565","title":"A Text Extraction Software Benchmark Based on a Synthesized Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vienna Science and Technology Fund","keywords":"Computer science; Ground truth; Correctness; Workflow; Information retrieval; Data mining; Benchmark (surveying); Scalability; Quality (philosophy); Process (computing); Snippet; Artificial intelligence; Database; Algorithm; Programming language","score_opus":0.03252267041055522,"score_gpt":0.31590586622439903,"score_spread":0.2833831958138438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231515836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039936168,0.000006696727,0.98557353,0.0013921933,0.00022704522,0.00014190616,0.000046895,0.008440681,0.0037716785],"genre_scores_gemma":[0.39756453,0.0000012272595,0.6010851,0.0010785387,0.000044836215,0.00003150157,0.000044493558,0.000009695892,0.00014005066],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889,0.000047999743,0.00014303932,0.00042705095,0.00026915938,0.00022278566],"domain_scores_gemma":[0.9965471,0.0007928166,0.00015414308,0.0023757285,0.000044964276,0.00008527312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044346732,0.00014432908,0.0001372022,0.00009927408,0.00055962714,0.0005962047,0.0014641588,0.000067856796,0.000073386516],"category_scores_gemma":[0.00256087,0.00011979762,0.000049130635,0.00006485039,0.000050187966,0.0005287549,0.00020245541,0.00013421137,0.00012404715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032649088,0.0002251297,0.0055057555,0.000021950907,0.000009753746,0.00008499458,0.000030805695,0.0000375302,0.000123543,0.0020250198,0.66574514,0.32615772],"study_design_scores_gemma":[0.001665901,0.00077300693,0.070439756,0.0006711196,0.00003679467,0.00011159715,0.0000034993807,0.75807786,0.011654419,0.068082,0.08683537,0.0016486612],"about_ca_topic_score_codex":0.0002483352,"about_ca_topic_score_gemma":0.000009099151,"teacher_disagreement_score":0.75804037,"about_ca_system_score_codex":0.000032707405,"about_ca_system_score_gemma":0.00006217565,"threshold_uncertainty_score":0.5749216},"labels":[],"label_agreement":null},{"id":"W4231608201","doi":"10.22215/etd/2009-09375","title":"A genetic algorithm to devise test case sequences based on a state machine diagram and data flow information","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Diagram; Computer science; Algorithm; Data flow diagram; State (computer science); Information flow; State diagram; Combinatorics; Mathematics; Philosophy; Database","score_opus":0.01779673111461176,"score_gpt":0.2920255916742575,"score_spread":0.27422886055964574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231608201","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017958968,0.0001006031,0.99172366,0.00021182447,0.00015174765,0.0005503567,0.0002097958,0.0048346277,0.00042151025],"genre_scores_gemma":[0.021643115,0.000024638926,0.9755746,0.0014472015,0.0000287968,0.000048756796,0.0010881933,0.000013531396,0.00013116207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845695,0.00004518337,0.00036289048,0.00053321343,0.00035120343,0.00025056675],"domain_scores_gemma":[0.9978712,0.0004228881,0.00016449326,0.0012247277,0.00014639761,0.0001702694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035165052,0.00030452907,0.0002361167,0.00040047462,0.00015558593,0.00061427837,0.0009313791,0.0001100463,0.0000039710267],"category_scores_gemma":[0.0007881818,0.00025930675,0.000025878719,0.00043451568,0.0000136405215,0.00059351313,0.00013124378,0.00020069121,0.00002200999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004336118,0.00003266263,0.00009935877,0.000041034695,0.0000032400321,0.00023329747,0.00026822262,0.00021278109,7.078452e-7,0.000004719714,0.004993583,0.99410605],"study_design_scores_gemma":[0.00013439122,0.00041581228,0.0020649296,0.00020538065,0.000013917422,0.00024319752,0.0000057493717,0.9945527,0.00006173587,0.0014683298,0.00047188526,0.00036198058],"about_ca_topic_score_codex":0.0014876683,"about_ca_topic_score_gemma":0.0005057071,"teacher_disagreement_score":0.9943399,"about_ca_system_score_codex":0.000040031788,"about_ca_system_score_gemma":0.0001873797,"threshold_uncertainty_score":0.99998593},"labels":[],"label_agreement":null},{"id":"W4232005383","doi":"10.1109/icse.2015.52","title":"Detecting Inconsistencies in JavaScript MVC Applications","year":2015,"lang":"en","type":"article","venue":"2015 IEEE/ACM 37th IEEE International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"Computer science; JavaScript; Web application; Consistency (knowledge bases); Model–view–controller; Identifier; Data mining; Software engineering; Programming language; Distributed computing; Operating system; Artificial intelligence; User interface","score_opus":0.10755743350707492,"score_gpt":0.32242141870734803,"score_spread":0.2148639852002731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232005383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013177169,0.00008355317,0.97647804,0.0004218332,0.002399049,0.0002904553,0.000011150005,0.006389224,0.0007495288],"genre_scores_gemma":[0.698558,0.000010751913,0.300556,0.00019556866,0.000265505,0.00023216978,0.000006372435,0.000030004745,0.00014566252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780345,0.000045024324,0.00047498406,0.00060178176,0.00065353874,0.00042120286],"domain_scores_gemma":[0.9975822,0.0004524487,0.00015657562,0.00091704924,0.0006672245,0.0002244942],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000695773,0.00031421322,0.00027888184,0.00057949097,0.00007401739,0.00028835243,0.0020333175,0.00013899597,0.000008761047],"category_scores_gemma":[0.0031125413,0.0003353519,0.000077779434,0.0005077067,0.000043579934,0.00055050553,0.0002547812,0.0004659223,0.0001040781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022120685,0.0018095102,0.18006726,0.0005241029,0.0006700285,0.0007524529,0.01333677,0.14632072,0.008540484,0.17358044,0.1527143,0.32146275],"study_design_scores_gemma":[0.0022784802,0.0005345367,0.006247958,0.0014986037,0.000027827968,0.0002939998,0.0002050226,0.8879427,0.014135269,0.06534889,0.018717205,0.0027695296],"about_ca_topic_score_codex":0.00015535162,"about_ca_topic_score_gemma":0.000024248537,"teacher_disagreement_score":0.741622,"about_ca_system_score_codex":0.0003616716,"about_ca_system_score_gemma":0.0002457967,"threshold_uncertainty_score":0.9999099},"labels":[],"label_agreement":null},{"id":"W4232175613","doi":"10.1007/978-3-642-35182-2_17","title":"Concurrent Test Generation Using Concolic Multi-trace Analysis","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Concolic testing; Computer science; Thread (computing); Concurrency; Code coverage; Programming language; Symbolic execution; TRACE (psycholinguistics); Test case; Parallel computing; Software; Machine learning","score_opus":0.07016234621544544,"score_gpt":0.3164600363995561,"score_spread":0.24629769018411068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232175613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016526639,0.0017084817,0.9943184,0.00010878667,0.001272385,0.00031999656,0.000007529927,0.0019891388,0.000109964276],"genre_scores_gemma":[0.37474182,0.000027620601,0.6242001,0.00039093112,0.00054488296,0.000007704754,0.000007489814,0.000025016885,0.000054452845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963906,0.00005067556,0.0005934392,0.0013945338,0.00085929723,0.0007114559],"domain_scores_gemma":[0.99664783,0.0008739816,0.00045569788,0.0014234291,0.00036851846,0.00023053143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011577622,0.0005536687,0.000668669,0.001389742,0.0003448515,0.00062296935,0.0022559257,0.0003419496,0.000013964938],"category_scores_gemma":[0.000373364,0.0005252962,0.00022199521,0.0014866951,0.00050129875,0.00062277965,0.0009645324,0.00067097787,0.000020634152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.782969e-7,0.000086543216,0.0035163462,0.000025070603,0.00005141856,0.00003245336,0.0006870477,0.035455238,0.00051833864,0.0014239866,0.000060078764,0.958143],"study_design_scores_gemma":[0.00013635837,0.00007339864,0.00042473222,0.00014583493,0.00008888514,0.00005260383,1.8825105e-8,0.99054176,0.0012421826,0.0062714536,0.00038098014,0.000641818],"about_ca_topic_score_codex":0.00010203603,"about_ca_topic_score_gemma":0.00007143486,"teacher_disagreement_score":0.9575012,"about_ca_system_score_codex":0.00049518066,"about_ca_system_score_gemma":0.0004707281,"threshold_uncertainty_score":0.99971986},"labels":[],"label_agreement":null},{"id":"W4232229135","doi":"10.1109/ibf50092.2020.9034868","title":"Message from the Chairs","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; World Wide Web","score_opus":0.03640098502946325,"score_gpt":0.23401821829736166,"score_spread":0.19761723326789843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232229135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095175457,0.000071768234,0.93978655,0.034309365,0.000059834932,0.000043441476,0.0000011269155,0.015473676,0.009302481],"genre_scores_gemma":[0.77400625,0.0000021707772,0.21029516,0.015521297,0.000086424065,0.0000045054717,5.769076e-7,0.0000035945466,0.000080053964],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99957234,0.000022635673,0.00005872218,0.00016056903,0.00010218672,0.00008357477],"domain_scores_gemma":[0.9993113,0.00030830156,0.00001701222,0.00030620958,0.000013606039,0.00004355513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007474063,0.000047661164,0.000047587928,0.0000042882466,0.000060013743,0.000085828586,0.0007985818,0.000016215583,0.00003273804],"category_scores_gemma":[0.00019436688,0.00002772127,0.000023245599,0.00012906206,0.000015680522,0.000060167633,0.00022215772,0.00006538429,0.00006973476],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001052159,0.000008451745,0.004829736,0.0000012589591,0.0000059866315,0.000011066777,0.0017142493,0.000004152026,0.000095943426,0.024450406,0.9139671,0.05491064],"study_design_scores_gemma":[0.0004364196,0.00022757439,0.02238292,0.000050886872,0.0000125698125,0.000011582463,0.000051277988,0.34687674,0.010580922,0.46757206,0.15109666,0.00070040656],"about_ca_topic_score_codex":0.00016303726,"about_ca_topic_score_gemma":0.0000021940355,"teacher_disagreement_score":0.7730545,"about_ca_system_score_codex":0.0000032225964,"about_ca_system_score_gemma":0.000012408577,"threshold_uncertainty_score":0.1483977},"labels":[],"label_agreement":null},{"id":"W4233095787","doi":"10.22215/etd/2012-07238","title":"Comparison of coverage criteria for the category partition method using automatically generated test suites with melba","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Library and Archives Canada","funders":"","keywords":"Partition (number theory); Computer science; Mathematics; Information retrieval; Combinatorics","score_opus":0.083910690938459,"score_gpt":0.4105903065037051,"score_spread":0.3266796155652461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233095787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00954346,0.0002903063,0.98638576,0.000048050963,0.00027035287,0.00052618317,0.000011763663,0.002640798,0.0002833053],"genre_scores_gemma":[0.43460637,0.0000019898707,0.5648913,0.000045264558,0.000054708125,0.000079107886,0.00012505561,0.00002344166,0.00017279212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985065,0.0001100314,0.0004768371,0.00032298526,0.00029725806,0.00028637482],"domain_scores_gemma":[0.9939646,0.0044873212,0.00045590667,0.00055334973,0.00048134758,0.00005748905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000781801,0.00026383257,0.00044643812,0.00011629776,0.00021577466,0.0001905629,0.0005842648,0.00018012719,0.000022705388],"category_scores_gemma":[0.00086319045,0.00016727905,0.0000819907,0.00029443245,0.000034961624,0.00023229187,0.000044904515,0.00015999586,0.0000017341989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006033871,0.0044330554,0.09613468,0.0075636157,0.0015135821,0.000017769775,0.031256754,0.00421637,0.2393988,0.08537133,0.1516448,0.37784585],"study_design_scores_gemma":[0.00022192669,0.00032762514,0.008768605,0.00029614219,0.00021914473,0.000013807844,0.00005871038,0.895781,0.08612504,0.007640204,0.00011594693,0.0004318644],"about_ca_topic_score_codex":0.00030820174,"about_ca_topic_score_gemma":0.00007541643,"teacher_disagreement_score":0.8915646,"about_ca_system_score_codex":0.00003922141,"about_ca_system_score_gemma":0.00019135971,"threshold_uncertainty_score":0.68214417},"labels":[],"label_agreement":null},{"id":"W4233113820","doi":"10.22215/etd/2009-10188","title":"Using machine learning to refine black-box test specifications and test suites","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Test (biology); Computer science; Artificial intelligence","score_opus":0.056099875847924155,"score_gpt":0.3105859834633714,"score_spread":0.25448610761544727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233113820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28917253,0.005076027,0.4932008,0.007495804,0.0015705737,0.003763985,0.00011164905,0.12900248,0.07060614],"genre_scores_gemma":[0.18712196,0.00008873272,0.7964563,0.00034345416,0.00015822482,0.000017740967,0.000214576,0.000052712203,0.015546322],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998347,0.000032526317,0.00035726183,0.00068488286,0.0002739094,0.00030442045],"domain_scores_gemma":[0.9964139,0.0023973612,0.00019653166,0.0006117787,0.00022654157,0.00015387569],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002896789,0.00032206002,0.0003051627,0.00041306624,0.00029837948,0.00040375371,0.0006241849,0.00017155593,0.000015517375],"category_scores_gemma":[0.0063554435,0.00030912049,0.00005257342,0.00069989864,0.000026099935,0.0001825776,0.00010305399,0.00039675008,0.000037735037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003606634,0.0014211808,0.3664109,0.0005799072,0.00008826744,0.00015568791,0.009539388,0.0003419891,0.043538462,0.017350148,0.07688973,0.48364824],"study_design_scores_gemma":[0.0012230788,0.0035174193,0.53956157,0.004416458,0.00030487924,0.00046396418,0.00035209005,0.30932924,0.04392457,0.045873724,0.043673985,0.0073590335],"about_ca_topic_score_codex":0.00048933463,"about_ca_topic_score_gemma":0.00026135085,"teacher_disagreement_score":0.4762892,"about_ca_system_score_codex":0.00006210349,"about_ca_system_score_gemma":0.00008639494,"threshold_uncertainty_score":0.9999361},"labels":[],"label_agreement":null},{"id":"W4233672025","doi":"10.22215/etd/2010-08757","title":"Hybrid strength two covering array constructions: using cover starters to create covering arrays","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Cover (algebra); Computer science; Humanities; Art; Engineering; Mechanical engineering","score_opus":0.016809667172424964,"score_gpt":0.2838758492318568,"score_spread":0.2670661820594319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233672025","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17581844,0.00003443195,0.80294037,0.000032486965,0.0029920877,0.00043566676,0.000032228323,0.009054744,0.008659564],"genre_scores_gemma":[0.24618416,0.000012428296,0.75132203,0.00033849906,0.0002674503,0.00005617949,0.00011927838,0.00009329059,0.00160668],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997119,0.000055078406,0.00058203604,0.0010490859,0.00056765054,0.00062716455],"domain_scores_gemma":[0.99756557,0.00032033058,0.00035553073,0.0011908149,0.00028329258,0.00028448866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003188561,0.00058826,0.0005599524,0.000534183,0.00041200727,0.00077622035,0.0011141123,0.00020915295,0.00007233862],"category_scores_gemma":[0.00038177063,0.00062072324,0.00018296653,0.00042291562,0.000050568156,0.0006408739,0.00014047408,0.0007632836,0.00006651885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056381203,0.0010093143,0.0112634525,0.0020667624,0.0015912623,0.00084743655,0.016117683,0.028863449,0.4158219,0.032363404,0.10420906,0.38528246],"study_design_scores_gemma":[0.0029154334,0.00085164624,0.0012298137,0.0056089438,0.00045982952,0.0013092477,0.00055252865,0.17376366,0.7109832,0.06763922,0.025321785,0.009364689],"about_ca_topic_score_codex":0.0011348579,"about_ca_topic_score_gemma":0.00010624235,"teacher_disagreement_score":0.37591776,"about_ca_system_score_codex":0.00020930385,"about_ca_system_score_gemma":0.000371804,"threshold_uncertainty_score":0.99962443},"labels":[],"label_agreement":null},{"id":"W4234480656","doi":"10.1145/1108792.1108795","title":"An empirical framework for comparing effectiveness of testing and property-based formal analysis","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Debugging; Computer science; Software engineering; Software bug; Formal methods; Random testing; Formal specification; Empirical research; Formal verification; Measure (data warehouse); Software testing; Software; Programming language; Data mining; Test case; Machine learning; Mathematics","score_opus":0.06517471039457418,"score_gpt":0.3506701034153422,"score_spread":0.28549539302076804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234480656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12954451,0.000011182083,0.86807555,0.00007653587,0.000010813329,0.00016003729,4.958085e-7,0.0020051994,0.00011566805],"genre_scores_gemma":[0.50383717,3.9606196e-8,0.49605116,0.00007760893,0.000011438248,0.000017650213,6.8382286e-7,0.000003066948,0.000001188365],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991348,0.000078763376,0.00018067923,0.00028292165,0.00012141966,0.00020141185],"domain_scores_gemma":[0.9967955,0.0025748238,0.00007026988,0.0003547085,0.0001369219,0.000067780544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009004658,0.000100234945,0.00025766963,0.00017113067,0.000109441804,0.00007771644,0.000323951,0.000056173656,7.763484e-7],"category_scores_gemma":[0.0007390483,0.0000679759,0.00005763063,0.0006747262,0.000038721675,0.00029978016,0.000079582685,0.000075929354,3.0952236e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031722753,0.00015762048,0.9066599,0.00012317365,0.00005392892,7.284645e-7,0.00012613797,0.00680615,0.00030198932,0.0035865847,0.000054745407,0.082097344],"study_design_scores_gemma":[0.00015174097,0.00026893354,0.07184025,0.000070556576,0.00003941952,0.000001988924,0.0000010009412,0.91125786,0.0044726804,0.011772435,0.000009578671,0.0001135615],"about_ca_topic_score_codex":0.00007628338,"about_ca_topic_score_gemma":0.000006088473,"teacher_disagreement_score":0.9044517,"about_ca_system_score_codex":0.000018674076,"about_ca_system_score_gemma":0.00003779785,"threshold_uncertainty_score":0.2771977},"labels":[],"label_agreement":null},{"id":"W4234836192","doi":"10.1145/2345141.1967693","title":"Software debugging and testing using the abstract diagnosis theory","year":2012,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Observability; Debugging; Dependency (UML); Program slicing; Controllability; Variable (mathematics); Set (abstract data type); Source code; A priori and a posteriori; Algorithm; Programming language; Theoretical computer science; Mathematics","score_opus":0.08703010010577043,"score_gpt":0.3037358530034371,"score_spread":0.21670575289766664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234836192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7836789,0.0044397274,0.1982977,0.00064609136,0.00058735954,0.0002892642,0.00000527483,0.01157454,0.00048113437],"genre_scores_gemma":[0.67097676,0.0000048214906,0.32848436,0.00036771028,0.00013603175,0.000013129828,5.7575124e-7,0.000011947027,0.0000046767796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987884,0.00009677342,0.00019085965,0.00026689304,0.00021313014,0.00044392265],"domain_scores_gemma":[0.9890731,0.009813259,0.00016215409,0.0007819581,0.000057522728,0.00011202718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012245781,0.0001764035,0.00014392535,0.0000769626,0.00048037982,0.00029772634,0.0010382332,0.00006226954,0.0000067645897],"category_scores_gemma":[0.006800782,0.00012252443,0.00003188054,0.000274821,0.00009463278,0.00075707445,0.0006098785,0.00019882439,0.00000913282],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002727311,0.000043410815,0.7634576,0.00004244164,0.000023740167,0.000011153673,0.0018881672,0.0000692978,0.00010340013,0.0013168001,0.0012656299,0.23177561],"study_design_scores_gemma":[0.00044179623,0.00018096078,0.7764336,0.0010083341,0.00022058468,0.00052444247,0.00022934815,0.033048987,0.005072656,0.17916043,0.0020113883,0.0016674903],"about_ca_topic_score_codex":0.00018354246,"about_ca_topic_score_gemma":0.0000033127226,"teacher_disagreement_score":0.23010813,"about_ca_system_score_codex":0.000022319822,"about_ca_system_score_gemma":0.00003208309,"threshold_uncertainty_score":0.81416625},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06046944475577618,"score_gpt":0.3077181642846764,"score_spread":0.24724871952890023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236669998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07067727,0.00013485651,0.9257042,0.0002511447,0.00007943813,0.00064611656,0.0000066484413,0.0024484845,0.000051875882],"genre_scores_gemma":[0.4010731,0.000011054049,0.5987321,0.000038156006,0.000011939508,0.00009715554,0.0000034914858,0.000009967124,0.000022988323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837625,0.0001803384,0.00046594584,0.0006160024,0.00017079915,0.00019066363],"domain_scores_gemma":[0.99502796,0.0028333687,0.00040004932,0.0009932833,0.0006676403,0.0000776787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016378337,0.00017090191,0.00021293046,0.00006684853,0.00049587607,0.000046678484,0.0004133434,0.00008222745,1.8064014e-7],"category_scores_gemma":[0.0077291825,0.0001376734,0.000045436278,0.0006429994,0.00030700176,0.00019746932,0.00013606843,0.00015547434,8.8409774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031420102,0.00025748755,0.1890419,0.00056025997,0.000016252208,2.9768145e-7,0.0013672521,0.012082109,0.012464524,0.0016863748,0.00097145984,0.78152066],"study_design_scores_gemma":[0.00017120209,0.000072272094,0.052994452,0.000062790525,0.000013103117,0.000028182058,0.0000024857288,0.88363796,0.0022894575,0.05975158,0.00078827,0.00018823259],"about_ca_topic_score_codex":0.000082020626,"about_ca_topic_score_gemma":4.429564e-7,"teacher_disagreement_score":0.87155586,"about_ca_system_score_codex":0.000041880834,"about_ca_system_score_gemma":0.00015200269,"threshold_uncertainty_score":0.92531115},"labels":[],"label_agreement":null},{"id":"W4237956829","doi":"10.1145/2016603.1967693","title":"Software debugging and testing using the abstract diagnosis theory","year":2011,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Observability; Debugging; Dependency (UML); Program slicing; Controllability; Variable (mathematics); Source code; Set (abstract data type); A priori and a posteriori; Context (archaeology); Algorithm; Programming language; Theoretical computer science; Mathematics","score_opus":0.13478969035681715,"score_gpt":0.28714426921478553,"score_spread":0.15235457885796838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237956829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70259804,0.0017837764,0.27720702,0.00032957684,0.00044999245,0.00036189152,0.0000060599164,0.015738646,0.0015249824],"genre_scores_gemma":[0.6002288,0.000004180764,0.39942428,0.0002725113,0.000042641776,0.000012054494,3.4889828e-7,0.000010923539,0.000004296383],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998843,0.000084305575,0.00020359718,0.00036510752,0.0001855761,0.00031837393],"domain_scores_gemma":[0.9929953,0.0058162455,0.00017201704,0.0008655889,0.00007357816,0.00007724837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008414573,0.00017791717,0.0001458796,0.000084249805,0.00043587878,0.00023265558,0.0013385287,0.000062067375,0.000012095747],"category_scores_gemma":[0.0051964447,0.00012427682,0.000032784472,0.00026982938,0.000119639815,0.00046506085,0.0006170947,0.00019311874,0.0000074710138],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008989212,0.00006867771,0.59460723,0.00006700737,0.000046557376,0.000096351774,0.005663409,0.000044985205,0.00011111838,0.0026232845,0.0011760789,0.39548633],"study_design_scores_gemma":[0.00033659683,0.00025708132,0.43777183,0.0008097811,0.00014855732,0.000325276,0.00018243493,0.027556665,0.0055642547,0.52556044,0.00032792156,0.0011591623],"about_ca_topic_score_codex":0.0005006721,"about_ca_topic_score_gemma":0.000010437142,"teacher_disagreement_score":0.5229372,"about_ca_system_score_codex":0.000015958414,"about_ca_system_score_gemma":0.000042626194,"threshold_uncertainty_score":0.62210053},"labels":[],"label_agreement":null},{"id":"W4238745643","doi":"10.22215/etd/2006-06634","title":"Traffic-aware stress testing of distributed real-time systems based on UML models using genetic algorithms","year":2006,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage","funders":"","keywords":"Computer science; Unified Modeling Language; Algorithm; Programming language; Software","score_opus":0.03484226928523558,"score_gpt":0.2733626140505468,"score_spread":0.2385203447653112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238745643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03326079,0.000077111836,0.95430636,0.000004767781,0.0003610458,0.00052561425,0.00020257589,0.010037739,0.0012240056],"genre_scores_gemma":[0.37020987,0.000002389815,0.6278152,0.000008838506,0.00011412011,0.00005111755,0.0013391403,0.00008579295,0.00037355025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970554,0.00012519109,0.00079431006,0.0008315248,0.00074823987,0.00044533765],"domain_scores_gemma":[0.9968975,0.000653518,0.00069561804,0.001038728,0.0006105598,0.00010406908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027890338,0.00050069974,0.00065468805,0.00039560502,0.00016452803,0.00023154028,0.001024326,0.00038311738,0.0000024752392],"category_scores_gemma":[0.00016752142,0.0004799431,0.0001415241,0.00082246226,0.000029333285,0.00015229579,0.000054765882,0.0002555403,0.000002410565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008546299,0.00015601178,0.00011145606,0.00043902837,0.00001678528,0.000034790402,0.000055238554,0.9788798,0.000150196,0.000064924505,0.0014309788,0.01865224],"study_design_scores_gemma":[0.00016528732,0.00018668977,0.00030495037,0.002155115,0.000040989366,0.000008769276,0.000008629808,0.995228,0.00093480863,0.00047632994,0.0000013265714,0.00048909377],"about_ca_topic_score_codex":0.0034943745,"about_ca_topic_score_gemma":0.0000127642015,"teacher_disagreement_score":0.3369491,"about_ca_system_score_codex":0.00015853158,"about_ca_system_score_gemma":0.00037618465,"threshold_uncertainty_score":0.9997652},"labels":[],"label_agreement":null},{"id":"W4239722293","doi":"10.1002/9780470382844.gloss","title":"Glossary","year":2008,"lang":"en","type":"other","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Glossary; Library science; Engineering; Citation; Sociology; Computer science; Philosophy","score_opus":0.018116398211921975,"score_gpt":0.24258748086514478,"score_spread":0.2244710826532228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239722293","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9925238e-8,0.00029089095,0.34672546,0.000051293977,0.00013015042,0.000033561453,4.975541e-7,0.056129053,0.5966391],"genre_scores_gemma":[0.0000075416588,0.000054059838,0.42929575,0.0003031546,0.00008381715,0.0000042047727,0.0000010943452,0.000075276985,0.5701751],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99939746,0.000012011513,0.00006649304,0.00025644788,0.00013685551,0.00013071114],"domain_scores_gemma":[0.99918187,0.000038497856,0.00004906524,0.0006818171,0.0000095490395,0.000039225444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000034206187,0.00012306435,0.00012396894,0.00014532042,0.000022639046,0.00003033636,0.0007518285,0.00013279327,0.00022283764],"category_scores_gemma":[0.000031897227,0.00010292356,0.000039830575,0.00013582851,0.000025675443,0.000027356002,0.00018033157,0.00008683709,0.00045184736],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4017983e-8,0.0000063711013,0.00004369862,0.0000039849288,0.0000033272595,0.000025630055,0.0000056771532,1.3660785e-8,9.761984e-8,0.0019955712,0.98529625,0.012619316],"study_design_scores_gemma":[0.000025591333,0.000013409706,0.000015099296,0.000056843033,9.009597e-7,0.0000620412,3.251769e-8,0.00029080483,0.000010354138,0.0062670237,0.9930922,0.00016570749],"about_ca_topic_score_codex":0.00027351416,"about_ca_topic_score_gemma":0.0000036893884,"teacher_disagreement_score":0.082570285,"about_ca_system_score_codex":0.000009316315,"about_ca_system_score_gemma":0.000039638202,"threshold_uncertainty_score":0.5807734},"labels":[],"label_agreement":null},{"id":"W4240999823","doi":"10.1109/cmsbse.2013.6605713","title":"Effectively using search-based software engineering techniques within model checking and its applications","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Search-based software engineering; Assertion; Software engineering; Software; Process (computing); Model checking; Heuristic; Software development; Software construction; Programming language; Artificial intelligence","score_opus":0.030477762737352792,"score_gpt":0.2658187234315718,"score_spread":0.23534096069421903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240999823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017099174,0.000064976404,0.9663185,0.00006295505,0.000011921757,0.00054773793,7.7357254e-7,0.01583581,0.000058170182],"genre_scores_gemma":[0.4301012,8.4205584e-7,0.5696037,0.00009991023,0.000011502219,0.00015990334,4.5518226e-7,0.000012452203,0.0000100857005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990277,0.000023126771,0.00016304724,0.00036646373,0.00017391145,0.00024569366],"domain_scores_gemma":[0.99903095,0.00031677957,0.000047336296,0.00034169294,0.00016236263,0.00010088699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030513015,0.00015845575,0.00013747529,0.00018335656,0.00015383358,0.00021424417,0.00038805575,0.000074851996,0.0000017734695],"category_scores_gemma":[0.0002394704,0.00014680291,0.000030164258,0.00032086254,0.00002575482,0.00044314616,0.00021572373,0.00016452202,0.000005631874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011038989,0.0004955972,0.018755645,0.0015233309,0.000119129065,0.000021181588,0.0025673052,0.25103813,0.19586916,0.12360891,0.002236129,0.40375444],"study_design_scores_gemma":[0.000046683366,0.000022485227,0.00021349252,0.000092818445,0.0000029483829,0.000010071223,8.737361e-7,0.9339437,0.060248666,0.005231659,0.0000066000734,0.00017999651],"about_ca_topic_score_codex":0.000107405205,"about_ca_topic_score_gemma":4.282476e-7,"teacher_disagreement_score":0.68290555,"about_ca_system_score_codex":0.00005658351,"about_ca_system_score_gemma":0.000067791,"threshold_uncertainty_score":0.59864485},"labels":[],"label_agreement":null},{"id":"W4242156770","doi":"10.1109/icse.2015.78","title":"DASE: Document-Assisted Symbolic Execution for Improving Automated Software Testing","year":2015,"lang":"en","type":"article","venue":"2015 IEEE/ACM 37th IEEE International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Symbolic execution; Documentation; Heuristics; Software; Focus (optics); Programming language; Software bug; Data mining; Software engineering; Operating system","score_opus":0.10146070391989331,"score_gpt":0.33731170688533973,"score_spread":0.23585100296544642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242156770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01438614,0.000052856914,0.9505137,0.00028913064,0.0038883318,0.00049573276,0.000049538237,0.030214597,0.00010994281],"genre_scores_gemma":[0.44624698,0.0000021914427,0.5527886,0.00015853163,0.00032199075,0.00022753551,0.000047634076,0.000058922524,0.000147619],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675655,0.00005707907,0.0006657779,0.00091190264,0.0009024041,0.0007062776],"domain_scores_gemma":[0.99566257,0.0010345057,0.0003595909,0.0010619193,0.0015002857,0.00038114784],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008810919,0.000533536,0.00042230188,0.0005482546,0.00018253089,0.00065022724,0.002274475,0.00023164111,0.000008005776],"category_scores_gemma":[0.010221026,0.0005606529,0.00013458676,0.000551344,0.00004662031,0.0009279533,0.00030780886,0.00041059163,0.0000570625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004944234,0.0014577323,0.029555453,0.001567543,0.0010865831,0.0005866289,0.0045592585,0.120312184,0.026875516,0.04868726,0.28087118,0.48394623],"study_design_scores_gemma":[0.0013169359,0.00045490157,0.0016496261,0.00072711613,0.000032538468,0.00015087731,0.000016851258,0.98047084,0.005627942,0.007485663,0.0009856994,0.0010809959],"about_ca_topic_score_codex":0.00015046958,"about_ca_topic_score_gemma":0.000003871445,"teacher_disagreement_score":0.8601587,"about_ca_system_score_codex":0.0005657884,"about_ca_system_score_gemma":0.00043377228,"threshold_uncertainty_score":0.9996845},"labels":[],"label_agreement":null},{"id":"W4242700588","doi":"10.1109/emsoft.2015.7318273","title":"A framework for mining hybrid automata from input/output traces","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automaton; Abstraction; Inference; Cluster analysis; Theoretical computer science; Hybrid system; Domain (mathematical analysis); Automata theory; Data mining; Artificial intelligence; Machine learning","score_opus":0.09249891101697935,"score_gpt":0.319693611244333,"score_spread":0.22719470022735364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242700588","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01346795,0.000115073744,0.9649491,0.0011761712,0.0003747055,0.00013557734,0.0000065245695,0.019099643,0.00067530625],"genre_scores_gemma":[0.20523211,9.35359e-7,0.7937167,0.0007389877,0.00012379323,0.00003615593,0.0000041869976,0.000011204137,0.00013590383],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989076,0.000031085136,0.00018886816,0.0003900532,0.00022530166,0.00025707],"domain_scores_gemma":[0.9977883,0.0012066974,0.000078640405,0.0006791869,0.000101872785,0.0001452662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041078808,0.00013401445,0.00016928355,0.00007404677,0.00007787147,0.0002537982,0.0009238644,0.000065715336,0.000003926846],"category_scores_gemma":[0.0016552574,0.00011563768,0.000052955453,0.00016565032,0.000027674285,0.0002914919,0.0002299439,0.00009140855,0.00003192778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013833213,0.00010105875,0.0031902615,0.000012387618,0.000026768736,0.000024990273,0.0023341256,0.000026233436,0.000012435458,0.022108376,0.56280226,0.4093473],"study_design_scores_gemma":[0.0002588823,0.00016279274,0.0003681324,0.00009129507,0.000006704985,0.000015955871,0.000021666612,0.26316673,0.0014641678,0.72771007,0.0064769974,0.00025662084],"about_ca_topic_score_codex":0.00013178069,"about_ca_topic_score_gemma":0.0000023215098,"teacher_disagreement_score":0.7056017,"about_ca_system_score_codex":0.000027977014,"about_ca_system_score_gemma":0.00009433464,"threshold_uncertainty_score":0.47155678},"labels":[],"label_agreement":null},{"id":"W4242926184","doi":"10.1002/9780470612514","title":"Software Specification Methods","year":2006,"lang":"en","type":"book","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Software; Programming language; Software engineering","score_opus":0.03658288294643618,"score_gpt":0.32019772551635645,"score_spread":0.28361484256992026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242926184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.875282e-9,0.00013612045,0.55940205,0.000068380265,0.0001816334,0.000085337495,0.0000012910601,0.02329346,0.4168317],"genre_scores_gemma":[3.6627176e-7,0.0000032468183,0.5240803,0.00014226783,0.00013426284,0.000011327453,0.000025336016,0.000018504323,0.4755844],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985162,0.000073588235,0.00030851061,0.0006083024,0.00027097482,0.00022242907],"domain_scores_gemma":[0.9975389,0.0006882042,0.00020431871,0.0013652074,0.00014543928,0.00005788548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005371227,0.00026537952,0.00027817258,0.00021924601,0.0000840802,0.00019198355,0.0013326551,0.00030313362,0.00003364217],"category_scores_gemma":[0.00022580691,0.0002445705,0.00012360945,0.00014547042,0.00004241806,0.00014671306,0.00029806822,0.0002970237,0.00018223969],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5082065e-7,0.000006805268,0.000007697538,0.000011520966,0.0000036075344,0.000003887701,0.000007735556,8.829526e-7,8.389757e-7,0.033710465,0.76749206,0.19875436],"study_design_scores_gemma":[0.000021843072,0.0000172376,0.00004098031,0.00004834651,0.0000052475834,0.00001379313,2.61729e-8,0.0006684322,0.000067303925,0.47725073,0.52163786,0.00022822176],"about_ca_topic_score_codex":0.000029705003,"about_ca_topic_score_gemma":0.0000014348486,"teacher_disagreement_score":0.44354028,"about_ca_system_score_codex":0.00016837606,"about_ca_system_score_gemma":0.00024153251,"threshold_uncertainty_score":0.99732953},"labels":[],"label_agreement":null},{"id":"W4243225916","doi":"10.1007/978-1-4614-4325-4_6","title":"Applications","year":2012,"lang":"en","type":"book-chapter","venue":"CMS books in mathematics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","score_opus":0.04060258556210177,"score_gpt":0.27200067472071837,"score_spread":0.2313980891586166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243225916","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6949727e-7,0.0005463163,0.48561305,0.000034642344,0.000053784956,0.00025426864,0.0000020714645,0.0031991787,0.5102965],"genre_scores_gemma":[0.00020612878,0.0000535218,0.7554694,0.0001232359,0.00014662194,0.00013266552,0.000004902414,0.000058796424,0.24380477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883515,0.000006452789,0.00038639622,0.0002866325,0.00024683066,0.00023851635],"domain_scores_gemma":[0.9980945,0.00028590238,0.00023213394,0.001256181,0.00005683896,0.00007443082],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034489637,0.00025346046,0.0003148731,0.00020281546,0.000054831413,0.00007431307,0.0010159571,0.00024245642,0.000026477795],"category_scores_gemma":[0.00005351734,0.00024859587,0.00008334385,0.000040154897,0.000067367226,0.000090109555,0.00033747868,0.00034846482,0.0003263628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.574514e-8,0.000023837396,0.000007319773,0.00010049783,0.0000059302592,0.0000039599154,0.00025298825,3.459433e-7,0.000001146573,0.956516,0.0066829715,0.036404893],"study_design_scores_gemma":[0.00003159113,0.000009122878,0.0000017023115,0.00027769175,0.000009491444,0.000025416015,5.4281924e-7,0.00088978966,0.000013622557,0.8535025,0.14500108,0.0002374535],"about_ca_topic_score_codex":0.0000015745586,"about_ca_topic_score_gemma":9.245719e-7,"teacher_disagreement_score":0.2698563,"about_ca_system_score_codex":0.000079597434,"about_ca_system_score_gemma":0.000057001176,"threshold_uncertainty_score":0.9999966},"labels":[],"label_agreement":null},{"id":"W4243258316","doi":"10.1109/icse.2004.1317431","title":"Using simulation to empirically investigate test coverage criteria based on statechart","year":2004,"lang":"en","type":"article","venue":"Proceedings. 26th International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Class (philosophy); Test case; Test (biology); Code coverage; Reliability engineering; Data mining; Machine learning; Artificial intelligence; Programming language; Software; Engineering","score_opus":0.08422974191687765,"score_gpt":0.34065714063343316,"score_spread":0.2564273987165555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243258316","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03229513,0.0000023709008,0.9597696,0.0007109272,0.00043760406,0.00025103142,0.000021533331,0.0060386504,0.0004731319],"genre_scores_gemma":[0.6269628,9.2284137e-7,0.371785,0.0010915506,0.00008299291,0.000030090907,0.00000688006,0.000026668731,0.000013100618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792707,0.0000061148744,0.00036426593,0.00064025295,0.00068388303,0.00037843577],"domain_scores_gemma":[0.99854606,0.00023134166,0.00013057668,0.00024817252,0.00060598535,0.00023785842],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029776955,0.00033757594,0.00022206787,0.00052853895,0.00012122748,0.00059354544,0.00090495043,0.00010376986,0.000027320604],"category_scores_gemma":[0.0039177476,0.00035357164,0.00006459219,0.0005020994,0.000022249782,0.00054936484,0.00018209893,0.0003127035,0.000040280276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043395063,0.00021275488,0.005232646,0.000078330806,0.000023227496,0.00003407396,0.0007033468,0.9547553,0.0046818308,0.030103667,0.00075905357,0.0033723563],"study_design_scores_gemma":[0.00035292338,0.000338487,0.0016349164,0.0007722633,0.0000042714814,0.000009266514,0.000002408069,0.9839637,0.004269964,0.007850423,0.0003652812,0.00043606505],"about_ca_topic_score_codex":0.000018839823,"about_ca_topic_score_gemma":3.5495418e-7,"teacher_disagreement_score":0.5946676,"about_ca_system_score_codex":0.00040545393,"about_ca_system_score_gemma":0.00014954047,"threshold_uncertainty_score":0.99989164},"labels":[],"label_agreement":null},{"id":"W4243372325","doi":"10.22215/etd/2016-11428","title":"Test Generation from an Extended Finite State Machine as a Multiobjective Optimization Problem","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Test suite; Extended finite-state machine; Computer science; Finite-state machine; Test case; Test (biology); Model-based testing; Suite; Software; Genetic algorithm; Code coverage; Reliability engineering; Algorithm; Machine learning; Engineering; Programming language","score_opus":0.014348365568041761,"score_gpt":0.28408740907707475,"score_spread":0.269739043509033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243372325","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011817415,0.000085551255,0.9830917,0.000113803726,0.00038191985,0.00052803615,0.000069282825,0.010801028,0.003746912],"genre_scores_gemma":[0.04924862,0.00006151733,0.93817043,0.00028751732,0.0002075943,0.0002234182,0.0032311792,0.00006935017,0.008500346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978825,0.00012010702,0.00041794693,0.0009240215,0.00038539545,0.00027003363],"domain_scores_gemma":[0.9977687,0.0004934496,0.00038604683,0.00076598156,0.00046777204,0.00011803334],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023929901,0.00038066754,0.00028545293,0.00025527805,0.00022737065,0.0003928652,0.00066758407,0.0002424686,0.00007420146],"category_scores_gemma":[0.0005989398,0.00030614328,0.00007004435,0.00027441105,0.00001755094,0.00083489146,0.00006688828,0.00021355767,0.000057700126],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017756816,0.0015341108,0.0013036773,0.00010698296,0.00023101887,0.00016025649,0.012297411,0.0191494,0.006954066,0.0050708484,0.014745519,0.93826914],"study_design_scores_gemma":[0.00043453433,0.00043054417,0.00086842244,0.00021513095,0.000025538831,0.0000076032397,0.0000079028205,0.9186772,0.0092557715,0.069306046,0.00008520096,0.00068608177],"about_ca_topic_score_codex":0.0020901184,"about_ca_topic_score_gemma":0.00046847333,"teacher_disagreement_score":0.9375831,"about_ca_system_score_codex":0.0001060542,"about_ca_system_score_gemma":0.00022950966,"threshold_uncertainty_score":0.9999391},"labels":[],"label_agreement":null},{"id":"W4243778460","doi":"10.1145/2775054.2694394","title":"Dual Execution for On the Fly Fine Grained Execution Comparison","year":2015,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Debugging; Programming language; Distributed computing","score_opus":0.13166431278598673,"score_gpt":0.32846661103871233,"score_spread":0.1968022982527256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243778460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21115905,0.00025492546,0.750595,0.020132609,0.0015457283,0.0011033585,0.000025090587,0.0126746325,0.002509658],"genre_scores_gemma":[0.9101549,6.2485316e-7,0.08891773,0.0005759532,0.00017557624,0.000058711616,0.00002184598,0.000009402792,0.00008524777],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988507,0.00008906463,0.00020872749,0.00030565698,0.00029843455,0.0002474005],"domain_scores_gemma":[0.9969852,0.0018393238,0.00015349411,0.00080231385,0.00013928008,0.00008037899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082873815,0.00014605711,0.00015465227,0.00007737436,0.0001985598,0.00018384484,0.0009173615,0.000068262656,0.0000019987692],"category_scores_gemma":[0.003230011,0.00010055397,0.000048492046,0.00021705242,0.000049421622,0.00021364867,0.00018182409,0.00012298467,0.000031594467],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013013808,0.00023300282,0.004152354,0.000033149914,0.000032177308,0.0000106267435,0.0033777256,0.0005880873,0.00031324718,0.08278324,0.86892307,0.03942316],"study_design_scores_gemma":[0.0020956574,0.0036926176,0.009190445,0.0003328668,0.000083249,0.000047862908,0.00023933884,0.47520882,0.01649473,0.44269553,0.048749458,0.0011694285],"about_ca_topic_score_codex":0.000098947385,"about_ca_topic_score_gemma":0.000020722771,"teacher_disagreement_score":0.8201736,"about_ca_system_score_codex":0.000042735464,"about_ca_system_score_gemma":0.0000508453,"threshold_uncertainty_score":0.41004717},"labels":[],"label_agreement":null},{"id":"W4243891992","doi":"10.1109/icse.2013.6606688","title":"On extracting unit tests from interactive live programming sessions","year":2013,"lang":"en","type":"article","venue":"2013 35th International Conference on Software Engineering (ICSE)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Session (web analytics); Unit testing; Cluster analysis; Software testing; Software; Software engineering; Machine learning; Programming language; World Wide Web","score_opus":0.042236101726807265,"score_gpt":0.29588421699843037,"score_spread":0.2536481152716231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243891992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072791256,0.00002878576,0.9129789,0.0009526746,0.0019413859,0.0004400617,0.000029256382,0.009968048,0.0008696158],"genre_scores_gemma":[0.68166035,0.00000909034,0.31747308,0.0002455657,0.00015352253,0.00015201526,0.000032868287,0.000034102854,0.00023939926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788105,0.00005015267,0.00038954706,0.00066712813,0.0005843462,0.00042778623],"domain_scores_gemma":[0.9964764,0.0018823736,0.00023594922,0.00061982684,0.00057786505,0.00020758343],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019007912,0.00038101754,0.0002566722,0.00034523255,0.00014807103,0.0007022059,0.0013413565,0.00014989368,0.0004033691],"category_scores_gemma":[0.0026401507,0.00036053848,0.00009796749,0.00023250324,0.000035388402,0.00090551673,0.00033709864,0.0007618796,0.0007536424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009496175,0.001667734,0.040260706,0.000110600275,0.0007665096,0.00031313612,0.008225133,0.01412296,0.0026479766,0.20829567,0.0630193,0.6604753],"study_design_scores_gemma":[0.0007622468,0.00058835483,0.03890965,0.0032549386,0.000022517124,0.000055879347,0.00012561386,0.9060483,0.00159714,0.042811155,0.00419548,0.001628741],"about_ca_topic_score_codex":0.0008704609,"about_ca_topic_score_gemma":0.0000089352825,"teacher_disagreement_score":0.89192533,"about_ca_system_score_codex":0.0001675819,"about_ca_system_score_gemma":0.00009552713,"threshold_uncertainty_score":0.99988467},"labels":[],"label_agreement":null},{"id":"W4246285000","doi":"10.32920/ryerson.14663895.v1","title":"Whole program analysis of Java programs for virtual calls and exception handling","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Call stack; Computer science; Java; Exception handling; Stack (abstract data type); Operating system; Static analysis; Virtual machine; strictfp; Code (set theory); Program analysis; Programming language; Real time Java","score_opus":0.04273522055698996,"score_gpt":0.3202934536791171,"score_spread":0.27755823312212713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246285000","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08045076,0.00018198078,0.91277397,0.00009086395,0.00013124425,0.00066620915,0.000005957396,0.005646595,0.000052442796],"genre_scores_gemma":[0.47149673,0.000011039114,0.52801234,0.000023186813,0.00002406986,0.00025319573,0.000110592126,0.000008136781,0.00006071078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983749,0.00005174249,0.0003938401,0.0007107169,0.0002442683,0.00022455904],"domain_scores_gemma":[0.9983491,0.0002291141,0.0002533654,0.0007346272,0.00035987102,0.00007392349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005376365,0.00020819073,0.0005271205,0.00033191618,0.00006587045,0.00037070707,0.000509313,0.000221526,0.0000021131564],"category_scores_gemma":[0.00022145954,0.00019059815,0.0002719121,0.0006347785,0.00006638734,0.00011365535,0.00096827064,0.00018205788,2.5373956e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047967837,0.00021499331,0.010864307,0.00019982092,0.00055471,0.0000030999406,0.0007532835,0.00038105348,0.00015282916,0.0004906565,0.0005625103,0.9858179],"study_design_scores_gemma":[0.00026211777,0.0006265259,0.009166578,0.0005558266,0.0008766961,0.000005529261,0.000034143155,0.9732003,0.0012903046,0.012964375,0.00039263399,0.00062495546],"about_ca_topic_score_codex":0.00028344378,"about_ca_topic_score_gemma":0.00006213302,"teacher_disagreement_score":0.98519295,"about_ca_system_score_codex":0.000028824204,"about_ca_system_score_gemma":0.00010448474,"threshold_uncertainty_score":0.7772367},"labels":[],"label_agreement":null},{"id":"W4246412311","doi":"10.1002/jcd.21602","title":"Variable strength covering arrays","year":2018,"lang":"en","type":"article","venue":"Journal of Combinatorial Designs","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hypergraph; Mathematics; Variable (mathematics); Homomorphism; Combinatorics; Order (exchange); Discrete mathematics; Mathematical analysis","score_opus":0.02761422325529419,"score_gpt":0.26846090353492696,"score_spread":0.24084668027963277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246412311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041027097,0.000047412883,0.9862108,0.00010024548,0.006119128,0.00004949672,3.8689683e-7,0.00090722175,0.0024625557],"genre_scores_gemma":[0.59934014,0.0000033556598,0.39956704,0.00007909162,0.0009766314,8.7374787e-7,8.53899e-8,0.000008624661,0.000024173321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873424,0.00009908579,0.00038418052,0.0001417491,0.0004066476,0.000234123],"domain_scores_gemma":[0.9982215,0.0004117907,0.000361926,0.0003436292,0.0005313782,0.00012976209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010375361,0.00012117376,0.00023753122,0.00015512851,0.0001386648,0.00019639873,0.00095113396,0.000074836986,0.000012176743],"category_scores_gemma":[0.0008587973,0.000105561936,0.00007667505,0.00040309076,0.000053445012,0.00052539626,0.00011804194,0.00022367407,0.000013520885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099454635,0.00041736115,0.0015777968,0.000024517201,0.00010038092,0.00011911608,0.0008096671,0.00004728708,0.007409677,0.82815325,0.14643988,0.014801609],"study_design_scores_gemma":[0.00083434884,0.0016795696,0.00018708405,0.00014733913,0.00001760451,0.00020245492,0.0000030681024,0.0036526138,0.017543543,0.9635979,0.01191993,0.00021454295],"about_ca_topic_score_codex":0.000012603862,"about_ca_topic_score_gemma":1.0696446e-7,"teacher_disagreement_score":0.5952374,"about_ca_system_score_codex":0.000071718045,"about_ca_system_score_gemma":0.0002502336,"threshold_uncertainty_score":0.43046907},"labels":[],"label_agreement":null},{"id":"W4246883339","doi":"10.22215/etd/2014-10588","title":"Mapping ACL to JavaMOP: A Feasibility Study","year":2014,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"USable; Suite; Computer science; Software engineering; Test suite; Debugging; Java; Test case; Programming language; Reliability engineering; Engineering; Machine learning; World Wide Web","score_opus":0.04234093436177168,"score_gpt":0.33030948437993707,"score_spread":0.2879685500181654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246883339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21754129,0.000034145025,0.714783,0.00018188656,0.0013482592,0.0018536536,0.0000013706626,0.03627996,0.027976414],"genre_scores_gemma":[0.75407207,4.9897653e-7,0.23698656,0.0004814489,0.000100171346,0.00015509888,0.000023692366,0.00002987367,0.008150578],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99788994,0.000115400384,0.00036597092,0.0008988756,0.0004306415,0.00029918342],"domain_scores_gemma":[0.9977377,0.00023974263,0.00013902073,0.0015162523,0.00022653797,0.00014071747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088946294,0.00029138493,0.0003687276,0.00031739668,0.00014263173,0.00028048118,0.0015434561,0.00015122659,0.000016689026],"category_scores_gemma":[0.0008340782,0.00026241023,0.00009031529,0.0005756114,0.0000063534007,0.00011621567,0.00022030123,0.0002521533,0.00016061196],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059741244,0.002085264,0.09592248,0.00049484137,0.0001506883,0.00007709988,0.036795832,0.000016487233,0.00021646911,0.003255236,0.43487546,0.4260504],"study_design_scores_gemma":[0.001376983,0.0037568922,0.8250576,0.0014837744,0.00007622767,0.0000303731,0.001629337,0.0114534795,0.0018673402,0.13945308,0.009067533,0.004747356],"about_ca_topic_score_codex":0.0004336458,"about_ca_topic_score_gemma":0.0002969858,"teacher_disagreement_score":0.72913516,"about_ca_system_score_codex":0.00007962749,"about_ca_system_score_gemma":0.00010098035,"threshold_uncertainty_score":0.99998283},"labels":[],"label_agreement":null},{"id":"W4246889973","doi":"10.22215/etd/2005-08236","title":"Technique and automation for testing of commercial-off-the-shelf components","year":2005,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Computer science; Automation; Engineering; Mechanical engineering","score_opus":0.039032232194455584,"score_gpt":0.30262781846636155,"score_spread":0.263595586271906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246889973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010955881,0.00031814608,0.9698661,0.00035815247,0.00028337876,0.0026963707,0.000012192702,0.010801528,0.004708272],"genre_scores_gemma":[0.10407103,0.000009928221,0.8945558,0.00012364739,0.00006783114,0.00059206225,0.00011088427,0.000026731232,0.00044205337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988639,0.00004516229,0.0003946123,0.00031153375,0.0002065961,0.00017821426],"domain_scores_gemma":[0.9976839,0.0011531477,0.00038452345,0.00045673424,0.00028607837,0.000035643283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005536596,0.00020320484,0.0002734909,0.0001697297,0.00019018703,0.00009139403,0.0006449002,0.00019163497,0.0000011896318],"category_scores_gemma":[0.0006162011,0.00016271889,0.00006147009,0.00025071076,0.000034085428,0.00015363858,0.000082904735,0.00015950408,9.56547e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015519594,0.00010141039,0.0015276485,0.00050355773,0.000028382985,9.032216e-7,0.00078050635,0.0000072783487,0.0034059882,0.0080182385,0.013689035,0.9719215],"study_design_scores_gemma":[0.0014364864,0.0012900905,0.12969625,0.0054153074,0.00022517482,0.00015244642,0.00009606263,0.49432892,0.13878721,0.2130158,0.012927715,0.0026285439],"about_ca_topic_score_codex":0.00012725811,"about_ca_topic_score_gemma":0.000033412758,"teacher_disagreement_score":0.969293,"about_ca_system_score_codex":0.00002883619,"about_ca_system_score_gemma":0.00007000026,"threshold_uncertainty_score":0.6635484},"labels":[],"label_agreement":null},{"id":"W4246930860","doi":"10.22215/etd/2007-08494","title":"A UML profile for developing airworthiness-compliant (RTCA DO-178B) safety-critical software","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage","funders":"","keywords":"Airworthiness; Engineering; Computer science; Aeronautics; Political science; Certification","score_opus":0.032402321004011324,"score_gpt":0.36067874967522084,"score_spread":0.32827642867120954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246930860","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016266151,0.0003993069,0.97170585,0.00027304734,0.0016795604,0.00087953,0.000025172467,0.01910059,0.0057742805],"genre_scores_gemma":[0.003535773,0.000015314432,0.98908305,0.00065846666,0.00026063566,0.0003583735,0.0005651274,0.000092550144,0.0054306984],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964899,0.000042551426,0.0008181168,0.0011649616,0.00062525045,0.0008592463],"domain_scores_gemma":[0.99518514,0.0024422389,0.00024990487,0.0009585785,0.0009932531,0.00017086153],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000876945,0.00059166766,0.0006397383,0.00045887087,0.0004981544,0.0004383006,0.00157149,0.0005802746,0.000024193956],"category_scores_gemma":[0.0045758304,0.00054597575,0.0002567799,0.00067890796,0.000056521145,0.00036061078,0.00019062513,0.0004989796,0.000066388304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107067746,0.0002111742,0.00078644464,0.0025684505,0.0001015587,0.00011999924,0.0017045161,0.0000057547754,0.000045847246,0.202869,0.17051445,0.6209657],"study_design_scores_gemma":[0.0018810909,0.001017474,0.012497513,0.010225333,0.00023621821,0.00040561886,0.00024691274,0.034674976,0.014337449,0.86100394,0.057822805,0.0056506805],"about_ca_topic_score_codex":0.00007213248,"about_ca_topic_score_gemma":0.00005725556,"teacher_disagreement_score":0.65813494,"about_ca_system_score_codex":0.00018010402,"about_ca_system_score_gemma":0.0006827835,"threshold_uncertainty_score":0.9996992},"labels":[],"label_agreement":null},{"id":"W4247047556","doi":"10.1145/2345156.2254091","title":"Parallelizing top-down interprocedural analyses","year":2012,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reachability; Scalability; Call graph; Graph; Modular design; Context (archaeology); Parallelism (grammar); Programming language; Top-down and bottom-up design; Static analysis; Theoretical computer science; Parallel computing; Database","score_opus":0.08809835399604228,"score_gpt":0.36376495046101753,"score_spread":0.27566659646497527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247047556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54186845,0.0035512773,0.41313732,0.002990159,0.0017665257,0.0003070557,0.0000049340874,0.027932314,0.008441951],"genre_scores_gemma":[0.78314054,0.0000044103213,0.21598691,0.00062307675,0.00016981889,0.000009423632,0.0000026450205,0.000008010984,0.000055171753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988362,0.000052073046,0.00020237896,0.0002589495,0.00021586324,0.00043449242],"domain_scores_gemma":[0.9981892,0.00069701474,0.000112009344,0.0008191588,0.000047046906,0.00013558663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031626233,0.00015998188,0.00017327482,0.0001284529,0.00012969547,0.00019291647,0.0014321749,0.000058648133,0.00001869301],"category_scores_gemma":[0.0011861268,0.00013078377,0.00006314043,0.00028757678,0.00003737568,0.00086129305,0.00050719344,0.00013587029,0.00010849191],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002015271,0.00032562437,0.6872506,0.00014515995,0.00015081996,0.00005200686,0.009297018,0.00013745356,0.0024059692,0.009367354,0.10844045,0.18240741],"study_design_scores_gemma":[0.0024970893,0.0016474469,0.5251513,0.0018018454,0.00049618236,0.0010562253,0.000773296,0.12933548,0.10145043,0.17087734,0.057332657,0.0075806906],"about_ca_topic_score_codex":0.000163613,"about_ca_topic_score_gemma":0.0000058659316,"teacher_disagreement_score":0.24127206,"about_ca_system_score_codex":0.000023247687,"about_ca_system_score_gemma":0.000025223902,"threshold_uncertainty_score":0.5333207},"labels":[],"label_agreement":null},{"id":"W4247094842","doi":"10.1109/icse.2013.6606563","title":"Comparing Multi-Point Stride Coverage and dataflow coverage","year":2013,"lang":"en","type":"article","venue":"2013 35th International Conference on Software Engineering (ICSE)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Computer science; Dataflow; Overhead (engineering); Tuple; Point (geometry); Parallel computing; Algorithm; Programming language; Mathematics","score_opus":0.04861954004122281,"score_gpt":0.26537905002441176,"score_spread":0.21675950998318894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247094842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026524559,0.000057053625,0.96691704,0.00043603967,0.00081797363,0.0002549504,0.000025929503,0.0046049724,0.00036145843],"genre_scores_gemma":[0.76946473,0.00008491728,0.22974423,0.00027389926,0.00008534682,0.000060294187,0.0000349181,0.00002751373,0.00022414126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982516,0.000031120588,0.0003759116,0.0005327924,0.00042205362,0.00038651712],"domain_scores_gemma":[0.9983988,0.0003448586,0.00013894637,0.0006223443,0.00029089357,0.00020417552],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025575224,0.00033966763,0.0002932111,0.00026285375,0.000105863845,0.0007462526,0.0011441162,0.000110826295,0.00011367368],"category_scores_gemma":[0.00074938004,0.00033998358,0.000061447805,0.00015245091,0.000042258253,0.0009695771,0.0005467702,0.00042252443,0.000180561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071900744,0.0010906511,0.19351965,0.00047645954,0.00069997343,0.00026967618,0.0030438693,0.04176726,0.003044912,0.42233276,0.14608072,0.18760216],"study_design_scores_gemma":[0.0006282212,0.00009799073,0.026121115,0.00033365862,0.0000062063386,0.00005316059,0.0000046887517,0.96410304,0.0004631512,0.006227108,0.0013795083,0.000582161],"about_ca_topic_score_codex":0.00049004063,"about_ca_topic_score_gemma":0.000007876253,"teacher_disagreement_score":0.92233574,"about_ca_system_score_codex":0.00011991146,"about_ca_system_score_gemma":0.000060718903,"threshold_uncertainty_score":0.9999052},"labels":[],"label_agreement":null},{"id":"W4247417056","doi":"10.1145/2070337.2070357","title":"Enhancing spark's contract checking facilities using symbolic execution","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Symbolic execution; SPARK (programming language); Software engineering; Programming language; Usability; Automation; Model checking; Design by contract; Software; Formal methods; Software development; Software construction; Operating system; Engineering","score_opus":0.08202945841302203,"score_gpt":0.27001853384797886,"score_spread":0.18798907543495683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247417056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12157861,0.00006270598,0.86119986,0.000015079668,0.00018067018,0.00007720228,4.3994217e-7,0.008990125,0.007895328],"genre_scores_gemma":[0.6727907,0.000001643417,0.32696968,0.00009900211,0.000027393602,0.0000043741984,2.7173613e-7,0.0000053773765,0.00010156006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990006,0.000040173927,0.00021351136,0.00028502088,0.00016390697,0.0002967742],"domain_scores_gemma":[0.99925536,0.00011412847,0.00007712385,0.00041319415,0.00007669804,0.000063483014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003810906,0.00013074002,0.00014822662,0.00011247107,0.00015079076,0.00010497116,0.00041310585,0.00006130398,0.00003790786],"category_scores_gemma":[0.00019001719,0.00011947241,0.000051252588,0.00018574117,0.000037578902,0.00049924204,0.00014582813,0.00010373808,0.000019934545],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058155496,0.0007236305,0.10175408,0.000414292,0.00020596193,0.00031024017,0.098748855,0.000107215754,0.12037374,0.42227414,0.0059091332,0.24912055],"study_design_scores_gemma":[0.0004686875,0.0002361529,0.02348559,0.00048352202,0.000027593906,0.00036649016,0.00020455022,0.21015352,0.5903672,0.17196998,0.00087989296,0.0013568252],"about_ca_topic_score_codex":0.0021984854,"about_ca_topic_score_gemma":0.000019425323,"teacher_disagreement_score":0.5512121,"about_ca_system_score_codex":0.00005057065,"about_ca_system_score_gemma":0.000052010033,"threshold_uncertainty_score":0.48719436},"labels":[],"label_agreement":null},{"id":"W4248114548","doi":"10.1109/sbst.2015.20","title":"JTExpert at the Third Unit Testing Tool Competition","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Unit testing; Test suite; Computer science; Java; Suite; CONTEST; Ranking (information retrieval); Source code; Software testing; Programming language; Code coverage; Code (set theory); Software quality; Software; Competition (biology); Test case; Software engineering; Artificial intelligence; Machine learning; Software development; Set (abstract data type)","score_opus":0.09944752895663983,"score_gpt":0.2917210306793673,"score_spread":0.19227350172272745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248114548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023682779,0.000118398726,0.86362827,0.0034394239,0.00032751562,0.00018053016,6.3934226e-7,0.023955207,0.08466721],"genre_scores_gemma":[0.53831935,9.810276e-7,0.45629913,0.002640605,0.00009698929,0.000024753677,0.0000021848032,0.00000945576,0.0026065728],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991962,0.00006127513,0.00012877247,0.00020011037,0.00023929539,0.00017437225],"domain_scores_gemma":[0.9985791,0.0005860395,0.000047862726,0.0005646169,0.00016391592,0.000058474634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056950905,0.0000880628,0.00007400726,0.00003515913,0.00018593551,0.00014280512,0.00061371847,0.00003333377,0.000009379618],"category_scores_gemma":[0.0009646445,0.000054904664,0.000022825421,0.0003320991,0.000047957863,0.00018514716,0.00043006497,0.00008661791,0.00017525634],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071305876,0.00008786128,0.049811732,0.000012119161,0.000012229113,0.000026549726,0.0018081091,0.0001755761,0.0005934342,0.11602896,0.736361,0.09507527],"study_design_scores_gemma":[0.0008966806,0.0006354893,0.016901067,0.00022368903,0.00001308288,0.00060544285,0.000096815034,0.42505148,0.010237316,0.4419246,0.10225852,0.0011558348],"about_ca_topic_score_codex":0.00026948634,"about_ca_topic_score_gemma":0.000013653655,"teacher_disagreement_score":0.6341025,"about_ca_system_score_codex":0.000047305402,"about_ca_system_score_gemma":0.00005847906,"threshold_uncertainty_score":0.22526242},"labels":[],"label_agreement":null},{"id":"W4248354362","doi":"10.22215/etd/2018-13273","title":"Comparison of Approaches to Category Partition Specifications, Selection Criteria, and the Impact of the ‘Error’ and ‘Single’ Annotations using Industrial Case Studies","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Partition (number theory); Computer science; Selection (genetic algorithm); Code (set theory); Reliability engineering; Regression testing; Code coverage; Test (biology); White-box testing; Software; Data mining; Machine learning; Programming language; Engineering; Mathematics; Software system; Software construction","score_opus":0.5374655900029118,"score_gpt":0.4350745023918684,"score_spread":0.10239108761104343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248354362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97119564,0.00037731524,0.026978245,0.00014063268,0.00024465422,0.0006084912,0.000008813832,0.00030460424,0.00014158327],"genre_scores_gemma":[0.97483903,0.000005747357,0.024977604,0.0000065018085,0.000073604984,0.00003401808,0.000012005355,0.000009235652,0.000042229658],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988107,0.00021454015,0.00042774185,0.00027232734,0.00016212492,0.00011256936],"domain_scores_gemma":[0.99846596,0.0003931042,0.000465457,0.00032938793,0.00031406234,0.00003201403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051521766,0.00016513834,0.00033411052,0.00016384816,0.00033213012,0.000096377466,0.0002061794,0.00011823972,0.00000168591],"category_scores_gemma":[0.0006129398,0.00009706364,0.0000658233,0.0005094976,0.00021309168,0.0001491084,0.00008249473,0.0001453095,1.6005983e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016109408,0.002489091,0.14732005,0.0016919315,0.0024544897,0.000015039496,0.4679874,0.002693541,0.015856387,0.044291236,0.13042033,0.18316956],"study_design_scores_gemma":[0.004068827,0.0032430948,0.08517571,0.0027558226,0.0014762532,0.0016537888,0.027919678,0.63631165,0.10250602,0.13246341,0.000105296866,0.0023204435],"about_ca_topic_score_codex":0.001169581,"about_ca_topic_score_gemma":0.00027973333,"teacher_disagreement_score":0.6336181,"about_ca_system_score_codex":0.00005770031,"about_ca_system_score_gemma":0.0001052331,"threshold_uncertainty_score":0.39581403},"labels":[],"label_agreement":null},{"id":"W4248501463","doi":"10.1002/spe.839","title":"Oto, a generic and extensible tool for marking programming assignments","year":2007,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Université du Québec à Montréal","keywords":"Computer science; Extensibility; Workload; Task (project management); Programming language; Automation; Process (computing); Software engineering; Source code; Code (set theory); Operating system; Engineering; Systems engineering","score_opus":0.028268078525108157,"score_gpt":0.32067617705254514,"score_spread":0.292408098527437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248501463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032496933,0.00078141206,0.9633939,0.00020731262,0.00015963898,0.00035420872,7.7170426e-7,0.0025513554,0.000054435426],"genre_scores_gemma":[0.26146787,0.000054097865,0.73738706,0.0008843614,0.000049595805,0.000117913776,0.0000010340757,0.000011893619,0.00002619547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851936,0.000035086563,0.00023372463,0.00053737545,0.00023776611,0.00043670952],"domain_scores_gemma":[0.99721,0.0020067755,0.00015904076,0.0003566458,0.00014782738,0.000119666074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010711784,0.00016744676,0.00015067821,0.00008916103,0.0003888928,0.0003799297,0.0002868794,0.000072988136,0.0000014594135],"category_scores_gemma":[0.0045168395,0.00015887378,0.00002800332,0.00027729778,0.00007500733,0.0013171566,0.00028039058,0.000117727875,0.0000018152926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045711568,0.000069682115,0.013570044,0.000047368576,0.000012081983,0.000053337717,0.0052417414,7.350993e-7,0.0005017083,0.0010762203,0.0008455975,0.9785358],"study_design_scores_gemma":[0.0043331548,0.004361338,0.042313278,0.0015408483,0.00026045795,0.006914927,0.0062930193,0.02420013,0.030315932,0.086012825,0.7872845,0.0061695785],"about_ca_topic_score_codex":0.000052338426,"about_ca_topic_score_gemma":0.0000011321305,"teacher_disagreement_score":0.9723662,"about_ca_system_score_codex":0.000030068964,"about_ca_system_score_gemma":0.00004063363,"threshold_uncertainty_score":0.64786845},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04962212616320409,"score_gpt":0.3113156837427992,"score_spread":0.2616935575795951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248647026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10421861,0.00011800311,0.8926222,0.00025071763,0.00007623665,0.0001703985,0.000035088204,0.0024894767,0.000019304935],"genre_scores_gemma":[0.5423722,0.000004415052,0.45748457,0.00009513962,0.000016086562,0.000001967961,0.000016352255,0.0000042731854,0.000004936439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824095,0.0001821735,0.00045151537,0.00065828755,0.00025869315,0.00020835357],"domain_scores_gemma":[0.99602854,0.0009673744,0.0003361685,0.002271335,0.00033010935,0.000066441986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001839679,0.00016834734,0.00026240782,0.00011894391,0.0003132579,0.0001804482,0.0010653164,0.000057439996,0.0000026565374],"category_scores_gemma":[0.007380912,0.0001226545,0.000055037694,0.0012314703,0.00013452508,0.00040474415,0.00033608152,0.00016642248,5.669326e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001184047,0.00012726072,0.15469313,0.00009100228,0.000036770856,0.0000022724764,0.0005318355,0.0032084605,0.0015679789,0.00007493391,0.00033072068,0.8393238],"study_design_scores_gemma":[0.00007157257,0.00004548904,0.16671772,0.000027230859,0.00006940669,0.000008101148,0.0000015063233,0.8212285,0.00018616911,0.01148616,0.000019759174,0.00013835994],"about_ca_topic_score_codex":0.00078329147,"about_ca_topic_score_gemma":0.0000042126453,"teacher_disagreement_score":0.8391854,"about_ca_system_score_codex":0.000032877742,"about_ca_system_score_gemma":0.00009130535,"threshold_uncertainty_score":0.8836174},"labels":[],"label_agreement":null},{"id":"W4249894557","doi":"10.22215/etd/2010-08791","title":"On the round trip path strategy for state based testing","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Path (computing); Computer science; Humanities; Political science; Art; Operating system","score_opus":0.06221995767341325,"score_gpt":0.3088627045222606,"score_spread":0.24664274684884735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249894557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023363167,0.00003505854,0.9417506,0.00032064551,0.0010511922,0.0012111817,0.00002040749,0.016102726,0.016145034],"genre_scores_gemma":[0.3975798,0.0000013366868,0.58986247,0.0013966853,0.00015403109,0.0005667727,0.00019351173,0.0000846771,0.010160726],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986126,0.000048995465,0.00026705075,0.00048406405,0.00028629636,0.00030100177],"domain_scores_gemma":[0.99403715,0.004577606,0.00024858583,0.00077774655,0.00030350056,0.000055431876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007056907,0.0002707391,0.00020361024,0.00011787433,0.00029116316,0.00050398597,0.001075674,0.00018588154,0.000011517643],"category_scores_gemma":[0.0021737101,0.00017471494,0.00009553874,0.00028205416,0.000017475533,0.00010088875,0.000025413474,0.000471079,0.00001096508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114463015,0.00035069432,0.00027269573,0.00040914144,0.0000570426,0.00002899621,0.0007929585,0.00046756832,0.0011036985,0.0890136,0.18678604,0.7206031],"study_design_scores_gemma":[0.0003437206,0.0008322154,0.0010042433,0.00043747787,0.000021634767,0.000004189803,0.000018172193,0.30862698,0.006704037,0.6805167,0.0007673306,0.0007232438],"about_ca_topic_score_codex":0.00020994233,"about_ca_topic_score_gemma":0.00009224489,"teacher_disagreement_score":0.71987987,"about_ca_system_score_codex":0.000028345628,"about_ca_system_score_gemma":0.00036344634,"threshold_uncertainty_score":0.71246684},"labels":[],"label_agreement":null},{"id":"W4250487516","doi":"10.1145/566172.566183","title":"Investigating the use of analysis contracts to support fault isolation in object oriented code","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Isolation (microbiology); Object-oriented programming; Fault detection and isolation; Software engineering; Programming language; Artificial intelligence","score_opus":0.08638116512189156,"score_gpt":0.29273032185097225,"score_spread":0.2063491567290807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250487516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18048307,0.0000046231876,0.816651,0.00076017587,0.000031285024,0.00014849564,0.0000018022429,0.0015525147,0.00036702922],"genre_scores_gemma":[0.71147245,7.580659e-7,0.28762054,0.0007875808,0.0000048417373,0.0000075477165,0.0000013132632,0.000002816576,0.000102110054],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903363,0.000080445745,0.00029328876,0.0002195954,0.00021039942,0.00016262736],"domain_scores_gemma":[0.9985475,0.00070556294,0.00010911739,0.00046899923,0.00011380181,0.000055028155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039419805,0.00008061607,0.00015811727,0.00026515665,0.000052409694,0.00007949739,0.00032822203,0.00003541088,0.000016090928],"category_scores_gemma":[0.0017371998,0.000057366193,0.00004875192,0.002086082,0.000028646016,0.00028096425,0.000102617145,0.00008610025,0.0000069882085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037394157,0.00017742226,0.85869193,0.000011485812,0.00011194042,0.000012900517,0.0086477995,0.019744031,0.0012771637,0.0050820378,0.055389117,0.050850403],"study_design_scores_gemma":[0.000090696216,0.000082059734,0.04057297,0.000020171086,0.000020323583,0.0000028644247,0.000006721702,0.9565708,0.0010958364,0.0008458542,0.00058893295,0.00010274759],"about_ca_topic_score_codex":0.00089327584,"about_ca_topic_score_gemma":0.00032437668,"teacher_disagreement_score":0.93682677,"about_ca_system_score_codex":0.000024616907,"about_ca_system_score_gemma":0.00001627515,"threshold_uncertainty_score":0.23393255},"labels":[],"label_agreement":null},{"id":"W4251131822","doi":"10.1145/2786763.2694394","title":"Dual Execution for On the Fly Fine Grained Execution Comparison","year":2015,"lang":"en","type":"article","venue":"ACM SIGARCH Computer Architecture News","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Debugging; Reuse; Identification (biology); Distributed computing; Programming language","score_opus":0.07261865442083672,"score_gpt":0.30802820684058124,"score_spread":0.23540955241974454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251131822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012450283,0.000059807648,0.9632173,0.017553123,0.00074168626,0.0008519,0.000006945823,0.0048396713,0.000279252],"genre_scores_gemma":[0.44477147,0.0000010469354,0.5514228,0.0027205518,0.00080498424,0.0001624283,0.000031256055,0.000028321687,0.0000571573],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732083,0.0003218969,0.00042176625,0.00072902,0.0006317702,0.000574707],"domain_scores_gemma":[0.99487555,0.0026637297,0.00018579421,0.001797641,0.0002515539,0.00022572509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010655714,0.00035735386,0.0003493406,0.00023764264,0.0003346805,0.00029577824,0.0020226138,0.00012448967,0.0000019622578],"category_scores_gemma":[0.0014901247,0.00024493955,0.00017216343,0.0005035924,0.000118020165,0.0001427467,0.00084816,0.00049029005,0.000022108352],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012643043,0.00019612923,0.0005782672,0.000023702672,0.00004040645,0.000013226147,0.003985554,0.0038543409,0.00020848641,0.018171746,0.52047765,0.45232403],"study_design_scores_gemma":[0.001752109,0.0032966563,0.0016644701,0.00019961463,0.000027013628,0.00015224551,0.000017161025,0.34615186,0.0030225962,0.56564903,0.07723372,0.0008335073],"about_ca_topic_score_codex":0.00009880206,"about_ca_topic_score_gemma":0.00003519346,"teacher_disagreement_score":0.5474773,"about_ca_system_score_codex":0.000100980054,"about_ca_system_score_gemma":0.0001409575,"threshold_uncertainty_score":0.9988345},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0432607937311662,"score_gpt":0.25965007470477164,"score_spread":0.21638928097360544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251245562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109989874,0.00013108655,0.8794623,0.00017946641,0.000102019076,0.00047828717,0.000006738712,0.009595705,0.00005452879],"genre_scores_gemma":[0.587909,0.000007565455,0.41185686,0.000055155764,0.000030004601,0.000105118816,0.000006471044,0.000010872967,0.000018956809],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871415,0.0000613941,0.00026663113,0.00054173206,0.00019221171,0.00022387886],"domain_scores_gemma":[0.9975461,0.0012199004,0.00013732674,0.00058126025,0.00042227752,0.000093146075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005395967,0.00016619277,0.00019157518,0.00006603947,0.0004639795,0.00009845254,0.0002446733,0.000083183935,3.41911e-7],"category_scores_gemma":[0.0023167229,0.00013866829,0.000031008298,0.0003443139,0.0001514578,0.00031228794,0.00003372233,0.00011273407,0.000001716273],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000298989,0.001251404,0.76139593,0.0035941964,0.000089000954,0.00006255285,0.012119901,0.022376474,0.0023207418,0.0064689494,0.015539887,0.17448194],"study_design_scores_gemma":[0.0019489042,0.0018419396,0.3484124,0.0010584894,0.000063582476,0.0013146644,0.00005963991,0.6089415,0.0014322492,0.03019264,0.002964646,0.0017693316],"about_ca_topic_score_codex":0.00022968517,"about_ca_topic_score_gemma":0.0000012514162,"teacher_disagreement_score":0.586565,"about_ca_system_score_codex":0.000056758847,"about_ca_system_score_gemma":0.00010952802,"threshold_uncertainty_score":0.5654729},"labels":[],"label_agreement":null},{"id":"W4252446732","doi":"10.1145/949415.949425","title":"*J","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Compiler; Java; Programming language; Just-in-time compilation; Metric (unit); Software engineering","score_opus":0.01687873843337306,"score_gpt":0.24021438045611965,"score_spread":0.22333564202274658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252446732","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023204608,0.000014062941,0.86653966,0.00009809193,0.000051589264,0.000011378453,7.624569e-9,0.011743508,0.12130967],"genre_scores_gemma":[0.38368446,3.1767e-7,0.6154587,0.00033598838,0.0000023961811,0.0000015253898,1.4531755e-8,9.669617e-7,0.0005155798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99976385,0.000012114108,0.00003208483,0.00007973317,0.00004548476,0.000066750836],"domain_scores_gemma":[0.99969345,0.000048698043,0.000006373519,0.00021847415,0.0000127341145,0.000020261243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010448907,0.000024053452,0.000022757878,0.000019396535,0.000023992947,0.000031430147,0.00017154109,0.000009833476,0.00001473308],"category_scores_gemma":[0.00014234999,0.000019243787,0.000009890186,0.00010283241,0.0000048311163,0.00006754808,0.000019492976,0.000019387206,0.00005903797],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7581954e-8,0.0000074917057,0.0020651782,4.8763565e-7,5.5458975e-7,0.000002442632,0.00002324133,4.9663146e-7,0.000017376233,0.92432886,0.057610586,0.015943244],"study_design_scores_gemma":[0.000051669445,0.000026736443,0.0006529884,0.0000035565085,3.9288778e-7,0.00004530838,5.4414494e-7,0.0030722101,0.007383251,0.940911,0.047744688,0.00010764532],"about_ca_topic_score_codex":0.000004714963,"about_ca_topic_score_gemma":1.4058357e-7,"teacher_disagreement_score":0.38345242,"about_ca_system_score_codex":0.0000035341902,"about_ca_system_score_gemma":0.000011043351,"threshold_uncertainty_score":0.07847389},"labels":[],"label_agreement":null},{"id":"W4253500466","doi":"10.22215/etd/2012-06901","title":"Improving testability with stateless method extraction","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Testability; Stateless protocol; Computer science; Mathematics; Algorithm; Statistics","score_opus":0.01902002175544895,"score_gpt":0.32283269567276585,"score_spread":0.3038126739173169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253500466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005350315,0.00009391369,0.9748171,0.000020124291,0.00042322223,0.00024009075,0.0000014371478,0.013444633,0.005609157],"genre_scores_gemma":[0.10433557,0.0000022728473,0.89349097,0.000030566327,0.000069278634,0.00006981318,0.000059131446,0.0000302619,0.001912141],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984169,0.000098230026,0.000256019,0.0005538077,0.0003431598,0.00033188364],"domain_scores_gemma":[0.99801946,0.0005284841,0.00029785887,0.00079657463,0.00025645178,0.00010116975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079601264,0.00027274605,0.0002621184,0.00014780479,0.00012841655,0.00019103702,0.00055449875,0.00020381378,0.000024289404],"category_scores_gemma":[0.00022021901,0.00020969064,0.00005462717,0.00030125224,0.000012494488,0.0006109185,0.000049798142,0.00037906284,0.000013972364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021319165,0.00010408446,0.0018693942,0.00021852447,0.000016836077,0.0000072603916,0.0007705226,0.000004146668,0.00081664533,0.0013062292,0.0010534598,0.9938116],"study_design_scores_gemma":[0.0020047128,0.0025074896,0.3759783,0.00215555,0.00066906255,0.0009572764,0.00091141235,0.16781628,0.27745467,0.15131249,0.007782888,0.01044987],"about_ca_topic_score_codex":0.0013578016,"about_ca_topic_score_gemma":0.00023542307,"teacher_disagreement_score":0.9833617,"about_ca_system_score_codex":0.00009067947,"about_ca_system_score_gemma":0.00018835675,"threshold_uncertainty_score":0.8550936},"labels":[],"label_agreement":null},{"id":"W4254152538","doi":"10.1109/ast.2015.13","title":"Adaptive Random Testing by Static Partitioning","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Random testing; Computer science; Overhead (engineering); Point (geometry); Isolation (microbiology); Test case; Parallel computing; Algorithm; Distributed computing; Theoretical computer science; Machine learning; Mathematics","score_opus":0.0889890986322632,"score_gpt":0.27574200080274397,"score_spread":0.18675290217048077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254152538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015285993,0.000047886446,0.97823095,0.00027318296,0.000073836105,0.00007308461,8.853106e-7,0.011135546,0.008636015],"genre_scores_gemma":[0.4603779,2.0675833e-7,0.5391557,0.0002971578,0.000014129176,0.00001412062,8.100025e-7,0.0000040883433,0.00013584063],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999226,0.00005566013,0.00013608387,0.00020472788,0.00019006414,0.00018751938],"domain_scores_gemma":[0.99879926,0.0006441526,0.000053607622,0.00024191,0.00014649173,0.00011457968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048032808,0.000081091064,0.00009898973,0.000038916358,0.000076789205,0.000127648,0.00030513416,0.000022687891,0.0000029967464],"category_scores_gemma":[0.0013981428,0.00006927028,0.00001650997,0.00028357471,0.000020166934,0.00028799858,0.000110037785,0.00007009527,0.00004360059],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015237257,0.00008944292,0.008267977,0.0000076270026,0.000015956211,0.000028541717,0.0013311799,0.0005372081,0.00011262218,0.010488624,0.88145024,0.09765537],"study_design_scores_gemma":[0.0009226115,0.00028992133,0.00012550472,0.000068000634,0.000005155661,0.000039126044,0.000029949253,0.73656416,0.0014706708,0.25880128,0.0013999658,0.00028367256],"about_ca_topic_score_codex":0.0001481599,"about_ca_topic_score_gemma":0.0000019754552,"teacher_disagreement_score":0.88005024,"about_ca_system_score_codex":0.00003151524,"about_ca_system_score_gemma":0.00006808679,"threshold_uncertainty_score":0.282476},"labels":[],"label_agreement":null},{"id":"W4254309703","doi":"10.1007/s10270-002-8208-5","title":"A UML-Based Approach to System Testing","year":2002,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Unified Modeling Language; Sequence diagram; Class diagram; Object Constraint Language; Software engineering; Applications of UML; Testability; Model-based testing; Context (archaeology); Test case; Programming language; UML tool; Test Management Approach; System testing; Activity diagram; Software development; Reliability engineering; Software; Software construction","score_opus":0.09020794658056883,"score_gpt":0.23924228661756475,"score_spread":0.14903434003699592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254309703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017127586,0.00056513114,0.95263827,0.00004528631,0.00054279296,0.0005968832,0.0000040986133,0.041766766,0.002128015],"genre_scores_gemma":[0.5439675,2.148012e-7,0.45553225,0.0001202785,0.00012467791,0.00016833228,0.0000015247389,0.00003598197,0.00004925389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996735,0.00016491904,0.000681472,0.0009957913,0.0006867924,0.00073601946],"domain_scores_gemma":[0.99722147,0.00045304262,0.00018222781,0.0014332054,0.0003928039,0.00031726522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009811245,0.00038692364,0.00048160035,0.0003797993,0.00042856325,0.0005823767,0.001422891,0.00016188304,6.658205e-7],"category_scores_gemma":[0.001130128,0.0003706245,0.00011726163,0.001226306,0.000019286721,0.00032932407,0.0002815387,0.0002723805,0.00011189516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028662357,0.00012304272,0.0024490238,0.0006973682,0.000019953743,0.000036373054,0.00083346723,0.9679515,0.000032206284,0.002499116,0.0045248126,0.020830266],"study_design_scores_gemma":[0.00017323722,0.000068747366,0.0000053360154,0.0009278898,0.0000100808575,0.00013784482,0.000030102483,0.99784034,0.000011057658,0.00022067073,0.000117361946,0.00045732362],"about_ca_topic_score_codex":0.00056374876,"about_ca_topic_score_gemma":5.240738e-7,"teacher_disagreement_score":0.54225475,"about_ca_system_score_codex":0.0002764631,"about_ca_system_score_gemma":0.00006921546,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W4254402004","doi":"10.22215/etd/2010-09070","title":"Systematic review of state based model based testing tools","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"State (computer science); Computer science; Programming language","score_opus":0.03741510849190186,"score_gpt":0.2970245142930462,"score_spread":0.25960940580114433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254402004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010930856,0.002252031,0.9833484,0.000057815374,0.00019190185,0.0012494022,0.000012583123,0.008510833,0.004267692],"genre_scores_gemma":[0.006571522,0.00004732342,0.99045837,0.0013492921,0.000010595797,0.0002835707,0.0001370692,0.000044696968,0.0010975898],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976435,0.000109038614,0.0009641495,0.00046503768,0.0005767563,0.00024155802],"domain_scores_gemma":[0.9948896,0.0018176767,0.00096868013,0.0014191231,0.0008268147,0.00007811118],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013176966,0.00032423722,0.0009237951,0.00022328005,0.00006683663,0.00012714513,0.001329098,0.0001768773,0.000008356989],"category_scores_gemma":[0.008160664,0.00026291652,0.00018079819,0.0005347698,0.000016181326,0.00018260456,0.00004445436,0.00036786927,0.000009215974],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002011172,0.000053739583,0.000012884053,0.994096,0.000014952654,0.0000057932775,0.000046781493,0.00024670092,0.00022353638,0.0002484404,0.002680945,0.002368213],"study_design_scores_gemma":[0.00005193967,0.000035619614,0.000008737048,0.35040766,0.00006921186,0.0000016911963,5.58774e-7,0.64408517,0.0019956646,0.0030918524,9.0371464e-7,0.00025102592],"about_ca_topic_score_codex":0.000059034443,"about_ca_topic_score_gemma":0.000018738998,"teacher_disagreement_score":0.64383847,"about_ca_system_score_codex":0.000031401658,"about_ca_system_score_gemma":0.000710304,"threshold_uncertainty_score":0.9999823},"labels":[],"label_agreement":null},{"id":"W4254576214","doi":"10.1109/icse.2000.870402","title":"Broad-spectrum studies of log file analysis","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 2000 International Conference on Software Engineering. ICSE 2000 the New Millennium","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; File system; Completeness (order theory); Unix file types; Computer file; Operating system; Stub file; Mathematics","score_opus":0.03605241013301291,"score_gpt":0.25861406051296104,"score_spread":0.22256165037994813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254576214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122507475,0.025221556,0.67731214,0.07558301,0.013472133,0.005136869,0.0017870162,0.03424638,0.044733394],"genre_scores_gemma":[0.9054832,0.00090907264,0.08619652,0.00039252397,0.00026131808,0.00006170098,0.0000066949615,0.00004474336,0.006644218],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980707,0.000010850553,0.00048528652,0.00041467356,0.00071636506,0.00030210306],"domain_scores_gemma":[0.9981059,0.00035839505,0.00038861943,0.00047906753,0.000590786,0.00007724613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029291815,0.00029168904,0.0004175258,0.00038922072,0.00009855987,0.00009449281,0.0026697156,0.000095299154,0.00042835114],"category_scores_gemma":[0.0014029817,0.00019454751,0.00029130705,0.001103783,0.00012753888,0.00024056269,0.00046835147,0.0003264293,0.000018359064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054658496,0.00040692638,0.008753724,0.00017719611,0.0026904438,0.00000416641,0.0076422608,0.006623908,0.0008486185,0.074972086,0.88231426,0.015511761],"study_design_scores_gemma":[0.0017493512,0.0010516118,0.02662478,0.0025404359,0.00085942075,0.00012714077,0.0002633047,0.8214161,0.0373001,0.049259286,0.05632124,0.002487265],"about_ca_topic_score_codex":0.00008510057,"about_ca_topic_score_gemma":0.0000038702315,"teacher_disagreement_score":0.825993,"about_ca_system_score_codex":0.00016516444,"about_ca_system_score_gemma":0.00007753473,"threshold_uncertainty_score":0.7933417},"labels":[],"label_agreement":null},{"id":"W4255107725","doi":"10.1007/978-1-4939-7131-2_101286","title":"Subgraph Identification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Biology; Botany","score_opus":0.02745455742923722,"score_gpt":0.25097130965708847,"score_spread":0.22351675222785125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255107725","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001057174,0.000065870954,0.49464178,0.0001022205,0.0002585319,0.000070428185,0.0000010474413,0.014497056,0.490362],"genre_scores_gemma":[0.0008401322,0.000023749753,0.16593707,0.0002987595,0.00016694223,0.0000073051588,0.000009030754,0.000024805211,0.8326922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989809,0.00000612653,0.00022039373,0.00043270487,0.00023327196,0.00012663292],"domain_scores_gemma":[0.9984738,0.00008631885,0.00015155213,0.0010748403,0.00016426545,0.00004917352],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023286015,0.00017097816,0.00014044113,0.00019635992,0.000072376686,0.00017507696,0.0009303946,0.00017996739,0.000231278],"category_scores_gemma":[0.00004835103,0.00015727375,0.00008599155,0.000042198622,0.00006658789,0.00013193808,0.00020681733,0.00012576704,0.0011328217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.0244553e-7,0.000003409937,0.00000869063,0.0000070474334,0.000008295449,0.000004233588,0.00004035348,2.4104562e-8,0.000005010991,0.5215671,0.45439866,0.023956887],"study_design_scores_gemma":[0.00001879455,0.000030403078,0.00003065892,0.000056930294,0.0000056731656,0.000014635097,6.99558e-8,0.00049157004,0.00017593804,0.88610786,0.1128564,0.000211054],"about_ca_topic_score_codex":0.000010524793,"about_ca_topic_score_gemma":0.0000025888894,"teacher_disagreement_score":0.3645408,"about_ca_system_score_codex":0.000024909548,"about_ca_system_score_gemma":0.000038607006,"threshold_uncertainty_score":0.99964494},"labels":[],"label_agreement":null},{"id":"W4255224654","doi":"10.22215/etd/2007-07874","title":"An empirical study of the regression testing of an industrial software product","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage","funders":"","keywords":"Product (mathematics); Software; Computer science; Statistics; Engineering; Mathematics; Programming language","score_opus":0.09995236811702643,"score_gpt":0.3939676865431514,"score_spread":0.29401531842612494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255224654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990351,0.000022944185,0.0045717424,0.00001129724,0.00064586767,0.00067236327,0.0000017879936,0.0034407447,0.00028221653],"genre_scores_gemma":[0.81665885,2.0218668e-7,0.182902,0.000021019136,0.0001650175,0.00001561166,0.000022059905,0.000025390638,0.00018985604],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99748677,0.0002736988,0.0006224535,0.00063289923,0.00076859305,0.00021559332],"domain_scores_gemma":[0.99647504,0.00049813074,0.0007288869,0.0016758564,0.0005482433,0.00007384464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010837151,0.00025914217,0.00039530935,0.00023907893,0.00015014104,0.000055603534,0.0018729818,0.0002632485,0.0000029051753],"category_scores_gemma":[0.003379135,0.00016046409,0.000063976506,0.0010908637,0.00003745847,0.00024529762,0.0001544389,0.000508879,3.5616551e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007917822,0.0024523647,0.41997987,0.00011107088,0.000028194698,0.0000125809875,0.006792413,0.0000469354,0.000558905,0.00002026147,0.004106658,0.5658116],"study_design_scores_gemma":[0.0023311307,0.011749196,0.8236554,0.004318833,0.00024681832,0.00006847022,0.0021898493,0.012576055,0.12838282,0.012366373,0.00010158153,0.002013462],"about_ca_topic_score_codex":0.00075142685,"about_ca_topic_score_gemma":0.00014107118,"teacher_disagreement_score":0.5637981,"about_ca_system_score_codex":0.000029257533,"about_ca_system_score_gemma":0.00034337727,"threshold_uncertainty_score":0.65435356},"labels":[],"label_agreement":null},{"id":"W4280619266","doi":"10.4230/lipics.itp.2022.18","title":"Automatic Test-Case Reduction in Proof Assistants: A Case Study in Coq","year":2022,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prevention of Organ Failure","funders":"","keywords":"Computer science; Reduction (mathematics); Test (biology); Proof assistant; Proof of concept; Programming language; Operating system; Mathematics; Mathematical proof","score_opus":0.02613850071469267,"score_gpt":0.29371747690243355,"score_spread":0.2675789761877409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280619266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9715615,0.000024498102,0.022183029,0.000120509576,0.0005464756,0.00261789,0.00009699233,0.0026443733,0.00020476966],"genre_scores_gemma":[0.9599725,9.1795107e-7,0.038543887,0.00015983902,0.000029013998,0.0011933314,0.000028732155,0.000033192802,0.000038579703],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966213,0.0001795942,0.0014813658,0.00043412487,0.0005879138,0.0006956769],"domain_scores_gemma":[0.99769294,0.00047520624,0.00048598563,0.0010805717,0.00013534476,0.0001299535],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022150115,0.00036085225,0.00046720606,0.0009027749,0.0005223856,0.00036862504,0.00096872234,0.00010026547,0.00001676452],"category_scores_gemma":[0.00056683196,0.0003674492,0.00011294242,0.0014309955,0.00006132442,0.0013057425,0.00092353363,0.0007238576,0.000008607249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108826236,0.012821591,0.5397379,0.0013596666,0.00015175028,0.047725197,0.17029272,0.0015437746,0.00002424353,0.0007517342,0.011247312,0.21423532],"study_design_scores_gemma":[0.0056073107,0.0022571418,0.0040364694,0.00023667057,0.000031458876,0.09849019,0.014130689,0.86991376,0.0000844795,0.0034712313,0.0006969973,0.0010436234],"about_ca_topic_score_codex":0.00056856044,"about_ca_topic_score_gemma":0.00019686569,"teacher_disagreement_score":0.86836994,"about_ca_system_score_codex":0.00059927464,"about_ca_system_score_gemma":0.00017409313,"threshold_uncertainty_score":0.99987775},"labels":[],"label_agreement":null},{"id":"W4280650798","doi":"10.18280/ria.360217","title":"Combinatorial Test Case Generation Using Q-Value Based Particle Swarm Optimization","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Particle swarm optimization; Pairwise comparison; Mathematical optimization; Computer science; Test case; Heuristic; Metaheuristic; Set (abstract data type); Value (mathematics); Fitness function; Function (biology); Swarm behaviour; Algorithm; Mathematics; Artificial intelligence; Machine learning; Genetic algorithm","score_opus":0.07369328942555042,"score_gpt":0.2950321892962207,"score_spread":0.2213388998706703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280650798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03259972,0.00006483465,0.96384627,0.00030471504,0.0008260152,0.00021989208,0.000004587359,0.0020288206,0.00010514341],"genre_scores_gemma":[0.8206525,0.0000014335433,0.17893712,0.00019870735,0.00010923193,0.000049176662,0.0000072636817,0.000014987253,0.000029614366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984822,0.00016617,0.00036106852,0.00044755015,0.0002562706,0.00028671644],"domain_scores_gemma":[0.9986304,0.00037808233,0.00014226903,0.00064893236,0.000116547446,0.00008377366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072928163,0.00013924963,0.00013656505,0.00010307935,0.0008599043,0.00017664315,0.0004751472,0.000039337137,0.00007178072],"category_scores_gemma":[0.00046722553,0.00016219098,0.00006538153,0.0008519222,0.000041178977,0.00024147682,0.00025879304,0.00018171589,0.000016258338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002604083,0.00018973269,0.00027445,0.0000067059123,0.0000022624374,0.0001986662,0.00031284045,0.98689157,0.0012784468,0.006478091,0.0004140143,0.0039506434],"study_design_scores_gemma":[0.00004994116,0.00017815887,9.996231e-7,0.000011639067,0.0000075147377,0.0005420246,0.000030256944,0.9404852,0.054596446,0.0037191098,0.00018960677,0.00018909402],"about_ca_topic_score_codex":0.00017263647,"about_ca_topic_score_gemma":0.0000017304263,"teacher_disagreement_score":0.78805274,"about_ca_system_score_codex":0.00016519542,"about_ca_system_score_gemma":0.000106916086,"threshold_uncertainty_score":0.6613956},"labels":[],"label_agreement":null},{"id":"W4281765649","doi":"10.1016/j.cca.2022.04.224","title":"M126 Effective utilization management strategies to limit inappropriate referred-out test requests","year":2022,"lang":"en","type":"article","venue":"Clinica Chimica Acta","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Nova Scotia Health Authority; Dalhousie University","funders":"","keywords":"Limit (mathematics); Test (biology); Utilization management; Operations management; Business; Intensive care medicine; Medicine; Risk analysis (engineering); Engineering; Mathematics; Political science; Health care; Biology; Law","score_opus":0.06263412735368994,"score_gpt":0.3412593811587694,"score_spread":0.27862525380507946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281765649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2618277,0.00024909741,0.4920358,0.025078649,0.0072118514,0.010094081,0.00012106407,0.08816693,0.11521482],"genre_scores_gemma":[0.9140382,0.000029355642,0.0837152,0.0012530932,0.00008061383,0.00047591206,0.000018570354,0.000030463909,0.00035862424],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99757814,0.00027383651,0.00047963372,0.0008537035,0.00042803556,0.00038667486],"domain_scores_gemma":[0.9970931,0.0011315222,0.00023030501,0.0013097927,0.00009450293,0.00014081712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011141151,0.00024073155,0.00028552415,0.00023632834,0.00040910358,0.00028401843,0.0016950945,0.00007012773,0.000022015176],"category_scores_gemma":[0.00095148326,0.00024321511,0.000097884345,0.0007013717,0.000050832266,0.0003424909,0.0018650701,0.00040888906,0.000045292345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037081473,0.0038499134,0.015153513,0.0003976893,0.00037723128,0.0003023909,0.011234265,0.00039386927,0.0041197347,0.059298012,0.5344192,0.37008342],"study_design_scores_gemma":[0.0032417204,0.009691903,0.1880007,0.0007851694,0.00023340965,0.00017084953,0.0005149837,0.050285548,0.0038908534,0.47609758,0.263274,0.0038132712],"about_ca_topic_score_codex":0.000013507253,"about_ca_topic_score_gemma":0.0000059191616,"teacher_disagreement_score":0.6522105,"about_ca_system_score_codex":0.0001591476,"about_ca_system_score_gemma":0.00009201922,"threshold_uncertainty_score":0.9918024},"labels":[],"label_agreement":null},{"id":"W4282828008","doi":"10.1109/icse-companion55297.2022.9793739","title":"DScribe: Co-generating Unit Tests and Documentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Nature","keywords":"Documentation; Computer science; Unit testing; Unit (ring theory); Operating system; Psychology; Software","score_opus":0.04851208535317507,"score_gpt":0.2975137824159923,"score_spread":0.24900169706281722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282828008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6429654,0.0001977636,0.3255224,0.0025368992,0.006106164,0.001322269,0.0001744225,0.019331677,0.0018430613],"genre_scores_gemma":[0.88563144,0.00003448057,0.11243396,0.0006612098,0.00030759224,0.00032849843,0.0001572165,0.00007775594,0.0003678225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567896,0.00006971617,0.0008181651,0.0012042401,0.0015760121,0.0006529121],"domain_scores_gemma":[0.99736196,0.00047013583,0.00049101736,0.0005841441,0.00078914675,0.00030361285],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00095189334,0.0006289936,0.0005082719,0.0008235316,0.0007847387,0.0011065159,0.0025880414,0.0001231793,0.00038831885],"category_scores_gemma":[0.0012529524,0.0007228681,0.00012221422,0.0010263851,0.000075967626,0.0011933433,0.0010920839,0.001078846,0.000048003625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013180097,0.0010756897,0.18114118,0.00038237174,0.00044562263,0.000121755686,0.0065318914,0.018991066,0.02062085,0.6612872,0.091391385,0.01787918],"study_design_scores_gemma":[0.002096802,0.0009146522,0.028751377,0.00046079632,0.000050558338,0.0007484998,0.00043496036,0.9243577,0.0043680156,0.020585574,0.014870422,0.002360622],"about_ca_topic_score_codex":0.00007767478,"about_ca_topic_score_gemma":0.0000015005567,"teacher_disagreement_score":0.90536666,"about_ca_system_score_codex":0.00044312957,"about_ca_system_score_gemma":0.000173617,"threshold_uncertainty_score":0.99993044},"labels":[],"label_agreement":null},{"id":"W4282830605","doi":"10.1109/icse-companion55297.2022.9793757","title":"DiffWatch: Watch Out for the Evolving Differential Testing in Deep Learning Libraries","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Python (programming language); Computer science; Differential (mechanical device); Deep learning; Artificial intelligence; Operating system; Engineering","score_opus":0.05555531626052307,"score_gpt":0.26780240175017994,"score_spread":0.21224708548965687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282830605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101973094,0.0001839694,0.87624454,0.0027451587,0.006116175,0.0012765724,0.00004521902,0.011003617,0.00041162048],"genre_scores_gemma":[0.90728134,0.000019087518,0.09060369,0.00024369308,0.00045253095,0.0008479208,0.00006357917,0.00010368601,0.00038444973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953721,0.00007615794,0.0009593977,0.0012229568,0.001452339,0.0009170109],"domain_scores_gemma":[0.99517524,0.0025667949,0.00054624415,0.0006447714,0.0008602522,0.00020672243],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010495606,0.00069023715,0.00062372,0.00060287485,0.0010448564,0.0012948996,0.0046168375,0.00014307248,0.00018875874],"category_scores_gemma":[0.005357674,0.00065822375,0.00022070279,0.0011557194,0.00008869839,0.0010285999,0.0018604238,0.0017728447,0.000019515273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036753368,0.0018016694,0.36077088,0.0006948164,0.0007029518,0.00009450622,0.024610035,0.09401854,0.009380265,0.42030638,0.04242463,0.044827793],"study_design_scores_gemma":[0.00092967803,0.00033495785,0.017678265,0.0002756273,0.00002512475,0.000079051264,0.00034785288,0.96330863,0.00061685225,0.011159656,0.004339793,0.00090450316],"about_ca_topic_score_codex":0.000076407676,"about_ca_topic_score_gemma":0.0000036225426,"teacher_disagreement_score":0.8692901,"about_ca_system_score_codex":0.00054211856,"about_ca_system_score_gemma":0.00017624203,"threshold_uncertainty_score":0.99974185},"labels":[],"label_agreement":null},{"id":"W4282835086","doi":"10.1109/icse-companion55297.2022.9793738","title":"MASS: A tool for Mutation Analysis of Space CPS","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"European Research Council; Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Scalability; Computer science; Context (archaeology); Software; Set (abstract data type); Mutation; Operating system; Programming language","score_opus":0.036619287075395565,"score_gpt":0.2779605335269983,"score_spread":0.2413412464516027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282835086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10035701,0.000042632066,0.8896901,0.0009116856,0.0022366277,0.0007816377,0.00024578682,0.0054478296,0.0002867123],"genre_scores_gemma":[0.7930458,0.000011434276,0.20555641,0.00020935708,0.00014372836,0.00052240456,0.00021526578,0.00005845186,0.00023714178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995617,0.00004892645,0.0010017903,0.0011341042,0.0016074089,0.0005908026],"domain_scores_gemma":[0.99599946,0.00079000555,0.0007725359,0.00073506555,0.0015196122,0.00018330275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011247093,0.00055925583,0.00080564513,0.001854586,0.00037263054,0.0003921811,0.0032076084,0.00013186288,0.00023424238],"category_scores_gemma":[0.002121869,0.00064217753,0.00042194736,0.0027186086,0.000059951108,0.00068569445,0.0006558519,0.00066650717,0.000013393674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022103815,0.0009251318,0.041863095,0.00034175024,0.0021149025,0.000031235224,0.0034704278,0.08997028,0.008495875,0.81681645,0.030840468,0.004909373],"study_design_scores_gemma":[0.000909679,0.00050487556,0.009297647,0.00014492785,0.00021312408,0.000052854644,0.00014029774,0.96571964,0.002466392,0.016021105,0.0035922625,0.00093719014],"about_ca_topic_score_codex":0.000045925914,"about_ca_topic_score_gemma":0.000001079686,"teacher_disagreement_score":0.87574935,"about_ca_system_score_codex":0.0005474038,"about_ca_system_score_gemma":0.00020080207,"threshold_uncertainty_score":0.999603},"labels":[],"label_agreement":null},{"id":"W4283080616","doi":"10.1109/icse-seip55303.2022.9793941","title":"The Impact of Flaky Tests on Historical Test Prioritization on Chrome","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Prioritization; Blocking (statistics); Pipeline (software); Computer science; Test (biology); Reliability engineering; Replication (statistics); Work (physics); Regression testing; Software; Engineering; Software development; Operating system; Computer network","score_opus":0.019321535303824963,"score_gpt":0.28688465220610365,"score_spread":0.2675631169022787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283080616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36646804,0.0007226608,0.47005337,0.01530252,0.0036417549,0.0023138686,0.000036703623,0.068052985,0.07340809],"genre_scores_gemma":[0.99226624,0.0000024056305,0.006913432,0.00012599178,0.000031172454,0.000022393357,0.0000010386645,0.000006838227,0.0006304906],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.999153,0.000054887398,0.00014396943,0.00018866113,0.00031561963,0.00014381707],"domain_scores_gemma":[0.99791175,0.0014236983,0.00007876329,0.0005002368,0.000049175193,0.000036356025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032759382,0.000080521095,0.000087598426,0.0000787905,0.00030236816,0.000040076222,0.00059910107,0.000017515478,0.000011806867],"category_scores_gemma":[0.00079200405,0.000051577346,0.00006159313,0.00041876576,0.00001696718,0.00005117848,0.00017825958,0.000137742,0.000006554196],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003120535,0.001054113,0.053655684,0.000009334728,0.000020024292,0.000026813703,0.00049010746,0.0022127512,0.0014001379,0.026228694,0.8001169,0.114754215],"study_design_scores_gemma":[0.0011397004,0.026419336,0.5193407,0.00012427254,0.000014507225,0.00019940194,0.0000115802,0.23370004,0.005238699,0.1923454,0.020269962,0.0011963848],"about_ca_topic_score_codex":0.00023129383,"about_ca_topic_score_gemma":0.0000012676636,"teacher_disagreement_score":0.77984697,"about_ca_system_score_codex":0.0005900372,"about_ca_system_score_gemma":0.00008472329,"threshold_uncertainty_score":0.2325602},"labels":[],"label_agreement":null},{"id":"W4283323653","doi":"10.1145/3544790","title":"Toward More Efficient Statistical Debugging with Abstraction Refinement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Office of Naval Research; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; National Science Foundation","keywords":"Debugging; Computer science; Algorithmic program debugging; Abstraction; Programming language; Pruning; Discriminative model; Software engineering; Machine learning","score_opus":0.07935506400377887,"score_gpt":0.3095148429020107,"score_spread":0.23015977889823183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283323653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063918293,0.00008663412,0.98712695,0.00052350835,0.00035850628,0.00012473846,0.0000141272885,0.005368729,0.000004986016],"genre_scores_gemma":[0.26329795,0.0000060098787,0.73634857,0.00016065703,0.000011977306,0.00013402024,0.0000038340577,0.000017554092,0.000019462737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986384,0.00015710252,0.00019670809,0.000448713,0.00025673152,0.000302352],"domain_scores_gemma":[0.9969836,0.00231218,0.000053653745,0.0005104115,0.000037998576,0.00010217881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007447452,0.00018522413,0.00021688761,0.00025985632,0.00033222753,0.00003808599,0.00035919854,0.000050880164,0.000027064225],"category_scores_gemma":[0.0005104965,0.00017569173,0.00003730339,0.00030877814,0.000039014558,0.000057521214,0.000049257185,0.00048338983,0.0000017485116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008148706,0.00019694622,0.0002006106,0.000080879465,0.00009565078,0.00011800372,0.0015820382,0.61358434,0.00020808131,0.002275776,0.00030117884,0.38127497],"study_design_scores_gemma":[0.0040839524,0.006481241,0.0201584,0.0003280176,0.00043440424,0.0077139204,0.00054933224,0.9129737,0.00818372,0.015292321,0.020279462,0.0035215353],"about_ca_topic_score_codex":0.00006889672,"about_ca_topic_score_gemma":7.603506e-7,"teacher_disagreement_score":0.37775344,"about_ca_system_score_codex":0.000096514355,"about_ca_system_score_gemma":0.000051157,"threshold_uncertainty_score":0.7164501},"labels":[],"label_agreement":null},{"id":"W4283689178","doi":"10.1016/j.cose.2022.102813","title":"Fuzzing vulnerability discovery techniques: Survey, challenges and future directions","year":2022,"lang":"en","type":"article","venue":"Computers & Security","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Fuzz testing; Computer science; Vulnerability (computing); Computer security; Data science; Programming language","score_opus":0.027466111279944364,"score_gpt":0.26526658250549223,"score_spread":0.23780047122554787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283689178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20015018,0.04405108,0.65521854,0.01729004,0.0076819942,0.0017655073,0.00015168289,0.07099304,0.0026979374],"genre_scores_gemma":[0.9281892,0.0009785054,0.06992544,0.00043832298,0.00030631834,0.0001156177,0.000014511169,0.000020079524,0.0000119673805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977232,0.00068078184,0.00024046666,0.00073498103,0.0003085829,0.00031194455],"domain_scores_gemma":[0.9981545,0.0007107791,0.000110414076,0.0008489032,0.00007386194,0.000101509315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001666219,0.00021510506,0.00026365262,0.00015487803,0.0007106764,0.00021303132,0.0008717395,0.00006187845,0.000003045762],"category_scores_gemma":[0.00010174239,0.00022340678,0.000075731754,0.00041276377,0.00008937602,0.00052063784,0.0016764167,0.0005220245,8.333115e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001784904,0.00042904227,0.007395054,0.00009330314,0.000039632145,0.000040608098,0.009422458,0.000010142341,0.00001576888,0.01987474,0.018048512,0.94461286],"study_design_scores_gemma":[0.000638139,0.0011071545,0.2492018,0.00012185736,0.000030133499,0.00071136706,0.00028165284,0.032794874,0.000374642,0.38641107,0.32620338,0.002123941],"about_ca_topic_score_codex":0.00030749015,"about_ca_topic_score_gemma":0.000055293716,"teacher_disagreement_score":0.94248897,"about_ca_system_score_codex":0.00012128385,"about_ca_system_score_gemma":0.000059014885,"threshold_uncertainty_score":0.9110264},"labels":[],"label_agreement":null},{"id":"W4284682233","doi":"10.1145/3510003.3510188","title":"Efficient online testing for DNN-enabled systems using surrogate-assisted and many-objective optimization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; Fonds National de la Recherche Luxembourg; National Research Foundation; European Commission","keywords":"Computer science; Reliability (semiconductor); Fidelity; High fidelity; Reliability engineering; Software; Test strategy; Artificial neural network; Embedded system; Real-time computing; Distributed computing; Machine learning; Engineering; Operating system","score_opus":0.04979620041711109,"score_gpt":0.266732807629432,"score_spread":0.21693660721232094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284682233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23062654,0.000037935108,0.76600605,0.00013320646,0.00080516073,0.0004877729,0.000047191734,0.0017797532,0.00007641334],"genre_scores_gemma":[0.6722386,6.5921205e-7,0.32759047,0.000022384127,0.0000342654,0.00006988574,0.0000029416742,0.00001586846,0.00002491005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987303,0.000009443706,0.0002925652,0.00034397782,0.0004239058,0.00019981853],"domain_scores_gemma":[0.998452,0.00034145266,0.00030026917,0.00012424697,0.000738138,0.00004387177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043121446,0.00016896277,0.00018470312,0.00022492411,0.0002518678,0.00017019312,0.0008011797,0.000036989808,0.0000020500079],"category_scores_gemma":[0.0020488757,0.00015359145,0.000052046464,0.00040072348,0.000025123703,0.00012752716,0.0005465847,0.00020405135,8.42275e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023345938,0.00008978755,0.005010437,0.00012810517,0.00004405057,8.265491e-7,0.0003042013,0.9667529,0.0020982532,0.024457853,0.00008482401,0.0010054101],"study_design_scores_gemma":[0.00023994195,0.00010808587,0.0012651397,0.00029530027,0.000010905123,0.000051462914,0.000054967048,0.99693406,0.00043431084,0.00042740922,0.000017433062,0.00016100316],"about_ca_topic_score_codex":0.00004118583,"about_ca_topic_score_gemma":1.0101732e-7,"teacher_disagreement_score":0.44161206,"about_ca_system_score_codex":0.00022884973,"about_ca_system_score_gemma":0.00006788645,"threshold_uncertainty_score":0.62632775},"labels":[],"label_agreement":null},{"id":"W4284693828","doi":"10.1145/3510003.3510106","title":"Nessie","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Callback; Computer science; Asynchronous communication; Unit testing; Test case; Generator (circuit theory); JavaScript; Test (biology); Operating system; Programming language; Software; Machine learning; Computer network","score_opus":0.02496960565977006,"score_gpt":0.24090047315395033,"score_spread":0.21593086749418028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284693828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31731638,0.00014424862,0.6144869,0.010409213,0.009864034,0.0010437182,0.00007375061,0.027837759,0.018824045],"genre_scores_gemma":[0.9210782,0.0000020536975,0.07837665,0.0001757049,0.000045774075,0.000067320376,8.364511e-7,0.000012487399,0.00024099034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988234,0.0000043789278,0.00019394043,0.0002442315,0.0005721875,0.00016184086],"domain_scores_gemma":[0.9993235,0.000081216094,0.00015327857,0.00017382295,0.00023170789,0.000036464207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002711871,0.00012401659,0.000114178336,0.00015385896,0.0001393715,0.00009453014,0.0022444006,0.000023284643,0.000040208175],"category_scores_gemma":[0.0006839926,0.000106105006,0.00007518635,0.00032329262,0.000020535428,0.00021432174,0.0009727676,0.00028989642,0.000002630905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019722273,0.00013121711,0.025954109,0.000058485846,0.00005977244,0.000003363934,0.0007660842,0.0031725408,0.0026480604,0.943578,0.013980355,0.009628266],"study_design_scores_gemma":[0.0011966962,0.0006936575,0.03647908,0.0009288747,0.00003133746,0.0003582512,0.00014645603,0.7370191,0.039136797,0.1598,0.022536954,0.001672765],"about_ca_topic_score_codex":0.000006888553,"about_ca_topic_score_gemma":4.621411e-8,"teacher_disagreement_score":0.783778,"about_ca_system_score_codex":0.00009905586,"about_ca_system_score_gemma":0.000042254138,"threshold_uncertainty_score":0.43268365},"labels":[],"label_agreement":null},{"id":"W4285490476","doi":"10.1145/3533767.3543293","title":"ATUA: an update-driven app testing tool","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"European Commission","keywords":"Computer science; Oracle; Android (operating system); Random testing; Code coverage; Source code; Regression testing; Model-based testing; Code (set theory); Test case; Software engineering; Programming language; Machine learning; Software; Operating system; Software development; Regression analysis","score_opus":0.03478549762453586,"score_gpt":0.26095904739117276,"score_spread":0.2261735497666369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285490476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033563126,0.000026499018,0.90735364,0.00063181215,0.00029334173,0.00016844773,0.0000025733564,0.05184007,0.0061204843],"genre_scores_gemma":[0.4433103,1.8262085e-7,0.555486,0.00095558655,0.000030717252,0.00003720214,0.000002699942,0.000007863426,0.00016942434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988862,0.0000806809,0.00014993119,0.0003675317,0.00027350115,0.00024214818],"domain_scores_gemma":[0.9989414,0.00021943141,0.00005534477,0.00067166955,0.00005258793,0.00005955523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003799346,0.00009933606,0.000097598066,0.00008714432,0.00042101828,0.00013480504,0.0011285762,0.00001927283,0.00006384647],"category_scores_gemma":[0.00023121052,0.000096836964,0.000028032991,0.0005440563,0.000017396478,0.00030677795,0.00095826684,0.0001792497,0.000030073968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069936805,0.0003806177,0.06418493,0.000016975446,0.000018758235,0.00019304497,0.0010218369,0.0029777717,0.0010157119,0.08901521,0.2377059,0.6034623],"study_design_scores_gemma":[0.00022944603,0.00054352405,0.0045201727,0.000011828578,0.000005530891,0.00026685867,0.000019762378,0.8819035,0.00057005545,0.09378748,0.017562829,0.00057901326],"about_ca_topic_score_codex":0.00012255892,"about_ca_topic_score_gemma":0.0000019173344,"teacher_disagreement_score":0.87892574,"about_ca_system_score_codex":0.0000477933,"about_ca_system_score_gemma":0.00006532162,"threshold_uncertainty_score":0.39488968},"labels":[],"label_agreement":null},{"id":"W4288406204","doi":"10.48550/arxiv.1903.11242","title":"An Empirical Study on Practicality of Specification Mining Algorithms on\\n a Real-world Application","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Debugging; Computer science; Program comprehension; Context (archaeology); Implementation; Inference; Programming language; Abstraction; Software engineering; Set (abstract data type); Root cause; Software; Algorithm; Artificial intelligence; Software system; Reliability engineering","score_opus":0.2026427942074081,"score_gpt":0.31376238393988776,"score_spread":0.11111958973247965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288406204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39435357,0.0000023093735,0.59933686,0.000118559044,0.00030481326,0.0013297743,0.000014230663,0.0019185682,0.0026212758],"genre_scores_gemma":[0.9809891,0.000034197274,0.01831682,0.00010990001,0.00015263907,0.000009490489,0.000029457446,0.00004434998,0.0003140685],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99392194,0.0011559451,0.0008039751,0.0030791692,0.00047069788,0.000568263],"domain_scores_gemma":[0.9903374,0.0020668437,0.0015024928,0.0051010307,0.00067255786,0.00031968235],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022810686,0.00064468203,0.0008359576,0.0008423784,0.00031759878,0.00018823931,0.002698731,0.00041009852,0.00001505105],"category_scores_gemma":[0.0004117945,0.0007512539,0.00025555948,0.0020273698,0.00024987583,0.0004928683,0.0010359074,0.0011411044,0.00013148066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009122141,0.0160182,0.78300136,0.00022967062,0.0003154416,0.00020979415,0.0061049378,0.111807875,0.000073665135,0.05292884,0.0014413671,0.026956618],"study_design_scores_gemma":[0.0006537738,0.0022895297,0.221637,0.0002624101,0.00015870611,0.0000029973369,0.0003193982,0.75475407,0.00021605351,0.018814815,0.00013532801,0.00075591385],"about_ca_topic_score_codex":0.0008575229,"about_ca_topic_score_gemma":0.00004110177,"teacher_disagreement_score":0.6429462,"about_ca_system_score_codex":0.0006619652,"about_ca_system_score_gemma":0.00043159764,"threshold_uncertainty_score":0.99949384},"labels":[],"label_agreement":null},{"id":"W4288723601","doi":"10.1007/s10664-022-10158-x","title":"GBGallery : A benchmark and framework for game testing","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Software engineering; Video game development; Test strategy; Software development; Game testing; Software; Database; Game Developer; Game design; Artificial intelligence; Programming language; Game design document","score_opus":0.04408833245119895,"score_gpt":0.28456053815274496,"score_spread":0.240472205701546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288723601","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017909167,0.00032365578,0.9699004,0.00037500713,0.00031921756,0.0001900908,0.0000052699133,0.010965148,0.000012002123],"genre_scores_gemma":[0.27993697,9.603775e-7,0.7193131,0.00041507935,0.00008661759,0.00020793857,0.0000023278349,0.000023429506,0.000013604414],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986637,0.000027298325,0.00021325311,0.00044744366,0.0002520745,0.00039622444],"domain_scores_gemma":[0.9954759,0.003915411,0.000057557747,0.00037189797,0.000049107042,0.00013014475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004130433,0.00018079043,0.00019845286,0.0001290258,0.00027360665,0.000113031565,0.00053265033,0.000060267324,0.000008476762],"category_scores_gemma":[0.0059794514,0.00019577536,0.00006174139,0.00059061876,0.00001673447,0.00013868198,0.0006909408,0.0003821112,0.0000012392709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000398163,0.00039281492,0.60476315,0.0005772759,0.0001464876,0.00021382161,0.0045756237,0.053589415,0.00019834955,0.0187963,0.0653415,0.25136545],"study_design_scores_gemma":[0.0005824194,0.0009323744,0.07590459,0.00025242678,0.000026161973,0.00041265468,0.000014686433,0.6742082,0.00014052514,0.19222225,0.053763453,0.0015402604],"about_ca_topic_score_codex":0.000008707528,"about_ca_topic_score_gemma":1.0253888e-7,"teacher_disagreement_score":0.62061876,"about_ca_system_score_codex":0.00008557643,"about_ca_system_score_gemma":0.000047447476,"threshold_uncertainty_score":0.7983487},"labels":[],"label_agreement":null},{"id":"W4292946475","doi":"","title":"ntegrating Formal Program Verification with Testing","year":2012,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prevention of Organ Failure","funders":"","keywords":"Computer science; Programming language; Formal verification; Formal methods; Software engineering","score_opus":0.028285916040893998,"score_gpt":0.2502259271547433,"score_spread":0.22194001111384928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292946475","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015962275,0.0004115199,0.9461975,0.0017384393,0.00014454365,0.0006847484,0.000007255965,0.012817669,0.02203602],"genre_scores_gemma":[0.41317278,0.0000128504225,0.58612955,0.00003959194,0.000025748559,0.00021631224,0.00007770685,0.00003062901,0.00029482483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954825,0.0019672865,0.00050784607,0.00088089163,0.00054138986,0.0006200686],"domain_scores_gemma":[0.9916398,0.0019814293,0.0007440341,0.0029292442,0.0024951468,0.0002103492],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0059901224,0.0004096456,0.00033994918,0.00020161257,0.0005515967,0.0010520468,0.002303493,0.00026835533,0.000006766885],"category_scores_gemma":[0.0030336755,0.00037920647,0.00011218997,0.00072001095,0.00016870667,0.0005985956,0.0019058473,0.0008452338,0.000018501063],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044311573,0.0005910296,0.010950703,0.00017860226,0.000042168536,0.0000052209857,0.006806708,0.000048757407,0.0003505629,0.049312472,0.0008133338,0.930896],"study_design_scores_gemma":[0.0011261632,0.000008743989,0.030588517,0.013118461,0.00015732876,0.00026304187,0.00008988621,0.84540206,0.051012255,0.047238216,0.007933402,0.0030619202],"about_ca_topic_score_codex":0.0007681405,"about_ca_topic_score_gemma":0.00015029748,"teacher_disagreement_score":0.9278341,"about_ca_system_score_codex":0.0001255015,"about_ca_system_score_gemma":0.00036945593,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W4293870966","doi":"","title":"Third International Competition on Runtime Verification CRV 2016","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Competition (biology); Runtime verification; Programming language; Formal verification","score_opus":0.01578126948584593,"score_gpt":0.23936021654750028,"score_spread":0.22357894706165435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293870966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020932294,0.00015565426,0.87788326,0.02365667,0.0008286171,0.0003241354,0.000046624282,0.005586071,0.08942574],"genre_scores_gemma":[0.6380504,0.00038473197,0.35142976,0.0005074214,0.000127207,0.00018318395,0.0004089233,0.000060576232,0.008847811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951177,0.0022436236,0.0005405222,0.0010947845,0.0006702395,0.00033308245],"domain_scores_gemma":[0.9921715,0.0018713129,0.0006481292,0.003154161,0.0020064628,0.00014840692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0039932863,0.00036746313,0.0003121266,0.00035738145,0.0003136655,0.00074352074,0.003333977,0.0003163455,0.00006727254],"category_scores_gemma":[0.0021041145,0.00034412814,0.00019979129,0.00026269926,0.00017198436,0.00030616435,0.0018667092,0.00056295126,0.00028136614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015957141,0.0006890504,0.0011714745,0.00007350202,0.00009125898,0.000009138246,0.002574556,0.000026906611,0.0015420066,0.7999293,0.0462262,0.14765064],"study_design_scores_gemma":[0.0014704317,0.000004525383,0.01337045,0.014421166,0.000057525132,0.000052522304,0.0000143440275,0.106885746,0.08075588,0.6917217,0.089063235,0.0021824867],"about_ca_topic_score_codex":0.00024904573,"about_ca_topic_score_gemma":0.000029513278,"teacher_disagreement_score":0.6359572,"about_ca_system_score_codex":0.00023934816,"about_ca_system_score_gemma":0.00027852558,"threshold_uncertainty_score":0.99990106},"labels":[],"label_agreement":null},{"id":"W4296938093","doi":"","title":"Validating a dynamic signature monitoring approach using the LTL model checking technique","year":2004,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Signature (topology); Computer science; Model checking; Algorithm; Mathematics","score_opus":0.03016117812969912,"score_gpt":0.2755443541943241,"score_spread":0.24538317606462498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296938093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004973517,0.0025289743,0.96168315,0.0007833113,0.00040087092,0.0027154307,0.00003481044,0.026609523,0.000270403],"genre_scores_gemma":[0.44799492,0.0000658489,0.54968274,0.00033498093,0.00017915726,0.0015172778,0.000020322648,0.00015309913,0.000051632574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99312645,0.0005127865,0.0012486028,0.0021239126,0.0012516694,0.0017365622],"domain_scores_gemma":[0.9927447,0.00043649197,0.0012614537,0.004747191,0.00042700273,0.00038319262],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0036752087,0.001385173,0.0010947487,0.001028461,0.0011590531,0.0018252489,0.0062817195,0.0018184159,0.0000013043472],"category_scores_gemma":[0.0009024787,0.0012269774,0.00066390354,0.0014095064,0.00022587185,0.00070319185,0.0061470517,0.004964606,0.0000020285117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019661797,0.00032844846,0.002105369,0.00052238523,0.00015066085,0.000115071845,0.0017404836,0.9537407,0.015566861,0.011743558,0.00032995341,0.013636845],"study_design_scores_gemma":[0.00016663231,0.00003870833,0.00018293713,0.001287919,0.000076740864,0.0003308952,0.000029216682,0.85215485,0.012882936,0.13171452,0.00000988198,0.0011247615],"about_ca_topic_score_codex":0.006249651,"about_ca_topic_score_gemma":0.000059125014,"teacher_disagreement_score":0.44302142,"about_ca_system_score_codex":0.0031560557,"about_ca_system_score_gemma":0.0018566957,"threshold_uncertainty_score":0.99988985},"labels":[],"label_agreement":null},{"id":"W4297854797","doi":"","title":"19 - A Comparison of the Specification Methods","year":2006,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Programming language","score_opus":0.04149303930787158,"score_gpt":0.31590510906213515,"score_spread":0.2744120697542636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297854797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037033663,0.0010528893,0.96477073,0.0051233186,0.00031809564,0.00037392843,0.000012151994,0.0024773919,0.022168124],"genre_scores_gemma":[0.25003585,0.000031980097,0.74836135,0.000053168278,0.000019048506,0.00004690718,0.000043147895,0.000020891175,0.0013876939],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99072456,0.007061508,0.0007194858,0.00074128236,0.00049117306,0.00026195892],"domain_scores_gemma":[0.989652,0.0031201898,0.0010979843,0.0044944882,0.0015455217,0.00008982263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071131117,0.00027965562,0.00041723115,0.00017846073,0.00030462616,0.00034077323,0.0040600486,0.0002611159,0.000008348201],"category_scores_gemma":[0.0033242044,0.00024297691,0.00025946408,0.00066936755,0.0002587414,0.00010765593,0.0030764074,0.00067006395,0.0000061474857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005003157,0.00123478,0.044592842,0.00032876813,0.000076060525,0.0000014235692,0.013516033,0.0003945699,0.002008341,0.21684162,0.059269536,0.661731],"study_design_scores_gemma":[0.0004288021,9.703626e-7,0.04953116,0.0032756852,0.00007958669,0.000018205295,0.000024506748,0.3275692,0.29076785,0.29392007,0.033390984,0.000992996],"about_ca_topic_score_codex":0.0021516953,"about_ca_topic_score_gemma":0.0001521551,"teacher_disagreement_score":0.660738,"about_ca_system_score_codex":0.000117020005,"about_ca_system_score_gemma":0.00030957282,"threshold_uncertainty_score":0.9908311},"labels":[],"label_agreement":null},{"id":"W4298876240","doi":"","title":"Automatic generation of vulnerability test suite for the Java Card verifier","year":2011,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Test suite; Java Card; Java; Suite; Vulnerability (computing); Operating system; Fuzz testing; Programming language; Computer security; Test case; Software; Real time Java","score_opus":0.04849763494859158,"score_gpt":0.26407298234755955,"score_spread":0.21557534739896797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298876240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02253767,0.0006529383,0.968007,0.0027308038,0.00037315176,0.0008625423,0.00004428412,0.0024086393,0.0023829541],"genre_scores_gemma":[0.6004183,0.000073716656,0.39857972,0.00006399778,0.000028084856,0.00023315503,0.00007064136,0.000022814134,0.0005095586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960246,0.0020291344,0.0005973819,0.00071525696,0.0003554688,0.00027815648],"domain_scores_gemma":[0.98628104,0.006867804,0.0006524688,0.003977171,0.0021330034,0.00008848691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007953113,0.0002761488,0.00036045178,0.00012339461,0.0003750331,0.00032452878,0.002620402,0.00022884058,0.000017862922],"category_scores_gemma":[0.0073217344,0.00023216566,0.00024291001,0.00025838893,0.00023571988,0.00014571569,0.001468377,0.0004065828,0.0000055395662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009623236,0.0015703896,0.011469521,0.0010181013,0.00023026258,0.0000028564052,0.033663917,0.00025397973,0.006202854,0.13241038,0.036595967,0.77657217],"study_design_scores_gemma":[0.00031072221,0.0000022721665,0.0059167747,0.0010219117,0.00006681265,0.000009281133,0.00001247502,0.7925206,0.12189875,0.07537037,0.0023533453,0.0005167269],"about_ca_topic_score_codex":0.0013477156,"about_ca_topic_score_gemma":0.0002768824,"teacher_disagreement_score":0.7922666,"about_ca_system_score_codex":0.0000832461,"about_ca_system_score_gemma":0.0003171351,"threshold_uncertainty_score":0.9467441},"labels":[],"label_agreement":null},{"id":"W4300469825","doi":"10.1145/2513228.2513286","title":"An interactive graph-based automation assistant","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Component (thermodynamics); Graph; Distributed computing; Interconnection; Computer network; Theoretical computer science","score_opus":0.024337433818536102,"score_gpt":0.3006874084814499,"score_spread":0.27634997466291383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300469825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056726425,0.00001571966,0.9496005,0.00041267395,0.00050601177,0.00028119757,0.0000031585346,0.041780837,0.0017272516],"genre_scores_gemma":[0.48040843,6.6941067e-7,0.51906896,0.00033140293,0.000030220594,0.000099125995,0.000019564039,0.000010538214,0.000031107367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983927,0.00014306465,0.00028010845,0.00067501975,0.00029502859,0.00021406809],"domain_scores_gemma":[0.9976101,0.00025970463,0.00025342486,0.0015093114,0.00025959837,0.00010787311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003216811,0.0002548022,0.00023265238,0.00031249286,0.00007984652,0.00073467364,0.0014558058,0.00021036294,0.00003562835],"category_scores_gemma":[0.00015233725,0.0002197135,0.00010699323,0.00018936086,0.000036539932,0.00042311128,0.00051949295,0.00042457358,0.00004922726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029340828,0.001674177,0.008012899,0.00055174343,0.0002035862,0.00009315856,0.00335199,0.007014915,0.000882287,0.06621893,0.2990152,0.6129518],"study_design_scores_gemma":[0.00006280929,0.00008410736,0.0038128917,0.00017538894,0.0000058552105,0.0000030843216,0.0000017836344,0.7686589,0.0013758503,0.2254128,0.00010249862,0.00030407106],"about_ca_topic_score_codex":0.00073447375,"about_ca_topic_score_gemma":0.0000079411175,"teacher_disagreement_score":0.76164395,"about_ca_system_score_codex":0.00010503714,"about_ca_system_score_gemma":0.00019104204,"threshold_uncertainty_score":0.8959657},"labels":[],"label_agreement":null},{"id":"W4300771635","doi":"10.1145/2001420","title":"Proceedings of the 2011 International Symposium on Software Testing and Analysis","year":2011,"lang":"en","type":"paratext","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software testing; Computer science; Software engineering; Software; Programming language","score_opus":0.03037372862193266,"score_gpt":0.2551291195448247,"score_spread":0.22475539092289204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300771635","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003057,0.00030303214,0.27015826,0.001306883,0.0035456975,0.0008328159,0.00008363051,0.008994288,0.7117184],"genre_scores_gemma":[0.024406597,0.00006067197,0.8854317,0.00088468625,0.000224326,0.000061553634,0.000012488169,0.000045124434,0.088872865],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9986045,0.00001349858,0.00030535946,0.00053452706,0.0003613484,0.0001808005],"domain_scores_gemma":[0.99830425,0.00035766503,0.00042081502,0.00041426503,0.00045272036,0.000050270828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026597257,0.00023823675,0.0003265137,0.0002859998,0.000100074845,0.00014386323,0.0015658429,0.00016939633,0.00012354087],"category_scores_gemma":[0.00043625032,0.0001570187,0.00014071794,0.0006422711,0.00008534893,0.00014356218,0.0008175571,0.00027728413,0.00008347412],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006077108,0.000098075834,0.051839255,0.00011426589,0.0004982257,0.0000012034853,0.000376683,0.000020805139,0.00005629446,0.0026949649,0.93185884,0.012435324],"study_design_scores_gemma":[0.0029350417,0.004544884,0.364257,0.0123248985,0.006057236,0.00063624606,0.000067223606,0.22515218,0.05495533,0.19719532,0.11892978,0.012944866],"about_ca_topic_score_codex":0.00037489051,"about_ca_topic_score_gemma":0.0000020286632,"teacher_disagreement_score":0.81292903,"about_ca_system_score_codex":0.000033083117,"about_ca_system_score_gemma":0.00005067837,"threshold_uncertainty_score":0.6403037},"labels":[],"label_agreement":null},{"id":"W4300949634","doi":"","title":"Integration testing of communicating systems with unknown components","year":2015,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Integration testing; Computer science; Programming language","score_opus":0.04369631623138119,"score_gpt":0.24079536833187573,"score_spread":0.19709905210049455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300949634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061503634,0.0003390093,0.9125252,0.0010660174,0.00006844259,0.00022191207,0.0000026481198,0.0026384469,0.021634737],"genre_scores_gemma":[0.5708027,0.0000047854055,0.42892125,0.000018964683,0.0000041180583,0.000016954158,0.00001558786,0.000011649621,0.00020399847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960352,0.0024973596,0.00043237218,0.00036094483,0.0004373116,0.00023680882],"domain_scores_gemma":[0.9917237,0.002664825,0.00050310406,0.001934721,0.003020567,0.00015306375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052628745,0.00017932826,0.00025378578,0.00014990557,0.00021990763,0.00027317097,0.0016508875,0.000073452895,0.0000010132425],"category_scores_gemma":[0.003828804,0.00015967223,0.000041741343,0.00082583155,0.00017040267,0.00034416324,0.0005764218,0.00023375986,0.00000667673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031493386,0.0015765813,0.06969969,0.00024077114,0.00011642154,0.000017749726,0.035005037,0.00082501926,0.016847303,0.5765153,0.004403991,0.29472065],"study_design_scores_gemma":[0.0010321132,0.0000073014803,0.005106908,0.004814791,0.00002563729,0.00012460213,0.00015686096,0.92940176,0.045511737,0.0108677,0.0023589018,0.00059169944],"about_ca_topic_score_codex":0.002561117,"about_ca_topic_score_gemma":0.00012770065,"teacher_disagreement_score":0.9285767,"about_ca_system_score_codex":0.00007461816,"about_ca_system_score_gemma":0.00016253062,"threshold_uncertainty_score":0.6511245},"labels":[],"label_agreement":null},{"id":"W4308627374","doi":"10.1145/3558489.3559073","title":"On the effectiveness of data balancing techniques in the context of ML-based test case prioritization","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Regression testing; Computer science; Context (archaeology); Prioritization; Regression analysis; Regression; Machine learning; Test data; Risk-based testing; Data mining; Reliability engineering; Artificial intelligence; Software; Software system; Statistics; Engineering; Software engineering","score_opus":0.034384400689239744,"score_gpt":0.2944197283149523,"score_spread":0.2600353276257125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308627374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09552133,0.00004525589,0.8997168,0.000640274,0.000056528665,0.0010068447,0.000039982227,0.0020694532,0.00090352213],"genre_scores_gemma":[0.9778539,4.2025104e-7,0.021678824,0.0003789946,0.000003952268,0.00007138435,0.000006611897,0.0000044959397,0.000001411904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986474,0.000647861,0.00017473397,0.00020429668,0.00023929712,0.000086418324],"domain_scores_gemma":[0.9880004,0.010749949,0.00009899766,0.0010880033,0.000054951302,0.000007732207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041341023,0.00006753257,0.00011070608,0.00008857495,0.00011072241,0.000022858081,0.0012925421,0.000016572247,0.000003976017],"category_scores_gemma":[0.0014966363,0.000040305975,0.000019098039,0.0005540218,0.000043419957,0.00009780352,0.0003752776,0.00013436686,1.6757146e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023011389,0.0037838067,0.20396346,0.000943312,0.00004695306,0.0012091066,0.006678756,0.0006865239,0.013204523,0.4336544,0.03270008,0.30289894],"study_design_scores_gemma":[0.0013310226,0.0031085827,0.024679286,0.0013262908,0.000033069955,0.0010659277,0.0007931507,0.5683755,0.29584107,0.1023101,0.00040459057,0.00073136017],"about_ca_topic_score_codex":0.0007300157,"about_ca_topic_score_gemma":0.000019278341,"teacher_disagreement_score":0.88233256,"about_ca_system_score_codex":0.0000310563,"about_ca_system_score_gemma":0.00006550191,"threshold_uncertainty_score":0.24018861},"labels":[],"label_agreement":null},{"id":"W4309874955","doi":"10.1016/j.jss.2022.111543","title":"Configuring mission-specific behavior in a product line of collaborating Small Unmanned Aerial Systems","year":2022,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Drone; Task (project management); Process (computing); Set (abstract data type); Computer science; Systems engineering; Software; Real-time computing; Distributed computing; Software engineering; Reliability engineering; Engineering; Operating system","score_opus":0.03856794910153191,"score_gpt":0.2618310104852299,"score_spread":0.22326306138369797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309874955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9448869,0.012859203,0.038457688,0.00010084014,0.0025380668,0.0005796769,0.000018477192,0.00054232334,0.00001680277],"genre_scores_gemma":[0.98052585,0.000038444625,0.01908714,0.000008741885,0.0002538255,0.000025806872,0.000001055012,0.00001470036,0.000044427605],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791074,0.00024946043,0.0009562281,0.0002348551,0.000444778,0.00020391367],"domain_scores_gemma":[0.99797404,0.00031165653,0.00091657904,0.00030680618,0.00039532018,0.000095577656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016794341,0.00014524552,0.0005024899,0.0003416333,0.00018021336,0.00016296301,0.0005045762,0.00004588572,0.0000018606406],"category_scores_gemma":[0.0003940791,0.00012609748,0.00005953064,0.0005148786,0.000028115202,0.00017670536,0.00020187192,0.00030663758,1.7046403e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012809386,0.0037087644,0.6437817,0.006817919,0.00040487509,0.0068837083,0.03560919,0.08808705,0.04529612,0.009545635,0.04281015,0.1157739],"study_design_scores_gemma":[0.05652478,0.05516408,0.19753152,0.07001533,0.0009326742,0.09802264,0.031753667,0.26135457,0.029307602,0.010869475,0.173175,0.0153486645],"about_ca_topic_score_codex":0.00018838211,"about_ca_topic_score_gemma":0.0000017801535,"teacher_disagreement_score":0.44625023,"about_ca_system_score_codex":0.00011223565,"about_ca_system_score_gemma":0.00021000573,"threshold_uncertainty_score":0.5142106},"labels":[],"label_agreement":null},{"id":"W4310506204","doi":"10.1145/3563767.3568132","title":"Evaluating the Quality of Student-Written Software Tests with Curated Mutation Analysis","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Correctness; Programming language; Assertion; Software engineering; Software quality; Code coverage; Software; Software testing; Test (biology); Invocation; Test case; Software development; Machine learning","score_opus":0.1151691530031579,"score_gpt":0.42743782641175704,"score_spread":0.31226867340859915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310506204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44146606,0.000022700095,0.55496854,0.00034363917,0.000027807508,0.0001495614,0.0000029043447,0.0029225764,0.00009622864],"genre_scores_gemma":[0.7683159,1.6201383e-7,0.2313391,0.00020768467,0.0000048693105,0.00005645324,0.0000056853746,0.000004118041,0.00006603695],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980295,0.0004579076,0.00029370675,0.00027865148,0.00080388127,0.00013640673],"domain_scores_gemma":[0.9976642,0.0011463333,0.00026525842,0.0006565875,0.00024281284,0.00002477002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002098082,0.00008864528,0.00017511616,0.0001403769,0.00032705892,0.00007075416,0.0008335816,0.000013261526,0.000030774056],"category_scores_gemma":[0.00046040837,0.00005657975,0.00006742023,0.0022557778,0.000037408292,0.0001294737,0.00038260283,0.00012678718,0.000001005583],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041931515,0.0004126136,0.8497679,0.000025961908,0.00059429154,0.000017470782,0.004572778,0.057827435,0.00032890384,0.0040165954,0.0016306081,0.080763504],"study_design_scores_gemma":[0.0003942759,0.001235009,0.70242655,0.000012911801,0.00020399228,0.000020229565,0.00024583767,0.280607,0.0002698611,0.014281863,0.000011654187,0.00029081147],"about_ca_topic_score_codex":0.00058140396,"about_ca_topic_score_gemma":0.000036099846,"teacher_disagreement_score":0.32684985,"about_ca_system_score_codex":0.000045338762,"about_ca_system_score_gemma":0.00008205744,"threshold_uncertainty_score":0.25155059},"labels":[],"label_agreement":null},{"id":"W4310673963","doi":"10.1016/j.infsof.2022.107129","title":"A probabilistic framework for mutation testing in deep neural networks","year":2022,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Testability; Context (archaeology); Machine learning; Probabilistic logic; Mutation; Set (abstract data type); Artificial intelligence; Test suite; Artificial neural network; Suite; Data mining; Model-based testing; Reliability engineering; Test case; Engineering","score_opus":0.01667141722285493,"score_gpt":0.2536663021430027,"score_spread":0.23699488492014775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310673963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011798713,0.00008639728,0.97883505,0.00066955376,0.00013829266,0.00038787766,0.0000021677483,0.00806535,0.00001661561],"genre_scores_gemma":[0.54785997,6.654372e-7,0.451323,0.00041250893,0.000006378547,0.00038444775,0.000008422591,0.0000038120018,8.1324305e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915415,0.000026912505,0.00031239545,0.00016180315,0.00011284985,0.00023191614],"domain_scores_gemma":[0.998724,0.00074109575,0.00015833315,0.00025314535,0.00009678962,0.00002665978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036578134,0.00010002244,0.00012633317,0.00046970195,0.00028230203,0.000083706735,0.00038880805,0.000105949934,0.000002090669],"category_scores_gemma":[0.0035997655,0.00010786853,0.000018577619,0.0010301183,0.00004873831,0.00047257193,0.0003203576,0.00031413807,7.925006e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073432116,0.000019581283,0.012170211,0.000030081559,0.0000023923494,0.0000045842335,0.00061363593,0.019882975,2.3154972e-7,0.05992569,0.00013936314,0.9072039],"study_design_scores_gemma":[0.0001514272,0.00014937272,0.000982531,0.0000099963045,0.0000014043237,0.00009935231,0.000032620013,0.660566,0.0000019007352,0.33770317,0.00020755816,0.00009469733],"about_ca_topic_score_codex":0.000017535476,"about_ca_topic_score_gemma":0.0000035143064,"teacher_disagreement_score":0.9071092,"about_ca_system_score_codex":0.00007196362,"about_ca_system_score_gemma":0.000029465453,"threshold_uncertainty_score":0.4398751},"labels":[],"label_agreement":null},{"id":"W4312260323","doi":"10.1109/tse.2022.3217544","title":"Dynamic Human-in-the-Loop Assertion Generation","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Assertion; Computer science; Programming language; TypeScript; JavaScript; Test (biology); Test case; Workflow; Notation; Automation; Software engineering; Variable (mathematics); Database; Arithmetic; Mathematics; Machine learning","score_opus":0.02170916402304557,"score_gpt":0.2527178957400945,"score_spread":0.23100873171704894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312260323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04391376,0.00003200619,0.9501663,0.00010632799,0.00058401364,0.0001535323,0.0000034664213,0.0050334376,0.0000071618874],"genre_scores_gemma":[0.90543044,0.0000022494255,0.09402318,0.0001632167,0.000017805436,0.00027606505,0.0000042402994,0.000018291454,0.00006448261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988868,0.000070144575,0.000200109,0.0002912585,0.00033320027,0.00021847735],"domain_scores_gemma":[0.99926084,0.00018391924,0.00003740201,0.0004643383,0.000023428158,0.000030056432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041990794,0.00013985502,0.0001034403,0.00029819418,0.00042838597,0.00009111392,0.0005620383,0.000037141832,0.000014163747],"category_scores_gemma":[0.00002376144,0.0001419721,0.00006939566,0.00066281104,0.000007883123,0.00021916065,0.000005189188,0.00043792566,0.000006134325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027805838,0.00018473882,0.00008227889,0.000015823069,0.00001158848,0.0000355966,0.0007506981,0.9722473,0.002918815,0.0004038073,0.0008221422,0.022524426],"study_design_scores_gemma":[0.0002582424,0.00021045443,0.00074151583,0.00002498923,0.000009362707,0.000108941575,0.000012289144,0.994596,0.002845647,0.00043012295,0.0004316919,0.0003307289],"about_ca_topic_score_codex":0.00003561301,"about_ca_topic_score_gemma":0.000009999077,"teacher_disagreement_score":0.8615167,"about_ca_system_score_codex":0.00019243619,"about_ca_system_score_gemma":0.000024693421,"threshold_uncertainty_score":0.5789454},"labels":[],"label_agreement":null},{"id":"W4312349853","doi":"10.1145/3524610.3527902","title":"XAI4FL","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Statement (logic); Computer science; Fault (geology); Ranking (information retrieval); Test (biology); Unit testing; Class (philosophy); Software bug; Problem statement; Test case; Software; Programming language; Artificial intelligence; Machine learning; Engineering","score_opus":0.013764278414417614,"score_gpt":0.22550378973091126,"score_spread":0.21173951131649366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312349853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010644192,0.000026454896,0.9461335,0.0011044783,0.00016837602,0.000032074597,2.4417153e-7,0.024670748,0.026799716],"genre_scores_gemma":[0.6223862,2.043958e-7,0.3749448,0.0013657418,0.000009683316,0.00002376175,2.8947653e-7,0.0000023065236,0.0012669737],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996155,0.000022348044,0.000043185522,0.000113864735,0.00012368236,0.00008142441],"domain_scores_gemma":[0.9996245,0.000059430662,0.0000121263465,0.0002762045,0.000008787567,0.000018978551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016187131,0.000027719998,0.00002920044,0.000037832546,0.00015053414,0.000028766573,0.0005227518,0.0000040978484,0.00010136391],"category_scores_gemma":[0.000029679424,0.000026024467,0.000015436877,0.00019469201,0.0000049304417,0.000057044417,0.0004922024,0.000058320747,0.000018711902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.244352e-7,0.0000444313,0.0031457744,0.0000013046026,0.0000023649209,0.000023826518,0.00023203244,0.000053723157,0.000049809245,0.21330309,0.6743675,0.10877552],"study_design_scores_gemma":[0.00014610139,0.00023574074,0.0019257406,0.0000022059335,0.000001317467,0.00020083146,0.000009229734,0.09937059,0.00094579003,0.6928463,0.20402783,0.0002883261],"about_ca_topic_score_codex":0.000032658394,"about_ca_topic_score_gemma":1.7893453e-7,"teacher_disagreement_score":0.6213218,"about_ca_system_score_codex":0.000016611219,"about_ca_system_score_gemma":0.000017126511,"threshold_uncertainty_score":0.11578021},"labels":[],"label_agreement":null},{"id":"W4312429593","doi":"10.1109/icsme55016.2022.00039","title":"What Made This Test Flake? Pinpointing Classes Responsible for Test Flakiness","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Regression testing; Code (set theory); Quality (philosophy); Fault (geology); Test (biology); Test suite; Class (philosophy); Reliability engineering; Debugging; Test case; Programming language; Software; Machine learning; Artificial intelligence; Software development; Engineering; Regression analysis","score_opus":0.030598165685785494,"score_gpt":0.2858525494159046,"score_spread":0.2552543837301191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312429593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008024589,0.0005865993,0.9087825,0.02018498,0.0027539434,0.0012006003,0.000026078544,0.05075511,0.0076856236],"genre_scores_gemma":[0.25411746,0.000016926148,0.7278015,0.0030674005,0.00019187863,0.0005834787,0.0000113027445,0.000049706785,0.0141603565],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981798,0.000075230775,0.000316426,0.000595593,0.00037466627,0.00045827933],"domain_scores_gemma":[0.99266577,0.006081781,0.00014563689,0.000861792,0.0001616665,0.00008332886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011478374,0.00019729766,0.0002143196,0.00023921311,0.0007920637,0.00070170226,0.0013427209,0.000048037156,0.00009527806],"category_scores_gemma":[0.0038314436,0.00018974433,0.0001005501,0.0008497089,0.00004379709,0.000916527,0.001018453,0.00022644014,0.0000232924],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003283675,0.0006246232,0.024458464,0.00012510753,0.000022851746,0.00007938822,0.0013155038,0.00012930368,0.010296773,0.025731642,0.8271123,0.11007122],"study_design_scores_gemma":[0.0016125179,0.0027204931,0.005546466,0.00041744782,0.00004503049,0.00079400575,0.00039646038,0.34120268,0.06326997,0.2677144,0.31401074,0.002269748],"about_ca_topic_score_codex":0.00006525146,"about_ca_topic_score_gemma":0.000010947958,"teacher_disagreement_score":0.5131015,"about_ca_system_score_codex":0.000094202594,"about_ca_system_score_gemma":0.00023657977,"threshold_uncertainty_score":0.7737549},"labels":[],"label_agreement":null},{"id":"W4312529070","doi":"10.1145/3510457.3513038","title":"The impact of flaky tests on historical test prioritization on chrome","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Prioritization; Blocking (statistics); Pipeline (software); Computer science; Test (biology); Reliability engineering; Work (physics); Code (set theory); Regression testing; Engineering; Software; Software development; Operating system; Programming language; Computer network","score_opus":0.019321535303824963,"score_gpt":0.28688465220610365,"score_spread":0.2675631169022787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312529070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36646804,0.0007226608,0.47005337,0.01530252,0.0036417549,0.0023138686,0.000036703623,0.068052985,0.07340809],"genre_scores_gemma":[0.99226624,0.0000024056305,0.006913432,0.00012599178,0.000031172454,0.000022393357,0.0000010386645,0.000006838227,0.0006304906],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.999153,0.000054887398,0.00014396943,0.00018866113,0.00031561963,0.00014381707],"domain_scores_gemma":[0.99791175,0.0014236983,0.00007876329,0.0005002368,0.000049175193,0.000036356025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032759382,0.000080521095,0.000087598426,0.0000787905,0.00030236816,0.000040076222,0.00059910107,0.000017515478,0.000011806867],"category_scores_gemma":[0.00079200405,0.000051577346,0.00006159313,0.00041876576,0.00001696718,0.00005117848,0.00017825958,0.000137742,0.000006554196],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003120535,0.001054113,0.053655684,0.000009334728,0.000020024292,0.000026813703,0.00049010746,0.0022127512,0.0014001379,0.026228694,0.8001169,0.114754215],"study_design_scores_gemma":[0.0011397004,0.026419336,0.5193407,0.00012427254,0.000014507225,0.00019940194,0.0000115802,0.23370004,0.005238699,0.1923454,0.020269962,0.0011963848],"about_ca_topic_score_codex":0.00023129383,"about_ca_topic_score_gemma":0.0000012676636,"teacher_disagreement_score":0.77984697,"about_ca_system_score_codex":0.0005900372,"about_ca_system_score_gemma":0.00008472329,"threshold_uncertainty_score":0.2325602},"labels":[],"label_agreement":null},{"id":"W4312663631","doi":"10.1007/978-3-031-19762-8_14","title":"Model-Driven Engineering in Digital Thread Platforms: A Practical Use Case and Future Challenges","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Galway; Science Foundation Ireland; European Commission; National University of Ireland","keywords":"Computer science; Interoperability; Software engineering; Model-driven architecture; Thread (computing); Orchestration; Context (archaeology); Software; Distributed computing; Software development; World Wide Web; Programming language","score_opus":0.05086537225321081,"score_gpt":0.2692703214509965,"score_spread":0.2184049491977857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312663631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001162519,0.0006140094,0.9948923,0.0007784956,0.00036242377,0.0002822278,0.000007721985,0.0016904601,0.00020981928],"genre_scores_gemma":[0.22179763,0.000319566,0.7772243,0.00030772242,0.0002574477,0.000024725112,0.000003799522,0.000044820103,0.000019952662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971074,0.000008539724,0.00037946572,0.0013136781,0.00063598255,0.0005549446],"domain_scores_gemma":[0.9974908,0.0011555181,0.00015522669,0.00095013354,0.00008875864,0.00015953631],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005078145,0.00047448042,0.00044153765,0.00082466076,0.00016854423,0.0007271978,0.0010595844,0.00027070148,0.0000028136833],"category_scores_gemma":[0.00030742155,0.00044251495,0.00006733806,0.00037507928,0.00022297767,0.0020084633,0.001900519,0.0012651355,0.0000016560374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011149884,0.000067521265,0.00030956182,0.000094169896,0.0000133995,0.0073978575,0.0034708271,0.08378496,0.0000025253578,0.11574773,0.000039855284,0.7890605],"study_design_scores_gemma":[0.00015603928,0.00014990328,0.00003669693,0.00017719767,0.000003405404,0.004305962,2.5768907e-7,0.8162206,0.0000061822066,0.17797223,0.0004906703,0.00048085864],"about_ca_topic_score_codex":0.000026442069,"about_ca_topic_score_gemma":0.000044121858,"teacher_disagreement_score":0.7885796,"about_ca_system_score_codex":0.00026672054,"about_ca_system_score_gemma":0.0002993416,"threshold_uncertainty_score":0.99980265},"labels":[],"label_agreement":null},{"id":"W4312751706","doi":"10.1007/978-3-031-19756-7_17","title":"On Technical Debt in Software Testing - Observations from Industry","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Technical debt; Computer science; Agile software development; Code refactoring; Test suite; Test case; Software engineering; Test Management Approach; White-box testing; Code coverage; Automation; Test (biology); Software; Software system; Software development; Programming language; Software construction; Engineering; Machine learning","score_opus":0.05620035206899127,"score_gpt":0.2735181785792026,"score_spread":0.2173178265102113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312751706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000732479,0.00013025841,0.9916401,0.0006615011,0.00080541754,0.00034904768,0.000016338145,0.0045148325,0.0011500553],"genre_scores_gemma":[0.086246066,0.0000040762716,0.91068375,0.0027029286,0.00019419804,0.000048873902,0.000014892261,0.000046794314,0.000058397967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99565685,0.0000644495,0.0006394453,0.0018270192,0.0011465049,0.00066571817],"domain_scores_gemma":[0.9922028,0.005363168,0.00030611007,0.0018186101,0.00015956318,0.00014970437],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009924521,0.0005381168,0.00052609557,0.0011170716,0.00038115325,0.0003913308,0.004256535,0.00064866425,0.000038454746],"category_scores_gemma":[0.003025729,0.00054782926,0.00009415191,0.0017036977,0.00038428433,0.00047544145,0.0024705727,0.0034557509,0.000012826044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009126733,0.00016388667,0.019925592,0.000028791845,0.000009178907,0.0005753759,0.00048246104,0.06585254,0.0000817957,0.027395232,0.00060615083,0.8848699],"study_design_scores_gemma":[0.00017447764,0.00022967007,0.007293069,0.0008511447,0.000004409322,0.000052797914,3.862677e-8,0.10479552,0.00007970812,0.88547194,0.00033245684,0.00071475835],"about_ca_topic_score_codex":0.0004006286,"about_ca_topic_score_gemma":0.00009912672,"teacher_disagreement_score":0.8841551,"about_ca_system_score_codex":0.00074617786,"about_ca_system_score_gemma":0.00080877123,"threshold_uncertainty_score":0.9996973},"labels":[],"label_agreement":null},{"id":"W4312785754","doi":"10.1145/3510454.3516840","title":"MASS","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; European Commission","keywords":"Computer science; Software; Cyber-physical system; Operating system","score_opus":0.015569225563169567,"score_gpt":0.23125383672071712,"score_spread":0.21568461115754756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312785754","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033823194,0.000020090278,0.94882756,0.0009197721,0.00013038823,0.000023788607,1.9318834e-7,0.018856075,0.030883877],"genre_scores_gemma":[0.4915299,1.8296416e-7,0.5062095,0.0009487178,0.000007373193,0.000019361185,2.1957645e-7,0.0000018707971,0.0012828876],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996439,0.000020822623,0.000038863425,0.000104376115,0.000116413976,0.00007561892],"domain_scores_gemma":[0.9996599,0.000052570536,0.000010959813,0.00025177005,0.000007754883,0.000017050741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014969253,0.00002532886,0.00002642741,0.00003430358,0.00012847708,0.000027401633,0.00048264276,0.000003879025,0.00008743897],"category_scores_gemma":[0.000022721446,0.00002384396,0.000013770072,0.00017452642,0.000004160812,0.000050986935,0.00028865237,0.00005336739,0.000015664926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.721655e-7,0.000031675838,0.0056574172,0.0000015280649,0.000002861995,0.00003134416,0.00022027006,0.000102396036,0.00016293356,0.31615365,0.5877074,0.08992774],"study_design_scores_gemma":[0.000074480406,0.00011124796,0.0004777238,0.000001049982,6.4528535e-7,0.000057519712,0.000005589879,0.06967519,0.0005439707,0.8688935,0.060013175,0.00014588583],"about_ca_topic_score_codex":0.00001938855,"about_ca_topic_score_gemma":6.9287836e-8,"teacher_disagreement_score":0.55273986,"about_ca_system_score_codex":0.000016017499,"about_ca_system_score_gemma":0.000014395226,"threshold_uncertainty_score":0.098815486},"labels":[],"label_agreement":null},{"id":"W4312796785","doi":"10.1145/3510454.3516856","title":"DScribe","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Documentation; Computer science; Redundancy (engineering); Unit testing; Artifact (error); Technical documentation; Template; Software engineering; Programming language; Software; Operating system; Artificial intelligence","score_opus":0.014937335638861552,"score_gpt":0.22409066610293493,"score_spread":0.2091533304640734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312796785","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006595055,0.000029635126,0.9379931,0.0013823082,0.00019039352,0.000033822053,3.0519152e-7,0.025921598,0.03378933],"genre_scores_gemma":[0.6331468,2.0130537e-7,0.36397365,0.0016246511,0.000009570662,0.000024061066,3.3210625e-7,0.0000023152709,0.0012184103],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99960744,0.000022995075,0.00004404128,0.00011550963,0.0001260667,0.00008396596],"domain_scores_gemma":[0.999626,0.000054560805,0.000011798391,0.0002787933,0.000009388033,0.000019462486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016105657,0.000028307451,0.000029649873,0.000037343616,0.00015371823,0.0000299757,0.00052885275,0.0000041333087,0.00014502788],"category_scores_gemma":[0.000030205514,0.000026627846,0.000015790523,0.00019474662,0.0000049406867,0.000060600752,0.0005050636,0.000059510377,0.000017103519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7659208e-7,0.000034169236,0.0018885366,9.798529e-7,0.0000018071385,0.000018615838,0.00019918449,0.00003337749,0.00003358907,0.24548148,0.68252724,0.06978054],"study_design_scores_gemma":[0.00011463938,0.00018896839,0.0010648839,0.0000017957284,0.0000011148954,0.00016712619,0.000009028082,0.07467245,0.0007511653,0.7458889,0.17690647,0.00023348971],"about_ca_topic_score_codex":0.00003503792,"about_ca_topic_score_gemma":1.8011514e-7,"teacher_disagreement_score":0.6324873,"about_ca_system_score_codex":0.000016766748,"about_ca_system_score_gemma":0.000016932152,"threshold_uncertainty_score":0.15879537},"labels":[],"label_agreement":null},{"id":"W4312834255","doi":"10.1109/tse.2022.3213041","title":"Data-Driven Mutation Analysis for Cyber-Physical Systems","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; European Space Agency","keywords":"Computer science; Interoperability; Test suite; Set (abstract data type); Data mining; Suite; Mutation; Software; Quality (philosophy); Programming language; Software engineering; Theoretical computer science; Test case; Machine learning; World Wide Web","score_opus":0.03462965960977726,"score_gpt":0.27028679770145464,"score_spread":0.23565713809167738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312834255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003439213,0.000026504791,0.9860259,0.000027891809,0.0007185461,0.000253482,0.0002762047,0.009229759,0.0000024619662],"genre_scores_gemma":[0.7525599,7.819052e-7,0.2468948,0.00002508685,0.000044059798,0.00037299143,0.000041188927,0.000022163616,0.000039023773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869174,0.00003843507,0.00020485805,0.00049267453,0.0003269382,0.00024538537],"domain_scores_gemma":[0.9981291,0.0007262564,0.00006329727,0.0009523332,0.000058495985,0.00007048906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025651604,0.00016365082,0.00023628795,0.000456239,0.0003435593,0.00011425762,0.00091442646,0.00003260106,0.0000041068233],"category_scores_gemma":[0.000055289758,0.00018573695,0.00014984152,0.0011886561,0.000009391322,0.00030637012,0.000017067687,0.00024273871,0.0000038144044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033907686,0.00006969737,0.000030878866,0.00001875937,0.00015348576,0.0000067740266,0.0001733591,0.99422455,0.000022042883,0.00016709116,0.00045406524,0.0046759266],"study_design_scores_gemma":[0.00013376231,0.000112521506,0.000082428225,0.000010523905,0.0001308493,0.00002126903,0.00000678181,0.99819505,0.00020535907,0.00009024677,0.00080108736,0.00021010461],"about_ca_topic_score_codex":0.000049840884,"about_ca_topic_score_gemma":0.0000020684379,"teacher_disagreement_score":0.74912065,"about_ca_system_score_codex":0.00013446197,"about_ca_system_score_gemma":0.00004012513,"threshold_uncertainty_score":0.75741327},"labels":[],"label_agreement":null},{"id":"W4313119435","doi":"10.1145/3568364.3568380","title":"Identifying Candidate Classes for Unit Testing Using Deep Learning Classifiers: An Empirical Validation","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Unit testing; Empirical research; Unit (ring theory); Deep learning; Statistics; Mathematics","score_opus":0.21395416272102558,"score_gpt":0.3930138495221044,"score_spread":0.1790596868010788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313119435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12177448,0.00002125632,0.86998796,0.00008728693,0.00019473917,0.00016635831,0.0000010656893,0.0075265164,0.00024034013],"genre_scores_gemma":[0.49869794,3.259897e-7,0.50098354,0.00013904198,0.00004583833,0.00004285165,0.000011565702,0.000015533009,0.00006336384],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830186,0.00025405208,0.00027216796,0.0004857229,0.00032698808,0.00035922485],"domain_scores_gemma":[0.9983185,0.00089083554,0.00017243638,0.00036677712,0.0001579713,0.00009345965],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001048953,0.00014607453,0.00015329015,0.00023408377,0.0013647428,0.00045481592,0.0006648544,0.000042089436,0.000015761747],"category_scores_gemma":[0.0008115569,0.00015476847,0.000050475493,0.0008089479,0.000026023103,0.0007076923,0.00048790473,0.00028990683,0.0000016539692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004115907,0.00035600274,0.5169733,0.00014526474,0.000068042136,0.0000706817,0.0058642756,0.06856468,0.008419808,0.0066403425,0.0037590882,0.38909733],"study_design_scores_gemma":[0.0001687816,0.00023001025,0.0012653492,0.000018986104,0.0000125102015,0.00010476739,0.00019263766,0.97821677,0.0009241902,0.017873153,0.0007398264,0.00025301395],"about_ca_topic_score_codex":0.0002693063,"about_ca_topic_score_gemma":0.000008601743,"teacher_disagreement_score":0.9096521,"about_ca_system_score_codex":0.00013990242,"about_ca_system_score_gemma":0.00013029108,"threshold_uncertainty_score":0.9999353},"labels":[],"label_agreement":null},{"id":"W4315606067","doi":"10.1145/3571253","title":"Taking Back Control in an Intermediate Representation for GPU Computing","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Compiler; Fuzz testing; Programming language; Control flow; Software engineering; Formal specification; Formal methods; Process (computing); Set (abstract data type); Software","score_opus":0.04405870110884504,"score_gpt":0.346137627226172,"score_spread":0.30207892611732695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315606067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820181,0.0000375535,0.010183098,0.0016208418,0.00021028084,0.0009367592,0.0000024140345,0.0048339698,0.00015699214],"genre_scores_gemma":[0.8636945,0.0000011125938,0.13598071,0.00016171558,0.00006356292,0.00005828126,0.0000018821139,0.00001559506,0.000022650993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998827,0.00001628904,0.00026980325,0.00035425485,0.00021930246,0.00031338588],"domain_scores_gemma":[0.9984976,0.0005300543,0.0003438508,0.00044107926,0.00015109256,0.00003633524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008976133,0.0001258368,0.00018550674,0.00021050133,0.00009797588,0.00018952765,0.0019841443,0.000054442953,6.2781186e-7],"category_scores_gemma":[0.004654191,0.00009695345,0.00007464437,0.0007634771,0.0000492025,0.00028133832,0.0005412544,0.00013410715,0.0000030659492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005054048,0.00012574342,0.23262353,0.0002728552,0.000021656215,0.0000038427393,0.00744779,0.000096725,0.0060806866,0.0034860675,0.0035753367,0.7462152],"study_design_scores_gemma":[0.0046993624,0.0021859012,0.34324014,0.0039417334,0.000066749875,0.000047613652,0.0027894215,0.40106785,0.08621111,0.15356588,0.0006995098,0.0014847292],"about_ca_topic_score_codex":0.000048701855,"about_ca_topic_score_gemma":0.0000035194505,"teacher_disagreement_score":0.7447305,"about_ca_system_score_codex":0.000029477227,"about_ca_system_score_gemma":0.000013165429,"threshold_uncertainty_score":0.55718374},"labels":[],"label_agreement":null},{"id":"W4319296048","doi":"10.1145/3579640","title":"<scp>Katana</scp> : Dual Slicing Based Context for Learning Bug Fixes","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Program slicing; Debugging; Leverage (statistics); Slicing; Context (archaeology); Program comprehension; Software; Statement (logic); Software engineering; Programming language; Artificial intelligence; Software system; World Wide Web","score_opus":0.0980160634797238,"score_gpt":0.31874940585467515,"score_spread":0.22073334237495135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319296048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011221275,0.00012091245,0.97171956,0.00023962167,0.0005533971,0.00017949542,0.000010275913,0.015951471,0.000003964952],"genre_scores_gemma":[0.13928589,0.000027478436,0.85997945,0.00022193418,0.000047880727,0.00015419035,0.000008486399,0.00003922333,0.00023546435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846286,0.00018271485,0.00024450553,0.0005010058,0.0001353594,0.00047355655],"domain_scores_gemma":[0.978791,0.02044156,0.000061511324,0.0005040626,0.000081577455,0.00012026844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013961601,0.00023558257,0.00033145733,0.00048364804,0.00031667715,0.00007057812,0.00038538707,0.00017354243,0.0000017208101],"category_scores_gemma":[0.010178397,0.00024482646,0.00011407614,0.00058501115,0.000040627554,0.00013601387,0.000029180923,0.00039135377,0.000008219636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019526527,0.00006662147,0.0014220094,0.00032317382,0.00014759049,0.0000462757,0.0025060868,0.21384183,0.001393289,0.0012582314,0.0034931004,0.77548224],"study_design_scores_gemma":[0.002051758,0.0015983623,0.0047864364,0.00046786162,0.0001402141,0.00024549256,0.0002537874,0.9093024,0.024176085,0.014401397,0.04181937,0.00075681007],"about_ca_topic_score_codex":0.000047109374,"about_ca_topic_score_gemma":0.0000029448747,"teacher_disagreement_score":0.77472544,"about_ca_system_score_codex":0.000030298183,"about_ca_system_score_gemma":0.000047313137,"threshold_uncertainty_score":0.9983734},"labels":[],"label_agreement":null},{"id":"W4319594569","doi":"10.1145/3583566","title":"COMET: Coverage-guided Model Generation For Deep Learning Library Testing","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Comet; Computer science; Layer (electronics); Set (abstract data type); Test set; Artificial intelligence; Machine learning; Algorithm; Data mining; Programming language; Chemistry","score_opus":0.21094581494621803,"score_gpt":0.3372706176748377,"score_spread":0.12632480272861965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319594569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051857023,0.00008061553,0.9763682,0.00021463513,0.00038600902,0.00016254156,0.000005722479,0.017590472,0.0000060855045],"genre_scores_gemma":[0.05716598,0.0000573755,0.9421505,0.0001781405,0.00006846637,0.00014743478,0.000014430401,0.000041102252,0.00017658056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987992,0.0001234289,0.0002268874,0.00042828333,0.00010103721,0.00032117788],"domain_scores_gemma":[0.9931397,0.0062516467,0.00005366887,0.00041132155,0.00005647064,0.000087236935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007956628,0.00018408301,0.00023712682,0.0003953178,0.0002916865,0.000087163324,0.00034537094,0.00014001068,0.0000017078946],"category_scores_gemma":[0.004808644,0.00019523471,0.00006671017,0.0006426124,0.000020333297,0.00027739664,0.000035052384,0.0002798914,0.0000038318126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042321853,0.000011779248,0.00022810599,0.000045468387,0.000020813202,0.000003839242,0.00026972126,0.7225696,0.0009941804,0.00046235518,0.00039563465,0.27499428],"study_design_scores_gemma":[0.00021153712,0.00014309832,0.00018064995,0.000029468096,0.000014816655,0.000042436477,0.0000025086265,0.98696196,0.0020899037,0.009750651,0.00036212028,0.00021086106],"about_ca_topic_score_codex":0.0000067673404,"about_ca_topic_score_gemma":2.703156e-7,"teacher_disagreement_score":0.2747834,"about_ca_system_score_codex":0.000018946977,"about_ca_system_score_gemma":0.000035289522,"threshold_uncertainty_score":0.796144},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0456312420782707,"score_gpt":0.2955049233390974,"score_spread":0.2498736812608267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322489317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46735862,0.000010726057,0.52071446,0.00011009374,0.00023509686,0.00032408713,0.00001917196,0.011221113,0.000006618931],"genre_scores_gemma":[0.57909185,6.0408337e-7,0.42075267,0.00002110248,0.000041079602,0.000022895096,0.00005871048,0.000009815505,0.0000012963166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983119,0.00013975463,0.00048515107,0.00057761476,0.00022062354,0.00026496066],"domain_scores_gemma":[0.9937956,0.0041784034,0.00033891905,0.0007160111,0.00084511255,0.00012597124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020192964,0.00016146236,0.0002278625,0.000099981255,0.0003682111,0.00010201705,0.00044427149,0.00011378238,2.6427693e-7],"category_scores_gemma":[0.016846806,0.00016118179,0.00003771846,0.001451455,0.00017320743,0.00028349046,0.00012450464,0.00013078662,0.0000016025073],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011889842,0.00008093044,0.92058694,0.00036442018,0.00000634468,9.222547e-7,0.00076356245,0.0012075987,0.002893696,0.002519441,0.001064881,0.07049934],"study_design_scores_gemma":[0.00029366234,0.00025587884,0.42577252,0.00011730203,0.000009659437,0.0000052985047,0.000012747297,0.42430222,0.0012387368,0.14775926,0.00002303252,0.0002096751],"about_ca_topic_score_codex":0.00011762573,"about_ca_topic_score_gemma":3.5803518e-7,"teacher_disagreement_score":0.49481446,"about_ca_system_score_codex":0.000044349927,"about_ca_system_score_gemma":0.00013024734,"threshold_uncertainty_score":0.9914347},"labels":[],"label_agreement":null},{"id":"W4322754178","doi":"10.1016/j.jss.2023.111666","title":"An empirical evaluation of quasi-static executable slices","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"Program slicing; Slicing; Executable; Computer science; Static analysis; Set (abstract data type); Closure (psychology); Programming language; Program analysis; Algorithm","score_opus":0.08142813142564716,"score_gpt":0.3702531606239323,"score_spread":0.2888250291982852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322754178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6214962,0.0011029099,0.3756624,0.00015435251,0.00044008173,0.00013540062,0.0000028310646,0.000984173,0.00002166328],"genre_scores_gemma":[0.95574605,0.000028624614,0.04408665,0.0000286214,0.00007827233,0.000004942288,8.7716705e-7,0.0000072168923,0.00001875393],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837214,0.0002182072,0.00045393006,0.00013029399,0.0006902433,0.00013521008],"domain_scores_gemma":[0.99818134,0.00039234696,0.00042716358,0.00025116277,0.00065369037,0.00009430084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032432503,0.00008329873,0.0002669952,0.00024297333,0.00007190236,0.00012261634,0.0003306602,0.000054694334,0.0000018908582],"category_scores_gemma":[0.00072852866,0.00006328318,0.000046533467,0.00039641038,0.00002542619,0.00046171865,0.000045480025,0.00009690266,0.000001680133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043788532,0.0005449085,0.54615706,0.0011837977,0.00019576853,0.00016356994,0.017798742,0.010233214,0.00065339735,0.0012557912,0.097398214,0.32437173],"study_design_scores_gemma":[0.0010503335,0.002039123,0.08094359,0.0014561533,0.00011601365,0.0007813874,0.00070708257,0.872532,0.00022369472,0.038586054,0.0011916793,0.00037286218],"about_ca_topic_score_codex":0.00008765349,"about_ca_topic_score_gemma":0.0000016214976,"teacher_disagreement_score":0.8622988,"about_ca_system_score_codex":0.000030239202,"about_ca_system_score_gemma":0.00014555285,"threshold_uncertainty_score":0.25806132},"labels":[],"label_agreement":null},{"id":"W4323316606","doi":"10.1007/s10270-023-01086-5","title":"Efficient regression testing of distributed real-time reactive systems in the context of model-driven development","year":2023,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regression testing; Context (archaeology); Timestamp; Overhead (engineering); TRACE (psycholinguistics); Distributed computing; Regression; Real-time computing; Programming language; Software development; Statistics","score_opus":0.06037124717234388,"score_gpt":0.2836356329457989,"score_spread":0.22326438577345503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323316606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31911308,0.00014727186,0.677114,0.000017455412,0.00014170741,0.00051601947,0.000020894611,0.0028956574,0.000033907912],"genre_scores_gemma":[0.9214289,0.0000037728637,0.078347735,0.000005612749,0.000022595277,0.00012918297,0.000026009424,0.000024285999,0.000011898273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684364,0.0002947973,0.0010969308,0.00052443414,0.0007998347,0.00044033927],"domain_scores_gemma":[0.9964589,0.0014831021,0.0005975707,0.000853524,0.0005417243,0.00006518874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023045659,0.00026949667,0.0005805471,0.00034698157,0.00017845136,0.000080480655,0.0010687081,0.00013826946,9.509071e-8],"category_scores_gemma":[0.0012270621,0.00019441167,0.00007705316,0.0014630492,0.000046892095,0.0001130638,0.00033764265,0.00021637442,0.000006184902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008478836,0.000052517018,0.0021305436,0.00024680857,0.000013820622,0.0000136625085,0.0050496757,0.98924875,0.00080987584,0.00036338525,0.00025455773,0.0018079219],"study_design_scores_gemma":[0.00019930417,0.000043761058,0.00012257553,0.003067708,0.000007985373,0.000020053278,0.00048410348,0.99534696,0.00017024184,0.00032667737,0.0000049879654,0.00020565855],"about_ca_topic_score_codex":0.0017338003,"about_ca_topic_score_gemma":0.0000030808812,"teacher_disagreement_score":0.60231584,"about_ca_system_score_codex":0.00018603857,"about_ca_system_score_gemma":0.00029786202,"threshold_uncertainty_score":0.79278773},"labels":[],"label_agreement":null},{"id":"W4361986063","doi":"10.1109/tse.2023.3256322","title":"Metamorphic Testing for Web System Security","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Computer science; Oracle; Security testing; Executable; Fuzz testing; Web application; Programming language; Database; Software engineering; Software; World Wide Web; Operating system; Cloud computing; Cloud computing security","score_opus":0.029534783520755,"score_gpt":0.24176754022297112,"score_spread":0.2122327567022161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361986063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059569743,0.000022787475,0.9242575,0.000034441342,0.0010799095,0.00027289338,0.000025735884,0.06833495,0.000014801593],"genre_scores_gemma":[0.646238,0.0000010824534,0.35336775,0.000022931463,0.00005293441,0.00024869206,0.0000014436268,0.0000364167,0.00003071459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858224,0.000021562333,0.00026565432,0.0004417525,0.00024663855,0.0004421304],"domain_scores_gemma":[0.9975663,0.0015867765,0.000053608903,0.0005552942,0.00012363581,0.00011438698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004722941,0.00023377311,0.00023545495,0.00044437335,0.0002560407,0.00012139427,0.000516942,0.00010273477,0.0000012861686],"category_scores_gemma":[0.0002954843,0.000248931,0.00014323721,0.0014070065,0.0000135007995,0.00025116227,0.000006038517,0.00024735346,0.000050774186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032029027,0.00027423468,0.0008696521,0.0027007286,0.0003764776,0.00022052086,0.0016125465,0.8141029,0.005875784,0.0049760784,0.014432539,0.15452655],"study_design_scores_gemma":[0.00024420835,0.00012484247,0.00015679003,0.00029530335,0.000023782608,0.000058574977,0.000005950233,0.9921062,0.005720155,0.00044894248,0.00045445844,0.00036077594],"about_ca_topic_score_codex":0.00001507822,"about_ca_topic_score_gemma":9.320522e-7,"teacher_disagreement_score":0.6402811,"about_ca_system_score_codex":0.000109540735,"about_ca_system_score_gemma":0.000059912934,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4362676437","doi":"10.1145/3586049","title":"Pushing the Limit of 1-Minimality of Language-Agnostic Program Reduction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Programming language; Reduction (mathematics); Computer science; Syntax; Implementation; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.027250278268288686,"score_gpt":0.3119918759498543,"score_spread":0.2847415976815656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362676437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99188614,0.00019717134,0.00010543115,0.0023459822,0.00014772823,0.000714815,0.000003016993,0.004171086,0.00042861307],"genre_scores_gemma":[0.9165206,0.000012781581,0.08322207,0.00002555528,0.000049541337,0.0000940577,0.0000011507127,0.000016278102,0.000057977242],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849635,0.000027395663,0.0003852749,0.00030008948,0.0005030544,0.00028780825],"domain_scores_gemma":[0.99772924,0.00054381276,0.00056271144,0.00086100795,0.0002690023,0.000034206183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001285646,0.00015789834,0.00024626407,0.00015540782,0.00012217132,0.000083770195,0.0029954049,0.000073208124,8.5473425e-7],"category_scores_gemma":[0.008172713,0.00009545082,0.00015025708,0.0013842892,0.0002298287,0.00018224677,0.0011514626,0.00021889496,0.0000017994666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037457732,0.00040434024,0.019134127,0.00082357513,0.00008366144,0.0000029829307,0.017131908,0.000018002103,0.029380472,0.0061389366,0.0068708966,0.9199736],"study_design_scores_gemma":[0.00055237836,0.00173956,0.05689075,0.002438754,0.00015149877,0.00009117721,0.0049898657,0.0017786083,0.88939446,0.040406037,0.00096837536,0.00059852854],"about_ca_topic_score_codex":0.00015941123,"about_ca_topic_score_gemma":0.0000013909593,"teacher_disagreement_score":0.9193751,"about_ca_system_score_codex":0.000019722469,"about_ca_system_score_gemma":0.000029886121,"threshold_uncertainty_score":0.9784091},"labels":[],"label_agreement":null},{"id":"W4367672983","doi":"10.1016/j.jss.2023.111734","title":"GitHub Copilot AI pair programmer: Asset or Liability?","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":340,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Programmer; Liability; Asset (computer security); Computer science; Computer security; Software engineering; Business; Programming language; Finance","score_opus":0.0401045157013695,"score_gpt":0.30122540886373395,"score_spread":0.2611208931623644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367672983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11872805,0.0022475095,0.85683924,0.004014459,0.0028885335,0.00071849255,0.000018118835,0.014478772,0.000066848595],"genre_scores_gemma":[0.8570566,0.000088842964,0.14115776,0.00039658422,0.00038480654,0.000031064785,0.0000025847535,0.00003328644,0.00084846327],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839944,0.00011569855,0.0005481407,0.00022252699,0.00042998034,0.0002841927],"domain_scores_gemma":[0.9980904,0.00062231143,0.0003392537,0.00037439994,0.00038712844,0.00018651511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015743411,0.00015339776,0.00037457794,0.00022575467,0.00014758138,0.00040634177,0.00051879446,0.00009184073,0.0000020905034],"category_scores_gemma":[0.0012035668,0.000101842925,0.000090608766,0.00061066047,0.000050983293,0.00045029106,0.00016715746,0.0002499911,0.00001071821],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005067293,0.00018111117,0.38308927,0.0008204465,0.00011375953,0.0007929514,0.0012903353,0.00013118268,0.000020998887,0.0012267872,0.48645508,0.12582742],"study_design_scores_gemma":[0.00529501,0.013624322,0.2095333,0.009799542,0.00021306661,0.015305363,0.0006704932,0.063830584,0.0003097507,0.078384906,0.5998933,0.0031403846],"about_ca_topic_score_codex":0.000063883635,"about_ca_topic_score_gemma":0.0000022014733,"teacher_disagreement_score":0.7383286,"about_ca_system_score_codex":0.000041022322,"about_ca_system_score_gemma":0.00016929925,"threshold_uncertainty_score":0.41530338},"labels":[],"label_agreement":null},{"id":"W4367692815","doi":"10.48550/arxiv.2305.00083","title":"Reflections on Surrogate-Assisted Search-Based Testing: A Taxonomy and Two Replication Studies based on Industrial ADAS and Simulink Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Computer science; Benchmark (surveying); Replication (statistics); Taxonomy (biology); Generalization; Machine learning; Heuristic; Artificial intelligence; Domain (mathematical analysis); Reliability engineering; Engineering","score_opus":0.6868043205396952,"score_gpt":0.3359967428355055,"score_spread":0.3508075777041897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367692815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1441168,0.00003170883,0.8403856,0.001089988,0.00035472482,0.0012431609,0.000033359116,0.011940664,0.0008039734],"genre_scores_gemma":[0.9717351,0.000016214199,0.027814163,0.00018964104,0.00005678877,0.000019782457,0.000015915033,0.00002599489,0.0001263506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745613,0.00028678423,0.00023168905,0.0015820919,0.00014732583,0.0002959838],"domain_scores_gemma":[0.9953999,0.0023878901,0.0002438992,0.001473638,0.0003360037,0.00015869828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007970613,0.00033296132,0.00036152435,0.00064742076,0.00040744807,0.00017173876,0.000600183,0.0002463115,4.369671e-7],"category_scores_gemma":[0.0012694006,0.00036648684,0.000077950914,0.0010203168,0.00018531113,0.00015514331,0.00077187334,0.00076017866,0.000005086961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011915947,0.00016608128,0.0060786945,0.00009336661,0.000074077296,0.00013698499,0.00011075891,0.97877645,0.000012568425,0.006838238,0.0012432721,0.006350329],"study_design_scores_gemma":[0.0007828886,0.00032192035,0.0007253092,0.0005531596,0.000046647783,0.0000020590799,0.000017930977,0.9580811,0.00008472963,0.039001152,0.000045601446,0.0003374459],"about_ca_topic_score_codex":0.00053494633,"about_ca_topic_score_gemma":0.000045209323,"teacher_disagreement_score":0.82761836,"about_ca_system_score_codex":0.00027691456,"about_ca_system_score_gemma":0.00034954058,"threshold_uncertainty_score":0.9998787},"labels":[],"label_agreement":null},{"id":"W4376869521","doi":"10.18280/isi.280211","title":"A Proposed Framework for Identity Verification in Passport Management Using Model Scaling and Semantic Similarity","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Similarity (geometry); Computer science; Identity (music); Scaling; Semantic similarity; Natural language processing; Artificial intelligence; Mathematics; Image (mathematics); Physics","score_opus":0.04678460880268017,"score_gpt":0.30477768080344586,"score_spread":0.2579930720007657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376869521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18425955,0.000010255172,0.81293446,0.000044205044,0.000078937934,0.0004426047,0.0000027693131,0.0021689287,0.00005829526],"genre_scores_gemma":[0.5837269,0.000009872556,0.4161399,0.00005356541,0.0000073813653,0.000043854678,0.000012428292,0.0000043812715,0.0000017387378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989874,0.00002246905,0.00038342833,0.00017054038,0.0002063151,0.00022988759],"domain_scores_gemma":[0.999304,0.00009471212,0.00017247307,0.0002829105,0.00010895843,0.000036932277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000987677,0.000113129194,0.00013739687,0.00038303513,0.00021738868,0.00036044337,0.00025535387,0.00008801858,2.1149458e-7],"category_scores_gemma":[0.00036426994,0.000117279975,0.000030443834,0.00077386986,0.00003956042,0.0028685858,0.00015274642,0.00008722306,0.0000036011402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059843456,0.00010035462,0.035546493,0.004666616,0.00006089176,0.00001637298,0.024798833,0.0686912,0.00017814524,0.51262367,0.0006976562,0.35255995],"study_design_scores_gemma":[0.00008799993,0.00000989736,0.0069039874,0.00021963652,0.0000045166507,0.0000035346561,0.00004860017,0.63455915,0.00008572692,0.35797992,0.000007750094,0.00008924884],"about_ca_topic_score_codex":0.000052954143,"about_ca_topic_score_gemma":0.0000032568787,"teacher_disagreement_score":0.56586796,"about_ca_system_score_codex":0.00015244196,"about_ca_system_score_gemma":0.000038661994,"threshold_uncertainty_score":0.47825384},"labels":[],"label_agreement":null},{"id":"W4377231357","doi":"10.1007/978-3-031-33271-5_15","title":"OAMIP: Optimizing ANN Architectures Using Mixed-Integer Programming","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal","funders":"","keywords":"Computer science; Integer programming; Integer (computer science); Parallel computing; Theoretical computer science; Algorithm; Programming language","score_opus":0.03867590991141418,"score_gpt":0.28250803511291356,"score_spread":0.24383212520149938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377231357","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000083012106,0.00025315429,0.98670024,0.00033256353,0.0020616301,0.0004577993,0.0000033462688,0.009531766,0.0005764898],"genre_scores_gemma":[0.044574056,0.000010158547,0.9540504,0.00051738846,0.00051273324,0.000016744603,0.000003934729,0.00009985107,0.0002147192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99474275,0.000060463844,0.0006668145,0.0021012907,0.0012513937,0.0011772831],"domain_scores_gemma":[0.9961098,0.0010864642,0.0003951571,0.0018481615,0.00032316105,0.0002372506],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014867489,0.00078987365,0.0007127806,0.0017345153,0.0004986193,0.0012171734,0.004135894,0.00043420226,0.000004282633],"category_scores_gemma":[0.00049058656,0.0007285714,0.00023432533,0.0013035925,0.00078146573,0.00035565213,0.0026352499,0.0013742003,0.00003039223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003436575,0.00002038877,0.000082856386,0.00006685446,0.000016103799,0.00025640597,0.00086502096,0.116498165,0.000047286565,0.0023792635,0.000086840955,0.87967736],"study_design_scores_gemma":[0.00010070582,0.00011765641,0.000026992264,0.0011935327,0.0000102565655,0.00022127418,1.11916606e-7,0.7011185,0.00052212225,0.29562953,0.00027557556,0.0007836888],"about_ca_topic_score_codex":0.00009513793,"about_ca_topic_score_gemma":0.00003945133,"teacher_disagreement_score":0.8788937,"about_ca_system_score_codex":0.00035271596,"about_ca_system_score_gemma":0.0005840967,"threshold_uncertainty_score":0.99981964},"labels":[],"label_agreement":null},{"id":"W4378191086","doi":"10.1109/syscon53073.2023.10131048","title":"Enhancing Boofuzz Process Monitoring for Closed-Source SCADA System Fuzzing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Fuzz testing; SCADA; Computer science; Context (archaeology); Software bug; Process (computing); Embedded system; Software; Computer security; Operating system; Engineering","score_opus":0.029144135486325898,"score_gpt":0.29944532814410946,"score_spread":0.2703011926577836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378191086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043334946,0.000052999156,0.8953778,0.00012880904,0.00056827,0.00027529467,5.958497e-7,0.059430927,0.00083034835],"genre_scores_gemma":[0.8007197,0.0000014255102,0.1983423,0.000038314894,0.00024747962,0.00014843674,0.0000010059346,0.000024308876,0.00047708253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849874,0.00002540416,0.00026803726,0.0004626696,0.00028176422,0.00046340123],"domain_scores_gemma":[0.9985776,0.00061627367,0.00009276489,0.0004803458,0.00014394609,0.0000890754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077456573,0.00016009287,0.00018800057,0.00019542001,0.00032661742,0.00025179752,0.0007784111,0.00006967556,3.267988e-7],"category_scores_gemma":[0.00036057006,0.00014691913,0.000070005844,0.0007671554,0.000013997771,0.00032503568,0.00021199675,0.00010163203,0.00004068855],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055685105,0.00020628983,0.12685528,0.0085935015,0.00022268448,0.00020581858,0.01670299,0.0043974514,0.021010976,0.053411614,0.07355963,0.6947781],"study_design_scores_gemma":[0.0007228925,0.00027862834,0.0030746935,0.0028686146,0.000028655846,0.000122799,0.00081994414,0.5837028,0.37924725,0.025489135,0.0022691411,0.0013754502],"about_ca_topic_score_codex":0.000056784844,"about_ca_topic_score_gemma":0.0000020381672,"teacher_disagreement_score":0.7573847,"about_ca_system_score_codex":0.00007677805,"about_ca_system_score_gemma":0.00006247164,"threshold_uncertainty_score":0.5991188},"labels":[],"label_agreement":null},{"id":"W4378418585","doi":"10.1109/icst57152.2023.00026","title":"Mutation Testing of Deep Reinforcement Learning Based on Real Faults","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Science and Engineering Research Council; Bombardier","keywords":"Reinforcement learning; Mutation; Computer science; Heuristic; Set (abstract data type); Artificial intelligence; Task (project management); Machine learning; Adaptive mutation; Order (exchange); Genetic algorithm; Engineering","score_opus":0.035808777308209985,"score_gpt":0.2859746181044491,"score_spread":0.2501658407962391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378418585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011064743,7.7614266e-7,0.96163946,0.00010509943,0.00005119669,0.00007585256,4.8680104e-8,0.014339433,0.012723364],"genre_scores_gemma":[0.81454706,3.780046e-7,0.18520698,0.00007752103,0.000010566931,0.000008833839,0.0000037780621,0.0000050725503,0.00013981397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920934,0.000034710447,0.00017306801,0.00018206029,0.0002488142,0.0001520183],"domain_scores_gemma":[0.99865615,0.00088575913,0.00009258034,0.00024180673,0.00009271154,0.00003096022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042741175,0.00007017656,0.000079272104,0.00017731816,0.0000825234,0.000024135534,0.00023257159,0.000028328634,0.0000039612646],"category_scores_gemma":[0.0011975159,0.00006303541,0.000024122475,0.0007240097,0.0000130152785,0.00008541766,0.00007517685,0.00007630958,0.000028216398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064018477,0.000023426652,0.013675296,0.000037997426,0.0000041525773,0.000028611563,0.00051874353,0.7991214,0.00034902588,0.0026101544,0.0014582735,0.18216656],"study_design_scores_gemma":[0.00010216632,0.00025644418,0.005190562,0.00005430623,0.0000012102801,0.0000015852816,0.000005798815,0.98919404,0.0028340695,0.0022716818,0.000015497557,0.000072637304],"about_ca_topic_score_codex":0.00019213292,"about_ca_topic_score_gemma":0.000001564526,"teacher_disagreement_score":0.8034823,"about_ca_system_score_codex":0.000022914644,"about_ca_system_score_gemma":0.000028147206,"threshold_uncertainty_score":0.25705096},"labels":[],"label_agreement":null},{"id":"W4378676681","doi":"10.1109/icstw58534.2023.00069","title":"Test Cost Reduction for 5G and Beyond using Machine Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); University of Ottawa; Carleton University","funders":"","keywords":"Reduction (mathematics); Test (biology); Computer science; Cost reduction; Machine learning; Artificial intelligence; Mathematics; Geology","score_opus":0.04976053073262066,"score_gpt":0.30632586942066975,"score_spread":0.2565653386880491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378676681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02894617,0.000066511944,0.94526553,0.0009135034,0.000234967,0.00027119165,0.0000017828202,0.02349451,0.00080582063],"genre_scores_gemma":[0.5043177,0.000010615741,0.49474654,0.000089771755,0.00006404348,0.000020701407,0.0000054368766,0.000011686631,0.0007335403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947417,0.000013031094,0.0000848148,0.00020737709,0.0000718307,0.00014877997],"domain_scores_gemma":[0.9993896,0.0003601795,0.00003377515,0.0001390797,0.000042105752,0.00003528763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003146495,0.00006320507,0.00006754897,0.0001050013,0.0002031385,0.000105124855,0.0001258987,0.000028942748,0.000001326651],"category_scores_gemma":[0.0005202555,0.00005773437,0.000015319352,0.00032085352,0.000020317451,0.00015744788,0.00006515229,0.00006456894,0.0000044574417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001541269,0.00012096005,0.10565451,0.0001849399,0.000031259122,0.000024772768,0.002174866,0.0022371262,0.03585198,0.015961245,0.07201507,0.7657279],"study_design_scores_gemma":[0.00012347387,0.00009351574,0.0006508058,0.000019580675,0.0000032167677,0.00006722941,0.0000072778867,0.97073287,0.0045697144,0.022290563,0.0013221935,0.00011956213],"about_ca_topic_score_codex":0.00009878925,"about_ca_topic_score_gemma":0.0000017298289,"teacher_disagreement_score":0.9684957,"about_ca_system_score_codex":0.000015139008,"about_ca_system_score_gemma":0.000015086467,"threshold_uncertainty_score":0.23543392},"labels":[],"label_agreement":null},{"id":"W4378676759","doi":"10.1109/icstw58534.2023.00071","title":"On factors that impact the relationship between code coverage and test suite effectiveness: a survey","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; Test (biology); Suite; Computer science; Code coverage; Empirical research; Code (set theory); Variety (cybernetics); Test case; Programming language; Statistics; Machine learning; Artificial intelligence; Software; Mathematics; Geography","score_opus":0.13644877090685006,"score_gpt":0.35406367320126025,"score_spread":0.2176149022944102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378676759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9265712,0.000009011517,0.06633101,0.0001151556,0.00004778959,0.00018019357,0.000034212622,0.006583561,0.00012787408],"genre_scores_gemma":[0.9994055,0.0000018565045,0.0004083214,0.000051071438,0.000009977345,0.0000111112395,0.00001811516,0.000010674972,0.00008334752],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988662,0.0003470713,0.00009613506,0.00027571525,0.00020341924,0.0002114758],"domain_scores_gemma":[0.9198281,0.07959407,0.000046333356,0.0004407939,0.000029913119,0.00006078367],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017709804,0.00013497123,0.00013736867,0.000118648735,0.00025546545,0.00022793557,0.00039875924,0.00005665236,0.0000018479483],"category_scores_gemma":[0.008675424,0.00007738162,0.000042448602,0.0006720952,0.00004493396,0.00017557466,0.000179222,0.00016687276,0.000029088778],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015967344,0.000006442445,0.9957241,0.000004728557,0.00000512696,0.0000017261575,0.00011524436,0.000010327198,0.0000020403313,0.0008303634,0.0026502623,0.00064807944],"study_design_scores_gemma":[0.00008315607,0.000129394,0.95413744,0.000034935332,0.000002557127,0.0000018632007,0.0000010994606,0.0010149478,0.00011131319,0.044372138,0.0000069142147,0.00010422301],"about_ca_topic_score_codex":0.0009471004,"about_ca_topic_score_gemma":0.000037244306,"teacher_disagreement_score":0.07924699,"about_ca_system_score_codex":0.000038836777,"about_ca_system_score_gemma":0.000033265274,"threshold_uncertainty_score":0.9996749},"labels":[],"label_agreement":null},{"id":"W4378676770","doi":"10.1109/icstw58534.2023.00060","title":"Analysis of mutation operators for FSM testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutation testing; Mutation; Computer science; Operator (biology); Finite-state machine; Software testing; Software fault tolerance; Process (computing); Software; Set (abstract data type); Fault (geology); Mutant; Theoretical computer science; Algorithm; Programming language; Artificial intelligence; Biology; Genetics","score_opus":0.062392869974473346,"score_gpt":0.32285233541539643,"score_spread":0.2604594654409231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378676770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035783835,0.0000035079752,0.9551799,0.00009413682,0.000038421942,0.00007108802,0.0000015085798,0.008486767,0.00034078668],"genre_scores_gemma":[0.552801,1.250801e-7,0.44706857,0.00004556632,0.00000533665,0.000014463897,0.0000036708434,0.0000022750044,0.000058998707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951726,0.000011463861,0.00013111273,0.00015009566,0.00009154974,0.00009851598],"domain_scores_gemma":[0.998755,0.00082251115,0.00004604632,0.00021444645,0.00014220565,0.000019821982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003513517,0.0000423304,0.00010292258,0.00037021315,0.000049195623,0.000034305267,0.0002356382,0.00001941171,0.0000014597856],"category_scores_gemma":[0.0010695407,0.000036715424,0.00005062685,0.0031476296,0.000009519659,0.00009450192,0.000061322935,0.000016922504,0.0000034346247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037170955,0.00007311844,0.23201396,0.00006417507,0.00047986838,0.0000141062455,0.0018825659,0.013163576,0.0021626824,0.04411873,0.03164942,0.6743741],"study_design_scores_gemma":[0.000038969225,0.000043136268,0.015737427,0.0000072078064,0.00003639058,6.329728e-7,0.000004450865,0.96852946,0.0029059136,0.012616651,0.000023575714,0.00005616716],"about_ca_topic_score_codex":0.00008486558,"about_ca_topic_score_gemma":0.000003553611,"teacher_disagreement_score":0.9553659,"about_ca_system_score_codex":0.000007425838,"about_ca_system_score_gemma":0.000021961223,"threshold_uncertainty_score":0.15123317},"labels":[],"label_agreement":null},{"id":"W4378942602","doi":"10.1145/3597926.3598135","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; York University","funders":"National Science Foundation","keywords":"Computer science; Task (project management); Vulnerability (computing); Code (set theory); Software security assurance; Secure coding; Computer security; Source code; Software; Artificial neural network; Software bug; Automation; Programming language; Software engineering; Artificial intelligence; Information security; Engineering; Security service","score_opus":0.038060447194846705,"score_gpt":0.2861846731068167,"score_spread":0.24812422591197003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378942602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028401879,0.00020050218,0.9511022,0.0026114273,0.0019868943,0.0011794313,0.000017294586,0.039986085,0.0000759638],"genre_scores_gemma":[0.85883117,0.0000073297374,0.13834137,0.00026501715,0.00055490836,0.001341586,0.000023135608,0.000049331098,0.0005861693],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783003,0.00018477826,0.00023083376,0.0010282905,0.00023707491,0.00048900273],"domain_scores_gemma":[0.9945963,0.0036086468,0.00024308577,0.0011943738,0.0002655447,0.00009203493],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008726011,0.00038041017,0.00048052968,0.00015979736,0.0002324434,0.00105574,0.0013660673,0.000350977,8.1931984e-7],"category_scores_gemma":[0.0018355342,0.00034276623,0.0002822644,0.00021151685,0.00006919151,0.00020878877,0.0024019866,0.0007886444,0.0000015011522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007131168,0.00028433232,0.04231357,0.0043454603,0.0004618696,0.00014863891,0.0063397787,0.10515891,0.0000057886714,0.027559958,0.6546026,0.1587078],"study_design_scores_gemma":[0.00007181149,0.000059915114,0.0007383786,0.0002034637,0.000008915395,0.0000043261016,0.000013424848,0.68263495,0.00006673793,0.31579205,0.00009767858,0.00030834504],"about_ca_topic_score_codex":0.00028317305,"about_ca_topic_score_gemma":0.00003578175,"teacher_disagreement_score":0.85599095,"about_ca_system_score_codex":0.00010890592,"about_ca_system_score_gemma":0.00004347981,"threshold_uncertainty_score":0.9999813},"labels":[],"label_agreement":null},{"id":"W4379137887","doi":"10.3233/mgs-230023","title":"A testing framework for JADE agent-based software","year":2023,"lang":"en","type":"article","venue":"Multiagent and Grid Systems","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"JADE (particle detector); Computer science; Usability; Multi-agent system; Integration testing; Test strategy; Unit testing; Process (computing); Software; Agent-oriented software engineering; Toolbox; Software engineering; Software development; Artificial intelligence; Human–computer interaction; Operating system; Programming language","score_opus":0.09283915703248641,"score_gpt":0.31041183346596274,"score_spread":0.21757267643347633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379137887","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010171055,0.00033377772,0.9718931,0.00025818954,0.0013635962,0.00055823434,0.000017587356,0.015388569,0.000015924776],"genre_scores_gemma":[0.31222758,0.000003433233,0.6865195,0.00020845312,0.00046212217,0.00038935622,0.000018372639,0.000030531563,0.00014061802],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861544,0.000057961424,0.0002646604,0.00045106126,0.00022296276,0.00038789664],"domain_scores_gemma":[0.9969778,0.0022103991,0.00011798791,0.00046414178,0.00011203627,0.00011761406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063695386,0.00017772603,0.00021672889,0.00016328685,0.00029948683,0.00029933653,0.0004182175,0.000106079155,6.014951e-7],"category_scores_gemma":[0.002096178,0.00015857136,0.00006554387,0.0005602028,0.000028961527,0.0001084624,0.0001397244,0.00011008031,0.000030113217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044174612,0.00027412243,0.31283358,0.0029352652,0.00015063006,0.00028806945,0.0038096611,0.007529341,0.0011942231,0.013137064,0.36334416,0.2944597],"study_design_scores_gemma":[0.00047018874,0.0001752692,0.010180301,0.0007458586,0.000014453848,0.000020135141,0.000027337574,0.9713801,0.00036941905,0.0075307256,0.008633184,0.00045300115],"about_ca_topic_score_codex":0.0001256619,"about_ca_topic_score_gemma":9.72343e-7,"teacher_disagreement_score":0.9638508,"about_ca_system_score_codex":0.000028434628,"about_ca_system_score_gemma":0.000041335472,"threshold_uncertainty_score":0.64663523},"labels":[],"label_agreement":null},{"id":"W4379537148","doi":"10.1145/3591233","title":"Recursive State Machine Guided Graph Folding for Context-Free Language Reachability","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Reachability; Scalability; Computer science; Graph; Theoretical computer science; Path (computing); Mathematics; Algorithm","score_opus":0.028197214482458714,"score_gpt":0.308115621640343,"score_spread":0.2799184071578843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379537148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9531513,0.0008251884,0.006637722,0.012322923,0.00049413583,0.0027847723,0.00007555477,0.023081591,0.00062685576],"genre_scores_gemma":[0.7109489,0.000011096875,0.2879315,0.00030630673,0.000062461164,0.00028751284,0.000005761242,0.00004187609,0.00040462802],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981947,0.000020307169,0.0003581659,0.000534833,0.0004023622,0.0004896331],"domain_scores_gemma":[0.99712104,0.0007784358,0.0003628772,0.0013499594,0.00031240185,0.00007527869],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015733605,0.00023758138,0.00029846115,0.0002322555,0.00022979412,0.00017485672,0.004543903,0.0000755088,9.269626e-7],"category_scores_gemma":[0.017415754,0.00017144227,0.00021663657,0.0010218944,0.00012043246,0.00022822927,0.001843862,0.00020486061,0.00000282012],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008813645,0.00021354697,0.018953059,0.00071441766,0.000118243224,0.000009194497,0.016791845,0.0000069926477,0.0074312612,0.023741689,0.10747231,0.8244593],"study_design_scores_gemma":[0.0015956456,0.0010309408,0.0045490456,0.0011493524,0.000072020244,0.00004760449,0.0016702814,0.0017216787,0.19653443,0.7870211,0.0037186437,0.00088927697],"about_ca_topic_score_codex":0.00026749456,"about_ca_topic_score_gemma":0.00001028335,"teacher_disagreement_score":0.82357,"about_ca_system_score_codex":0.00004991868,"about_ca_system_score_gemma":0.000025597927,"threshold_uncertainty_score":0.990861},"labels":[],"label_agreement":null},{"id":"W4381853525","doi":"10.1016/j.infsof.2023.107286","title":"Reflections on Surrogate-Assisted Search-Based Testing: A Taxonomy and Two Replication Studies based on Industrial ADAS and Simulink Models","year":2023,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Ottawa","funders":"Horizon 2020; HORIZON EUROPE Framework Programme; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme","keywords":"Computer science; Benchmark (surveying); Replication (statistics); Machine learning; Heuristic; Taxonomy (biology); Generalization; Artificial intelligence; Reliability engineering; Search-based software engineering; Software; Engineering; Software system; Programming language","score_opus":0.2884403668754432,"score_gpt":0.3828625042578708,"score_spread":0.09442213738242755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381853525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14164045,0.000086406,0.7960034,0.011688583,0.00021194368,0.0013684273,0.000025817577,0.048459042,0.0005159268],"genre_scores_gemma":[0.8856675,0.000015593525,0.11319718,0.00084644713,0.000013678177,0.00022213014,0.000020202702,0.00000839867,0.000008863295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988533,0.000052721516,0.00032986864,0.0003417543,0.0001884005,0.00023390297],"domain_scores_gemma":[0.9978443,0.0011073826,0.00015614607,0.00056768727,0.00025493483,0.00006955203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062000635,0.00017261796,0.00020673039,0.0011085826,0.0003996286,0.00014358452,0.00021415234,0.00019987114,3.5831118e-7],"category_scores_gemma":[0.0033627497,0.00016036928,0.000018960478,0.0013565941,0.00019135566,0.00045876196,0.00017468623,0.00031663186,0.0000073164606],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005075825,0.000050489147,0.009915852,0.00007198673,0.000021832402,0.000007096685,0.00040204523,0.008270482,0.000015619646,0.008886407,0.0029449263,0.9693625],"study_design_scores_gemma":[0.0016046416,0.00088992406,0.002036838,0.00025834728,0.000012170993,0.000030258529,0.00010653336,0.9591013,0.00043045933,0.03297262,0.002230058,0.00032684318],"about_ca_topic_score_codex":0.00004257406,"about_ca_topic_score_gemma":0.000006769914,"teacher_disagreement_score":0.9690357,"about_ca_system_score_codex":0.000061958286,"about_ca_system_score_gemma":0.00011014407,"threshold_uncertainty_score":0.65396696},"labels":[],"label_agreement":null},{"id":"W4382930431","doi":"10.1016/j.scico.2023.102990","title":"AmbieGen: A search-based framework for autonomous systems testing","year":2023,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Modular design; Software deployment; Autonomous system (mathematics); Architecture; Robot; Scenario testing; Test case; Distributed computing; Artificial intelligence; Software engineering; Machine learning; Programming language","score_opus":0.0676608071989877,"score_gpt":0.3268068828846064,"score_spread":0.2591460756856187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382930431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011393717,0.000037447837,0.9749328,0.00025385636,0.00075723947,0.0006193952,0.0000016616128,0.011977534,0.00002635492],"genre_scores_gemma":[0.39497632,1.7031427e-7,0.6048055,0.000038290596,0.000085755564,0.00007676825,9.884722e-7,0.000010861904,0.0000053092804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973008,0.000049658076,0.0003890664,0.000708943,0.00071013,0.0008413907],"domain_scores_gemma":[0.9967106,0.0015079849,0.00019098849,0.0008218538,0.0005950604,0.00017351618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030266605,0.00018303085,0.00026639138,0.00062894076,0.00049367733,0.0007383706,0.00220505,0.000070158014,2.1156556e-7],"category_scores_gemma":[0.00093025726,0.00017370182,0.00008875638,0.0045218463,0.00045786466,0.00043315245,0.0005610158,0.00016251036,0.000009489309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039923157,0.00008535866,0.0024813472,0.00028248414,0.000008709315,0.000015891581,0.0007197911,0.017190734,0.0005578463,0.057937317,0.0006403649,0.9200762],"study_design_scores_gemma":[0.00011766097,0.00037948124,0.00086307205,0.00037842692,0.000003130017,0.000012456116,0.00000915123,0.9767142,0.0015797726,0.0194353,0.000292425,0.00021491626],"about_ca_topic_score_codex":0.00006778606,"about_ca_topic_score_gemma":2.3644641e-7,"teacher_disagreement_score":0.9595235,"about_ca_system_score_codex":0.00007391203,"about_ca_system_score_gemma":0.0005844146,"threshold_uncertainty_score":0.71201247},"labels":[],"label_agreement":null},{"id":"W4384009688","doi":"10.1109/icse-companion58688.2023.00047","title":"DaMAT: A Data-driven Mutation Analysis Tool","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Space Agency","keywords":"Computer science; Interoperability; Mutation testing; Software; Mutation; Source code; Set (abstract data type); Software engineering; Programming language; Operating system","score_opus":0.06459783877168492,"score_gpt":0.32580100139882423,"score_spread":0.26120316262713933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384009688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00905455,0.0000041535905,0.95993346,0.0005235363,0.000055067016,0.000048688205,0.0000043830214,0.029556578,0.00081958517],"genre_scores_gemma":[0.5401783,0.0000021719393,0.45906436,0.00022476431,0.000021003565,0.000009441224,0.00009382454,0.000004226174,0.00040191872],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918884,0.000028018669,0.00012530478,0.00033024477,0.00018505164,0.00014252354],"domain_scores_gemma":[0.99845874,0.00023600663,0.000037286463,0.00119735,0.00004188653,0.000028715189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035440866,0.000060834678,0.00009820905,0.00030851524,0.00006970677,0.000151428,0.0010541256,0.000025462867,0.000014422824],"category_scores_gemma":[0.00027935108,0.000052484036,0.000036436188,0.002559417,0.000011576726,0.00037632725,0.0005667867,0.000041380652,0.00023638192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023045038,0.00006704312,0.043802667,0.00002217585,0.00039221032,0.00020614281,0.0010401591,0.005046025,0.00008526454,0.0260499,0.6467012,0.27658486],"study_design_scores_gemma":[0.000033658525,0.0000121603125,0.015317006,0.000003329623,0.000029425368,0.0000038169396,0.000002191876,0.96982735,0.000053969547,0.014099311,0.0005319886,0.000085780295],"about_ca_topic_score_codex":0.00012208862,"about_ca_topic_score_gemma":0.000013876423,"teacher_disagreement_score":0.96478134,"about_ca_system_score_codex":0.000010226881,"about_ca_system_score_gemma":0.000023978955,"threshold_uncertainty_score":0.303829},"labels":[],"label_agreement":null},{"id":"W4384026493","doi":"10.1109/icse-companion58688.2023.00087","title":"GLAD: Neural Predicate Synthesis to Repair Omission Faults","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Machine translation; Programming language; Debugger; Predicate (mathematical logic); Generative grammar; Machine learning; Natural language processing; Debugging","score_opus":0.030055209051162008,"score_gpt":0.28562750589366626,"score_spread":0.25557229684250427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384026493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091902524,0.000022064518,0.5550625,0.012829188,0.0006462132,0.0004048678,0.000003563998,0.33292735,0.006201767],"genre_scores_gemma":[0.710065,0.0000029530481,0.2871765,0.0009098008,0.000055822882,0.00006225302,8.7130536e-7,0.000013235476,0.0017135962],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886554,0.00004505812,0.00015842773,0.00039933567,0.00025179732,0.0002798371],"domain_scores_gemma":[0.9984553,0.0006199036,0.000029955023,0.00068690715,0.000043001935,0.00016495105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041612767,0.000105529834,0.000112525115,0.00018501836,0.000114717855,0.000056006233,0.00069603254,0.000047097295,0.000013395229],"category_scores_gemma":[0.0018556361,0.00008363103,0.00006497038,0.00084971986,0.000013686677,0.00015201274,0.00049573823,0.0000692589,0.00038928303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061371115,0.000027578904,0.0057739583,0.000016858941,0.000007327032,0.00006242687,0.00030114068,0.0000900888,0.0003417784,0.0011130042,0.8535985,0.1386612],"study_design_scores_gemma":[0.000097152646,0.00020193016,0.04115099,0.00021008695,0.000008021029,0.000042333555,0.00000794628,0.92053896,0.009963423,0.014365545,0.0129300095,0.0004836051],"about_ca_topic_score_codex":0.00008937931,"about_ca_topic_score_gemma":0.0000015476012,"teacher_disagreement_score":0.92044884,"about_ca_system_score_codex":0.000019797804,"about_ca_system_score_gemma":0.000024792704,"threshold_uncertainty_score":0.50035757},"labels":[],"label_agreement":null},{"id":"W4384154545","doi":"10.1145/3597926.3604927","title":"SymRustC: A Hybrid Fuzzer for Rust","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzz testing; Concolic testing; Computer science; Rust (programming language); Benchmark (surveying); Compiler; Programming language; Symbolic execution; Software","score_opus":0.0370533003331452,"score_gpt":0.2912337161585949,"score_spread":0.2541804158254497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384154545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017527305,0.000011990466,0.94705236,0.001408941,0.00023431033,0.0001491153,0.0000023721443,0.046554934,0.0028332402],"genre_scores_gemma":[0.2816756,0.0000037496043,0.71249545,0.0011412838,0.00010188175,0.00013128389,0.0000058191285,0.000015757885,0.0044291588],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992946,0.00000964373,0.000101528414,0.00024241072,0.0001128339,0.000238985],"domain_scores_gemma":[0.99910915,0.0003520849,0.000023318695,0.00041204144,0.00005368558,0.000049709946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029453993,0.000074368974,0.000082118495,0.00010884615,0.000093454306,0.00010102437,0.0005077316,0.000020915972,0.000006625652],"category_scores_gemma":[0.00027514712,0.00006289337,0.00005191045,0.00033883264,0.000014419681,0.00012730849,0.00017891532,0.000040475603,0.00019647327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011541254,0.000011013449,0.00044996536,0.000011022477,0.0000042062425,0.000010112699,0.00006230672,0.000007981106,0.00003123381,0.026285972,0.90002316,0.073101856],"study_design_scores_gemma":[0.0004221705,0.00022164814,0.002056239,0.00005388452,0.0000074382147,0.00006186811,0.0000070024757,0.3196912,0.0063090813,0.54874235,0.12189685,0.00053026224],"about_ca_topic_score_codex":0.00002397571,"about_ca_topic_score_gemma":6.6211317e-7,"teacher_disagreement_score":0.77812636,"about_ca_system_score_codex":0.000012300645,"about_ca_system_score_gemma":0.00002890523,"threshold_uncertainty_score":0.25647172},"labels":[],"label_agreement":null},{"id":"W4384302810","doi":"10.1109/icse48619.2023.00167","title":"Carving UI Tests to Generate API Tests and API Specification","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Application programming interface; Web API; Web application; Web testing; Unit testing; Ajax; Operating system; Test suite; Embedded system; Database; Web server; Web service; Test case; World Wide Web; Software; Web development; The Internet; Web application security; Machine learning","score_opus":0.04563962302134925,"score_gpt":0.2969470074372192,"score_spread":0.2513073844158699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384302810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2043358,0.00009543081,0.74574226,0.0045252866,0.00034573706,0.00031276024,0.0000017250796,0.04070207,0.003938935],"genre_scores_gemma":[0.6309548,0.000013835381,0.36742216,0.00054465124,0.0000886548,0.000027825457,0.0000022605764,0.000011638153,0.0009342059],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990262,0.000027347054,0.00014443595,0.00039692005,0.00016796034,0.00023716273],"domain_scores_gemma":[0.99898124,0.0002762263,0.000034300294,0.00051860226,0.0000770539,0.00011256509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035380723,0.00010689857,0.0000984664,0.00018814107,0.00012627263,0.00023520377,0.00040922404,0.000039215276,0.000004148839],"category_scores_gemma":[0.00038878078,0.00009693333,0.00001713098,0.00084317307,0.000016994018,0.00017442262,0.00033372868,0.00006350565,0.00020368925],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003227961,0.000054988548,0.06681196,0.00004831274,0.000013506414,0.000067478504,0.0018070812,0.00020380126,0.017729,0.037060577,0.37173018,0.5044699],"study_design_scores_gemma":[0.00038406134,0.0003566314,0.5443753,0.00022730915,0.000011610251,0.00013952654,0.000032303382,0.26268163,0.030068185,0.14510436,0.015311675,0.0013073704],"about_ca_topic_score_codex":0.00010959656,"about_ca_topic_score_gemma":0.000013020738,"teacher_disagreement_score":0.5031625,"about_ca_system_score_codex":0.000027263748,"about_ca_system_score_gemma":0.00002672546,"threshold_uncertainty_score":0.39528263},"labels":[],"label_agreement":null},{"id":"W4384345629","doi":"10.1109/icse48619.2023.00155","title":"Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Fidelity; Artificial intelligence; High fidelity; Machine learning; Artificial neural network; Human–computer interaction","score_opus":0.05353553344486145,"score_gpt":0.29601844755624895,"score_spread":0.2424829141113875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384345629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00912086,0.000021133877,0.97349906,0.00007542186,0.00017879598,0.00035609907,9.033539e-7,0.01485789,0.0018898115],"genre_scores_gemma":[0.6992723,0.0000021609862,0.29809663,0.00003987282,0.000055221597,0.00007242565,0.000008334532,0.000013318603,0.0024397373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890196,0.000035006058,0.00030408538,0.0002707951,0.00020757614,0.00028059923],"domain_scores_gemma":[0.99769324,0.0014967568,0.00016670783,0.00031505068,0.00028411357,0.000044146684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006801116,0.00011126238,0.00019553516,0.0002000533,0.00013158553,0.000067106455,0.00041530802,0.000044767858,0.00000120972],"category_scores_gemma":[0.0021152645,0.00009710347,0.000049509887,0.00080145156,0.00001896358,0.00014566517,0.00024102195,0.00009628205,0.000008467405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000548924,0.00026626894,0.037795227,0.0016944029,0.00022844109,0.000056259163,0.003463312,0.55320233,0.0068890858,0.09550369,0.09430547,0.20654064],"study_design_scores_gemma":[0.00018745584,0.00029520484,0.00084320543,0.00017040008,0.000004927162,0.00000709324,0.000042901374,0.99221146,0.0014546503,0.004077012,0.000575146,0.00013053062],"about_ca_topic_score_codex":0.00030479004,"about_ca_topic_score_gemma":0.0000012206472,"teacher_disagreement_score":0.69015145,"about_ca_system_score_codex":0.000044491517,"about_ca_system_score_gemma":0.00006558582,"threshold_uncertainty_score":0.39597645},"labels":[],"label_agreement":null},{"id":"W4384345653","doi":"10.1109/icse48619.2023.00146","title":"ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolutionary Search","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test suite; Code coverage; Test case; Abstract syntax tree; Fault coverage; Scalability; Minification; Similarity (geometry); Automatic test pattern generation; Test (biology); Java; Regression testing; Syntax; Programming language; Software; Artificial intelligence; Machine learning; Software development; Operating system; Engineering","score_opus":0.04103145356441748,"score_gpt":0.29445215780038997,"score_spread":0.2534207042359725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384345653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052954536,0.000030052961,0.8866823,0.009734902,0.00017813517,0.0005823857,0.00007898605,0.045489077,0.0042696632],"genre_scores_gemma":[0.8127243,0.000005637907,0.18609054,0.0006969166,0.000035201054,0.0000142156105,0.00001567088,0.00001254553,0.00040498434],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988022,0.000060093138,0.00015753027,0.0004340963,0.00028175442,0.00026433571],"domain_scores_gemma":[0.9958421,0.0033726657,0.000032752967,0.0005098109,0.00013053532,0.00011214565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042348934,0.00013229212,0.00011062442,0.0002092674,0.00025342422,0.00012319129,0.00027066603,0.00008050734,0.000012723216],"category_scores_gemma":[0.0018729696,0.00012177291,0.00002752179,0.0008651432,0.000097225944,0.000166944,0.0002156991,0.00014435542,0.00006225174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013596115,0.0006632686,0.4143102,0.00012532256,0.000009521098,0.0029526572,0.00060239027,0.0073646167,0.00016953968,0.002085847,0.5507798,0.020923257],"study_design_scores_gemma":[0.00017672814,0.00022453633,0.020621898,0.000037316444,0.0000030618119,0.00017553812,0.0000068006375,0.97448784,0.0003631312,0.003501293,0.00024011852,0.0001617535],"about_ca_topic_score_codex":0.00015097446,"about_ca_topic_score_gemma":0.00001654565,"teacher_disagreement_score":0.9671232,"about_ca_system_score_codex":0.00004810454,"about_ca_system_score_gemma":0.00009618677,"threshold_uncertainty_score":0.4965755},"labels":[],"label_agreement":null},{"id":"W4384345700","doi":"10.1109/icse48619.2023.00122","title":"GameRTS: A Regression Testing Framework for Video Games","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regression testing; Game design; Test suite; Sequential game; Video game; Context (archaeology); Game testing; Game Developer; Regression analysis; Software; Machine learning; Artificial intelligence; Test case; Software development; Game theory; Game design document; Programming language; Software construction; Multimedia","score_opus":0.07865055184339448,"score_gpt":0.3418979753851524,"score_spread":0.2632474235417579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384345700","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014332797,0.000042284628,0.950128,0.0011300036,0.0002398983,0.00016668033,8.236031e-7,0.045932937,0.00092608965],"genre_scores_gemma":[0.06405591,0.000002506103,0.93444514,0.0009238091,0.000092853435,0.00010693349,0.0000013205357,0.000015458452,0.0003560829],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891686,0.000024652922,0.00017153025,0.00037982676,0.00017992768,0.00032719242],"domain_scores_gemma":[0.99562865,0.0035322984,0.00007775633,0.0005784472,0.00011287649,0.00006995984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046269209,0.00012275612,0.00013519528,0.00015280758,0.00016800636,0.00015279565,0.000612711,0.00006490266,0.000003980617],"category_scores_gemma":[0.0067673353,0.00009363518,0.00005587302,0.001040626,0.000025383259,0.00018435816,0.00026643035,0.00010719248,0.000056805642],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046886425,0.000030364898,0.007142163,0.000054688073,0.000008580724,0.000024304469,0.00040232192,0.000029330005,0.00026264024,0.072330505,0.39890265,0.52080774],"study_design_scores_gemma":[0.00008283251,0.00010730928,0.0013501222,0.00040712277,0.0000026711489,0.000016537047,0.000007752218,0.17075348,0.0014208449,0.82075715,0.0048935134,0.00020065032],"about_ca_topic_score_codex":0.00002920154,"about_ca_topic_score_gemma":4.976066e-7,"teacher_disagreement_score":0.7484267,"about_ca_system_score_codex":0.000017415541,"about_ca_system_score_gemma":0.000042871638,"threshold_uncertainty_score":0.8101621},"labels":[],"label_agreement":null},{"id":"W4384948641","doi":"10.1109/sp46215.2023.10179314","title":"QueryX: Symbolic Query on Decompiled Code for Finding Bugs in COTS Binaries","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Callback; Symbolic execution; Programming language; Scalability; Dead code; Code (set theory); Program analysis; Control flow; Static program analysis; Unreachable code; Symbolic data analysis; Static analysis; Binary code; Theoretical computer science; Source code; Redundant code; Legacy code; Binary number; Code generation; Database; Operating system; Software; Set (abstract data type); Software development","score_opus":0.0654954515918125,"score_gpt":0.3375128509832877,"score_spread":0.2720173993914752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384948641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3088817,0.000045826964,0.6328232,0.0043729995,0.0008038875,0.0007628284,0.000015530462,0.04950981,0.0027841595],"genre_scores_gemma":[0.8820029,0.000008882965,0.1160692,0.00091215747,0.000048699792,0.0001648343,0.000008394226,0.000020265152,0.0007647006],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987543,0.00004364148,0.00023169952,0.00040043372,0.0001710253,0.0003989067],"domain_scores_gemma":[0.9977123,0.0016750874,0.000055248216,0.00045251587,0.000046183195,0.00005867117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062070065,0.0001453465,0.00020265361,0.00044618727,0.00014059398,0.00015323122,0.0005998078,0.000076792414,0.0000039941096],"category_scores_gemma":[0.0007237156,0.00013143466,0.000058747555,0.0008497375,0.00003155195,0.00017188612,0.00019144002,0.00011367687,0.00007863494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005647074,0.0002429162,0.08865572,0.00014717931,0.000028366128,0.00011869921,0.002805823,0.001303439,0.00048097683,0.30386856,0.53172743,0.07056442],"study_design_scores_gemma":[0.0011148382,0.00057763554,0.054073807,0.00052484643,0.000006580971,0.000019256513,0.00004727151,0.5392903,0.0073086307,0.3882355,0.007929459,0.00087184],"about_ca_topic_score_codex":0.00010724391,"about_ca_topic_score_gemma":0.00008795112,"teacher_disagreement_score":0.57312113,"about_ca_system_score_codex":0.000057850855,"about_ca_system_score_gemma":0.000066390385,"threshold_uncertainty_score":0.535975},"labels":[],"label_agreement":null},{"id":"W4385187421","doi":"10.1109/sp46215.2023.10179420","title":"Examining Zero-Shot Vulnerability Repair with Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":178,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Zero (linguistics); Computer science; Vulnerability (computing); Ground zero; Computer security; Physics; Linguistics; Nuclear physics","score_opus":0.07209621342546572,"score_gpt":0.3021107687630803,"score_spread":0.23001455533761456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385187421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10485226,0.000019284498,0.80979776,0.000118302174,0.00005523905,0.00010508026,0.0000017155787,0.07664462,0.008405714],"genre_scores_gemma":[0.7341148,0.000001052392,0.26456004,0.00027451364,0.000017129896,0.000025445703,0.0000033471129,0.00001105306,0.0009926218],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998686,0.00006724424,0.00015243408,0.00047110303,0.00026351845,0.0003596862],"domain_scores_gemma":[0.9984936,0.00037561756,0.000039795512,0.0009539632,0.000059095397,0.00007792358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009948318,0.00012960976,0.00014362797,0.000115691706,0.0001391435,0.000085863525,0.00049786776,0.000049471506,0.000011651763],"category_scores_gemma":[0.00020594479,0.00009701772,0.000038486152,0.00076053455,0.0000283925,0.00035713005,0.00032757202,0.0001368062,0.000072528404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047214933,0.00057931803,0.16284233,0.0002489634,0.00013898281,0.0012357024,0.026004652,0.0051546306,0.0009278814,0.17691909,0.54351234,0.08238888],"study_design_scores_gemma":[0.00029638805,0.00023552525,0.0063267285,0.00006950757,0.000005681428,0.00003877035,0.00007172536,0.92332745,0.0010464053,0.06776404,0.0004249555,0.00039282482],"about_ca_topic_score_codex":0.00009363167,"about_ca_topic_score_gemma":0.000012748695,"teacher_disagreement_score":0.91817284,"about_ca_system_score_codex":0.000024946563,"about_ca_system_score_gemma":0.000043745687,"threshold_uncertainty_score":0.39562678},"labels":[],"label_agreement":null},{"id":"W4385301141","doi":"10.1109/serp4iot59158.2023.00013","title":"ra4xstate: An Efficient Quantitative Robustness Analysis Approach for Statecharts","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Computer science; Robustness testing; Timestamp; Distributed computing; Data mining; Real-time computing; Programming language; Software","score_opus":0.0697830445199318,"score_gpt":0.3369201709998566,"score_spread":0.2671371264799248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385301141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01795624,0.000008866614,0.960226,0.00012150255,0.00006286437,0.00027691427,0.000009325197,0.021078838,0.00025946178],"genre_scores_gemma":[0.25624722,0.0000013854697,0.7432784,0.0000579268,0.000009444787,0.000120014614,0.000057832527,0.000010786747,0.00021700996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854875,0.00006733991,0.00021175519,0.0005650046,0.00024624262,0.00036090176],"domain_scores_gemma":[0.99856436,0.0004190597,0.00007468175,0.00064832525,0.00019256558,0.00010100463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009773903,0.00014310828,0.00022868662,0.0005816903,0.00018858247,0.00018965923,0.0006768036,0.000047299025,0.00000329346],"category_scores_gemma":[0.00018781029,0.00011969667,0.00011735027,0.0031173767,0.00003794131,0.00018776403,0.0001603216,0.000063085914,0.000008815777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016992562,0.0002199778,0.00075139344,0.000040239735,0.00017835067,0.000009872126,0.0018637094,0.92634934,0.000048676364,0.04378686,0.015840402,0.010894185],"study_design_scores_gemma":[0.00011705336,0.0001302101,0.00055268226,0.000003335213,0.00003613765,0.0000014126754,0.00006297116,0.9941278,0.00033638073,0.0043951888,0.000051884344,0.00018493495],"about_ca_topic_score_codex":0.00006902826,"about_ca_topic_score_gemma":0.000004844735,"teacher_disagreement_score":0.23829097,"about_ca_system_score_codex":0.00002625306,"about_ca_system_score_gemma":0.000039260758,"threshold_uncertainty_score":0.48810884},"labels":[],"label_agreement":null},{"id":"W4385301350","doi":"10.1109/sbft59156.2023.00011","title":"RIGAA at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Context (archaeology); Track (disk drive); Competition (biology); Reinforcement learning; Cyber-physical system; Artificial intelligence; Operating system; Geology; Ecology","score_opus":0.02585882803850791,"score_gpt":0.27060755010390386,"score_spread":0.24474872206539594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385301350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36502817,0.00011556899,0.4995379,0.0057647293,0.002085373,0.00093707436,0.00001924374,0.09597356,0.03053838],"genre_scores_gemma":[0.98179007,0.0000049243154,0.006334028,0.0003342113,0.00025598888,0.00009354056,0.000014182395,0.000015546519,0.011157497],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998856,0.00009445882,0.00015647437,0.00031136553,0.0003210809,0.00026063187],"domain_scores_gemma":[0.9983497,0.00081858854,0.00005143347,0.0006813928,0.000054425702,0.000044422995],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048011428,0.00011632926,0.00013226624,0.00006188053,0.00025880506,0.00021807128,0.00064806355,0.000041492745,0.000017562726],"category_scores_gemma":[0.00012863374,0.000074641684,0.00007099768,0.000623266,0.000057499063,0.0001648248,0.00034630104,0.000114516566,0.0016927798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028915447,0.000068041416,0.0010419827,0.000034140015,0.000015585494,0.000034941248,0.00048893184,0.00042867608,0.00062588317,0.16566573,0.8215784,0.010014786],"study_design_scores_gemma":[0.0002896146,0.00022949658,0.016956903,0.00017091863,0.000013929234,0.000117179705,0.0000375366,0.85415846,0.0021784552,0.092403136,0.032820046,0.0006242963],"about_ca_topic_score_codex":0.00022712992,"about_ca_topic_score_gemma":0.000012940873,"teacher_disagreement_score":0.85372984,"about_ca_system_score_codex":0.000047440553,"about_ca_system_score_gemma":0.000022784237,"threshold_uncertainty_score":0.99908453},"labels":[],"label_agreement":null},{"id":"W4385374119","doi":"10.48550/arxiv.2307.14733","title":"StubCoder: Automated Generation and Repair of Stub Code for Mock Objects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Stub (electronics); Computer science; Unit testing; Regression testing; Test case; Leverage (statistics); Programming language; Software; Engineering; Structural engineering; Artificial intelligence; Software development; Machine learning; Regression analysis","score_opus":0.1711203268709225,"score_gpt":0.23986957764398073,"score_spread":0.06874925077305824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385374119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19701406,0.00005976223,0.7737534,0.000044848657,0.00036295288,0.0004845863,0.000051755953,0.028142013,0.00008662424],"genre_scores_gemma":[0.94038546,0.00006874342,0.0588598,0.000029913577,0.000043763266,0.0000046767063,0.000027711882,0.000021986838,0.0005579527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985828,0.00008276128,0.00020648302,0.0008372294,0.00007901382,0.00021174822],"domain_scores_gemma":[0.9982508,0.00031734369,0.00024168506,0.00086245313,0.0002533829,0.00007436389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003917229,0.00020742622,0.00030720345,0.00026739252,0.00012384017,0.000058697926,0.00066044834,0.00021545311,6.1231526e-7],"category_scores_gemma":[0.00026025917,0.00024121761,0.00013196022,0.00036820804,0.000066278924,0.00015045337,0.0010874126,0.00017064357,0.0000029978353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015514833,0.0007269838,0.0688699,0.003198052,0.0011516813,0.0006121735,0.0042822626,0.51945776,0.0012641501,0.18594253,0.21102363,0.003315734],"study_design_scores_gemma":[0.00021884461,0.00010700933,0.001476185,0.000114275455,0.000042677355,0.0000023882203,0.000008009469,0.9347634,0.0004329935,0.06256379,0.00004235869,0.00022810909],"about_ca_topic_score_codex":0.00016812065,"about_ca_topic_score_gemma":0.00007281858,"teacher_disagreement_score":0.74337137,"about_ca_system_score_codex":0.00007334915,"about_ca_system_score_gemma":0.00014342596,"threshold_uncertainty_score":0.9836569},"labels":[],"label_agreement":null},{"id":"W4385477690","doi":"10.1109/sp46215.2023.10179438","title":"Finding Specification Blind Spots via Fuzz Testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spec#; Computer science; Codebase; Fuzz testing; Programming language; Code coverage; Source code; Software","score_opus":0.13349067738027193,"score_gpt":0.3164290038649961,"score_spread":0.1829383264847242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385477690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021996804,0.000010329405,0.92107975,0.00062411185,0.00024230688,0.00011035727,2.9696557e-7,0.044992365,0.010943648],"genre_scores_gemma":[0.5696615,0.0000013784969,0.42957342,0.00010376021,0.000076782184,0.000011271648,0.0000022904087,0.000008316072,0.0005612873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990461,0.00002363819,0.00016794795,0.0003165806,0.00019827124,0.00024745372],"domain_scores_gemma":[0.9987187,0.00060757186,0.00006326407,0.00047858126,0.00007615961,0.00005574398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005108091,0.00009164051,0.00008270345,0.00022567308,0.00016104453,0.00015421616,0.0005474854,0.0000435886,0.000008574365],"category_scores_gemma":[0.00066104083,0.000085380525,0.000026063099,0.0015657665,0.00001705538,0.00023517381,0.00020761114,0.000091743386,0.0005148001],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002832217,0.00004097615,0.03186904,0.00002137825,0.000007520052,0.000054148713,0.0005062548,0.000132493,0.0032626097,0.012892448,0.0745478,0.8766625],"study_design_scores_gemma":[0.00028680897,0.0000841913,0.1210765,0.00009927282,0.0000045743486,0.00007991922,0.000009951178,0.64261615,0.007313949,0.22586137,0.0020717406,0.0004955554],"about_ca_topic_score_codex":0.000040027837,"about_ca_topic_score_gemma":8.4818356e-7,"teacher_disagreement_score":0.87616694,"about_ca_system_score_codex":0.000027454398,"about_ca_system_score_gemma":0.000025991845,"threshold_uncertainty_score":0.66168857},"labels":[],"label_agreement":null},{"id":"W4385489881","doi":"10.1007/978-3-031-39764-6_14","title":"Granular Traceability Between Requirements and Test Cases for Safety-Critical Software Systems","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Traceability; Computer science; Requirements traceability; Test case; Software engineering; Software; Requirements engineering; Programming language; Requirement","score_opus":0.05911583272759753,"score_gpt":0.3129168050163533,"score_spread":0.2538009722887558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489881","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006972291,0.0004292669,0.990819,0.00055498263,0.0011894519,0.0008555206,0.00009351879,0.005947781,0.00004075463],"genre_scores_gemma":[0.1752596,0.000029477389,0.8233934,0.00031062288,0.000680378,0.00007114879,0.000021237227,0.00008171045,0.00015241039],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99565744,0.000050754083,0.0007304127,0.0018884474,0.00088542956,0.0007875223],"domain_scores_gemma":[0.97979456,0.017967343,0.00020513855,0.0013813743,0.00040415596,0.0002474497],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022149773,0.0005604803,0.00075646123,0.0005902547,0.00052884745,0.00073833903,0.0020569914,0.00038815907,0.0000011163739],"category_scores_gemma":[0.007974178,0.00052525953,0.0001270673,0.0004927418,0.0010076729,0.00047384694,0.0011604519,0.00056415773,0.000008166692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015258132,0.00008270671,0.027037598,0.0010658881,0.00002222808,0.00030816562,0.00058467954,0.0010236269,0.000013242768,0.013321531,0.0005444014,0.95598066],"study_design_scores_gemma":[0.00039773967,0.0009179166,0.003435804,0.0022302486,0.000046627083,0.00023714297,1.4863535e-7,0.16417377,0.00012319951,0.8263777,0.0007484513,0.0013112595],"about_ca_topic_score_codex":0.000070494425,"about_ca_topic_score_gemma":0.000014506078,"teacher_disagreement_score":0.9546694,"about_ca_system_score_codex":0.00025239986,"about_ca_system_score_gemma":0.0003347662,"threshold_uncertainty_score":0.9997199},"labels":[],"label_agreement":null},{"id":"W4385659392","doi":"10.21203/rs.3.rs-3226069/v1","title":"Using Data Mining Techniques to Generate Test Cases from Graph Transformation Systems Specifications","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Test suite; Model-based testing; Change impact analysis; Model transformation; Graph; Regression testing; Automation; Test case; Code coverage; Transformation (genetics); Graph rewriting; Software; Data mining; Software system; Theoretical computer science; Software construction; Programming language; Artificial intelligence; Machine learning; Engineering","score_opus":0.6196641684472338,"score_gpt":0.48093299807095913,"score_spread":0.1387311703762747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385659392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008712919,0.0005427527,0.9684951,0.0012054427,0.000476158,0.0018069977,0.0016500008,0.016933063,0.00017758776],"genre_scores_gemma":[0.32143027,0.0002517703,0.67562735,0.000035520527,0.0006418637,0.00058782846,0.0012609833,0.000081646656,0.00008279522],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955305,0.00051355356,0.00061805075,0.0013766468,0.0012945118,0.0006667644],"domain_scores_gemma":[0.99126846,0.0031596848,0.00016319046,0.004281416,0.0008768076,0.00025046818],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0033281043,0.00031409803,0.0003822374,0.0014019964,0.0005980462,0.0017408805,0.004315593,0.00030096268,0.000003299868],"category_scores_gemma":[0.0032526474,0.00031888188,0.000077820914,0.0017927513,0.00008680652,0.00052076246,0.004095162,0.0009033888,0.00005761519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005431414,0.0010070667,0.018164743,0.0047887303,0.0003769509,0.0014533532,0.018524265,0.0118361255,0.011488779,0.0076156813,0.7231794,0.20151056],"study_design_scores_gemma":[0.0001510346,0.00032760648,0.0025128408,0.009777294,0.00003997001,0.000085522675,0.00046181882,0.9424013,0.0069011743,0.02954758,0.0063709766,0.0014228984],"about_ca_topic_score_codex":0.008992103,"about_ca_topic_score_gemma":0.00009923321,"teacher_disagreement_score":0.9305652,"about_ca_system_score_codex":0.0002887145,"about_ca_system_score_gemma":0.00052724604,"threshold_uncertainty_score":0.9999263},"labels":[],"label_agreement":null},{"id":"W4385768129","doi":"10.24963/ijcai.2023/542","title":"Revisiting the Evaluation of Deep Learning-Based Compiler Testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Compiler; Generator (circuit theory); Correctness; Programming language; Optimizing compiler; Domain-specific language; Compiler construction; Artificial intelligence","score_opus":0.11359556129603447,"score_gpt":0.34106120201102075,"score_spread":0.22746564071498626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385768129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028103227,0.0000678324,0.9480744,0.0011569185,0.00008971099,0.00020370004,1.544513e-7,0.01688406,0.005420012],"genre_scores_gemma":[0.8944204,3.477765e-7,0.10537428,0.00011429117,0.000043836393,0.00001693193,0.0000016013618,0.00000579722,0.000022524307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987597,0.0002449299,0.00018304872,0.00017732498,0.00048364754,0.00015137246],"domain_scores_gemma":[0.99694675,0.0021450894,0.00012307071,0.00035187267,0.00041320792,0.000019991307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039974414,0.000066821354,0.00008549174,0.00009048517,0.00017666125,0.00006203757,0.00044635747,0.000023969902,0.0000103227185],"category_scores_gemma":[0.005253917,0.000046006873,0.000032481596,0.0010690397,0.000030701365,0.00007770637,0.00013444934,0.000111150825,0.000028611932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.8614734e-7,0.000005572636,0.031613875,0.000018453477,0.0000041229737,0.0000012091032,0.00020884286,0.042452496,0.0001544795,0.0009307925,0.0010364994,0.9235731],"study_design_scores_gemma":[0.000077567434,0.000022149372,0.030584265,0.000057454185,0.0000066416883,0.0000020969737,0.000008270061,0.96098953,0.00050215697,0.0076247626,0.00006575848,0.000059345315],"about_ca_topic_score_codex":0.000044110497,"about_ca_topic_score_gemma":7.544887e-7,"teacher_disagreement_score":0.9235137,"about_ca_system_score_codex":0.000019682313,"about_ca_system_score_gemma":0.000052287636,"threshold_uncertainty_score":0.62898093},"labels":[],"label_agreement":null},{"id":"W4385977849","doi":"10.1007/s41870-023-01390-9","title":"A study of the interactive role of metamorphic testing and machine learning in the quality assurance of a deep learning forecasting application","year":2023,"lang":"en","type":"article","venue":"International Journal of Information Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Mitacs","keywords":"Machine learning; Computer science; Artificial intelligence; Metamorphic rock; Generalization; Software quality; Deep learning; Quality (philosophy); Software; Algorithm; Software development; Programming language","score_opus":0.030810263423512226,"score_gpt":0.3040353657264644,"score_spread":0.27322510230295216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385977849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8899102,0.000041401378,0.10921811,0.00040557576,0.00004879339,0.00013702818,8.300097e-7,0.00015995998,0.000078048826],"genre_scores_gemma":[0.98617643,0.0000061871847,0.013783118,0.000014528434,0.0000065013487,0.000009867227,5.7685133e-7,0.0000021501453,6.14765e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985734,0.00014108313,0.00077358563,0.000058784753,0.0003830481,0.0000700507],"domain_scores_gemma":[0.9959552,0.0012996816,0.0018854826,0.00013338763,0.00071906584,0.0000071440504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018294583,0.00006138548,0.00016703433,0.0006503638,0.000045807486,0.000022332948,0.0008755419,0.000041834606,2.739014e-7],"category_scores_gemma":[0.0073136194,0.000041036586,0.00003436711,0.0009922053,0.000057550154,0.00048178635,0.000254499,0.00037450696,2.4005928e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027276876,0.00008708541,0.55262524,0.000027341364,0.000057313995,0.0000020119528,0.012095896,0.009268311,0.001476945,0.0024040916,0.0000045917914,0.42192388],"study_design_scores_gemma":[0.0010347358,0.00074937905,0.30626363,0.0003983648,0.000018917928,0.00039458103,0.008019372,0.62700784,0.007912796,0.04800891,0.00006690239,0.00012459332],"about_ca_topic_score_codex":0.00014181198,"about_ca_topic_score_gemma":0.000019048744,"teacher_disagreement_score":0.6177395,"about_ca_system_score_codex":0.000025144798,"about_ca_system_score_gemma":0.00003216519,"threshold_uncertainty_score":0.87556136},"labels":[],"label_agreement":null},{"id":"W4386031629","doi":"10.1145/3617171","title":"<scp>StubCoder</scp> : Automated Generation and Repair of Stub Code for Mock Objects","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Hong Kong University of Science and Technology; Impact Fund; National Science Foundation","keywords":"Stub (electronics); Computer science; Unit testing; Regression testing; Leverage (statistics); Test case; Programming language; Software; Software development; Artificial intelligence; Engineering; Structural engineering; Machine learning; Software construction","score_opus":0.12252016812216412,"score_gpt":0.3394841656674571,"score_spread":0.21696399754529297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386031629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047828432,0.00017542786,0.93096876,0.000056164055,0.00033742664,0.0001881508,0.000021623866,0.020422237,0.0000017792055],"genre_scores_gemma":[0.08577038,0.00009740872,0.91381526,0.000050283514,0.000025322537,0.000110636596,0.0000068705926,0.000023366887,0.000100443154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988977,0.000120952354,0.00023671915,0.00038694462,0.00009879504,0.00025888853],"domain_scores_gemma":[0.99328816,0.0060394304,0.0000584181,0.00045104168,0.000087307024,0.00007564911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009393048,0.00016362593,0.0002827594,0.00034693594,0.00013779584,0.000025372032,0.00021714522,0.00014562183,3.001151e-7],"category_scores_gemma":[0.0043067993,0.00016706248,0.00006831203,0.00043161062,0.00003677633,0.00011073469,0.000026372056,0.00013799699,8.549983e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066336324,0.0004977217,0.0053698835,0.0029448615,0.0011850841,0.000079363366,0.019332321,0.38994044,0.0450244,0.0065177903,0.034471698,0.49457008],"study_design_scores_gemma":[0.0004578548,0.00049301155,0.0030454341,0.00007782199,0.000052308846,0.000078908335,0.000029846184,0.9724969,0.017616209,0.0045252005,0.00097150926,0.00015497977],"about_ca_topic_score_codex":0.000019939951,"about_ca_topic_score_gemma":0.000004148839,"teacher_disagreement_score":0.5825565,"about_ca_system_score_codex":0.000015628471,"about_ca_system_score_gemma":0.00003164868,"threshold_uncertainty_score":0.681261},"labels":[],"label_agreement":null},{"id":"W4386140507","doi":"10.1007/s10664-023-10363-2","title":"A comparison of reinforcement learning frameworks for software testing tasks","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Regression testing; Software performance testing; Software engineering; System integration testing; Software reliability testing; Software development; Adaptation (eye); Context (archaeology); Test strategy; Reinforcement learning; Software inspection; Manual testing; Software testing; Software construction; Machine learning; Software; Software quality; Programming language","score_opus":0.06973939181903052,"score_gpt":0.35039542706618215,"score_spread":0.28065603524715166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386140507","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014462404,0.000107738066,0.95816946,0.00011609215,0.00030068605,0.00026869407,0.0000018636539,0.0265605,0.000012583083],"genre_scores_gemma":[0.44839302,0.000001263909,0.5512787,0.00006548847,0.00007747795,0.000091636626,0.000012845375,0.00003470445,0.00004486924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792284,0.000027709151,0.0005696762,0.00046463145,0.00040300633,0.0006121518],"domain_scores_gemma":[0.9940146,0.0049387002,0.00018759698,0.0004905515,0.00021803974,0.00015048088],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005765295,0.00026913846,0.0004463816,0.00030291115,0.00019096614,0.00009405167,0.0007281156,0.0002742961,0.000003558172],"category_scores_gemma":[0.017922437,0.00027577413,0.00014598809,0.0015287899,0.000029038352,0.00019724634,0.00042629775,0.00067096297,0.000015821432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065271793,0.0000453128,0.34595644,0.00029851033,0.00003686968,0.000009685733,0.0009760349,0.58968806,0.00011650944,0.00019016516,0.0131597705,0.049516086],"study_design_scores_gemma":[0.00024785503,0.0003686287,0.016040094,0.00043067063,0.000014320244,0.0000076289916,0.000008849095,0.9749947,0.0012233724,0.0023331763,0.0038736844,0.00045702554],"about_ca_topic_score_codex":0.000014645267,"about_ca_topic_score_gemma":2.3152698e-7,"teacher_disagreement_score":0.4339306,"about_ca_system_score_codex":0.000079355625,"about_ca_system_score_gemma":0.0000638294,"threshold_uncertainty_score":0.9999694},"labels":[],"label_agreement":null},{"id":"W4386231449","doi":"10.1145/3611643.3616255","title":"Accelerating Continuous Integration with Parallel Batch Testing","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reduction (mathematics); Queue; Regression testing; Variable (mathematics); Test case; Test (biology); Execution time; Software; Parallel computing; Real-time computing; Operating system; Software development; Programming language; Machine learning","score_opus":0.1211693237630664,"score_gpt":0.2987040689830362,"score_spread":0.17753474521996981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386231449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027361813,0.000023610603,0.93574715,0.000669012,0.00033866905,0.00036832725,0.0000016539166,0.055789758,0.0043256297],"genre_scores_gemma":[0.18210112,0.0000027552544,0.81660765,0.00020553176,0.0001236334,0.00015768819,0.000016083595,0.00003914577,0.0007463966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978314,0.00007854713,0.00040705045,0.0009121246,0.00039163654,0.00037920984],"domain_scores_gemma":[0.99708366,0.0009988858,0.00031786857,0.0011132676,0.0004010605,0.00008526283],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064918667,0.00036466165,0.00038058154,0.00019841477,0.00018988183,0.0010053898,0.0013603434,0.00022286586,0.0000035543294],"category_scores_gemma":[0.0013339376,0.0002813373,0.00006352668,0.00050656433,0.000040558825,0.0002305224,0.0016394414,0.000762956,0.000040273466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021335603,0.00021114184,0.06790953,0.00042964588,0.0001737988,0.0004661706,0.0034468751,0.011103519,0.00030765356,0.025984664,0.12078901,0.76915663],"study_design_scores_gemma":[0.00021188322,0.00024794327,0.004926955,0.0015841955,0.00002008204,0.000073218645,0.000027473985,0.8277021,0.00051294354,0.16372117,0.00006198768,0.00091000926],"about_ca_topic_score_codex":0.0013971393,"about_ca_topic_score_gemma":0.000070528215,"teacher_disagreement_score":0.8165986,"about_ca_system_score_codex":0.00007073592,"about_ca_system_score_gemma":0.00023710036,"threshold_uncertainty_score":0.9999639},"labels":[],"label_agreement":null},{"id":"W4386442953","doi":"10.1145/3617172","title":"On the Caching Schemes to Speed Up Program Reduction","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reduction (mathematics); Debugging; Compiler; Cache; Parallel computing; Process (computing); ENCODE; Memory footprint; Encoding (memory); Compile time; Computation; Theoretical computer science; Computer engineering; Algorithm; Programming language; Artificial intelligence","score_opus":0.1289523923715804,"score_gpt":0.35603718592683653,"score_spread":0.22708479355525613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386442953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04509002,0.000020191053,0.9355958,0.0016198803,0.0009033249,0.0002492549,0.0000019429092,0.016514782,0.000004770838],"genre_scores_gemma":[0.15202692,0.000016529366,0.8473761,0.00022641216,0.00004227526,0.00013081418,0.0000014154589,0.00002316275,0.00015635302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882126,0.00017044051,0.00015809218,0.0003944431,0.00014395923,0.00031183078],"domain_scores_gemma":[0.9953255,0.0038078397,0.000029390309,0.0007012476,0.00004163644,0.00009438429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011388606,0.00017245121,0.0001767402,0.00035876274,0.0002559603,0.00007199566,0.00047738926,0.000097986784,0.0000035714195],"category_scores_gemma":[0.0036887173,0.00013716971,0.00006104656,0.00082586054,0.000029153709,0.000084685744,0.00003322637,0.00036655524,0.000026853531],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019833353,0.00004596597,0.00002780976,0.000030718944,0.0000488365,0.000008740358,0.0012035167,0.038831577,0.0011190743,0.004454753,0.0020372241,0.9521719],"study_design_scores_gemma":[0.0027356953,0.008335557,0.010523158,0.0019254443,0.0002963012,0.0016812615,0.0004703902,0.49243787,0.16402136,0.24685949,0.06540162,0.005311852],"about_ca_topic_score_codex":0.000028858542,"about_ca_topic_score_gemma":4.8693556e-7,"teacher_disagreement_score":0.9468601,"about_ca_system_score_codex":0.000029797628,"about_ca_system_score_gemma":0.000020364687,"threshold_uncertainty_score":0.5593618},"labels":[],"label_agreement":null},{"id":"W4386515768","doi":"10.1007/978-3-031-40436-8_13","title":"Applying Formal Verification to an Open-Source Real-Time Operating System","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Promela; Computer science; Rotation formalisms in three dimensions; Programming language; Variety (cybernetics); Model checking; Semantics (computer science); Formal methods; Formal specification; Code (set theory); Formal verification; Specification language; Software engineering; Artificial intelligence","score_opus":0.034057987013124694,"score_gpt":0.28208893732041257,"score_spread":0.2480309503072879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386515768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012380104,0.000013430428,0.984719,0.00016824219,0.0007448636,0.0012862717,0.000003778894,0.009953564,0.0029870553],"genre_scores_gemma":[0.058342844,0.000003894262,0.9396712,0.0006818273,0.00038652937,0.00020651656,0.000013227855,0.000089328925,0.00060459424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957344,0.00006533949,0.0006189506,0.0018882897,0.00090633787,0.0007866915],"domain_scores_gemma":[0.9963238,0.00061509723,0.00028943122,0.0021921392,0.00030163553,0.00027788998],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0026812102,0.0005016983,0.00054969103,0.0008449458,0.0007140328,0.0023442665,0.0069909557,0.0002740594,0.0000027724218],"category_scores_gemma":[0.00026887126,0.00048802444,0.000059424878,0.0010544632,0.00016291784,0.0014680824,0.004187761,0.00052748737,0.00016756066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040679856,0.000017569271,0.000048050704,0.000064355874,0.0000056114404,0.000047794947,0.0012078257,0.030128269,0.0006828535,0.01301117,0.00015480845,0.95462763],"study_design_scores_gemma":[0.00013448496,0.00035720543,0.00009054257,0.0013933652,0.000005818377,0.00010698448,4.1845112e-7,0.971405,0.0009081396,0.024294086,0.000471645,0.0008322704],"about_ca_topic_score_codex":0.0002687535,"about_ca_topic_score_gemma":0.000018918794,"teacher_disagreement_score":0.9537954,"about_ca_system_score_codex":0.00044869128,"about_ca_system_score_gemma":0.00042920373,"threshold_uncertainty_score":0.9997572},"labels":[],"label_agreement":null},{"id":"W4386889431","doi":"10.1145/3624745","title":"Search-Based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; McMaster University","keywords":"Fitness function; Computer science; Domain (mathematical analysis); Software; Set (abstract data type); Function (biology); Search-based software engineering; Software engineering; Artificial intelligence; Machine learning; Data mining; Software system; Programming language; Software construction; Genetic algorithm","score_opus":0.09860297203966012,"score_gpt":0.31119659442560965,"score_spread":0.21259362238594953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386889431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03720156,0.00008710573,0.94110364,0.00046977994,0.0002795826,0.00016418794,0.00003240039,0.020659843,0.0000018816519],"genre_scores_gemma":[0.04909941,0.00001832913,0.9503654,0.00020854683,0.000021889331,0.0001106276,0.000021763031,0.000044443303,0.00010957929],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981062,0.0002621122,0.00030354905,0.00062362716,0.00020500585,0.00049953186],"domain_scores_gemma":[0.98972404,0.0092220465,0.000050262293,0.00065340707,0.0001402629,0.00021000381],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094355346,0.00029222376,0.0003499792,0.00046309317,0.00038222322,0.00011932747,0.00044768935,0.00021068809,0.000005561503],"category_scores_gemma":[0.005557699,0.0002969432,0.000059121874,0.0011001762,0.000101817815,0.00015983869,0.00006013044,0.00042703544,0.0000131372235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003570678,0.0001547302,0.0062517086,0.000401967,0.00017483026,0.00009126534,0.0006904894,0.1939349,0.005271782,0.00030831376,0.0030831967,0.7896011],"study_design_scores_gemma":[0.0010276651,0.00072916126,0.012071197,0.00027486635,0.00009057206,0.00025580547,0.000020497402,0.97561926,0.005052044,0.0033120087,0.00059782976,0.0009491062],"about_ca_topic_score_codex":0.000056647452,"about_ca_topic_score_gemma":0.0000020683149,"teacher_disagreement_score":0.788652,"about_ca_system_score_codex":0.000038295806,"about_ca_system_score_gemma":0.000088943794,"threshold_uncertainty_score":0.99994826},"labels":[],"label_agreement":null},{"id":"W4386950100","doi":"10.2139/ssrn.4580607","title":"Hardening of Network Segmentation Using  Automated Referential Penetration Testing","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Segmentation; Penetration (warfare); Hardening (computing); Computer science; Penetration test; Artificial intelligence; Reliability engineering; Materials science; Structural engineering; Engineering; Composite material; Operations research","score_opus":0.0736148210369201,"score_gpt":0.3234858426626048,"score_spread":0.24987102162568467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386950100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06922781,0.0004759024,0.9202167,0.000061755556,0.00095306215,0.00017650612,0.0000013911477,0.008850322,0.00003655898],"genre_scores_gemma":[0.64328694,0.00016175355,0.35594356,0.000012852024,0.00047841575,0.000007631338,0.000015909509,0.000038506878,0.000054448115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668115,0.00020260726,0.0006815908,0.00043296267,0.00055588706,0.0014458123],"domain_scores_gemma":[0.9977154,0.0003468782,0.0010752066,0.00041570768,0.00039170685,0.00005509648],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035391094,0.00025332015,0.00032070396,0.00028289482,0.00030288374,0.00031408726,0.0009320399,0.00024068572,0.0000010845881],"category_scores_gemma":[0.00059419917,0.00026447716,0.00012515116,0.00054165674,0.00002666827,0.00023948832,0.0006190203,0.002550786,0.000003187052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006602655,0.00018921675,0.045355808,0.00051247154,0.0011286582,0.00005877486,0.001612467,0.75849,0.008463015,0.038872503,0.0045581977,0.14069286],"study_design_scores_gemma":[0.00012291766,0.00011614118,0.0009409126,0.0005505455,0.00004134377,0.00019189902,0.000016707458,0.52207494,0.00020763773,0.47553232,0.0000012653755,0.00020338212],"about_ca_topic_score_codex":0.00043157453,"about_ca_topic_score_gemma":0.00011681804,"teacher_disagreement_score":0.5740591,"about_ca_system_score_codex":0.00085688446,"about_ca_system_score_gemma":0.003501493,"threshold_uncertainty_score":0.99998075},"labels":[],"label_agreement":null},{"id":"W4387165217","doi":"10.1007/s10270-023-01123-3","title":"Fault localization in DSLTrans model transformations by combining symbolic execution and spectrum-based analysis","year":2023,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; Polytechnique Montréal","funders":"Agencia Estatal de Investigación; Austrian Science Fund; Bundesministerium für Digitalisierung und Wirtschaftsstandort; Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung; Ministerio de Ciencia e Innovación; Universidad de Málaga","keywords":"Computer science; Symbolic execution; Programming language; Model checking; Parallel computing; Fault (geology); Theoretical computer science; Software engineering; Software","score_opus":0.022085225537430975,"score_gpt":0.2562257732166029,"score_spread":0.23414054767917192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387165217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035957403,0.00023445976,0.95391506,0.00016149812,0.00007696651,0.00027968554,0.000019009798,0.009332583,0.000023344734],"genre_scores_gemma":[0.9742458,0.00003305919,0.025381306,0.000084995954,0.000011657397,0.00009143245,0.000117190786,0.000022197668,0.000012383263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981025,0.00010493096,0.0005578055,0.0004780648,0.0003682421,0.00038849056],"domain_scores_gemma":[0.9991138,0.00018814986,0.000099477555,0.00041685032,0.00008582881,0.00009590906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007675617,0.0002119343,0.000354904,0.0009426007,0.00026960534,0.00025119717,0.00033905165,0.0001330467,3.5367006e-7],"category_scores_gemma":[0.0001011377,0.00022561268,0.00009141588,0.002719963,0.000024803212,0.000502049,0.00003905714,0.0001730554,0.000003967504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019434224,0.000017990737,0.0035195423,0.000067687295,0.000021094642,0.000002156572,0.0012241341,0.9935232,0.000023338396,0.00067348423,0.00024198888,0.00068345125],"study_design_scores_gemma":[0.0002609988,0.000020638045,0.000031311043,0.0001942655,0.000046123514,0.0000032895257,0.000047555033,0.9923483,0.000033808912,0.0067596463,0.000007728752,0.000246332],"about_ca_topic_score_codex":0.0010034218,"about_ca_topic_score_gemma":0.000045012108,"teacher_disagreement_score":0.9382884,"about_ca_system_score_codex":0.00010327568,"about_ca_system_score_gemma":0.00007992813,"threshold_uncertainty_score":0.9200218},"labels":[],"label_agreement":null},{"id":"W4387735187","doi":"10.1145/3628159","title":"Generation-based Differential Fuzzing for Deep Learning Libraries","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Fuzz testing; Computer science; Context (archaeology); Task (project management); Machine learning; Artificial intelligence; Deep learning; Benchmark (surveying); Software engineering; Software; Programming language","score_opus":0.14059899809814053,"score_gpt":0.32340425284178986,"score_spread":0.18280525474364934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387735187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003663086,0.00006648527,0.9819157,0.00026672683,0.0006297991,0.00012127646,0.0000032453916,0.013332745,9.469452e-7],"genre_scores_gemma":[0.13744475,0.000015985208,0.86215746,0.000085986496,0.00006850307,0.00014559683,0.000012251384,0.000025007712,0.000044463017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989687,0.000123654,0.00016999632,0.0003569888,0.000091466536,0.0002891776],"domain_scores_gemma":[0.99368,0.0058231223,0.000037569713,0.00034863112,0.00003763375,0.00007304002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004813405,0.00016239313,0.00020598892,0.0003478197,0.00031736237,0.00009894692,0.0003042371,0.00012434035,0.0000037828775],"category_scores_gemma":[0.002561527,0.00016609656,0.000077979785,0.00036186754,0.000028994406,0.00013689318,0.000018964212,0.00023014122,0.0000031607665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002917692,0.00004951024,0.00051302067,0.00016945391,0.00009126016,0.00001130847,0.0011274552,0.3252201,0.0028969443,0.006522725,0.0004763269,0.6628927],"study_design_scores_gemma":[0.00035133664,0.00024086259,0.00048354975,0.00003724261,0.000024694644,0.00001541059,0.000008718038,0.9807503,0.0070693884,0.009779502,0.0009468533,0.0002920987],"about_ca_topic_score_codex":0.0000081991075,"about_ca_topic_score_gemma":9.818601e-7,"teacher_disagreement_score":0.66260064,"about_ca_system_score_codex":0.000020922149,"about_ca_system_score_gemma":0.000028640658,"threshold_uncertainty_score":0.67732215},"labels":[],"label_agreement":null},{"id":"W4387855793","doi":"10.23977/acss.2023.070813","title":"Research on Vehicle Security Chip Application and Testing Based on Fault Injection","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fault injection; Automotive industry; Embedded system; Chip; Fault (geology); Computer science; Fault detection and isolation; Automotive engineering; Engineering; Software; Electrical engineering; Operating system; Telecommunications","score_opus":0.06852609827714659,"score_gpt":0.3622269567651739,"score_spread":0.2937008584880273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387855793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1743295,0.0006102262,0.8201261,0.00021547341,0.0003523188,0.00051191077,0.0000022534325,0.003379683,0.00047251055],"genre_scores_gemma":[0.9906238,0.000028436361,0.0089927325,0.00010807396,0.00013370144,0.00009812238,0.0000018975144,0.000008633337,0.000004631726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984072,0.0002666996,0.00021811294,0.000509646,0.00033973833,0.000258614],"domain_scores_gemma":[0.9971399,0.0022970485,0.00007086623,0.00032926854,0.00010329614,0.00005967491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001783802,0.000116619725,0.0001623048,0.00036525103,0.00021396628,0.00021587579,0.0002498284,0.000061436825,9.429623e-8],"category_scores_gemma":[0.000114805436,0.0001042782,0.000013079444,0.0010866643,0.000046954065,0.00023556041,0.00012998798,0.00022931937,0.00000718303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002798163,0.00014159843,0.042430736,0.0003850878,0.0000052310324,0.00003674972,0.0008547631,0.22409871,0.00024355223,0.0086371,0.0017126934,0.7214258],"study_design_scores_gemma":[0.00015813783,0.00046624415,0.0040781708,0.00039983584,4.694506e-7,0.000008201313,0.000008857411,0.97727406,0.00009866556,0.017108122,0.0002840135,0.00011520074],"about_ca_topic_score_codex":0.00013486587,"about_ca_topic_score_gemma":0.00000497341,"teacher_disagreement_score":0.81629425,"about_ca_system_score_codex":0.000034294226,"about_ca_system_score_gemma":0.000018308345,"threshold_uncertainty_score":0.42523417},"labels":[],"label_agreement":null},{"id":"W4388032626","doi":"","title":"Heap Fuzzing:Automatic Garbage Collection Testing with Expert-Guided Random Events","year":2023,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Fuzz testing; Heap (data structure); Computer science; Garbage collection; Random testing; Garbage; Programming language; Database; Machine learning; Test case; Software","score_opus":0.0294070827596225,"score_gpt":0.25298723274485946,"score_spread":0.22358014998523695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388032626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0923755,0.00015160405,0.87064904,0.0056099994,0.00016066123,0.0004907771,0.0000022130394,0.01881294,0.011747268],"genre_scores_gemma":[0.57486147,0.000030644627,0.4225042,0.00014123636,0.000014170832,0.00011591039,0.000020763699,0.000032211436,0.0022794185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960999,0.0020054881,0.00038992675,0.00059865124,0.00048736742,0.0004186695],"domain_scores_gemma":[0.9931623,0.003838755,0.0002724138,0.0014663048,0.0011122916,0.00014796562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046555153,0.00023046207,0.00026019677,0.00030480628,0.0006720249,0.0003425432,0.0011161163,0.000085152984,0.00001158592],"category_scores_gemma":[0.0047693877,0.00021365381,0.000076668606,0.002375278,0.000088486915,0.0003279551,0.00045998386,0.00020289044,0.000057824156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059160768,0.0017240999,0.090596355,0.00041422626,0.00028283533,0.0001595591,0.060160954,0.0004191732,0.014039122,0.03573063,0.14963129,0.6467826],"study_design_scores_gemma":[0.0025046477,0.000005317909,0.021095881,0.0028841197,0.00002394781,0.00018250945,0.00006581246,0.9156928,0.03358167,0.020803388,0.0023294983,0.00083039753],"about_ca_topic_score_codex":0.00076906325,"about_ca_topic_score_gemma":0.000107724285,"teacher_disagreement_score":0.91527367,"about_ca_system_score_codex":0.00009560239,"about_ca_system_score_gemma":0.0001718123,"threshold_uncertainty_score":0.8712549},"labels":[],"label_agreement":null},{"id":"W4388072373","doi":"10.2316/j.2023.206-0886","title":"PROBABILISTIC MODEL CHECKING METHOD FOR ROBOT PERFORMANCE OPTIMISATION, 461-470.","year":2023,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Probabilistic logic; Model checking; Robot; Statistical model; Artificial intelligence; Programming language","score_opus":0.04118871263207958,"score_gpt":0.32994843460602785,"score_spread":0.2887597219739483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388072373","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007178605,0.000019364732,0.9894882,0.0021758706,0.0003808401,0.000085547974,0.0000014609653,0.00063963124,0.000030468567],"genre_scores_gemma":[0.32641518,0.000027006614,0.6733507,0.00007923957,0.00007905978,0.0000050876447,0.0000037664415,0.0000056094655,0.000034359142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910444,0.000020667656,0.00033932072,0.0001180587,0.00031349028,0.00010399875],"domain_scores_gemma":[0.9986335,0.00025809396,0.00031677744,0.00009517287,0.00065731676,0.00003911105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086660066,0.00007742762,0.00011333149,0.0002499694,0.00007816266,0.00018371883,0.0003909918,0.000038920418,4.973339e-7],"category_scores_gemma":[0.0004916634,0.000069298105,0.00004935237,0.00015342438,0.000014278658,0.000464743,0.00007840056,0.00007468182,0.0000012475593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054205643,0.000017223201,0.00028143855,0.000021280252,0.000021394706,0.0000017280468,0.0003075855,0.9111461,0.00020019797,0.009547905,0.0010929983,0.07735674],"study_design_scores_gemma":[0.0001992364,0.00006179327,0.0017437801,0.000104584935,0.000008449554,0.00006863492,0.0000028998509,0.9285526,0.00031368068,0.06882981,0.00004300426,0.00007149949],"about_ca_topic_score_codex":0.0000019783924,"about_ca_topic_score_gemma":2.2233868e-7,"teacher_disagreement_score":0.31923658,"about_ca_system_score_codex":0.000054711723,"about_ca_system_score_gemma":0.0000773356,"threshold_uncertainty_score":0.28258947},"labels":[],"label_agreement":null},{"id":"W4388408996","doi":"10.1109/dsaa60987.2023.10302571","title":"Towards Deep Learning Models for Automatic Computer Program Grading","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Python (programming language); Feature engineering; Leverage (statistics); Deep learning; Machine learning; Implementation; Grading (engineering); Compiler; Programming language; Software engineering","score_opus":0.0649315470941495,"score_gpt":0.313413597167929,"score_spread":0.2484820500737795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388408996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019465538,0.000010190877,0.90056306,0.00031089247,0.00017279555,0.00035550172,2.1262491e-7,0.095950425,0.00069038133],"genre_scores_gemma":[0.21837151,0.0000020872458,0.7810711,0.00012573104,0.00005674068,0.00020713353,0.000004049034,0.000015100759,0.00014650128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988617,0.000035019242,0.00018782406,0.00034136392,0.00019405058,0.00038005714],"domain_scores_gemma":[0.99911034,0.0003665744,0.000054654265,0.00031249307,0.00008257246,0.000073376395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005145805,0.00012967098,0.00015758428,0.0001830736,0.00020617347,0.00028270925,0.00058893464,0.000053389347,0.0000020350838],"category_scores_gemma":[0.00013132875,0.00011294622,0.00008414521,0.00062438677,0.000020514355,0.0003134581,0.0002768472,0.00010365362,0.000029237428],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.612458e-7,0.000019414289,0.00015970341,0.000034299977,0.000007525031,0.000004327748,0.0003719091,0.00352674,0.0000027009419,0.015182913,0.008525637,0.97216445],"study_design_scores_gemma":[0.00008982265,0.00020925103,0.00023930293,0.000034127785,0.0000027508424,0.000009291718,0.0000034272402,0.84270084,0.000053345288,0.15617935,0.00034035885,0.00013813136],"about_ca_topic_score_codex":0.000023318604,"about_ca_topic_score_gemma":9.119378e-7,"teacher_disagreement_score":0.97202635,"about_ca_system_score_codex":0.000027971368,"about_ca_system_score_gemma":0.000028344723,"threshold_uncertainty_score":0.4605813},"labels":[],"label_agreement":null},{"id":"W4388483618","doi":"10.1109/ase56229.2023.00148","title":"Towards Autonomous Testing Agents via Conversational Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Test strategy; Autonomy; Software testing; Process (computing); Software engineering; Process management; Knowledge management; Human–computer interaction; Data science; Software; Engineering; Programming language; Political science","score_opus":0.057643131007728256,"score_gpt":0.2978644873038421,"score_spread":0.24022135629611382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005257066,0.000016391681,0.951187,0.0003955961,0.00016289367,0.00008848479,0.0000046560835,0.034138937,0.008748933],"genre_scores_gemma":[0.6984534,5.4106357e-7,0.30007008,0.00060958863,0.000038186823,0.00001504262,0.000008998127,0.000009225323,0.000794931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989493,0.00002829965,0.00015239972,0.00030143413,0.00025987648,0.00030869507],"domain_scores_gemma":[0.99919474,0.00022594357,0.00004752639,0.00037998467,0.00007917951,0.00007263443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004445419,0.0001061599,0.00009988545,0.00014183199,0.00012766605,0.00010069123,0.00053768407,0.000047287027,0.000035704732],"category_scores_gemma":[0.00028979869,0.00009899405,0.000037639693,0.0006665213,0.000015950087,0.00031136096,0.00037166913,0.00008501193,0.00028274738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057718025,0.0002774714,0.016596029,0.00010875834,0.00010811703,0.00047291289,0.013475651,0.0078104367,0.0008013682,0.18106149,0.32058346,0.4586985],"study_design_scores_gemma":[0.00010996024,0.00002130972,0.0025438007,0.000011401061,0.000002320011,0.000015184013,0.000008464162,0.92202735,0.00026022448,0.07456091,0.00031196096,0.00012711201],"about_ca_topic_score_codex":0.00022100602,"about_ca_topic_score_gemma":0.0000020316284,"teacher_disagreement_score":0.91421694,"about_ca_system_score_codex":0.000031497326,"about_ca_system_score_gemma":0.00008532065,"threshold_uncertainty_score":0.40368602},"labels":[],"label_agreement":null},{"id":"W4388483694","doi":"10.1109/ase56229.2023.00100","title":"FLUX: Finding Bugs with LLVM IR Based Unit Test Crossovers","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Compiler; Optimizing compiler; Interprocedural optimization; Software bug; Benchmark (surveying); Parallel computing; Fuzz testing; Test suite; Unit testing; Operating system; Programming language; Test case; Software; Loop optimization","score_opus":0.03891028125000218,"score_gpt":0.28167980977821744,"score_spread":0.24276952852821526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049420983,0.000006580848,0.8568181,0.0016404839,0.00017308166,0.00019244789,0.0000045516244,0.07696924,0.014774554],"genre_scores_gemma":[0.68781555,5.4889176e-7,0.3076593,0.00081542693,0.000029134417,0.000019942489,0.000006856869,0.000017723762,0.0036355432],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988821,0.000020402817,0.0001237236,0.00034802058,0.0002774291,0.00034830772],"domain_scores_gemma":[0.99813974,0.0010642809,0.000049620096,0.00058409566,0.000073240386,0.00008900159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003292942,0.00013749389,0.000115985444,0.00020568214,0.00020991925,0.0002634061,0.00066390017,0.00004936737,0.000033356053],"category_scores_gemma":[0.0004572818,0.000107728076,0.00003365879,0.0014069658,0.00005471207,0.000227679,0.0001725382,0.00011749062,0.00023817547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017086926,0.00017355669,0.38704288,0.000082151644,0.000028894781,0.00044249345,0.00098423,0.000958166,0.0012539531,0.011711826,0.5700868,0.027217953],"study_design_scores_gemma":[0.0012623727,0.00082903996,0.079612665,0.0003585311,0.000015400818,0.00006866902,0.000041633786,0.86773473,0.013295455,0.022426762,0.013200469,0.0011542699],"about_ca_topic_score_codex":0.0001231803,"about_ca_topic_score_gemma":0.000008858762,"teacher_disagreement_score":0.8667766,"about_ca_system_score_codex":0.000027799004,"about_ca_system_score_gemma":0.00011676748,"threshold_uncertainty_score":0.43930236},"labels":[],"label_agreement":null},{"id":"W4388483831","doi":"10.1109/ase56229.2023.00079","title":"Fuzzing for CPS Mutation Testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Entomological Society of America","keywords":"Fuzz testing; Symbolic execution; Computer science; White-box testing; Software testing; Mutation testing; Software reliability testing; Mutation; Non-regression testing; Test strategy; Software performance testing; Software; Test case; Process (computing); Manual testing; Programming language; Software engineering; System integration testing; Reliability engineering; Keyword-driven testing; Software development; Software construction; Machine learning; Engineering","score_opus":0.09621675244336558,"score_gpt":0.3177917592940461,"score_spread":0.2215750068506805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483831","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00478558,0.0000047692984,0.9519954,0.00036481,0.0001197957,0.00010115939,3.359765e-7,0.04102919,0.0015990157],"genre_scores_gemma":[0.29966322,1.3351392e-7,0.6998785,0.00016655592,0.00003638491,0.00003660176,0.0000018741403,0.000005377157,0.00021130352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994656,0.000009189621,0.000093312134,0.00017678319,0.00008514528,0.00016998811],"domain_scores_gemma":[0.9986502,0.0010222927,0.000030619623,0.00018995223,0.00007987976,0.000027063963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003754587,0.000050374972,0.000050925064,0.000098439756,0.00011819517,0.000093902236,0.00025053005,0.000021670847,7.018948e-7],"category_scores_gemma":[0.00148189,0.000046138306,0.000021066746,0.0006065521,0.0000070790816,0.00015736853,0.000085297,0.000029295796,0.000040993644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011704913,0.000013973648,0.0043983073,0.000039568204,0.0000054117686,0.000017880617,0.00047859043,0.00028921026,0.0012421492,0.032173626,0.07567049,0.88566965],"study_design_scores_gemma":[0.00008690591,0.000060704573,0.0023216165,0.00002749325,0.0000014372544,0.000014994591,0.0000048425845,0.7505776,0.0026692643,0.2435688,0.00055505586,0.00011128101],"about_ca_topic_score_codex":0.000026481663,"about_ca_topic_score_gemma":7.011059e-7,"teacher_disagreement_score":0.88555837,"about_ca_system_score_codex":0.000011749773,"about_ca_system_score_gemma":0.00002263584,"threshold_uncertainty_score":0.18814655},"labels":[],"label_agreement":null},{"id":"W4388848588","doi":"10.1145/3631972","title":"Improving Automated Program Repair with Domain Adaptation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Adaptation (eye); Software engineering; Domain (mathematical analysis)","score_opus":0.07110201268549876,"score_gpt":0.31706774702128526,"score_spread":0.2459657343357865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388848588","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006462396,0.000030180025,0.8142383,0.00010960389,0.00018320188,0.00017015202,0.0000019430813,0.17880225,0.000001948538],"genre_scores_gemma":[0.022467613,0.000013219212,0.9771716,0.000055565186,0.00001652538,0.00020702778,0.0000040405835,0.000027899123,0.000036502784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880886,0.0001369851,0.00017622835,0.0004206297,0.00013518197,0.00032212248],"domain_scores_gemma":[0.9972019,0.0020298804,0.000048573416,0.0005716604,0.000058543526,0.00008945129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008231703,0.00018006617,0.00020482416,0.00036563195,0.00016130877,0.000049558606,0.00028371927,0.000118559474,9.809571e-7],"category_scores_gemma":[0.0010055475,0.00016138174,0.000053858137,0.0008254279,0.000037680602,0.00015930022,0.00002145214,0.00023758918,0.0000061551286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003875078,0.00008893695,0.00045895643,0.00016740798,0.000109135646,0.000094298615,0.0018759413,0.06487897,0.00027080788,0.0005948008,0.00046998216,0.930952],"study_design_scores_gemma":[0.00032554823,0.0006509062,0.0026814546,0.00008047886,0.00002252906,0.00018180997,0.000029832896,0.9925557,0.0004087041,0.002198415,0.0005607963,0.00030382242],"about_ca_topic_score_codex":0.00007030285,"about_ca_topic_score_gemma":0.0000035098903,"teacher_disagreement_score":0.9306482,"about_ca_system_score_codex":0.000028306196,"about_ca_system_score_gemma":0.00004121796,"threshold_uncertainty_score":0.65809566},"labels":[],"label_agreement":null},{"id":"W4388917353","doi":"10.1007/978-981-99-8311-7_15","title":"TorchProbe: Fuzzing Dynamic Deep Learning Compilers","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Compiler; Deep learning; Programming language; Artificial intelligence","score_opus":0.019919948858547153,"score_gpt":0.260890147370234,"score_spread":0.24097019851168688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388917353","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034527013,0.0003230989,0.9836413,0.00039351295,0.0018704449,0.00030017027,0.0000014216192,0.011465756,0.0019697594],"genre_scores_gemma":[0.13594726,0.000092874216,0.8614934,0.0008519901,0.0003379134,0.000021869417,0.000011903905,0.000121163386,0.0011216266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953944,0.000060674643,0.0005775829,0.0018777555,0.0011336163,0.0009559895],"domain_scores_gemma":[0.99621534,0.0015219789,0.000352359,0.0014560875,0.00025001515,0.00020424523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014860865,0.00063618977,0.0006157409,0.0013105955,0.00052351726,0.00077409414,0.0040060575,0.00038906108,0.000007966067],"category_scores_gemma":[0.00054516847,0.00063116377,0.00017118771,0.0011263039,0.00062088866,0.00047930877,0.002239758,0.0016389241,0.00014052694],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021813046,0.000011536782,0.00020342768,0.000047563753,0.000009877727,0.00015828254,0.00070953486,0.04015623,0.000036481182,0.0045851665,0.00006352609,0.9540162],"study_design_scores_gemma":[0.000101499405,0.00012933176,0.0001898878,0.0005948493,0.000005233941,0.00007002943,7.878983e-8,0.66602206,0.000067284804,0.33178934,0.0004098929,0.00062051625],"about_ca_topic_score_codex":0.000042201485,"about_ca_topic_score_gemma":0.00005332157,"teacher_disagreement_score":0.95339566,"about_ca_system_score_codex":0.00045890952,"about_ca_system_score_gemma":0.00034508813,"threshold_uncertainty_score":0.99961394},"labels":[],"label_agreement":null},{"id":"W4389158953","doi":"10.1145/3611643.3616272","title":"Statfier: Automated Testing of Static Analyzers via Semantic-Preserving Program Transformations","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Huawei Technologies; National Natural Science Foundation of China","keywords":"Computer science; Static analysis; Heuristics; Key (lock); Test suite; Spectrum analyzer; Spurious relationship; Selection (genetic algorithm); Program analysis; Documentation; Static program analysis; Programming language; Data mining; Test case; Software; Artificial intelligence; Machine learning","score_opus":0.040952538539588405,"score_gpt":0.32100017087266985,"score_spread":0.28004763233308144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389158953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048577428,0.00000858023,0.838717,0.00042022896,0.0000617063,0.00033433386,0.0000031716725,0.11019648,0.0016811113],"genre_scores_gemma":[0.50661665,0.0000014419887,0.49326837,0.000030367859,0.000004053531,0.00003313654,0.0000058173014,0.000007949247,0.000032237516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987398,0.000053130592,0.00037372703,0.00021865619,0.0002891317,0.0003255657],"domain_scores_gemma":[0.9984624,0.000703829,0.00010605687,0.00046682628,0.00018790102,0.00007300181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005183482,0.00011867616,0.00017337067,0.00034012267,0.00013437793,0.00010576287,0.0006462782,0.000038978185,0.000007826058],"category_scores_gemma":[0.0005581069,0.000106107465,0.00004932483,0.002682372,0.000038920945,0.0004293505,0.00015086669,0.00008775122,0.00002371425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005550812,0.0003966325,0.04523105,0.0009093596,0.00014402068,0.00006956015,0.0069128354,0.010927346,0.003119498,0.0032671504,0.09775286,0.83126414],"study_design_scores_gemma":[0.00009159791,0.00010827836,0.0055695735,0.00008450188,0.0000081065755,0.00000849431,0.000019471889,0.97920483,0.0013985048,0.013321405,0.00005824275,0.00012695992],"about_ca_topic_score_codex":0.00036481628,"about_ca_topic_score_gemma":0.000014245365,"teacher_disagreement_score":0.9682775,"about_ca_system_score_codex":0.000018372019,"about_ca_system_score_gemma":0.00007020274,"threshold_uncertainty_score":0.43269366},"labels":[],"label_agreement":null},{"id":"W4389159649","doi":"10.1145/3611643.3616292","title":"Code Coverage Criteria for Asynchronous Programs","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Asynchronous communication; JavaScript; Test suite; Asynchrony (computer programming); Software engineering; Metric (unit); Code (set theory); Software quality; Code coverage; Plug-in; Test case; Programming language; Test (biology); Software; Machine learning; Software development","score_opus":0.05903462948133558,"score_gpt":0.3321103564791753,"score_spread":0.2730757269978397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389159649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026806865,0.0000097476,0.94976383,0.0006584346,0.00023685516,0.00025954095,0.0000027116907,0.044815686,0.0015724871],"genre_scores_gemma":[0.41174605,0.000003387624,0.5866724,0.00042951308,0.000068134024,0.00018927742,0.000013448234,0.000013424967,0.00086432113],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99922264,0.000015677624,0.00011554788,0.0002670435,0.00011005582,0.00026904166],"domain_scores_gemma":[0.99923164,0.00023057338,0.000027903367,0.00039896162,0.00005916615,0.000051764273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032374382,0.00008485117,0.00009582462,0.00007107987,0.00010067789,0.00020570138,0.0004972158,0.00003917325,0.00000613164],"category_scores_gemma":[0.0001692925,0.000073854295,0.00004817527,0.00035254718,0.0000185507,0.00014919783,0.00016388518,0.000038027734,0.000082394195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041323583,0.00006516509,0.0020827472,0.000047323305,0.00001056497,0.000020976047,0.0003222142,0.000009377452,0.00018027611,0.027593309,0.38266188,0.58700204],"study_design_scores_gemma":[0.0004692838,0.00061817374,0.0024622574,0.000069254806,0.0000057859024,0.000037631897,0.000004451448,0.4327417,0.0025457959,0.508799,0.05176357,0.00048304824],"about_ca_topic_score_codex":0.00002520875,"about_ca_topic_score_gemma":0.00000337971,"teacher_disagreement_score":0.586519,"about_ca_system_score_codex":0.0000183117,"about_ca_system_score_gemma":0.000033847344,"threshold_uncertainty_score":0.30116907},"labels":[],"label_agreement":null},{"id":"W4389161815","doi":"10.1145/3611643.3613872","title":"Prioritizing Natural Language Test Cases Based on Highly-Used Game Features","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test case; Test (biology); Code coverage; Machine learning; Test suite; Test Management Approach; Natural language; System under test; Artificial intelligence; Data mining; Software; Programming language; Software system","score_opus":0.01845999358637851,"score_gpt":0.28596608037730753,"score_spread":0.267506086790929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389161815","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42761445,0.0008784602,0.089363515,0.016004128,0.0030390131,0.0012249125,0.000037896727,0.4475589,0.014278716],"genre_scores_gemma":[0.9363222,0.0000013259689,0.061033506,0.0013059728,0.00008725492,0.000015959402,0.000008677414,0.000016012467,0.0012090855],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987865,0.000040134215,0.0001308049,0.00038498495,0.00032105306,0.000336541],"domain_scores_gemma":[0.99661267,0.002597848,0.000043011925,0.00062926253,0.0000453442,0.00007186088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025482484,0.0001623053,0.00014233394,0.00025804163,0.000114204486,0.0002201111,0.0005919196,0.000060090046,0.000004137234],"category_scores_gemma":[0.0016062164,0.00013083928,0.000065773784,0.00078925875,0.000029324861,0.00014555821,0.00015272188,0.00020190867,0.000111354304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028343502,0.00037433495,0.025426831,0.00015468715,0.000027701364,0.0066767917,0.003260696,0.00020217242,0.016114037,0.010664456,0.73512685,0.20194307],"study_design_scores_gemma":[0.0015992412,0.0013008495,0.1313211,0.00079115113,0.000022498843,0.00048760197,0.00010615916,0.79609984,0.053282022,0.0086222105,0.0043623615,0.002004932],"about_ca_topic_score_codex":0.0002002539,"about_ca_topic_score_gemma":0.000019259258,"teacher_disagreement_score":0.7958977,"about_ca_system_score_codex":0.000038042333,"about_ca_system_score_gemma":0.000049090166,"threshold_uncertainty_score":0.5335471},"labels":[],"label_agreement":null},{"id":"W4389162832","doi":"10.1145/3611643.3613101","title":"Ad Hoc Syntax-Guided Program Reduction","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Abstract syntax tree; Debugging; Interpreter; Compiler; Grammar; Reduction (mathematics); Syntax; Parsing; Context (archaeology); Natural language processing; Linguistics","score_opus":0.05371215305656096,"score_gpt":0.33135786602655554,"score_spread":0.2776457129699946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389162832","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05748154,0.00013330545,0.43168357,0.005789933,0.001312966,0.0006871895,7.203299e-7,0.49143678,0.011473982],"genre_scores_gemma":[0.22049,0.000025698533,0.776431,0.00012661652,0.00006175147,0.00012070304,0.0000035935639,0.000011412028,0.0027292098],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991961,0.000024489518,0.0001217116,0.00027333325,0.00016919638,0.00021514266],"domain_scores_gemma":[0.99933314,0.00006381793,0.000032908403,0.00046085258,0.000056978246,0.00005227271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028414265,0.000077737066,0.00007411654,0.00013193254,0.00009165552,0.00012644139,0.0004195471,0.000041484043,0.0000068591976],"category_scores_gemma":[0.00016118902,0.00006721468,0.00003682908,0.0008804529,0.00002347165,0.00019106033,0.00017369271,0.00006797748,0.00027647676],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.2191174e-7,0.000027756358,0.00015472966,0.0000063292573,0.0000034169245,0.000010080699,0.0001414263,0.000005720614,0.00015318881,0.0024764123,0.3614911,0.6355292],"study_design_scores_gemma":[0.0005703957,0.001139315,0.011166067,0.00023207554,0.000017612647,0.0007394069,0.000050391114,0.34415203,0.02303615,0.48779967,0.12974747,0.001349412],"about_ca_topic_score_codex":0.000024667275,"about_ca_topic_score_gemma":7.669629e-7,"teacher_disagreement_score":0.6341798,"about_ca_system_score_codex":0.000021600781,"about_ca_system_score_gemma":0.000028074108,"threshold_uncertainty_score":0.35536417},"labels":[],"label_agreement":null},{"id":"W4389165112","doi":"10.1145/3611643.3616275","title":"PPR: Pairwise Program Reduction","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Compiler; Debugging; Benchmark (surveying); Reduction (mathematics); Pairwise comparison; Programming language; Software bug; Parallel computing; Software; Mathematics; Artificial intelligence","score_opus":0.03433554962418357,"score_gpt":0.30685562694519075,"score_spread":0.2725200773210072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389165112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022553641,0.000025396219,0.5018205,0.0028786976,0.0007473136,0.00036713394,2.9255474e-7,0.46003848,0.011568521],"genre_scores_gemma":[0.36864775,0.0000059426984,0.62898344,0.00009199113,0.00007278988,0.000088724235,0.0000024011374,0.000007474334,0.0020994698],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994139,0.000012559121,0.00008017962,0.00020213328,0.00012516865,0.00016604032],"domain_scores_gemma":[0.9994949,0.00004764873,0.000019805399,0.00036059765,0.000036208134,0.000040835992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023653357,0.00005524754,0.00004991948,0.00009909107,0.00006968923,0.00008200107,0.0003157989,0.000029003484,0.0000051737857],"category_scores_gemma":[0.00009531527,0.00004677113,0.000028091294,0.0007507967,0.000017671526,0.00015013166,0.00013054992,0.00005083673,0.00025243906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9529056e-7,0.000026978338,0.00046836864,0.0000041921458,0.0000019277747,0.000007032853,0.00011037873,0.00000581409,0.000060258284,0.0081025865,0.34640428,0.64480776],"study_design_scores_gemma":[0.00023725706,0.00050164456,0.00821936,0.00006348409,0.000005358324,0.0001543284,0.000017099352,0.32761055,0.006650901,0.60926515,0.046718795,0.00055607775],"about_ca_topic_score_codex":0.00003248324,"about_ca_topic_score_gemma":3.8539218e-7,"teacher_disagreement_score":0.6442517,"about_ca_system_score_codex":0.0000121139,"about_ca_system_score_gemma":0.000019023157,"threshold_uncertainty_score":0.32446775},"labels":[],"label_agreement":null},{"id":"W4389205823","doi":"10.22215/etd/2023-15772","title":"Hy2: A Hybrid Vulnerability Analysis Method","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Vulnerability (computing); Emulation; Vulnerability assessment; Computer science; Abstraction; Static analysis; Software; Computer security; Programming language","score_opus":0.03027486160120678,"score_gpt":0.36178810521173965,"score_spread":0.33151324361053286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389205823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014785074,0.000042316064,0.9508316,0.00007944337,0.0005260661,0.00015053329,0.000005324284,0.040782385,0.006103845],"genre_scores_gemma":[0.023382077,0.000008384775,0.95165753,0.00014887853,0.00006288979,0.00011127905,0.00038851882,0.00003565081,0.024204772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977632,0.0001953122,0.0003893572,0.00091655925,0.00043848532,0.00029709685],"domain_scores_gemma":[0.99714464,0.0008822377,0.00019788758,0.0014556965,0.00022464876,0.000094873496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013134112,0.00028153387,0.00053560454,0.00077529193,0.00013997883,0.00024278213,0.0012834835,0.0001566022,0.000044576],"category_scores_gemma":[0.0010082126,0.00025180445,0.000413264,0.002456314,0.000011045623,0.00013015713,0.00013696335,0.0003416386,0.000113355854],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021853659,0.00023869412,0.004620385,0.00037127294,0.0021986028,0.0002605946,0.0022308384,0.00045535932,0.00004058074,0.008379982,0.2744209,0.70676094],"study_design_scores_gemma":[0.00015642517,0.000121715595,0.027222948,0.000119853044,0.0010735183,0.00001971136,0.00004055566,0.568291,0.0047084456,0.39572203,0.0010213841,0.0015024304],"about_ca_topic_score_codex":0.0013343376,"about_ca_topic_score_gemma":0.00027405377,"teacher_disagreement_score":0.70525855,"about_ca_system_score_codex":0.000060146413,"about_ca_system_score_gemma":0.00012891799,"threshold_uncertainty_score":0.99999344},"labels":[],"label_agreement":null},{"id":"W4389209036","doi":"10.1145/3611643.3616332","title":"A Generative and Mutational Approach for Synthesizing Bug-Exposing Test Cases to Guide Compiler Fuzzing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China; China Postdoctoral Science Foundation; Tencent","keywords":"Fuzz testing; Computer science; Compiler; Programming language; Compiler correctness; Interprocedural optimization; Optimizing compiler; Code coverage; Compiler construction; Software bug; Toolchain; Test case; Key (lock); Software engineering; Operating system; Loop optimization; Software; Machine learning","score_opus":0.06749669479941017,"score_gpt":0.32009621749096473,"score_spread":0.25259952269155456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389209036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00809,0.000026268672,0.9831663,0.00068573485,0.000047468056,0.00027544794,0.00000674673,0.0067573665,0.00094471296],"genre_scores_gemma":[0.23167615,8.535658e-7,0.7673804,0.0005946787,0.00006158763,0.00011111849,0.000007129775,0.000010747903,0.00015731381],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901164,0.000021795555,0.00018105483,0.0003916287,0.00014964277,0.0002442431],"domain_scores_gemma":[0.99676895,0.0027920804,0.00004129093,0.00020278103,0.000111844034,0.00008304209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043519097,0.0001198369,0.00013261687,0.00017700279,0.00030400362,0.000251037,0.00024142856,0.000032708685,9.710718e-7],"category_scores_gemma":[0.001729883,0.00010767211,0.000030424893,0.00041006054,0.000026789745,0.00018394274,0.0002086495,0.000045967125,0.0000058913106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029597268,0.000366054,0.030711899,0.00033491937,0.00012013461,0.00023741552,0.012569864,0.008712387,0.024249857,0.079688,0.5266127,0.31636718],"study_design_scores_gemma":[0.00018347581,0.00020566411,0.0026325765,0.000095562216,0.000009086784,0.00019274621,0.000111091875,0.9717102,0.010338777,0.013316915,0.00081004895,0.0003938654],"about_ca_topic_score_codex":0.000063706524,"about_ca_topic_score_gemma":0.0000029603357,"teacher_disagreement_score":0.9629978,"about_ca_system_score_codex":0.000033661472,"about_ca_system_score_gemma":0.0000470376,"threshold_uncertainty_score":0.4390741},"labels":[],"label_agreement":null},{"id":"W4389230915","doi":"10.1109/iavvc57316.2023.10328120","title":"Structured Testing Framework for ADAS Algorithm Development","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; General Motors of Canada; University of Waterloo; U.S. Department of Energy","keywords":"Computer science; Integration testing; Test Management Approach; Test harness; Automation; Protocol (science); Software; Test strategy; Test (biology); White-box testing; Test case; Software engineering; Model-based testing; Development (topology); Software development; Embedded system; Algorithm; Programming language; Software construction; Machine learning; Engineering","score_opus":0.06897894952777034,"score_gpt":0.31434616436116264,"score_spread":0.2453672148333923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389230915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057022396,0.000010490091,0.9659859,0.00023717123,0.00026268332,0.00016042717,9.68411e-7,0.032529056,0.00024306895],"genre_scores_gemma":[0.010817527,3.3815382e-7,0.9884563,0.00031921876,0.000074125935,0.000075016615,0.0000037181546,0.000012484336,0.00024128745],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999021,0.000011943119,0.00016852628,0.00031291266,0.00017781829,0.00030783386],"domain_scores_gemma":[0.99820036,0.0012299796,0.00004952368,0.00034787031,0.000109028806,0.00006322535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033146093,0.00011062148,0.00010625307,0.000116806754,0.0002055924,0.00012706312,0.00056729955,0.000068565925,0.0000032038222],"category_scores_gemma":[0.0013646106,0.00009563004,0.00002780829,0.0007928437,0.00001333488,0.00010159805,0.00023230314,0.00008741483,0.000034059456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.8317515e-7,0.0000057382094,0.00069823896,0.000009865185,0.0000057686298,0.0000053318063,0.0002465374,0.000014089185,0.000018811877,0.012188267,0.01597576,0.9708312],"study_design_scores_gemma":[0.00009289195,0.000052094347,0.0049214335,0.000073905656,0.0000018838467,0.000013795816,0.000005639163,0.24597572,0.003805692,0.73998415,0.004813471,0.00025929447],"about_ca_topic_score_codex":0.000011887401,"about_ca_topic_score_gemma":8.610663e-7,"teacher_disagreement_score":0.97057194,"about_ca_system_score_codex":0.0000278771,"about_ca_system_score_gemma":0.000098000906,"threshold_uncertainty_score":0.38996798},"labels":[],"label_agreement":null},{"id":"W4389363106","doi":"10.48550/arxiv.2312.00938","title":"WATonoBus: Field-Tested All-Weather Autonomous Shuttle Technology","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adverse weather; Upstream (networking); Computer science; Modular design; Extreme weather; Architecture; Snow; Enhanced Data Rates for GSM Evolution; Control (management); Perception; Artificial intelligence; Meteorology; Climate change; Geography; Telecommunications","score_opus":0.10394377979326326,"score_gpt":0.21687567386380482,"score_spread":0.11293189407054156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389363106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048166778,0.000073899784,0.90378696,0.0015820649,0.0008315552,0.00034235942,0.000008151076,0.043737914,0.0014702972],"genre_scores_gemma":[0.9633236,0.000071215625,0.03260283,0.0003313412,0.00006397426,0.000006012634,0.000012844193,0.00004841406,0.0035397904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771076,0.00008063429,0.00024391328,0.0013575809,0.00009422779,0.00051288545],"domain_scores_gemma":[0.9968963,0.00040858405,0.00023202717,0.0021697963,0.00016428834,0.00012899392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028741575,0.00037812808,0.00040464482,0.0007420699,0.00014153348,0.0001364014,0.0029870193,0.0006973349,0.00002090993],"category_scores_gemma":[0.00030789795,0.00042982964,0.00019705245,0.001116702,0.000106402054,0.00017694003,0.0036519172,0.0008487653,0.00033677107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000758964,0.00089116883,0.09899575,0.00055691996,0.0013088086,0.009299785,0.0019550116,0.079819866,0.0002129982,0.6001076,0.17003661,0.03673958],"study_design_scores_gemma":[0.00027746186,0.00015262968,0.0004657618,0.0002225673,0.000075327545,0.000028673641,0.00001808428,0.33598685,0.00072944077,0.6584569,0.0027743308,0.0008119148],"about_ca_topic_score_codex":0.00038716794,"about_ca_topic_score_gemma":0.00002919581,"teacher_disagreement_score":0.9151568,"about_ca_system_score_codex":0.00020413414,"about_ca_system_score_gemma":0.00022221307,"threshold_uncertainty_score":0.99981534},"labels":[],"label_agreement":null},{"id":"W4389817810","doi":"10.1007/978-1-4842-9843-5_15","title":"Automated Testing with Unity","year":2023,"lang":"en","type":"book-chapter","venue":"Apress eBooks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Manitoba Beekeepers' Association","funders":"","keywords":"Computer science","score_opus":0.07365327430997477,"score_gpt":0.25951624547731744,"score_spread":0.18586297116734268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389817810","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017337863,0.000024687817,0.031155635,0.000033207543,0.0001956217,0.00026016135,0.000009129505,0.14960861,0.8186956],"genre_scores_gemma":[0.004368435,0.0000019876538,0.2850198,0.00031994173,0.00017286799,0.00006461049,0.000014647385,0.00020771484,0.70983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835676,0.0000238384,0.0002619365,0.00061080314,0.0004091145,0.00033752283],"domain_scores_gemma":[0.9973875,0.0008197933,0.0002468715,0.0011967611,0.00023522199,0.00011380864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002518328,0.00038222352,0.0003413116,0.00021808213,0.00019625494,0.00020836595,0.0011704664,0.00025402653,0.000002293301],"category_scores_gemma":[0.00019625685,0.00032976514,0.000058817357,0.000054172102,0.00012243555,0.000070105896,0.00060888706,0.00047719473,0.000099874174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017040886,0.000027438642,0.00022560717,0.00037101618,0.00026885507,0.0014413142,0.0007502374,0.00007869264,0.00007490748,0.6526341,0.10667049,0.23744033],"study_design_scores_gemma":[0.00050172256,0.0006152728,0.00028681397,0.0045549404,0.00012259818,0.00038534016,0.0000013173556,0.06499474,0.00066873885,0.8801454,0.045317173,0.0024059934],"about_ca_topic_score_codex":0.00015965107,"about_ca_topic_score_gemma":0.000010242825,"teacher_disagreement_score":0.25386414,"about_ca_system_score_codex":0.000041134695,"about_ca_system_score_gemma":0.00016522787,"threshold_uncertainty_score":0.9999154},"labels":[],"label_agreement":null},{"id":"W4390091644","doi":"10.48550/arxiv.2312.12604","title":"An empirical study of testing machine learning in the wild","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Oracle; Software reliability testing; White-box testing; Regression testing; Software construction; Software engineering; Test strategy; System integration testing; Software system; Workflow; Software quality assurance; Software quality; Empirical research; Artificial intelligence; Machine learning; Software; Software development; Database; Programming language","score_opus":0.21095865101335456,"score_gpt":0.2677698645024746,"score_spread":0.05681121348912002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390091644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8276145,0.000010642759,0.16763727,0.000060903887,0.00009873674,0.00028186286,0.0000014570581,0.004118913,0.00017574828],"genre_scores_gemma":[0.9935074,0.000004335327,0.0063267895,0.000048270034,0.000026244034,0.0000019266477,0.0000037260356,0.000015720465,0.00006562707],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803215,0.0005777553,0.00022647592,0.0007830656,0.00013963929,0.00024089128],"domain_scores_gemma":[0.99726444,0.0011408341,0.00023504047,0.0012019526,0.00010469562,0.00005300498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011383567,0.00020690323,0.000276993,0.00035412092,0.00013885355,0.00008729545,0.002507863,0.00013121233,0.0000010127899],"category_scores_gemma":[0.000623495,0.00018569361,0.00006252708,0.0014294161,0.000053718944,0.00015361664,0.001419032,0.00096514367,0.0000064159462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005674866,0.00035242425,0.8607209,0.000024122053,0.00001360279,0.0003844552,0.0024202953,0.13442804,0.000002504784,0.00037832832,0.00015571005,0.0011139618],"study_design_scores_gemma":[0.00021860236,0.0004919872,0.09181459,0.000107714804,0.000021314101,0.000005270176,0.00021053731,0.8745031,0.0000030268393,0.03239835,0.000008294884,0.00021723207],"about_ca_topic_score_codex":0.0026089717,"about_ca_topic_score_gemma":0.00020983441,"teacher_disagreement_score":0.7689063,"about_ca_system_score_codex":0.000059747454,"about_ca_system_score_gemma":0.00009812069,"threshold_uncertainty_score":0.7572366},"labels":[],"label_agreement":null},{"id":"W4390189471","doi":"10.1109/milcom58377.2023.10356308","title":"Input Output Grammar Coverage in Fuzzing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Fuzz testing; Computer science; Grammar; Code coverage; Code (set theory); Natural language processing; Data mining; Artificial intelligence; Programming language; Set (abstract data type); Software","score_opus":0.032718849871889805,"score_gpt":0.2711694917751658,"score_spread":0.238450641903276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390189471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043459788,0.000025553592,0.8934067,0.0013794362,0.00030739576,0.00012505415,4.993617e-7,0.04848526,0.012810318],"genre_scores_gemma":[0.90721804,0.000009849399,0.09100101,0.0006324547,0.000027351385,0.000015185161,0.000001616653,0.000008207704,0.0010862785],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991477,0.000031222946,0.00014272152,0.00025731005,0.00015915978,0.00026188092],"domain_scores_gemma":[0.99924195,0.00026782326,0.000025240544,0.0003997414,0.000021484417,0.000043738797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044135196,0.00008164922,0.00009814628,0.00024868638,0.000048493195,0.00010817702,0.0005221817,0.00004200623,0.000003182048],"category_scores_gemma":[0.00028369526,0.0000746621,0.000028896278,0.0009714368,0.000013056969,0.00019968998,0.00031972793,0.000104103325,0.00021069136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002991767,0.00006452727,0.10287778,0.000031061692,0.0000070519573,0.00038087857,0.0013031051,0.0003630875,0.00013209108,0.047717538,0.21889274,0.6282272],"study_design_scores_gemma":[0.00048067025,0.00011756638,0.08264044,0.00012790506,0.0000019133604,0.000037121124,0.00001081258,0.26205316,0.0011995139,0.63942814,0.013301293,0.000601438],"about_ca_topic_score_codex":0.000204719,"about_ca_topic_score_gemma":0.000014077373,"teacher_disagreement_score":0.86375827,"about_ca_system_score_codex":0.00002837101,"about_ca_system_score_gemma":0.000029804323,"threshold_uncertainty_score":0.3044632},"labels":[],"label_agreement":null},{"id":"W4390679819","doi":"10.1109/dsc59305.2023.00078","title":"FixGPT: A Novel Three-Tier Deep Learning Model for Automated Program Repair","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Identifier; Artificial intelligence; Machine learning; Deep learning; Benchmarking; Transformer; Data mining; Programming language","score_opus":0.053623571966626885,"score_gpt":0.3244303272742805,"score_spread":0.27080675530765363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390679819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060196634,0.000007906458,0.6065494,0.0001589472,0.000052920976,0.00028285437,5.7043934e-7,0.3920314,0.0003140815],"genre_scores_gemma":[0.0433546,0.0000012188804,0.95469415,0.00014344629,0.00002684219,0.00040235865,0.000008416321,0.000023905139,0.0013450463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871427,0.000021107862,0.00020344899,0.00044087777,0.0002020511,0.00041823403],"domain_scores_gemma":[0.99895287,0.0003065999,0.000062562496,0.00046854667,0.00013331081,0.00007610406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007905386,0.00014484154,0.00015084753,0.00015398694,0.00021681307,0.00014660985,0.0005294471,0.00008634959,0.0000016770143],"category_scores_gemma":[0.00056341296,0.00012636524,0.000118876684,0.00072132156,0.00002745099,0.0002068093,0.00028728502,0.00012285763,0.000033853194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010260494,0.00036401523,0.008887991,0.0001529151,0.000077649485,0.000020747806,0.0015926284,0.08057761,0.00013074865,0.01329963,0.30318418,0.5917016],"study_design_scores_gemma":[0.00017218861,0.00014097613,0.0008970666,0.000025465593,0.0000044390154,0.000007694133,0.00000211346,0.98068213,0.000026942638,0.017273504,0.00058252073,0.00018492584],"about_ca_topic_score_codex":0.000042257972,"about_ca_topic_score_gemma":0.000011704918,"teacher_disagreement_score":0.9001045,"about_ca_system_score_codex":0.000027632628,"about_ca_system_score_gemma":0.000052689236,"threshold_uncertainty_score":0.5153025},"labels":[],"label_agreement":null},{"id":"W4390824862","doi":"10.23977/jeis.2023.080615","title":"Research on the requirement decomposition and test verification for vehicle data security","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Automotive industry; Test data; Decomposition; Data mining; Software engineering; Engineering","score_opus":0.11930741518378968,"score_gpt":0.41757559014321943,"score_spread":0.29826817495942975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390824862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7523563,0.00026883732,0.21275346,0.032831088,0.00022597495,0.00054752245,0.000011286717,0.0004837304,0.00052180624],"genre_scores_gemma":[0.99558204,0.00031193002,0.0038593851,0.00021997593,0.000018369012,0.000003962139,0.0000019212387,9.861075e-7,0.0000014357435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907476,0.000024237397,0.00020013831,0.000086894164,0.00044734782,0.0001666282],"domain_scores_gemma":[0.99817795,0.00089975895,0.00015309712,0.00028393618,0.00044415763,0.000041133866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008017391,0.000034381643,0.00004520659,0.000266627,0.00047325346,0.0004416602,0.00070303,0.000015210724,2.0645484e-7],"category_scores_gemma":[0.0016436903,0.000022822516,0.000007577618,0.00085061626,0.00010352285,0.0034522377,0.00018963765,0.0001342494,0.0000016911569],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038148704,0.00006642543,0.001002505,0.000047035817,0.0000068853396,6.769681e-7,0.003207104,0.00009810729,0.0062015266,0.74708927,0.039163984,0.20307834],"study_design_scores_gemma":[0.00022738974,0.0010789856,0.010043562,0.00006964176,0.0000028562945,0.000037037502,0.00009257325,0.82113993,0.0051472234,0.14875777,0.013317975,0.000085058],"about_ca_topic_score_codex":0.0000019831161,"about_ca_topic_score_gemma":3.034413e-7,"teacher_disagreement_score":0.8210418,"about_ca_system_score_codex":0.000051829353,"about_ca_system_score_gemma":0.00020256174,"threshold_uncertainty_score":0.42589393},"labels":[],"label_agreement":null},{"id":"W4391211964","doi":"10.48550/arxiv.2401.12364","title":"Guiding the Search Towards Failure-Inducing Test Inputs Using Support Vector Machines","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Support vector machine; Sorting; Computer science; Machine learning; Artificial intelligence; Structured support vector machine; Genetic algorithm; Data mining; Pattern recognition (psychology); Algorithm","score_opus":0.15501503968045655,"score_gpt":0.24686351685003938,"score_spread":0.09184847716958283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391211964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.280432,0.00015956271,0.7007833,0.0015427376,0.0017226491,0.000524313,0.000031168103,0.013029084,0.0017751905],"genre_scores_gemma":[0.9729615,0.000022558324,0.025984375,0.00018484081,0.0002545605,0.0000015411296,0.00000681828,0.00004622794,0.0005376208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737513,0.00017751692,0.00028119658,0.0013710164,0.00023308488,0.0005620526],"domain_scores_gemma":[0.9971131,0.0005594051,0.00017151263,0.0017597754,0.00023636202,0.00015986265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010234725,0.00044616548,0.00036868552,0.0004497664,0.0004241765,0.0006349696,0.002981254,0.00030425892,0.000018107667],"category_scores_gemma":[0.0004239916,0.00038811797,0.00026337156,0.001181239,0.00014417243,0.0002437321,0.0073591406,0.0010891509,0.00006872444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008481343,0.0010463257,0.112274,0.0043389,0.0018508112,0.018470068,0.019800993,0.40309548,0.006375053,0.25584722,0.10963976,0.06717659],"study_design_scores_gemma":[0.000107143154,0.000066915425,0.00059075595,0.0005801583,0.00010206869,0.00009766413,0.000017571647,0.91056514,0.0011758382,0.08572709,0.00034560627,0.0006240814],"about_ca_topic_score_codex":0.0013308838,"about_ca_topic_score_gemma":0.000032824537,"teacher_disagreement_score":0.69252944,"about_ca_system_score_codex":0.0004120403,"about_ca_system_score_gemma":0.0007604627,"threshold_uncertainty_score":0.99985707},"labels":[],"label_agreement":null},{"id":"W4391462747","doi":"10.1109/ms.2024.3418570","title":"Generative AI to Generate Test Data Generators","year":2024,"lang":"en","type":"preprint","venue":"IEEE Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Generative grammar; Test (biology); Computer science; Artificial intelligence; Test data; Natural language processing; Programming language","score_opus":0.06607790163968237,"score_gpt":0.3343913292862057,"score_spread":0.26831342764652333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391462747","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003939874,0.0017903505,0.94463503,0.003761155,0.006668181,0.0007034603,0.0010690694,0.03734825,0.00008464838],"genre_scores_gemma":[0.034721237,0.00004938627,0.95399636,0.007593847,0.0021719695,0.0003042894,0.00032130466,0.00015861701,0.00068296504],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99479246,0.00014984197,0.00065267255,0.002923238,0.00073489686,0.0007469062],"domain_scores_gemma":[0.9919965,0.00053670513,0.00019424691,0.006402212,0.00044336333,0.00042694793],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007905639,0.00082074787,0.0006746313,0.0005151604,0.00043084976,0.0014605294,0.006891445,0.0005193544,0.000013358365],"category_scores_gemma":[0.0017022786,0.00078135496,0.00017273548,0.00089889584,0.00007543144,0.00027660085,0.020898715,0.0015919022,0.0005279829],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019490933,0.00007171521,0.00081444613,0.0001882346,0.00008398412,0.00027727152,0.0008101612,0.002214569,0.00016806272,0.00026262287,0.9587247,0.036382314],"study_design_scores_gemma":[0.0003844529,0.00051529426,0.00028158663,0.002819311,0.00027679646,0.00024740142,0.0000057699785,0.3753757,0.0319814,0.5258946,0.056712735,0.0055050133],"about_ca_topic_score_codex":0.000236557,"about_ca_topic_score_gemma":0.000041257197,"teacher_disagreement_score":0.90201193,"about_ca_system_score_codex":0.000230325,"about_ca_system_score_gemma":0.0010701396,"threshold_uncertainty_score":0.99957603},"labels":[],"label_agreement":null},{"id":"W4391614764","doi":"10.1145/3644388","title":"DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Black box; Artificial neural network; Artificial intelligence; Deep neural networks; Machine learning; Test (biology)","score_opus":0.0672593941211773,"score_gpt":0.31481957568626506,"score_spread":0.24756018156508774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391614764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002063585,0.00059376843,0.9861279,0.00008165612,0.0006214374,0.00030228554,0.0000064511496,0.012057963,0.0000021509095],"genre_scores_gemma":[0.15537937,0.000029208319,0.8440926,0.000089898014,0.00008365029,0.000236933,0.0000046523796,0.00004022201,0.00004348699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998518,0.00012562031,0.00022193171,0.0006458594,0.00009242849,0.00039615345],"domain_scores_gemma":[0.99214107,0.0072510005,0.000032398835,0.00038974578,0.00007945255,0.00010632608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007457686,0.00026317753,0.0002825395,0.0003564174,0.00018719949,0.00012645725,0.00035626293,0.00022444018,0.0000015643705],"category_scores_gemma":[0.002091928,0.00025675242,0.0001265354,0.00057944603,0.000053459025,0.00020522186,0.000021754127,0.0004898547,0.0000011573505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019349767,0.00011586762,0.00025423727,0.00019810328,0.000113356495,0.000008329506,0.0009808593,0.44980103,0.00015252084,0.00067480723,0.0001240089,0.54755753],"study_design_scores_gemma":[0.00020957178,0.00030967325,0.00025317277,0.00003457642,0.00004708979,0.00020090745,0.000008963939,0.9966417,0.00072517886,0.0010928365,0.00020896494,0.0002673716],"about_ca_topic_score_codex":0.000025518633,"about_ca_topic_score_gemma":0.0000027973,"teacher_disagreement_score":0.54729015,"about_ca_system_score_codex":0.0000643727,"about_ca_system_score_gemma":0.000026175549,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4391941017","doi":"10.1016/j.jnca.2024.103851","title":"Hardening of network segmentation using automated referential penetration testing","year":2024,"lang":"en","type":"article","venue":"Journal of Network and Computer Applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Penetration (warfare); Hardening (computing); Artificial intelligence; Computer vision; Composite material; Materials science; Operations research","score_opus":0.037988586729007415,"score_gpt":0.3028060182771774,"score_spread":0.26481743154817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391941017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009404648,0.0011324642,0.9876951,0.00005655291,0.00028722952,0.00011455323,5.054188e-7,0.0012641316,0.000044808472],"genre_scores_gemma":[0.36069167,0.000025111805,0.6384391,0.000033518023,0.0007945663,0.000004797148,0.0000016531543,0.0000066597386,0.0000029086373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989594,0.000052628835,0.00047311446,0.00016754183,0.00019980343,0.00014746706],"domain_scores_gemma":[0.99879944,0.00044658512,0.000311384,0.00015834844,0.00023023853,0.000054011227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005476423,0.00009702222,0.00016416957,0.00010227172,0.00016054383,0.00024023601,0.00025598344,0.00005188342,9.213782e-7],"category_scores_gemma":[0.00001212215,0.000088820525,0.000050944713,0.0006566995,0.000025244866,0.00028493218,0.00010356007,0.00016745726,6.213974e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012551017,0.00009197382,0.0086950995,0.00022470728,0.0001865505,0.000022079861,0.000721351,0.31275132,0.0016081675,0.022376899,0.03539506,0.6179142],"study_design_scores_gemma":[0.00007611193,0.00009868947,0.0024355403,0.00046011456,0.000034137338,0.00021406417,0.0000016968522,0.9728091,0.00004991514,0.02333357,0.0004004313,0.000086625514],"about_ca_topic_score_codex":0.000008169305,"about_ca_topic_score_gemma":7.811233e-7,"teacher_disagreement_score":0.6600578,"about_ca_system_score_codex":0.000028867473,"about_ca_system_score_gemma":0.000093499744,"threshold_uncertainty_score":0.36219957},"labels":[],"label_agreement":null},{"id":"W4391974543","doi":"10.1109/tse.2024.3368208","title":"Software Testing With Large Language Models: Survey, Landscape, and Vision","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":394,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Software engineering; Software","score_opus":0.017120406674413505,"score_gpt":0.2519216021540697,"score_spread":0.23480119547965622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391974543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009641844,0.0006335574,0.965713,0.000019242982,0.00037173167,0.0001313164,0.000041951713,0.023433784,0.000013526967],"genre_scores_gemma":[0.5931725,0.000010745647,0.40663287,0.000033833414,0.000026074465,0.00003106284,0.000003327154,0.000044931563,0.000044681503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856365,0.000035357447,0.0001922715,0.00055191707,0.0002780079,0.0003788106],"domain_scores_gemma":[0.9979014,0.0014236281,0.000025642867,0.0004460401,0.00007669147,0.00012659685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043079478,0.0002758799,0.00020431529,0.00033350475,0.00017399146,0.00035665702,0.00029405832,0.000100362035,0.0000046503014],"category_scores_gemma":[0.00013071214,0.0002414727,0.000047824036,0.0008946389,0.000019081139,0.0006385835,0.000010289656,0.00041292812,0.000010370413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049305752,0.00031618515,0.0046950006,0.0010785576,0.00022373944,0.0007250738,0.0040107854,0.47152072,0.0002554365,0.0005504697,0.0029715376,0.5136032],"study_design_scores_gemma":[0.00023358544,0.00025050392,0.0011536588,0.0008959645,0.000020881916,0.00016276269,0.000007736919,0.99570847,0.00069302507,0.0002500827,0.00014398812,0.00047933887],"about_ca_topic_score_codex":0.00007347211,"about_ca_topic_score_gemma":0.000018368864,"teacher_disagreement_score":0.5835306,"about_ca_system_score_codex":0.000043735563,"about_ca_system_score_gemma":0.000056271307,"threshold_uncertainty_score":0.9846971},"labels":[],"label_agreement":null},{"id":"W4391998081","doi":"10.1007/s10515-024-00417-0","title":"Using data mining techniques to generate test cases from graph transformation systems specifications","year":2024,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transformation (genetics); Graph; Data mining; Test (biology); Graph rewriting; Theoretical computer science; Geology; Chemistry","score_opus":0.10704843451474054,"score_gpt":0.30585336290967075,"score_spread":0.1988049283949302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391998081","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014106096,0.00084348605,0.86857,0.00007451457,0.0005942629,0.00026228547,0.0001676307,0.11537167,0.0000100369925],"genre_scores_gemma":[0.38176322,0.000014285611,0.6178668,0.000030141462,0.00012500053,0.000044198714,0.00011271385,0.000039038943,0.0000046200707],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998345,0.000028091099,0.0004178658,0.0006095934,0.00026088397,0.00033854207],"domain_scores_gemma":[0.99748707,0.0011055084,0.000048219197,0.0011437546,0.00008859025,0.0001268769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036020236,0.00025982488,0.00021799255,0.0005210715,0.00015573166,0.00085160084,0.0010667978,0.00011008218,0.0000019547147],"category_scores_gemma":[0.00086424494,0.0002697926,0.00004295649,0.0012639486,0.0000129783275,0.0010827311,0.00023238444,0.00016314855,0.000019712232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013325659,0.0004312117,0.0056016343,0.0025538362,0.00080722803,0.002502545,0.017467486,0.343933,0.11435906,0.0092935385,0.19684426,0.30619287],"study_design_scores_gemma":[0.000028355742,0.000029099565,0.00022160035,0.00087125873,0.00002207709,0.00015368522,0.000009443686,0.9916781,0.0043612677,0.00008528972,0.0021943164,0.00034547428],"about_ca_topic_score_codex":0.00038352713,"about_ca_topic_score_gemma":0.0000023041798,"teacher_disagreement_score":0.64774513,"about_ca_system_score_codex":0.00011523065,"about_ca_system_score_gemma":0.000081687176,"threshold_uncertainty_score":0.99997544},"labels":[],"label_agreement":null},{"id":"W4391998095","doi":"10.1007/s10664-023-10433-5","title":"Evaluating the impact of flaky simulators on testing autonomous driving systems","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Replication (statistics); Key (lock); Scope (computer science); Code coverage; Simulation; Machine learning; Operating system; Statistics; Software; Mathematics; Programming language","score_opus":0.08166117695653764,"score_gpt":0.382740428437695,"score_spread":0.3010792514811574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391998095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3181773,0.0006337332,0.6648792,0.000049973656,0.0005592858,0.00019127864,0.0000019979407,0.015460415,0.000046781537],"genre_scores_gemma":[0.90906656,7.105418e-7,0.090658106,0.00001594235,0.00017778913,0.00002912883,7.75879e-7,0.000033444,0.00001753143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819064,0.000070631984,0.00041922738,0.00045634957,0.00043615143,0.00042700703],"domain_scores_gemma":[0.9920613,0.0070006237,0.000081150174,0.00064229657,0.000102960774,0.00011164112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008557593,0.00027611415,0.0002797238,0.00021323175,0.00013094707,0.00034516162,0.0007429481,0.00009477434,0.0000022762263],"category_scores_gemma":[0.0067758556,0.00018407048,0.00018954511,0.0011339703,0.000027594046,0.00021823228,0.00019068106,0.00043522337,0.000013235176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014108847,0.000023411914,0.026586583,0.000102277474,0.00005286303,0.00002832965,0.00045597032,0.9353039,0.00025324032,0.00023218877,0.0010775281,0.035882268],"study_design_scores_gemma":[0.000047957477,0.00037547632,0.023873597,0.00071153574,0.000009390677,0.000044428944,0.0000011926463,0.9740264,0.000107077634,0.0005256711,0.00005931027,0.00021799764],"about_ca_topic_score_codex":0.00011701354,"about_ca_topic_score_gemma":9.881979e-8,"teacher_disagreement_score":0.5908893,"about_ca_system_score_codex":0.00026049785,"about_ca_system_score_gemma":0.000175335,"threshold_uncertainty_score":0.81118214},"labels":[],"label_agreement":null},{"id":"W4392942125","doi":"10.1109/bcd57833.2023.10466329","title":"PyTPU: Migration of Python Code for Heterogenous Acceleration with Automated Test Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Python (programming language); Computer science; Programming language; Unit testing; Software","score_opus":0.06133012185637991,"score_gpt":0.30122957876112694,"score_spread":0.239899456904747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392942125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15753742,0.0000060583757,0.81650627,0.00040875716,0.000059164588,0.0002984059,0.000007416628,0.025125792,0.000050705603],"genre_scores_gemma":[0.6991139,0.0000024567255,0.300547,0.00009195001,0.000034781442,0.000075010255,0.000057245223,0.000010122502,0.00006750938],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925655,0.000020199022,0.0001910703,0.00023055574,0.00015931025,0.00014228874],"domain_scores_gemma":[0.99914354,0.0002290191,0.000098796576,0.00029043696,0.00021077799,0.000027415044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025359745,0.00008976866,0.00010386077,0.00013626134,0.000108447166,0.00011987186,0.00020081809,0.000048395883,0.0000010309],"category_scores_gemma":[0.00016839764,0.00007226367,0.000026206364,0.0004920534,0.000015824044,0.00026949742,0.000034239183,0.000027390583,0.000006064267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006205004,0.00055499515,0.036429234,0.00025397076,0.000075488846,0.00001644759,0.0037290428,0.011900845,0.4331935,0.011881161,0.40563825,0.09626504],"study_design_scores_gemma":[0.00014838054,0.00049982406,0.0018191647,0.000016517872,0.0000041871563,0.000007788276,0.000002034145,0.9046909,0.09148144,0.0010170101,0.00021712022,0.00009563425],"about_ca_topic_score_codex":0.00007154071,"about_ca_topic_score_gemma":0.00015620475,"teacher_disagreement_score":0.8927901,"about_ca_system_score_codex":0.000021864495,"about_ca_system_score_gemma":0.000048243008,"threshold_uncertainty_score":0.29468268},"labels":[],"label_agreement":null},{"id":"W4393108609","doi":"10.1145/3589335.3651463","title":"A Study of Vulnerability Repair in JavaScript Programs with Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"JavaScript; Computer science; Unobtrusive JavaScript; Secure coding; Web application; Context (archaeology); Programming language; World Wide Web; Computer security; Vulnerability (computing); Code (set theory); Software engineering; Rich Internet application; Software security assurance; Information security","score_opus":0.04482670237209341,"score_gpt":0.312129429966993,"score_spread":0.2673027275948996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393108609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79650587,0.00044445696,0.16626886,0.000091535425,0.00019260141,0.0018132937,0.00000914984,0.03298076,0.0016934652],"genre_scores_gemma":[0.8042591,0.0000013145033,0.1952208,0.000034186723,0.00001529263,0.00031632977,0.0000036735626,0.000019274581,0.00012998242],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975178,0.0001926657,0.0004690729,0.0010510383,0.00045668738,0.00031269318],"domain_scores_gemma":[0.9975089,0.00011042103,0.00012384646,0.0020898336,0.00010830911,0.000058690657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014450869,0.0002900785,0.00048330333,0.00026565592,0.000026949774,0.00010159653,0.0010472975,0.00015426375,0.0000021933677],"category_scores_gemma":[0.00008447366,0.00021163451,0.000110333734,0.00046367693,0.000036364865,0.00010002987,0.0032352312,0.0008249641,0.0000028804798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017624193,0.034958508,0.28862825,0.00654243,0.0010599114,0.004149239,0.40262687,0.010139411,0.000021437114,0.0355802,0.029798739,0.18631874],"study_design_scores_gemma":[0.0007383869,0.0016119623,0.0022875099,0.0015801701,0.000046154353,0.0000332333,0.001123346,0.64678377,0.000120392404,0.3448274,0.00003299234,0.0008146845],"about_ca_topic_score_codex":0.0040308074,"about_ca_topic_score_gemma":0.0012461398,"teacher_disagreement_score":0.63664436,"about_ca_system_score_codex":0.000081333324,"about_ca_system_score_gemma":0.00018281302,"threshold_uncertainty_score":0.8630205},"labels":[],"label_agreement":null},{"id":"W4393547037","doi":"10.5281/zenodo.2677940","title":"Testing Selectivity of USP5 Zf-UBD Analogues with SPR Assay","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Selectivity; Chemistry; Mathematics; Chromatography; Computational biology; Biological system; Computer science; Biology; Biochemistry","score_opus":0.05905873052827128,"score_gpt":0.26357634429834026,"score_spread":0.204517613770069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393547037","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032478184,0.00012968662,0.1685012,0.00025281732,0.00027188694,0.001184333,0.80180776,0.017514851,0.010012702],"genre_scores_gemma":[0.0121432645,0.000033323027,0.038186107,0.00015994563,0.00019852791,1.3304778e-7,0.94780815,0.0012959491,0.00017459558],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973158,0.00054256915,0.00031835856,0.00074219296,0.00065617,0.00042487917],"domain_scores_gemma":[0.99655914,0.00031326924,0.0004071686,0.0014467811,0.0011446615,0.00012898291],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014615711,0.00027504773,0.0003608065,0.00046341488,0.0008779832,0.00078599976,0.0030926915,0.00015199323,0.00032192393],"category_scores_gemma":[0.0035703336,0.00025637096,0.000054573564,0.0014343391,0.0001644876,0.0003252436,0.0023639323,0.0005831862,0.0012987016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011104235,0.00009928772,0.00001647878,0.00016989987,0.000034797595,0.000018781784,0.00006529093,0.000025352658,0.0000892934,0.00008114052,0.979511,0.019877532],"study_design_scores_gemma":[0.00019180906,0.0007128807,0.00043623318,0.0002817684,0.000024945803,0.00021858406,0.0000041644817,0.0012139307,0.0001677012,0.00037103263,0.9960358,0.00034112614],"about_ca_topic_score_codex":0.00018497604,"about_ca_topic_score_gemma":0.0000011148052,"teacher_disagreement_score":0.1460004,"about_ca_system_score_codex":0.00013243135,"about_ca_system_score_gemma":0.000026358732,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W4393610751","doi":"10.5281/zenodo.6994691","title":"Flakify: A Black-Box, Language Model-based Predictor for Flaky Tests – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Black box; Computer science; Programming language; Mathematics; Artificial intelligence; Statistics","score_opus":0.03671388466794158,"score_gpt":0.283911857080683,"score_spread":0.24719797241274144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393610751","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025709973,0.000053122527,0.34032878,0.0006259262,0.00012411783,0.0011295127,0.64430803,0.012733281,0.000671517],"genre_scores_gemma":[0.0007424046,0.000023273355,0.02298119,0.00049562985,0.00016943127,0.0000025409659,0.9742064,0.0010670796,0.000312035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967918,0.00036289045,0.0004168503,0.0012187936,0.000690019,0.00051965687],"domain_scores_gemma":[0.99534464,0.00024545737,0.0003574064,0.0032910497,0.0005515719,0.00020986382],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014961502,0.00032452858,0.00030095686,0.00052735803,0.0019623272,0.001162658,0.0044741253,0.00017811883,0.0037735633],"category_scores_gemma":[0.004813689,0.0003601764,0.00013430625,0.00081858214,0.00015305527,0.00027089103,0.0026916037,0.0005691948,0.00067518273],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025287383,0.00014771201,2.572484e-7,0.00019550382,0.000020483436,0.000014274569,0.00027264716,0.00022790414,0.0000917367,0.0002883617,0.98656464,0.012151177],"study_design_scores_gemma":[0.00038547057,0.0004607296,0.0000071479653,0.00006933565,0.000027155622,0.000037218597,0.000010417393,0.038210973,0.00010272671,0.0011023827,0.9592222,0.0003642666],"about_ca_topic_score_codex":0.000034502682,"about_ca_topic_score_gemma":6.6558596e-7,"teacher_disagreement_score":0.3298984,"about_ca_system_score_codex":0.00033036276,"about_ca_system_score_gemma":0.000037810896,"threshold_uncertainty_score":0.999885},"labels":[],"label_agreement":null},{"id":"W4393662211","doi":"10.5281/zenodo.2677941","title":"Testing Selectivity of USP5 Zf-UBD Analogues with SPR Assay","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Selectivity; Chemistry; Computer science; Biochemistry","score_opus":0.07578319720065074,"score_gpt":0.28229883875497114,"score_spread":0.2065156415543204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393662211","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025758352,0.00009796302,0.0005636635,0.0000117345735,0.00006223373,0.00025347885,0.9961399,0.0027046704,0.00016382278],"genre_scores_gemma":[0.00032750829,7.133679e-7,0.028714607,0.00009839589,0.00009657826,0.000074536,0.97063905,0.000022407017,0.000026204727],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980221,0.00012696057,0.0002768195,0.00069678214,0.0005044128,0.00037291995],"domain_scores_gemma":[0.9953216,0.0020392954,0.000554589,0.0015286945,0.000472622,0.00008319898],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024762697,0.00036594633,0.00050781376,0.00024766312,0.000087005945,0.0001610827,0.0018196118,0.00027811466,0.001205024],"category_scores_gemma":[0.006973625,0.0003080101,0.00007921815,0.00089388504,0.000014733631,0.00024999637,0.00068637147,0.0005369938,0.00046616315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017583742,0.000037851507,0.00019701186,0.00047023883,0.00001983613,0.00003243135,0.000008605936,0.000011752233,0.0000019480754,6.9783255e-7,0.99733365,0.0018842231],"study_design_scores_gemma":[0.00019953951,0.0006726445,0.0032208348,0.013422529,0.00003885535,0.00015162161,6.821732e-7,0.0030943684,0.00037664792,0.00044397157,0.9773605,0.0010178029],"about_ca_topic_score_codex":0.00025913146,"about_ca_topic_score_gemma":0.00003782097,"teacher_disagreement_score":0.028150944,"about_ca_system_score_codex":0.000060271745,"about_ca_system_score_gemma":0.00042576858,"threshold_uncertainty_score":0.9999372},"labels":[],"label_agreement":null},{"id":"W4393677065","doi":"10.5281/zenodo.7455766","title":"ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolutionary Search – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Computer science; Code (set theory); Test (biology); Similarity (geometry); Programming language; Artificial intelligence; Biology; Mathematics; Statistics","score_opus":0.04402094876027669,"score_gpt":0.2760535441570954,"score_spread":0.2320325953968187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393677065","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007263965,0.000059447488,0.03452404,0.002403775,0.000119898476,0.0011719066,0.94996184,0.010146574,0.0015398627],"genre_scores_gemma":[0.004577559,0.00011057801,0.0096508935,0.0006509151,0.00013007723,9.3719933e-7,0.983924,0.0007992754,0.00015581716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962581,0.0007127635,0.00041200244,0.0013316321,0.00083364634,0.00045188185],"domain_scores_gemma":[0.99516636,0.0010187844,0.00026593378,0.0026345192,0.0006667916,0.00024759126],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001545762,0.00032779388,0.00026449133,0.00062218384,0.003378026,0.0011566437,0.0021236527,0.00019764304,0.0052251867],"category_scores_gemma":[0.010096894,0.00037363725,0.000065389075,0.0011949824,0.0002851889,0.0003020338,0.0029990862,0.00087501894,0.00056278304],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016181602,0.0004006759,0.000012903807,0.00013302255,0.000009409473,0.00029531503,0.00010753764,0.00018365608,0.000015272706,0.00008259728,0.99096376,0.007779691],"study_design_scores_gemma":[0.00032440893,0.00093552336,0.00016767783,0.000077458964,0.00002171792,0.0010998442,0.00001633252,0.0342077,0.000028436023,0.00029439514,0.9624466,0.00037991672],"about_ca_topic_score_codex":0.00010900244,"about_ca_topic_score_gemma":0.0000012382417,"teacher_disagreement_score":0.03402405,"about_ca_system_score_codex":0.00042306172,"about_ca_system_score_gemma":0.000033761575,"threshold_uncertainty_score":0.99988025},"labels":[],"label_agreement":null},{"id":"W4393740131","doi":"10.5281/zenodo.6994692","title":"Flakify: A Black-Box, Language Model-based Predictor for Flaky Tests – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Black box; Computer science; R package; Programming language; Artificial intelligence; Mathematics; Statistics","score_opus":0.03671388466794158,"score_gpt":0.283911857080683,"score_spread":0.24719797241274144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393740131","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025709973,0.000053122527,0.34032878,0.0006259262,0.00012411783,0.0011295127,0.64430803,0.012733281,0.000671517],"genre_scores_gemma":[0.0007424046,0.000023273355,0.02298119,0.00049562985,0.00016943127,0.0000025409659,0.9742064,0.0010670796,0.000312035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967918,0.00036289045,0.0004168503,0.0012187936,0.000690019,0.00051965687],"domain_scores_gemma":[0.99534464,0.00024545737,0.0003574064,0.0032910497,0.0005515719,0.00020986382],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014961502,0.00032452858,0.00030095686,0.00052735803,0.0019623272,0.001162658,0.0044741253,0.00017811883,0.0037735633],"category_scores_gemma":[0.004813689,0.0003601764,0.00013430625,0.00081858214,0.00015305527,0.00027089103,0.0026916037,0.0005691948,0.00067518273],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025287383,0.00014771201,2.572484e-7,0.00019550382,0.000020483436,0.000014274569,0.00027264716,0.00022790414,0.0000917367,0.0002883617,0.98656464,0.012151177],"study_design_scores_gemma":[0.00038547057,0.0004607296,0.0000071479653,0.00006933565,0.000027155622,0.000037218597,0.000010417393,0.038210973,0.00010272671,0.0011023827,0.9592222,0.0003642666],"about_ca_topic_score_codex":0.000034502682,"about_ca_topic_score_gemma":6.6558596e-7,"teacher_disagreement_score":0.3298984,"about_ca_system_score_codex":0.00033036276,"about_ca_system_score_gemma":0.000037810896,"threshold_uncertainty_score":0.999885},"labels":[],"label_agreement":null},{"id":"W4393757241","doi":"10.5281/zenodo.7455765","title":"ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolutionary Search – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Computer science; Code (set theory); Test (biology); Similarity (geometry); Minification; Programming language; Artificial intelligence; Biology; Mathematics; Statistics; Paleontology","score_opus":0.04402094876027669,"score_gpt":0.2760535441570954,"score_spread":0.2320325953968187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393757241","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007263965,0.000059447488,0.03452404,0.002403775,0.000119898476,0.0011719066,0.94996184,0.010146574,0.0015398627],"genre_scores_gemma":[0.004577559,0.00011057801,0.0096508935,0.0006509151,0.00013007723,9.3719933e-7,0.983924,0.0007992754,0.00015581716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962581,0.0007127635,0.00041200244,0.0013316321,0.00083364634,0.00045188185],"domain_scores_gemma":[0.99516636,0.0010187844,0.00026593378,0.0026345192,0.0006667916,0.00024759126],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001545762,0.00032779388,0.00026449133,0.00062218384,0.003378026,0.0011566437,0.0021236527,0.00019764304,0.0052251867],"category_scores_gemma":[0.010096894,0.00037363725,0.000065389075,0.0011949824,0.0002851889,0.0003020338,0.0029990862,0.00087501894,0.00056278304],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016181602,0.0004006759,0.000012903807,0.00013302255,0.000009409473,0.00029531503,0.00010753764,0.00018365608,0.000015272706,0.00008259728,0.99096376,0.007779691],"study_design_scores_gemma":[0.00032440893,0.00093552336,0.00016767783,0.000077458964,0.00002171792,0.0010998442,0.00001633252,0.0342077,0.000028436023,0.00029439514,0.9624466,0.00037991672],"about_ca_topic_score_codex":0.00010900244,"about_ca_topic_score_gemma":0.0000012382417,"teacher_disagreement_score":0.03402405,"about_ca_system_score_codex":0.00042306172,"about_ca_system_score_gemma":0.000033761575,"threshold_uncertainty_score":0.99988025},"labels":[],"label_agreement":null},{"id":"W4393772048","doi":"10.5281/zenodo.8309515","title":"Search-based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions - Dataset and Results","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Software; Software testing; Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.053576618488732214,"score_gpt":0.26812928173125283,"score_spread":0.21455266324252062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393772048","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000091733484,0.000045615594,0.053240195,0.00063319906,0.00008282686,0.00041305978,0.9327517,0.012664327,0.00007731164],"genre_scores_gemma":[0.00008705009,0.00003682615,0.033662334,0.00022238154,0.00006107909,3.3354138e-7,0.9652705,0.0005612969,0.00009818618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686575,0.00050911837,0.0004983615,0.0010426863,0.00056879566,0.0005152614],"domain_scores_gemma":[0.99702674,0.00060239696,0.00022035766,0.0012305209,0.00061027985,0.00030970838],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013353297,0.00032480116,0.00029752497,0.000443569,0.0023863956,0.0023783855,0.0019036734,0.00019599932,0.00008541332],"category_scores_gemma":[0.008598714,0.0003397288,0.000028412596,0.0011222931,0.00030127523,0.00028973175,0.0036340023,0.0005816547,0.001752262],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001648964,0.000059932685,0.0000020106177,0.00016728835,0.000025357225,0.000046979167,0.000036649453,0.000054196928,0.000044602803,0.000015131905,0.9800938,0.019437559],"study_design_scores_gemma":[0.0005585785,0.00038931955,0.00017498316,0.00022993107,0.000031793526,0.0001425378,0.0000059013696,0.023386158,0.000019470961,0.0001717854,0.97446585,0.00042368114],"about_ca_topic_score_codex":0.0002399646,"about_ca_topic_score_gemma":0.000002000921,"teacher_disagreement_score":0.03251878,"about_ca_system_score_codex":0.000094439354,"about_ca_system_score_gemma":0.000029040624,"threshold_uncertainty_score":0.99990547},"labels":[],"label_agreement":null},{"id":"W4393978605","doi":"10.1007/978-3-031-57259-3_19","title":"TracerX: Pruning Dynamic Symbolic Execution with Deletion and Weakest Precondition Interpolation (Competition Contribution)","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Precondition; Computer science; Pruning; Interpolation (computer graphics); Competition (biology); Algorithm; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.007317886509596298,"score_gpt":0.2327990402987306,"score_spread":0.2254811537891343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393978605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011254137,0.0004874331,0.99326414,0.0006096727,0.0006138175,0.00046952043,0.000007985417,0.0028070782,0.0006149643],"genre_scores_gemma":[0.82493347,0.000041607003,0.17452529,0.00017406326,0.00013385259,0.000024997167,0.000050340506,0.000029560633,0.00008683864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974442,0.00003467906,0.0003995063,0.001195884,0.0005371712,0.00038854487],"domain_scores_gemma":[0.99844366,0.00034776752,0.00026254918,0.0005685616,0.0002756404,0.00010184372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006839562,0.00041706275,0.00034551232,0.0009312551,0.00027847392,0.00076542766,0.0006234343,0.0002771322,0.0000058006913],"category_scores_gemma":[0.00008962882,0.0003766797,0.000056883207,0.0005029305,0.00041805988,0.0008909946,0.000317941,0.00067021797,0.000016647555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030518935,0.00005746459,0.00042686352,0.00025543568,0.00003702364,0.00009495825,0.0014609421,0.006556096,0.00074211514,0.21123695,0.00003676519,0.7790649],"study_design_scores_gemma":[0.00014147798,0.0002523521,0.0007074193,0.0016880874,0.00001701931,0.00028525773,1.181631e-7,0.6068713,0.00021209018,0.38934317,0.00010841557,0.00037326902],"about_ca_topic_score_codex":0.000026204476,"about_ca_topic_score_gemma":0.0000798471,"teacher_disagreement_score":0.823808,"about_ca_system_score_codex":0.00042627833,"about_ca_system_score_gemma":0.00019691589,"threshold_uncertainty_score":0.9998685},"labels":[],"label_agreement":null},{"id":"W4394015350","doi":"10.1016/j.infsof.2024.107468","title":"Effective test generation using pre-trained Large Language Models and mutation testing","year":2024,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Test (biology); Mutation; Computer science; Natural language processing; Genetics; Biology; Gene","score_opus":0.01684748034253352,"score_gpt":0.2775876674362418,"score_spread":0.2607401870937083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394015350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15050168,0.00043336322,0.83588797,0.0001577461,0.00007520317,0.00022673816,0.0000072010616,0.012666152,0.000043926466],"genre_scores_gemma":[0.7107661,0.000006381202,0.28902397,0.00012692546,0.000020050102,0.000034390705,0.000011653948,0.0000056059475,0.0000049165997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992799,0.000018946153,0.00022335109,0.00019139577,0.000108309716,0.00017810996],"domain_scores_gemma":[0.9992214,0.00037738885,0.000070898604,0.00018595782,0.00010936654,0.000035002828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003156947,0.00012438797,0.00011317268,0.0004882875,0.00018505091,0.00031601646,0.00013310042,0.00015425595,7.6838256e-7],"category_scores_gemma":[0.0012768471,0.00011647337,0.000014256314,0.0005956185,0.00005256283,0.0017368202,0.0001542251,0.00016139552,0.0000035021055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013628166,0.000013210391,0.0025315536,0.00012501112,0.000010477244,0.000015671165,0.0040263305,0.00029251963,0.00069065735,0.013593907,0.00024772232,0.97845155],"study_design_scores_gemma":[0.00014609561,0.000101475205,0.0007259908,0.00009629407,0.00000750205,0.00030755252,0.000036660684,0.9643289,0.0007541211,0.03326168,0.00009088668,0.00014288412],"about_ca_topic_score_codex":0.000038391292,"about_ca_topic_score_gemma":0.000003532882,"teacher_disagreement_score":0.9783087,"about_ca_system_score_codex":0.000042818785,"about_ca_system_score_gemma":0.000044141005,"threshold_uncertainty_score":0.47496462},"labels":[],"label_agreement":null},{"id":"W4394746056","doi":"10.1145/3597503.3639112","title":"Mozi: Discovering DBMS Bugs via Configuration-Based Equivalent Transformation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Correctness; Programming language; SQL; Semantics (computer science); Database; Query language; Transformation (genetics); Task (project management)","score_opus":0.01918079054616061,"score_gpt":0.2707753826562442,"score_spread":0.25159459211008356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394746056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020054006,0.00007330566,0.97393084,0.001524924,0.00031586632,0.00013873455,8.978207e-7,0.016117288,0.0058927303],"genre_scores_gemma":[0.9274188,0.0000032451553,0.07194069,0.00036061506,0.00004227678,0.000025960751,0.000005840139,0.000007902424,0.00019463341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991687,0.000028172924,0.00019722844,0.00022436414,0.0002091874,0.00017232995],"domain_scores_gemma":[0.999351,0.00027672443,0.000021789561,0.00026691894,0.00004043256,0.000043133918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025521137,0.000101666126,0.00008025038,0.000109724606,0.000094477444,0.00028122633,0.00029077654,0.00004259543,0.00003266153],"category_scores_gemma":[0.000029455188,0.00008352132,0.000053650416,0.00027018346,0.000018384018,0.0006305156,0.000020583117,0.00010501515,0.000083282175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012152863,0.000104906496,0.0006435403,0.00055160414,0.0000514548,0.000060105252,0.008605608,0.004338082,0.010097844,0.30160525,0.028569866,0.6453596],"study_design_scores_gemma":[0.000076786004,0.00005020738,0.00015513922,0.00013022528,0.000004334761,0.000006634438,0.000004904077,0.9608776,0.014876926,0.021460716,0.0022040887,0.00015245467],"about_ca_topic_score_codex":0.000106284555,"about_ca_topic_score_gemma":0.0000045449187,"teacher_disagreement_score":0.9565395,"about_ca_system_score_codex":0.000054324883,"about_ca_system_score_gemma":0.00006790756,"threshold_uncertainty_score":0.34059006},"labels":[],"label_agreement":null},{"id":"W4394927149","doi":"10.1007/s10270-024-01170-4","title":"Improving repair of semantic ATL errors using a social diversity metric","year":2024,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; McGill University; Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Metric (unit); Diversity (politics); Natural language processing; Information retrieval; Data science; Artificial intelligence; Sociology","score_opus":0.055793967027818005,"score_gpt":0.2822911530338823,"score_spread":0.2264971860060643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394927149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.115833305,0.002151225,0.86229795,0.000013232504,0.00090515125,0.00020057267,0.0000052495043,0.018575156,0.000018179087],"genre_scores_gemma":[0.8290654,0.0000030285453,0.17071521,0.000014541689,0.00014345946,0.0000070642373,0.0000014322791,0.00002801856,0.000021895394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976663,0.00012507656,0.0005385515,0.00065862987,0.00059459085,0.00041687908],"domain_scores_gemma":[0.9986686,0.0003156615,0.00017486048,0.0005284047,0.00023134073,0.00008109813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001236419,0.00024309118,0.00041662794,0.0006061833,0.0005446203,0.00022034746,0.0007449157,0.0001557803,8.2008677e-7],"category_scores_gemma":[0.0004917876,0.0002392078,0.00028374253,0.0013702621,0.000040250918,0.0005637289,0.0011565441,0.0002622372,0.0000049990795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006542919,0.0005277799,0.13518928,0.024375722,0.0014116782,0.0013593339,0.045177206,0.610596,0.0025770173,0.022743769,0.008189547,0.14778726],"study_design_scores_gemma":[0.00007154067,0.000034076966,0.00003213157,0.00065131666,0.000055295113,0.000055816763,0.000056310586,0.9960989,0.000024997504,0.0026454153,0.000012867162,0.00026133726],"about_ca_topic_score_codex":0.0050896537,"about_ca_topic_score_gemma":0.000004080676,"teacher_disagreement_score":0.71323204,"about_ca_system_score_codex":0.0002314189,"about_ca_system_score_gemma":0.00019916744,"threshold_uncertainty_score":0.97546107},"labels":[],"label_agreement":null},{"id":"W4395113782","doi":"10.1007/978-3-031-57540-2_5","title":"Accurify: Automated New Testflows Generation for Attack Variants in Threat Hunting","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Ericsson (Canada)","funders":"","keywords":"Computer science; Computer security; Artificial intelligence","score_opus":0.056137756697451434,"score_gpt":0.3139452280827616,"score_spread":0.2578074713853102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395113782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012904007,0.0005407868,0.9869766,0.0008831344,0.0020016897,0.0006517409,0.0000052864852,0.0080959555,0.0007157666],"genre_scores_gemma":[0.05183544,0.000016689317,0.9455695,0.00093822915,0.0009804432,0.000032037904,0.00001437844,0.00006506638,0.00054818945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620676,0.000022680939,0.0006313454,0.0018207623,0.0006155759,0.0007028879],"domain_scores_gemma":[0.99729,0.0009779166,0.00022569206,0.0011754793,0.0001903842,0.00014051925],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011866798,0.0005429607,0.00052750256,0.0011416958,0.00019903191,0.0011125817,0.0023303425,0.00042545478,0.000005128664],"category_scores_gemma":[0.0005324347,0.0005091445,0.00012426812,0.0009610297,0.00017074701,0.00062087196,0.0009865974,0.0006895943,0.00003172884],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057275465,0.000040937288,0.00039473485,0.0001551121,0.00001714057,0.00015273316,0.0012088751,0.041356087,0.0004046223,0.015087787,0.0035891952,0.937587],"study_design_scores_gemma":[0.00014648952,0.00009507595,0.00009293497,0.0007137647,0.000006337506,0.000047948433,1.4003032e-8,0.72625667,0.0003509415,0.27145085,0.0004172657,0.00042170344],"about_ca_topic_score_codex":0.000144574,"about_ca_topic_score_gemma":0.0001700217,"teacher_disagreement_score":0.9371653,"about_ca_system_score_codex":0.00035791306,"about_ca_system_score_gemma":0.0008347357,"threshold_uncertainty_score":0.99992436},"labels":[],"label_agreement":null},{"id":"W4396214523","doi":"10.1145/3649850","title":"PyDex: Repairing Bugs in Introductory Python Assignments using LLMs","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Python (programming language); Programming language; Computer science; Software engineering","score_opus":0.022964714500130406,"score_gpt":0.3016022634851895,"score_spread":0.2786375489850591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396214523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98320264,0.0015062989,0.0018558447,0.0018053086,0.0006185505,0.0005108527,0.0000011092351,0.009931546,0.00056786893],"genre_scores_gemma":[0.7647365,0.000005270509,0.23493694,0.000074529926,0.00010800951,0.000026182568,2.463254e-7,0.000025711068,0.000086610555],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983932,0.000016478929,0.00029861543,0.0005265693,0.00041074015,0.00035440907],"domain_scores_gemma":[0.9988913,0.0001950701,0.00013668777,0.0006550771,0.00007760933,0.00004424143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009984892,0.00019069518,0.00019896204,0.00028431823,0.0000901704,0.0003195602,0.002136603,0.000077910314,0.000001474818],"category_scores_gemma":[0.0025456608,0.00013990588,0.000100439014,0.00089123985,0.000075765274,0.00038452973,0.0012008825,0.0003267503,0.000003074438],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032703243,0.00037598677,0.09573543,0.0014414106,0.00010675666,0.00006893549,0.0113395555,0.00006485149,0.060888026,0.016118092,0.01237003,0.80145824],"study_design_scores_gemma":[0.0013374945,0.00144285,0.025917964,0.02127973,0.0001950276,0.00063887116,0.0015678158,0.06679298,0.62090516,0.24288005,0.0139838895,0.0030581937],"about_ca_topic_score_codex":0.000109200584,"about_ca_topic_score_gemma":0.000001090763,"teacher_disagreement_score":0.79840004,"about_ca_system_score_codex":0.000133891,"about_ca_system_score_gemma":0.000041152885,"threshold_uncertainty_score":0.5705196},"labels":[],"label_agreement":null},{"id":"W4396796398","doi":"10.3390/biomedinformatics4020069","title":"A Smartphone-Based Algorithm for L Test Subtask Segmentation","year":2024,"lang":"en","type":"article","venue":"BioMedInformatics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Artificial intelligence; Segmentation; Algorithm; Computer vision; Geology","score_opus":0.019163561674323558,"score_gpt":0.28097800109259485,"score_spread":0.2618144394182713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396796398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000103607344,0.000102332466,0.988897,0.00041076975,0.0006770232,0.00025747286,0.00003930546,0.009371736,0.00014072635],"genre_scores_gemma":[0.0056275814,0.0000059623917,0.99361086,0.0004087124,0.00009253738,0.00010729126,0.000053586624,0.000010845978,0.00008265148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991511,0.000005765723,0.00026803493,0.0001374123,0.00022271175,0.00021497034],"domain_scores_gemma":[0.9987586,0.00077161385,0.00005520068,0.0002665101,0.00007858556,0.00006946417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003586448,0.00011748512,0.000098727294,0.00025272934,0.00008913308,0.0003991488,0.00036467315,0.000058004032,0.000002758499],"category_scores_gemma":[0.0001526837,0.00010033609,0.000062153485,0.00052734296,0.000034009336,0.00048698555,0.00005723387,0.00006127695,0.00005271443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.636906e-7,0.000023031243,0.000039284503,0.00016684842,0.0000068304657,0.0000025250652,0.00056892063,0.000001678572,0.00010850599,0.00043172957,0.06482736,0.9338228],"study_design_scores_gemma":[0.00015983876,0.00015874922,0.000037639005,0.00010512102,0.00000769832,0.000013613094,0.000008963433,0.9745041,0.003714281,0.005628816,0.015516676,0.00014448474],"about_ca_topic_score_codex":0.000005758581,"about_ca_topic_score_gemma":2.2609314e-7,"teacher_disagreement_score":0.97450244,"about_ca_system_score_codex":0.000066292676,"about_ca_system_score_gemma":0.0001316679,"threshold_uncertainty_score":0.40915868},"labels":[],"label_agreement":null},{"id":"W4396871671","doi":"10.1145/3664601","title":"Testing Updated Apps by Adapting Learned Models","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Computer science; Correctness; Adaptation (eye); Software; Software inspection; Software performance testing; Machine learning; Software engineering; Human–computer interaction; Software development; Software quality; Operating system; Software construction; Programming language","score_opus":0.1504107154579445,"score_gpt":0.32533558583462185,"score_spread":0.17492487037667737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396871671","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015173838,0.0011612372,0.97401685,0.0002777055,0.00047356656,0.00009113009,0.000007733946,0.022437379,0.000017029053],"genre_scores_gemma":[0.1220973,0.00003867004,0.8775322,0.00011895673,0.000029011919,0.000041885407,0.0000037809382,0.000037305173,0.000100924364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984988,0.00015573496,0.0002443892,0.0005950379,0.00013730247,0.00036873893],"domain_scores_gemma":[0.9937888,0.005451973,0.000030515275,0.0005581787,0.00005436626,0.000116212446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010145092,0.00023750284,0.00025532415,0.00029706556,0.00016516619,0.00014824719,0.00046509667,0.00016775892,0.0000043910113],"category_scores_gemma":[0.001732681,0.00023594644,0.00006323133,0.00065020483,0.00003525448,0.00030808846,0.000035860816,0.0005202289,0.000006924128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005658148,0.00002794928,0.000020609457,0.00008147678,0.00006339031,0.000029953197,0.00044943014,0.03542572,0.0018059883,0.0015599903,0.0009931903,0.9595367],"study_design_scores_gemma":[0.00016849159,0.00023823166,0.000046352994,0.0002748262,0.00004074526,0.00036533992,0.000009838456,0.95856214,0.003474042,0.033093996,0.0032415877,0.0004843929],"about_ca_topic_score_codex":0.000069800975,"about_ca_topic_score_gemma":4.1309144e-7,"teacher_disagreement_score":0.95905226,"about_ca_system_score_codex":0.000038331367,"about_ca_system_score_gemma":0.000044070668,"threshold_uncertainty_score":0.96216166},"labels":[],"label_agreement":null},{"id":"W4398239453","doi":"10.1145/3639478.3643062","title":"Technical Brief on Software Engineering for FMware","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Software; Engineering management; Trustworthiness; Foundation (evidence); Quality (philosophy); Software engineering; Software quality; Software testing; Software development; Systems engineering; Engineering; Computer security","score_opus":0.019046383439439946,"score_gpt":0.26932644212361306,"score_spread":0.25028005868417313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398239453","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007814468,0.00011796172,0.9366939,0.00047499852,0.00030463884,0.00014068,0.0000027447238,0.06172007,0.0004668518],"genre_scores_gemma":[0.09215727,0.00000168252,0.9067981,0.00041533617,0.00009764707,0.000087076216,0.0000022358024,0.000020193042,0.00042045073],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999159,0.000005158798,0.00012146819,0.00035925966,0.00013821595,0.00021689583],"domain_scores_gemma":[0.998737,0.00075998827,0.000009681731,0.00040043096,0.00003531911,0.000057584428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019379519,0.000116712996,0.00009727647,0.00012740995,0.000050236904,0.00022963896,0.0004671481,0.000067951165,0.000005325744],"category_scores_gemma":[0.0007466181,0.00009755868,0.000079928875,0.00027381376,0.0000103563025,0.00014407666,0.000117724194,0.00012689512,0.00002773744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033909516,0.000041674164,0.00018773605,0.00016714803,0.0000114904415,0.000047657,0.000071656825,0.00018564193,0.00016204211,0.37640643,0.46356276,0.15915237],"study_design_scores_gemma":[0.00021614671,0.0006784404,0.00079809054,0.0008675041,0.000013316157,0.00018655321,9.598618e-7,0.69288576,0.0063691144,0.08238492,0.21480265,0.0007965177],"about_ca_topic_score_codex":0.0000069436314,"about_ca_topic_score_gemma":4.901298e-7,"teacher_disagreement_score":0.69270015,"about_ca_system_score_codex":0.00004235587,"about_ca_system_score_gemma":0.00003872051,"threshold_uncertainty_score":0.39783275},"labels":[],"label_agreement":null},{"id":"W4399036954","doi":"10.29007/rdbb","title":"Efficient Simulation for Hardware Model Checking","year":2024,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Correctness; Executable; Model checking; Semantics (computer science); Programming language; Formal verification; Set (abstract data type); Speedup; Symbolic trajectory evaluation; Computer engineering; Parallel computing; Theoretical computer science","score_opus":0.043641389716917105,"score_gpt":0.33103879876707565,"score_spread":0.28739740905015854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399036954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016612459,0.0002620738,0.9742263,0.00029301184,0.0005556115,0.00020223307,9.618702e-7,0.007550149,0.0002972265],"genre_scores_gemma":[0.6183277,4.2993486e-7,0.38147867,0.00006501054,0.00007270491,0.000009358452,0.0000012112852,0.000009817826,0.00003512056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893534,0.000024103561,0.00025373788,0.00038445115,0.0001414533,0.0002608941],"domain_scores_gemma":[0.99871325,0.00088329025,0.000041820127,0.00028037225,0.000052987314,0.000028292487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006220936,0.0001183306,0.00013054551,0.00015713715,0.00013463646,0.00024288536,0.00035765575,0.000052232797,8.8864573e-7],"category_scores_gemma":[0.00046629156,0.000119058845,0.000057409856,0.00038554883,0.00002242156,0.00013070359,0.00022452835,0.0001266535,0.0000028314282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026127268,0.000008012116,0.00017933639,0.00006581711,0.0000027522806,0.0000061700284,0.0014033864,0.91815317,0.000012505134,0.011333442,0.00027315094,0.06855967],"study_design_scores_gemma":[0.00009481988,0.00002573935,0.00009207541,0.00030253603,0.0000019048289,0.000007871607,0.000006648887,0.9559586,0.00015396712,0.04293624,0.00028570642,0.00013386387],"about_ca_topic_score_codex":0.000008032932,"about_ca_topic_score_gemma":8.6483584e-7,"teacher_disagreement_score":0.6017152,"about_ca_system_score_codex":0.000085414045,"about_ca_system_score_gemma":0.00005961048,"threshold_uncertainty_score":0.48550788},"labels":[],"label_agreement":null},{"id":"W4399061142","doi":"10.1145/3663529.3663787","title":"On Polyglot Program Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Polyglot; Computer science; Programming language","score_opus":0.04053516960178625,"score_gpt":0.3158553354438702,"score_spread":0.2753201658420839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399061142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031656714,0.00014370386,0.7056999,0.0010580644,0.00041618096,0.00017094974,2.8586257e-7,0.21826385,0.07108137],"genre_scores_gemma":[0.43471622,2.74295e-7,0.5644736,0.00031939457,0.00003551762,0.000023365272,1.9506533e-7,0.0000063322605,0.0004250746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993341,0.000012620629,0.000082285835,0.0002667387,0.000136331,0.0001679196],"domain_scores_gemma":[0.9990124,0.00060512696,0.000008827987,0.00030468352,0.000025671281,0.000043254648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016917777,0.00007634931,0.000051868068,0.00009164226,0.000053095348,0.0003870739,0.0003563314,0.000025642565,0.000006178237],"category_scores_gemma":[0.00036244595,0.000057418292,0.00002571146,0.00053220364,0.000014106924,0.00012798185,0.00010145079,0.00009990131,0.00016437373],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9121757e-7,0.00002457003,0.00015028183,0.000009179953,0.0000021372532,0.00003093766,0.00003122939,0.0000039166234,0.0000148593645,0.107746296,0.041376997,0.8506094],"study_design_scores_gemma":[0.000032692944,0.0004236988,0.00070833846,0.00023283689,0.0000022003487,0.000075838645,5.1621504e-7,0.6156969,0.00080320507,0.3753782,0.0064442633,0.00020131547],"about_ca_topic_score_codex":0.000041507108,"about_ca_topic_score_gemma":3.0640848e-7,"teacher_disagreement_score":0.8504081,"about_ca_system_score_codex":0.00001790919,"about_ca_system_score_gemma":0.000038340564,"threshold_uncertainty_score":0.37325627},"labels":[],"label_agreement":null},{"id":"W4399169339","doi":"10.1109/wf-iot58464.2023.10539471","title":"A Software QA Framework for Autonomous Vehicle Open Source Application: OpenPilot","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Software deployment; Robustness (evolution); Software quality; Reliability engineering; Robustness testing; Regression testing; Software; Embedded system; Software engineering; Software system; Engineering; Software development; Operating system","score_opus":0.053631510355192924,"score_gpt":0.3356348568949485,"score_spread":0.28200334653975556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399169339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003720737,0.000017828132,0.9599868,0.0028039808,0.000113172624,0.0008123829,0.0000031426137,0.035249267,0.00064131565],"genre_scores_gemma":[0.0547667,0.0000017706128,0.9401169,0.0018517165,0.00008388815,0.0009191147,0.000009608149,0.000028494385,0.0022218444],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998685,0.00002658831,0.00021182923,0.00056562695,0.00016212267,0.000348814],"domain_scores_gemma":[0.9975413,0.0010996443,0.000082084596,0.0010723502,0.00010195091,0.00010267623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005944843,0.00014016971,0.00017965706,0.0000923848,0.00031412175,0.0005958363,0.0027707322,0.000092466,0.0000119741335],"category_scores_gemma":[0.0007111125,0.00013074942,0.00005654135,0.0008207575,0.000030564606,0.00034769473,0.0014611764,0.00011766921,0.000315774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010517952,0.00007878736,0.0028916704,0.000033541248,0.000016878319,0.000004459839,0.00048987253,0.00018584744,0.000038370985,0.20259751,0.23434511,0.55930746],"study_design_scores_gemma":[0.00024277029,0.00015727221,0.0013360634,0.000048733298,0.000004729097,0.000009772533,0.000008738823,0.16374336,0.0007319791,0.7679821,0.0654074,0.0003270439],"about_ca_topic_score_codex":0.00017759205,"about_ca_topic_score_gemma":0.0000042611996,"teacher_disagreement_score":0.5653846,"about_ca_system_score_codex":0.00003829296,"about_ca_system_score_gemma":0.00010001379,"threshold_uncertainty_score":0.57456636},"labels":[],"label_agreement":null},{"id":"W4399338452","doi":"10.11591/ijece.v14i4.pp4315-4324","title":"Optimized automated testing: test case generation and maintenance using latent semantic analysis-based TextRank and particle swarm optimization algorithms","year":2024,"lang":"en","type":"article","venue":"International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Particle swarm optimization; Automatic summarization; Latent semantic analysis; Machine learning; Data mining; Software; Test case; Process (computing); Artificial intelligence; Multi-swarm optimization; Semantic analysis (machine learning); Algorithm; Programming language","score_opus":0.013636976004132873,"score_gpt":0.258746922159197,"score_spread":0.2451099461550641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399338452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11374121,0.0046135047,0.8802601,0.00041583343,0.00072097796,0.000065890985,0.000003353807,0.00017773792,0.0000013529009],"genre_scores_gemma":[0.8412393,0.00028197034,0.15810917,0.000053362186,0.00029807052,0.0000012189997,0.0000014696346,0.000013035884,0.000002403847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982047,0.000058206515,0.0007559359,0.00024823283,0.0005128126,0.0002201087],"domain_scores_gemma":[0.99769783,0.0005629645,0.00040363995,0.00007512251,0.0010990931,0.000161331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067314744,0.0002035802,0.0003541293,0.0007053861,0.00006288346,0.00090122264,0.0002917098,0.00007083597,8.4632654e-7],"category_scores_gemma":[0.00020481518,0.00016810402,0.000102892685,0.00041038185,0.00002894061,0.00051087805,0.00009277224,0.0003097801,8.065738e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041455834,0.000115983195,0.002491654,0.000033314438,0.0013867815,0.0030318995,0.00022688319,0.97550046,0.0019976697,0.0024065454,0.00013879701,0.012628541],"study_design_scores_gemma":[0.0006807417,0.0004415813,0.0005055732,0.0002906806,0.00014317415,0.017712502,0.000002478091,0.97967684,0.00019413543,0.00013626095,0.000048874263,0.00016716559],"about_ca_topic_score_codex":0.000022342574,"about_ca_topic_score_gemma":6.3117756e-7,"teacher_disagreement_score":0.7274981,"about_ca_system_score_codex":0.00016749422,"about_ca_system_score_gemma":0.00014385386,"threshold_uncertainty_score":0.86905104},"labels":[],"label_agreement":null},{"id":"W4399619591","doi":"10.1145/3672449","title":"An Empirical Study on the Characteristics of Database Access Bugs in Java Applications","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Database; SQL; Java; Database schema; Stored procedure; Query by Example; View; Commit; Database model; Database design; World Wide Web; Programming language; Web search query","score_opus":0.16223068351507128,"score_gpt":0.4138237030113616,"score_spread":0.2515930194962903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399619591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052035023,0.00005990022,0.94482696,0.00030855872,0.0001919388,0.00025454175,0.000018772236,0.002302598,0.0000017240727],"genre_scores_gemma":[0.61005265,0.000019021727,0.38960946,0.00009780752,0.000019983521,0.00018109688,0.0000024804974,0.000013028454,0.000004466948],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99884033,0.000254499,0.00023900793,0.00038309966,0.00011752061,0.00016555694],"domain_scores_gemma":[0.99294806,0.0060236384,0.000029322842,0.0009097428,0.000033400425,0.000055844324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011421186,0.00014204666,0.0002091479,0.00032468405,0.00007228038,0.000076102544,0.0007359617,0.00007136938,0.0000035275398],"category_scores_gemma":[0.000812518,0.00011003682,0.00003540812,0.00057719514,0.00003834155,0.00016161971,0.000033256827,0.00038744946,0.000002133665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050401508,0.0013984486,0.01793093,0.00029725218,0.00014684362,0.00007815703,0.005931817,0.0047509,0.0009242333,0.004573623,0.0002764047,0.963641],"study_design_scores_gemma":[0.002064476,0.007250251,0.4665651,0.00193771,0.00046959423,0.0006046954,0.0005873355,0.43674102,0.01837249,0.052878823,0.009243886,0.0032846236],"about_ca_topic_score_codex":0.000046523826,"about_ca_topic_score_gemma":0.0000025068202,"teacher_disagreement_score":0.96035635,"about_ca_system_score_codex":0.000021596741,"about_ca_system_score_gemma":0.00004091522,"threshold_uncertainty_score":0.44871712},"labels":[],"label_agreement":null},{"id":"W4399913729","doi":"10.1016/j.eswa.2024.124557","title":"Basis path coverage testing of MPI programs based on multi-task evolutionary optimization","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Path (computing); Basis (linear algebra); Machine learning; Artificial intelligence; Mathematics; Programming language","score_opus":0.028408197792053412,"score_gpt":0.26922609703886186,"score_spread":0.24081789924680844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399913729","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004013705,0.0008031985,0.9900589,0.00016072353,0.000086011874,0.00092343305,0.000011453226,0.0074001285,0.0005160363],"genre_scores_gemma":[0.45274177,0.0000037215761,0.5452727,0.000048960446,0.00005307103,0.0017995232,0.000024301991,0.000018271732,0.000037685764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867755,0.000059589293,0.00028927915,0.0004713289,0.00031786974,0.00018439285],"domain_scores_gemma":[0.998404,0.00045297327,0.00011872091,0.00071884034,0.00023368323,0.000071775685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022517118,0.00016126245,0.00016164452,0.00017465412,0.00016913062,0.00016457884,0.00040177535,0.00006494856,0.0000012715797],"category_scores_gemma":[0.000089088775,0.00013072028,0.000041098374,0.0010849392,0.00004852086,0.00018086271,0.000047699767,0.00010083071,0.000011454935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029940533,0.002089254,0.015863143,0.0012053697,0.00012562524,0.000048689835,0.0021477279,0.670837,0.00087944354,0.031074176,0.024667658,0.25103197],"study_design_scores_gemma":[0.00011688901,0.00014853237,0.00014341086,0.0007801356,0.000005249135,0.000021853395,0.000008425222,0.9952458,0.00008112245,0.00015673897,0.0031285763,0.00016327684],"about_ca_topic_score_codex":0.00021050478,"about_ca_topic_score_gemma":6.269559e-7,"teacher_disagreement_score":0.45270163,"about_ca_system_score_codex":0.00009624695,"about_ca_system_score_gemma":0.00016950622,"threshold_uncertainty_score":0.5330618},"labels":[],"label_agreement":null},{"id":"W4400242288","doi":"10.1145/3643991.3644914","title":"A Mutation-Guided Assessment of Acceleration Approaches for Continuous Integration: An Empirical Study of YourBase","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; University of Waterloo","funders":"","keywords":"Acceleration; Computer science; Mutation; Empirical research; Physics; Mathematics; Genetics; Biology; Statistics","score_opus":0.18885613775120386,"score_gpt":0.421461520203657,"score_spread":0.23260538245245316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400242288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2329929,0.000012469781,0.7644637,0.00014078648,0.00007081173,0.00041337567,0.0000015930038,0.0016567921,0.00024753239],"genre_scores_gemma":[0.65683395,1.4134466e-7,0.34300205,0.000020569465,0.000018022256,0.00008643624,0.0000070210185,0.0000043503514,0.000027480179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905264,0.00007255756,0.0003330788,0.0002651573,0.00019825604,0.000078332974],"domain_scores_gemma":[0.99903655,0.00036067734,0.000077338555,0.0003028661,0.00019362476,0.000028926375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005388581,0.000083697654,0.00016081317,0.00013808522,0.00003911081,0.00012387986,0.00025349561,0.000034444423,0.0000030521144],"category_scores_gemma":[0.0001411807,0.000064919805,0.000041360763,0.00030063777,0.00001813915,0.0003391214,0.000045931956,0.00005446807,2.1708486e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039356102,0.007336198,0.09983567,0.0005413764,0.00023589664,0.000037097536,0.044821855,0.0023546398,0.001825898,0.15057018,0.04460578,0.64779603],"study_design_scores_gemma":[0.00023105876,0.0014243356,0.00661684,0.000038064165,0.000017377306,0.0000088613515,0.00032300616,0.9752208,0.0029066377,0.013107131,0.000013521162,0.00009239555],"about_ca_topic_score_codex":0.00008432803,"about_ca_topic_score_gemma":0.000019338653,"teacher_disagreement_score":0.9728661,"about_ca_system_score_codex":0.00002398915,"about_ca_system_score_gemma":0.0001147485,"threshold_uncertainty_score":0.26473528},"labels":[],"label_agreement":null},{"id":"W4400266862","doi":"10.1145/3643991.3649106","title":"Mining Our Way Back to Incremental Builds for DevOps Pipelines","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"DevOps; Computer science; Pipeline transport; Pipeline (software); Data science; Software engineering; Engineering; Software deployment; Programming language","score_opus":0.044570625776325916,"score_gpt":0.3248629375192195,"score_spread":0.2802923117428936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400266862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049365726,0.00008647813,0.97822726,0.004185166,0.0005421557,0.00018814216,0.0000022807274,0.010683492,0.0011484703],"genre_scores_gemma":[0.28421757,7.147765e-7,0.71318704,0.0010362964,0.0001528215,0.00003596144,0.0000017140848,0.00001126139,0.0013565928],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990934,0.000012619242,0.0001629786,0.00035987925,0.00013709874,0.0002340147],"domain_scores_gemma":[0.9993395,0.00021764588,0.000014169051,0.00028924283,0.00005736628,0.000082031234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034589935,0.00011328149,0.00010050559,0.00012976665,0.000068988484,0.00030973332,0.00050164864,0.000038987997,0.000008356857],"category_scores_gemma":[0.00020231282,0.00009319211,0.0000547342,0.00032827575,0.0000051666143,0.00021582376,0.000257046,0.000047119076,0.00013139332],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000235896,0.0000146391885,0.00061398745,0.000038807564,0.000008413698,0.000006789369,0.00033793345,0.000008326794,0.0005778037,0.005199582,0.8834525,0.1097389],"study_design_scores_gemma":[0.00047186416,0.0009470021,0.00084589975,0.00089757604,0.000026410375,0.00013838834,0.00014635338,0.65057254,0.045911584,0.059517324,0.2391796,0.0013454971],"about_ca_topic_score_codex":0.000058152906,"about_ca_topic_score_gemma":0.00000976806,"teacher_disagreement_score":0.6505642,"about_ca_system_score_codex":0.000033921704,"about_ca_system_score_gemma":0.00003985847,"threshold_uncertainty_score":0.3800264},"labels":[],"label_agreement":null},{"id":"W4400484320","doi":"10.1145/3663529.3664459","title":"Enhancing Code Representation for Improved Graph Neural Network-Based Fault Localization","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Graph; Representation (politics); Artificial neural network; Code (set theory); Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.027174466698568107,"score_gpt":0.3059534606372797,"score_spread":0.2787789939387116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400484320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027008652,0.00011216427,0.98146284,0.00079402426,0.00052307954,0.00026797174,0.0000016513727,0.016472999,0.00009521498],"genre_scores_gemma":[0.41729513,0.0000022224297,0.58122855,0.0010579986,0.00014879035,0.000088938454,0.00002359984,0.000016266955,0.00013851527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908113,0.000033261662,0.0001963497,0.00037281172,0.00010256392,0.00021386464],"domain_scores_gemma":[0.99897635,0.00053195923,0.000038642105,0.00031131424,0.000100264755,0.000041466054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031703003,0.000099184996,0.00009241362,0.00009720893,0.00012190867,0.0003210497,0.00025118765,0.00005076575,0.0000029363193],"category_scores_gemma":[0.00019987387,0.00008734804,0.00006994895,0.000572662,0.000017074557,0.0002837014,0.000048303566,0.000062921834,0.0000030379451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043306234,0.000094368326,0.0025309608,0.00037915196,0.0000554895,0.000020112937,0.0006723846,0.14970148,0.0063073896,0.04985707,0.34321275,0.44712552],"study_design_scores_gemma":[0.00008484192,0.00007034642,0.00003660968,0.00005552136,0.000005782413,0.0000033288059,0.0000010117811,0.9372782,0.008966022,0.052589804,0.00079902663,0.00010950883],"about_ca_topic_score_codex":0.00007448536,"about_ca_topic_score_gemma":0.000030920477,"teacher_disagreement_score":0.78757674,"about_ca_system_score_codex":0.000025393356,"about_ca_system_score_gemma":0.00004909519,"threshold_uncertainty_score":0.35619497},"labels":[],"label_agreement":null},{"id":"W4400484351","doi":"10.1145/3663529.3663804","title":"ATheNA-S: A Testing Tool for Simulink Models Driven by Software Requirements and Domain Expertise","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Software engineering; Software testing; Domain (mathematical analysis); Software; Programming language","score_opus":0.05609008688266483,"score_gpt":0.29812934737171304,"score_spread":0.24203926048904822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400484351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007322642,0.00069991464,0.9741086,0.00038136545,0.00011460379,0.0003292015,0.000008415857,0.016857633,0.00017763709],"genre_scores_gemma":[0.2059244,0.0000063096486,0.7932374,0.00043181522,0.00004495733,0.00012926754,0.000003257376,0.000022143942,0.00020047271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986624,0.000025319345,0.0002375012,0.00056606776,0.00019333909,0.00031537632],"domain_scores_gemma":[0.99841446,0.0010133624,0.000026128588,0.00038472965,0.000080415346,0.00008089904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033899324,0.00017641972,0.00015418901,0.00008454425,0.00016128975,0.0004487777,0.0004190954,0.00006975388,0.000002040913],"category_scores_gemma":[0.0005251357,0.00014875043,0.000049371283,0.00024410748,0.00003902696,0.0006424625,0.00027983848,0.000085219224,0.0000044822987],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001188322,0.00011159022,0.0025475582,0.00034390503,0.000066171284,0.000055110133,0.0040706,0.00048442066,0.0030175878,0.015888978,0.16016188,0.8132403],"study_design_scores_gemma":[0.00014170268,0.00011870779,0.000008782969,0.00021798656,0.0000050235008,0.000016427548,0.0000036512613,0.75213027,0.00040989107,0.24580492,0.00092969264,0.00021293123],"about_ca_topic_score_codex":0.000033447468,"about_ca_topic_score_gemma":6.5865987e-7,"teacher_disagreement_score":0.8130274,"about_ca_system_score_codex":0.000052889696,"about_ca_system_score_gemma":0.000053168067,"threshold_uncertainty_score":0.6065867},"labels":[],"label_agreement":null},{"id":"W4400484638","doi":"10.1145/3663529.3663780","title":"AutoOffAB: Toward Automated Offline A/B Testing for Data-Driven Requirement Engineering","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"","keywords":"Computer science; Software engineering; Reliability engineering; Engineering","score_opus":0.12448711876038791,"score_gpt":0.3383702706052155,"score_spread":0.2138831518448276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400484638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020542696,0.00015554966,0.87073976,0.00084842875,0.00046207142,0.0002121236,0.000011909589,0.12708399,0.0002807461],"genre_scores_gemma":[0.14306383,0.0000011667355,0.8564576,0.00013748925,0.00011935794,0.00004263322,0.000027261123,0.00002376489,0.00012690286],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857336,0.000011909563,0.0002853942,0.00059837033,0.00020281968,0.00032813667],"domain_scores_gemma":[0.9980629,0.000822756,0.00003460133,0.00090871577,0.0000953413,0.0000756666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059422135,0.00016602155,0.000155395,0.0001547344,0.000067850626,0.00042259725,0.0012436131,0.000052674575,0.000003985668],"category_scores_gemma":[0.0011252532,0.00014411706,0.00003921674,0.0005346096,0.000012678862,0.00054855744,0.00069287745,0.00010143284,0.000022207054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037950829,0.00009512084,0.0005969604,0.0008574099,0.00013066854,0.00012736006,0.0005225373,0.004585214,0.0047323373,0.040059872,0.6162087,0.33208007],"study_design_scores_gemma":[0.00006755873,0.000091791684,0.000098490505,0.00022531432,0.00001030838,0.000030342724,6.4989587e-7,0.98818773,0.0005347246,0.0025003506,0.008055783,0.0001969673],"about_ca_topic_score_codex":0.00005989106,"about_ca_topic_score_gemma":8.0415e-7,"teacher_disagreement_score":0.9836025,"about_ca_system_score_codex":0.00006343104,"about_ca_system_score_gemma":0.00011723172,"threshold_uncertainty_score":0.5876923},"labels":[],"label_agreement":null},{"id":"W4400485045","doi":"10.1145/3664646.3664772","title":"Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reliability (semiconductor); Computer science; Code (set theory); Chain (unit); Reliability engineering; Risk analysis (engineering); Programming language; Business; Engineering","score_opus":0.012576388123733047,"score_gpt":0.26814752903102007,"score_spread":0.255571140907287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400485045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032380454,0.00016141262,0.9609082,0.0023172195,0.00017473556,0.00020661946,0.00002283579,0.003636967,0.00019158458],"genre_scores_gemma":[0.8263441,0.000004064595,0.17328915,0.00010355813,0.000010785862,0.00003205228,0.0000044150734,0.0000046422374,0.00020728384],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999248,0.00006623345,0.00021975803,0.0002384383,0.00013515928,0.00009238466],"domain_scores_gemma":[0.9988885,0.00025472773,0.000042555523,0.0006129512,0.00016976935,0.000031515152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060461136,0.000064887994,0.00008854782,0.000052584648,0.000038893388,0.000038062586,0.00041942962,0.00003741638,0.0000050161234],"category_scores_gemma":[0.0005261008,0.00004271772,0.0000317914,0.0005896968,0.00004648231,0.00008247874,0.00008286112,0.00006875914,0.0000049935848],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010702239,0.00022419413,0.0010009136,0.00014280678,0.000028930232,0.0000012669508,0.0019694362,0.0008529021,0.4939511,0.061869595,0.36407813,0.07586999],"study_design_scores_gemma":[0.000048852427,0.0002035301,0.0014273264,0.000068653404,0.000008405085,0.000002093201,0.0000060168563,0.5264503,0.44463664,0.023804761,0.0032052794,0.00013819935],"about_ca_topic_score_codex":0.00053831306,"about_ca_topic_score_gemma":0.000004198278,"teacher_disagreement_score":0.7939636,"about_ca_system_score_codex":0.000024592035,"about_ca_system_score_gemma":0.000066590794,"threshold_uncertainty_score":0.1741978},"labels":[],"label_agreement":null},{"id":"W4400499041","doi":"10.1007/978-3-031-64171-8_18","title":"Pairing Security Advisories with Vulnerable Functions Using Open-Source LLMs","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Computer science; Pairing; Open source; Computer security; Programming language; Physics; Software","score_opus":0.026368676353523822,"score_gpt":0.26663719090995813,"score_spread":0.2402685145564343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400499041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015910564,0.00059315306,0.9876259,0.00036639333,0.0012259404,0.0004150713,0.000004642871,0.004953212,0.004656612],"genre_scores_gemma":[0.16865754,0.000011097148,0.8285397,0.00075677474,0.00042454022,0.00002286585,0.0000040575696,0.000086026856,0.0014973576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961433,0.00004339857,0.00042771857,0.0018503413,0.00083262846,0.0007026037],"domain_scores_gemma":[0.9969488,0.0007373893,0.00021968018,0.001647123,0.00027316395,0.00017385058],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013318883,0.0006004448,0.0005484895,0.0007868899,0.0007759135,0.0025334323,0.003919101,0.00026028565,0.000012075385],"category_scores_gemma":[0.00015562335,0.0004993553,0.000093979885,0.001152281,0.0006653795,0.001042261,0.0035551921,0.0014654812,0.000031030624],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025531785,0.00009237865,0.0010118001,0.0003318955,0.0000810043,0.00051258074,0.00461648,0.17985407,0.00006527019,0.038963746,0.0010436889,0.77340156],"study_design_scores_gemma":[0.00011974908,0.0001977979,0.000010336558,0.0014694717,0.000017861721,0.000311703,2.2693206e-7,0.510521,0.0003420677,0.4833338,0.0029915697,0.000684401],"about_ca_topic_score_codex":0.00029241526,"about_ca_topic_score_gemma":0.000098989985,"teacher_disagreement_score":0.7727172,"about_ca_system_score_codex":0.0003673792,"about_ca_system_score_gemma":0.00072699145,"threshold_uncertainty_score":0.9997458},"labels":[],"label_agreement":null},{"id":"W4400499064","doi":"10.1007/978-3-031-64171-8_5","title":"Modularizing Directed Greybox Fuzzing for Binaries over Multiple CPU Architectures","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Fuzz testing; Computer science; Programming language; Operating system; Parallel computing; Software","score_opus":0.022033722642859514,"score_gpt":0.26275811713292646,"score_spread":0.24072439449006694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400499064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017883716,0.0013725429,0.98418987,0.00056993234,0.00225079,0.0006868902,0.000016624204,0.010036278,0.0006982653],"genre_scores_gemma":[0.21590504,0.000011770768,0.7821957,0.00077965076,0.0005876163,0.000053766318,0.000009343342,0.00008768655,0.00036944263],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954625,0.000028576394,0.00058649713,0.0021273354,0.00086786924,0.0009272516],"domain_scores_gemma":[0.9952256,0.0025430797,0.0002537925,0.0015366732,0.00026660255,0.00017421528],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00095217745,0.0007550332,0.0006752924,0.0014133004,0.00047535976,0.0013361865,0.0030500942,0.00041146355,0.0000041359835],"category_scores_gemma":[0.0008913472,0.0006708308,0.00027053786,0.0008127369,0.0006448323,0.00030766716,0.0018113843,0.00102707,0.000013286366],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022455743,0.000045126457,0.00066571863,0.00033371625,0.00005725818,0.00018458269,0.0022660748,0.026586164,0.0004456859,0.025589349,0.0005829662,0.9432209],"study_design_scores_gemma":[0.0001226253,0.00010978819,0.00010195904,0.00076859136,0.000010842466,0.000052688465,2.4774817e-8,0.48480445,0.0009143779,0.51140743,0.0011789704,0.00052825897],"about_ca_topic_score_codex":0.00009089639,"about_ca_topic_score_gemma":0.000067170724,"teacher_disagreement_score":0.94269264,"about_ca_system_score_codex":0.000296644,"about_ca_system_score_gemma":0.00039735303,"threshold_uncertainty_score":0.99970055},"labels":[],"label_agreement":null},{"id":"W4400582740","doi":"10.1145/3643759","title":"Understanding and Detecting Annotation-Induced Faults of Static Analyzers","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence","score_opus":0.05424952230509408,"score_gpt":0.25652039502094065,"score_spread":0.20227087271584657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71253705,0.00016105373,0.2813063,0.00037567885,0.00032418594,0.00020219108,0.0000037565899,0.0050496133,0.000040210565],"genre_scores_gemma":[0.81972224,0.0000036669683,0.18020669,0.000021320913,0.000016252006,0.0000075035737,1.4335247e-7,0.000016797969,0.0000054247475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990235,0.0000037166355,0.00024297155,0.0002707667,0.00028279005,0.00017627455],"domain_scores_gemma":[0.99868834,0.00073930336,0.00011205148,0.0003133069,0.000102751255,0.000044223503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036725475,0.00014663323,0.00017408421,0.0002653476,0.000061551524,0.000082571605,0.0009067489,0.00005312228,5.5340513e-7],"category_scores_gemma":[0.005813382,0.00011516182,0.00006311793,0.0007721891,0.000030222312,0.00026519733,0.00039893264,0.00018951348,4.946142e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014641382,0.0004489607,0.23882113,0.028307844,0.0013364188,0.000048674123,0.049691744,0.012731254,0.18484172,0.2829949,0.03413437,0.16649657],"study_design_scores_gemma":[0.00068152405,0.0009246173,0.023599628,0.008466234,0.00014830672,0.00013806908,0.00029657412,0.5341299,0.25423193,0.1759917,0.00013447549,0.0012570078],"about_ca_topic_score_codex":0.000013385014,"about_ca_topic_score_gemma":2.0551543e-7,"teacher_disagreement_score":0.52139866,"about_ca_system_score_codex":0.00007372833,"about_ca_system_score_gemma":0.000027708871,"threshold_uncertainty_score":0.69595814},"labels":[],"label_agreement":null},{"id":"W4400978763","doi":"10.1109/tse.2024.3433463","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Oracle; Test (biology); Artificial neural network; Machine learning; Artificial intelligence; Data mining; Software engineering","score_opus":0.0715888736640746,"score_gpt":0.32531120179375506,"score_spread":0.25372232812968043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400978763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003105365,0.00030902843,0.9794731,0.000078010504,0.0020418623,0.0002934086,0.000008906988,0.014684932,0.000005374083],"genre_scores_gemma":[0.5750729,0.00000365502,0.4245925,0.000031223786,0.000101538484,0.0001509139,0.0000037805685,0.000024902834,0.000018614348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987964,0.000022430168,0.00021738272,0.00039595301,0.00033649086,0.0002313533],"domain_scores_gemma":[0.9980827,0.0013473534,0.000028168164,0.00031817862,0.00016090884,0.000062721876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006126131,0.00017194798,0.000121821635,0.0004755925,0.00018280649,0.00073445967,0.00023340489,0.000084829,0.000005203648],"category_scores_gemma":[0.0004818787,0.00017889346,0.00010368009,0.00093729846,0.00000833983,0.0009988125,0.0000023201233,0.0002104141,0.0000087527615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.27718e-7,0.00005045619,0.000023131533,0.0000825326,0.000021017193,0.000005230546,0.00013738555,0.35680225,0.0014821737,0.00013341749,0.0010508839,0.6402107],"study_design_scores_gemma":[0.00009620027,0.00007930615,0.00005396589,0.00008893503,0.00003259746,0.000021882206,0.0000012757529,0.9847773,0.014074741,0.00023735253,0.0003389926,0.00019745145],"about_ca_topic_score_codex":0.000007298679,"about_ca_topic_score_gemma":9.716007e-7,"teacher_disagreement_score":0.6400132,"about_ca_system_score_codex":0.00018641345,"about_ca_system_score_gemma":0.000086413595,"threshold_uncertainty_score":0.7295064},"labels":[],"label_agreement":null},{"id":"W4401047823","doi":"10.1145/3680468","title":"Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Evolutionary algorithm; Population; Evolutionary robotics; Domain knowledge","score_opus":0.12685296961192286,"score_gpt":0.3405972594143513,"score_spread":0.21374428980242846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401047823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005557078,0.0007651869,0.9841644,0.000114898074,0.0011612342,0.00025181173,0.0000032651803,0.012969781,0.000013670252],"genre_scores_gemma":[0.12530477,0.000034169225,0.87402195,0.000034994853,0.000057570946,0.00021064004,0.000004288781,0.000025862713,0.0003057269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874574,0.00009632128,0.00026722605,0.0003901248,0.00013619485,0.0003643716],"domain_scores_gemma":[0.99042857,0.008982731,0.00002805123,0.00036815138,0.00009480803,0.00009767777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010293993,0.00018742544,0.00022298915,0.00040548368,0.00024309436,0.00013840354,0.00033036174,0.00013413673,0.000001707372],"category_scores_gemma":[0.002859866,0.00018461476,0.00006940481,0.00041270687,0.000031423748,0.00021954626,0.000031198302,0.0004037939,0.000004841588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011226152,0.000014446324,0.000120845194,0.0005860868,0.000081410595,0.000013806776,0.0008091304,0.6531241,0.00018037256,0.004245945,0.00031830807,0.3404943],"study_design_scores_gemma":[0.00015737278,0.0004478839,0.00017432695,0.00032313645,0.000025011956,0.0002834617,0.000016700613,0.98969346,0.00046891067,0.0011589122,0.0069838753,0.00026694758],"about_ca_topic_score_codex":0.00006891335,"about_ca_topic_score_gemma":2.3601935e-7,"teacher_disagreement_score":0.34022737,"about_ca_system_score_codex":0.000114439106,"about_ca_system_score_gemma":0.0001509167,"threshold_uncertainty_score":0.7528372},"labels":[],"label_agreement":null},{"id":"W4401073387","doi":"10.1109/tse.2024.3435067","title":"Mitigating the Uncertainty and Imprecision of Log-Based Code Coverage Without Requiring Additional Logging Statements","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"","keywords":"Computer science; Logging; Code (set theory); Programming language; Data mining; Set (abstract data type)","score_opus":0.019196045384707247,"score_gpt":0.28167165167033514,"score_spread":0.2624756062856279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401073387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009060855,0.000118925964,0.98536205,0.00007226511,0.00041738682,0.00014499534,0.00019504208,0.0046216804,0.000006793986],"genre_scores_gemma":[0.8158635,0.000009679625,0.18394122,0.000060279763,0.000024209561,0.000055051478,0.0000076124597,0.000023655048,0.000014795584],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987743,0.000034357774,0.00029154806,0.0003474637,0.0003170153,0.00023530329],"domain_scores_gemma":[0.997576,0.0019189835,0.000053864846,0.00033079227,0.00005702713,0.00006331976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003677355,0.00018779808,0.00016218319,0.0002155732,0.00018612955,0.00015707385,0.00028563416,0.00005985568,0.000026583082],"category_scores_gemma":[0.000121002035,0.0001559849,0.00008036031,0.00033439932,0.00004908332,0.00036580313,0.0000082058705,0.00032484147,0.0000033652973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011819488,0.000044212877,0.00014804206,0.0003106533,0.00007234054,0.00002349653,0.00045781423,0.8792587,0.00097469677,0.00027840465,0.001014178,0.117405646],"study_design_scores_gemma":[0.0001765716,0.00008882172,0.00014560364,0.0012984881,0.0000178856,0.000028284598,0.000004677283,0.9890104,0.00730101,0.0011678318,0.0005419553,0.00021846655],"about_ca_topic_score_codex":0.000026392494,"about_ca_topic_score_gemma":0.0000022196375,"teacher_disagreement_score":0.80680263,"about_ca_system_score_codex":0.00008602475,"about_ca_system_score_gemma":0.000071049915,"threshold_uncertainty_score":0.63608795},"labels":[],"label_agreement":null},{"id":"W4401172336","doi":"10.1007/978-3-031-47821-5_15","title":"Model Acceptance Testing","year":2024,"lang":"en","type":"book-chapter","venue":"CIGRE green books","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Opal-Rt Technologies (Canada)","funders":"","keywords":"Acceptance testing; Psychology; Computer science; Software engineering","score_opus":0.07991491499171106,"score_gpt":0.26715256573564944,"score_spread":0.1872376507439384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401172336","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027120866,0.0014305915,0.17076227,0.00020822918,0.00034362052,0.00021280545,0.000017541988,0.024868887,0.80215335],"genre_scores_gemma":[0.0014732889,0.000011565017,0.23393309,0.0005594873,0.00033813517,0.000023636518,0.0000053883405,0.0001178354,0.7635376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976252,0.000007772853,0.00042507908,0.0010477848,0.00047307354,0.00042111415],"domain_scores_gemma":[0.9976248,0.00028309412,0.00021895261,0.0015212453,0.00019709574,0.00015481515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025376375,0.000545739,0.0004421514,0.00028467897,0.00015663564,0.00031935604,0.0018058174,0.00039885077,0.00001960329],"category_scores_gemma":[0.000084930274,0.00053973484,0.0002056058,0.000069739894,0.000114108465,0.00020438897,0.0010134947,0.0008483757,0.0005324885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018135183,0.000006328891,0.000032316482,0.00019300554,0.000051340874,0.00032976235,0.00022209673,0.00004487652,0.0000142429835,0.65213406,0.067924336,0.27904582],"study_design_scores_gemma":[0.00004164715,0.000045825993,0.0000043973823,0.0008888592,0.000031135365,0.00008828842,1.7870687e-7,0.17099658,0.000015548481,0.8008808,0.026450763,0.0005560039],"about_ca_topic_score_codex":0.00004666371,"about_ca_topic_score_gemma":0.0000118613525,"teacher_disagreement_score":0.27848983,"about_ca_system_score_codex":0.00012234306,"about_ca_system_score_gemma":0.0002284245,"threshold_uncertainty_score":0.99970543},"labels":[],"label_agreement":null},{"id":"W4401420422","doi":"10.1145/3643656.3643899","title":"Predicting the Lifetime of Flaky Tests on Chrome","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Materials science; Reliability engineering; Computer science; Engineering","score_opus":0.016369370122478938,"score_gpt":0.2733729501834212,"score_spread":0.25700358006094226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401420422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10448017,0.0010824761,0.7235981,0.009873088,0.0014862545,0.00045798335,0.000004565573,0.0880594,0.07095794],"genre_scores_gemma":[0.95829237,0.0000028542554,0.040851396,0.00030512892,0.00007434401,0.000007957429,2.3545627e-7,0.000006451497,0.00045924113],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993542,0.000024444025,0.00012455226,0.00019183257,0.000185681,0.00011930728],"domain_scores_gemma":[0.9985584,0.00093265873,0.0000230086,0.0004327447,0.000028240225,0.000024922121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003619275,0.00006843424,0.00006882948,0.00006649616,0.000054200587,0.00010335553,0.00054500176,0.000027007538,0.000009939197],"category_scores_gemma":[0.00028294142,0.00003919921,0.000039154154,0.00034348466,0.000034321827,0.00009702702,0.00015198918,0.00011009317,0.000047525657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005835426,0.00016794742,0.025968518,0.0002475338,0.00008690342,0.0001029499,0.004198062,0.00021884489,0.0024177271,0.20548785,0.38465944,0.37643838],"study_design_scores_gemma":[0.00012864669,0.00082000036,0.027821194,0.0012279977,0.000018266197,0.0001478553,0.000010394078,0.7733008,0.020962533,0.16768107,0.007477054,0.00040416353],"about_ca_topic_score_codex":0.00006031442,"about_ca_topic_score_gemma":0.0000011004054,"teacher_disagreement_score":0.8538122,"about_ca_system_score_codex":0.000012535968,"about_ca_system_score_gemma":0.000042322037,"threshold_uncertainty_score":0.15984975},"labels":[],"label_agreement":null},{"id":"W4401543513","doi":"10.1145/3643991.3645072","title":"Analyzing Developer Use of ChatGPT Generated Code in Open Source GitHub Projects","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Open source; Source code; Code (set theory); Programming language; Open source software; Code review; Software engineering; World Wide Web; Static program analysis; Software; Software development; Set (abstract data type)","score_opus":0.0982006071357781,"score_gpt":0.3196408188539973,"score_spread":0.2214402117182192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401543513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06085172,0.00019270659,0.9310867,0.00038975003,0.000105087354,0.00026024383,0.0000013393122,0.006374544,0.000737875],"genre_scores_gemma":[0.47156042,0.000007586821,0.5271007,0.00017604415,0.000011967365,0.0000203689,0.0000016899178,0.000012003544,0.0011092481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899185,0.000060022878,0.0002420112,0.0003840199,0.00012564418,0.00019643924],"domain_scores_gemma":[0.99921006,0.00024226708,0.00003476014,0.0003953244,0.000079708225,0.000037896792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048576208,0.0001092125,0.00016712402,0.0002875473,0.000036339432,0.0006356419,0.0008416256,0.000050299288,0.000007566259],"category_scores_gemma":[0.0002629618,0.000087061664,0.000024883511,0.0013415157,0.000023557583,0.0007078091,0.0007053817,0.000109694345,0.000011090881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021826874,0.00027637326,0.16390987,0.00028477638,0.00012059851,0.00032775322,0.0098493025,0.0018077318,0.0048501454,0.03053304,0.15763448,0.6303841],"study_design_scores_gemma":[0.00018978544,0.00008926373,0.0051214932,0.00068167446,0.000007022544,0.00004799952,0.000010841062,0.95117474,0.023555184,0.004347918,0.014329944,0.00044411203],"about_ca_topic_score_codex":0.0014928911,"about_ca_topic_score_gemma":0.00012708973,"teacher_disagreement_score":0.94936705,"about_ca_system_score_codex":0.000044517354,"about_ca_system_score_gemma":0.00023393269,"threshold_uncertainty_score":0.6129509},"labels":[],"label_agreement":null},{"id":"W4401544398","doi":"10.1145/3643991.3644930","title":"Automating GUI-based Test Oracles for Mobile Apps","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Computer science; Mobile apps; Test (biology); World Wide Web","score_opus":0.01853026080516836,"score_gpt":0.30211460840373283,"score_spread":0.2835843475985645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401544398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010456927,0.00023697903,0.940987,0.00042785896,0.00018323286,0.00022992934,0.0000033218553,0.055759557,0.0011264283],"genre_scores_gemma":[0.34867284,5.7020105e-7,0.65059733,0.00027151083,0.0000536898,0.00017535678,0.0000021092,0.000011549631,0.00021504471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918073,0.00001176485,0.00016044876,0.00031771808,0.00012592792,0.00020340711],"domain_scores_gemma":[0.99743897,0.0020536259,0.000024497604,0.00037111738,0.00006633756,0.00004545403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003665585,0.00010302649,0.00009446352,0.00010567338,0.00010279619,0.00039591105,0.00046472077,0.000042218926,0.000010489971],"category_scores_gemma":[0.0005821147,0.00008346888,0.00006445989,0.0003194501,0.000020410529,0.00018154032,0.00009028775,0.00006315821,0.000041966803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.010828e-7,0.00007989461,0.0017701982,0.00025267043,0.000009065585,0.000018662244,0.00023226827,0.00015998872,0.0007007907,0.017597485,0.19332276,0.7858553],"study_design_scores_gemma":[0.00005702667,0.0001420973,0.000115418254,0.00017050728,0.0000035860887,0.000009352327,0.0000022744175,0.9578847,0.004925172,0.028098065,0.008441507,0.00015025318],"about_ca_topic_score_codex":0.000027573518,"about_ca_topic_score_gemma":0.0000015028292,"teacher_disagreement_score":0.95772475,"about_ca_system_score_codex":0.000027097194,"about_ca_system_score_gemma":0.00009253184,"threshold_uncertainty_score":0.38177794},"labels":[],"label_agreement":null},{"id":"W4401632577","doi":"10.22215/etd/2024-16009","title":"Multilingual Fault Localization for Deep Learning Compilers","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Compiler; Codebase; Computer science; Deep learning; Programming language; Artificial intelligence; Software","score_opus":0.019550250925042846,"score_gpt":0.31594250928791834,"score_spread":0.29639225836287547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401632577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074910105,0.00043994247,0.9700778,0.000032993816,0.0013741682,0.00033568835,0.0000013833916,0.023556145,0.0034327414],"genre_scores_gemma":[0.25185755,0.000052040654,0.7152812,0.00036388848,0.00040609392,0.0003199843,0.0018613758,0.00015867838,0.029699178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864817,0.00003092702,0.0002831566,0.0005612256,0.00023739884,0.00023910754],"domain_scores_gemma":[0.99890226,0.00037403326,0.00012454708,0.00028712518,0.00025691898,0.000055088505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025420135,0.00023900213,0.00022298883,0.00023899256,0.00018184543,0.0003260092,0.000524717,0.00025351977,0.0000075182847],"category_scores_gemma":[0.00056246546,0.00022525343,0.00012645865,0.00029571264,0.000012514631,0.00011998094,0.000054524193,0.00030739428,0.000043022315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026727634,0.000062868516,0.00020294271,0.0010805287,0.000078539684,0.000018449315,0.008662705,0.004989113,0.0000660511,0.009501232,0.04990277,0.92540807],"study_design_scores_gemma":[0.00010602961,0.000102174316,0.00003310511,0.000313286,0.000027499907,0.0000046327073,0.00011140794,0.9652055,0.0017603814,0.02168567,0.010296427,0.00035388547],"about_ca_topic_score_codex":0.000073731775,"about_ca_topic_score_gemma":0.000070790695,"teacher_disagreement_score":0.9602164,"about_ca_system_score_codex":0.0000544224,"about_ca_system_score_gemma":0.00008747028,"threshold_uncertainty_score":0.9185568},"labels":[],"label_agreement":null},{"id":"W4401724691","doi":"10.1145/3688842","title":"My Fuzzers Won’t Build: An Empirical Study of Fuzzing Build Failures","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Software engineering; Software bug; Context (archaeology); Software; Set (abstract data type); Operating system; Programming language","score_opus":0.09234755339412065,"score_gpt":0.36974165303234796,"score_spread":0.2773940996382273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401724691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10270327,0.00036559044,0.88809365,0.00029208596,0.00058175216,0.00014873008,0.0000037579114,0.0078088455,0.0000023291545],"genre_scores_gemma":[0.4357216,0.000014023222,0.56412226,0.000043239765,0.000027010363,0.00003465624,6.8713945e-7,0.000020637448,0.000015887801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825394,0.000360489,0.0002828536,0.0006057197,0.00019039321,0.00030660746],"domain_scores_gemma":[0.9944891,0.0044657914,0.000037694965,0.0008215825,0.000053835673,0.0001320173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011969456,0.00024235119,0.00035768753,0.0005427864,0.00013757848,0.0000852885,0.000594044,0.00015883228,0.00000523212],"category_scores_gemma":[0.001060373,0.0002280647,0.00008090747,0.0005916672,0.00004892909,0.00025973274,0.000040368195,0.00055225036,0.0000026453713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043728294,0.0005913611,0.0038787564,0.0003255652,0.0003270332,0.00012337836,0.012316614,0.03363759,0.0011434406,0.00082007836,0.00053296186,0.9462595],"study_design_scores_gemma":[0.008248434,0.038473587,0.06312873,0.004005428,0.0021101625,0.0051155905,0.004831299,0.66131186,0.046831585,0.09532479,0.06015806,0.010460442],"about_ca_topic_score_codex":0.00012203223,"about_ca_topic_score_gemma":0.000006466406,"teacher_disagreement_score":0.93579906,"about_ca_system_score_codex":0.000033464978,"about_ca_system_score_gemma":0.000051095383,"threshold_uncertainty_score":0.93002087},"labels":[],"label_agreement":null},{"id":"W4401815668","doi":"10.1007/978-3-031-64136-7_5","title":"Verification and Validation of Quantum Software","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Universität Innsbruck","keywords":"Computer science; Software verification; Software engineering; Verification and validation; Software; Programming language; Software construction; Software development; Mathematics; Statistics","score_opus":0.02981192027902278,"score_gpt":0.2559897412367009,"score_spread":0.2261778209576781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401815668","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017483993,0.0006634833,0.8929622,0.00017138892,0.00022289512,0.00012660702,0.000006010744,0.009080014,0.09674993],"genre_scores_gemma":[0.023968687,0.00026003836,0.59745705,0.00013279401,0.00011951512,0.000018205057,0.000050274633,0.000073622956,0.3779198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992381,0.0000045480083,0.00020103494,0.0003187535,0.00017005048,0.0000675463],"domain_scores_gemma":[0.9991696,0.00014351837,0.00010992707,0.0004569441,0.00009139209,0.000028618791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015760462,0.00013313798,0.00015400452,0.00015689047,0.000025200436,0.00007244484,0.000258276,0.0001392732,0.000013511785],"category_scores_gemma":[0.00006498432,0.00012008333,0.00004212977,0.00003609478,0.00004084031,0.000099339355,0.00015626987,0.0001176125,0.00003491759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.5674025e-7,0.0000027791814,0.000019328874,0.00009554515,0.000009783645,0.000002341275,0.000061304396,7.43073e-7,0.000010679847,0.96643955,0.009125697,0.024231713],"study_design_scores_gemma":[0.000021489157,0.00005380974,0.000020858453,0.0002894852,0.000016197133,0.0000143016405,2.6218737e-7,0.0041132597,0.0007356078,0.98358816,0.010988654,0.00015789346],"about_ca_topic_score_codex":0.000016773876,"about_ca_topic_score_gemma":2.450006e-7,"teacher_disagreement_score":0.29550514,"about_ca_system_score_codex":0.000017751052,"about_ca_system_score_gemma":0.000036471836,"threshold_uncertainty_score":0.48968562},"labels":[],"label_agreement":null},{"id":"W4401905737","doi":"10.1109/icst60714.2024.00052","title":"MOTIF: A tool for Mutation Testing with Fuzzing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Université du Luxembourg; Entomological Society of America","keywords":"Fuzz testing; Computer science; Mutation testing; Software testing; Programming language; Mutation; Genetics; Biology; Software","score_opus":0.033953021041505084,"score_gpt":0.2770897851717789,"score_spread":0.24313676413027382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401905737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036901615,0.000047686146,0.9708073,0.0003487424,0.00008547313,0.00014022061,4.5068163e-7,0.023642462,0.0012374826],"genre_scores_gemma":[0.37646005,9.745546e-8,0.6232245,0.00010027412,0.00003198234,0.000035566107,6.270431e-7,0.0000065108584,0.0001404282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994238,0.000007832673,0.00008944763,0.00024176024,0.00009805262,0.00013907718],"domain_scores_gemma":[0.99887335,0.00083648704,0.00001659502,0.0001780934,0.000074881435,0.000020601425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023944603,0.00006928773,0.00005571531,0.000076073135,0.00007619626,0.00034399025,0.00018310088,0.00002047436,0.0000011147054],"category_scores_gemma":[0.00036492964,0.000050624854,0.000019018764,0.00036165238,0.00001039215,0.0002921711,0.000041615614,0.00004787142,0.000008597032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027787812,0.000017216866,0.0017911434,0.00014865476,0.0000149599455,0.000059973354,0.0005511354,0.00019895268,0.00035387333,0.050673317,0.012940566,0.93324745],"study_design_scores_gemma":[0.00007162719,0.0001948209,0.0004125485,0.0002349784,0.0000059308354,0.00014015696,0.0000028762204,0.9017503,0.0015509133,0.0948734,0.00060996966,0.00015246232],"about_ca_topic_score_codex":0.000027117996,"about_ca_topic_score_gemma":0.0000012339434,"teacher_disagreement_score":0.933095,"about_ca_system_score_codex":0.000020214862,"about_ca_system_score_gemma":0.000056684225,"threshold_uncertainty_score":0.3317106},"labels":[],"label_agreement":null},{"id":"W4401905742","doi":"10.1109/icst60714.2024.00055","title":"Insights into System Failures: ML-Assisted Testing and Failure Models for Cyber-Physical Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cyber-physical system; Computer science; Reliability engineering; System testing; Engineering; Software engineering; Operating system","score_opus":0.03310137089038518,"score_gpt":0.26533859974567836,"score_spread":0.2322372288552932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401905742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057543814,0.00076463475,0.96259165,0.00031551823,0.0003100596,0.00045787607,0.0000018352014,0.028764954,0.0010390788],"genre_scores_gemma":[0.6846511,6.022292e-7,0.31492043,0.000025762205,0.00013919517,0.00015151394,0.0000013957817,0.000020678068,0.00008938481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984313,0.000059711616,0.00028018202,0.00069112,0.00025739663,0.00028025883],"domain_scores_gemma":[0.9972541,0.0018736864,0.000056670448,0.0005023207,0.00018389765,0.00012932389],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002318244,0.00023965965,0.0002970899,0.00019774406,0.00023981689,0.0010522373,0.0004927298,0.00010442737,9.346442e-8],"category_scores_gemma":[0.00023207479,0.0001812786,0.00007059734,0.0005712258,0.000045216853,0.00064363086,0.00024878615,0.00015144615,0.000007808254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000351778,0.000047396356,0.000064102096,0.002083043,0.000063111154,0.000070249545,0.0022871112,0.0007632181,0.0012099548,0.94050914,0.019338733,0.03356042],"study_design_scores_gemma":[0.00009070183,0.00011109053,0.000016403741,0.0009143918,0.000016496799,0.00010479858,0.000054512988,0.92905813,0.0001708403,0.068331905,0.0008885218,0.00024221548],"about_ca_topic_score_codex":0.0006082641,"about_ca_topic_score_gemma":0.000014387438,"teacher_disagreement_score":0.9282949,"about_ca_system_score_codex":0.00009596126,"about_ca_system_score_gemma":0.00009606444,"threshold_uncertainty_score":0.99998474},"labels":[],"label_agreement":null},{"id":"W4401907837","doi":"10.1109/icst60714.2024.00006","title":"Message from the Program Co-Chairs; ICST 2024","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Human–computer interaction","score_opus":0.024138685192223983,"score_gpt":0.31336838351121926,"score_spread":0.28922969831899525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401907837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011122961,0.0017302139,0.82497126,0.008186149,0.00121199,0.0003783827,0.00001308794,0.09561149,0.066785134],"genre_scores_gemma":[0.5246658,0.000027289005,0.46584377,0.0017256582,0.00034488624,0.0001396101,0.0000083389405,0.000025710095,0.0072189504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911267,0.000037792106,0.00011849981,0.00033518524,0.00020738905,0.00018844091],"domain_scores_gemma":[0.9985679,0.00073316763,0.000014555918,0.0006143909,0.00002425098,0.000045730052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030065814,0.00010636619,0.00007943223,0.0000338746,0.00010279936,0.0007552266,0.0008508944,0.000045319066,0.0000992581],"category_scores_gemma":[0.000093133654,0.00006139797,0.000059874503,0.00031385233,0.000049653117,0.00012992267,0.00021417045,0.00018375568,0.00023781424],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4283423e-7,0.00001921339,0.0005033064,0.0000052157898,0.000010908076,0.000033000044,0.00031074643,7.261922e-7,0.000011065416,0.020173263,0.7197039,0.25922832],"study_design_scores_gemma":[0.0000694271,0.0001296948,0.0011910667,0.00019418007,0.0000137743,0.000034012483,0.000014817398,0.1510949,0.0011533728,0.31573677,0.53004384,0.0003241165],"about_ca_topic_score_codex":0.0003740889,"about_ca_topic_score_gemma":0.0000141196815,"teacher_disagreement_score":0.5235535,"about_ca_system_score_codex":0.000017875405,"about_ca_system_score_gemma":0.000048761965,"threshold_uncertainty_score":0.7282667},"labels":[],"label_agreement":null},{"id":"W4401908463","doi":"10.1109/icst60714.2024.00039","title":"Are We Testing or Being Tested? Exploring the Practical Applications of Large Language Models in Software Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software testing; Software reliability testing; Software performance testing; Software engineering; System integration testing; Test strategy; Software; Programming language; Software construction; Software system","score_opus":0.15819021582175738,"score_gpt":0.35758823244720933,"score_spread":0.19939801662545195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401908463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049595963,0.00027021245,0.9811241,0.00095087837,0.00007045831,0.00031350716,0.000003564114,0.011130475,0.0011771859],"genre_scores_gemma":[0.48779753,0.000004267228,0.51172376,0.00011999014,0.000052100542,0.00022338914,5.5255623e-7,0.000017736602,0.00006068047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984089,0.000075357464,0.00038855622,0.00045890542,0.0002956624,0.0003726025],"domain_scores_gemma":[0.9903975,0.00860476,0.00013468438,0.00066023937,0.0001436828,0.00005911374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009463958,0.0001707074,0.0001928523,0.00022910576,0.00017019239,0.00024189816,0.0006486486,0.000053179014,0.0000035731541],"category_scores_gemma":[0.0043243333,0.0001132202,0.000042036612,0.0023081303,0.000041483465,0.0008136247,0.00047882902,0.00039111578,0.000007569341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000963005,0.00048208336,0.05810988,0.0012353803,0.000053086682,0.00086069305,0.012929866,0.003590662,0.0006226971,0.0972526,0.004571524,0.8202819],"study_design_scores_gemma":[0.00012138168,0.00006619739,0.0015935403,0.0019584747,0.000017440765,0.00024107036,0.0005027242,0.91714144,0.0010618222,0.07664268,0.0003082701,0.00034496997],"about_ca_topic_score_codex":0.00015713224,"about_ca_topic_score_gemma":0.000036449226,"teacher_disagreement_score":0.9135508,"about_ca_system_score_codex":0.000053978958,"about_ca_system_score_gemma":0.00015862215,"threshold_uncertainty_score":0.5176943},"labels":[],"label_agreement":null},{"id":"W4402034738","doi":"10.32920/26871409","title":"Transformer Models for Automated Bug Triaging and Duplicate Bug Detection","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Manitoba; Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Transformer; Engineering","score_opus":0.04005328244476049,"score_gpt":0.30055055257399427,"score_spread":0.2604972701292338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402034738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023542687,0.00041920092,0.91635776,0.00084419834,0.0005159105,0.00074877957,0.000010104804,0.07785709,0.00089269713],"genre_scores_gemma":[0.67130435,0.00004150199,0.3277138,0.00014855046,0.00007117712,0.0004536954,0.000006484434,0.000036481768,0.00022397294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982459,0.000029197927,0.0003456992,0.00089811167,0.00017403606,0.00030703322],"domain_scores_gemma":[0.9988405,0.0002727786,0.00008552811,0.00060554955,0.00010829254,0.00008732675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005802638,0.00030277495,0.00032118784,0.00029344732,0.00012706907,0.00055649003,0.00054202875,0.00026836008,0.0000010562433],"category_scores_gemma":[0.00006197382,0.00026460498,0.00014707167,0.00021685085,0.000033058008,0.00016279,0.0004929311,0.0004075641,0.0000056234194],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059989583,0.00011628027,0.000042144442,0.0029394075,0.0002911709,0.000022254739,0.0026816265,0.007860924,0.002196902,0.02261503,0.032811794,0.9283625],"study_design_scores_gemma":[0.00009951598,0.00003245179,0.000009217139,0.00014638573,0.000023562203,0.000018826588,8.876783e-7,0.59808254,0.002974558,0.39827126,0.00013771158,0.00020309021],"about_ca_topic_score_codex":0.0002654327,"about_ca_topic_score_gemma":0.000010204974,"teacher_disagreement_score":0.92815936,"about_ca_system_score_codex":0.00006544673,"about_ca_system_score_gemma":0.00009526544,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W4402048137","doi":"10.1145/3690631","title":"T-Rec: Fine-Grained Language-Agnostic Program Reduction Guided by Lexical Syntax","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Syntax; Programming language; Reduction (mathematics); Natural language processing; Abstract syntax tree; Artificial intelligence","score_opus":0.0649629231789791,"score_gpt":0.3495486032377718,"score_spread":0.2845856800587927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402048137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005930984,0.0011444557,0.96911067,0.0008399004,0.0010136374,0.000198845,0.00001139707,0.021743802,0.000006282328],"genre_scores_gemma":[0.11304548,0.000055345376,0.88632566,0.00006646891,0.00006866483,0.00017264223,0.0000091547245,0.00003289638,0.00022371435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854696,0.00016497115,0.00024719627,0.0005555986,0.00014498868,0.000340305],"domain_scores_gemma":[0.99619925,0.0030303844,0.000026649166,0.00057334005,0.000040955605,0.00012939658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000678729,0.00023692768,0.00025699066,0.00029903513,0.00011968849,0.00012494353,0.00038705484,0.0001867301,0.000010880982],"category_scores_gemma":[0.0024392044,0.00022534606,0.000094565396,0.00051056145,0.000055503595,0.0001707942,0.00002490656,0.00044675916,0.000010744283],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008112876,0.00007486794,0.00001069497,0.00012717165,0.00006906418,0.000044553322,0.00066384696,0.0015838912,0.0024547332,0.00056613405,0.0058990438,0.9884979],"study_design_scores_gemma":[0.0029190423,0.006974622,0.0013347093,0.0035144568,0.0009113926,0.014531721,0.00016012901,0.5994504,0.18901128,0.07109649,0.103821725,0.006274058],"about_ca_topic_score_codex":0.00009482848,"about_ca_topic_score_gemma":0.0000013023906,"teacher_disagreement_score":0.9822238,"about_ca_system_score_codex":0.00004923537,"about_ca_system_score_gemma":0.000044223034,"threshold_uncertainty_score":0.9189345},"labels":[],"label_agreement":null},{"id":"W4402050968","doi":"10.1007/s10664-024-10477-1","title":"On combining commit grouping and build skip prediction to reduce redundant continuous integration activity","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Commit; Computer science; Database","score_opus":0.021112466439620347,"score_gpt":0.28530239328041973,"score_spread":0.2641899268407994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402050968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21643277,0.00011884489,0.76722264,0.0006548041,0.0006082682,0.00015359507,0.0000034848065,0.014774957,0.00003064267],"genre_scores_gemma":[0.8669764,0.0000037587165,0.13260134,0.00020132714,0.0001120936,0.000043489486,0.0000033048802,0.000028677832,0.000029647279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861926,0.00004041895,0.00021651176,0.0005482761,0.00026482227,0.00031068508],"domain_scores_gemma":[0.9982319,0.0011634437,0.000029867053,0.00035015485,0.00005221976,0.00017241115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040918562,0.00022727426,0.00021856398,0.0002598206,0.00013608647,0.0004275401,0.0002835311,0.00010680062,0.0000018165259],"category_scores_gemma":[0.0018866383,0.00021603792,0.00005028531,0.0006476004,0.000019301391,0.00036657145,0.00020944397,0.00045334283,0.000012506724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068908426,0.00029184108,0.021161497,0.00046682297,0.00014117893,0.0002917821,0.0060163615,0.0122079095,0.008170389,0.012833222,0.08313455,0.85521555],"study_design_scores_gemma":[0.00037700948,0.0011871778,0.0632141,0.0034379254,0.000032587224,0.0002500824,0.000010134882,0.9047509,0.009865593,0.009819921,0.005994017,0.0010605445],"about_ca_topic_score_codex":0.000045162196,"about_ca_topic_score_gemma":9.587746e-7,"teacher_disagreement_score":0.892543,"about_ca_system_score_codex":0.00016171468,"about_ca_system_score_gemma":0.000033387256,"threshold_uncertainty_score":0.8809771},"labels":[],"label_agreement":null},{"id":"W4402264853","doi":"10.62973/12-105","title":"OGC OWS-9 - OWS Context evaluation IP Engineering Report","year":2013,"lang":"en","type":"report","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defence Science and Technology Group; Natural Resources Canada; U.S. Army Corps of Engineers; Defence Science and Technology Laboratory; National Geospatial-Intelligence Agency; Federal Aviation Administration; U.S. Geological Survey; National Aeronautics and Space Administration","keywords":"Context (archaeology); Computer science; Geography; Archaeology","score_opus":0.07937924010193935,"score_gpt":0.3261484479895635,"score_spread":0.24676920788762413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402264853","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001895935,0.0018629166,0.8847199,0.00028693458,0.0037934345,0.001051173,0.0000025923807,0.033282466,0.074811],"genre_scores_gemma":[0.13843031,0.00035078754,0.811159,0.00051146845,0.0018661913,0.0013747463,0.00022834197,0.00021558591,0.045863528],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99566054,0.00008450343,0.0008327496,0.00095620455,0.0020332425,0.0004327484],"domain_scores_gemma":[0.99489355,0.0004967455,0.0005854245,0.0020312793,0.0018396087,0.00015337366],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0048983167,0.00043698927,0.0005455472,0.00036223576,0.000092437826,0.00039844483,0.0010815469,0.00042682965,0.00016640319],"category_scores_gemma":[0.0071697347,0.0003850814,0.00019365345,0.00035587887,0.00002581235,0.0003929886,0.0004453052,0.00048530003,0.00015192213],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.474799e-7,0.000026860529,0.00037309044,0.000090418376,0.000048773272,0.00015619071,0.00006768347,0.000053441898,0.000014324201,0.00053799554,0.7574598,0.24117103],"study_design_scores_gemma":[0.00033903224,0.00018233774,0.0028714056,0.001581088,0.00018158296,0.0068110614,0.0000055564537,0.4883135,0.0009950518,0.017653933,0.47874403,0.0023214128],"about_ca_topic_score_codex":0.0022308151,"about_ca_topic_score_gemma":0.000012891073,"teacher_disagreement_score":0.48826006,"about_ca_system_score_codex":0.0005060929,"about_ca_system_score_gemma":0.0015793265,"threshold_uncertainty_score":0.9998601},"labels":[],"label_agreement":null},{"id":"W4402352815","doi":"10.1109/ijcnn60899.2024.10650368","title":"Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Reinforcement learning; Computer science; Penetration (warfare); Machine learning; Artificial intelligence; Reinforcement; Psychology; Engineering; Social psychology; Operations research","score_opus":0.03125521645134659,"score_gpt":0.28878440336496997,"score_spread":0.25752918691362336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402352815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002825249,0.000044924207,0.91311455,0.00031278632,0.00012258452,0.00014557719,1.2965029e-7,0.024488008,0.06148891],"genre_scores_gemma":[0.7073455,8.3050367e-7,0.29109874,0.00021821736,0.000035521047,0.000025824924,0.0000046277355,0.00001281546,0.0012579585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988606,0.000035626144,0.00021256726,0.00035487395,0.0002853337,0.0002510304],"domain_scores_gemma":[0.9982196,0.0012078832,0.000049185142,0.00035470346,0.000096049655,0.00007259751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045921328,0.00017108135,0.000114018745,0.00024589954,0.00017672396,0.00042123854,0.00032941494,0.000045922352,0.000019310413],"category_scores_gemma":[0.0007576273,0.00012281875,0.00003288253,0.0007753488,0.000022080141,0.00031550135,0.00007889628,0.00025219514,0.00008073561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043552285,0.000121162826,0.015032102,0.0004803462,0.00004615621,0.00014301654,0.0016220072,0.17621303,0.00024371957,0.02452387,0.025249284,0.75628173],"study_design_scores_gemma":[0.00010319176,0.0007384517,0.00053473626,0.0006128965,0.0000051003544,0.000017373368,0.00000188106,0.99365187,0.0007123777,0.00068903103,0.0027401166,0.00019295767],"about_ca_topic_score_codex":0.0000875791,"about_ca_topic_score_gemma":0.000011136509,"teacher_disagreement_score":0.81743884,"about_ca_system_score_codex":0.000117391675,"about_ca_system_score_gemma":0.00031114527,"threshold_uncertainty_score":0.5008403},"labels":[],"label_agreement":null},{"id":"W4402442339","doi":"10.1145/3650212.3652126","title":"LPR: Large Language Models-Aided Program Reduction","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Government of Canada; University of Waterloo","funders":"","keywords":"Computer science; Compiler; Programming language; JavaScript; Generality; Semantics (computer science); Debugging; Reduction (mathematics)","score_opus":0.02354237607111619,"score_gpt":0.3102948756575512,"score_spread":0.286752499586435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402442339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002713124,0.00051517907,0.8984004,0.0006250374,0.0003656647,0.00015527291,8.3100457e-7,0.08749774,0.009726704],"genre_scores_gemma":[0.57533354,0.0000048102397,0.42314467,0.0000780345,0.00007500865,0.000041905245,0.000002513463,0.0000085294505,0.0013109563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992037,0.000022105274,0.000107004285,0.00030698048,0.00015140424,0.00020881325],"domain_scores_gemma":[0.9994774,0.00004531964,0.000012956771,0.00038796995,0.000029763463,0.000046605863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026138898,0.00008648737,0.00007000597,0.000105766536,0.00005851423,0.00032070855,0.000322624,0.000045463385,0.00001237104],"category_scores_gemma":[0.000033563956,0.00006987316,0.000047527577,0.00039967205,0.0000132797595,0.00045625283,0.00013075973,0.00011138643,0.00006651272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010825858,0.00009794798,0.000020885896,0.000042008156,0.000011999934,0.000058938003,0.0017715369,0.000027005191,0.00025176097,0.1805056,0.1432747,0.67393655],"study_design_scores_gemma":[0.00004819799,0.000078392564,0.000017477325,0.00006452284,0.000003902671,0.00010493254,0.000015808859,0.83521414,0.0017030169,0.15755822,0.0050391927,0.00015220381],"about_ca_topic_score_codex":0.000074398624,"about_ca_topic_score_gemma":0.000002068397,"teacher_disagreement_score":0.83518714,"about_ca_system_score_codex":0.000026784592,"about_ca_system_score_gemma":0.000037147358,"threshold_uncertainty_score":0.30925998},"labels":[],"label_agreement":null},{"id":"W4402442387","doi":"10.1145/3650212.3680359","title":"ThinkRepair: Self-Directed Automated Program Repair","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science","score_opus":0.012641153618666493,"score_gpt":0.29300937128207494,"score_spread":0.28036821766340847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402442387","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012983805,0.0003106798,0.0015731193,0.0004794596,0.0003991641,0.00024976768,4.47999e-7,0.98856604,0.008291487],"genre_scores_gemma":[0.004757189,0.0000057823804,0.994046,0.00025002123,0.000049178154,0.000084430016,0.0000023114749,0.000018026716,0.0007870719],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872726,0.000057108,0.00019877052,0.0004997813,0.00023435368,0.0002827427],"domain_scores_gemma":[0.9989025,0.00025766334,0.000021339953,0.000655115,0.000079717975,0.00008364493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039770387,0.00015017303,0.00012308799,0.00015775058,0.000090942434,0.00040604037,0.0005190948,0.00008189877,0.0000149049],"category_scores_gemma":[0.00015510042,0.000117696516,0.00012598702,0.0009725961,0.00002195327,0.00032395104,0.00021082483,0.00014959661,0.00018336288],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6925124e-7,0.00006734523,0.00026670733,0.000035135065,0.000028092585,0.000093951465,0.00023030731,0.0000012681594,4.905521e-7,0.002088319,0.9882928,0.008895218],"study_design_scores_gemma":[0.000032945736,0.00011781846,0.00045462893,0.000073278956,0.000007421334,0.00009168955,6.7167434e-7,0.97099864,0.000014678232,0.009939533,0.018099075,0.00016960854],"about_ca_topic_score_codex":0.000087859815,"about_ca_topic_score_gemma":0.000002554347,"teacher_disagreement_score":0.9924729,"about_ca_system_score_codex":0.000052387848,"about_ca_system_score_gemma":0.00011413987,"threshold_uncertainty_score":0.47995245},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4402442473","doi":"10.1145/3650212.3680332","title":"Semantic Constraint Inference for Web Form Test Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Inference; Constraint (computer-aided design); Test (biology); Natural language processing; Artificial intelligence; Semantic Web; Information retrieval; Programming language; Mathematics; Geology","score_opus":0.046113461862748825,"score_gpt":0.30886525854924146,"score_spread":0.2627517966864926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402442473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015860389,0.0000664259,0.98174816,0.0010062803,0.00027376867,0.00015587363,0.0000031684065,0.013632373,0.0015279249],"genre_scores_gemma":[0.668412,0.0000027511605,0.3310674,0.00020696557,0.00006938278,0.00003714452,0.0000026314628,0.000004339686,0.00019732327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938697,0.0000059220038,0.00012562663,0.00024323944,0.00009090045,0.00014736976],"domain_scores_gemma":[0.99889165,0.0007590166,0.000015461832,0.00023365467,0.00006437194,0.00003586557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023139048,0.00007837697,0.000068226465,0.000078026584,0.0000692011,0.0003620907,0.00024699338,0.000036745685,0.0000083473615],"category_scores_gemma":[0.0004779213,0.000062817046,0.00003768354,0.0001752849,0.000024708272,0.00023806443,0.00006490393,0.00005192825,0.000027241507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7970144e-7,0.000044954242,0.0014399759,0.00011399845,0.0000116334395,0.000014734771,0.0003439115,0.000011883674,0.008370171,0.4268894,0.1628948,0.39986405],"study_design_scores_gemma":[0.000040779447,0.00008898207,0.00007822719,0.000052150303,0.0000031946686,0.000024518318,9.605875e-7,0.90375274,0.003714617,0.08944544,0.002691764,0.00010661095],"about_ca_topic_score_codex":0.00001559311,"about_ca_topic_score_gemma":0.000010133737,"teacher_disagreement_score":0.9037409,"about_ca_system_score_codex":0.000023093235,"about_ca_system_score_gemma":0.00012642924,"threshold_uncertainty_score":0.3491649},"labels":[],"label_agreement":null},{"id":"W4402457261","doi":"10.1145/3650212.3680354","title":"Domain Adaptation for Code Model-Based Unit Test Case Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; York University","funders":"","keywords":"Computer science; Unit testing; Code generation; Adaptation (eye); Code (set theory); Test (biology); Domain (mathematical analysis); Code coverage; Programming language; Operating system; Software; Key (lock)","score_opus":0.0997005380221137,"score_gpt":0.32023556997296465,"score_spread":0.22053503195085095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402457261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002096213,0.00004935822,0.9853143,0.0008179459,0.0001197066,0.00017521599,0.00000984421,0.011194826,0.00022257707],"genre_scores_gemma":[0.4168349,3.1283133e-7,0.5826545,0.00024054636,0.000041588384,0.00005393668,0.000009161287,0.0000066478765,0.00015840847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993905,0.000016293647,0.00012210119,0.0002573812,0.00009326743,0.000120457684],"domain_scores_gemma":[0.999094,0.00051208027,0.00001839746,0.00025219668,0.000084868014,0.000038429585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030040156,0.00007993534,0.000056759727,0.00010321702,0.0001156365,0.00025791064,0.000152972,0.00004137514,0.0000017669678],"category_scores_gemma":[0.00012119739,0.00007023759,0.000034873097,0.0002196195,0.000012611765,0.00021017397,0.000024333518,0.000046270958,0.000007340153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071184604,0.00017976378,0.00027475096,0.00019681182,0.000019698396,0.00066444447,0.0019024429,0.1656633,0.0046660923,0.4499068,0.14311184,0.23340695],"study_design_scores_gemma":[0.00007105548,0.000069442576,0.0000019829874,0.000020648475,0.0000037373231,0.00009856694,0.0000024730339,0.9347602,0.001887774,0.062090218,0.000898526,0.000095369476],"about_ca_topic_score_codex":0.00004846954,"about_ca_topic_score_gemma":0.00005915104,"teacher_disagreement_score":0.7690969,"about_ca_system_score_codex":0.000029499139,"about_ca_system_score_gemma":0.00012501294,"threshold_uncertainty_score":0.28642058},"labels":[],"label_agreement":null},{"id":"W4402457710","doi":"10.1145/3650212.3680398","title":"Characterizing and Detecting Program Representation Faults of Static Analysis Frameworks","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Representation (politics); Static analysis; Program analysis; Programming language","score_opus":0.02245917158366384,"score_gpt":0.333704196811921,"score_spread":0.31124502522825714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402457710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16859898,0.00007771219,0.82357186,0.0002087244,0.000049290353,0.00009217564,3.9316865e-7,0.0072440864,0.00015675697],"genre_scores_gemma":[0.6177772,0.0000042076053,0.3821462,0.00003516584,0.000007983598,0.000012056702,0.0000010214675,0.0000029032792,0.00001323608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929035,0.000032261087,0.00017731563,0.0002640299,0.00012781953,0.00010824967],"domain_scores_gemma":[0.99914587,0.00047900635,0.000050019073,0.00024987163,0.000044472024,0.000030738374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026030713,0.000065054315,0.0001244065,0.0002556995,0.00003907329,0.00018110429,0.00014405309,0.00005670284,0.0000027084982],"category_scores_gemma":[0.00025626694,0.000055052467,0.000047645528,0.0012160062,0.000021279036,0.00025587747,0.000097680386,0.00014272652,0.0000010113818],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011021518,0.000018544117,0.012870512,0.00006861468,0.00010388606,0.000009962853,0.0015353664,0.00002180817,0.0005729678,0.0011761868,0.000085892054,0.9835352],"study_design_scores_gemma":[0.0000261797,0.00007817435,0.013386576,0.00012478384,0.00006637842,0.000009472014,0.000021361157,0.9648974,0.0052914005,0.015961802,0.00003470423,0.00010174588],"about_ca_topic_score_codex":0.000117551856,"about_ca_topic_score_gemma":0.0000033068452,"teacher_disagreement_score":0.9834334,"about_ca_system_score_codex":0.000008963317,"about_ca_system_score_gemma":0.000012502312,"threshold_uncertainty_score":0.22449744},"labels":[],"label_agreement":null},{"id":"W4402473702","doi":"10.1109/ccece59415.2024.10667115","title":"Optimized Test Data Generation for Path Testing Using Improved Combined Fitness Function with Modified Particle Swarm Optimization Algorithm","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Particle swarm optimization; Fitness function; Algorithm; Computer science; Path (computing); Multi-swarm optimization; Test functions for optimization; Test data; Mathematical optimization; Function (biology); Mathematics; Machine learning; Genetic algorithm","score_opus":0.10710881190519414,"score_gpt":0.2976885004140749,"score_spread":0.19057968850888077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402473702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012029986,0.000058210353,0.9874824,0.00016757505,0.00031615223,0.00055446767,0.000018623872,0.010168884,0.00003063396],"genre_scores_gemma":[0.12865262,0.000001580368,0.87079465,0.00010146249,0.00014670812,0.000077878925,0.00013752887,0.000029857272,0.0000577127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984329,0.00003964057,0.0002942354,0.0007524751,0.0001944182,0.00028638417],"domain_scores_gemma":[0.99794084,0.0007444781,0.000092885566,0.0008625518,0.00028633853,0.000072933704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006627118,0.00019348609,0.00017298147,0.000088893175,0.00028111218,0.00077051873,0.00049548835,0.000071189286,0.0000023098764],"category_scores_gemma":[0.0006464282,0.00015676237,0.000026635136,0.0007051478,0.000029763882,0.0011784796,0.00022764571,0.000094986404,0.0000011914995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055576274,0.00025856227,0.0002249728,0.00012123743,0.00006882269,0.000014444422,0.00018387412,0.80626404,0.008594488,0.0014347868,0.0031571412,0.17962205],"study_design_scores_gemma":[0.00062300573,0.00037440294,0.000012465578,0.0000852467,0.00004770154,0.000022566117,0.0000036649142,0.99537504,0.0022132604,0.0009844957,0.000011751309,0.0002464048],"about_ca_topic_score_codex":0.0001324873,"about_ca_topic_score_gemma":0.0000020975842,"teacher_disagreement_score":0.189111,"about_ca_system_score_codex":0.0000626529,"about_ca_system_score_gemma":0.00017015403,"threshold_uncertainty_score":0.74301296},"labels":[],"label_agreement":null},{"id":"W4402516053","doi":"10.1145/3695989","title":"Non-Flaky and Nearly Optimal Time-Based Treatment of Asynchronous Wait Web Tests","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Asynchronous communication; Web application; World Wide Web; Computer network","score_opus":0.04587187782534556,"score_gpt":0.3016080723484287,"score_spread":0.2557361945230831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402516053","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03617386,0.001001693,0.9580816,0.00017012387,0.00025129944,0.0001209851,0.000011482216,0.004185811,0.0000031393702],"genre_scores_gemma":[0.23839651,0.00007297598,0.7613836,0.000023805813,0.000019552252,0.000040342537,0.0000015576662,0.000019749326,0.000041930525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990086,0.00006875843,0.00019264282,0.00040966467,0.00009009286,0.00023026302],"domain_scores_gemma":[0.9957834,0.0035991778,0.00002655485,0.00045977818,0.000034838675,0.00009628425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034120918,0.00020931856,0.0003151806,0.00031689112,0.00007370742,0.000058404665,0.00020384189,0.00013048615,0.000006415947],"category_scores_gemma":[0.00030690155,0.000188587,0.00007675681,0.0002767466,0.000062563035,0.00010590183,0.00001253318,0.00014679447,0.0000048640063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003734067,0.00015690927,0.00035995443,0.00027375904,0.00015654972,0.000077100936,0.0010487707,0.024913596,0.003549477,0.0001909977,0.00011832438,0.9691172],"study_design_scores_gemma":[0.0010052031,0.0045755925,0.0023353181,0.00048066818,0.0001738186,0.00048462936,0.000006078808,0.957886,0.028247269,0.0015626076,0.0025443707,0.0006984536],"about_ca_topic_score_codex":0.000041981268,"about_ca_topic_score_gemma":9.836835e-7,"teacher_disagreement_score":0.9684188,"about_ca_system_score_codex":0.00004403935,"about_ca_system_score_gemma":0.00008967437,"threshold_uncertainty_score":0.7690355},"labels":[],"label_agreement":null},{"id":"W4402526955","doi":"10.1145/3679006.3685068","title":"Using Category Partition to Detect Metamorphic Relations","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Partition (number theory); Metamorphic rock; Computer science; Artificial intelligence; Geology; Mathematics; Combinatorics; Petrology","score_opus":0.08057092530792093,"score_gpt":0.32251630077330123,"score_spread":0.2419453754653803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402526955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031588792,0.00016217736,0.9762751,0.0007559824,0.0002234673,0.000072201496,3.773154e-7,0.017402632,0.0019491953],"genre_scores_gemma":[0.5339306,5.51293e-7,0.46562913,0.00017918591,0.000024929386,0.000009342434,3.411541e-7,0.0000047216627,0.00022119665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938405,0.00002849086,0.00010820004,0.0002337004,0.00011310084,0.00013246843],"domain_scores_gemma":[0.9994642,0.00015375171,0.000010311317,0.00028178224,0.00003290514,0.00005705665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025514845,0.00006522246,0.00005786869,0.0001738543,0.0000883879,0.00021680143,0.00020389185,0.000030492998,0.000024734944],"category_scores_gemma":[0.00012131204,0.00005645382,0.000035810506,0.00060292264,0.000009582263,0.0002836279,0.00009277514,0.000076067816,0.00024216305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029239418,0.000041073432,0.0014790723,0.00007317482,0.000067167784,0.0001697534,0.0015193067,0.004511819,0.011726481,0.44093853,0.25714922,0.28232148],"study_design_scores_gemma":[0.000022700195,0.00005256273,0.00057964196,0.00007827563,0.000014042803,0.000071626455,0.0000015282088,0.5715456,0.005747459,0.4167673,0.0049188305,0.00020040291],"about_ca_topic_score_codex":0.00014221919,"about_ca_topic_score_gemma":0.0000066792654,"teacher_disagreement_score":0.5670338,"about_ca_system_score_codex":0.000043924592,"about_ca_system_score_gemma":0.000054947188,"threshold_uncertainty_score":0.3112597},"labels":[],"label_agreement":null},{"id":"W4402526960","doi":"10.1145/3678722.3685532","title":"Directed or Undirected: Investigating Fuzzing Strategies in a CI/CD Setup (Registered Report)","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Naval Information Warfare Center Pacific; Advanced Research Projects Agency; Defense Advanced Research Projects Agency","keywords":"Fuzz testing; Computer science; Programming language; Software","score_opus":0.0665116022280347,"score_gpt":0.3284333257113033,"score_spread":0.2619217234832686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402526960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11727995,0.0014907116,0.58577955,0.0027304625,0.0015012551,0.0007203473,0.000005705402,0.24361816,0.04687384],"genre_scores_gemma":[0.5581231,0.000007541567,0.4405754,0.0001945551,0.0000629374,0.00004319494,0.000006283536,0.000024091229,0.00096290413],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800926,0.000106927306,0.00050805433,0.00070599746,0.0002845281,0.00038521606],"domain_scores_gemma":[0.99826217,0.0007580675,0.00009948465,0.0007106289,0.00006922996,0.000100420286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007453995,0.00021867594,0.00023924804,0.0003582999,0.00009559639,0.001031925,0.0005637441,0.00009932379,0.000020456693],"category_scores_gemma":[0.0014283569,0.00017048945,0.00005451385,0.0016995143,0.00006728154,0.0007337719,0.00026765553,0.00029616884,0.000023497423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037210422,0.00038497546,0.04875976,0.002150783,0.0002644486,0.04035483,0.020779701,0.0003925207,0.013934121,0.14450108,0.3259649,0.40247568],"study_design_scores_gemma":[0.00041865424,0.00024515946,0.01532022,0.004140433,0.00002473029,0.003582816,0.00023833438,0.5993742,0.0035874853,0.36452794,0.007033045,0.0015070289],"about_ca_topic_score_codex":0.0014989182,"about_ca_topic_score_gemma":0.00046527013,"teacher_disagreement_score":0.5989816,"about_ca_system_score_codex":0.00009974495,"about_ca_system_score_gemma":0.0004676641,"threshold_uncertainty_score":0.99508756},"labels":[],"label_agreement":null},{"id":"W4402527174","doi":"10.1145/3678722.3685529","title":"The Havoc Paradox in Generator-Based Fuzzing (Registered Report)","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Generator (circuit theory); Computer science; Computer security; Programming language; Physics; Power (physics); Software","score_opus":0.036559975035849394,"score_gpt":0.29856286036877877,"score_spread":0.26200288533292937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402527174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048551853,0.001342059,0.9676754,0.004711729,0.0006378748,0.00013235203,2.9420906e-7,0.017040636,0.003604492],"genre_scores_gemma":[0.79682475,0.0000070454366,0.2017356,0.0005090981,0.00006739801,0.000041311192,0.0000010320811,0.000011802768,0.00080195395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988934,0.000054022057,0.00026149958,0.0003684224,0.00019306835,0.00022960795],"domain_scores_gemma":[0.99846745,0.00059573224,0.000039667226,0.0008250085,0.00003093787,0.000041230196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091411656,0.00010087722,0.00008760861,0.0000942916,0.000119071236,0.0005954515,0.00057761854,0.000041219413,0.0000023345035],"category_scores_gemma":[0.00035010412,0.000064826425,0.000049609644,0.000461996,0.00003670434,0.00014181556,0.000116799136,0.00014173845,0.000019879924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007225471,0.00007705111,0.013666951,0.000087449655,0.000024380906,0.0057018064,0.0005859627,0.00026589865,0.00065605546,0.12683077,0.3654848,0.48661163],"study_design_scores_gemma":[0.00013613373,0.00006125036,0.0016141287,0.00026475982,0.0000040138616,0.00035198202,0.000005180706,0.8431059,0.00398215,0.09493551,0.055181544,0.00035745898],"about_ca_topic_score_codex":0.00014396511,"about_ca_topic_score_gemma":0.00004456084,"teacher_disagreement_score":0.84284,"about_ca_system_score_codex":0.00004918791,"about_ca_system_score_gemma":0.00014140016,"threshold_uncertainty_score":0.57419527},"labels":[],"label_agreement":null},{"id":"W4402527462","doi":"10.1145/3678720.3685320","title":"Abstract Debugging with GobPie","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Debugging; Computer science; Programming language; Software engineering","score_opus":0.01472623548697537,"score_gpt":0.2515278555332744,"score_spread":0.236801620046299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402527462","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015785504,0.00030773456,0.9093209,0.0010038875,0.00013264125,0.000045713405,2.1462365e-7,0.059205506,0.028404886],"genre_scores_gemma":[0.6811732,0.0000019698655,0.3182503,0.00021223343,0.00003031988,0.0000064898563,3.021652e-7,0.000007317293,0.00031783458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934214,0.0000051713564,0.0000799029,0.00026085263,0.00014475375,0.00016716072],"domain_scores_gemma":[0.9993942,0.00020646519,0.000010600944,0.00031831395,0.000023089608,0.000047355894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001630542,0.000084013394,0.000061354935,0.00008894316,0.00005166715,0.00037388553,0.00035201854,0.000025092886,0.00002461369],"category_scores_gemma":[0.00002766423,0.000055996814,0.000023891502,0.00030321445,0.000018900946,0.00032044743,0.00007406858,0.00010420693,0.00012087128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023278883,0.000033910044,0.001957061,0.00008725515,0.000036511403,0.0005065418,0.0004263297,0.000034390156,0.00022912424,0.11944086,0.19027436,0.6869713],"study_design_scores_gemma":[0.00030634634,0.00043801925,0.019683264,0.0016594368,0.000030183297,0.0010811056,0.000010496507,0.4455892,0.010519296,0.44497594,0.07416385,0.001542838],"about_ca_topic_score_codex":0.000060120932,"about_ca_topic_score_gemma":0.0000036310983,"teacher_disagreement_score":0.6854285,"about_ca_system_score_codex":0.000019072111,"about_ca_system_score_gemma":0.00006513948,"threshold_uncertainty_score":0.3605387},"labels":[],"label_agreement":null},{"id":"W4402571068","doi":"10.1109/icstw60967.2024.00031","title":"Replay-Based Continual Learning for Test Case Prioritization","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Prioritization; Computer science; Test (biology); Software engineering; Artificial intelligence; Machine learning; Process management; Engineering","score_opus":0.01782511303937027,"score_gpt":0.2913492331547891,"score_spread":0.2735241201154188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402571068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013171023,0.00007724289,0.9711504,0.00047953884,0.00017460814,0.00014383989,0.0000012224629,0.026005417,0.00065060816],"genre_scores_gemma":[0.61110276,4.042576e-7,0.3879505,0.00015129895,0.000050958308,0.000028381852,0.0000034090606,0.000008625791,0.0007036403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993439,0.000018366847,0.00012495584,0.00028417326,0.000085147905,0.00014350378],"domain_scores_gemma":[0.9980776,0.0015756395,0.00002204055,0.00020224988,0.000085859676,0.000036661102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036370274,0.00007507027,0.00006979563,0.00009269576,0.000120731995,0.00032739987,0.00014905806,0.00004025468,0.00000447247],"category_scores_gemma":[0.0012781743,0.00006686661,0.00004047901,0.00025353525,0.000014179546,0.000172193,0.000040210285,0.000084729494,0.000011193999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008420404,0.00012914056,0.0116067,0.00039651617,0.000022318989,0.0028561293,0.001021621,0.0006913556,0.0010984148,0.066213034,0.24946189,0.6664945],"study_design_scores_gemma":[0.00009924626,0.00018288984,0.000038025242,0.00008492589,0.0000049127652,0.00051883457,0.000003376854,0.9770811,0.002455575,0.007724454,0.0116754,0.00013125964],"about_ca_topic_score_codex":0.000037813534,"about_ca_topic_score_gemma":0.000003502698,"teacher_disagreement_score":0.97638977,"about_ca_system_score_codex":0.000022350312,"about_ca_system_score_gemma":0.00007246582,"threshold_uncertainty_score":0.31571245},"labels":[],"label_agreement":null},{"id":"W4402571187","doi":"10.1109/icstw60967.2024.00014","title":"An End-to-End Test Case Prioritization Framework using Optimized Machine Learning Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"End-to-end principle; Computer science; Test (biology); Prioritization; End user; End milling; End of history; Artificial intelligence; Engineering; Operating system; Management science; Mechanical engineering","score_opus":0.04802987512244553,"score_gpt":0.3161299016249306,"score_spread":0.26810002650248504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402571187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005004756,0.00019129243,0.9707406,0.00020425423,0.00019129943,0.0001439254,0.000002809874,0.023104755,0.00041627904],"genre_scores_gemma":[0.47055787,0.0000032837236,0.5291626,0.00014712635,0.000052954085,0.0000057345674,0.0000026265618,0.000016030712,0.00005178593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868137,0.00007999899,0.00021577832,0.0005201308,0.0002365038,0.000266247],"domain_scores_gemma":[0.99838936,0.0008617061,0.00003340142,0.0004763254,0.00008911214,0.00015006396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005134063,0.00016653573,0.00015312979,0.00024776565,0.00024085447,0.0007918892,0.00037668523,0.00009680756,0.000032848395],"category_scores_gemma":[0.00056939584,0.00015261199,0.00004440614,0.0007983241,0.000020413518,0.0007759556,0.00018944703,0.0003223854,0.000016701688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012228763,0.00023384069,0.002305325,0.0001257652,0.00004088345,0.005071333,0.0077308486,0.639802,0.0016576877,0.07063582,0.0013317238,0.27105254],"study_design_scores_gemma":[0.00004886776,0.0001005255,0.0000056090307,0.00016322141,0.000008608471,0.0010770435,0.0000051259663,0.9629945,0.0004322757,0.034863837,0.00009495291,0.0002054339],"about_ca_topic_score_codex":0.0005338321,"about_ca_topic_score_gemma":0.000005437285,"teacher_disagreement_score":0.4655531,"about_ca_system_score_codex":0.00006691891,"about_ca_system_score_gemma":0.00007975011,"threshold_uncertainty_score":0.7636206},"labels":[],"label_agreement":null},{"id":"W4402571211","doi":"10.1109/icstw60967.2024.00062","title":"TCPGraphix: A Visualization Tool for ML-Powered Test Case Prioritization Data Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Visualization; Prioritization; Data visualization; Test (biology); Data mining; Engineering; Process management; Geology","score_opus":0.04666377528138762,"score_gpt":0.3563540356949651,"score_spread":0.3096902604135775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402571211","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040297347,0.00017442122,0.9837349,0.0002624241,0.00014674365,0.00024150079,0.000046047735,0.014834998,0.00015597585],"genre_scores_gemma":[0.5401105,0.000013244778,0.45909604,0.0001955233,0.000061254315,0.000037769434,0.00024034992,0.0000135283535,0.0002317751],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880916,0.000027036758,0.00022975734,0.00060595386,0.00016174455,0.00016637803],"domain_scores_gemma":[0.99783385,0.00086475007,0.00004105455,0.0010883437,0.00013053487,0.000041441886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005524245,0.000113031325,0.00013457373,0.00047120632,0.00012928083,0.0006282782,0.00059247424,0.000056520814,0.000009761747],"category_scores_gemma":[0.0010624003,0.000101196914,0.00007051376,0.0026084003,0.000017547742,0.0007054796,0.0002504822,0.000042546813,0.0000060831767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009536858,0.000476577,0.027949546,0.0005166327,0.00083943305,0.0011876482,0.0019127243,0.00020333687,0.0004521458,0.24632832,0.3993534,0.32077068],"study_design_scores_gemma":[0.00005865358,0.00005658187,0.0002638633,0.000029787223,0.00014220776,0.0001478529,0.0000030633355,0.98022777,0.0001601412,0.01689508,0.0018500412,0.00016498685],"about_ca_topic_score_codex":0.00010895941,"about_ca_topic_score_gemma":0.000033849316,"teacher_disagreement_score":0.9800244,"about_ca_system_score_codex":0.000024059296,"about_ca_system_score_gemma":0.000062119434,"threshold_uncertainty_score":0.6058501},"labels":[],"label_agreement":null},{"id":"W4402571307","doi":"10.1109/icstw60967.2024.00021","title":"Annotating Control-Flow Graphs for Formalized Test Coverage Criteria","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Computer science; Control flow; Test (biology); Control flow graph; Control (management); Programming language; Software engineering; Artificial intelligence","score_opus":0.017486802881724738,"score_gpt":0.2954803116486411,"score_spread":0.27799350876691636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402571307","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004183085,0.00020314833,0.97464913,0.0009587075,0.00041539271,0.0002532175,0.000021771586,0.021503411,0.0015769014],"genre_scores_gemma":[0.4508608,0.0000035175244,0.5477678,0.0010190288,0.0000464556,0.00008480016,0.00000415025,0.000012765443,0.0002006279],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898046,0.00002297649,0.00022198411,0.00034192024,0.00013720593,0.0002954373],"domain_scores_gemma":[0.99741954,0.00206813,0.0000324912,0.00032908705,0.00008875485,0.00006197459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000511543,0.00013915534,0.00015946897,0.00012867905,0.00013677328,0.0006529616,0.00042501895,0.000049719285,0.000015256614],"category_scores_gemma":[0.000745773,0.000114475595,0.00010835909,0.0003094828,0.000022961462,0.0005178344,0.000079373945,0.00008212336,0.000015314152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019856594,0.00009336557,0.0020883933,0.00031421837,0.000053044645,0.000074482705,0.0007964584,0.000041283507,0.0022410825,0.12525691,0.55036706,0.31865385],"study_design_scores_gemma":[0.00033943105,0.00016902451,0.00011830032,0.00007932176,0.0000075738544,0.00003370527,0.0000010600863,0.7553169,0.0006570732,0.23674707,0.0063550463,0.0001754682],"about_ca_topic_score_codex":0.00002447901,"about_ca_topic_score_gemma":0.0000011418409,"teacher_disagreement_score":0.75527567,"about_ca_system_score_codex":0.000019025054,"about_ca_system_score_gemma":0.000049161896,"threshold_uncertainty_score":0.6296524},"labels":[],"label_agreement":null},{"id":"W4402860132","doi":"10.1145/3697014","title":"ZigZagFuzz: Interleaved Fuzzing of Program Options and Files","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"Samsung; Hanyang University","keywords":"Fuzz testing; Computer science; Programming language; Software","score_opus":0.08854984899731846,"score_gpt":0.34345537315099234,"score_spread":0.25490552415367385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402860132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00658927,0.0013785925,0.9831352,0.00018638145,0.00038061535,0.000115260955,0.0000067501455,0.008202528,0.000005352024],"genre_scores_gemma":[0.14909342,0.00017190358,0.85057896,0.000025056986,0.000016893733,0.000062200634,0.0000011604076,0.000015702713,0.000034706234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911356,0.000092569586,0.00019452481,0.00033563963,0.0000756357,0.00018809682],"domain_scores_gemma":[0.99641985,0.0030772781,0.000023963685,0.00037198703,0.000035999692,0.00007090285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052492117,0.0001482481,0.00021656562,0.00033280288,0.00007102237,0.00006721029,0.00024083488,0.000105710926,0.0000034041798],"category_scores_gemma":[0.0008699887,0.00013996693,0.000058011978,0.00030969625,0.00006485175,0.00014215278,0.000030116686,0.00026481884,0.0000012447821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035281853,0.00003474136,0.00006664998,0.00019969589,0.00005649789,0.000008809383,0.00083963637,0.0008568038,0.00051104155,0.0030418488,0.000080732105,0.9943],"study_design_scores_gemma":[0.0016868174,0.0055262013,0.011337717,0.0052340147,0.0005787519,0.0037450478,0.00023047677,0.71175325,0.046278525,0.18271828,0.027636932,0.00327398],"about_ca_topic_score_codex":0.000026717886,"about_ca_topic_score_gemma":0.0000010853727,"teacher_disagreement_score":0.99102604,"about_ca_system_score_codex":0.000014298667,"about_ca_system_score_gemma":0.000024082281,"threshold_uncertainty_score":0.57076854},"labels":[],"label_agreement":null},{"id":"W4402979393","doi":"10.1109/tse.2024.3469582","title":"LTM: Scalable and Black-Box Similarity-Based Test Suite Minimization Based on Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Science Foundation Ireland","keywords":"Computer science; Test suite; Suite; Scalability; Black box; Minification; Similarity (geometry); Test (biology); Software testing; Programming language; Artificial intelligence; Natural language processing; Test case; Software; Machine learning; Operating system","score_opus":0.012067979201598519,"score_gpt":0.22770173116824316,"score_spread":0.21563375196664464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402979393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001432422,0.00008662547,0.9806431,0.00019527732,0.00035407042,0.00017842131,0.00003590108,0.017046025,0.000028166498],"genre_scores_gemma":[0.6632918,0.0000049414907,0.3362948,0.00023206514,0.000027600006,0.00004264557,0.0000045661664,0.000041606825,0.0000599433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867594,0.000024012805,0.00020535839,0.00050723355,0.00028910048,0.00029833417],"domain_scores_gemma":[0.99788606,0.0014246844,0.00002402616,0.0004934448,0.00005091288,0.00012086499],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020667662,0.0002614324,0.00017890391,0.0004843797,0.00013017144,0.00030191327,0.00026552536,0.00012651029,0.000009662934],"category_scores_gemma":[0.00011387472,0.0002702732,0.000085593085,0.00068189256,0.000031499665,0.00035803556,0.000003526949,0.0003578018,0.00001447407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004475282,0.00007888707,0.00003810965,0.00016375522,0.000009704159,0.00003741865,0.00022347661,0.9870446,0.00014538845,0.000081445985,0.0005824695,0.011590295],"study_design_scores_gemma":[0.00017947594,0.0001343657,0.000035475816,0.00044612412,0.000017726348,0.00000752856,0.0000018612352,0.9885599,0.009991651,0.00018774855,0.00015344236,0.00028467525],"about_ca_topic_score_codex":0.000026382735,"about_ca_topic_score_gemma":0.000002214557,"teacher_disagreement_score":0.6618594,"about_ca_system_score_codex":0.00009594816,"about_ca_system_score_gemma":0.00007834757,"threshold_uncertainty_score":0.99997497},"labels":[],"label_agreement":null},{"id":"W4403060990","doi":"10.1109/tse.2024.3472476","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Ottawa","funders":"Science Foundation Ireland","keywords":"Computer science; Test (biology); Programming language; Code (set theory); Code coverage; Software engineering; Reliability engineering; Software; Engineering","score_opus":0.017848771159971646,"score_gpt":0.2560316308607052,"score_spread":0.23818285970073355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403060990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008022438,0.00062449294,0.9593624,0.00003331389,0.00066675333,0.00026973427,0.00016593197,0.030849563,0.000005382283],"genre_scores_gemma":[0.59936863,0.000012760299,0.4002969,0.000031263004,0.00008010405,0.00008137764,0.000002688558,0.000051452243,0.000074808006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851143,0.000011515032,0.0002809961,0.000557418,0.00020065717,0.0004379714],"domain_scores_gemma":[0.9965426,0.0028013168,0.000033931185,0.00043535314,0.00007047758,0.00011635118],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003443667,0.00028202604,0.00022457645,0.0003051761,0.00029438088,0.0002725372,0.0002651197,0.00012609772,0.0000022255967],"category_scores_gemma":[0.00042559594,0.00029223156,0.00013440875,0.0004710964,0.000025987916,0.0006548538,0.000010677408,0.00033226353,0.000002604951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026534652,0.00061057456,0.0030604764,0.003684525,0.0004057478,0.00039672013,0.01670396,0.89469934,0.0070497766,0.0035069466,0.0038097678,0.06604563],"study_design_scores_gemma":[0.00015409557,0.000117349926,0.0000308666,0.00044197036,0.000039478567,0.00010920648,0.000020193333,0.99254304,0.005458753,0.0004939426,0.00027318991,0.00031788668],"about_ca_topic_score_codex":0.00004810248,"about_ca_topic_score_gemma":0.000011367756,"teacher_disagreement_score":0.5913462,"about_ca_system_score_codex":0.00010491369,"about_ca_system_score_gemma":0.00007390536,"threshold_uncertainty_score":0.999953},"labels":[],"label_agreement":null},{"id":"W4403064409","doi":"10.3389/frobt.2024.1346580","title":"AAT4IRS: automated acceptance testing for industrial robotic systems","year":2024,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure; Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Software engineering; Process (computing); Software; Acceptance testing; Robustness testing; Industrial robot; Robot; Robustness (evolution); Artificial intelligence; Operating system","score_opus":0.04334930426113736,"score_gpt":0.28442739993703703,"score_spread":0.24107809567589966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403064409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022842649,0.0023233981,0.98385966,0.00059678045,0.0036042477,0.00030837787,0.0000027461779,0.009005787,0.00007058178],"genre_scores_gemma":[0.2591157,0.000012331129,0.74041253,0.00010119614,0.00019161629,0.000044101675,0.0000028812565,0.000020504449,0.0000991238],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885017,0.000035905472,0.00026857495,0.0004047868,0.00013198901,0.0003085764],"domain_scores_gemma":[0.9992104,0.00035954738,0.000048118367,0.00025519446,0.000059979753,0.00006675183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041840333,0.00015188917,0.00023927358,0.0002195019,0.00009599727,0.00064398843,0.00036322584,0.0001258452,1.5984459e-7],"category_scores_gemma":[0.00048654032,0.00014183621,0.000033517197,0.00061230693,0.000042107968,0.00027644218,0.00011283094,0.00021012822,0.0000010510664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009540409,0.000068083675,0.0456765,0.00050816295,0.00006304987,0.000110173154,0.00047325145,0.17338577,0.000034417473,0.020086395,0.6149792,0.14460547],"study_design_scores_gemma":[0.0001710214,0.000087147964,0.0002719725,0.0005755036,0.00000988153,0.000020658385,0.000008486829,0.98302275,0.000009912821,0.014979789,0.00066155277,0.00018130554],"about_ca_topic_score_codex":0.000036916168,"about_ca_topic_score_gemma":6.765826e-7,"teacher_disagreement_score":0.809637,"about_ca_system_score_codex":0.000066313056,"about_ca_system_score_gemma":0.00009703094,"threshold_uncertainty_score":0.6209995},"labels":[],"label_agreement":null},{"id":"W4403427009","doi":"10.5753/sblp.2024.3471","title":"Semantic conflict detection via dynamic analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Artificial intelligence; Information retrieval; Natural language processing","score_opus":0.011761843050324437,"score_gpt":0.274519036368925,"score_spread":0.26275719331860053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403427009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032884106,0.00019029378,0.96703386,0.00028345812,0.00020614019,0.00004154183,2.1442015e-7,0.02818881,0.00076727866],"genre_scores_gemma":[0.9304995,0.0000052226183,0.06875289,0.00014223898,0.000013829336,0.000007772235,9.742676e-7,0.000005349451,0.0005722274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999298,0.000023575309,0.00011457309,0.00029793763,0.00013152574,0.00013443822],"domain_scores_gemma":[0.9993794,0.0001616283,0.000015354251,0.00037606707,0.000030199319,0.000037347087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021167293,0.00007935716,0.00010037358,0.00038257198,0.000057058285,0.00025066672,0.00028007737,0.000038040736,0.000016639757],"category_scores_gemma":[0.00003538662,0.000065579996,0.00010186056,0.001577478,0.000014648358,0.00017503329,0.00007988064,0.000082247316,0.000096850104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017130544,0.000041603504,0.0020984565,0.00007379599,0.00056079397,0.000119568394,0.0006106202,0.00017493931,0.005539672,0.005269853,0.0030686222,0.98244035],"study_design_scores_gemma":[0.000013146652,0.000027405444,0.0018685205,0.000011304813,0.00006154602,0.0000269576,5.2265585e-7,0.9789511,0.0020795115,0.016217232,0.0006443531,0.00009842136],"about_ca_topic_score_codex":0.00024247028,"about_ca_topic_score_gemma":0.0000543692,"teacher_disagreement_score":0.98234195,"about_ca_system_score_codex":0.000034725483,"about_ca_system_score_gemma":0.0000144570195,"threshold_uncertainty_score":0.26742747},"labels":[],"label_agreement":null},{"id":"W4403536012","doi":"10.1145/3691620.3695551","title":"Efficient Incremental Code Coverage Analysis for Regression Test Suites","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Regression testing; Code coverage; Programming language; Code (set theory); Test (biology); Regression analysis; Parallel computing; Machine learning; Software; Software development","score_opus":0.02530939162931477,"score_gpt":0.3040384391541011,"score_spread":0.27872904752478633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016613428,0.00024255872,0.96914065,0.00041476582,0.00014592153,0.00014791684,0.00001716525,0.012484841,0.0007927526],"genre_scores_gemma":[0.82381475,0.0000027690392,0.1754654,0.00016693903,0.00003061998,0.000028680144,0.000009121812,0.0000069802277,0.00047471537],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999034,0.000017249626,0.0001613976,0.0003890994,0.0002048935,0.00019338503],"domain_scores_gemma":[0.99715805,0.0023405734,0.000028642608,0.00037364822,0.00004432025,0.000054739423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004053066,0.0001119692,0.00013657956,0.00027839254,0.00011271958,0.0003232509,0.00039301792,0.00003881237,0.00001905444],"category_scores_gemma":[0.000603091,0.000080166574,0.00013842761,0.0009582738,0.000019888521,0.000060559032,0.00018347579,0.00006173744,0.000017969862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021373407,0.0007532004,0.31787843,0.00034827236,0.000726042,0.00015339312,0.001454359,0.004383183,0.008607027,0.085733324,0.40917322,0.17076817],"study_design_scores_gemma":[0.00007636395,0.00010291853,0.0024329186,0.00007759353,0.00005797206,0.0000072315565,0.0000020415082,0.9863122,0.004730745,0.0040254327,0.0020118004,0.00016278698],"about_ca_topic_score_codex":0.000044143442,"about_ca_topic_score_gemma":0.000007221681,"teacher_disagreement_score":0.981929,"about_ca_system_score_codex":0.00005382699,"about_ca_system_score_gemma":0.00003630521,"threshold_uncertainty_score":0.3269098},"labels":[],"label_agreement":null},{"id":"W4403536208","doi":"10.1145/3691620.3695533","title":"Developer-Applied Accelerations in Continuous Integration: A Detection Approach and Catalog of Patterns","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Huawei Technologies (Canada); University of Waterloo","funders":"","keywords":"Computer science; Database","score_opus":0.022935272753777453,"score_gpt":0.2514001286771509,"score_spread":0.22846485592337343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032004878,0.000054269203,0.96231264,0.00007920369,0.00004305597,0.00011093883,9.049011e-7,0.0022893695,0.0031047128],"genre_scores_gemma":[0.84667015,0.0000041377857,0.15319224,0.000035833593,0.000008170069,0.00004038482,0.0000033511346,0.0000035710457,0.00004218842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994742,0.000014274511,0.00015225503,0.00021024817,0.00007158163,0.00007743525],"domain_scores_gemma":[0.9996901,0.00009438009,0.000017671597,0.0001505951,0.00002913836,0.000018102979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018117085,0.0000648938,0.000087396504,0.00015683482,0.00002904357,0.00013185163,0.00013764256,0.000039090493,0.0000016405047],"category_scores_gemma":[0.000037930015,0.00005302008,0.000011456138,0.00033743237,0.000017611386,0.00017150401,0.00007221977,0.00008385049,0.000001554957],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031206862,0.00007428985,0.005487691,0.000098855875,0.0000112896005,0.000007728179,0.0035922527,0.000018353136,0.003774509,0.07451328,0.00061325275,0.9118054],"study_design_scores_gemma":[0.0004909104,0.0002489537,0.06368508,0.0003898305,0.00001645719,0.00027377493,0.00024337671,0.7364547,0.14156045,0.0551703,0.0007061698,0.0007599607],"about_ca_topic_score_codex":0.00025976918,"about_ca_topic_score_gemma":0.00012074516,"teacher_disagreement_score":0.91104543,"about_ca_system_score_codex":0.00001888824,"about_ca_system_score_gemma":0.00003368817,"threshold_uncertainty_score":0.21620962},"labels":[],"label_agreement":null},{"id":"W4403536220","doi":"10.1145/3691620.3695527","title":"Test-Driven Development and LLM-based Code Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Test (biology); Code generation; Test-driven development; Programming language; Code (set theory); Software engineering; Software development; Operating system; Software","score_opus":0.04352896262435825,"score_gpt":0.27534288710410176,"score_spread":0.23181392447974353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007499058,0.00012621026,0.9794038,0.0007669297,0.00009919891,0.00005056273,3.8907524e-7,0.011470419,0.00058345165],"genre_scores_gemma":[0.39465716,9.986958e-7,0.60480654,0.00030498614,0.000023335982,0.00001082238,0.0000015262644,0.0000034902307,0.00019113024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999494,0.000009684688,0.00008746199,0.0002193129,0.00009829765,0.00009119733],"domain_scores_gemma":[0.99958694,0.00019313306,0.000009140372,0.0001508675,0.00002402559,0.00003587125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013643566,0.00006234019,0.000045862984,0.00006984481,0.00006577668,0.00024663945,0.00013795792,0.000025118185,0.0000040716977],"category_scores_gemma":[0.00007601859,0.00005065993,0.000009705713,0.00013981643,0.000012239874,0.00011212702,0.00006136049,0.000042311567,0.000021424861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.612354e-7,0.000090693386,0.007297809,0.00007528549,0.000012879067,0.000069132315,0.00095016713,0.00013527776,0.0032537808,0.025914084,0.16981278,0.7923874],"study_design_scores_gemma":[0.000038820133,0.00004437429,0.0006208868,0.00004278938,0.0000015135973,0.000011534801,3.9325323e-7,0.96212476,0.0220741,0.002591305,0.012336896,0.00011264577],"about_ca_topic_score_codex":0.000009088826,"about_ca_topic_score_gemma":0.000007332614,"teacher_disagreement_score":0.96198946,"about_ca_system_score_codex":0.000023296881,"about_ca_system_score_gemma":0.00009761425,"threshold_uncertainty_score":0.23783498},"labels":[],"label_agreement":null},{"id":"W4403536584","doi":"10.1145/3691620.3695269","title":"Towards a Robust Waiting Strategy for Web GUI Testing for an Industrial Software System","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Computer science; Software testing; Software engineering; Software; Web testing; Operating system; The Internet; Web application security; Web development","score_opus":0.2161010280282333,"score_gpt":0.32922369103425075,"score_spread":0.11312266300601745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002529089,0.000090005226,0.9473725,0.00015406514,0.00073083263,0.00076329295,0.000032392712,0.047290694,0.0010371493],"genre_scores_gemma":[0.40119898,1.0619659e-7,0.5977889,0.000052401814,0.00057788607,0.00025072103,0.000009693417,0.000030623127,0.00009068591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811417,0.000046215955,0.00040438192,0.0007064187,0.00022449292,0.0005043322],"domain_scores_gemma":[0.99721074,0.0017913855,0.00008443027,0.00048636354,0.00029074517,0.0001363188],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001212056,0.00023664952,0.00025317777,0.00018367612,0.00029194052,0.0010901653,0.00081659935,0.00017891645,0.0000017082837],"category_scores_gemma":[0.0021296826,0.00020430596,0.00011567253,0.00054191926,0.000025065967,0.00057373923,0.00016665748,0.00017672089,0.000004046682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012701015,0.000041902673,0.0004959154,0.000690127,0.000036332833,0.000021252012,0.00020223598,0.0009183368,0.00021571918,0.063019186,0.058935918,0.8754104],"study_design_scores_gemma":[0.00030731584,0.0007056986,0.000016643111,0.0006388822,0.00002094691,0.00008486643,0.000045089688,0.98375446,0.00042938892,0.012540938,0.0011322958,0.00032346562],"about_ca_topic_score_codex":0.00018064937,"about_ca_topic_score_gemma":0.000008754804,"teacher_disagreement_score":0.9828361,"about_ca_system_score_codex":0.00012467762,"about_ca_system_score_gemma":0.00058262877,"threshold_uncertainty_score":0.9999468},"labels":[],"label_agreement":null},{"id":"W4403536618","doi":"10.1145/3691620.3695261","title":"The Importance of Accounting for Execution Failures when Predicting Test Flakiness","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Test (biology); Reliability engineering; Accounting; Engineering; Business","score_opus":0.01749802715021794,"score_gpt":0.2739698035962184,"score_spread":0.2564717764460005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046598855,0.00050617487,0.9829404,0.0018644065,0.00031607112,0.00019318228,0.0000024742305,0.008636754,0.00088068383],"genre_scores_gemma":[0.77298206,0.0000040212703,0.2265791,0.000071208255,0.00010852779,0.00005246472,0.0000010494756,0.000008688862,0.00019289747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921113,0.000010226639,0.00022465552,0.00022670021,0.00015274632,0.00017452803],"domain_scores_gemma":[0.9971858,0.0022745682,0.000074572985,0.00032789473,0.0001197769,0.000017341945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074692955,0.00007923297,0.00007931831,0.000048554375,0.00018241262,0.00030434888,0.0005241146,0.00003440865,0.0000012296485],"category_scores_gemma":[0.0013752216,0.000050793187,0.000050190432,0.00021678097,0.000036476984,0.00031397998,0.00013620564,0.0000685964,0.000001306531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000740793,0.00005317672,0.21042208,0.00048607588,0.00004859408,0.00001013932,0.0017757567,0.000042181076,0.0024135401,0.2606347,0.20921564,0.3148907],"study_design_scores_gemma":[0.000090980226,0.00010436306,0.003112151,0.000397175,0.000013264288,0.0000297598,0.000031617892,0.67329323,0.0077464045,0.29984984,0.015126635,0.00020461477],"about_ca_topic_score_codex":0.000057635334,"about_ca_topic_score_gemma":0.000021607308,"teacher_disagreement_score":0.76832217,"about_ca_system_score_codex":0.000018019462,"about_ca_system_score_gemma":0.000054357934,"threshold_uncertainty_score":0.29348433},"labels":[],"label_agreement":null},{"id":"W4403537012","doi":"10.1145/3691620.3695363","title":"Slicer4D: A Slicing-based Debugger for Java","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Debugger; Computer science; Slicing; Java; Programming language; Program slicing; Operating system; Debugging; World Wide Web","score_opus":0.021165357591978955,"score_gpt":0.29685853510375787,"score_spread":0.2756931775117789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403537012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034446083,0.00016939412,0.95568943,0.0025041073,0.0003300699,0.00017334404,0.000001484652,0.03852145,0.0022662417],"genre_scores_gemma":[0.3828741,7.993733e-7,0.6142273,0.0018879761,0.00008137867,0.00009095603,0.0000019908355,0.000015400808,0.00082009594],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991075,0.000015477786,0.00013855229,0.00036331435,0.00013947481,0.00023572697],"domain_scores_gemma":[0.9986742,0.000758216,0.00001656427,0.00042947673,0.00006112842,0.00006039649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033627564,0.00011204828,0.0000999941,0.00014762385,0.0000624106,0.00032571863,0.00047950665,0.000049525355,0.000017891076],"category_scores_gemma":[0.00017720275,0.00008883171,0.000090223766,0.00034154463,0.000017660206,0.00017172097,0.00007180477,0.000073593445,0.00006374506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044162407,0.000044035136,0.00039433214,0.00013370423,0.000018704655,0.000023866469,0.00032154773,0.00006182941,0.00021412196,0.082419075,0.74081117,0.1755532],"study_design_scores_gemma":[0.00012113675,0.00013025597,0.00008138272,0.000110993045,0.000007394364,0.000015546668,9.0937215e-7,0.84339774,0.0032611908,0.075069524,0.07759192,0.00021202561],"about_ca_topic_score_codex":0.0000751134,"about_ca_topic_score_gemma":0.0000046648447,"teacher_disagreement_score":0.84333587,"about_ca_system_score_codex":0.000031332598,"about_ca_system_score_gemma":0.000106041785,"threshold_uncertainty_score":0.36224517},"labels":[],"label_agreement":null},{"id":"W4403576996","doi":"10.48550/arxiv.2410.11769","title":"Can Search-Based Testing with Pareto Optimization Effectively Cover Failure-Revealing Test Inputs?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Cover (algebra); Pareto principle; Test (biology); Computer science; Pareto optimal; Reliability engineering; Mathematical optimization; Multi-objective optimization; Mathematics; Engineering; Geology; Paleontology","score_opus":0.05888171160340358,"score_gpt":0.19741529985547052,"score_spread":0.13853358825206694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403576996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032189667,0.0000261652,0.95572025,0.00037412715,0.00015998012,0.00049139047,0.00003053938,0.010410043,0.00059784454],"genre_scores_gemma":[0.8317044,0.0000026910761,0.167891,0.0001472997,0.00006006395,0.000005005597,0.000021960928,0.00004816929,0.00011945716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974131,0.00018891763,0.0002152307,0.00148994,0.00020780486,0.00048502645],"domain_scores_gemma":[0.9965359,0.001464636,0.00021867569,0.0011125696,0.00046831777,0.0001998947],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005132179,0.00047106433,0.00038492904,0.00051541126,0.00025299902,0.00046248868,0.001340079,0.0002830446,0.000004484414],"category_scores_gemma":[0.0006086908,0.00047851552,0.00012031286,0.0016697384,0.00016180119,0.00019210091,0.0016900614,0.0010440339,0.000027960103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011226156,0.000056255914,0.018878989,0.00027002968,0.000043858152,0.0005153351,0.000120128636,0.97760683,0.000017386916,0.001555462,0.0005701423,0.00035437665],"study_design_scores_gemma":[0.00027814417,0.00022327107,0.000470583,0.001394291,0.00008364505,0.00001645322,0.000004544768,0.9798371,0.00046331235,0.016619818,0.00001475011,0.00059405545],"about_ca_topic_score_codex":0.00075028144,"about_ca_topic_score_gemma":0.000044501383,"teacher_disagreement_score":0.7995147,"about_ca_system_score_codex":0.00048115963,"about_ca_system_score_gemma":0.0008100448,"threshold_uncertainty_score":0.99976665},"labels":[],"label_agreement":null},{"id":"W4403935634","doi":"10.1145/3652620.3687793","title":"Concretize: A Model-Driven Tool for Scenario-Based Autonomous Vehicle Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Systems engineering; Engineering","score_opus":0.043968900466269646,"score_gpt":0.2870173616240917,"score_spread":0.24304846115782205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403935634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034650639,0.00007129409,0.9593587,0.0010704648,0.00013985558,0.00027802773,0.0000052106425,0.034646224,0.00096518715],"genre_scores_gemma":[0.41719705,1.6490577e-7,0.5818635,0.00055987167,0.00003569665,0.0000762474,0.0000018043398,0.000014037444,0.00025160887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881154,0.000019540386,0.00021190749,0.00048204872,0.00015781396,0.00031712768],"domain_scores_gemma":[0.9981242,0.001195782,0.00003262504,0.00045412485,0.0001274409,0.00006587014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003569242,0.00015036648,0.00014529393,0.000108377324,0.00014259249,0.00045309175,0.0005602166,0.00006935463,0.0000038159155],"category_scores_gemma":[0.0005374676,0.00013133026,0.000082005514,0.00037366926,0.000036662324,0.00024253326,0.00012820696,0.00012048569,0.000023362629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024053756,0.00012248728,0.0038502323,0.0005766509,0.000062327825,0.0001334066,0.0010437327,0.07541749,0.0079512745,0.18898486,0.20000602,0.52182746],"study_design_scores_gemma":[0.00013822719,0.00011116527,0.000028863395,0.00012496958,0.0000067831297,0.000010402117,4.645122e-7,0.96656376,0.0017779791,0.030086843,0.0009485407,0.00020201887],"about_ca_topic_score_codex":0.000051472183,"about_ca_topic_score_gemma":0.0000011041884,"teacher_disagreement_score":0.89114624,"about_ca_system_score_codex":0.00007318829,"about_ca_system_score_gemma":0.00036280308,"threshold_uncertainty_score":0.5355493},"labels":[],"label_agreement":null},{"id":"W4404341048","doi":"10.48550/arxiv.2410.21798","title":"Efficient Incremental Code Coverage Analysis for Regression Test Suites","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Waterloo","keywords":"Regression testing; Computer science; Code (set theory); Test (biology); Programming language; Code coverage; Regression analysis; Statistics; Mathematics; Machine learning; Software; Geology","score_opus":0.07111415282567106,"score_gpt":0.22798706258257947,"score_spread":0.15687290975690843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404341048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22480345,0.00015686764,0.76692843,0.00009791556,0.00038085252,0.00039461668,0.00015164359,0.0066082375,0.00047798254],"genre_scores_gemma":[0.98229176,0.00002571105,0.016698329,0.00007459232,0.00005869664,0.0000051964475,0.00005601706,0.00002318941,0.00076653756],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978521,0.00006926313,0.00023279378,0.0013507853,0.00013992327,0.00035516135],"domain_scores_gemma":[0.9967436,0.0014870638,0.0002274735,0.0012526198,0.00015295397,0.00013629318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046676415,0.0003512967,0.00042261154,0.00074089813,0.00020334557,0.00026708437,0.0015057783,0.00024446417,0.000009836773],"category_scores_gemma":[0.00050596154,0.00034914498,0.000484909,0.0014342644,0.00007610196,0.000048575712,0.003289746,0.0004527255,0.000030142191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008168874,0.0008223621,0.206715,0.00089451036,0.0016871708,0.0010151264,0.0007653159,0.6694427,0.00030638993,0.08918149,0.02566974,0.0034184742],"study_design_scores_gemma":[0.00018554508,0.00008001835,0.0013453267,0.00027171374,0.0004823701,0.0000031578545,0.000005603332,0.93071824,0.00033924115,0.06597755,0.00016785758,0.00042336178],"about_ca_topic_score_codex":0.0001506271,"about_ca_topic_score_gemma":0.000026423577,"teacher_disagreement_score":0.7574883,"about_ca_system_score_codex":0.00031245692,"about_ca_system_score_gemma":0.00015962422,"threshold_uncertainty_score":0.99989605},"labels":[],"label_agreement":null},{"id":"W4404406203","doi":"10.1007/s10664-024-10564-3","title":"Can search-based testing with pareto optimization effectively cover failure-revealing test inputs?","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; HORIZON EUROPE Reforming and enhancing the European Research and Innovation system; Technische Universität München; European Commission","keywords":"Cover (algebra); Pareto principle; Reliability engineering; Computer science; Engineering; Mathematical optimization; Mathematics; Mechanical engineering","score_opus":0.02105501579744261,"score_gpt":0.25535485620899456,"score_spread":0.23429984041155194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404406203","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073423116,0.00012425256,0.96389335,0.00089756557,0.00015640548,0.00024344794,0.000008736138,0.0273138,0.000020147896],"genre_scores_gemma":[0.50223076,4.2856695e-7,0.4973808,0.00019124176,0.00008827004,0.000043048265,0.0000075211474,0.00004749534,0.000010475882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979359,0.000051619278,0.0002743934,0.0006991413,0.00047843385,0.0005604955],"domain_scores_gemma":[0.99458957,0.0045320923,0.000042539166,0.00044581422,0.0001737889,0.00021620825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046048392,0.00034731237,0.00027279026,0.00030457298,0.00016379617,0.0005566832,0.00051436323,0.00012799974,0.000005486373],"category_scores_gemma":[0.003716754,0.00030074728,0.00007247796,0.0017888668,0.000043765172,0.00036013316,0.00017302678,0.00050930964,0.000017335931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028386903,0.00003612791,0.075687945,0.00023744257,0.00002318834,0.00016845696,0.00021039518,0.9183418,0.00008690227,0.0000359758,0.001760019,0.0034088911],"study_design_scores_gemma":[0.00016640047,0.00026221055,0.0048872125,0.0009815374,0.000015676287,0.00006682674,7.7028665e-7,0.99125594,0.0013018444,0.00013114183,0.00046228114,0.00046814798],"about_ca_topic_score_codex":0.000066041015,"about_ca_topic_score_gemma":0.0000022503655,"teacher_disagreement_score":0.49488842,"about_ca_system_score_codex":0.00027150623,"about_ca_system_score_gemma":0.000249433,"threshold_uncertainty_score":0.99994445},"labels":[],"label_agreement":null},{"id":"W4404514810","doi":"10.1145/3689944.3696162","title":"BinEq - A Benchmark of Compiled Java Programs to Assess Alternative Builds","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Java; Benchmark (surveying); Programming language; Software engineering; Operating system; Geography; Cartography","score_opus":0.10245218925202816,"score_gpt":0.3377391067043839,"score_spread":0.23528691745235575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404514810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08257225,0.000008348736,0.8923448,0.0009108861,0.00028848607,0.0003734319,0.0000024309475,0.018816002,0.004683382],"genre_scores_gemma":[0.5739671,0.0000015091622,0.42543948,0.00021012296,0.000028102204,0.000049542003,0.000004703055,0.000007782233,0.00029168592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988311,0.00004753901,0.00022059468,0.00032719856,0.00031195735,0.00026162513],"domain_scores_gemma":[0.9988116,0.00032168723,0.000072309194,0.00053254765,0.0001635563,0.000098302226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044420836,0.000117099546,0.00018610647,0.0002359345,0.000050044524,0.00008755173,0.00095589424,0.000037933187,0.000008801628],"category_scores_gemma":[0.00023741329,0.0000976955,0.00005370728,0.0014419748,0.000032419513,0.0001369766,0.00051432993,0.00007497561,0.00006125811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019940582,0.00049434684,0.11783014,0.000108954046,0.00009919903,0.00011297732,0.0030962224,0.0003627865,0.0019749685,0.0979443,0.3295534,0.4484028],"study_design_scores_gemma":[0.0011446759,0.0027433888,0.08343832,0.0007849112,0.00002419194,0.00005606725,0.00006666634,0.53886986,0.045870353,0.31411245,0.011367576,0.0015215719],"about_ca_topic_score_codex":0.0003135547,"about_ca_topic_score_gemma":0.000007830027,"teacher_disagreement_score":0.53850704,"about_ca_system_score_codex":0.000020517597,"about_ca_system_score_gemma":0.00004172198,"threshold_uncertainty_score":0.39839068},"labels":[],"label_agreement":null},{"id":"W4404860113","doi":"10.1007/s10664-024-10589-8","title":"Contrasting test selection, prioritization, and batch testing at scale","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Prioritization; Selection (genetic algorithm); Scale (ratio); Test (biology); Computer science; Regression testing; Reliability engineering; Engineering; Machine learning; Biology; Geography; Management science; Cartography; Operating system; Software","score_opus":0.016660816534096935,"score_gpt":0.2537672231562379,"score_spread":0.23710640662214097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404860113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043348573,0.0006820197,0.9247217,0.00028658434,0.0002671727,0.00010915838,0.0000023682023,0.030534482,0.000047935635],"genre_scores_gemma":[0.5154388,0.000004572682,0.48409325,0.000115907744,0.00019028597,0.000023278826,0.0000022334684,0.00003442233,0.00009726094],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986075,0.000016994296,0.00026447728,0.0005208901,0.0002209009,0.00036920185],"domain_scores_gemma":[0.9961893,0.0033158185,0.0000303802,0.00019340136,0.000118573036,0.00015251075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030727903,0.00020419822,0.00017694583,0.00015260198,0.00022343115,0.00037971485,0.00023659348,0.00009642054,0.0000043863693],"category_scores_gemma":[0.0056741484,0.00020713145,0.00003743677,0.0010801813,0.000026157899,0.0003449387,0.0002575862,0.00025193885,0.000016592112],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.019847e-7,0.000025287765,0.95486224,0.0002186542,0.000016156102,0.00004476535,0.00042505437,0.0011452684,0.0009108341,0.0001620083,0.009716628,0.03247243],"study_design_scores_gemma":[0.00011732141,0.0001045481,0.12222808,0.00054038747,0.000015067568,0.00051819626,0.0000011876617,0.8676903,0.0010444006,0.0020727196,0.0051730135,0.0004947563],"about_ca_topic_score_codex":0.00001469796,"about_ca_topic_score_gemma":0.0000015158278,"teacher_disagreement_score":0.8665451,"about_ca_system_score_codex":0.00014542507,"about_ca_system_score_gemma":0.000058954018,"threshold_uncertainty_score":0.84465754},"labels":[],"label_agreement":null},{"id":"W4405094850","doi":"10.48550/arxiv.2412.03843","title":"Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metamorphic rock; Test (biology); Computer science; Artificial intelligence; Geology; Paleontology","score_opus":0.2180923605641594,"score_gpt":0.27285307060026287,"score_spread":0.05476071003610347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405094850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14395933,0.0003269992,0.84840393,0.000084824445,0.00076542154,0.0008974894,0.00012148824,0.0052732965,0.00016722242],"genre_scores_gemma":[0.9368472,0.00001554531,0.06166931,0.000063453095,0.00019992798,0.000014412504,0.000023413428,0.000044129796,0.0011226292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741626,0.00018362024,0.00027725575,0.0014778259,0.0001359003,0.00050912006],"domain_scores_gemma":[0.9969475,0.0011277149,0.00013389047,0.0010377923,0.0005157358,0.00023735214],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005684894,0.00041126355,0.00046459356,0.0006205532,0.00042911165,0.000511246,0.0013588192,0.00024962192,0.0000034300756],"category_scores_gemma":[0.0004007086,0.00045742234,0.00019566003,0.0008633958,0.00009749037,0.00020843986,0.0024824128,0.0005621869,0.000054146334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011630248,0.00009280985,0.0022262377,0.00034274423,0.00016093416,0.001212049,0.00034297977,0.9427096,0.0003340829,0.044806127,0.0075106216,0.00025015994],"study_design_scores_gemma":[0.00010791952,0.0001511603,0.000087809385,0.0005117344,0.00009306243,0.00011209416,0.00002214197,0.98884964,0.00038609328,0.00890803,0.00023263953,0.00053770083],"about_ca_topic_score_codex":0.0008347879,"about_ca_topic_score_gemma":0.000014127382,"teacher_disagreement_score":0.79288787,"about_ca_system_score_codex":0.00072328874,"about_ca_system_score_gemma":0.0008861835,"threshold_uncertainty_score":0.99978775},"labels":[],"label_agreement":null},{"id":"W4405850275","doi":"10.36548/jitdw.2024.4.002","title":"Increasing Clustering Efficiency with QRDSO and WAC-HACK: A Hybrid Optimization Framework in Software Testing","year":2024,"lang":"en","type":"article","venue":"Journal of Information Technology and Digital World","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PotashCorp (Canada)","funders":"","keywords":"Cluster analysis; Software testing; Computer science; Software; Artificial intelligence; Programming language","score_opus":0.0071124343636870474,"score_gpt":0.22081059287896276,"score_spread":0.2136981585152757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405850275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058981445,0.00035226095,0.938425,0.00044359695,0.00005933315,0.000059879585,0.0000010420548,0.0013676845,0.00030976502],"genre_scores_gemma":[0.5777637,0.0000073649244,0.42216,0.000052872463,0.000008369299,0.0000014283007,4.947146e-7,0.0000029616072,0.0000028503039],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923956,0.000009738147,0.0003796842,0.000095584386,0.00013457991,0.00014085593],"domain_scores_gemma":[0.9990706,0.00047113354,0.00018777256,0.00010971495,0.00012014699,0.000040646533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003632024,0.00010234443,0.00014261599,0.0015251497,0.000083503284,0.00065543444,0.00019521335,0.000060039765,4.4012498e-7],"category_scores_gemma":[0.0015744996,0.00008036397,0.000014318438,0.0014145033,0.00008100589,0.0031269253,0.00015590228,0.000340815,9.03516e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004051674,0.00003337062,0.07632545,0.0002004006,0.000019387695,0.00012654337,0.00078765926,0.009323955,0.0000047087983,0.008862697,0.0001938091,0.9040815],"study_design_scores_gemma":[0.0004943829,0.0006287648,0.0029534462,0.005041107,0.000014177047,0.009423872,0.00011868624,0.8451687,0.00016826736,0.13511442,0.00047279237,0.0004013579],"about_ca_topic_score_codex":0.0000029346322,"about_ca_topic_score_gemma":7.8125305e-7,"teacher_disagreement_score":0.90368015,"about_ca_system_score_codex":0.000035924277,"about_ca_system_score_gemma":0.00006501842,"threshold_uncertainty_score":0.632037},"labels":[],"label_agreement":null},{"id":"W4406460194","doi":"10.1109/tps-isa62245.2024.00043","title":"Fine-Tuning LLMs for Code Mutation: A New Era of Cyber Threats","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Computer security; Code (set theory); Mutation; Internet privacy; Programming language; Genetics; Biology","score_opus":0.04922846117780114,"score_gpt":0.323486207207921,"score_spread":0.2742577460301198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406460194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007799341,0.00045265714,0.98715997,0.001733449,0.00021511436,0.0001082973,0.0000017978432,0.007919665,0.0016291196],"genre_scores_gemma":[0.23071149,0.0000020662474,0.76711434,0.0001431222,0.00006366521,0.00001498219,0.0000021173823,0.000008313869,0.0019399239],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939287,0.00000852632,0.00014225511,0.00022355486,0.00011106287,0.00012170619],"domain_scores_gemma":[0.999095,0.00051624543,0.000025744555,0.00026349956,0.00005767094,0.000041832882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017448748,0.00007349696,0.00009533517,0.000058974092,0.00003689888,0.00011042354,0.00028483535,0.00003340791,0.000013714502],"category_scores_gemma":[0.0001250656,0.000060024075,0.000055533226,0.00026644705,0.000014637339,0.00018173268,0.00007124099,0.00006717637,0.000010641149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002978349,0.000017615223,0.00031062952,0.000071161754,0.00002079914,0.000023820154,0.0011535006,0.00007786956,0.00020882259,0.107736014,0.19921438,0.6911624],"study_design_scores_gemma":[0.00017381577,0.00017818491,0.00025537866,0.00035112663,0.000012217314,0.00008028886,0.0000036168265,0.3972148,0.008264395,0.58918077,0.004092573,0.00019280468],"about_ca_topic_score_codex":0.00009743233,"about_ca_topic_score_gemma":0.000015827118,"teacher_disagreement_score":0.6909696,"about_ca_system_score_codex":0.000013174869,"about_ca_system_score_gemma":0.00011403068,"threshold_uncertainty_score":0.24477108},"labels":[],"label_agreement":null},{"id":"W4406688914","doi":"10.1016/b978-0-08-057206-2.50019-x","title":"10.1016/b978-0-08-057206-2.50019-x","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.0132082003442451,"score_gpt":0.19251967506130138,"score_spread":0.17931147471705627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406688914","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.300727e-8,0.00023601919,0.0012902668,0.0002527741,0.000009245674,0.00030997288,0.00002466085,0.01615003,0.981727],"genre_scores_gemma":[6.325458e-7,5.9731184e-7,0.027208187,0.00016018386,0.00025572334,0.00002629892,0.00002759965,0.00009570388,0.97222507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976365,0.000027755576,0.00042019578,0.00090494787,0.00052535284,0.00048522238],"domain_scores_gemma":[0.99749166,0.00026383204,0.00016445844,0.001672933,0.00013609549,0.0002710329],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028454076,0.0005512633,0.00052948465,0.0003992087,0.00014370822,0.00024805975,0.0019592927,0.0003873669,0.9372073],"category_scores_gemma":[0.00008880764,0.00056794914,0.00021297102,0.00012709787,0.00007097939,0.00017329166,0.0005197984,0.00048069571,0.9893143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058009728,0.0000098071705,6.2288015e-9,0.000007207077,0.000015462101,0.000032479,0.000008895507,0.000003542525,4.1624233e-7,0.0002860785,0.44672877,0.55290157],"study_design_scores_gemma":[0.00008948449,0.0002350601,5.3449804e-7,0.00027983953,0.000023396884,0.0000702588,1.0240177e-8,0.00046444908,0.0000115451985,0.01806725,0.9800853,0.0006728297],"about_ca_topic_score_codex":0.000023597833,"about_ca_topic_score_gemma":1.092798e-7,"teacher_disagreement_score":0.55222875,"about_ca_system_score_codex":0.00010336085,"about_ca_system_score_gemma":0.0001340107,"threshold_uncertainty_score":0.9996772},"labels":[],"label_agreement":null},{"id":"W4406866174","doi":"10.1145/3715008","title":"Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Reinforcement learning; Suite; Scalability; Minification; Similarity (geometry); Test (biology); Artificial intelligence; Software engineering; Machine learning; Test case; Programming language; Operating system","score_opus":0.04087899492526334,"score_gpt":0.2917156633049735,"score_spread":0.2508366683797102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406866174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067306927,0.00008041264,0.99257207,0.0003545817,0.00019545786,0.0001362995,0.0000012803806,0.005963729,0.000023099008],"genre_scores_gemma":[0.14192058,0.000047140762,0.8572,0.00024075777,0.000010690467,0.000059343784,0.0000038419157,0.000015537882,0.0005020677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888325,0.00010955156,0.00020404342,0.0003989814,0.000120325014,0.00028385752],"domain_scores_gemma":[0.9949325,0.0043269275,0.00004898452,0.0005229933,0.00009653943,0.00007206542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005198114,0.00019817566,0.00024440142,0.00035499458,0.00024833524,0.000071624796,0.00034780212,0.00013464851,0.0000055326846],"category_scores_gemma":[0.0023257807,0.00018560245,0.000040122326,0.00058144744,0.00004033226,0.00016255939,0.00003194706,0.0003870799,0.0000018496779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004394072,0.00010973517,0.007514234,0.00025126076,0.00012235259,0.000021797327,0.0006588008,0.7208798,0.00019694894,0.0013792531,0.0004772531,0.2683446],"study_design_scores_gemma":[0.0021569063,0.0020988304,0.006890507,0.001140158,0.00022132088,0.00027142288,0.000063285304,0.94634444,0.018546226,0.008020303,0.01277443,0.0014721571],"about_ca_topic_score_codex":0.000040912302,"about_ca_topic_score_gemma":0.0000024060303,"teacher_disagreement_score":0.26687247,"about_ca_system_score_codex":0.000046379708,"about_ca_system_score_gemma":0.000058524838,"threshold_uncertainty_score":0.75686485},"labels":[],"label_agreement":null},{"id":"W4407375771","doi":"10.1109/tse.2025.3541166","title":"Automated Test Case Repair Using Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Programming language; Test (biology); Software engineering; Model-based testing; Reliability engineering; Test case; Natural language processing; Machine learning","score_opus":0.016937912449282302,"score_gpt":0.264907490693648,"score_spread":0.2479695782443657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407375771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009358951,0.000096496624,0.90476704,0.000015470667,0.0004894387,0.00013186163,0.000010277585,0.08510706,0.000023427989],"genre_scores_gemma":[0.53487766,0.0000019415818,0.46496207,0.00006583085,0.000010554537,0.00002198244,3.5509353e-7,0.000017051023,0.000042596745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988812,0.00002033586,0.0002463415,0.0003911656,0.00015342658,0.0003074914],"domain_scores_gemma":[0.9984996,0.00063288596,0.00003498438,0.00068491016,0.000068299574,0.000079366284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017544035,0.00022297614,0.00018966875,0.00043648347,0.00021149157,0.00009569794,0.00031368807,0.00011118816,0.0000031618697],"category_scores_gemma":[0.00012691318,0.00024282468,0.00013082149,0.0008844071,0.000017425644,0.00035412257,0.000007101853,0.00028227543,0.0000058275978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022510148,0.00010507154,0.00004631103,0.0000817144,0.000044898872,0.0008406144,0.00036143404,0.98531306,0.0004115987,0.00015805714,0.0005646908,0.012070272],"study_design_scores_gemma":[0.00013793843,0.000032319575,0.000011976043,0.00021163725,0.000021244517,0.0006315795,0.000004883669,0.99227154,0.006227059,0.00019467971,0.00002675878,0.00022840318],"about_ca_topic_score_codex":0.00018095727,"about_ca_topic_score_gemma":0.000004738054,"teacher_disagreement_score":0.52551866,"about_ca_system_score_codex":0.00014644676,"about_ca_system_score_gemma":0.00007236205,"threshold_uncertainty_score":0.9902103},"labels":[],"label_agreement":null},{"id":"W4407416591","doi":"10.1007/978-3-031-81573-7_6","title":"Leveraging Conversational AI for Accelerating User-Driven Software Testing","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Software testing; Human–computer interaction; Software; Software engineering; Programming language","score_opus":0.048905755139386414,"score_gpt":0.26813146808301624,"score_spread":0.21922571294362983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407416591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002992717,0.00013047231,0.99638367,0.0009831651,0.00045989174,0.00062224275,0.000049601906,0.0007904907,0.00055056333],"genre_scores_gemma":[0.0029009057,0.000011249034,0.99626297,0.00052556314,0.00012949917,0.000054530155,0.00003731201,0.000015257366,0.00006273316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868125,0.000009420968,0.00061139057,0.00021597357,0.00023146752,0.00025049213],"domain_scores_gemma":[0.9966273,0.0018642389,0.00047905857,0.00054942176,0.00044213395,0.00003788427],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000425702,0.00028500013,0.00035467782,0.00024988482,0.0013552951,0.0003790437,0.0019978383,0.00019477437,2.9778968e-7],"category_scores_gemma":[0.00065919966,0.00025295926,0.00018110455,0.000265125,0.00023133616,0.0004686175,0.0009450107,0.00038348496,1.4827971e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014532075,0.000012815388,0.0000772065,0.00055982324,0.00009807952,9.0909715e-8,0.0014293724,0.8423688,0.0000059235394,0.08846105,0.0012155613,0.06576986],"study_design_scores_gemma":[0.00017675043,0.00005026281,0.000034179797,0.00060818705,0.000035503537,0.00000765475,0.0000010852735,0.97996205,0.000054333494,0.008686919,0.010088133,0.00029495865],"about_ca_topic_score_codex":0.00002953795,"about_ca_topic_score_gemma":0.000010239487,"teacher_disagreement_score":0.13759325,"about_ca_system_score_codex":0.00008892671,"about_ca_system_score_gemma":0.00039439605,"threshold_uncertainty_score":0.99999225},"labels":[],"label_agreement":null},{"id":"W4407639620","doi":"10.1109/acit62805.2024.10877022","title":"A Data-Driven Approach Towards Software Regression Testing Quality Optimization","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Becton Dickinson (Canada)","funders":"","keywords":"Regression testing; Computer science; Quality (philosophy); Software quality; Software testing; Regression analysis; Software; Reliability engineering; Machine learning; Software development; Software construction; Programming language; Engineering","score_opus":0.17284480908161898,"score_gpt":0.3693146945969045,"score_spread":0.19646988551528555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407639620","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009082857,0.0002143686,0.9537755,0.00028495467,0.000212522,0.00012533281,0.000012548241,0.041817054,0.0034668748],"genre_scores_gemma":[0.030496158,0.0000048589686,0.9689248,0.00016008667,0.000089178706,0.000017400596,0.00007694283,0.000017463368,0.00021307473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823046,0.00010856296,0.00028345129,0.00078441517,0.0003564604,0.00023663156],"domain_scores_gemma":[0.99773556,0.00056606776,0.00006338291,0.0014352618,0.00011987602,0.00007985248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000915199,0.00016603975,0.00016456847,0.00013381224,0.00014726071,0.0005782654,0.0014883128,0.000084879626,0.00000852326],"category_scores_gemma":[0.0021513575,0.00012244737,0.000035622743,0.0008631046,0.00003399798,0.00092021,0.001187015,0.00018808956,0.000016910057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032584787,0.00011716825,0.002015615,0.00033281077,0.000027800477,0.00004200986,0.00049647957,0.023806736,0.000031108782,0.0077606114,0.10502568,0.8603407],"study_design_scores_gemma":[0.000041115614,0.000026358537,0.0002581659,0.0001805489,0.0000055070855,0.000040770534,0.0000032168205,0.993093,0.000037393147,0.0056190356,0.00050535187,0.00018952534],"about_ca_topic_score_codex":0.00017822499,"about_ca_topic_score_gemma":0.0000010399166,"teacher_disagreement_score":0.96928626,"about_ca_system_score_codex":0.000047581238,"about_ca_system_score_gemma":0.00017283545,"threshold_uncertainty_score":0.5576227},"labels":[],"label_agreement":null},{"id":"W4407771524","doi":"10.1145/3641554.3701809","title":"How Effective and Efficient are Student-Written Software Tests?","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Universitas Brawijaya","keywords":"Computer science; Software testing; Software; Software engineering; Programming language","score_opus":0.008202861097243937,"score_gpt":0.26587968550532937,"score_spread":0.2576768244080854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407771524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053324644,0.0002789469,0.92956764,0.0022828076,0.00024141303,0.00036224807,0.0000012401949,0.013095969,0.00084509025],"genre_scores_gemma":[0.8240743,0.0000030296014,0.1742175,0.0007215432,0.000018568648,0.00006392392,3.3899002e-7,0.000006049422,0.000894709],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99899656,0.000055575565,0.000097708806,0.00044265133,0.00018449317,0.0002230385],"domain_scores_gemma":[0.99851364,0.0007675462,0.000050748542,0.0004976042,0.000109779336,0.000060663704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002346556,0.00014828505,0.00017128576,0.00015474245,0.00015891892,0.00044682762,0.00052856846,0.00005843669,7.7322613e-7],"category_scores_gemma":[0.0006996894,0.00012055536,0.00003874687,0.00043212343,0.00005553771,0.00011632273,0.00059150805,0.00012169579,0.0000041788403],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008565275,0.00041843776,0.44171843,0.00014833602,0.000081755796,0.000099095196,0.00086084066,0.000054437565,0.00011500911,0.023803134,0.06120243,0.47148952],"study_design_scores_gemma":[0.00089796114,0.0003843422,0.9166379,0.0006104381,0.000035334873,0.00004575056,0.00010143292,0.02056444,0.0021373332,0.055239722,0.0026359307,0.00070944126],"about_ca_topic_score_codex":0.000026411824,"about_ca_topic_score_gemma":0.000004725613,"teacher_disagreement_score":0.7707497,"about_ca_system_score_codex":0.000043057385,"about_ca_system_score_gemma":0.000025432826,"threshold_uncertainty_score":0.4916105},"labels":[],"label_agreement":null},{"id":"W4407848466","doi":"10.1145/3696443.3708929","title":"LLM-Vectorizer: LLM-Based Verified Loop Vectorizer","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Loop (graph theory); Mathematics","score_opus":0.011359170845947314,"score_gpt":0.26283494927821155,"score_spread":0.2514757784322642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407848466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032098414,0.00010539179,0.9566396,0.0013124348,0.0011673706,0.00016603828,0.0000010256077,0.023106452,0.014291848],"genre_scores_gemma":[0.5837663,0.000002692257,0.4098922,0.0026714876,0.00007844666,0.0000493597,0.000003164242,0.0000146380125,0.0035217046],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985282,0.00007018761,0.00024997877,0.00052373024,0.00026433228,0.00036359232],"domain_scores_gemma":[0.99808884,0.00055325835,0.00005857615,0.0010766493,0.00013541142,0.00008728619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035056268,0.00020534985,0.00022357218,0.00022702674,0.00015657271,0.00022076866,0.0010848204,0.00011384401,0.000039413317],"category_scores_gemma":[0.00046280219,0.00018197493,0.00009971431,0.0009281191,0.00005059327,0.0001828664,0.00023359054,0.0001827795,0.000083247214],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000427707,0.0007986341,0.012558133,0.0001233147,0.00007518167,0.00007309402,0.00018216792,0.00009421029,0.00415336,0.1702219,0.6763363,0.13534096],"study_design_scores_gemma":[0.003990074,0.0014796897,0.01996483,0.0008022215,0.00009464659,0.000028754037,0.00001047522,0.2691509,0.20850639,0.31582442,0.17740023,0.0027473618],"about_ca_topic_score_codex":0.00021317531,"about_ca_topic_score_gemma":0.0000053466765,"teacher_disagreement_score":0.58055645,"about_ca_system_score_codex":0.000085401334,"about_ca_system_score_gemma":0.00023822933,"threshold_uncertainty_score":0.7420722},"labels":[],"label_agreement":null},{"id":"W4408120458","doi":"10.5220/0013186800003896","title":"On the Generation of Input Space Model for Model-Driven Requirements-Based Testing","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Space (punctuation); Model-based testing; Systems engineering; Engineering; Operating system; Test case","score_opus":0.166819225024256,"score_gpt":0.33517492766224016,"score_spread":0.16835570263798416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408120458","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005009769,0.000004618139,0.9893242,0.0019808877,0.000039317343,0.000259655,0.0000015756874,0.001870342,0.0015096341],"genre_scores_gemma":[0.48988563,1.13611684e-7,0.5089168,0.0009096318,0.0000056751387,0.000039990602,8.478315e-7,0.000002930459,0.00023840157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932235,0.0000223918,0.00016504657,0.00021911711,0.00014483155,0.00012626835],"domain_scores_gemma":[0.9985403,0.00070064527,0.000075818745,0.00047108295,0.0001963318,0.000015819454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036412658,0.00008427098,0.00008846508,0.00008072878,0.00013191726,0.000051824543,0.00044242735,0.00003488103,4.1914026e-7],"category_scores_gemma":[0.00087243016,0.000058588197,0.000037596532,0.00025237858,0.000022279417,0.00008467263,0.00008325496,0.000050071205,5.188357e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036179758,0.00004036721,0.00019152765,0.000016244343,0.000004886309,9.5532734e-8,0.000079309495,0.72799885,0.0035039072,0.23375708,0.029912284,0.00449182],"study_design_scores_gemma":[0.00009678324,0.000047661324,0.000005246957,0.000055692526,0.0000035263527,7.80194e-8,4.3998205e-7,0.86302525,0.0144635495,0.1222434,0.0000047010094,0.000053660093],"about_ca_topic_score_codex":0.00002178638,"about_ca_topic_score_gemma":0.0000035546373,"teacher_disagreement_score":0.48487586,"about_ca_system_score_codex":0.00003486824,"about_ca_system_score_gemma":0.00015432475,"threshold_uncertainty_score":0.23891573},"labels":[],"label_agreement":null},{"id":"W4408729936","doi":"10.63485/waect-f7t64","title":"Beta testers needed for Canadian public domain registry","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public domain; Domain (mathematical analysis); Business; Computer science; Geography; Mathematics","score_opus":0.056251919102948654,"score_gpt":0.2695010204006764,"score_spread":0.21324910129772776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408729936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020714125,0.00011060664,0.94548523,0.019519951,0.00089934154,0.0007728688,0.00003485182,0.018310506,0.01279523],"genre_scores_gemma":[0.10916855,0.000013444584,0.88639605,0.0029267145,0.00016251112,0.00026555554,0.000059790404,0.000035445144,0.0009719117],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99789923,0.00004674271,0.00032029275,0.00083637354,0.00024318443,0.00065417675],"domain_scores_gemma":[0.9967796,0.0003518012,0.00017907895,0.0020002606,0.00022100387,0.00046826128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042608863,0.00032453766,0.0003320875,0.00044649825,0.0003237598,0.00060705666,0.0027053568,0.00032405215,0.0000049394084],"category_scores_gemma":[0.00044645093,0.00031868796,0.00018338581,0.0002639983,0.00008429678,0.00016389493,0.00085848244,0.00042221026,0.000012486967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012809941,0.000027663742,0.0027054735,0.0000767978,0.000032978278,0.000044541048,0.0002686627,0.000010547021,0.0000027255219,0.015951201,0.9669733,0.013904841],"study_design_scores_gemma":[0.00074606296,0.00021384544,0.0015898184,0.0005152299,0.000027293734,0.0006201443,0.000043478984,0.030545063,0.000410744,0.68486583,0.27766496,0.0027575188],"about_ca_topic_score_codex":0.11767062,"about_ca_topic_score_gemma":0.018126108,"teacher_disagreement_score":0.68930835,"about_ca_system_score_codex":0.00030864985,"about_ca_system_score_gemma":0.0020991124,"threshold_uncertainty_score":0.9999265},"labels":[],"label_agreement":null},{"id":"W4408734932","doi":"10.1007/s42979-025-03800-0","title":"A Mechanized Method for Risk-Based Test Case Generation and Prioritization by an Improved Correlation System","year":2025,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tornado Spectral Systems (Canada)","funders":"","keywords":"Prioritization; Test (biology); Reliability engineering; Computer science; Correlation; Risk analysis (engineering); Statistics; Engineering; Mathematics; Geology; Business; Management science","score_opus":0.012951214921615752,"score_gpt":0.28994047690220215,"score_spread":0.2769892619805864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408734932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003406934,0.000037945832,0.9920713,0.00013708671,0.00058035133,0.00054438453,0.000009646626,0.003201522,0.000010846798],"genre_scores_gemma":[0.38018098,5.0591115e-7,0.61956644,0.00015585758,0.00003786613,0.00004213523,0.0000055833475,0.0000041273415,0.000006476102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984851,0.00011888668,0.00024840434,0.00072258903,0.00018939977,0.00023563553],"domain_scores_gemma":[0.99818003,0.00064090535,0.00016985748,0.0005141224,0.00040324082,0.000091836526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001954461,0.00014150397,0.00014961266,0.00027417828,0.00076366216,0.00067082327,0.0004974297,0.00006535319,1.2165113e-7],"category_scores_gemma":[0.00046197593,0.00013683569,0.000026035708,0.0010192344,0.00006713796,0.0007194067,0.00015848949,0.00008028208,3.7804693e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011841608,0.00016140348,0.0020268678,0.00014594436,0.0000089332,0.000019975745,0.0005948831,0.0031961792,0.02906848,0.021046875,0.003204205,0.9405144],"study_design_scores_gemma":[0.00038362175,0.00022663723,0.00010133442,0.000049963473,0.000010835012,0.00008527913,0.0000020390141,0.98466843,0.0106560625,0.0036412044,0.000026224972,0.00014835961],"about_ca_topic_score_codex":0.0001758929,"about_ca_topic_score_gemma":0.000010001247,"teacher_disagreement_score":0.98147225,"about_ca_system_score_codex":0.0001207965,"about_ca_system_score_gemma":0.00023680729,"threshold_uncertainty_score":0.64687645},"labels":[],"label_agreement":null},{"id":"W4408851891","doi":"10.1145/3725212","title":"Towards On-the-Fly Code Performance Profiling","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"National Key Research and Development Program of China","keywords":"Computer science; Profiling (computer programming); On the fly; Programming language; Software engineering; Operating system","score_opus":0.088324649823905,"score_gpt":0.3216710607829046,"score_spread":0.23334641095899958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408851891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011264966,0.00011360438,0.98125535,0.0012073652,0.00060199766,0.00013628701,0.0000033546087,0.0053654024,0.00005166796],"genre_scores_gemma":[0.14231686,0.000058060352,0.8566374,0.0007073841,0.000017672477,0.00009177348,6.226311e-7,0.000012561227,0.00015763783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891007,0.0001406869,0.00018931463,0.00037090472,0.000113023656,0.00027599162],"domain_scores_gemma":[0.9949314,0.004143266,0.0000330005,0.00078465027,0.000054644945,0.00005302036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009904177,0.00018647283,0.00021380359,0.00025897057,0.00025000735,0.000052258827,0.00065064034,0.00011959337,0.0000037778993],"category_scores_gemma":[0.0022594372,0.00014902072,0.000060245566,0.00044226553,0.000050276798,0.000089264984,0.00003365813,0.00043847252,0.000004301174],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034758876,0.00007684087,0.00057692075,0.00015047927,0.00010103387,0.0000087175995,0.0004445989,0.018930165,0.0003772582,0.020886628,0.0006934613,0.95771915],"study_design_scores_gemma":[0.0020595398,0.0023989633,0.013497296,0.0020010015,0.00023744449,0.0004954943,0.00007003049,0.5028499,0.3312757,0.111971065,0.030533083,0.0026105],"about_ca_topic_score_codex":0.000015467867,"about_ca_topic_score_gemma":5.9558846e-7,"teacher_disagreement_score":0.95510864,"about_ca_system_score_codex":0.000036137055,"about_ca_system_score_gemma":0.000059345588,"threshold_uncertainty_score":0.60768884},"labels":[],"label_agreement":null},{"id":"W4409077140","doi":"10.1109/tbdata.2025.3556615","title":"Utility-Driven Data Analytics Algorithm for Transaction Modifications Using Pre-Large Concept With Single Database Scan","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Database transaction; Analytics; Database; Transaction processing; Data mining; Transaction data; Algorithm; Transaction log; Distributed transaction","score_opus":0.2046491776236223,"score_gpt":0.3506634177596448,"score_spread":0.14601424013602252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409077140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000107626234,0.00005022339,0.98497474,0.00031057774,0.00058976223,0.0005964316,0.010885365,0.0024531959,0.00003209601],"genre_scores_gemma":[0.3086544,0.0000186274,0.6898686,0.00016071938,0.00005059634,0.000035601326,0.0010758628,0.000022267399,0.000113328584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997641,0.000090264984,0.00037233654,0.0012057582,0.0003068527,0.00038377795],"domain_scores_gemma":[0.99332064,0.00046729975,0.00012413802,0.0057920762,0.0001869223,0.000108919274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044247496,0.00025536335,0.0002582278,0.00034249408,0.00070319884,0.00025700594,0.0030513944,0.00010435013,0.0000053397102],"category_scores_gemma":[0.00004692887,0.0002489482,0.00004835842,0.0010456811,0.00013696804,0.001323324,0.000044268607,0.0002852978,0.0000021073427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005056488,0.0013643601,0.000028020726,0.0000733205,0.00021296713,0.00000517989,0.0002023866,0.004781262,0.00061803684,0.00016836644,0.009364096,0.9831314],"study_design_scores_gemma":[0.0005851764,0.00010330808,0.00003625224,0.00018233147,0.00019681585,0.000015423024,0.00001572079,0.99014896,0.0045056236,0.0003057851,0.0036404673,0.00026412762],"about_ca_topic_score_codex":0.00034771542,"about_ca_topic_score_gemma":0.00030613848,"teacher_disagreement_score":0.9853677,"about_ca_system_score_codex":0.00008550451,"about_ca_system_score_gemma":0.00041483247,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4409602065","doi":"10.1007/978-3-031-85859-8_13","title":"Cross Language Soccer Framework: An Open Source Framework for the RoboCup 2D Soccer Simulation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Pleiades Robotics (Canada)","funders":"","keywords":"Computer science; Open source; Artificial intelligence; Human–computer interaction; Programming language","score_opus":0.037695864528258786,"score_gpt":0.36416690756772285,"score_spread":0.32647104303946406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409602065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020180561,0.0005037881,0.9921686,0.0012962037,0.001608807,0.0013436982,0.000012481795,0.002665508,0.0003807503],"genre_scores_gemma":[0.06165292,0.000009676617,0.93001556,0.0065704277,0.0007360738,0.00008328715,0.000008820278,0.000056924586,0.0008662979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958954,0.00007008553,0.00058050186,0.0018543823,0.0008070148,0.0007926536],"domain_scores_gemma":[0.98654914,0.0095390575,0.00040521214,0.0029438045,0.00041855135,0.00014426548],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002039093,0.0006108902,0.00057166145,0.0004369034,0.0010250116,0.0036166261,0.009689765,0.00074959,0.000027863603],"category_scores_gemma":[0.002013312,0.00046945535,0.00016955174,0.00074482313,0.000686463,0.0009341549,0.0038110423,0.0014138242,0.000010506401],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012681654,0.000029055307,0.00015993422,0.00003479655,0.000015187089,0.00000793,0.0018094917,0.17432535,0.0000026543728,0.040345654,0.0001460744,0.7831112],"study_design_scores_gemma":[0.00008667388,0.000092468115,0.00011194642,0.00050264876,0.0000101445285,0.000005573034,1.9445385e-7,0.5012276,0.00008490446,0.49641624,0.0010990357,0.00036257965],"about_ca_topic_score_codex":0.00013897358,"about_ca_topic_score_gemma":0.000028614404,"teacher_disagreement_score":0.78274864,"about_ca_system_score_codex":0.00024898324,"about_ca_system_score_gemma":0.0005952957,"threshold_uncertainty_score":0.9997757},"labels":[],"label_agreement":null},{"id":"W4409728046","doi":"10.1016/j.jss.2025.112453","title":"An empirical evaluation of static, dynamic, and hybrid slicing of WebAssembly binaries","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Slicing; Computer science; Computer graphics (images)","score_opus":0.027482611779639187,"score_gpt":0.346174844022441,"score_spread":0.3186922322428018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409728046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5768839,0.0017965245,0.42089495,0.000098951125,0.00013732625,0.00007524199,0.0000024336523,0.000102277925,0.000008414296],"genre_scores_gemma":[0.9453214,0.000042769567,0.054583147,0.000025812313,0.000012982906,0.0000019016452,4.2947894e-7,0.00000388993,0.000007667082],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867356,0.0001795471,0.0005318773,0.00012374017,0.00039888624,0.00009239286],"domain_scores_gemma":[0.998036,0.00043343825,0.00048380235,0.00020909306,0.0007843,0.00005331623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001981071,0.000086318396,0.00033342675,0.00024729557,0.000062883,0.000080892554,0.00020930459,0.000040056177,3.8654616e-7],"category_scores_gemma":[0.0007140242,0.00006757293,0.000035382902,0.00016713294,0.000056261084,0.0003063645,0.000061167564,0.00009338633,3.8355346e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008676796,0.0003656274,0.6455732,0.0022381204,0.00026287523,0.000044505516,0.006640668,0.0022085612,0.0023908264,0.0024658055,0.007390176,0.33033285],"study_design_scores_gemma":[0.0018516955,0.0019427114,0.17065494,0.004925593,0.0002773386,0.00067042187,0.0006271412,0.76277494,0.0017805296,0.053882882,0.00024231893,0.0003695154],"about_ca_topic_score_codex":0.00008317034,"about_ca_topic_score_gemma":0.0000028167096,"teacher_disagreement_score":0.76056635,"about_ca_system_score_codex":0.000034183755,"about_ca_system_score_gemma":0.00020309674,"threshold_uncertainty_score":0.27555442},"labels":[],"label_agreement":null},{"id":"W4409795042","doi":"10.61091/jcmcc127b-386","title":"RESTful API-based software interface testing techniques and common problems analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Software testing; Software engineering; Interface (matter); Software; Operating system; Programming language","score_opus":0.018204846784951725,"score_gpt":0.2816590800225939,"score_spread":0.26345423323764217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409795042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1524381,0.0010490993,0.839511,0.00037734373,0.0035274639,0.0004342187,0.0000014683266,0.0021005294,0.00056078465],"genre_scores_gemma":[0.70015097,0.000009831219,0.29960704,0.000039996692,0.00016775225,0.0000037478098,4.583192e-7,0.000016332731,0.0000039059714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972704,0.00017930058,0.001252733,0.00039103083,0.0005382972,0.0003682259],"domain_scores_gemma":[0.99423623,0.00309251,0.0011559583,0.0005380672,0.0008111123,0.00016614106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024788093,0.00036145936,0.0010224,0.0008519333,0.00040368244,0.000670671,0.0009799494,0.00020411654,5.9267876e-7],"category_scores_gemma":[0.0018782691,0.00032761582,0.00018697651,0.0018358423,0.00013502734,0.00030788896,0.0006994018,0.00061557133,2.955832e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013453208,0.0018943337,0.049913663,0.001987361,0.0014292353,0.00019196994,0.0023652057,0.0006377857,0.00067302457,0.796374,0.0018816183,0.14251725],"study_design_scores_gemma":[0.0016376772,0.00088212424,0.00046416855,0.0016701445,0.00037925952,0.00010308413,0.000025133046,0.082917675,0.002400566,0.9086914,0.00040275953,0.00042598974],"about_ca_topic_score_codex":0.000049168393,"about_ca_topic_score_gemma":8.738519e-7,"teacher_disagreement_score":0.5477128,"about_ca_system_score_codex":0.0001004568,"about_ca_system_score_gemma":0.00021103479,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W4410344404","doi":"10.1145/3735553","title":"Large Language Models for Automated Web-Form-Test Generation: An Empirical Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Software engineering; Web application; Natural language processing; Programming language; World Wide Web; Information retrieval","score_opus":0.10826609347819456,"score_gpt":0.39020246290793753,"score_spread":0.281936369429743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410344404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03186381,0.00010234411,0.95178664,0.00018467382,0.0004041658,0.00031964053,0.00001929288,0.015316723,0.0000027011351],"genre_scores_gemma":[0.3135576,0.000006053249,0.6859276,0.0002336763,0.000027066471,0.0001727869,0.0000059270246,0.000013756957,0.00005550555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987487,0.00016332814,0.00023587319,0.00046732553,0.000092660535,0.00029209486],"domain_scores_gemma":[0.9960326,0.0030528533,0.000032771022,0.0007172469,0.00008163228,0.00008291172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010318039,0.00019289664,0.0002743344,0.00031992584,0.00023362883,0.00007263767,0.00043153824,0.00014466482,0.000001996026],"category_scores_gemma":[0.001588337,0.00018780379,0.000059674618,0.0003762717,0.000017532753,0.00022704597,0.000027882314,0.00021114839,8.3988465e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016257248,0.0053170673,0.009873119,0.00056896947,0.0007884064,0.00011505817,0.036108814,0.29474047,0.004995228,0.0068088043,0.009807663,0.6307138],"study_design_scores_gemma":[0.0006277429,0.0005282648,0.0006150365,0.000023828576,0.000039595867,0.00002562179,0.000059287013,0.99400026,0.000804028,0.0027803609,0.0002818047,0.0002141893],"about_ca_topic_score_codex":0.000018123923,"about_ca_topic_score_gemma":0.000012713529,"teacher_disagreement_score":0.69925976,"about_ca_system_score_codex":0.000034365858,"about_ca_system_score_gemma":0.00006556336,"threshold_uncertainty_score":0.7658416},"labels":[],"label_agreement":null},{"id":"W4410394325","doi":"10.1109/tse.2025.3570897","title":"Using Cooperative Co-Evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Evolutionary algorithm; Artificial intelligence; Distributed computing; Geology","score_opus":0.047251793029374996,"score_gpt":0.3055320633810115,"score_spread":0.25828027035163653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410394325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008792962,0.00015359906,0.98171747,0.00005833947,0.0010002222,0.0006137702,0.000055945326,0.0076009776,0.0000066947396],"genre_scores_gemma":[0.5774199,0.0000030920005,0.4220361,0.0000688372,0.000043326734,0.00022737344,0.0000020413718,0.000025897993,0.00017344068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846196,0.00004268531,0.00031968975,0.0005291216,0.00021052122,0.00043599153],"domain_scores_gemma":[0.9971633,0.0019109722,0.000035824334,0.0004997701,0.00025666656,0.00013348549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003138952,0.00027699966,0.00029736655,0.00062945235,0.00048133268,0.00023889437,0.0004533585,0.000103660714,0.000002403598],"category_scores_gemma":[0.00032874374,0.0002996254,0.00011044067,0.00091343396,0.000023965726,0.0002900104,0.000009353593,0.00025902642,0.00000855636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045432016,0.00006588204,0.00014119808,0.00007893083,0.000053140157,0.00001832536,0.00011898856,0.9939077,0.0017509765,0.00034737552,0.00075828726,0.0027546776],"study_design_scores_gemma":[0.00018614542,0.00016623273,0.000120013035,0.0003743316,0.000030698022,0.00009220784,0.000007512775,0.97673965,0.021457652,0.00002382831,0.00045604442,0.00034568572],"about_ca_topic_score_codex":0.000109632616,"about_ca_topic_score_gemma":0.0000027387175,"teacher_disagreement_score":0.56862694,"about_ca_system_score_codex":0.00036188474,"about_ca_system_score_gemma":0.00024259173,"threshold_uncertainty_score":0.9999456},"labels":[],"label_agreement":null},{"id":"W4410538223","doi":"10.1109/icst62969.2025.10989029","title":"ML-Based Test Case Prioritization: A Research and Production Perspective in CI Environments","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Prioritization; Perspective (graphical); Test (biology); Production (economics); Computer science; Reliability engineering; Risk analysis (engineering); Engineering; Process management; Artificial intelligence; Business; Geology","score_opus":0.04430461546752107,"score_gpt":0.3633840419375879,"score_spread":0.3190794264700668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410538223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064658076,0.0003640297,0.90854377,0.013582863,0.00017883825,0.000907655,0.0000014573164,0.0045844554,0.0071788374],"genre_scores_gemma":[0.89708567,0.0000064294422,0.101939395,0.000095405034,0.000014950824,0.000037679478,3.7688844e-7,0.000003000445,0.0008171216],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99919623,0.00006185924,0.000092383685,0.0003654749,0.00014264358,0.00014143651],"domain_scores_gemma":[0.9992479,0.00033633475,0.00001394807,0.0003046961,0.000071788454,0.000025345324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055644644,0.000056648398,0.000059104776,0.00029297188,0.00013497005,0.000082743056,0.000139172,0.00003425939,0.0000020990253],"category_scores_gemma":[0.0012015282,0.000054419466,0.00000667937,0.00073694997,0.00008080115,0.00012939551,0.00012895149,0.00012934861,0.0000034138168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043217355,0.0026307367,0.6280366,0.00019236786,0.00002524637,0.0024947664,0.0053948895,0.00024002789,0.0023167946,0.17232688,0.058064435,0.128234],"study_design_scores_gemma":[0.0013528741,0.00086385215,0.06142004,0.0005881501,0.000008098594,0.0008720213,0.0005691275,0.20121922,0.027650606,0.70286614,0.0019412924,0.00064857287],"about_ca_topic_score_codex":0.0003927464,"about_ca_topic_score_gemma":0.00004221126,"teacher_disagreement_score":0.83242756,"about_ca_system_score_codex":0.00014975842,"about_ca_system_score_gemma":0.000068184134,"threshold_uncertainty_score":0.22191615},"labels":[],"label_agreement":null},{"id":"W4411058752","doi":"10.1145/3727582.3728681","title":"Leveraging LLM Enhanced Commit Messages to Improve Machine Learning Based Test Case Prioritization","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Ontario Tech University","funders":"","keywords":"Commit; Prioritization; Computer science; Test (biology); Machine learning; Artificial intelligence; Process management; Engineering; Database","score_opus":0.01080975645387326,"score_gpt":0.26644774812461836,"score_spread":0.2556379916707451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411058752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050185607,0.000038175313,0.97913736,0.0015294424,0.00015149516,0.0002070393,0.0000011202159,0.011039349,0.0028774326],"genre_scores_gemma":[0.68958634,9.598958e-7,0.30795678,0.0012433807,0.000014114494,0.00002623183,0.0000023859445,0.000007544597,0.0011622708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989036,0.000067900306,0.0002146829,0.00041940997,0.00014838252,0.00024608077],"domain_scores_gemma":[0.99826175,0.000983744,0.000057648176,0.0004791008,0.00014454935,0.000073237374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041525316,0.00015295132,0.0001558852,0.00023592985,0.0003011132,0.00025206056,0.0004224522,0.000051766692,0.000010434442],"category_scores_gemma":[0.0015759318,0.00014697568,0.000038170398,0.00071552437,0.000016497803,0.0001808805,0.00027132832,0.00019450313,0.00001136751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020769456,0.00056253327,0.05068899,0.00028210046,0.00004540868,0.0008629817,0.0019661405,0.005790497,0.029467562,0.005881675,0.027609907,0.87682146],"study_design_scores_gemma":[0.00041476107,0.00022516452,0.0008203891,0.0002057756,0.000010853027,0.000054085154,0.000015748376,0.89612615,0.096054785,0.004415614,0.0012954542,0.00036123316],"about_ca_topic_score_codex":0.0004366867,"about_ca_topic_score_gemma":0.000026238702,"teacher_disagreement_score":0.8903356,"about_ca_system_score_codex":0.00006844753,"about_ca_system_score_gemma":0.000081556485,"threshold_uncertainty_score":0.59934944},"labels":[],"label_agreement":null},{"id":"W4411087888","doi":"10.1145/3742894","title":"The Havoc Paradox in Generator-Based Fuzzing","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Computer science; Generator (circuit theory); Programming language; Software; Power (physics)","score_opus":0.0603762164017855,"score_gpt":0.3174931715724063,"score_spread":0.25711695517062083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411087888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036697853,0.0005996084,0.9909579,0.0009103751,0.00056014105,0.0000940335,0.000001046057,0.0032004658,0.0000066316125],"genre_scores_gemma":[0.12888606,0.000052675292,0.87054634,0.0003648936,0.000011209586,0.00008036626,4.0065476e-7,0.000009635844,0.000048431375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890786,0.00020960205,0.00020716552,0.00031831925,0.00007953326,0.00027753704],"domain_scores_gemma":[0.99205565,0.007169219,0.000028140772,0.0006680635,0.000033541877,0.000045362973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010995426,0.00014954415,0.0001871535,0.00028745778,0.00022425625,0.00006950423,0.0005308977,0.00011188429,7.1998096e-7],"category_scores_gemma":[0.002217167,0.00012408358,0.000050672224,0.000512468,0.000044699278,0.000066643515,0.000021415934,0.00033684765,0.0000012123453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024255653,0.000057023037,0.0018348153,0.00005600943,0.00004029771,0.00001836065,0.00024100553,0.044420496,0.00037429566,0.006706925,0.0003516169,0.9458749],"study_design_scores_gemma":[0.003139637,0.0007291164,0.02266729,0.0010390946,0.00011491533,0.0001708871,0.000058474772,0.7438399,0.047454428,0.14404854,0.034788005,0.0019497087],"about_ca_topic_score_codex":0.000044392913,"about_ca_topic_score_gemma":0.000009082593,"teacher_disagreement_score":0.9439252,"about_ca_system_score_codex":0.000041242693,"about_ca_system_score_gemma":0.00006553103,"threshold_uncertainty_score":0.5059982},"labels":[],"label_agreement":null},{"id":"W4411113098","doi":"10.18653/v1/2025.findings-naacl.197","title":"TESTEVAL: Benchmarking Large Language Models for Test Case Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmarking; Computer science; Test (biology); Programming language; Natural language processing; Geology","score_opus":0.032397878695373764,"score_gpt":0.31183753192380914,"score_spread":0.2794396532284354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411113098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028135502,0.000109295375,0.98732674,0.000313611,0.0001679195,0.0002121322,0.000005004019,0.0063430737,0.0027086695],"genre_scores_gemma":[0.519079,9.4596396e-7,0.47971517,0.0005692628,0.000060241367,0.000047697973,0.0000049199757,0.000004290565,0.0005184297],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927336,0.000017465289,0.000146337,0.00028271857,0.00007858344,0.00020156376],"domain_scores_gemma":[0.9988453,0.0005890579,0.000034789693,0.00040927416,0.00009069014,0.0000309193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038772635,0.00009182998,0.00009097526,0.000112725116,0.00019509647,0.00016229086,0.000264217,0.0000492416,0.0000031057086],"category_scores_gemma":[0.0003936134,0.00008262067,0.000041767395,0.00025868858,0.000008273279,0.0002564327,0.00013931854,0.000052680123,0.000001798039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003178704,0.00033608745,0.0028435595,0.000119459335,0.000027897842,0.0004259263,0.0020249346,0.0010041457,0.002357102,0.3388038,0.34092072,0.3111332],"study_design_scores_gemma":[0.00014845197,0.00004337662,0.000015063118,0.00002533608,0.0000050902327,0.000097757,0.000008172824,0.9678833,0.002372333,0.028906738,0.00039204766,0.000102323764],"about_ca_topic_score_codex":0.00011319341,"about_ca_topic_score_gemma":0.000058678914,"teacher_disagreement_score":0.9668792,"about_ca_system_score_codex":0.000030396577,"about_ca_system_score_gemma":0.000051030085,"threshold_uncertainty_score":0.33691728},"labels":[],"label_agreement":null},{"id":"W4411271577","doi":"10.1109/msr66628.2025.00022","title":"Revisiting Defects4J for Fault Localization in Diverse Development Scenarios","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Concordia University","funders":"","keywords":"Computer science; Fault (geology); Development (topology); Systems engineering; Geology; Engineering; Seismology; Mathematics","score_opus":0.023507470805200638,"score_gpt":0.2886050368149066,"score_spread":0.26509756600970596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411271577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016329022,0.00003445087,0.9934924,0.0002538718,0.0000715644,0.00019272743,1.0725842e-7,0.0031547332,0.0011672449],"genre_scores_gemma":[0.36463457,0.0000015014352,0.6342137,0.0009013149,0.00000955976,0.000040363302,0.000001986806,0.0000028436755,0.00019416286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993716,0.00001960962,0.00016498445,0.000218626,0.00007544951,0.00014973349],"domain_scores_gemma":[0.99945897,0.00023646087,0.00003238324,0.00018072138,0.00007272295,0.000018747127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034996888,0.00006795142,0.00008434016,0.0001532991,0.00010678339,0.00007225421,0.00027255568,0.000036489797,0.0000014330752],"category_scores_gemma":[0.00050226663,0.00006350533,0.000020074338,0.0004075763,0.0000079944975,0.000117947406,0.00015976293,0.00004027874,0.000004035838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066865537,0.000057911693,0.06816461,0.00019202456,0.000010973362,0.0000073612628,0.0010317696,0.0027561947,0.000038576527,0.051559366,0.026071347,0.8501032],"study_design_scores_gemma":[0.00042046804,0.000022412221,0.0030746008,0.0005690061,0.000003557376,0.0000020134264,0.000019613359,0.9505616,0.0032758443,0.028754871,0.013059429,0.0002365989],"about_ca_topic_score_codex":0.000045617602,"about_ca_topic_score_gemma":0.000013268486,"teacher_disagreement_score":0.9478054,"about_ca_system_score_codex":0.00007438368,"about_ca_system_score_gemma":0.00008970475,"threshold_uncertainty_score":0.25896722},"labels":[],"label_agreement":null},{"id":"W4411300576","doi":"10.1007/978-3-031-95497-9_2","title":"Temporal and Spatial Fault Detection for Connected Cyber-Physical Systems","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Cyber-physical system; Fault (geology); Fault detection and isolation; Real-time computing; Artificial intelligence; Operating system; Seismology; Geology","score_opus":0.01582217726198094,"score_gpt":0.25824702030820834,"score_spread":0.2424248430462274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411300576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016312415,0.00019845601,0.99432147,0.00020085111,0.0015951075,0.0006830312,0.000009489134,0.0025416475,0.00028682023],"genre_scores_gemma":[0.74117327,0.0000055928554,0.25780928,0.00028359905,0.0004702375,0.000051180683,0.000006098642,0.0000236473,0.00017711955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739814,0.00003391828,0.0003584483,0.0012902785,0.00047717182,0.00044202863],"domain_scores_gemma":[0.9969964,0.0015249635,0.0002254991,0.0008176603,0.0003256627,0.00010981732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055280677,0.00041987523,0.00051711616,0.0005981816,0.00029672004,0.0006047298,0.0012781917,0.000286203,4.0132085e-7],"category_scores_gemma":[0.00036259484,0.0003846678,0.00009508726,0.00038058884,0.0003710285,0.0002515478,0.00070647843,0.0004714728,0.0000020340196],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008551359,0.000018740126,0.00006678882,0.00009216667,0.000009468578,0.000013447168,0.00022429429,0.0013390632,0.00006971651,0.0049164738,0.00010683282,0.99313444],"study_design_scores_gemma":[0.00019666072,0.00024810943,0.000050796792,0.0004507342,0.00000907197,0.000059816986,3.176474e-8,0.8046558,0.0008586699,0.19251962,0.00056365813,0.0003870597],"about_ca_topic_score_codex":0.00040757493,"about_ca_topic_score_gemma":0.000097604905,"teacher_disagreement_score":0.9927474,"about_ca_system_score_codex":0.00017933984,"about_ca_system_score_gemma":0.00031832178,"threshold_uncertainty_score":0.9998605},"labels":[],"label_agreement":null},{"id":"W4411440374","doi":"10.1007/s10664-025-10661-x","title":"Supporting multi-dimensional unit test classification","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Unit testing; Test (biology); Unit (ring theory); Artificial intelligence; Pattern recognition (psychology); Geology; Psychology; Operating system; Mathematics education","score_opus":0.04423106979949689,"score_gpt":0.34067254859068613,"score_spread":0.29644147879118926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411440374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010679972,0.00011379149,0.9713554,0.00066116627,0.00030435182,0.000111676614,0.0000018549114,0.016716829,0.000054992186],"genre_scores_gemma":[0.42888668,9.3318033e-7,0.57018584,0.0005349859,0.00003781327,0.000030100662,0.000006478042,0.0000144247615,0.00030272183],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986003,0.000022832188,0.0003376119,0.00043011803,0.00021717726,0.00039193063],"domain_scores_gemma":[0.997534,0.0016681949,0.000070394686,0.0005045161,0.00011633687,0.00010658502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003653619,0.00019419072,0.00018494151,0.00022844576,0.00014296798,0.00011563777,0.00058684975,0.00011527851,0.0000069315183],"category_scores_gemma":[0.005936855,0.00019009103,0.000074742224,0.0008629489,0.000022604347,0.0002135735,0.00028784713,0.0002866406,0.000030965035],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023528257,0.00022935972,0.93297845,0.00009577847,0.000029858746,0.000039177885,0.00017161352,0.0035578487,0.0008075076,0.0013368527,0.034575224,0.026175985],"study_design_scores_gemma":[0.0002728696,0.000042710206,0.34154877,0.00019414064,0.000010351791,0.000020941377,0.0000018627693,0.64514107,0.0011290426,0.0020588492,0.009193354,0.00038604878],"about_ca_topic_score_codex":0.00001242957,"about_ca_topic_score_gemma":6.606442e-7,"teacher_disagreement_score":0.6415832,"about_ca_system_score_codex":0.0000822188,"about_ca_system_score_gemma":0.00009998502,"threshold_uncertainty_score":0.7751687},"labels":[],"label_agreement":null},{"id":"W4411450040","doi":"10.1145/3715741","title":"Understanding and Characterizing Mock Assertions in Unit Tests","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Assertion; Test (biology); Testability; Complement (music); Unit testing; Programming language; Control flow; Test case; Software engineering; Reliability engineering; Machine learning; Software","score_opus":0.05208794963468529,"score_gpt":0.26277533769608935,"score_spread":0.21068738806140405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411450040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87084645,0.00016524862,0.11636051,0.003683979,0.0004753258,0.00043902211,0.0000031739,0.007546982,0.0004792975],"genre_scores_gemma":[0.88893074,0.000007371475,0.11080316,0.00015605707,0.000011402755,0.000021499212,1.6906476e-7,0.000011259167,0.00005833878],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991672,0.0000036480976,0.0002055411,0.0002565745,0.00015677219,0.00021025952],"domain_scores_gemma":[0.99898756,0.0004183603,0.00008183287,0.00040654166,0.00007031894,0.000035364676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028267433,0.00014500513,0.00016830537,0.00033156332,0.000083460625,0.00009827772,0.0013248624,0.000068493064,3.6748258e-7],"category_scores_gemma":[0.005764493,0.00012210176,0.000038891274,0.00090198434,0.000028565162,0.00024727674,0.0008549483,0.00023822686,5.137527e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014628813,0.00012333968,0.84594965,0.0005216215,0.00004285828,0.000002683647,0.00075700274,0.00025732187,0.0075768135,0.1358705,0.005826236,0.00305732],"study_design_scores_gemma":[0.00055878307,0.00013004204,0.7854823,0.0033593532,0.00002103145,0.000026197764,0.000032210777,0.02356692,0.016549528,0.16914651,0.00059386424,0.00053330243],"about_ca_topic_score_codex":0.000011165147,"about_ca_topic_score_gemma":7.725355e-7,"teacher_disagreement_score":0.060467407,"about_ca_system_score_codex":0.00008864116,"about_ca_system_score_gemma":0.000027221618,"threshold_uncertainty_score":0.6901053},"labels":[],"label_agreement":null},{"id":"W4411523015","doi":"10.1145/3728876","title":"MoDitector: Module-Directed Testing for Autonomous Driving Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Root cause; Computer science; Debugging; Reliability (semiconductor); Reliability engineering; Root cause analysis; Process (computing); Scenario testing; Embedded system; Engineering; Artificial intelligence","score_opus":0.016940612286937884,"score_gpt":0.23593435620730108,"score_spread":0.2189937439203632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411523015","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13275772,0.0004229309,0.80849934,0.00066023716,0.0024425348,0.0015386444,0.000014396265,0.05332772,0.00033645696],"genre_scores_gemma":[0.45410925,6.3882254e-7,0.5454134,0.000056540022,0.000064183725,0.00017255283,4.2769975e-7,0.000027252667,0.00015579432],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852234,0.0000049305913,0.00037012761,0.0004607684,0.00026326178,0.0003785629],"domain_scores_gemma":[0.9968408,0.0014537734,0.00022490321,0.0008919362,0.0005292993,0.00005931651],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004636242,0.00026336024,0.00032217565,0.00028673222,0.0001704137,0.00019087442,0.003315284,0.00011651368,2.1041816e-7],"category_scores_gemma":[0.030714579,0.00021678592,0.00012634673,0.001030539,0.000029526185,0.00021106473,0.0010274294,0.0002324453,0.0000010799907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008711891,0.00071683014,0.32793772,0.007613173,0.0006751289,0.000005445713,0.0013842353,0.074712075,0.028103767,0.14116189,0.3258212,0.091781415],"study_design_scores_gemma":[0.000463924,0.00023712576,0.017684143,0.0026753047,0.0000434567,0.00002356578,0.0000045245624,0.9423926,0.018120522,0.015679559,0.0020843842,0.0005909101],"about_ca_topic_score_codex":0.000025673138,"about_ca_topic_score_gemma":1.3026505e-7,"teacher_disagreement_score":0.8676805,"about_ca_system_score_codex":0.00013816742,"about_ca_system_score_gemma":0.000069179456,"threshold_uncertainty_score":0.97745013},"labels":[],"label_agreement":null},{"id":"W4411551806","doi":"10.1109/icse55347.2025.00141","title":"Feature-Driven End-to-End Test Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"End-to-end principle; Computer science; Test (biology); Feature (linguistics); Artificial intelligence; Geology","score_opus":0.020466836786324962,"score_gpt":0.27702694174716963,"score_spread":0.2565601049608447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411551806","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010753515,0.00002952236,0.96889776,0.008214894,0.0002592372,0.00010730348,8.601611e-7,0.009459448,0.011955604],"genre_scores_gemma":[0.35453597,0.0000014166365,0.6372688,0.002954567,0.0000623316,0.000019510035,0.0000023044,0.0000035278977,0.0051516257],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932814,0.000019740593,0.00008104704,0.00028564525,0.0001338114,0.00015160117],"domain_scores_gemma":[0.99914914,0.0002342305,0.000020281866,0.00047037896,0.00007723245,0.00004876148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014250459,0.00008608825,0.00008225856,0.00014466839,0.0001067263,0.00017712107,0.00049410225,0.00004840847,0.000010182134],"category_scores_gemma":[0.0004143892,0.000074494055,0.000027985301,0.00048561633,0.0000127417425,0.00013029003,0.00021448628,0.00007881334,0.000048289934],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.296432e-7,0.00003171165,0.0070269187,0.000004171126,0.000004484115,0.0000049226146,0.000075783144,0.000044538647,0.0033160222,0.026746158,0.8739598,0.08878508],"study_design_scores_gemma":[0.00042697802,0.00037850742,0.027201515,0.00016896022,0.000019991567,0.000038844948,0.000004420412,0.64082015,0.13585715,0.043097377,0.15114494,0.0008411613],"about_ca_topic_score_codex":0.000056166875,"about_ca_topic_score_gemma":0.000022830962,"teacher_disagreement_score":0.72281486,"about_ca_system_score_codex":0.00003437379,"about_ca_system_score_gemma":0.00006143732,"threshold_uncertainty_score":0.30377793},"labels":[],"label_agreement":null},{"id":"W4411799800","doi":"10.1109/se4ads66461.2025.00007","title":"AI-Augmented Metamorphic Testing for Comprehensive Validation of Autonomous Vehicles","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Metamorphic rock; Geology","score_opus":0.061548962206652055,"score_gpt":0.3180466203913648,"score_spread":0.2564976581847127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411799800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019807873,0.0000659349,0.97115856,0.001001694,0.00011856647,0.0002573259,0.000001834482,0.0070060855,0.00058209343],"genre_scores_gemma":[0.5202649,3.185687e-7,0.47904804,0.0005513583,0.000007107901,0.00002910309,0.000002280839,0.0000033995414,0.00009347108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992353,0.00003461363,0.00024885163,0.00023885921,0.00009924224,0.00014318914],"domain_scores_gemma":[0.99797314,0.0011441122,0.00010137347,0.00034802099,0.00041106538,0.000022267595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021315659,0.00009399772,0.00016590116,0.00016703499,0.00008802373,0.000058223497,0.00039801816,0.00004028722,0.0000010269138],"category_scores_gemma":[0.0005337522,0.000085879554,0.00005137447,0.0004908963,0.00003229266,0.00015207235,0.00014940437,0.00005356679,0.000001520447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038844457,0.00048927194,0.046489008,0.0007421318,0.0002797761,0.0000073209458,0.0006203691,0.0020167502,0.07634499,0.2636513,0.15968518,0.44963503],"study_design_scores_gemma":[0.0005240272,0.00025302032,0.006548995,0.00021601122,0.000038088652,0.0000067669775,0.000007899085,0.4927843,0.29841936,0.19971193,0.0012526237,0.00023699304],"about_ca_topic_score_codex":0.00009351598,"about_ca_topic_score_gemma":5.8243637e-7,"teacher_disagreement_score":0.50045705,"about_ca_system_score_codex":0.000025332309,"about_ca_system_score_gemma":0.00009088389,"threshold_uncertainty_score":0.35020667},"labels":[],"label_agreement":null},{"id":"W4411950604","doi":"10.1109/forge66646.2025.00020","title":"Testing Refactoring Engine via Historical Bug Report driven LLM","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Programming language; Software engineering; Software","score_opus":0.02902503802755674,"score_gpt":0.2717983015721504,"score_spread":0.24277326354459366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411950604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021601648,0.00006218209,0.9610442,0.00079845043,0.0006971393,0.0000706251,6.6767136e-8,0.020856595,0.0143106],"genre_scores_gemma":[0.3692505,5.717634e-7,0.6275213,0.00016318,0.000064015476,0.000012051584,5.5683483e-7,0.000006692482,0.0029811398],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877584,0.000024343804,0.00030754603,0.0004327536,0.00019980318,0.00025972104],"domain_scores_gemma":[0.9983785,0.0005578998,0.000084185165,0.0007643758,0.00014532144,0.000069680624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035378817,0.00013491865,0.00017479133,0.00017414165,0.00013567603,0.00008451093,0.0006103114,0.000067060835,0.000003409003],"category_scores_gemma":[0.0018392403,0.00012294156,0.00004848666,0.00074849994,0.000013152226,0.00018248013,0.0003645735,0.00017680261,0.000008994384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004080067,0.00028077283,0.30013382,0.00008908162,0.00004874928,0.001186071,0.00027759332,0.00018218112,0.0046942695,0.010308901,0.20176028,0.4810342],"study_design_scores_gemma":[0.00074714125,0.00055188825,0.09940843,0.00088774686,0.000058506637,0.0017812302,0.000004754002,0.4924258,0.021058384,0.23136812,0.14965633,0.0020516508],"about_ca_topic_score_codex":0.0005177047,"about_ca_topic_score_gemma":0.0000023893147,"teacher_disagreement_score":0.49224362,"about_ca_system_score_codex":0.0003823283,"about_ca_system_score_gemma":0.000095218355,"threshold_uncertainty_score":0.50134116},"labels":[],"label_agreement":null},{"id":"W4412537309","doi":"10.1109/ast66626.2025.00009","title":"Simulink Mutation Testing using CodeBERT","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Mutation; Mutation testing; Software testing; Genetics; Programming language; Biology; Software","score_opus":0.049422659587397964,"score_gpt":0.32144220324181105,"score_spread":0.2720195436544131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412537309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055521536,0.000028604567,0.97140634,0.00026606076,0.00013746698,0.0000603983,9.2895476e-8,0.011893793,0.010655077],"genre_scores_gemma":[0.41207853,1.261906e-7,0.5871512,0.00056390755,0.000010353759,0.0000020686807,2.331384e-7,0.0000022717659,0.00019128564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994019,0.00002410231,0.00013440479,0.0002098281,0.00009159669,0.00013813443],"domain_scores_gemma":[0.99887866,0.00065262284,0.00003611354,0.00029299283,0.0001161118,0.000023482415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002039093,0.00007056567,0.000073870615,0.000114463524,0.0001249776,0.00012015012,0.00033024125,0.00003602977,0.0000018493566],"category_scores_gemma":[0.00097669,0.00006498171,0.000019605806,0.0006518514,0.000016062155,0.0001823123,0.00014746448,0.00006452179,0.000006729596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003210099,0.000096000105,0.03544721,0.00006341295,0.000024960076,0.000059220856,0.00036275134,0.006756281,0.0022221133,0.07052505,0.019385641,0.86505413],"study_design_scores_gemma":[0.000059104917,0.00001339039,0.00073541916,0.0000594396,0.0000027721312,0.000011907461,0.0000012396386,0.9071652,0.0017090441,0.08999945,0.00016590476,0.00007712879],"about_ca_topic_score_codex":0.00021637841,"about_ca_topic_score_gemma":0.000001943549,"teacher_disagreement_score":0.9004089,"about_ca_system_score_codex":0.000034857057,"about_ca_system_score_gemma":0.000081314975,"threshold_uncertainty_score":0.26498774},"labels":[],"label_agreement":null},{"id":"W4412703957","doi":"10.1145/3696630.3728608","title":"A Tool for Generating Exceptional Behavior Tests With Large Language Models","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Alliance de recherche numérique du Canada; University of Texas at Austin; Cisco Systems; National Science Foundation","keywords":"Computer science; Programming language; Artificial intelligence; Natural language processing","score_opus":0.03533501993292639,"score_gpt":0.31782319660617253,"score_spread":0.28248817667324616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412703957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014486652,0.00008446008,0.97275764,0.000118580894,0.00016658258,0.00074003305,0.00009687284,0.010929194,0.00061996636],"genre_scores_gemma":[0.1171035,0.0000011569501,0.87931204,0.0004936882,0.00012446832,0.001247599,0.00006034977,0.000014402393,0.0016428183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842745,0.00003290764,0.0002504399,0.0007047799,0.00026566276,0.000318747],"domain_scores_gemma":[0.99841803,0.00030401043,0.00012207255,0.00088597625,0.00022214693,0.00004778716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037984873,0.00026417905,0.00025714963,0.0001499767,0.00015615436,0.00029314993,0.0009093061,0.0001849839,0.000009552877],"category_scores_gemma":[0.00012664353,0.00021827125,0.00010621404,0.00013653384,0.000018407169,0.00011294043,0.0011316473,0.00028743994,0.000002386886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007380431,0.002284085,0.025753466,0.00205826,0.00035812418,0.00027835564,0.009874085,0.055464108,0.0009507028,0.30881545,0.2164221,0.37766746],"study_design_scores_gemma":[0.00031620872,0.0000848046,0.0004225817,0.0003715039,0.00003700381,0.00002145864,0.000005279979,0.9567052,0.0003383764,0.041100148,0.000083547,0.0005138484],"about_ca_topic_score_codex":0.000084897256,"about_ca_topic_score_gemma":0.00002739973,"teacher_disagreement_score":0.9012411,"about_ca_system_score_codex":0.00006431923,"about_ca_system_score_gemma":0.00034777963,"threshold_uncertainty_score":0.8900843},"labels":[],"label_agreement":null},{"id":"W4413185076","doi":"10.1016/j.neucom.2025.131208","title":"A distance for mixed-variable and hierarchical domains with meta variables","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Trottier Family Foundation; Fonds de recherche du Québec – Nature et technologies; European Commission; Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Office National d'études et de Recherches Aérospatiales; HORIZON EUROPE Framework Programme; Agence Nationale de la Recherche","keywords":"Variable (mathematics); Computer science; Mathematics; Artificial intelligence; Statistics","score_opus":0.015196723601141998,"score_gpt":0.2552330632174972,"score_spread":0.24003633961635523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413185076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019561516,0.00017076323,0.99187136,0.0006810851,0.00011692837,0.0002651946,0.0000017024286,0.0036347103,0.0013020915],"genre_scores_gemma":[0.23497328,0.0000017533014,0.7640511,0.00078575034,0.00003194239,0.00005379614,8.517815e-7,0.0000098355285,0.00009169431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987782,0.00006238502,0.00018687356,0.00053359,0.00012480086,0.00031411301],"domain_scores_gemma":[0.9977292,0.0016629333,0.00007071396,0.00040462147,0.00007373134,0.000058826423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040466318,0.0001644258,0.00026174553,0.000099015706,0.00032412857,0.00024237887,0.00047550368,0.00004510948,4.0976568e-7],"category_scores_gemma":[0.00030570957,0.00012971617,0.00004369052,0.0004782012,0.00006013324,0.00013080666,0.00031980686,0.00015530466,2.6132327e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029926072,0.00008553867,0.0031963324,0.00021322718,0.00018661156,0.000018965884,0.0001541923,0.0006457638,0.00022985703,0.9339852,0.008582628,0.052671764],"study_design_scores_gemma":[0.00093715667,0.00030773503,0.001932412,0.0002989434,0.00021955154,0.00009720204,0.0000035070996,0.5863571,0.00088567095,0.36608708,0.042401064,0.00047257246],"about_ca_topic_score_codex":0.00002364132,"about_ca_topic_score_gemma":0.0000021670899,"teacher_disagreement_score":0.58571136,"about_ca_system_score_codex":0.000010625495,"about_ca_system_score_gemma":0.000079915786,"threshold_uncertainty_score":0.52896714},"labels":[],"label_agreement":null},{"id":"W4413212461","doi":"10.1109/ms.2025.3597574","title":"When AI-Generated Unit Tests Validate Bugs: The Risk of Faulty Assertions","year":2025,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Software bug; Computer science; Unit testing; Software engineering; Programming language; Reliability engineering; Software; Engineering","score_opus":0.025979699802465107,"score_gpt":0.2993781457658547,"score_spread":0.2733984459633896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413212461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061113484,0.00021075614,0.9280491,0.0012750408,0.0005356716,0.00022066223,0.00003465508,0.008374388,0.0001862465],"genre_scores_gemma":[0.807926,0.00002151597,0.19008172,0.0011048027,0.000046537916,0.000057016892,0.00000942226,0.000016382493,0.0007365832],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985343,0.00022780146,0.00032755098,0.00036995765,0.0002605915,0.00027979125],"domain_scores_gemma":[0.99704695,0.0010403916,0.00017145499,0.0012433325,0.00044127207,0.000056590914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056279695,0.00018789459,0.00021319871,0.00016747549,0.00053186796,0.00012725835,0.0013737227,0.00010702842,0.0000070577094],"category_scores_gemma":[0.0016765024,0.00013581676,0.00010712662,0.000999197,0.000105620325,0.00020926759,0.00031523392,0.00031800667,0.000017632125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018152447,0.0003537072,0.47490555,0.00011962694,0.0003076962,0.0000248961,0.0026165163,0.0027386507,0.0012726361,0.005041053,0.41359776,0.09900373],"study_design_scores_gemma":[0.0011326332,0.00033541274,0.15630302,0.000914842,0.0002850448,0.000042189287,0.0000340365,0.053732038,0.06803026,0.69237155,0.025640532,0.0011784625],"about_ca_topic_score_codex":0.00055202364,"about_ca_topic_score_gemma":0.000047644866,"teacher_disagreement_score":0.7468125,"about_ca_system_score_codex":0.00003147524,"about_ca_system_score_gemma":0.00021623183,"threshold_uncertainty_score":0.5538447},"labels":[],"label_agreement":null},{"id":"W4413373092","doi":"10.1007/978-3-032-02018-5_35","title":"Uncovering Unsafe Feature Interactions in Vehicle Control Using Generative AI and Digital Twins","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Critical Systems Labs","funders":"","keywords":"Computer science; Generative grammar; Feature (linguistics); Control (management); Human–computer interaction; Artificial intelligence","score_opus":0.017737517385578803,"score_gpt":0.27524651233036507,"score_spread":0.25750899494478624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413373092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041928948,0.0002801786,0.9957346,0.0010505359,0.00073915167,0.0002697228,0.000011281501,0.00086988177,0.0006253837],"genre_scores_gemma":[0.62504673,0.000009599282,0.37199154,0.0025298689,0.00018700269,0.0000073695337,0.000002673942,0.000020003317,0.0002052131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774295,0.000029171631,0.00032645723,0.0010893389,0.00038386745,0.0004281987],"domain_scores_gemma":[0.9980999,0.0008114503,0.00015378348,0.0006747572,0.00016602023,0.00009408896],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033781157,0.000396771,0.000434454,0.0008898687,0.00021922859,0.0009968341,0.0010987846,0.0001740128,0.0000015397104],"category_scores_gemma":[0.000277413,0.00037903307,0.00006978201,0.0006320389,0.00032222597,0.0009640664,0.0008806677,0.0009653907,0.0000017308622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014623567,0.000051449726,0.005095643,0.00006394648,0.000025820302,0.00020477569,0.0012351956,0.10221428,0.00028334712,0.0042614057,0.00026452212,0.886285],"study_design_scores_gemma":[0.00025365193,0.000058199104,0.00028511972,0.00090250664,0.0000056876206,0.00007530355,8.3913974e-8,0.82691187,0.00033796564,0.17039232,0.00036993914,0.00040736614],"about_ca_topic_score_codex":0.00008385693,"about_ca_topic_score_gemma":0.00009256376,"teacher_disagreement_score":0.8858776,"about_ca_system_score_codex":0.000387594,"about_ca_system_score_gemma":0.00046502004,"threshold_uncertainty_score":0.9998662},"labels":[],"label_agreement":null},{"id":"W4413387697","doi":"10.1016/j.infsof.2025.107874","title":"Assessing the impact of tuning parameter in instance selection based bug resolution classification","year":2025,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Selection (genetic algorithm); Resolution (logic); Computer science; Artificial intelligence; Machine learning; Data mining","score_opus":0.02271485433639512,"score_gpt":0.3239449150073322,"score_spread":0.30123006067093705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413387697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1330033,0.000049183054,0.86367714,0.00058379624,0.000034856625,0.00012819772,5.067899e-7,0.0023280762,0.00019496308],"genre_scores_gemma":[0.8913966,0.00000522528,0.10844277,0.00011686195,0.0000017132413,0.000029300907,0.0000032168289,0.0000016991927,0.0000026536677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930686,0.000045911576,0.0003199924,0.000109580906,0.000085565465,0.00013206726],"domain_scores_gemma":[0.99907273,0.00030802295,0.00019338039,0.00026783012,0.0001469988,0.000011027441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043520806,0.00008261146,0.00011219969,0.00075008825,0.000119649325,0.000114903596,0.00027061685,0.00014297309,7.2090154e-7],"category_scores_gemma":[0.0012623242,0.00006303972,0.000027190583,0.0014164213,0.00009305819,0.0010421383,0.00005572938,0.00019600448,8.137057e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008133222,0.00002875788,0.45106488,0.000038736398,0.000008364986,2.908145e-7,0.00033912258,0.001063214,0.00016545625,0.0155014135,0.00068727904,0.5310944],"study_design_scores_gemma":[0.00025911292,0.000058714057,0.25392693,0.00015581424,0.0000029175144,0.000008227919,0.000042518783,0.709492,0.0005202645,0.035238266,0.00020212281,0.00009305192],"about_ca_topic_score_codex":0.00011223083,"about_ca_topic_score_gemma":0.0000071823465,"teacher_disagreement_score":0.7583933,"about_ca_system_score_codex":0.000114535665,"about_ca_system_score_gemma":0.00014632141,"threshold_uncertainty_score":0.2570685},"labels":[],"label_agreement":null},{"id":"W4413863275","doi":"10.1007/978-3-031-94533-5_21","title":"Model-Based Testing of Non-deterministic Systems","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science","score_opus":0.03303807198923141,"score_gpt":0.27285629151377133,"score_spread":0.2398182195245399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413863275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027151758,0.00018929622,0.99239814,0.00007183649,0.0009693768,0.0003703283,0.000007298429,0.0019229553,0.0040435954],"genre_scores_gemma":[0.33663616,0.0000015619898,0.66280216,0.00029069497,0.000081213395,0.000012215786,0.0000013174484,0.000018868413,0.00015581411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662435,0.000028038252,0.00070899416,0.0012839478,0.0008227234,0.0005319577],"domain_scores_gemma":[0.99475896,0.0023117189,0.00047576136,0.0018089298,0.0005298698,0.000114762755],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010071301,0.00049668207,0.0006983757,0.0011596454,0.00018316657,0.00033336424,0.003575028,0.00030817586,7.7921504e-7],"category_scores_gemma":[0.00086489855,0.00047127114,0.00011632482,0.0008961285,0.0005598132,0.00020561126,0.0010371306,0.0005913867,0.0000038221942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038098804,0.00003789379,0.0003846872,0.00044742186,0.000008215586,0.00007167979,0.00013983417,0.4906715,0.00012293103,0.0036821833,0.00016112193,0.50426877],"study_design_scores_gemma":[0.00010505413,0.00013911481,0.000030734926,0.0024099604,0.000008785958,0.00001997445,8.419861e-9,0.8671281,0.00041947514,0.12933499,0.000023653836,0.00038018645],"about_ca_topic_score_codex":0.00004941311,"about_ca_topic_score_gemma":0.000003540531,"teacher_disagreement_score":0.50388855,"about_ca_system_score_codex":0.0002126699,"about_ca_system_score_gemma":0.0017253853,"threshold_uncertainty_score":0.9997739},"labels":[],"label_agreement":null},{"id":"W4414093251","doi":"10.3390/make7030097","title":"A Review of Large Language Models for Automated Test Case Generation","year":2025,"lang":"en","type":"review","venue":"Machine Learning and Knowledge Extraction","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Test (biology); Natural language generation; Natural language; Focus (optics); Software; Test case","score_opus":0.04220589820370538,"score_gpt":0.4041485293505684,"score_spread":0.361942631146863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414093251","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.7880694e-7,0.75710577,0.237969,0.000013787943,0.00015064454,0.00047256539,0.000025029598,0.0039760205,0.00028702634],"genre_scores_gemma":[0.00004325447,0.9666857,0.03197354,0.000028286828,0.00011042475,0.00018433217,0.00019686883,0.000023613251,0.00075395993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846214,0.00029830527,0.0005207765,0.00045031245,0.00007900445,0.00018944494],"domain_scores_gemma":[0.9975311,0.0014671674,0.0004618606,0.00031390073,0.00017825788,0.000047703732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137592,0.0002832668,0.0008516959,0.00028920075,0.00022845968,0.00006707022,0.00019094208,0.00019358043,0.0000026336622],"category_scores_gemma":[0.0020782643,0.00024234867,0.00021192015,0.00046801398,0.000013884738,0.00017270927,0.00013282479,0.0004010916,0.0000028777888],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.7574353e-7,0.000065759916,0.0000013307516,0.090849794,0.0000171212,0.00001672944,0.00009144425,0.000002840266,9.0935856e-7,0.00015286492,0.0064731734,0.90232766],"study_design_scores_gemma":[0.00009291365,0.000080414706,8.198179e-8,0.06901033,0.00021609582,0.00071201316,0.0000012030206,0.49852836,0.0000018522705,0.00007543867,0.4310791,0.00020220512],"about_ca_topic_score_codex":0.00005743802,"about_ca_topic_score_gemma":0.00001622399,"teacher_disagreement_score":0.9021255,"about_ca_system_score_codex":0.000052885218,"about_ca_system_score_gemma":0.00018749185,"threshold_uncertainty_score":0.9882692},"labels":[],"label_agreement":null},{"id":"W4414193951","doi":"10.1007/978-3-032-05188-2_10","title":"Test Generation for Deep Reinforcement Learning Using LRP-Guided Mutation of Classified Configurations","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Reinforcement learning; Classifier (UML); Relevance (law); Key (lock); Binary number; Binary classification","score_opus":0.057442439023788226,"score_gpt":0.3055683181089162,"score_spread":0.24812587908512798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414193951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033882334,0.000084209314,0.9967013,0.00018149705,0.0006139691,0.0005889195,0.0000018728161,0.00085749157,0.000936842],"genre_scores_gemma":[0.27117008,0.0000063452903,0.72806376,0.0002885043,0.00016866313,0.000022233171,0.000028549104,0.000014824826,0.00023704612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767905,0.000027435732,0.0006510218,0.000819696,0.00050222984,0.00032054714],"domain_scores_gemma":[0.9967081,0.0013754494,0.00050222175,0.0006699474,0.0006864301,0.000057867575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078502705,0.0003053526,0.0003662377,0.00079243333,0.00036006092,0.00028463826,0.0010075689,0.00022442556,0.0000037087837],"category_scores_gemma":[0.0012977102,0.00030879388,0.0001017792,0.0004859708,0.00023773703,0.00034447268,0.00030690644,0.00032977367,0.0000010449809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029999555,0.000020353204,0.00006149481,0.000092812734,0.000011468516,0.0000058799496,0.000579581,0.6813957,0.003762501,0.020989792,0.00011090377,0.29296654],"study_design_scores_gemma":[0.0001791612,0.00017484794,0.00001423682,0.0003668163,0.00001363987,0.000018023293,8.0269466e-8,0.9311112,0.010279783,0.057454478,0.000115021634,0.00027267172],"about_ca_topic_score_codex":0.000042722626,"about_ca_topic_score_gemma":0.00001701999,"teacher_disagreement_score":0.29269385,"about_ca_system_score_codex":0.0002799912,"about_ca_system_score_gemma":0.00062491524,"threshold_uncertainty_score":0.9999364},"labels":[],"label_agreement":null},{"id":"W4414276204","doi":"10.5753/sast.2025.13826","title":"Detecção de Conflitos Semânticos com Testes Gerados por LLM","year":2025,"lang":"pt","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Merge (version control)","score_opus":0.023181220685524074,"score_gpt":0.3002464998347447,"score_spread":0.27706527914922063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414276204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003642496,0.00090611714,0.9597639,0.006280456,0.00089451176,0.0005407261,0.000008352331,0.019535122,0.008428356],"genre_scores_gemma":[0.7841845,0.000028608969,0.1767109,0.007043938,0.00009775789,0.00007252037,0.000003397275,0.000035526347,0.03182286],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970132,0.00023515872,0.0006159711,0.00088016654,0.0003744591,0.00088104384],"domain_scores_gemma":[0.9955618,0.0021996156,0.00017987318,0.0014981831,0.00031989624,0.0002406557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008951826,0.00045580807,0.00050239515,0.0003894668,0.00039205732,0.0008495797,0.0017607266,0.00030364637,0.00008089275],"category_scores_gemma":[0.0017070147,0.00043986196,0.0001914988,0.0010784148,0.00017461214,0.00030630306,0.00083055027,0.0004951498,0.00015200478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030282567,0.0008819574,0.11349505,0.00050458475,0.00019151992,0.00023881554,0.0018502225,0.0000427945,0.001248072,0.040908046,0.54619515,0.2944135],"study_design_scores_gemma":[0.0013277165,0.00080447417,0.017618839,0.0020865086,0.0001842179,0.00022470628,0.00006176495,0.80973047,0.029755728,0.10958403,0.02698958,0.0016319779],"about_ca_topic_score_codex":0.00065466407,"about_ca_topic_score_gemma":0.00001542593,"teacher_disagreement_score":0.8096877,"about_ca_system_score_codex":0.00016669653,"about_ca_system_score_gemma":0.0006522108,"threshold_uncertainty_score":0.99980533},"labels":[],"label_agreement":null},{"id":"W4414404854","doi":"10.1109/tse.2025.3612253","title":"MetaSel: A Test Selection Approach for Fine-Tuned DNN Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Ottawa","funders":"Alliance de recherche numérique du Canada; Mitacs; Huawei Technologies","keywords":"Covariate; Software deployment; Model selection; Selection (genetic algorithm); Context (archaeology); Subspace topology; Statistical hypothesis testing; Test data; Probability distribution","score_opus":0.01927186097653321,"score_gpt":0.24144192629660027,"score_spread":0.22217006532006706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414404854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015468604,0.00005240419,0.98134243,0.000051534305,0.00042074634,0.00039244618,0.000019383451,0.017520318,0.000046071324],"genre_scores_gemma":[0.313001,0.000003270593,0.6862107,0.00007738808,0.0000234762,0.00042034304,0.000003121638,0.000024455796,0.0002362232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987122,0.000016579392,0.00026223558,0.00049246644,0.00017359121,0.00034293075],"domain_scores_gemma":[0.99826986,0.0010372117,0.000042601736,0.00044871416,0.00012856991,0.000073029536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024769953,0.00025234892,0.00024018264,0.00046437583,0.00023219042,0.00012507076,0.00045083172,0.00012553626,0.000001656288],"category_scores_gemma":[0.00019209948,0.00026821945,0.00016442507,0.0009359812,0.000014482076,0.0003693583,0.0000043221276,0.000268647,0.000002433326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010426489,0.0002474293,0.000037087833,0.00016013213,0.00007861808,0.0000014231821,0.000102031576,0.9570686,0.00051298935,0.0014040967,0.0029776576,0.03739951],"study_design_scores_gemma":[0.00029981782,0.00010323451,0.000020104455,0.000080860955,0.000037885373,0.000012816797,0.0000011210391,0.9746172,0.022227028,0.0019885625,0.0003440328,0.0002673359],"about_ca_topic_score_codex":0.000018921593,"about_ca_topic_score_gemma":0.0000017353822,"teacher_disagreement_score":0.31284633,"about_ca_system_score_codex":0.00013263531,"about_ca_system_score_gemma":0.00008417072,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W4414682256","doi":"10.48550/arxiv.2506.19045","title":"Efficient Black-Box Fault Localization for System-Level Test Code Using Large Language Models","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code (set theory); TRACE (psycholinguistics); Pruning; Test suite; Code coverage; Inference; Source code; Test case; Debugging; Fault (geology)","score_opus":0.10090066710501147,"score_gpt":0.2378397593333464,"score_spread":0.13693909222833492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414682256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013613792,0.000057232748,0.9782396,0.000017637632,0.00036161352,0.0006583172,0.0002982197,0.0061966837,0.0005569294],"genre_scores_gemma":[0.9245339,0.00000586772,0.07460333,0.00008986721,0.000050646642,0.0000037269615,0.000042038988,0.000021476648,0.000649162],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979686,0.000096478434,0.00027089947,0.0011043104,0.00012694119,0.0004327359],"domain_scores_gemma":[0.9974643,0.00048151248,0.00029581663,0.0012584341,0.00038986275,0.00011007923],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004741585,0.00034240793,0.00038298185,0.00039181492,0.00028844795,0.0001509828,0.0014458391,0.00033690486,0.0000011311787],"category_scores_gemma":[0.0002492472,0.00039787078,0.00019784734,0.0006687545,0.00006512497,0.000119222044,0.0015643853,0.00029409822,0.000005973763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075435382,0.00010943688,0.0003653024,0.0004619253,0.000027027298,0.00005136253,0.00044522778,0.93972665,0.000009375094,0.057932604,0.00075285876,0.00011068815],"study_design_scores_gemma":[0.00036202575,0.000030634597,0.00001157787,0.0008227477,0.000080719976,0.0000041919657,0.000071717666,0.98384047,0.00017203395,0.014171333,0.000039647926,0.00039288483],"about_ca_topic_score_codex":0.00031245805,"about_ca_topic_score_gemma":0.000022936587,"teacher_disagreement_score":0.9109201,"about_ca_system_score_codex":0.000507633,"about_ca_system_score_gemma":0.0003194955,"threshold_uncertainty_score":0.9998473},"labels":[],"label_agreement":null},{"id":"W4414988640","doi":"10.1145/3763160","title":"Products of Recursive Programs for Hypersafety Verification","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Key (lock); Product (mathematics); Class (philosophy); Property (philosophy); Set (abstract data type); Simple (philosophy); Parametric statistics","score_opus":0.021377923818186817,"score_gpt":0.2885382608968596,"score_spread":0.26716033707867276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414988640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.823473,0.0038774863,0.05814149,0.06544024,0.0020214177,0.015765386,0.000024144674,0.023119481,0.008137386],"genre_scores_gemma":[0.5414841,0.000003847966,0.45811152,0.000058618807,0.000021442493,0.00016610092,0.0000012758095,0.000007649838,0.00014544794],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990089,0.0000076978085,0.00024822808,0.00033182683,0.00020274163,0.00020064064],"domain_scores_gemma":[0.9981927,0.00018710493,0.0003174952,0.00069180806,0.0005912745,0.000019612653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054869143,0.00012377671,0.00018392513,0.00011479209,0.00009529277,0.00006251957,0.002250404,0.000061676634,1.3413728e-7],"category_scores_gemma":[0.006517768,0.00008859184,0.00008948561,0.0007619991,0.0001050033,0.00013289954,0.0004457087,0.00009736394,2.9617016e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005940941,0.000324331,0.008385836,0.0008940827,0.00005445024,1.47473e-7,0.001833395,9.899455e-7,0.008791664,0.08004806,0.009296762,0.8903109],"study_design_scores_gemma":[0.00058432826,0.0007867903,0.005073501,0.0018654197,0.000084031584,0.0000075333537,0.00045342583,0.00033213547,0.82493097,0.15571226,0.009826821,0.0003428064],"about_ca_topic_score_codex":0.00002073771,"about_ca_topic_score_gemma":3.0057998e-7,"teacher_disagreement_score":0.88996804,"about_ca_system_score_codex":0.000029905184,"about_ca_system_score_gemma":0.000049566483,"threshold_uncertainty_score":0.78028476},"labels":[],"label_agreement":null},{"id":"W4415007091","doi":"10.1145/3763053","title":"Boosting Program Reduction with the Missing Piece of Syntax-Guided Transformations","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Reduction (mathematics); Boosting (machine learning); Leverage (statistics); Program analysis; Program transformation; Key (lock); Abstract syntax tree; Minification","score_opus":0.01579920877483586,"score_gpt":0.2941947941011593,"score_spread":0.2783955853263234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415007091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8439472,0.0013799936,0.046791166,0.070590794,0.0003956854,0.00485758,0.0000046718765,0.017654866,0.014378072],"genre_scores_gemma":[0.6882117,0.0000028542959,0.31148914,0.00010189243,0.00001732454,0.00009455479,3.9519023e-7,0.000008380212,0.00007380305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989362,0.000015540905,0.00028034177,0.0002326451,0.00030718825,0.00022808094],"domain_scores_gemma":[0.99856913,0.00021678422,0.00032472593,0.00055930094,0.00030571994,0.000024354289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006255131,0.00014722267,0.000172921,0.0001315772,0.0003009226,0.0001761595,0.0020030604,0.000051384817,3.1158e-7],"category_scores_gemma":[0.0014036536,0.00008122491,0.00008229107,0.0010334525,0.00017685443,0.00025659284,0.0003078535,0.00020480865,2.4529893e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021103255,0.00019145948,0.0020774312,0.00042878007,0.000060857292,4.4669474e-7,0.00392132,0.000015251637,0.0058674663,0.011427079,0.005854013,0.9701348],"study_design_scores_gemma":[0.0010965739,0.001435569,0.005925852,0.008223853,0.0003303032,0.00023029826,0.0037560104,0.0051955325,0.8992598,0.06701239,0.006689196,0.00084463874],"about_ca_topic_score_codex":0.000050339087,"about_ca_topic_score_gemma":8.142556e-7,"teacher_disagreement_score":0.96929014,"about_ca_system_score_codex":0.000030381254,"about_ca_system_score_gemma":0.00005217753,"threshold_uncertainty_score":0.3722218},"labels":[],"label_agreement":null},{"id":"W4416240214","doi":"10.1007/s10664-025-10700-7","title":"Fuzzing-based mutation testing of C/C++ software in cyber-physical systems","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Kangwon National University; European Space Agency","keywords":"Fuzz testing; Symbolic execution; Code coverage; Process (computing); Software testing; Mutation testing; Mutation; Software; Software bug; Test case","score_opus":0.02328434506771092,"score_gpt":0.2833576778545125,"score_spread":0.26007333278680156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416240214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12074714,0.00023157442,0.87084526,0.00007979422,0.0002898045,0.0001828661,0.0000024058659,0.0075912983,0.000029836048],"genre_scores_gemma":[0.67071134,3.0207838e-7,0.3291052,0.000070125905,0.000036041038,0.000048205795,0.0000030119988,0.000016387374,0.000009416397],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983263,0.000057830384,0.00045916915,0.00045219003,0.00031484297,0.0003896737],"domain_scores_gemma":[0.9958228,0.003323096,0.0001098148,0.00050660153,0.00015766881,0.00008001168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037942608,0.00024195816,0.0003925974,0.0004729523,0.000059941332,0.000088160436,0.0006105587,0.000122066034,5.8977054e-7],"category_scores_gemma":[0.0070249545,0.0002481102,0.000088858964,0.001918226,0.000031539563,0.00021059338,0.00018416856,0.00031453627,0.000004022447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008600548,0.00026576238,0.56466424,0.00076805404,0.000028615044,0.000099241915,0.0004261025,0.403086,0.00019697065,0.00073638477,0.0015382898,0.028181756],"study_design_scores_gemma":[0.00042487183,0.00011697904,0.085944705,0.0011888229,0.000012577245,0.000012902667,0.000003599929,0.9071342,0.0015484256,0.0028699667,0.00034171564,0.0004012304],"about_ca_topic_score_codex":0.00014232291,"about_ca_topic_score_gemma":0.0000012802349,"teacher_disagreement_score":0.5499642,"about_ca_system_score_codex":0.00016521175,"about_ca_system_score_gemma":0.00015957636,"threshold_uncertainty_score":0.99999714},"labels":[],"label_agreement":null},{"id":"W4416248181","doi":"10.1007/s10664-025-10761-8","title":"SBEST: Spectrum-based fault localization without fault-triggering tests","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Concordia University","funders":"","keywords":"Stack (abstract data type); Software bug; Context (archaeology); TRACE (psycholinguistics); Call stack; Fault (geology); Software regression; Software; Debugging","score_opus":0.01565781770040737,"score_gpt":0.28534965561632986,"score_spread":0.2696918379159225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416248181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013589659,0.00020604886,0.9603709,0.00056990894,0.00045643613,0.00019573471,0.0000015757662,0.024522327,0.00008738725],"genre_scores_gemma":[0.73704773,0.00000308053,0.26188353,0.0008266711,0.00008129121,0.000030872347,0.0000068340096,0.00003345054,0.00008655217],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805874,0.0000370401,0.00039593826,0.0006189129,0.00035830037,0.0005310681],"domain_scores_gemma":[0.99815595,0.0007701451,0.00007497206,0.0007457039,0.00009728661,0.00015594765],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029888723,0.00032995266,0.00032596022,0.00039154294,0.00017841152,0.00023509545,0.00081173645,0.00017303712,0.0000067100996],"category_scores_gemma":[0.0024440452,0.0003300446,0.000114387934,0.001494956,0.000033240103,0.00027776693,0.00025416428,0.00034571218,0.000024605813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011476716,0.00018452399,0.56948876,0.0003021368,0.000053713356,0.00008842591,0.00022660481,0.39394453,0.0001181643,0.0011133985,0.015944825,0.018523455],"study_design_scores_gemma":[0.00035547354,0.00007117067,0.026351627,0.0004587669,0.000015530873,0.000015519441,7.002429e-7,0.95582885,0.0026805731,0.0031061973,0.010577179,0.0005384132],"about_ca_topic_score_codex":0.000047419497,"about_ca_topic_score_gemma":0.0000034864138,"teacher_disagreement_score":0.72345805,"about_ca_system_score_codex":0.00021393452,"about_ca_system_score_gemma":0.00014476497,"threshold_uncertainty_score":0.9999152},"labels":[],"label_agreement":null},{"id":"W4416298547","doi":"10.4204/eptcs.436.5","title":"Mutation Testing for Industrial Robotic Systems","year":2025,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Chicoutimi","funders":"","keywords":"Mutation; Software; Reliability (semiconductor); Process (computing); Robot; Industrial robot; Quality (philosophy); Mutation testing","score_opus":0.020033874459946397,"score_gpt":0.2757728134674147,"score_spread":0.2557389390074683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416298547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009617007,0.00008251045,0.9846288,0.0005626137,0.00060749054,0.00057187246,1.8571956e-7,0.0026422213,0.0012872827],"genre_scores_gemma":[0.84482074,6.886517e-7,0.15478186,0.00017709807,0.00010139379,0.00010214107,2.8820807e-7,0.000006850967,0.0000089149935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997448,0.000022842489,0.0003855784,0.0008144372,0.00038741913,0.0009416787],"domain_scores_gemma":[0.9981726,0.0009274331,0.00011048517,0.0002659355,0.00043863957,0.000084936546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030692862,0.0001889582,0.00024475568,0.00055131206,0.00035705822,0.00077788805,0.0019849595,0.00010243485,3.883495e-7],"category_scores_gemma":[0.0027589295,0.00017550748,0.000039698007,0.0033913937,0.00059271476,0.0006226308,0.00047738495,0.00037511415,0.0000018922068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006187547,0.000030915304,0.0009010869,0.00002314505,0.000002483097,0.0000011642687,0.000085561216,0.00031143328,0.00011642201,0.962304,0.00027615516,0.035941456],"study_design_scores_gemma":[0.00021326772,0.0002425007,0.0001556847,0.00015693474,0.0000029775201,0.00002325489,0.0000015982663,0.5439157,0.000740592,0.45440194,0.00002671998,0.00011884419],"about_ca_topic_score_codex":0.000010026496,"about_ca_topic_score_gemma":2.1780085e-7,"teacher_disagreement_score":0.83520377,"about_ca_system_score_codex":0.00042779968,"about_ca_system_score_gemma":0.00064832927,"threshold_uncertainty_score":0.7501192},"labels":[],"label_agreement":null},{"id":"W4416368800","doi":"10.48550/arxiv.2510.02534","title":"ZeroFalse: Improving Precision in Static Analysis with LLMs","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Static analysis; False positive paradox; Benchmark (surveying); Reliability (semiconductor); Precision and recall; Static program analysis; Software; Java","score_opus":0.03196078289550708,"score_gpt":0.2928788205595702,"score_spread":0.26091803766406313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416368800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37276635,0.00014949069,0.62238014,0.00022098538,0.00015978835,0.00025590486,0.000005567534,0.00384077,0.00022101768],"genre_scores_gemma":[0.77155685,0.000017189182,0.22782016,0.00019147666,0.00002343096,0.0000882857,0.0000149484795,0.000012313854,0.0002753711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99753654,0.00015074485,0.00047597685,0.0010851843,0.00037679888,0.00037474214],"domain_scores_gemma":[0.99693877,0.00065597426,0.00030401858,0.0018615528,0.00016027778,0.00007942232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077505055,0.00033583236,0.0005796845,0.00095568213,0.00008516798,0.00020763319,0.0016168313,0.0002163157,0.000005480053],"category_scores_gemma":[0.0005732821,0.0002860032,0.00014821978,0.0018522772,0.00004454396,0.00018396095,0.0019541304,0.0007014101,0.0000106153],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009979241,0.00007931952,0.95820475,0.00015236395,0.00015197623,0.000078615056,0.000606326,0.0036941105,0.00001888033,0.00009441638,0.00065940496,0.036249842],"study_design_scores_gemma":[0.00045936345,0.00020956509,0.6310969,0.0017952521,0.00043880462,0.000009303045,0.000014747839,0.3373438,0.001116886,0.02626564,0.00011974108,0.0011299673],"about_ca_topic_score_codex":0.0017394,"about_ca_topic_score_gemma":0.00017182503,"teacher_disagreement_score":0.39879048,"about_ca_system_score_codex":0.0001570681,"about_ca_system_score_gemma":0.00032082864,"threshold_uncertainty_score":0.99995923},"labels":[],"label_agreement":null},{"id":"W4416799210","doi":"10.1109/snpd65828.2025.11252591","title":"Making the Case for LLM-Generated Automated Program Repair Benchmarks","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Overfitting; Benchmark (surveying); Benchmarking; Focus (optics); Quality (philosophy); Quality assurance","score_opus":0.04917975613988371,"score_gpt":0.3669347614918263,"score_spread":0.31775500535194257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416799210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035967168,0.0015632372,0.5769847,0.0052686096,0.002390051,0.004688204,0.00001552884,0.39584917,0.009643762],"genre_scores_gemma":[0.41555116,0.00000691002,0.58074486,0.0016220942,0.000089636305,0.0006682895,0.000010168954,0.000020578169,0.0012863086],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966185,0.00030658234,0.0008309723,0.0011174821,0.0002330153,0.0008934546],"domain_scores_gemma":[0.99544877,0.0016567198,0.00025612244,0.0018481326,0.000692699,0.000097555676],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019330471,0.0004732132,0.00040668948,0.0002782335,0.0015511318,0.0012363446,0.0013690868,0.0003002823,0.000040797462],"category_scores_gemma":[0.0016905101,0.00033838887,0.00036099544,0.002330499,0.00024524712,0.00026922676,0.0008429853,0.00036791986,0.0000060130756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017116889,0.00032837671,0.00026474864,0.00015046401,0.000115690724,0.00044963,0.00029493496,0.00010494357,0.000004830112,0.009835409,0.76761127,0.22082256],"study_design_scores_gemma":[0.00033601854,0.0005075391,0.00011738677,0.000412374,0.00010116173,0.0008398434,0.000027855733,0.9723616,0.00021929886,0.011571726,0.013103429,0.0004017188],"about_ca_topic_score_codex":0.0005386882,"about_ca_topic_score_gemma":0.00007480591,"teacher_disagreement_score":0.9722567,"about_ca_system_score_codex":0.00014169929,"about_ca_system_score_gemma":0.0005720744,"threshold_uncertainty_score":0.99990684},"labels":[],"label_agreement":null},{"id":"W4416961966","doi":"10.1109/pst65910.2025.11268838","title":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Concordia University","funders":"Concordia University","keywords":"Process (computing); Hacker; Baseline (sea); Fuzz testing; Soundness","score_opus":0.032705316852876025,"score_gpt":0.3436117691507119,"score_spread":0.31090645229783587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416961966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012906544,0.00031197644,0.84457636,0.00048027586,0.00066048384,0.0007707741,0.000006700868,0.01760454,0.1342982],"genre_scores_gemma":[0.54893935,0.0000054473635,0.44788155,0.0021964214,0.00008418264,0.00008395536,0.000005189528,0.000023804161,0.00078013673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607205,0.0003104576,0.00082276517,0.0012408937,0.00055087317,0.0010029323],"domain_scores_gemma":[0.9908266,0.0062478944,0.00032343742,0.001694736,0.0007028205,0.0002045293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013066247,0.00063743955,0.0005253373,0.0008341769,0.00076094264,0.0008958263,0.0013855224,0.00045634943,0.00003905998],"category_scores_gemma":[0.0051329345,0.0006151836,0.00019334196,0.0033531266,0.00006620227,0.0008220147,0.0005508188,0.00093813636,0.00011864803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003861537,0.008739623,0.021350928,0.0022154779,0.00045196683,0.00021488646,0.048408207,0.014008317,0.00025038826,0.35974923,0.07177803,0.47244677],"study_design_scores_gemma":[0.00061981275,0.0006496985,0.00074155506,0.0030844572,0.00005304049,0.000006196774,0.0000566275,0.9206434,0.0012494328,0.07215202,0.00018263815,0.0005611284],"about_ca_topic_score_codex":0.00013294104,"about_ca_topic_score_gemma":0.0000618088,"teacher_disagreement_score":0.9066351,"about_ca_system_score_codex":0.0006321503,"about_ca_system_score_gemma":0.0018341085,"threshold_uncertainty_score":0.99963},"labels":[],"label_agreement":null},{"id":"W4417036956","doi":"10.5753/sbqs.2025.15010","title":"Automated Test Case Generation in a Real-World System Using a Customized AI Agent: An Experience Report","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Context (archaeology); Component (thermodynamics); Process (computing); Quality (philosophy); Test (biology); Test case; Software; Keyword-driven testing; Test Management Approach","score_opus":0.06728239215720491,"score_gpt":0.3727870787301468,"score_spread":0.30550468657294194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417036956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41170943,0.00008823133,0.5464778,0.00016635463,0.0011452263,0.00100049,0.0000036990557,0.037480697,0.0019280512],"genre_scores_gemma":[0.7959353,0.000004589571,0.20282464,0.00033532962,0.000093712086,0.00011968498,0.000008411627,0.00002400643,0.0006543675],"study_design_codex":"case_report","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948606,0.00054372643,0.0017771695,0.0016266688,0.0004631957,0.000728672],"domain_scores_gemma":[0.99615,0.00046020927,0.0005328224,0.002129666,0.000495149,0.00023212747],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020530114,0.0005129582,0.0007202896,0.0012642012,0.0006524578,0.0011386747,0.00079260516,0.00024004112,0.000013421436],"category_scores_gemma":[0.0013130585,0.0005242302,0.00011916569,0.0041430737,0.00014155141,0.0011862146,0.0005363124,0.00035422182,0.000006926023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002646029,0.004785539,0.2507269,0.0022368827,0.00022263786,0.48855036,0.03956237,0.029157082,0.020945577,0.025454365,0.051099192,0.0869945],"study_design_scores_gemma":[0.00072470505,0.000078894074,0.0005616832,0.0010110246,0.00003692994,0.010065379,0.00012495527,0.98381245,0.002855412,0.00016013625,0.000052094612,0.0005163208],"about_ca_topic_score_codex":0.03749168,"about_ca_topic_score_gemma":0.0025071134,"teacher_disagreement_score":0.9546554,"about_ca_system_score_codex":0.0011724079,"about_ca_system_score_gemma":0.0009993588,"threshold_uncertainty_score":0.99989825},"labels":[],"label_agreement":null},{"id":"W4417132523","doi":"10.1109/saner-c66551.2025.00015","title":"Assessing Data Augmentation-Induced Bias in Training and Testing of Machine Learning Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Debugging; Training set; Software; Test data; Test (biology); Training (meteorology); Non-regression testing; Keyword-driven testing; Software testing","score_opus":0.4312538849540782,"score_gpt":0.4003276714823415,"score_spread":0.030926213471736685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417132523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17884316,0.0009415351,0.8140272,0.00030859184,0.00016547208,0.00021661885,0.0000030755841,0.0020685515,0.0034258096],"genre_scores_gemma":[0.6492382,0.000028465289,0.35055307,0.000097333635,0.000011818296,0.0000040767504,0.0000070371525,0.00001052996,0.000049455604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970927,0.00034524544,0.0008885851,0.0009435329,0.0003152579,0.00041468337],"domain_scores_gemma":[0.9945691,0.003885567,0.00038832554,0.0009175916,0.00016582437,0.00007354502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031340213,0.00027906912,0.0004839441,0.0006393285,0.00028747274,0.000698798,0.0011160328,0.00012476947,0.0000045702614],"category_scores_gemma":[0.0057611563,0.00029256687,0.000027547529,0.0018800468,0.00009300768,0.0022945362,0.0017555287,0.0005391894,4.60019e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037500158,0.00008575393,0.08075041,0.0001748777,0.000025162768,0.000014787666,0.003435118,0.0026380124,0.0010531913,0.0023319714,0.000086150656,0.9094008],"study_design_scores_gemma":[0.00044536497,0.00007442163,0.0043988354,0.0019501804,0.000023641327,0.000014227191,0.00025772184,0.96333545,0.00077847997,0.028471906,0.000007919217,0.00024185811],"about_ca_topic_score_codex":0.0026008387,"about_ca_topic_score_gemma":0.000056170953,"teacher_disagreement_score":0.9606974,"about_ca_system_score_codex":0.00005799226,"about_ca_system_score_gemma":0.0005307381,"threshold_uncertainty_score":0.9999527},"labels":[],"label_agreement":null},{"id":"W4417436230","doi":"10.1145/3785363","title":"Galápagos: Automated N-Version Programming with LLMs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Correctness; Redundancy (engineering); Software; Symbolic execution; Program analysis; Automatic programming; Software quality; Programming paradigm; Software testing","score_opus":0.04061881690512797,"score_gpt":0.3080365130385907,"score_spread":0.2674176961334627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417436230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003194809,0.00013278502,0.97065353,0.00029284606,0.0002955776,0.00013349271,0.000001596274,0.025284525,0.000010808771],"genre_scores_gemma":[0.06623493,0.000020825359,0.9333974,0.00016522198,0.0000078355715,0.00005978187,0.0000015333815,0.0000141553055,0.00009831004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893105,0.0001146751,0.00016211288,0.00040288205,0.000106063395,0.0002832052],"domain_scores_gemma":[0.9971249,0.0020955002,0.00003525863,0.00060525775,0.00006642104,0.00007265815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005209685,0.00018892493,0.00023534975,0.0003707302,0.00017894141,0.00006139717,0.00040864872,0.00013333945,0.000002277636],"category_scores_gemma":[0.0008958234,0.00016619886,0.00004473586,0.0006051086,0.0000458134,0.00013410911,0.00002711689,0.00028050283,0.0000027935348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006333141,0.00012491064,0.0009925452,0.00019737554,0.00016256051,0.000060159087,0.00060057704,0.015658647,0.00033229322,0.0017039017,0.00092691026,0.97917676],"study_design_scores_gemma":[0.0068789846,0.005039911,0.015817638,0.0039138175,0.00064572296,0.002460371,0.00019165706,0.8121606,0.051725823,0.0275713,0.069231145,0.0043630395],"about_ca_topic_score_codex":0.000041995703,"about_ca_topic_score_gemma":0.0000016264552,"teacher_disagreement_score":0.97481376,"about_ca_system_score_codex":0.00003768907,"about_ca_system_score_gemma":0.00005054304,"threshold_uncertainty_score":0.67773926},"labels":[],"label_agreement":null},{"id":"W48642625","doi":"","title":"Validation Against Actual Behavior: Still a Challenge for Testing Tools.","year":2010,"lang":"en","type":"article","venue":"Software Engineering Research and Practice","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Carleton University","funders":"","keywords":"Computer science; Traceability; Software engineering; Acceptance testing; Model-based testing; Quality (philosophy); Code (set theory); Test (biology); Test case; Programming language; Machine learning","score_opus":0.13507361304108773,"score_gpt":0.3782731407054294,"score_spread":0.24319952766434166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W48642625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08041573,0.00024753166,0.90771216,0.0008649204,0.0005174346,0.0007986516,0.000016613883,0.009175932,0.00025104586],"genre_scores_gemma":[0.34764603,0.000025968644,0.65182495,0.000038804417,0.00017029805,0.00023248605,0.000008763709,0.000024721941,0.000027963877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998265,0.00007575659,0.00019469307,0.00046394777,0.00045264445,0.0005479448],"domain_scores_gemma":[0.9750965,0.02326371,0.00006966183,0.0005533652,0.000805056,0.0002117121],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032535614,0.0001649356,0.00014155667,0.00024893164,0.000276333,0.00061701576,0.0005358634,0.00013715371,0.0000017734757],"category_scores_gemma":[0.1098104,0.0001667789,0.000030715022,0.0004873968,0.000057701054,0.0013790188,0.00029716516,0.0008484438,0.0000075279154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069879294,0.0004371752,0.002131461,0.00030160585,0.000045447643,0.00012015555,0.0016525805,0.00015948218,0.012457841,0.012145778,0.0040887343,0.96638983],"study_design_scores_gemma":[0.0050439783,0.009728331,0.02478152,0.0014263404,0.00018236645,0.002733922,0.00024760637,0.25323927,0.02840833,0.053639162,0.61486995,0.0056991954],"about_ca_topic_score_codex":0.000029403025,"about_ca_topic_score_gemma":0.0000013332512,"teacher_disagreement_score":0.9606907,"about_ca_system_score_codex":0.000035448928,"about_ca_system_score_gemma":0.0001264254,"threshold_uncertainty_score":0.89768803},"labels":[],"label_agreement":null},{"id":"W49013149","doi":"","title":"Software Testing and Quality Assurance","year":2007,"lang":"en","type":"book","venue":"John Wiley & Sons eBooks","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Quality assurance; Software quality assurance; Software quality; Software quality analyst; Computer science; Software engineering; Software; Reliability engineering; Engineering; Operations management; Operating system; Software development; External quality assessment","score_opus":0.05730441950692096,"score_gpt":0.29686374559851847,"score_spread":0.23955932609159752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W49013149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012484651,0.0015653764,0.53442603,0.000103109,0.00071232184,0.0006800285,0.000050799204,0.03545665,0.42688084],"genre_scores_gemma":[0.00083991425,0.000021201422,0.7711219,0.0009546548,0.00042745756,0.000051363484,0.000010091502,0.00010122619,0.22647217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664277,0.000118389515,0.0007129301,0.0011562827,0.000673914,0.00069571554],"domain_scores_gemma":[0.99319726,0.0040203845,0.00059073657,0.0015854262,0.00033353522,0.0002726435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015463132,0.00061454874,0.00073213613,0.00033697824,0.0003956965,0.0003709407,0.0013053234,0.0005793397,0.0000025721438],"category_scores_gemma":[0.002950571,0.0006204633,0.000164784,0.00014143526,0.00023130732,0.00015246822,0.00080564455,0.0009731792,0.000034407876],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008580002,0.000036191726,0.004465744,0.00049380085,0.00006744394,0.00019295006,0.00046023517,0.0000022201343,0.0000265118,0.00857555,0.34038442,0.6452863],"study_design_scores_gemma":[0.0008584452,0.0005261434,0.006977947,0.008565509,0.00013438072,0.0005884323,0.000005117331,0.0012675005,0.00033056655,0.6353242,0.34130844,0.0041133272],"about_ca_topic_score_codex":0.00021511737,"about_ca_topic_score_gemma":0.000045642213,"teacher_disagreement_score":0.641173,"about_ca_system_score_codex":0.00020638772,"about_ca_system_score_gemma":0.00083286373,"threshold_uncertainty_score":0.99962467},"labels":[],"label_agreement":null},{"id":"W49830884","doi":"10.1007/978-3-642-36054-1_7","title":"People-Centered Software Development: An Overview of Agile Methodologies","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Agile software development; Computer science; Agile Unified Process; Agile usability engineering; Software engineering; Focus (optics); Test-driven development; Software development; Quality assurance; Lean software development; Systems engineering; Software; Software development process; Engineering; Programming language; Operations management","score_opus":0.14082622124068347,"score_gpt":0.33964033243070785,"score_spread":0.19881411119002437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W49830884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019613969,0.0014226468,0.9935094,0.00010762912,0.00078002934,0.00041014058,0.0000038621533,0.0032552385,0.00031490458],"genre_scores_gemma":[0.012601839,0.00007873605,0.9864927,0.0005511173,0.000093324845,0.000023419472,0.00000780451,0.00003717883,0.000113857954],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960889,0.00010887578,0.00075976975,0.0014746094,0.0009215143,0.0006463189],"domain_scores_gemma":[0.99493533,0.0019529583,0.0005446634,0.0019183602,0.00047564993,0.00017304228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015372047,0.0005840167,0.00085055904,0.00085136615,0.00021460187,0.00036538826,0.0046678125,0.00035978112,0.000039014147],"category_scores_gemma":[0.0009949765,0.00051750574,0.00013075481,0.0006741233,0.00048490285,0.0007833414,0.0021806979,0.00058399385,0.000030926156],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002418673,0.000031821357,0.0004051616,0.00013774436,0.000010969792,0.0000137270945,0.001433803,0.00076491595,0.000037356862,0.003178575,0.0001177625,0.9938657],"study_design_scores_gemma":[0.0002960088,0.00043332877,0.0027675768,0.00219766,0.000014877232,0.00012213817,2.4212028e-7,0.051591758,0.005543357,0.9341841,0.0014007082,0.0014482563],"about_ca_topic_score_codex":0.00008112329,"about_ca_topic_score_gemma":0.000054787728,"teacher_disagreement_score":0.9924175,"about_ca_system_score_codex":0.00020421686,"about_ca_system_score_gemma":0.0007198618,"threshold_uncertainty_score":0.99972767},"labels":[],"label_agreement":null},{"id":"W58067616","doi":"10.1007/978-3-642-35267-6_13","title":"Regression Testing of Object-Oriented Software: A Technique Based on Use Cases and Associated Tool","year":2012,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Regression testing; Computer science; Software; Information retrieval; Data mining; Software engineering; Programming language; Software development; Software construction","score_opus":0.07075414036268389,"score_gpt":0.30479052641519233,"score_spread":0.23403638605250843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58067616","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006628236,0.00023626286,0.991084,0.00015713667,0.00014208397,0.00074775727,0.00002999126,0.0019534195,0.0049865306],"genre_scores_gemma":[0.19756155,0.00017602378,0.80170625,0.00039859634,0.0000093031185,0.000043598935,0.000028573608,0.000009730142,0.000066398636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983953,0.00006237098,0.00062348164,0.0002557231,0.00044383528,0.00021927021],"domain_scores_gemma":[0.9930639,0.0039278036,0.0006022664,0.001726502,0.00059926056,0.0000802216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015817754,0.0002314728,0.00027979733,0.0010401718,0.00039199283,0.00028724887,0.0013282077,0.00016519964,0.0000010384949],"category_scores_gemma":[0.003527172,0.0002113917,0.00003235163,0.00063811685,0.00064359646,0.0035544108,0.0014839816,0.00039875388,0.0000020522275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000094162815,0.000111876376,0.013178564,0.00011037507,0.000007644113,0.0000022267632,0.0010774953,0.000107053056,0.000022031718,0.084834024,0.00072653464,0.89981276],"study_design_scores_gemma":[0.00087272277,0.0008376012,0.040697325,0.008559584,0.00003204221,0.00019524306,0.000005224579,0.9074894,0.00043305193,0.019994687,0.01943944,0.0014436517],"about_ca_topic_score_codex":0.000042166932,"about_ca_topic_score_gemma":0.0000017104122,"teacher_disagreement_score":0.90738237,"about_ca_system_score_codex":0.000121934245,"about_ca_system_score_gemma":0.0002480789,"threshold_uncertainty_score":0.8620303},"labels":[],"label_agreement":null},{"id":"W6191748","doi":"10.1111/j.1440-1754.1983.tb02042.x","title":"Generative hierarchical contracts for conformance testing of sequential containers","year":2007,"lang":"en","type":"article","venue":"Australian paediatric journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Domain (mathematical analysis); Component (thermodynamics); Generative grammar; Domain analysis; Conformance testing; Domain model; Fuzz testing; Unit testing; Generative model; Software testing; Software engineering; Model-based testing; Software; Programming language; Artificial intelligence; Software development; Domain knowledge; Test case; Machine learning; Mathematics; Software construction","score_opus":0.052735595578852996,"score_gpt":0.31585327629823523,"score_spread":0.26311768071938224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6191748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058702208,0.00009110911,0.9387869,0.00058175303,0.000596601,0.00021692607,0.0000067701944,0.0007353416,0.00028234135],"genre_scores_gemma":[0.58593196,0.0000047244694,0.41336426,0.0001367169,0.0004840049,0.0000030357166,0.0000013226929,0.0000074421628,0.0000665051],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99827737,0.000048966012,0.0006174927,0.00020699657,0.00032088638,0.0005283068],"domain_scores_gemma":[0.99741125,0.0012169823,0.000476574,0.00020497365,0.00045352065,0.00023668134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019534111,0.00016028034,0.00024605604,0.00026461107,0.00019634768,0.00012649434,0.00059021584,0.00010504657,0.00000352986],"category_scores_gemma":[0.001398841,0.00014125268,0.0001239331,0.00047743358,0.00008775834,0.00037572725,0.000062874875,0.00038029606,0.0000022299741],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038972587,0.0005033528,0.15885966,0.00021126115,0.00033793596,0.00084917597,0.003369551,0.0010725746,0.020168189,0.051954977,0.17487901,0.5874046],"study_design_scores_gemma":[0.019710226,0.010716378,0.13490047,0.00090867473,0.00052423775,0.013896466,0.0003425138,0.08541765,0.2068137,0.48495162,0.036850963,0.0049671074],"about_ca_topic_score_codex":0.000022502483,"about_ca_topic_score_gemma":0.0000018840142,"teacher_disagreement_score":0.58243746,"about_ca_system_score_codex":0.00006799498,"about_ca_system_score_gemma":0.00025609927,"threshold_uncertainty_score":0.5760117},"labels":[],"label_agreement":null},{"id":"W658116578","doi":"","title":"SToP : Scalable Termination analysis of (C) Programs (tool presentation)","year":2012,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emera (Canada)","funders":"","keywords":"Program slicing; Computer science; Slicing; Scalability; Modular design; Programming language; Program analysis; Code (set theory); Static analysis; Operating system; World Wide Web","score_opus":0.022731433104984475,"score_gpt":0.262514607741428,"score_spread":0.2397831746364435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W658116578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05349784,0.00038184284,0.93437934,0.0015539196,0.00017106916,0.0005002965,0.000019279476,0.0031512082,0.006345229],"genre_scores_gemma":[0.64160067,0.000044045566,0.3566819,0.000025027466,0.000011446323,0.0001070247,0.00030274148,0.000018495732,0.001208626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99475336,0.0028881726,0.0006494227,0.0007356196,0.000620559,0.00035287175],"domain_scores_gemma":[0.99209964,0.0014804478,0.0008758677,0.0029233969,0.0024932083,0.00012745782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0058475747,0.0002891951,0.00048931513,0.0006515216,0.0001988382,0.00045603226,0.002139811,0.00025673138,0.00003297235],"category_scores_gemma":[0.0016876746,0.0003069174,0.00031884655,0.0016774837,0.00016759148,0.00037241753,0.0018805555,0.00039623975,0.000011055566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006718601,0.0018439674,0.08668517,0.0003987889,0.0008265378,0.0000055625615,0.019968718,0.000335951,0.00062275835,0.093767606,0.0021811845,0.793357],"study_design_scores_gemma":[0.00052440615,0.000001609009,0.16129112,0.0023283004,0.0010262427,0.000011529772,0.00003602881,0.74581766,0.0329288,0.052604984,0.0021621457,0.0012671587],"about_ca_topic_score_codex":0.0013812344,"about_ca_topic_score_gemma":0.00016978741,"teacher_disagreement_score":0.7920899,"about_ca_system_score_codex":0.0001039412,"about_ca_system_score_gemma":0.00020341185,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W6889756539","doi":"10.26262/heal.auth.ir.286909","title":"Φυσικοθεραπευτικές τεχνικές για την αποκατάσταση του επώδυνου ημιπληγικού ώμου μετά από εγκεφαλικό επεισόδιο: Συστηματική ανασκόπηση και μετα-ανάλυση","year":2015,"lang":"el","type":"article","venue":"Aristotle University of Thessaloniki","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stroke (engine); MEDLINE; Cochrane collaboration; Systematic review; Meta-analysis; Clinical trial","score_opus":0.06140312759617738,"score_gpt":0.21973553710706073,"score_spread":0.15833240951088334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889756539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2223589,0.009656729,0.5507335,0.026418194,0.010540546,0.0037023544,0.0007040588,0.036614943,0.13927077],"genre_scores_gemma":[0.8741504,0.00027698436,0.11303436,0.0007588606,0.00033235754,0.000002984754,0.000046815916,0.00015165721,0.011245562],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99289244,0.0007609714,0.0009405534,0.0019567728,0.0018396502,0.0016095988],"domain_scores_gemma":[0.9918714,0.001022451,0.0012170103,0.003490844,0.0012576708,0.0011405868],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024501411,0.0010845149,0.0015310146,0.000865933,0.001014546,0.0003472225,0.005535002,0.00090470817,0.00020659351],"category_scores_gemma":[0.001166808,0.0012439277,0.0007167121,0.001651399,0.0013177233,0.0013296177,0.0030270508,0.0013791004,0.0010907551],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010161782,0.0027963053,0.0379836,0.00057441636,0.00074586354,0.0016059073,0.022791782,0.0009851343,0.00043674113,0.017264476,0.84851795,0.065281674],"study_design_scores_gemma":[0.010416913,0.0043594,0.034390334,0.0035471716,0.0015219288,0.00047522294,0.0041998406,0.08207107,0.0034116933,0.16419229,0.6842746,0.0071395165],"about_ca_topic_score_codex":0.012553543,"about_ca_topic_score_gemma":0.00040357455,"teacher_disagreement_score":0.6517915,"about_ca_system_score_codex":0.0008879388,"about_ca_system_score_gemma":0.001372959,"threshold_uncertainty_score":0.9998455},"labels":[],"label_agreement":null},{"id":"W6891916858","doi":"10.48550/arxiv.2308.13129","title":"Accelerating Continuous Integration with Parallel Batch Testing","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reduction (mathematics); Variable (mathematics); Regression testing; Test case; Test (biology); Batch processing; Execution time; Constant (computer programming); System under test","score_opus":0.19237847088836976,"score_gpt":0.21561095712481182,"score_spread":0.023232486236442057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891916858","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08262781,0.000010505643,0.89836055,0.00010231934,0.00024926764,0.00028856486,0.0000036273857,0.017060041,0.0012972844],"genre_scores_gemma":[0.76832026,0.000008131071,0.23080452,0.000062377956,0.00006618722,0.000004078716,0.000012978732,0.000030482535,0.00069098326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979687,0.00011679217,0.00023177962,0.0011632523,0.00012760804,0.00039188823],"domain_scores_gemma":[0.99735856,0.000669919,0.00035608897,0.0011339643,0.00036505648,0.00011639794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040225367,0.00035781637,0.00035381736,0.00027140102,0.00026275744,0.00037978115,0.0015549692,0.00023876535,0.0000026854107],"category_scores_gemma":[0.00051387557,0.0003556349,0.00009094298,0.0009760072,0.00007896484,0.0003617998,0.0014962952,0.0007354713,0.000044515604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086516564,0.00035247242,0.25989228,0.00044673335,0.0003610841,0.0049467226,0.0031588988,0.5303923,0.00015652829,0.14362669,0.016332947,0.040246863],"study_design_scores_gemma":[0.0002264705,0.00011517494,0.003817038,0.0005048826,0.00003489913,0.000020662445,0.00003323271,0.8552912,0.00007235539,0.13932955,0.000020200017,0.00053436327],"about_ca_topic_score_codex":0.00079570134,"about_ca_topic_score_gemma":0.00007261044,"teacher_disagreement_score":0.6856924,"about_ca_system_score_codex":0.000150332,"about_ca_system_score_gemma":0.00022575477,"threshold_uncertainty_score":0.99988955},"labels":[],"label_agreement":null},{"id":"W6893218605","doi":"10.5281/zenodo.14950000","title":"Investigating Groundwater Resources using Vertical Electrical Sounding: A Case Study in Baidoa, Somalia.","year":2025,"lang":"en","type":"dissertation","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Situated; Groundwater; Population; Quarter (Canadian coin); Hydrogeology; Bay; Water resources; Drilling","score_opus":0.07027851002359313,"score_gpt":0.31043246749962505,"score_spread":0.2401539574760319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893218605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96426105,0.00009819783,0.01950676,0.00008105059,0.0002267811,0.0008697952,0.000006967298,0.00834556,0.006603834],"genre_scores_gemma":[0.98966926,0.0000043658324,0.008618952,0.000080973616,0.00010579419,3.2057292e-7,0.00025843913,0.00073147396,0.0005304466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966897,0.00078956917,0.0005314928,0.00087590696,0.0005631889,0.0005501622],"domain_scores_gemma":[0.99836344,0.00016722045,0.00013442733,0.000728199,0.000437209,0.00016952526],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012284182,0.000293581,0.00032740922,0.0009393393,0.0019554663,0.0021273517,0.0017482431,0.0001921111,0.00013544525],"category_scores_gemma":[0.0026486132,0.00031509798,0.00006847677,0.0016872417,0.000062016305,0.00034615886,0.0011526536,0.00081141305,0.0001463969],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036328033,0.0060870945,0.0052207047,0.002123839,0.0007156172,0.01826314,0.16859028,0.00058561645,0.0060855043,0.015373389,0.14497931,0.63161224],"study_design_scores_gemma":[0.010284154,0.010078611,0.017848967,0.007259385,0.00081787724,0.028573766,0.01687333,0.6180366,0.004385971,0.060035273,0.21606629,0.009739766],"about_ca_topic_score_codex":0.00053633534,"about_ca_topic_score_gemma":0.000013857837,"teacher_disagreement_score":0.6218725,"about_ca_system_score_codex":0.00038806873,"about_ca_system_score_gemma":0.000027425585,"threshold_uncertainty_score":0.9999301},"labels":[],"label_agreement":null},{"id":"W6893802102","doi":"10.5281/zenodo.4671169","title":"MANDOLINE: Dynamic Slicing of Android Applications with Trace-Based Alias Analysis","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Program slicing; Debugging; Slicing; Android (operating system); Suite; Static analysis; Call graph; Benchmark (surveying)","score_opus":0.018263106225872388,"score_gpt":0.2659056568033319,"score_spread":0.2476425505774595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893802102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001093267,0.00070869474,0.9755437,0.00038488136,0.000012006951,0.0003038013,0.015512648,0.0055048065,0.0009362285],"genre_scores_gemma":[0.76841736,0.0000011447011,0.22242497,0.00016690216,0.000014255225,0.00023620458,0.008600167,0.000012150917,0.00012682333],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992523,0.000027295015,0.00014611104,0.00027490038,0.00017275305,0.00012664455],"domain_scores_gemma":[0.99872416,0.00024609346,0.00010936962,0.00063692697,0.0002375345,0.000045924007],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004744386,0.000088657376,0.00016995653,0.00014047895,0.00006130586,0.00005557833,0.0003616901,0.000037491624,0.00096505415],"category_scores_gemma":[0.00020085044,0.000079249316,0.00008076206,0.0015121892,0.0000056971908,0.00007879359,0.00007277232,0.00007213906,0.000023660112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007165672,0.0021068407,0.044036,0.0044233394,0.0023726912,0.00084380724,0.0019131715,0.05203068,0.0029996661,0.0017103414,0.56679946,0.32069236],"study_design_scores_gemma":[0.0008905115,0.00017234264,0.029771464,0.0018691036,0.0002859707,0.00008087989,0.000012514025,0.91461,0.03311972,0.0021188252,0.01625587,0.0008127557],"about_ca_topic_score_codex":0.000011948359,"about_ca_topic_score_gemma":0.000025308625,"teacher_disagreement_score":0.86257935,"about_ca_system_score_codex":0.000019891162,"about_ca_system_score_gemma":0.00011424132,"threshold_uncertainty_score":0.9999482},"labels":[],"label_agreement":null},{"id":"W6894279115","doi":"10.5281/zenodo.7553308","title":"Demystifying Issues, Challenges, and Solutions for Multilingual Software Development (Artifact)","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Scripting language; Software; Artifact (error); Process (computing); Coding (social sciences); Sampling (signal processing)","score_opus":0.14318193509934804,"score_gpt":0.304539451893625,"score_spread":0.16135751679427698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894279115","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009038848,0.002067056,0.90923923,0.004562255,0.000266577,0.0011299285,0.000060283597,0.07120059,0.0024352132],"genre_scores_gemma":[0.43023497,0.0011040501,0.56384784,0.00027094674,0.0003285911,0.0000018425986,0.0010323738,0.0019843583,0.0011950551],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852926,0.000108978886,0.00020113093,0.000460146,0.00023493779,0.00046557083],"domain_scores_gemma":[0.99894285,0.00014167686,0.000063717525,0.00037799188,0.0003405684,0.0001332111],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011823336,0.00012354316,0.000117946554,0.00024798352,0.0026254912,0.00050092733,0.0008438406,0.00005695855,0.00005611574],"category_scores_gemma":[0.0021688975,0.00013338384,0.00002722212,0.0003750012,0.00006860431,0.00024392612,0.0017597589,0.00013166718,0.00077079487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000573062,0.000034707587,0.000004064312,0.000079022335,0.000015186123,0.000006573451,0.0035476366,0.00002330325,0.00016455163,0.0040611154,0.05225166,0.93980646],"study_design_scores_gemma":[0.00032071304,0.00013599644,0.0016368792,0.00009133315,0.0000055919063,0.00007843761,0.00010419005,0.011163313,0.0005499678,0.007259161,0.9783804,0.00027401713],"about_ca_topic_score_codex":0.0000063971656,"about_ca_topic_score_gemma":4.0162206e-7,"teacher_disagreement_score":0.93953246,"about_ca_system_score_codex":0.00007334058,"about_ca_system_score_gemma":0.000008590379,"threshold_uncertainty_score":0.99867296},"labels":[],"label_agreement":null},{"id":"W6902284112","doi":"10.6084/m9.figshare.26653996.v1","title":"Additional file 2 of Performance analysis of conventional and AI-based variant callers using short and long reads","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Venn diagram; Degree (music); Indel; Diagram; Training set","score_opus":0.04056998422942117,"score_gpt":0.2757366639307596,"score_spread":0.2351666797013384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902284112","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031255526,0.00010505267,0.005889861,0.000015652095,0.000009455281,0.000041060037,0.9931284,0.00042375742,0.0000742067],"genre_scores_gemma":[0.34139028,0.0000012368265,0.09424544,0.000120482226,0.00003135169,0.00010677729,0.56404185,0.0000114255945,0.000051115207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994493,0.00001371169,0.00013113873,0.00018159609,0.00015065818,0.00007358303],"domain_scores_gemma":[0.9987972,0.00090769335,0.000038572547,0.00012945119,0.000095373136,0.00003174897],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000043258246,0.00006256308,0.00011977284,0.00021287613,0.00003597558,0.000041748153,0.000111087225,0.000035383153,0.3902832],"category_scores_gemma":[0.00040251898,0.000059735932,0.00004849804,0.0004645151,0.000018108341,0.00013570095,0.00008063014,0.000056502715,0.00000363337],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012296764,0.000009879859,0.00018973275,0.00017391899,0.00007010225,0.000012855554,0.000016794109,0.00019653353,0.0000030327649,0.000028134531,0.9957885,0.003509279],"study_design_scores_gemma":[0.000021735746,0.00003136045,0.015668485,0.002412052,0.000032734606,0.000017847024,4.193849e-7,0.97119427,0.00006478763,0.00009110299,0.010386481,0.00007872183],"about_ca_topic_score_codex":0.000004031372,"about_ca_topic_score_gemma":0.0000014310942,"teacher_disagreement_score":0.98540205,"about_ca_system_score_codex":0.000011955422,"about_ca_system_score_gemma":0.00010676989,"threshold_uncertainty_score":0.61027414},"labels":[],"label_agreement":null},{"id":"W6910685597","doi":"10.48550/arxiv.1608.07883","title":"Fault Localization in Web Applications via Model Finding","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Satisfiability; Set (abstract data type); Focus (optics); Object (grammar); Fault (geology); Boolean satisfiability problem; Web application; Fault model","score_opus":0.07762958019746287,"score_gpt":0.2147679170845426,"score_spread":0.13713833688707971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6910685597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024301931,0.000018886496,0.991216,0.00008987372,0.00007580326,0.00029194253,0.000007934001,0.0041319854,0.0017373657],"genre_scores_gemma":[0.9752185,0.000059829228,0.024218736,0.00009740748,0.000030478788,0.000008598443,0.000009676524,0.000015492215,0.00034128618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985939,0.00006196347,0.00017834974,0.0008345163,0.000075263815,0.00025600434],"domain_scores_gemma":[0.99845123,0.00013693333,0.00017652642,0.0010382519,0.00011488123,0.000082181265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002208009,0.00020686105,0.00019711493,0.00040835817,0.00011348737,0.00006795953,0.001356169,0.00025236374,0.0000025885129],"category_scores_gemma":[0.00004773398,0.00022352744,0.000079904814,0.00060087844,0.000057403464,0.0002522342,0.0011863555,0.00029311,0.000037622787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005338891,0.00008587255,0.007020166,0.00006059407,0.000014727175,0.000045242326,0.00016247864,0.8688735,0.000040638,0.11594726,0.002043282,0.0057009202],"study_design_scores_gemma":[0.00009326341,0.00000526152,0.00002920205,0.000094398245,0.0000056932017,0.0000012625679,8.0249924e-7,0.6322478,0.000035697718,0.3671928,0.00011995149,0.00017387753],"about_ca_topic_score_codex":0.000047786445,"about_ca_topic_score_gemma":0.00002192472,"teacher_disagreement_score":0.9727883,"about_ca_system_score_codex":0.00026794287,"about_ca_system_score_gemma":0.00018712966,"threshold_uncertainty_score":0.9115185},"labels":[],"label_agreement":null},{"id":"W6912448652","doi":"10.5281/zenodo.4671168","title":"MANDOLINE: Dynamic Slicing of Android Applications with Trace-Based Alias Analysis","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleofection; Hyporeflexia; TSG101; Subpoena; Hemopericardium; Tantalum carbide","score_opus":0.020738530750386112,"score_gpt":0.25133448420449733,"score_spread":0.2305959534541112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912448652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039439783,0.00008560807,0.9854272,0.00045910056,0.000009074162,0.00016277243,0.000029536734,0.003871291,0.0060114423],"genre_scores_gemma":[0.92033595,0.000015126242,0.07885462,0.0000847283,0.000014796645,1.3923179e-7,0.00032203304,0.00021722948,0.00015538989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881977,0.00015811922,0.00019280621,0.0003622098,0.00028229493,0.00018482834],"domain_scores_gemma":[0.9983367,0.00006370268,0.00011418446,0.0007298351,0.0006734069,0.00008219272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038349014,0.00009154596,0.00015557134,0.0002947959,0.0006450965,0.00034145723,0.0008500617,0.000031982097,0.0002489902],"category_scores_gemma":[0.00022630725,0.00008942021,0.000057715184,0.0022184267,0.00007500094,0.00013557338,0.00038993842,0.00011983143,0.00011015183],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014806371,0.0017668529,0.0011351441,0.0006853262,0.0011818672,0.00020469251,0.003283907,0.013719072,0.020337569,0.034921654,0.076136805,0.84647906],"study_design_scores_gemma":[0.0024315803,0.0009175157,0.011570397,0.000251489,0.0005345817,0.00054433534,0.0001531283,0.40792513,0.02573874,0.00533345,0.5434493,0.0011503488],"about_ca_topic_score_codex":0.000015250392,"about_ca_topic_score_gemma":9.249568e-7,"teacher_disagreement_score":0.91639197,"about_ca_system_score_codex":0.00005490043,"about_ca_system_score_gemma":0.000010445675,"threshold_uncertainty_score":0.49616256},"labels":[],"label_agreement":null},{"id":"W6931120072","doi":"10.5281/zenodo.4661878","title":"Test Sequence Generation with Cayley Graphs","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Test suite; Sequence (biology); Set (abstract data type); Graph; Directed graph; State (computer science)","score_opus":0.08709964338621846,"score_gpt":0.27480716160866375,"score_spread":0.1877075182224453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931120072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02012794,0.0075192694,0.35430077,0.0116504105,0.0016836534,0.0034104297,0.22214773,0.30165154,0.07750827],"genre_scores_gemma":[0.65681887,0.000002960814,0.32213828,0.0015431513,0.00013870593,0.00020753044,0.018716387,0.000024247272,0.0004099026],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999311,0.000020473302,0.00007668344,0.00028777405,0.00016110932,0.00014301117],"domain_scores_gemma":[0.9990414,0.0001723003,0.00004246802,0.000469579,0.00022317437,0.000051084742],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003094931,0.00008433254,0.00006801306,0.0000343764,0.00009468949,0.00018499448,0.00031473447,0.000036776037,0.0017989248],"category_scores_gemma":[0.0012883156,0.00007349695,0.000022009748,0.00040349062,0.000003998598,0.00022826839,0.00011944687,0.000060810005,0.00020110534],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0513223e-7,0.00004190806,0.0012272093,0.00003710933,0.000005502054,0.00043418637,0.00014721767,0.000035097783,0.0020547865,0.00044330413,0.9733534,0.0222199],"study_design_scores_gemma":[0.0011471139,0.0009897556,0.012463173,0.008017378,0.00002668938,0.0051559084,0.000014413803,0.28330863,0.5230231,0.03576619,0.127016,0.0030716565],"about_ca_topic_score_codex":0.0000055348223,"about_ca_topic_score_gemma":0.000009492867,"teacher_disagreement_score":0.8463374,"about_ca_system_score_codex":0.000018801798,"about_ca_system_score_gemma":0.00014228039,"threshold_uncertainty_score":0.99911356},"labels":[],"label_agreement":null},{"id":"W6931820053","doi":"10.5683/sp3/bmr1jt","title":"Supplementary data for: Implementation of Dunaliella tertiolecta and Desmodesmus communis in a photobioreactor prototype for treatment of wastewater in a recirculating aquaculture system","year":2025,"lang":"en","type":"dataset","venue":"Borealis","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Photobioreactor; Wastewater; Aquaculture; Sewage treatment; Recirculating aquaculture system; Dunaliella; Bioprocess","score_opus":0.048858509544572826,"score_gpt":0.34523377894963414,"score_spread":0.2963752694050613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931820053","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013602437,0.00010863174,0.0014956325,0.00005414743,0.000025576774,0.0031138896,0.9937403,0.00009946185,0.000002115997],"genre_scores_gemma":[0.0068195486,0.00003808297,0.03688281,0.000017873817,0.000013206296,0.0012417886,0.9549776,0.000008089484,0.000001044234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984347,0.00011299452,0.00065845624,0.00044599077,0.00012954972,0.00021831169],"domain_scores_gemma":[0.9977516,0.00042161276,0.00035729798,0.0013643105,0.00007891696,0.000026277954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045164218,0.00023342785,0.0005333592,0.0002923988,0.00004309905,0.000038746115,0.0008221767,0.00014086402,0.0000010419207],"category_scores_gemma":[0.000055844645,0.00019692096,0.00005505021,0.00018923024,0.000028247314,0.00009623847,0.0002998837,0.000057711113,4.8977338e-9],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001382212,0.00020429824,0.004652302,0.0028272548,0.000105005565,0.0000060095263,0.0010770208,0.0000018018837,0.00025551356,0.000070674774,0.98327845,0.0073834215],"study_design_scores_gemma":[0.022586295,0.010299641,0.004891496,0.019005973,0.0012018055,0.00011121733,0.0016445757,0.042547874,0.057823393,0.0041400683,0.83272976,0.0030179177],"about_ca_topic_score_codex":0.14677243,"about_ca_topic_score_gemma":0.044885475,"teacher_disagreement_score":0.15054874,"about_ca_system_score_codex":0.00017492344,"about_ca_system_score_gemma":0.00015218889,"threshold_uncertainty_score":0.9725429},"labels":[],"label_agreement":null},{"id":"W6948256836","doi":"10.48550/arxiv.1403.7261","title":"Generating Complete and Finite Test Suite for ioco: Is It Possible?","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Nondeterministic algorithm; Test suite; Conformance testing; Model-based testing; Relation (database); Construct (python library); Domain (mathematical analysis); Test case","score_opus":0.12393388249532612,"score_gpt":0.22448050045350496,"score_spread":0.10054661795817883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948256836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038525928,0.000044597033,0.95709723,0.00033847353,0.00022645676,0.00039294048,0.000058216876,0.0028896863,0.00042646818],"genre_scores_gemma":[0.8505493,0.00003816233,0.14713106,0.0010960483,0.00012641164,0.00000471799,0.000019126508,0.00002581078,0.0010094017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980391,0.00007400055,0.00023043547,0.0011818367,0.000082414255,0.00039218008],"domain_scores_gemma":[0.99648154,0.0016954844,0.00029053225,0.0011385083,0.00023266033,0.00016127681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044696714,0.00034435344,0.00037695718,0.00024316084,0.00034034083,0.00034513118,0.0013073024,0.00025080875,0.0000061044884],"category_scores_gemma":[0.0005162967,0.0003949886,0.00015113462,0.00028804055,0.00011074342,0.00018950067,0.0017717908,0.0003687456,0.000015887048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121025034,0.0007480026,0.23037511,0.003708756,0.0006326751,0.0005752089,0.0065338165,0.29414165,0.0011662422,0.14561059,0.28104085,0.035346057],"study_design_scores_gemma":[0.00028937942,0.0001092558,0.0003874283,0.00021071137,0.000038308175,0.000006219437,0.000004603296,0.91697156,0.00010981958,0.080001086,0.0014077591,0.0004638753],"about_ca_topic_score_codex":0.00013641277,"about_ca_topic_score_gemma":0.000014532492,"teacher_disagreement_score":0.81202334,"about_ca_system_score_codex":0.00007141449,"about_ca_system_score_gemma":0.000110871086,"threshold_uncertainty_score":0.9998502},"labels":[],"label_agreement":null},{"id":"W6950093527","doi":"10.5281/zenodo.4673775","title":"Assisting Bug Report Assignment Using Automated Fault Localisation: An Industrial Case Study","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Nucleofection; TSG101; Subpoena; Hyporeflexia; Protein isoform; Diafiltration","score_opus":0.1660847211701703,"score_gpt":0.334696775609391,"score_spread":0.16861205443922067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950093527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37660396,0.000020730637,0.57586044,0.00032140827,0.00034876852,0.0006110235,0.000020019581,0.041870024,0.0043436196],"genre_scores_gemma":[0.9766434,6.553857e-7,0.022479376,0.00006701769,0.00016446268,7.317268e-8,0.00018572976,0.0003846608,0.000074665724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727076,0.00082838774,0.00039789447,0.0006588721,0.00053311774,0.00031097702],"domain_scores_gemma":[0.9976817,0.00006243666,0.00019909721,0.0009631794,0.00090531696,0.00018827469],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016447611,0.00014976294,0.00016179815,0.0001696511,0.0023639016,0.0018302702,0.0008174317,0.0000757137,0.00035408835],"category_scores_gemma":[0.0025381004,0.00016428127,0.000035158555,0.0009963545,0.000060027505,0.00051647634,0.0015163529,0.00027769664,0.00012605799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050851326,0.0036511326,0.0021907894,0.000090808804,0.00027790884,0.112133205,0.015252321,0.005057639,0.0053073824,0.0015552348,0.23449717,0.6199356],"study_design_scores_gemma":[0.0022601958,0.0014624533,0.0012434307,0.00020340926,0.000088842615,0.13861202,0.002751208,0.7286484,0.0026052687,0.0010928047,0.11984518,0.0011867535],"about_ca_topic_score_codex":0.00021298282,"about_ca_topic_score_gemma":9.695526e-7,"teacher_disagreement_score":0.7235908,"about_ca_system_score_codex":0.00024493405,"about_ca_system_score_gemma":0.000028701917,"threshold_uncertainty_score":0.99920595},"labels":[],"label_agreement":null},{"id":"W6958025877","doi":"10.6084/m9.figshare.24187913","title":"Additional file 2 of Modeled small airways lung deposition of two fixed-dose triple therapy combinations assessed with in silico functional respiratory imaging","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Deposition (geology); In silico; Lung; Respiratory system; Respiratory physiology","score_opus":0.05275886261047619,"score_gpt":0.2692414870036287,"score_spread":0.21648262439315252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958025877","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010874055,0.000059278227,0.004852365,0.000054346587,0.000027115413,0.00031015227,0.9902883,0.0026784393,0.0006425978],"genre_scores_gemma":[0.21589257,7.543646e-7,0.036817066,0.0002289521,0.000050958937,0.0022596007,0.7446127,0.000033927052,0.00010346244],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990423,0.00006418761,0.00022879303,0.0002433466,0.00026482725,0.00015659252],"domain_scores_gemma":[0.99700636,0.0021966805,0.00018014808,0.0002804076,0.00030176798,0.000034658686],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007588627,0.000108443186,0.00014206654,0.00031158922,0.00008652705,0.00003383664,0.0002869416,0.000036505626,0.12989949],"category_scores_gemma":[0.0011380706,0.000105354324,0.000050813607,0.0009283643,0.000013467983,0.00026043525,0.00008883403,0.00011403987,0.00003362476],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008180524,0.0001006154,0.00015875154,0.000029808052,0.000005481652,0.000007812201,0.00004615018,0.00088484434,0.00007115248,0.000057579622,0.9955119,0.0031177623],"study_design_scores_gemma":[0.001972576,0.00026502178,0.062068626,0.004088137,0.0000041213593,0.000017191422,0.000010846984,0.917487,0.0026875045,0.004862856,0.006150028,0.0003860957],"about_ca_topic_score_codex":0.000022926408,"about_ca_topic_score_gemma":0.0000122671745,"teacher_disagreement_score":0.9893618,"about_ca_system_score_codex":0.0000431623,"about_ca_system_score_gemma":0.00024240788,"threshold_uncertainty_score":0.8708959},"labels":[],"label_agreement":null},{"id":"W6976748706","doi":"10.6068/dp14ba8065bc151","title":"Most Recent Data (2002). Statistics Canada. CANSIM: Society and Community - Time Use | Country: Canada | Table: Health behaviour in school-aged children 2002, Canadian student response to question: How many times a week do you usually eat or drink these items? | Variable: 15 years, French fries, Less than once a week, Males | Units: %, 2002. Data-Planet™ Statistical Ready Reference by Conquest Systems, Inc. Dataset-ID: 075-001-191.","year":2015,"lang":"en","type":"other","venue":"Data Planet","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Official statistics; Socioeconomic status; Population; Population statistics; Economic statistics; Descriptive statistics; Social statistics; Statistics education","score_opus":0.03957358349309021,"score_gpt":0.2749211646409417,"score_spread":0.23534758114785148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976748706","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009676173,0.0022641404,0.00023378302,0.00009379156,0.0003143608,0.0011647436,0.99521303,0.0006105309,0.00009592725],"genre_scores_gemma":[0.000015535617,0.0010631518,0.012639098,0.0013757751,0.00010357719,0.000031289586,0.97753596,0.00018563509,0.00704998],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99146366,0.003065066,0.00087215437,0.001796157,0.0014884698,0.0013145206],"domain_scores_gemma":[0.9869664,0.002351489,0.00065124524,0.007991399,0.00037228578,0.0016672345],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0038331023,0.0008943797,0.0011604143,0.00021370177,0.00048318846,0.0016273973,0.0075330157,0.00046950887,0.0007170234],"category_scores_gemma":[0.0021563626,0.000891521,3.1702615e-7,0.0011932065,0.00023093146,0.00074708485,0.0039014022,0.0020758638,0.00002901462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072524104,0.00018316203,0.0015986179,0.00012258017,0.00014162452,0.0007852301,0.000030299432,0.000009891478,2.0090677e-7,0.000035692257,0.9968189,0.0002012611],"study_design_scores_gemma":[0.00063745724,0.0002462179,0.0013722748,0.00033711013,0.000106327076,0.00033603166,0.00015923637,0.0026656005,6.2335923e-9,4.0688255e-7,0.9931333,0.0010060002],"about_ca_topic_score_codex":0.9999626,"about_ca_topic_score_gemma":0.9999044,"teacher_disagreement_score":0.07986949,"about_ca_system_score_codex":0.0012849412,"about_ca_system_score_gemma":0.08115443,"threshold_uncertainty_score":0.999409},"labels":[],"label_agreement":null},{"id":"W6977087287","doi":"10.6084/m9.figshare.26653996","title":"Additional file 2 of Performance analysis of conventional and AI-based variant callers using short and long reads","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Venn diagram; Degree (music); Indel; Diagram; Training set","score_opus":0.04056998422942117,"score_gpt":0.2757366639307596,"score_spread":0.2351666797013384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977087287","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031255526,0.00010505267,0.005889861,0.000015652095,0.000009455281,0.000041060037,0.9931284,0.00042375742,0.0000742067],"genre_scores_gemma":[0.34139028,0.0000012368265,0.09424544,0.000120482226,0.00003135169,0.00010677729,0.56404185,0.0000114255945,0.000051115207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994493,0.00001371169,0.00013113873,0.00018159609,0.00015065818,0.00007358303],"domain_scores_gemma":[0.9987972,0.00090769335,0.000038572547,0.00012945119,0.000095373136,0.00003174897],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000043258246,0.00006256308,0.00011977284,0.00021287613,0.00003597558,0.000041748153,0.000111087225,0.000035383153,0.3902832],"category_scores_gemma":[0.00040251898,0.000059735932,0.00004849804,0.0004645151,0.000018108341,0.00013570095,0.00008063014,0.000056502715,0.00000363337],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012296764,0.000009879859,0.00018973275,0.00017391899,0.00007010225,0.000012855554,0.000016794109,0.00019653353,0.0000030327649,0.000028134531,0.9957885,0.003509279],"study_design_scores_gemma":[0.000021735746,0.00003136045,0.015668485,0.002412052,0.000032734606,0.000017847024,4.193849e-7,0.97119427,0.00006478763,0.00009110299,0.010386481,0.00007872183],"about_ca_topic_score_codex":0.000004031372,"about_ca_topic_score_gemma":0.0000014310942,"teacher_disagreement_score":0.98540205,"about_ca_system_score_codex":0.000011955422,"about_ca_system_score_gemma":0.00010676989,"threshold_uncertainty_score":0.61027414},"labels":[],"label_agreement":null},{"id":"W6979226034","doi":"","title":"Exploring Challenges in Test Mocking: Developer Questions and Insights from StackOverflow","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Latent Dirichlet allocation; Popularity; Key (lock); Selection (genetic algorithm); Advice (programming); Test (biology); Topic model; Unit testing","score_opus":0.20006299142686132,"score_gpt":0.28784583702743455,"score_spread":0.08778284560057323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979226034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769291,0.002417456,0.01496889,0.0013448374,0.00021765505,0.00009006818,9.4690455e-7,0.0030913693,0.000939625],"genre_scores_gemma":[0.9614651,0.00080105645,0.037405394,0.00019844672,0.000026227708,0.000057026675,0.000001078791,0.000008112071,0.00003751786],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990289,0.00004653964,0.00019357885,0.00043739236,0.000103806145,0.00018975757],"domain_scores_gemma":[0.9986311,0.0007655408,0.000036831752,0.00045905192,0.000057994308,0.00004946782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013242583,0.00013869784,0.0001550829,0.00021193078,0.00014244832,0.00007151204,0.0003882939,0.000056058147,9.605833e-7],"category_scores_gemma":[0.00076940825,0.00013226185,0.000018089942,0.00038486093,0.000037497477,0.000532639,0.00034021083,0.00017536631,0.00001187499],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020242153,0.00007977945,0.9389387,0.000019430425,0.00001065338,0.000043567085,0.0029642917,0.000010404052,0.00025289948,0.008199662,0.00028354683,0.04919508],"study_design_scores_gemma":[0.00015813808,0.000024567908,0.96371955,0.0003701031,0.0000035933404,0.0000021348876,0.000044116714,0.0018400473,0.001232142,0.03120633,0.0012186604,0.00018061556],"about_ca_topic_score_codex":0.00029536587,"about_ca_topic_score_gemma":0.00015906969,"teacher_disagreement_score":0.049014468,"about_ca_system_score_codex":0.000050595212,"about_ca_system_score_gemma":0.00007396737,"threshold_uncertainty_score":0.5393481},"labels":[],"label_agreement":null},{"id":"W6979250945","doi":"","title":"Advanced Penetration Testing for Enhancing 5G Security","year":2024,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Limiting; Hyporeflexia; Proteogenomics; TSG101; Nucleofection","score_opus":0.06575916532810426,"score_gpt":0.21057147694091943,"score_spread":0.14481231161281516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979250945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076705694,0.00006836752,0.9136123,0.000049053244,0.00023735328,0.00014713102,0.0000018193734,0.007999541,0.0011787257],"genre_scores_gemma":[0.94077134,0.00000356603,0.05890667,0.00005282931,0.000049801813,0.0000016877499,0.000001982207,0.000009513483,0.00020258226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991251,0.000026638809,0.000100501,0.0004915848,0.000043601183,0.00021253401],"domain_scores_gemma":[0.9987791,0.0006997481,0.00004066554,0.00031653978,0.00010463641,0.00005927276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026976303,0.00010876884,0.00009240349,0.0001265756,0.00016107301,0.00013526551,0.0004031779,0.0000525896,0.0000022169447],"category_scores_gemma":[0.0003451709,0.00012240415,0.000058748985,0.000743583,0.000024193954,0.0006156524,0.00008224396,0.00010691152,0.000016337173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003456587,0.00012954039,0.007971448,0.0005039548,0.00006700902,0.00044566163,0.0016384132,0.017848069,0.008977385,0.8649809,0.006463051,0.09094003],"study_design_scores_gemma":[0.000103509534,0.00010911444,0.00020091611,0.000119242686,0.000010433193,0.000009115484,0.000008833949,0.74601734,0.0026642433,0.25015038,0.0004382041,0.00016865894],"about_ca_topic_score_codex":0.000031498297,"about_ca_topic_score_gemma":0.00002260564,"teacher_disagreement_score":0.86406565,"about_ca_system_score_codex":0.00008178819,"about_ca_system_score_gemma":0.00008329952,"threshold_uncertainty_score":0.49914962},"labels":[],"label_agreement":null},{"id":"W6979280317","doi":"","title":"Simulink Mutation Testing using CodeBERT","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutation; Mutation testing; Process (computing); Mutant; Frameshift mutation","score_opus":0.11593985627887145,"score_gpt":0.2193839124784322,"score_spread":0.10344405619956075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979280317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12795049,0.000015244899,0.86519074,0.0000440982,0.00012108593,0.00006772617,3.9951001e-7,0.004130995,0.0024791905],"genre_scores_gemma":[0.8988768,0.000001193576,0.10054546,0.00020385075,0.000013314175,1.6018541e-7,6.656302e-7,0.0000047066446,0.00035386713],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921316,0.000052383588,0.00010337532,0.0003963457,0.000041066607,0.0001936877],"domain_scores_gemma":[0.9987991,0.000511653,0.00006908283,0.00042436112,0.00014855276,0.000047254907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017774983,0.00010597422,0.00010471738,0.00019867015,0.00021240157,0.00007100176,0.00055225973,0.00006131874,0.0000018838872],"category_scores_gemma":[0.0004239335,0.00012385615,0.000040956813,0.0013844855,0.00004421385,0.000344164,0.00023090321,0.000110151355,0.000011843265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027372937,0.00020878937,0.13758022,0.0000995989,0.00008526822,0.00096967,0.00041584705,0.43773708,0.0009780885,0.3673545,0.0035004378,0.051043134],"study_design_scores_gemma":[0.00014807975,0.000020529522,0.0010423749,0.000065772336,0.000012689027,0.000007260537,0.00000482428,0.88934976,0.00029961325,0.1088465,0.00008343791,0.000119163786],"about_ca_topic_score_codex":0.00020701025,"about_ca_topic_score_gemma":0.000004584303,"teacher_disagreement_score":0.7709263,"about_ca_system_score_codex":0.000100935125,"about_ca_system_score_gemma":0.00010656166,"threshold_uncertainty_score":0.5050707},"labels":[],"label_agreement":null},{"id":"W6979735060","doi":"","title":"Acoustical comparisons of Alberta concert halls","year":2003,"lang":"en","type":"article","venue":"NPARC","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.028814005696070427,"score_gpt":0.27822762024950576,"score_spread":0.24941361455343533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979735060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003012156,0.000023118695,0.9174902,0.0003415781,0.00013298518,0.00006514807,4.7726786e-7,0.0015002608,0.07743406],"genre_scores_gemma":[0.59615594,0.0000010601348,0.4035434,0.00012536487,0.0000071989625,0.000004062196,2.0923021e-7,0.0000035877167,0.0001591688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992147,0.000057611804,0.00017025933,0.00019995913,0.0001701184,0.0001873438],"domain_scores_gemma":[0.9987012,0.0006443304,0.000054825054,0.00046160104,0.00006658618,0.00007142487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019691522,0.000083151834,0.00016089072,0.00004278963,0.00004473474,0.000028583372,0.00044606233,0.000049111564,0.00005166661],"category_scores_gemma":[0.0007491005,0.00007544951,0.00004164532,0.00018658656,0.00007851085,0.000074403375,0.000077227436,0.00009453748,0.000021440617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004436895,0.00022743162,0.023315927,0.000029673316,0.000022996865,0.000013878796,0.0005470013,0.00004189634,0.0055484166,0.5722844,0.38465062,0.013313287],"study_design_scores_gemma":[0.0008802987,0.0004968766,0.005935594,0.00020914353,0.000036383517,0.00018163184,0.000017328966,0.16144453,0.059866864,0.72600585,0.04409928,0.00082623214],"about_ca_topic_score_codex":0.00006477669,"about_ca_topic_score_gemma":0.000003774054,"teacher_disagreement_score":0.5931438,"about_ca_system_score_codex":0.000013619921,"about_ca_system_score_gemma":0.000068768095,"threshold_uncertainty_score":0.30767417},"labels":[],"label_agreement":null},{"id":"W6990863403","doi":"","title":"Enabling Language-Specific Transformations in Language-Agnostic Program Reduction","year":2023,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Metis; Program transformation; Transformation (genetics); Reduction (mathematics); Matching (statistics); Domain (mathematical analysis); Abstract syntax tree; Rewriting","score_opus":0.015273204512537096,"score_gpt":0.24332602162394068,"score_spread":0.22805281711140357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990863403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98912215,0.000364865,0.0015214914,0.0003926916,0.00047295046,0.0005401004,0.000010122078,0.007330894,0.00024471246],"genre_scores_gemma":[0.594972,0.0009859917,0.22147878,0.000017814024,0.0001747149,0.000024116067,0.0017291876,0.000119518656,0.18049785],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99887425,0.000058514106,0.00016199614,0.0003692497,0.0002644907,0.00027152995],"domain_scores_gemma":[0.9991619,0.000095498086,0.00016114557,0.00042617036,0.000098771954,0.000056486133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022737775,0.00018479311,0.0002649835,0.0007612806,0.00014239791,0.00006309929,0.00066327065,0.00021015234,0.000013485077],"category_scores_gemma":[0.000048066493,0.0002247701,0.00010921286,0.000887647,0.000037226833,0.00038915445,0.000052834377,0.0003054649,0.000052194257],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003230421,0.00016319267,0.00011789088,0.00038925768,0.000031795716,0.00018141209,0.7364854,0.00014858299,0.0018961304,0.00023812328,0.006682761,0.2536331],"study_design_scores_gemma":[0.0036705446,0.0013684276,0.031919293,0.007707648,0.00028658766,0.000119496144,0.886645,0.028903136,0.024226934,0.009665488,0.0016824632,0.003804968],"about_ca_topic_score_codex":0.01988367,"about_ca_topic_score_gemma":0.009089386,"teacher_disagreement_score":0.39415014,"about_ca_system_score_codex":0.0000890913,"about_ca_system_score_gemma":0.000070511676,"threshold_uncertainty_score":0.986643},"labels":[],"label_agreement":null},{"id":"W6998781786","doi":"","title":"Automatic fault localization in concurrent programs using noising and search strategies","year":2021,"lang":"en","type":"dissertation","venue":"e-scholar@UOIT (University of Ontario Institute of Technology)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Debugging; Concurrency; Program slicing; Set (abstract data type); Java; Code (set theory); Heuristic; Fault (geology); Algorithmic program debugging; Software","score_opus":0.027375496572537194,"score_gpt":0.2635435827122169,"score_spread":0.2361680861396797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6998781786","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973163,0.0004361027,0.024314068,0.000036204267,0.00029248258,0.00032070937,0.0000028806637,0.0011751448,0.00025937875],"genre_scores_gemma":[0.23822607,0.000044280103,0.7614978,0.0000047344283,0.000004948969,0.0000011620319,0.00011743529,0.00001258634,0.000090971684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984815,0.000015163934,0.00032411484,0.0005567019,0.00034980034,0.00027269748],"domain_scores_gemma":[0.99865764,0.0000047724866,0.00037436324,0.00052272726,0.0003880368,0.000052427793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037514474,0.00025725816,0.00054829766,0.00092687696,0.0002917974,0.0001244897,0.0009269917,0.00057432643,0.000010573264],"category_scores_gemma":[0.00010391454,0.0003347413,0.00008437454,0.0012187076,0.00019831132,0.0012817461,0.00035946508,0.0010203838,9.922275e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016164078,0.00028702477,0.002898916,0.0009743821,0.00010454317,0.00025552596,0.010495396,0.00044133858,0.00077619153,0.005195471,0.000059108945,0.97849596],"study_design_scores_gemma":[0.009485718,0.002908748,0.07152249,0.050534904,0.0011574156,0.00070008263,0.030892666,0.5509059,0.017734056,0.06814207,0.18905354,0.0069624097],"about_ca_topic_score_codex":0.021781333,"about_ca_topic_score_gemma":0.037892174,"teacher_disagreement_score":0.97153354,"about_ca_system_score_codex":0.0005000388,"about_ca_system_score_gemma":0.0017225951,"threshold_uncertainty_score":0.9999105},"labels":[],"label_agreement":null},{"id":"W7000725270","doi":"","title":"Fuzzing OpenMP Compilers","year":2024,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Fuzz testing; Compiler; Correctness; Test suite; Suite; Flexibility (engineering); Compile time; Code (set theory)","score_opus":0.015617168249005255,"score_gpt":0.22445262208487107,"score_spread":0.20883545383586583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000725270","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9450196,0.0013767823,0.009928449,0.0030867993,0.0037846284,0.00077763374,0.00003729909,0.02431712,0.011671671],"genre_scores_gemma":[0.094478495,0.00012739039,0.22073792,0.00007139036,0.00008436092,0.0000011395865,0.0002661943,0.00006598032,0.68416715],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877524,0.000042322266,0.00011578312,0.00051257137,0.00030188687,0.00025219953],"domain_scores_gemma":[0.99895763,0.00007942273,0.00016320625,0.0005800737,0.00013553623,0.00008411657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019194042,0.00022656118,0.00033736872,0.0003891253,0.0001692176,0.00010871282,0.0013864887,0.00022543596,0.000030227751],"category_scores_gemma":[0.000023945468,0.0002630311,0.00017013217,0.00038272276,0.00005135261,0.00030219718,0.0002750385,0.0003334025,0.00017464273],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087955166,0.00016793147,0.00069945655,0.002120782,0.00038564682,0.00085118937,0.47576028,0.00007038908,0.0018992305,0.0116585735,0.4142429,0.09205565],"study_design_scores_gemma":[0.005711208,0.0036409353,0.02980023,0.033822447,0.0026292836,0.00034961817,0.2665097,0.18789983,0.02888149,0.3521542,0.07327286,0.015328177],"about_ca_topic_score_codex":0.017217712,"about_ca_topic_score_gemma":0.004080879,"teacher_disagreement_score":0.8505411,"about_ca_system_score_codex":0.00007059017,"about_ca_system_score_gemma":0.00011849269,"threshold_uncertainty_score":0.9999822},"labels":[],"label_agreement":null},{"id":"W7008673472","doi":"","title":"Complemento para la automatización de pruebas de aceptación para Visual Studio","year":2011,"lang":"es","type":"other","venue":"e-Archivo (Carlos III University of Madrid)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Studio; Software","score_opus":0.031688985633827604,"score_gpt":0.27727159360236614,"score_spread":0.24558260796853854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008673472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019522823,0.0004734139,0.8091355,0.00041454512,0.00039387285,0.0014468612,0.00022975872,0.011606363,0.15677688],"genre_scores_gemma":[0.24081303,0.0008007051,0.68467146,0.00029977097,0.000402138,0.000010226856,0.000076565506,0.00038449658,0.072541595],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954632,0.0009434401,0.00049570977,0.0011695189,0.0007731354,0.0011549976],"domain_scores_gemma":[0.9963659,0.0007951042,0.0008542461,0.0013544997,0.00016152489,0.00046869865],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011196362,0.0008042947,0.0011312165,0.0007841495,0.00050796865,0.0001496188,0.0032458713,0.00047328745,0.0013346408],"category_scores_gemma":[0.00015975948,0.00097101927,0.00047680942,0.00053996907,0.0009301837,0.0002752524,0.001986933,0.0008265275,0.00025337617],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045612224,0.0025732494,0.05700647,0.0017329991,0.0018942989,0.0016393081,0.036028046,0.00005093852,0.0005862616,0.018254431,0.80704284,0.07273506],"study_design_scores_gemma":[0.008264398,0.0034296052,0.19836272,0.009717037,0.0016460175,0.00059420237,0.0014699647,0.039753783,0.0015448877,0.028306384,0.7008107,0.0061003156],"about_ca_topic_score_codex":0.005781058,"about_ca_topic_score_gemma":0.00026892286,"teacher_disagreement_score":0.22129022,"about_ca_system_score_codex":0.00034534317,"about_ca_system_score_gemma":0.00079809286,"threshold_uncertainty_score":0.9995783},"labels":[],"label_agreement":null},{"id":"W7018138705","doi":"","title":"Darker Politics: Democracies, Labour Rights and Climate Change - Poster","year":2022,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Feud; Journalism; Climate change; Event (particle physics); Spanish Civil War; Civil rights; Newspaper","score_opus":0.01294080700003063,"score_gpt":0.1718596429534687,"score_spread":0.15891883595343806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018138705","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041789716,0.00041953503,0.0008868297,0.00042397517,0.0002940936,0.00041649965,0.0022391703,0.018020045,0.976882],"genre_scores_gemma":[0.0062478175,0.00018409903,0.013461282,0.00062382914,0.00021741606,4.8732903e-7,0.00045383573,0.00022956477,0.97858167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784946,0.00013573118,0.00013112473,0.0009241674,0.00032441414,0.00063508237],"domain_scores_gemma":[0.99833053,0.00017955241,0.00024844744,0.00087243674,0.000021593309,0.00034741266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000040846637,0.0004784409,0.00042190903,0.0013662631,0.0006363242,0.00053294474,0.0020614665,0.0003079734,0.0006969541],"category_scores_gemma":[0.000011022694,0.00057619176,0.00016486441,0.0012539974,0.00026416618,0.0024434477,0.0035041715,0.0004299985,0.0000870036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032647466,0.0001112108,0.011360371,0.00010995102,0.000106278,0.0017962939,0.00029659015,2.1035262e-7,1.2271445e-7,0.1314576,0.8519237,0.002805032],"study_design_scores_gemma":[0.00038385185,0.00010123838,0.00037618613,0.00018628588,0.000040273957,0.00005490199,0.00009587457,0.000028089205,0.000001846312,0.004113838,0.993927,0.000690609],"about_ca_topic_score_codex":0.00028782553,"about_ca_topic_score_gemma":0.000015129801,"teacher_disagreement_score":0.14200331,"about_ca_system_score_codex":0.00014250385,"about_ca_system_score_gemma":0.00012726808,"threshold_uncertainty_score":0.99966896},"labels":[],"label_agreement":null},{"id":"W7033563533","doi":"","title":"Real-time detection of water quality aberrations in a water distribution system","year":2009,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contamination; Water quality; Tap water; Turbidity; Water pollution; Sewage; Water treatment","score_opus":0.014269534646226862,"score_gpt":0.2367184476112001,"score_spread":0.22244891296497324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033563533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94326156,0.00002693639,0.052782737,0.00030811207,0.00021141858,0.0003764613,0.000021975462,0.0017300776,0.001280726],"genre_scores_gemma":[0.9970426,0.000012214492,0.0018223716,0.0000025996524,0.000017678918,7.167467e-7,0.00033620137,0.0000062447807,0.00075935567],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99875146,0.00022752662,0.0002684015,0.00026610636,0.00028904417,0.00019744849],"domain_scores_gemma":[0.9988024,0.00009589142,0.00024221992,0.0005895315,0.00023991887,0.000030006217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086293527,0.00014694291,0.00031765059,0.00017588149,0.00019038297,0.000022544513,0.00080206024,0.00020013357,0.000005073165],"category_scores_gemma":[0.0000327561,0.00011085853,0.0001388331,0.00026300654,0.00004741218,0.00022159611,0.00009654863,0.00018274061,0.000022240782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002545588,0.00017362826,0.000153403,0.00064618647,0.00007072005,0.000019090818,0.015266298,0.000119860284,0.9693597,0.0018433897,0.0017760862,0.010317109],"study_design_scores_gemma":[0.001932021,0.0009350685,0.5593818,0.0017988292,0.00047138726,0.000049547063,0.004165399,0.03640543,0.3667075,0.025859566,0.0005794996,0.0017139282],"about_ca_topic_score_codex":0.006369171,"about_ca_topic_score_gemma":0.0005550039,"teacher_disagreement_score":0.60265213,"about_ca_system_score_codex":0.00015654146,"about_ca_system_score_gemma":0.000044527256,"threshold_uncertainty_score":0.9628324},"labels":[],"label_agreement":null},{"id":"W7034311940","doi":"","title":"Superkül Completes Canada’s First Active House – Azure Magazine","year":2013,"lang":"en","type":"other","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Work (physics); Doors; Order (exchange)","score_opus":0.013561359358344214,"score_gpt":0.20949878691136892,"score_spread":0.1959374275530247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034311940","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037721704,0.0003384295,0.10499507,0.0022454585,0.0006587442,0.000470397,0.00004588783,0.0603295,0.83091277],"genre_scores_gemma":[0.00080658705,0.0000339185,0.21817876,0.001473469,0.00025171286,0.0000577075,0.00001651901,0.00043532057,0.778746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984629,0.00003346,0.00017517075,0.0005686263,0.00036619641,0.00039360355],"domain_scores_gemma":[0.9982934,0.00025595838,0.00012937485,0.0011050818,0.0000695278,0.00014667303],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000058211725,0.0003668574,0.00037153237,0.0001811123,0.00008871427,0.00014532448,0.0014046183,0.00020116102,0.0011128334],"category_scores_gemma":[0.000120747354,0.00030476553,0.000057643967,0.00019949015,0.00005290917,0.000093465984,0.00037384316,0.00024710633,0.00040018288],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.2002913e-7,0.0000144031965,0.00014262926,0.000026201138,0.000022684324,0.000021094722,0.000025970894,4.2475534e-7,0.0000010113712,0.0014857018,0.99423146,0.0040280926],"study_design_scores_gemma":[0.0000943537,0.00003573919,0.00029723308,0.00017273778,0.0000073369247,0.00002303378,0.0000013768637,0.0015758548,0.000043809385,0.0010878945,0.99618953,0.0004711088],"about_ca_topic_score_codex":0.7772692,"about_ca_topic_score_gemma":0.736039,"teacher_disagreement_score":0.113183685,"about_ca_system_score_codex":0.00014290008,"about_ca_system_score_gemma":0.0004985144,"threshold_uncertainty_score":0.99994045},"labels":[],"label_agreement":null},{"id":"W7036048626","doi":"","title":"APG 504 - Floating Heads","year":2022,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Crew; Aviation; Certificate; Crash; Aviation safety","score_opus":0.007905021846431473,"score_gpt":0.1957923208804181,"score_spread":0.18788729903398663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036048626","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020804541,0.00032642647,0.00011432863,0.00018580332,0.00035334745,0.0002717747,0.00003311982,0.0073690424,0.9913441],"genre_scores_gemma":[0.00010087981,0.000050042556,0.082193345,0.00064643135,0.00010689716,0.000019403915,0.00006141458,0.00009508883,0.9167265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981845,0.000098957826,0.00054008485,0.00028942202,0.00056343846,0.00032361393],"domain_scores_gemma":[0.9981928,0.00023809784,0.0005962794,0.00078886986,0.00008833323,0.00009561641],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004006445,0.00031030603,0.00036850313,0.0001370419,0.00013274906,0.00011031164,0.0011369186,0.00019787386,0.24990958],"category_scores_gemma":[0.00032438827,0.00032682257,0.00014358471,0.000020190942,0.00006750376,2.8653912e-7,0.0005097173,0.0003697912,0.00325877],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042351417,0.000023146651,0.0000058371193,0.00016529644,0.00001839947,0.000017881119,0.00012209233,0.000073842035,4.4934534e-8,0.00012232285,0.99123365,0.008213278],"study_design_scores_gemma":[0.00016948117,0.00012613824,0.0000026878474,0.00015581319,0.0000122218335,0.00010439696,0.0000095337655,0.00030466437,0.0000038014352,0.00024813725,0.99852234,0.00034081115],"about_ca_topic_score_codex":0.004454618,"about_ca_topic_score_gemma":0.000110076166,"teacher_disagreement_score":0.2466508,"about_ca_system_score_codex":0.00007495271,"about_ca_system_score_gemma":0.000050853498,"threshold_uncertainty_score":0.9999184},"labels":[],"label_agreement":null},{"id":"W7036703262","doi":"","title":"Conference report: opportunity and challenge in wood drying: Quality control and energy saving","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Theme (computing); Control (management); European union; Energy (signal processing)","score_opus":0.05657642606882203,"score_gpt":0.29346110468898073,"score_spread":0.23688467862015872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036703262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05983328,0.00014118133,0.9225812,0.0022238912,0.000079324505,0.0000596309,5.5738514e-7,0.003479903,0.011601036],"genre_scores_gemma":[0.96438086,0.000029158915,0.03488358,0.00055268547,0.000017858261,0.000011544407,6.511228e-7,0.000004709366,0.000118974924],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878764,0.00017867271,0.00028915243,0.000403145,0.00014207252,0.0001992937],"domain_scores_gemma":[0.9984652,0.0007253622,0.00012268175,0.00046775915,0.00006785493,0.00015116231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014879579,0.000119289376,0.00022571385,0.00008272709,0.000075757074,0.00012730462,0.00023056298,0.00006926447,0.000003040503],"category_scores_gemma":[0.0014247405,0.000106799416,0.000015534119,0.00008962497,0.00006576118,0.00021406444,0.0002068029,0.000108165616,3.1538167e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073112465,0.00010293299,0.05586344,0.000049399612,0.000009917787,0.00011181274,0.00084414834,0.0000010670642,0.00033394678,0.43224826,0.00077998947,0.5096478],"study_design_scores_gemma":[0.0017153791,0.00039250453,0.18283573,0.00026753917,0.000010865991,0.0004829007,0.000046572055,0.15181662,0.00039679217,0.6565747,0.004458713,0.0010016542],"about_ca_topic_score_codex":0.0013203672,"about_ca_topic_score_gemma":0.0002449567,"teacher_disagreement_score":0.9045476,"about_ca_system_score_codex":0.000012629092,"about_ca_system_score_gemma":0.000049230424,"threshold_uncertainty_score":0.43551537},"labels":[],"label_agreement":null},{"id":"W7036737297","doi":"","title":"Cost effective basement wall drainage alternatives employing exterior insulation basement systems (EIBS)","year":2001,"lang":"en","type":"article","venue":"NPARC","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Research Council Canada","keywords":"Drainage; Basement; Thermal insulation; Moisture; Current (fluid)","score_opus":0.034961439353279875,"score_gpt":0.29583459653355165,"score_spread":0.26087315718027176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036737297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10024118,0.0000834769,0.88804054,0.0003560078,0.00038293496,0.0011953608,0.0000026001917,0.0047192797,0.004978643],"genre_scores_gemma":[0.9341034,0.00001211503,0.06481152,0.0002589146,0.00009390676,0.0005589536,0.0000050558024,0.000017624096,0.00013846779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826694,0.00020857913,0.0002807395,0.0004833335,0.00041589336,0.00034449436],"domain_scores_gemma":[0.9986609,0.00038703077,0.0001553738,0.00056960766,0.0001227879,0.00010425336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072861754,0.00020420527,0.00020359801,0.00017661584,0.00020574914,0.00029061234,0.0005429376,0.000049735198,0.000025172094],"category_scores_gemma":[0.00018337197,0.00018887491,0.000058221958,0.00033626758,0.000034166558,0.0003943801,0.0002411576,0.00012808284,0.00003521612],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006750192,0.00061625184,0.06400111,0.00021548664,0.00013403331,0.0004376578,0.006742235,0.0008168712,0.022468226,0.028422358,0.007859243,0.868219],"study_design_scores_gemma":[0.00169087,0.000941994,0.10916218,0.0012172962,0.000037461472,0.00017688604,0.000059953698,0.792168,0.008995972,0.06912913,0.015226276,0.0011939498],"about_ca_topic_score_codex":0.0002695339,"about_ca_topic_score_gemma":0.000003560341,"teacher_disagreement_score":0.8670251,"about_ca_system_score_codex":0.0002442375,"about_ca_system_score_gemma":0.000030319625,"threshold_uncertainty_score":0.77020955},"labels":[],"label_agreement":null},{"id":"W7036862229","doi":"","title":"2003 Christmas Bird Counts in Nebraska","year":2004,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Snow; Buteo; Waterfowl; Dozen; Ornithology","score_opus":0.009654367088606739,"score_gpt":0.19573137451864106,"score_spread":0.18607700743003433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036862229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08200867,0.0005212968,0.88266635,0.002694083,0.0006667831,0.00040199942,0.000009163088,0.009367861,0.02166378],"genre_scores_gemma":[0.6623419,0.000037230613,0.3359979,0.00023132475,0.000033434982,4.2226307e-7,0.0000018613471,0.000012758825,0.0013431762],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99933314,0.000021639615,0.00008222043,0.00022707015,0.00017267467,0.0001632566],"domain_scores_gemma":[0.9994175,0.000045412347,0.00006893815,0.0003260629,0.000085516695,0.000056597473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014609334,0.000081151185,0.0001369453,0.00020114856,0.00006896793,0.000017694625,0.0006137202,0.000078248326,0.00002832836],"category_scores_gemma":[0.00006774604,0.00010275328,0.000037031037,0.0008277879,0.00006603647,0.00022169408,0.0001694598,0.00011635344,0.00017129979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008739546,0.0015128261,0.13014573,0.00024917242,0.00010308543,0.001579923,0.010330196,0.0013477653,0.00080202444,0.22933742,0.30406743,0.320437],"study_design_scores_gemma":[0.0080482885,0.0012395673,0.3989903,0.0014645961,0.00006175945,0.00018925322,0.0005039807,0.050777167,0.0013489828,0.37530714,0.15937594,0.0026930282],"about_ca_topic_score_codex":0.0010502525,"about_ca_topic_score_gemma":0.00015634067,"teacher_disagreement_score":0.58033323,"about_ca_system_score_codex":0.00007825891,"about_ca_system_score_gemma":0.00017615268,"threshold_uncertainty_score":0.4190157},"labels":[],"label_agreement":null},{"id":"W7038428449","doi":"","title":"Haçlıların Anadolu’da kuşattığı kaleler ve Türk savunması","year":2016,"lang":"tr","type":"dissertation","venue":"DSpace - AKÜ (Afyon Kocatepe University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Point (geometry); Quarter (Canadian coin)","score_opus":0.0204608054640158,"score_gpt":0.2341937781290641,"score_spread":0.21373297266504832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038428449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33745438,0.0035081015,0.28702083,0.009520608,0.019098084,0.005709807,0.00086131145,0.070534766,0.2662921],"genre_scores_gemma":[0.6336546,0.0013691935,0.054173153,0.00088246394,0.0011364014,0.000021871818,0.00085184455,0.00048244267,0.30742803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932998,0.00041501547,0.00068369304,0.0026196404,0.001242947,0.0017389365],"domain_scores_gemma":[0.99383956,0.00072943035,0.0011384891,0.0022732385,0.0012237487,0.0007955233],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0006920485,0.0014426552,0.0012299961,0.0024654742,0.0012876425,0.00086116116,0.003884404,0.0014216788,0.0002639329],"category_scores_gemma":[0.0005026269,0.0015405611,0.0006563068,0.0029222607,0.00042553895,0.0014751119,0.0009249711,0.0013174543,0.0017612685],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014395807,0.0018684057,0.06018217,0.002135696,0.001650122,0.005941692,0.024679314,0.000093795155,0.0044161063,0.081370905,0.6975701,0.11865215],"study_design_scores_gemma":[0.008112636,0.0029994664,0.032371696,0.012125886,0.0018569282,0.00033280504,0.0029978391,0.0078786155,0.011517511,0.01709226,0.889194,0.013520334],"about_ca_topic_score_codex":0.0026021812,"about_ca_topic_score_gemma":0.00055975147,"teacher_disagreement_score":0.29620022,"about_ca_system_score_codex":0.0009865304,"about_ca_system_score_gemma":0.0011105596,"threshold_uncertainty_score":0.9998747},"labels":[],"label_agreement":null},{"id":"W7039326777","doi":"","title":"Le modèle antarctique","year":2012,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology)","score_opus":0.005637717421746731,"score_gpt":0.14927996539349433,"score_spread":0.1436422479717476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039326777","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041967235,0.0023540838,0.01623471,0.012355959,0.00072393124,0.00024529258,0.00013124711,0.00040717534,0.9671279],"genre_scores_gemma":[0.53071564,0.00031072914,0.075757235,0.0033291457,0.00034213773,0.000021608208,0.000009144865,0.0001541078,0.38936028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99697834,0.00015261745,0.00037254326,0.0004914328,0.0014065992,0.00059844943],"domain_scores_gemma":[0.99805254,0.0005473779,0.0003356127,0.0005918548,9.409425e-7,0.00047167414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000023299152,0.0004061982,0.00047174277,0.00004859049,0.00026983893,0.00007407686,0.0008289316,0.000102215265,0.00014048071],"category_scores_gemma":[0.000010040748,0.00043662902,0.000055292523,0.00013186102,0.00019728727,0.0005620276,0.0005913174,0.00032393157,1.5295056e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004484957,0.00008512325,0.007910811,0.00037237664,0.00009650617,0.00012550651,0.00014430206,0.000018764782,0.0006670647,0.9120729,0.035668485,0.042793322],"study_design_scores_gemma":[0.00041223835,0.0001356898,0.017247148,0.0011042671,0.000038246388,0.000089591165,0.00021423482,0.008211221,0.026703088,0.03494774,0.9098321,0.0010644391],"about_ca_topic_score_codex":0.07157292,"about_ca_topic_score_gemma":0.051046174,"teacher_disagreement_score":0.87712514,"about_ca_system_score_codex":0.000010474064,"about_ca_system_score_gemma":0.007915826,"threshold_uncertainty_score":0.99980855},"labels":[],"label_agreement":null},{"id":"W7039669055","doi":"","title":"Mechanická a chemická regulace pcháče rolního","year":2007,"lang":"en","type":"dissertation","venue":"Digital Repository (National Repository of Grey Literature)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thistle; Chemical control; Arable land; Vegetation (pathology); Perennial plant; Weed control","score_opus":0.008220208854451792,"score_gpt":0.2602790487211613,"score_spread":0.2520588398667095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039669055","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06137131,0.015460344,0.035752013,0.00019707532,0.015885709,0.0022938836,0.00016714666,0.019988598,0.8488839],"genre_scores_gemma":[0.86049837,0.000022566828,0.033754464,0.00021820575,0.001315684,0.00012367591,0.001284079,0.00017807921,0.102604896],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99423265,0.00008473739,0.00140712,0.0013530955,0.0023810097,0.00054137193],"domain_scores_gemma":[0.99310017,0.00063014595,0.0014145275,0.0012531148,0.0033284128,0.00027361576],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004668869,0.00076983083,0.0007407715,0.00080491405,0.00038415307,0.0017379448,0.0018707471,0.00095186563,0.0000017829606],"category_scores_gemma":[0.0010144217,0.00079027313,0.0005679514,0.000987064,0.00010747223,0.0024614003,0.00020718083,0.00085464783,0.000010186496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029467274,0.005413499,0.0073302016,0.00834064,0.0033253843,0.0067010922,0.023743272,0.00014638515,0.23592827,0.19361524,0.40540156,0.107107714],"study_design_scores_gemma":[0.0015040007,0.0010955445,0.00718339,0.010345731,0.00022170124,0.0051038763,0.00010454677,0.004776361,0.79845196,0.13607733,0.03042574,0.0047098324],"about_ca_topic_score_codex":0.000017488204,"about_ca_topic_score_gemma":9.900895e-7,"teacher_disagreement_score":0.79912704,"about_ca_system_score_codex":0.00041033764,"about_ca_system_score_gemma":0.00088140223,"threshold_uncertainty_score":0.9994548},"labels":[],"label_agreement":null},{"id":"W7042304904","doi":"","title":"Petition for Truing Up of transmission tariff under “System Strengthening Scheme in Roorkee in Northern Region” – EQ","year":2025,"lang":"en","type":"other","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scheme (mathematics); Tariff; Transmission (telecommunications); Quarter (Canadian coin)","score_opus":0.02588655558605262,"score_gpt":0.26128980982712,"score_spread":0.2354032542410674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042304904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009367995,0.00027623057,0.945892,0.00013866607,0.00016433514,0.00040196622,0.000002487531,0.003925375,0.049105264],"genre_scores_gemma":[0.07118598,0.00003479597,0.82925135,0.00008495723,0.00009233038,0.00015688197,0.000026177453,0.00019597478,0.09897154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865407,0.00006601966,0.0004082745,0.00046242203,0.00018115799,0.00022803742],"domain_scores_gemma":[0.9989591,0.00029611227,0.00020904254,0.00045114857,0.000052475418,0.000032067528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031957089,0.00021782829,0.0003756983,0.00073300884,0.00002641108,0.000034601704,0.00053476746,0.00028550107,0.0000094555735],"category_scores_gemma":[0.000080562,0.00019977512,0.000091120906,0.00042603156,0.000019835747,0.0000693848,0.000069586735,0.00018831044,0.0000012606064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012472602,0.00048792784,0.03203485,0.006514459,0.00013551705,0.000075300086,0.002795401,0.00072156364,0.00019443636,0.12737559,0.20539448,0.62414575],"study_design_scores_gemma":[0.009243939,0.0007915491,0.0029281138,0.11992928,0.00009914441,0.00007249851,0.0005982415,0.6371785,0.0030284484,0.11929294,0.1025665,0.004270849],"about_ca_topic_score_codex":0.0018533475,"about_ca_topic_score_gemma":0.0014211023,"teacher_disagreement_score":0.6364569,"about_ca_system_score_codex":0.000120916535,"about_ca_system_score_gemma":0.00015676972,"threshold_uncertainty_score":0.8146593},"labels":[],"label_agreement":null},{"id":"W7084066819","doi":"10.1007/978-3-032-00006-4_2","title":"Trichomorphology","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature","funders":"","keywords":"Focus (optics); Diversity (politics); Taxonomy (biology); Line drawings; Biological evolution","score_opus":0.02019131002627012,"score_gpt":0.24671869105733785,"score_spread":0.22652738103106773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084066819","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.876243e-8,0.00016277717,0.39552972,0.00029929454,0.0002141299,0.00005328183,0.0000011230078,0.012315168,0.5914245],"genre_scores_gemma":[0.000031920987,0.000027020304,0.23152307,0.0012543673,0.000036744786,0.0000047951203,0.000003362164,0.000008416626,0.7671103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912685,0.000007803242,0.00018093581,0.0004076572,0.0001306968,0.00014606354],"domain_scores_gemma":[0.9986194,0.0003312492,0.000078888675,0.00085052394,0.00007917725,0.000040787323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012727952,0.00018710387,0.00024074038,0.0002482323,0.00004683351,0.00005784968,0.0009814638,0.00026307817,0.00012705677],"category_scores_gemma":[0.00009599979,0.00016850329,0.00008842616,0.000046152065,0.000036850637,0.00004522451,0.00043036084,0.00024446964,0.00019888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.271053e-7,0.0000016994588,0.0000024412332,0.0000040987593,0.000005194852,0.000022697679,0.0000025752379,3.5598283e-8,1.4758267e-7,0.5213754,0.42401186,0.05457358],"study_design_scores_gemma":[0.000036163045,0.000029202172,0.0000027349647,0.00005389681,0.0000055178994,0.000028908189,1.415422e-8,0.00033751354,0.000011964001,0.5812344,0.41811034,0.00014931538],"about_ca_topic_score_codex":0.000015416043,"about_ca_topic_score_gemma":0.0000011665069,"teacher_disagreement_score":0.17568581,"about_ca_system_score_codex":0.000034764154,"about_ca_system_score_gemma":0.00011813049,"threshold_uncertainty_score":0.6871365},"labels":[],"label_agreement":null},{"id":"W7091358849","doi":"10.1109/access.2025.3622024","title":"Robust Real-Time Arabic Speech Recognition for AAVs in Adverse Acoustic Conditions Using Lightweight CNNs","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Latency (audio); Inference; Noise (video); Robustness (evolution); Pattern recognition (psychology); Arabic; Ranging; Speech enhancement","score_opus":0.07700867099233005,"score_gpt":0.34108491656649564,"score_spread":0.2640762455741656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7091358849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19339263,0.000023006349,0.8004722,0.00023993342,0.00061979605,0.0005099536,0.000025445179,0.0036241005,0.0010929186],"genre_scores_gemma":[0.6350947,0.000024606266,0.36376864,0.0004896152,0.00013830178,0.00018073313,0.00003569167,0.00002352439,0.00024418355],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874604,0.0000576809,0.00030572154,0.00044289455,0.00013707436,0.0003105726],"domain_scores_gemma":[0.9985166,0.0006695471,0.00011592249,0.00046096946,0.00018551477,0.00005143017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033062883,0.000158968,0.00020999827,0.0004653914,0.00019027614,0.00018726836,0.00080484955,0.000111831556,0.00001335933],"category_scores_gemma":[0.00032026588,0.00016466672,0.000069349655,0.0009250478,0.00004355019,0.0008881277,0.00013090782,0.00013164988,0.000019685605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025791756,0.002649897,0.051995087,0.0017726279,0.00033665536,0.0007381867,0.0016564769,0.050312933,0.08940611,0.0030890699,0.5663915,0.23139349],"study_design_scores_gemma":[0.0011438397,0.00009969685,0.007066669,0.0016433767,0.00009027328,0.000050150014,0.0000075744874,0.67615247,0.046646904,0.26619005,0.00018099233,0.0007279751],"about_ca_topic_score_codex":0.00029844846,"about_ca_topic_score_gemma":0.0000443785,"teacher_disagreement_score":0.62583953,"about_ca_system_score_codex":0.00011464917,"about_ca_system_score_gemma":0.00015762205,"threshold_uncertainty_score":0.6714914},"labels":[],"label_agreement":null},{"id":"W7092191125","doi":"10.1109/ms.2025.3621625","title":"What Inputs Drive Effective Large Language Model-Based Unit Test Generation?","year":2025,"lang":"","type":"article","venue":"IEEE Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Unit testing; Correctness; Software quality; Code coverage; Code (set theory); Test (biology); Test Management Approach; Test case","score_opus":0.01701364261331757,"score_gpt":0.29850441364940394,"score_spread":0.2814907710360864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092191125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026728949,0.002151287,0.95309526,0.0009676892,0.0035255293,0.0011647366,0.000109138084,0.012163467,0.0000939532],"genre_scores_gemma":[0.84357756,0.000057155125,0.14775486,0.006341422,0.000340568,0.00031385108,0.000058689155,0.000065303175,0.0014905907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957441,0.0003871639,0.00066794624,0.0015237217,0.0006465194,0.0010305409],"domain_scores_gemma":[0.99380034,0.0027159164,0.0003118872,0.0020842438,0.0008262089,0.00026138648],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000978462,0.00074486143,0.0006624273,0.00065839285,0.0014180252,0.0012836084,0.0016590176,0.00049961463,0.000022997016],"category_scores_gemma":[0.0030994704,0.00079573406,0.00029856534,0.0016918944,0.00021710075,0.001314674,0.0006928804,0.0008058812,0.000094940646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010161786,0.004024118,0.07226044,0.0015798499,0.000488294,0.0007804072,0.029777357,0.07953401,0.0038384034,0.0025539019,0.20038334,0.6046783],"study_design_scores_gemma":[0.0011871207,0.00033832883,0.0007485168,0.001877419,0.00011013484,0.000009086434,0.000024291521,0.9567597,0.028459826,0.009024722,0.00057963823,0.00088122574],"about_ca_topic_score_codex":0.000075206844,"about_ca_topic_score_gemma":0.00006963343,"teacher_disagreement_score":0.8772257,"about_ca_system_score_codex":0.0003134489,"about_ca_system_score_gemma":0.0010844849,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W7097569464","doi":"","title":"M.: Formalizing a structured natural language requirements specification notation","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Notation; Formal specification; Readability; B-Method; Specification language; Programming language specification; Software requirements specification; Formal methods","score_opus":0.03928953644046304,"score_gpt":0.2763948160140021,"score_spread":0.23710527957353908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097569464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028969692,0.00033355225,0.94869614,0.0005468578,0.0003716282,0.00016816266,5.328874e-7,0.012890189,0.008023279],"genre_scores_gemma":[0.7164593,0.0000025195445,0.28295287,0.0002160097,0.00003272348,0.0000049852333,0.0000025685163,0.000003646165,0.00032537887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993333,0.000019332929,0.0001322755,0.00018824381,0.00018209283,0.00014471656],"domain_scores_gemma":[0.9994835,0.000045292018,0.00006145023,0.00033598312,0.00004485088,0.000028878874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010411729,0.00007310076,0.00005724677,0.000078322504,0.000083625506,0.00011738833,0.00032984154,0.000026436457,0.000036554527],"category_scores_gemma":[0.000100445686,0.000062904284,0.000024083562,0.00021991822,0.0000103864,0.0005030233,0.00006126574,0.000064613334,0.000042078962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028520365,0.000048064998,0.0026258738,0.000018574181,0.00001188504,0.000014762737,0.005938107,0.000010345717,0.008495975,0.022628019,0.05133307,0.9088725],"study_design_scores_gemma":[0.0005277242,0.0000966874,0.017404119,0.000058956248,0.0000071708787,0.00007067111,0.000056897807,0.9269068,0.029436367,0.023065146,0.0018456839,0.0005237843],"about_ca_topic_score_codex":0.000028469318,"about_ca_topic_score_gemma":0.000003503952,"teacher_disagreement_score":0.92689645,"about_ca_system_score_codex":0.000034605866,"about_ca_system_score_gemma":0.0000033208,"threshold_uncertainty_score":0.25651622},"labels":[],"label_agreement":null},{"id":"W7099317437","doi":"","title":"Contents","year":2002,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Relation (database); Identification (biology); Class (philosophy); Set (abstract data type)","score_opus":0.05935730714539072,"score_gpt":0.24303471369861357,"score_spread":0.18367740655322284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099317437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007382483,0.00005222024,0.9134235,0.0007981024,0.00009071067,0.000026058142,5.2496915e-8,0.02023582,0.064635314],"genre_scores_gemma":[0.71510327,0.0000019025858,0.28170946,0.000843263,0.00000970245,0.0000025410131,3.6033907e-8,0.0000015852844,0.0023282394],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996931,0.0000069413068,0.000046450536,0.00009984706,0.00006938902,0.00008427128],"domain_scores_gemma":[0.99965036,0.000047516925,0.000010474815,0.0002446125,0.00001935795,0.000027705264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000377762,0.000032212138,0.000033586526,0.000024989367,0.000029634553,0.00004378739,0.00030976027,0.000012962956,0.000058731086],"category_scores_gemma":[0.00006607119,0.000025770396,0.00001431466,0.0000926933,0.0000078807225,0.00010397136,0.00006532178,0.000026016061,0.00025007635],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.1976468e-7,0.000042206266,0.006214817,0.0000015957305,0.0000026934401,0.000013208001,0.00014005427,4.9166965e-7,0.00004874446,0.044967324,0.71387434,0.23469442],"study_design_scores_gemma":[0.0004581702,0.00020601321,0.006800158,0.00004042863,0.0000028858537,0.0001457148,0.0000023537905,0.6714691,0.004712737,0.26248035,0.053129155,0.0005529397],"about_ca_topic_score_codex":0.000015279651,"about_ca_topic_score_gemma":2.1544771e-7,"teacher_disagreement_score":0.714365,"about_ca_system_score_codex":0.0000047605054,"about_ca_system_score_gemma":7.69111e-7,"threshold_uncertainty_score":0.3214309},"labels":[],"label_agreement":null},{"id":"W7099896649","doi":"","title":"Human Resources and","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human capital; Workforce; Population ageing; Human resources; Population; Ageing society; Labour supply; Capital (architecture)","score_opus":0.012969221405160066,"score_gpt":0.24422599092828162,"score_spread":0.23125676952312155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099896649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2740065,0.00017510822,0.60099566,0.0010355753,0.00004227108,0.000060297538,1.4799463e-7,0.033835217,0.08984924],"genre_scores_gemma":[0.78891516,2.0548052e-7,0.20994706,0.00013399194,0.000023054665,0.0000015358448,9.510062e-8,0.0000016689094,0.0009772471],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997076,0.000007802538,0.00004903668,0.00011215505,0.000053640888,0.0000697751],"domain_scores_gemma":[0.99976814,0.0000327524,0.000012293873,0.0001615791,0.000010531599,0.000014712379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079778816,0.000033730583,0.000033678134,0.000031885662,0.00007259403,0.000085751155,0.0001575385,0.000014276945,0.0000024210583],"category_scores_gemma":[0.000010980359,0.000027291973,0.000007081342,0.00006482088,0.00001939321,0.000066130226,0.00008689998,0.000023270175,0.00000367614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.120054e-7,0.00004400568,0.07484089,0.000008637497,0.000002343741,0.000017392296,0.00020524273,0.0000033311753,0.00082696,0.43881184,0.4450482,0.040190853],"study_design_scores_gemma":[0.00010328052,0.00006560551,0.120732605,0.000014828196,0.0000013147129,0.000037154532,0.0000013193958,0.0045208163,0.0015403251,0.8588754,0.013927796,0.00017958588],"about_ca_topic_score_codex":0.00040199392,"about_ca_topic_score_gemma":0.0000073092287,"teacher_disagreement_score":0.5149087,"about_ca_system_score_codex":0.0000026650453,"about_ca_system_score_gemma":0.000001915631,"threshold_uncertainty_score":0.111293435},"labels":[],"label_agreement":null},{"id":"W7101429739","doi":"10.2139/ssrn.5664811","title":"Were you on Facebook 10 years ago? You may be able to claim part of this $50 million payout","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Payment; Compensation (psychology); Financial compensation; Quarter (Canadian coin)","score_opus":0.023074247127207587,"score_gpt":0.2844251055892946,"score_spread":0.26135085846208705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101429739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029673865,0.011791604,0.8724357,0.019465534,0.007133298,0.0040561543,0.0002160372,0.01420745,0.041020345],"genre_scores_gemma":[0.4994496,0.018893085,0.19402282,0.0066005797,0.0028509432,0.00067105785,0.00013937407,0.00037364123,0.2769989],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99561024,0.00022348537,0.00068346376,0.00079110113,0.00073247135,0.001959263],"domain_scores_gemma":[0.9975455,0.00023182457,0.00051941146,0.0012842029,0.00024527442,0.00017380624],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026060652,0.0004366257,0.00060108193,0.0005896591,0.00019531214,0.00022318248,0.0024322881,0.00039570217,0.000083876126],"category_scores_gemma":[0.0003504515,0.0004176596,0.0003485602,0.00033757908,0.000053818552,0.00012453194,0.0010723327,0.0038308634,0.000082492414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002417905,0.0004816415,0.0017943433,0.00024421676,0.0007398244,0.00006151101,0.0022979584,0.0027956336,0.0001360159,0.07152161,0.4448642,0.47482127],"study_design_scores_gemma":[0.0007448555,0.001975927,0.0003156883,0.0026422888,0.00013142769,0.00027352924,0.000076213226,0.0024085704,0.0018573963,0.69370484,0.2945352,0.0013340442],"about_ca_topic_score_codex":0.0003520423,"about_ca_topic_score_gemma":0.00008542688,"teacher_disagreement_score":0.6784129,"about_ca_system_score_codex":0.0011346522,"about_ca_system_score_gemma":0.003981609,"threshold_uncertainty_score":0.9998275},"labels":[],"label_agreement":null},{"id":"W7105692598","doi":"10.1109/ijcnn64981.2025.11227916","title":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Code (set theory); Heuristic; Server; Sensitivity (control systems); Test case; Source code; Computational complexity theory; Component (thermodynamics)","score_opus":0.1273860547350612,"score_gpt":0.3602348113149539,"score_spread":0.23284875657989268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105692598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004322262,0.00016711548,0.9705383,0.0014287091,0.0004162943,0.007303059,0.00023016942,0.01533858,0.00025548102],"genre_scores_gemma":[0.37483618,0.000006675844,0.6220284,0.0012778963,0.00006783652,0.0012428642,0.000015920241,0.00008677164,0.0004374377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935891,0.00013062712,0.0013579971,0.0023780905,0.0007130112,0.0018311758],"domain_scores_gemma":[0.9885392,0.006487882,0.00072472234,0.0017041789,0.002154634,0.0003893564],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0021869265,0.0010406905,0.0011659848,0.00061743456,0.0017898221,0.00097324484,0.0018375672,0.00067332364,0.0000019914335],"category_scores_gemma":[0.0039769546,0.0009832361,0.00037867,0.0017743504,0.00033658484,0.00036146797,0.00071538624,0.0007999334,0.000005272311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002372078,0.0009107943,0.00070670136,0.00091086846,0.00017199655,0.0000073172655,0.0027566527,0.9003216,0.00018926653,0.07562223,0.008277211,0.009888143],"study_design_scores_gemma":[0.0025302507,0.0005270766,0.00004638401,0.002441332,0.00029606026,0.000043217984,0.000050930223,0.9314583,0.0014064856,0.059911627,0.00015285463,0.0011354601],"about_ca_topic_score_codex":0.00010567059,"about_ca_topic_score_gemma":0.00007354106,"teacher_disagreement_score":0.37051392,"about_ca_system_score_codex":0.00077363173,"about_ca_system_score_gemma":0.0013953418,"threshold_uncertainty_score":0.9995097},"labels":[],"label_agreement":null},{"id":"W7106150544","doi":"10.48550/arxiv.2511.14432","title":"Mutation Testing for Industrial Robotic Systems","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Chicoutimi","funders":"","keywords":"Mutation; Software; Reliability (semiconductor); Process (computing); Robot; Industrial robot; Quality (philosophy); Mutation testing","score_opus":0.24057651389724458,"score_gpt":0.23107414152037709,"score_spread":0.00950237237686749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106150544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009063968,0.0001069169,0.9761292,0.00006714535,0.004270304,0.0018649406,0.00004246009,0.007195032,0.0012600658],"genre_scores_gemma":[0.955827,0.000014719944,0.040105604,0.000058996422,0.00044806223,0.00001618783,0.000033369255,0.0000309481,0.0034650965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957338,0.00039791138,0.00067836954,0.0022306687,0.00017267924,0.00078658597],"domain_scores_gemma":[0.99199075,0.0039998456,0.000941498,0.0016945417,0.0011224633,0.00025088832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012376864,0.00067591906,0.00081939675,0.0007367097,0.00072008715,0.0006170331,0.002523574,0.00091311766,0.0000037380012],"category_scores_gemma":[0.0033231857,0.0008718206,0.00034761988,0.0021660018,0.00017984102,0.00048764376,0.001805762,0.0009917486,0.000023234925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006480569,0.00014370281,0.0070479875,0.00057260325,0.00015646534,0.0001957948,0.00022206466,0.9289629,0.0000054433826,0.04885556,0.0035771618,0.01019555],"study_design_scores_gemma":[0.0009168389,0.00032008698,0.000181391,0.0021209028,0.0003019104,0.000023652496,0.000032552285,0.92783535,0.000033134198,0.0672738,0.00020426253,0.00075614447],"about_ca_topic_score_codex":0.0012969614,"about_ca_topic_score_gemma":0.000008614282,"teacher_disagreement_score":0.94676304,"about_ca_system_score_codex":0.00067726837,"about_ca_system_score_gemma":0.0013657191,"threshold_uncertainty_score":0.99937326},"labels":[],"label_agreement":null},{"id":"W7106650730","doi":"10.32913/mic-ict-research.v2025.n1.1277","title":"A Rich High-Order Mutation Testing Dataset for Software Fortification","year":2024,"lang":"","type":"article","venue":"Research and Development on Information and Communication Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Mutation; Mutation testing; Random forest; Software; Software testing; Test (biology)","score_opus":0.11383902518043638,"score_gpt":0.3782881379797234,"score_spread":0.264449112799287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106650730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008402587,0.0037263779,0.969584,0.010911267,0.00016553032,0.0017755111,0.00022326746,0.005034021,0.0001774608],"genre_scores_gemma":[0.33178094,0.001142751,0.6634086,0.0002835951,0.000018771269,0.0010262456,0.0022425868,0.000019389956,0.000077119366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997606,0.00012989045,0.0008163533,0.00045338733,0.00049470074,0.0004997155],"domain_scores_gemma":[0.99529195,0.002087018,0.00020116121,0.0009967806,0.0012985057,0.00012461003],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028087518,0.0002456235,0.00022032786,0.0019969775,0.001549987,0.0014350412,0.0008233308,0.0003355569,0.000006627849],"category_scores_gemma":[0.0033193126,0.00024308117,0.000013307528,0.0022381742,0.00041468407,0.0016117434,0.00084383413,0.0006974664,0.000083742605],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020011861,0.000055329365,0.00019192831,0.00039446086,0.0000276574,9.5146663e-7,0.0013251737,0.0000069302164,0.000009358968,0.04887215,0.013135742,0.9359603],"study_design_scores_gemma":[0.0012693376,0.0018469546,0.0025047364,0.0023943668,0.000022534634,0.00017035895,0.000953348,0.21998006,0.003520433,0.3759226,0.39038512,0.0010301344],"about_ca_topic_score_codex":0.00004522533,"about_ca_topic_score_gemma":0.000006812164,"teacher_disagreement_score":0.93493015,"about_ca_system_score_codex":0.00017054885,"about_ca_system_score_gemma":0.000668656,"threshold_uncertainty_score":0.99974984},"labels":[],"label_agreement":null},{"id":"W7117154141","doi":"10.1145/3756681.3756991","title":"PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritization","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Prioritization; Test case; Process (computing); Mutation; Code coverage; Code (set theory); Test (biology); Software","score_opus":0.03586475559047253,"score_gpt":0.2990342536693706,"score_spread":0.26316949807889806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117154141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033819485,0.00036934612,0.9548264,0.0006521331,0.0014673517,0.000599968,0.0000040807436,0.006740556,0.001520666],"genre_scores_gemma":[0.67348254,0.000024029381,0.32541877,0.00047887745,0.00017447697,0.00001168383,0.0000053593003,0.000015147229,0.00038912043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722755,0.00014533507,0.0007046655,0.00094304926,0.00046726846,0.00051215634],"domain_scores_gemma":[0.9976769,0.00045292973,0.00023575175,0.00097027957,0.0005515423,0.000112616304],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006184702,0.00034834715,0.00031514003,0.00046305373,0.00068436784,0.0008200126,0.00072468806,0.00021681687,0.00002461363],"category_scores_gemma":[0.0013636273,0.00035670886,0.000106969455,0.0018398869,0.000109957466,0.00026593407,0.00056821783,0.00023544994,0.000021309452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021645423,0.0040525347,0.03929709,0.0005798043,0.00014923862,0.00011548304,0.0030487808,0.1661957,0.1588038,0.06331199,0.035215456,0.5292085],"study_design_scores_gemma":[0.0002511609,0.00015047686,0.00095498323,0.00044761266,0.000045634224,0.000022915021,0.00000385702,0.9688519,0.026540231,0.0020627747,0.0003101365,0.00035828774],"about_ca_topic_score_codex":0.00018738284,"about_ca_topic_score_gemma":0.000009405718,"teacher_disagreement_score":0.80265623,"about_ca_system_score_codex":0.00041266906,"about_ca_system_score_gemma":0.00076879875,"threshold_uncertainty_score":0.9998885},"labels":[],"label_agreement":null},{"id":"W7117322255","doi":"10.1016/j.jss.2025.112759","title":"On software testing reference ontologies","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ontology; Process ontology; IDEF5; Formality; Upper ontology; Domain (mathematical analysis); Ontology components; Ontology-based data integration","score_opus":0.04469546520606831,"score_gpt":0.2869665398924838,"score_spread":0.24227107468641546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117322255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02838859,0.003239708,0.9639367,0.00021430278,0.0009171311,0.00012256205,0.0000032050405,0.0026507124,0.00052710326],"genre_scores_gemma":[0.6171363,0.000035087614,0.38223916,0.00026768073,0.00006544482,0.0000062804966,3.3960214e-7,0.0000083303585,0.00024136742],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872535,0.000083183695,0.00048799143,0.00021719796,0.00027800474,0.00020827995],"domain_scores_gemma":[0.9969828,0.0017090602,0.00039013397,0.000363046,0.00047692916,0.000078004006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006770188,0.00015881362,0.00035818788,0.00027978228,0.0001850776,0.00028034832,0.0006239161,0.000107494045,6.182013e-7],"category_scores_gemma":[0.0054564686,0.00011771137,0.00005344564,0.00035446035,0.00004641725,0.0002802638,0.00016284514,0.00031061325,0.000002053878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068057336,0.0002323299,0.27006248,0.0009533699,0.00018357951,0.0005398278,0.0008578837,0.0008714501,0.00009543427,0.0719505,0.116724014,0.53746104],"study_design_scores_gemma":[0.003900972,0.0062988233,0.18607669,0.03123546,0.00020237325,0.0052576778,0.00040932864,0.01706355,0.0005334972,0.7168551,0.029662045,0.0025044633],"about_ca_topic_score_codex":0.00008198918,"about_ca_topic_score_gemma":0.0000016157109,"teacher_disagreement_score":0.6449046,"about_ca_system_score_codex":0.00005842652,"about_ca_system_score_gemma":0.00016172242,"threshold_uncertainty_score":0.65322965},"labels":[],"label_agreement":null},{"id":"W7124996121","doi":"10.1109/aiware69974.2025.00012","title":"Turning Manual Tasks Into Actions: Assessing the Effectiveness of Gemini-Generated Selenium Tests","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Executable; HTML; Software; Test (biology); Hypertext; User interface","score_opus":0.02708333145676899,"score_gpt":0.3548974381655703,"score_spread":0.3278141067088013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124996121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1395845,0.00089031813,0.8467509,0.00038708653,0.001601715,0.00056458096,0.000002008426,0.0050659613,0.005152896],"genre_scores_gemma":[0.9071586,0.000036021745,0.09195679,0.0001899647,0.00009654977,0.000075102675,0.0000035207881,0.000020175792,0.00046328997],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99590033,0.0016555993,0.0007041616,0.00084167643,0.0003833228,0.0005148793],"domain_scores_gemma":[0.987211,0.010369044,0.00034338838,0.0012931174,0.000699679,0.00008379277],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003611313,0.00043848853,0.0005530207,0.00041202962,0.0009057421,0.0008095965,0.0013549158,0.0002681825,0.000013972671],"category_scores_gemma":[0.0030324878,0.00031919166,0.00018045428,0.0025968866,0.00034459628,0.00065522094,0.00071733067,0.0005328123,0.000009031157],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014343916,0.0010771069,0.12094146,0.001850747,0.0006576745,0.000033327942,0.0034771552,0.00371215,0.14689478,0.021975843,0.0129314875,0.6863048],"study_design_scores_gemma":[0.00081772334,0.0005919681,0.12726367,0.0045189667,0.00021690961,0.00006845921,0.00015038856,0.3610571,0.4544048,0.048861314,0.0011730506,0.0008756618],"about_ca_topic_score_codex":0.0011306166,"about_ca_topic_score_gemma":0.000017574044,"teacher_disagreement_score":0.7675741,"about_ca_system_score_codex":0.0002799341,"about_ca_system_score_gemma":0.0009471201,"threshold_uncertainty_score":0.99992603},"labels":[],"label_agreement":null},{"id":"W7125608420","doi":"10.1109/cascon66301.2025.00085","title":"Optimizing Test Case Reduction in CI/CD Pipelines Using Integer Linear Programming","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Ontario Tech University","funders":"","keywords":"Test suite; Test case; Reduction (mathematics); System under test; Pipeline transport; Test (biology); Integer programming; Test Management Approach; Software deployment; Software","score_opus":0.04453385423626503,"score_gpt":0.33276822099642644,"score_spread":0.2882343667601614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125608420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025603676,0.00088936114,0.9623987,0.0008340954,0.0013932671,0.00063028175,0.000001682027,0.007711548,0.0005373727],"genre_scores_gemma":[0.45230654,0.000019709561,0.5469691,0.00012224165,0.00016654785,0.000021836333,0.0000010914947,0.000019425454,0.00037352677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650234,0.00017316206,0.001080437,0.001154951,0.0002839709,0.0008051108],"domain_scores_gemma":[0.9973937,0.0007550437,0.00026107114,0.0009921653,0.0004637252,0.00013425249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014842629,0.0004779754,0.00049217703,0.0010814948,0.0004803503,0.0006789937,0.0006891529,0.0003000139,0.0000161628],"category_scores_gemma":[0.0026633372,0.00048537165,0.0001500947,0.0032921599,0.00019838416,0.0007330077,0.0008057541,0.0007237767,0.000011398201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031089676,0.0010304066,0.009974505,0.00043035086,0.000042724743,0.00303653,0.0036800436,0.01013427,0.0012095358,0.0008742694,0.003168574,0.9663877],"study_design_scores_gemma":[0.00034968578,0.00012956226,0.000024565006,0.0020184785,0.000041792853,0.00337471,0.00024121921,0.9871436,0.003285602,0.0023367258,0.0005303309,0.00052375795],"about_ca_topic_score_codex":0.0036810888,"about_ca_topic_score_gemma":0.00009393849,"teacher_disagreement_score":0.9770093,"about_ca_system_score_codex":0.0003504685,"about_ca_system_score_gemma":0.00048811457,"threshold_uncertainty_score":0.9997598},"labels":[],"label_agreement":null},{"id":"W7125807424","doi":"10.17504/protocols.io.6qpvryedogmk/v1","title":"Generation of Mutagenic Libraries using a POPCode Method v1","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Subcloning; Amplicon; Gene; DNA; Protocol (science); Ensembl","score_opus":0.13088762140403756,"score_gpt":0.3680847536034365,"score_spread":0.23719713219939895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125807424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005113637,0.0013749754,0.98596793,0.00051473314,0.0007485799,0.0002251445,0.0000029934351,0.0036853075,0.0023666872],"genre_scores_gemma":[0.2533698,0.000015684816,0.74510306,0.00051035464,0.000069596106,0.0000054706006,0.0000014630523,0.000009792907,0.0009147504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977778,0.0003317293,0.0006675289,0.0006129994,0.00027634515,0.00033358077],"domain_scores_gemma":[0.99787426,0.0005971663,0.00025002265,0.00097481074,0.00023868472,0.00006508482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088323257,0.00025364512,0.0004031493,0.000442034,0.00026469075,0.00041979266,0.00086523267,0.0001833634,0.000049986364],"category_scores_gemma":[0.00071017875,0.00024924867,0.00015662183,0.0014707908,0.00012154711,0.0006673141,0.000731418,0.00018030647,0.0000036276176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024053234,0.00032595996,0.004992362,0.00038431177,0.00022046662,0.00001831167,0.0023943312,0.0032705197,0.03344146,0.34005415,0.03762706,0.577247],"study_design_scores_gemma":[0.00012756628,0.00006860094,0.00014911516,0.00019528589,0.00005120825,0.000012589165,0.000006138871,0.79590565,0.12882958,0.07425893,0.00020643078,0.00018890387],"about_ca_topic_score_codex":0.000652444,"about_ca_topic_score_gemma":0.000007313973,"teacher_disagreement_score":0.79263514,"about_ca_system_score_codex":0.000058531194,"about_ca_system_score_gemma":0.0007288415,"threshold_uncertainty_score":0.99999595},"labels":[],"label_agreement":null},{"id":"W7125894626","doi":"10.1109/ase63991.2025.00308","title":"MobileUPReg: Identifying User-Perceived Performance Regressions in Mobile OS Versions","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Concordia University","funders":"","keywords":"Wilcoxon signed-rank test; Regression; Mobile device; Focus (optics); Regression analysis; Regression testing; Baseline (sea); Linear regression","score_opus":0.027014622866123644,"score_gpt":0.3113889806829244,"score_spread":0.28437435781680076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125894626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75437075,0.002287167,0.2073674,0.00075118936,0.0029909937,0.0017405773,0.0000098503,0.01354936,0.01693272],"genre_scores_gemma":[0.9223691,0.0009507353,0.06557115,0.0005325551,0.000043286298,0.00031724825,0.00000374999,0.000024350773,0.0101877935],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996085,0.0002574446,0.0009128153,0.0012789266,0.0005021463,0.0009636619],"domain_scores_gemma":[0.99636847,0.000997834,0.00020005615,0.0019800474,0.00024485248,0.00020872838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008688452,0.00050238345,0.0005614462,0.0010402374,0.00086454005,0.00052736606,0.0022856223,0.00034534623,0.00022200751],"category_scores_gemma":[0.0005877481,0.00048477878,0.0002040178,0.002962004,0.00023947851,0.0011477346,0.0018555985,0.0008662946,0.0001769997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005933085,0.0011273246,0.47094363,0.0006258369,0.00007819061,0.00012861511,0.0050361343,0.0026264533,0.001256617,0.0028398575,0.14323759,0.37204042],"study_design_scores_gemma":[0.0021455067,0.0006123578,0.34840703,0.016390875,0.00008007618,0.00005386096,0.00043373837,0.6038755,0.0057349596,0.009642025,0.010822959,0.0018010801],"about_ca_topic_score_codex":0.00043415488,"about_ca_topic_score_gemma":0.000050100432,"teacher_disagreement_score":0.60124904,"about_ca_system_score_codex":0.00034537746,"about_ca_system_score_gemma":0.0005659808,"threshold_uncertainty_score":0.9997604},"labels":[],"label_agreement":null},{"id":"W7125931302","doi":"10.1109/ase63991.2025.00365","title":"PrioTestCI: Efficient Test Case Prioritization in GitHub Workflows for CI Optimization","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Workflow; Test suite; Test case; Test (biology); Prioritization; Software; Regression testing; Code (set theory); Reduction (mathematics)","score_opus":0.01531142197187153,"score_gpt":0.2894594539366552,"score_spread":0.27414803196478366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125931302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002056153,0.00046371645,0.9871166,0.0014226949,0.0008022139,0.0018644844,0.0000128602005,0.005112428,0.0011488681],"genre_scores_gemma":[0.40026766,0.000026005067,0.5985364,0.00044576687,0.000060222505,0.00014151704,0.000010132336,0.00001756135,0.0004947404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997008,0.00011079877,0.0009070409,0.0010528984,0.00027346404,0.0006477468],"domain_scores_gemma":[0.9954925,0.002692061,0.00022433474,0.00092193927,0.00055208727,0.00011706971],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010995432,0.00038608751,0.0003955422,0.0008206451,0.00041721185,0.0006753535,0.00064109726,0.0003015934,0.000018069852],"category_scores_gemma":[0.0051720017,0.00041244962,0.000117969146,0.0031129038,0.00009529335,0.00026137306,0.00038508122,0.00024723326,0.000007521375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029836889,0.0010777245,0.01335004,0.000350384,0.000017770479,0.00030619677,0.0007184244,0.66691625,0.00002036115,0.006146418,0.009890978,0.30117562],"study_design_scores_gemma":[0.00081998715,0.00020042583,0.0003106248,0.00092626456,0.000028404069,0.00017015592,0.000012467049,0.99157417,0.00039893735,0.0047864006,0.00036210724,0.00041003406],"about_ca_topic_score_codex":0.00021885274,"about_ca_topic_score_gemma":0.00005894391,"teacher_disagreement_score":0.3982115,"about_ca_system_score_codex":0.00034661943,"about_ca_system_score_gemma":0.0005568466,"threshold_uncertainty_score":0.99983275},"labels":[],"label_agreement":null},{"id":"W7125939950","doi":"10.1109/ase63991.2025.00251","title":"Who’s to Blame? Rethinking the Brittleness of Automated Web GUI Testing from a Pragmatic Perspective","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Automation; Perspective (graphical); Web application; Test (biology); Test case; Software testing; Brittleness","score_opus":0.0263521555170315,"score_gpt":0.30838494502954805,"score_spread":0.28203278951251654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125939950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07113356,0.001408073,0.8400175,0.015296101,0.0013522668,0.0022795373,0.00003444399,0.043141212,0.025337294],"genre_scores_gemma":[0.64360017,0.0000064742217,0.35433543,0.0014954341,0.00006361335,0.000072834926,8.9993836e-7,0.000022188062,0.00040296203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995854,0.0006057169,0.0010342861,0.0011382592,0.0007177261,0.000649976],"domain_scores_gemma":[0.98670214,0.008894408,0.0005004499,0.00208814,0.0016834349,0.00013145171],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021484678,0.00047517315,0.0007307596,0.0004351419,0.000635014,0.00070540945,0.0029026982,0.0002314349,0.000028595901],"category_scores_gemma":[0.018918578,0.0003739773,0.00016889238,0.0041899285,0.00030532514,0.00031464014,0.0019914443,0.0005598736,0.000024413092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014024296,0.001350515,0.04821903,0.0012137914,0.0014097813,0.00018852466,0.15774438,0.0042701783,0.009955906,0.2081681,0.2389755,0.32836407],"study_design_scores_gemma":[0.0002518174,0.00015992102,0.0066892393,0.004730875,0.000089079236,0.0000129629825,0.0003823457,0.76344156,0.0022034568,0.22157843,0.0000918762,0.0003683926],"about_ca_topic_score_codex":0.010985149,"about_ca_topic_score_gemma":0.00017938018,"teacher_disagreement_score":0.7591714,"about_ca_system_score_codex":0.0003362356,"about_ca_system_score_gemma":0.0012482256,"threshold_uncertainty_score":0.9998712},"labels":[],"label_agreement":null},{"id":"W7125982494","doi":"10.1109/ase63991.2025.00211","title":"DRIFT: Debug-based Trace Inference for Firmware Testing","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Firmware; Fuzz testing; Debugging; Concept drift; Binary number; Source code; TRACE (psycholinguistics); Interrupt","score_opus":0.05398414036472179,"score_gpt":0.3325451358902314,"score_spread":0.2785609955255096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125982494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006638092,0.0006853191,0.96698046,0.0035474047,0.00071379635,0.00094469194,0.000014157443,0.019154957,0.007295398],"genre_scores_gemma":[0.49441996,0.000002479086,0.5021948,0.0016520023,0.00005490273,0.00015212354,0.0000025863953,0.00001752739,0.0015036147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644196,0.000114559305,0.000813133,0.0012910404,0.00036988588,0.00096940005],"domain_scores_gemma":[0.98630273,0.010712,0.0002758786,0.0015229685,0.000982389,0.00020404806],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010750617,0.00054637995,0.0005400449,0.0004392619,0.00079952664,0.00085636944,0.0020433639,0.0003208069,0.0000326058],"category_scores_gemma":[0.014124972,0.00054487394,0.00023278201,0.0022203582,0.00018624906,0.00040676867,0.00047910522,0.00040740045,0.000017649669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031563024,0.00034631568,0.0473189,0.00056233513,0.00004058464,0.000015136736,0.00023066155,0.0009123965,0.000085721564,0.016882319,0.06965014,0.8639239],"study_design_scores_gemma":[0.0006966704,0.0004397332,0.0037531597,0.0016576136,0.000054039196,0.0000048199536,0.000007230572,0.91524017,0.0036669325,0.069016,0.0048225843,0.0006410724],"about_ca_topic_score_codex":0.00039664356,"about_ca_topic_score_gemma":0.00003568022,"teacher_disagreement_score":0.91432774,"about_ca_system_score_codex":0.00015682365,"about_ca_system_score_gemma":0.00177069,"threshold_uncertainty_score":0.99970025},"labels":[],"label_agreement":null},{"id":"W7126241841","doi":"10.1109/iconat66879.2025.11362663","title":"Enhanced Context-Aware Testing for Mobile Applications Using a Hybrid Grammatical Evolution Method","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Genetic programming; Grammatical evolution; Domain (mathematical analysis); Search-based software engineering; Key (lock); Software; Model-based testing; Test case; Test (biology)","score_opus":0.047344349910948914,"score_gpt":0.3659966721439838,"score_spread":0.31865232223303486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126241841","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000386605,0.0003993781,0.985378,0.00020949283,0.0003483011,0.0034073512,0.00002373641,0.009176769,0.00067032105],"genre_scores_gemma":[0.44060272,9.790735e-7,0.5573643,0.00025491888,0.00008008653,0.0014211092,0.0000044304834,0.00001767425,0.0002538153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965497,0.00022557349,0.000958437,0.0011950195,0.00030155666,0.0007697112],"domain_scores_gemma":[0.9915322,0.0056038955,0.0003362705,0.0012021831,0.0011554281,0.00016999558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014903378,0.00042760896,0.0005755116,0.00037860768,0.0010262266,0.00047092003,0.0010780987,0.00018655014,0.00001076654],"category_scores_gemma":[0.002407818,0.0004474633,0.0002297469,0.0017035905,0.00017389926,0.00037034423,0.00054308376,0.00031481995,0.000012227977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017092083,0.00028116122,0.0002942724,0.00047074203,0.00006443824,0.0000016444696,0.00015933662,0.0007650301,0.0031277172,0.07054363,0.0026624047,0.9216125],"study_design_scores_gemma":[0.00033367836,0.0001911461,0.00003845768,0.00046057344,0.000096370786,0.00002627987,0.00003611021,0.7717688,0.012792919,0.21344522,0.00045091548,0.0003595306],"about_ca_topic_score_codex":0.00039496823,"about_ca_topic_score_gemma":0.000007282979,"teacher_disagreement_score":0.921253,"about_ca_system_score_codex":0.00044772925,"about_ca_system_score_gemma":0.0008714902,"threshold_uncertainty_score":0.9997977},"labels":[],"label_agreement":null},{"id":"W7133004228","doi":"","title":"PathDiff: Systematic Differential Testing Using Symbolic Analysis","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Fuzz testing; Path (computing); Symbolic execution; Differential (mechanical device); Process (computing); Software bug; Software","score_opus":0.06123085727894456,"score_gpt":0.37725920008032965,"score_spread":0.3160283428013851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133004228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47777358,0.0020166393,0.5009101,0.000038069735,0.002599729,0.0018564378,0.000020170737,0.01382033,0.0009649399],"genre_scores_gemma":[0.9231466,0.000015792,0.073822275,0.00006217824,0.00022143313,0.00026748632,0.00021591366,0.00013081929,0.002117503],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99238753,0.001146584,0.0015909655,0.001923421,0.0018266765,0.0011248405],"domain_scores_gemma":[0.9917157,0.0024737543,0.002347902,0.0025404182,0.00059642666,0.00032578342],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012856032,0.0011345227,0.0024814159,0.0020789832,0.0017141588,0.0011995139,0.002670642,0.00042346382,0.00042225004],"category_scores_gemma":[0.003281245,0.0011911291,0.0009575696,0.007954816,0.00007982853,0.00027018102,0.00090229616,0.0012115071,0.00003021262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028175177,0.0045921886,0.05076062,0.30843002,0.028444886,0.00432831,0.5066245,0.04916466,0.016026925,0.006018596,0.00281076,0.022516774],"study_design_scores_gemma":[0.00022130256,0.00020888295,0.002467963,0.007797608,0.0076600276,0.0001491393,0.0013602432,0.9772751,0.00020749087,0.0011375948,0.0000043723217,0.0015103271],"about_ca_topic_score_codex":0.004476783,"about_ca_topic_score_gemma":0.000051700175,"teacher_disagreement_score":0.92811036,"about_ca_system_score_codex":0.0005852068,"about_ca_system_score_gemma":0.0005796166,"threshold_uncertainty_score":0.99983734},"labels":[],"label_agreement":null},{"id":"W7148299376","doi":"10.1504/ijeg.2025.152653","title":"A DQCNN-feedback mechanism-based mobile app testing using MFWKLST-based pattern analysis","year":2025,"lang":"en","type":"article","venue":"International Journal of Electronic Governance","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trusted Positioning (Canada)","funders":"","keywords":"Focus (optics); Graphical user interface; Interface (matter); Mobile device; Quality assurance; User interface; Mobile robot; Mechanism (biology)","score_opus":0.012256202442092553,"score_gpt":0.282056034378821,"score_spread":0.2697998319367284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148299376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06232744,0.00046939775,0.93528223,0.0007510285,0.0004460278,0.00008716572,0.0000058613723,0.00051311316,0.00011771557],"genre_scores_gemma":[0.90372854,0.000008727922,0.09499928,0.0011005455,0.00009700174,0.000008984997,0.0000016446745,0.000011588285,0.000043681674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976698,0.000085946514,0.0006397723,0.00033516914,0.0008639248,0.00040538667],"domain_scores_gemma":[0.9971123,0.00063577894,0.001002448,0.00039308073,0.0007899772,0.00006643284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073708186,0.00021297928,0.00034912972,0.00047139067,0.00009094391,0.00023525476,0.0020428933,0.00007617717,0.000011894688],"category_scores_gemma":[0.0006752438,0.0002050385,0.00031154018,0.001386583,0.00003761825,0.00033058535,0.00013911696,0.00040916985,0.0000028351592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031662735,0.0015589746,0.16371028,0.00010341658,0.004623369,0.00075274636,0.0002388819,0.34305543,0.015027456,0.0363605,0.0056523182,0.4286],"study_design_scores_gemma":[0.0009056624,0.00027740138,0.0045325803,0.0004321894,0.00017983594,0.00006497602,0.0000024773378,0.9538664,0.016487738,0.022270415,0.0007095971,0.00027070876],"about_ca_topic_score_codex":0.0002981268,"about_ca_topic_score_gemma":0.000032528053,"teacher_disagreement_score":0.8414011,"about_ca_system_score_codex":0.0008521386,"about_ca_system_score_gemma":0.0012898529,"threshold_uncertainty_score":0.8361227},"labels":[],"label_agreement":null},{"id":"W7151951935","doi":"10.1109/aibiec68052.2025.11473598","title":"GAE-HVD: Graph Autoencoder-based Hybrid Vulnerability Detection via Static-Dynamic Program Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Graph; Program analysis; Computer program; Field (mathematics); Vulnerability (computing)","score_opus":0.01241540303499054,"score_gpt":0.3103491914558713,"score_spread":0.29793378842088075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7151951935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020169217,0.00017718256,0.94485915,0.001016711,0.00073418557,0.0013321893,0.0000147662795,0.031200228,0.0004963883],"genre_scores_gemma":[0.6009337,0.000007775121,0.39792863,0.0005794314,0.00001311936,0.00025993606,0.000015489471,0.000017558112,0.0002443714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936293,0.0008776306,0.0013895817,0.0021416424,0.0008516963,0.001110164],"domain_scores_gemma":[0.9942342,0.0012556446,0.0004616846,0.0029400594,0.0008063473,0.0003020567],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024004686,0.00074442674,0.0009876249,0.002255567,0.0009252182,0.00081948703,0.0016596173,0.00024589832,0.0000993433],"category_scores_gemma":[0.0011145956,0.00073370896,0.0009104691,0.010285641,0.0004641313,0.0004983884,0.0004554073,0.0007733505,0.000025109106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047242374,0.0015244248,0.014658482,0.0002610816,0.00078817585,0.000038634094,0.00011217858,0.00997053,0.000089396024,0.0002283432,0.00092171767,0.9713598],"study_design_scores_gemma":[0.00038835075,0.00065246184,0.012933745,0.00010757394,0.0009621708,0.000007866305,0.0000046222253,0.9209073,0.0036516143,0.059574716,0.0001536812,0.00065589056],"about_ca_topic_score_codex":0.0024318257,"about_ca_topic_score_gemma":0.0007705886,"teacher_disagreement_score":0.9707039,"about_ca_system_score_codex":0.0004904697,"about_ca_system_score_gemma":0.0006523189,"threshold_uncertainty_score":0.9995114},"labels":[],"label_agreement":null},{"id":"W7153576139","doi":"10.1145/3779657.3779658","title":"From Scenario to Code: Structured Prompting for LLM-Based Unit Test Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Innovation and Economic Development Trois Rivières","funders":"","keywords":"Unit testing; Test case; Code (set theory); Readability; Test (biology); Java; Software; Relevance (law); Code coverage","score_opus":0.05725744101598945,"score_gpt":0.327343913897419,"score_spread":0.27008647288142956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7153576139","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016217282,0.00009681044,0.9676535,0.005054992,0.0013982787,0.0015134627,0.000090592264,0.0076812343,0.00029384412],"genre_scores_gemma":[0.4273968,5.4629203e-7,0.5685072,0.002794992,0.00024620836,0.0001212144,0.00004453329,0.000019089119,0.0008694224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970551,0.00010022863,0.000679168,0.00122701,0.0003404533,0.00059805333],"domain_scores_gemma":[0.99554825,0.0021789528,0.00019954517,0.0012178587,0.00066379504,0.00019158683],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006528637,0.00041825802,0.00040717062,0.00037642487,0.00067429006,0.0010888594,0.0012169292,0.00024707685,0.00004339067],"category_scores_gemma":[0.0042664395,0.00041485386,0.00012791522,0.0012001767,0.00006219623,0.00024037095,0.00037033434,0.00024261243,0.000016403494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007959019,0.0006280155,0.023335682,0.00024631133,0.00009890533,0.0000114202285,0.0016584218,0.006718171,0.022904867,0.0065744324,0.33499226,0.6027519],"study_design_scores_gemma":[0.0006544622,0.0004490528,0.0017484986,0.00048760636,0.000046754794,0.0000010455518,0.000006845553,0.9102795,0.0574977,0.025062483,0.0032947264,0.0004712943],"about_ca_topic_score_codex":0.0010345572,"about_ca_topic_score_gemma":0.00034614615,"teacher_disagreement_score":0.90356135,"about_ca_system_score_codex":0.00016281361,"about_ca_system_score_gemma":0.0009060899,"threshold_uncertainty_score":0.9999481},"labels":[],"label_agreement":null},{"id":"W7155389882","doi":"10.13182/t133-49198","title":"A Scenario-driven Automated Testing Framework for Plant Protection System","year":2025,"lang":"","type":"article","venue":"Transactions of the American Nuclear Society","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Automation; Materials testing; System testing; Control system; Systems analysis; Reliability (semiconductor)","score_opus":0.027274014576663563,"score_gpt":0.2735241818869985,"score_spread":0.24625016731033494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7155389882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008227338,0.00004440628,0.97402185,0.0019288652,0.00092119456,0.0012870618,0.00006204263,0.013436867,0.0000703663],"genre_scores_gemma":[0.5562293,0.000008462866,0.44331762,0.00027014708,0.00003602596,0.000073184536,3.7433816e-7,0.000029347237,0.000035548896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777615,0.0002055116,0.0006042636,0.0006077229,0.00032532765,0.00048099726],"domain_scores_gemma":[0.9965995,0.0009545522,0.00080873497,0.0011970286,0.00036460115,0.00007561124],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004995328,0.00032337528,0.000563591,0.00010483179,0.0014843611,0.0001817668,0.0013531415,0.00018175022,0.0000020622444],"category_scores_gemma":[0.00036570986,0.00028338586,0.0007535602,0.002870482,0.000745515,0.00016702384,0.00009985567,0.00065653335,0.0000033697245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007840167,0.0027531334,0.0031328811,0.010746503,0.0043911533,0.000006053965,0.02930505,0.054854304,0.0113071455,0.02453192,0.08305814,0.7751297],"study_design_scores_gemma":[0.0002367168,0.00041203116,0.0016519673,0.0026976536,0.00023189351,0.00002782147,0.00049065775,0.9914328,0.00047208444,0.0015973907,0.00047508607,0.00027390823],"about_ca_topic_score_codex":0.0013195587,"about_ca_topic_score_gemma":0.0000033305141,"teacher_disagreement_score":0.9365785,"about_ca_system_score_codex":0.00039916288,"about_ca_system_score_gemma":0.0003451807,"threshold_uncertainty_score":0.99996185},"labels":[],"label_agreement":null},{"id":"W80670519","doi":"10.1007/978-1-4614-4325-4_3","title":"Ordering the Blocks of Designs","year":2012,"lang":"en","type":"book-chapter","venue":"CMS books in mathematics","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","score_opus":0.0768544269866471,"score_gpt":0.27281935626787385,"score_spread":0.19596492928122675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W80670519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019403142,0.0011711593,0.5631422,0.00006588358,0.00018712383,0.00036465563,0.0000021311976,0.0021281452,0.4329193],"genre_scores_gemma":[0.008445717,0.00006816123,0.886205,0.00011515241,0.00013568767,0.000035613393,0.0000013604272,0.00008927427,0.10490399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875736,0.000014598836,0.0004787098,0.00021104353,0.00030362475,0.00023463534],"domain_scores_gemma":[0.99764776,0.00069832994,0.00036533913,0.0011750619,0.00007245141,0.00004103654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007342017,0.0002509102,0.00037678637,0.00014691117,0.00005487673,0.000047235862,0.0012616747,0.00019519372,0.000020113983],"category_scores_gemma":[0.00019201217,0.00018386904,0.00009874221,0.00004436718,0.00012402948,0.00006306539,0.0004385924,0.00036896224,0.000018073331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.285334e-7,0.00004498347,0.000034221815,0.00030203664,0.00003072334,0.000017081476,0.0029804884,0.000011629634,0.000023229499,0.9653367,0.0064840824,0.02473404],"study_design_scores_gemma":[0.000052313055,0.000030443864,0.000004025874,0.0009837697,0.00002138608,0.000052441,0.0000034717868,0.0039039247,0.00026428388,0.98859173,0.005843974,0.00024825946],"about_ca_topic_score_codex":0.0000053622493,"about_ca_topic_score_gemma":0.0000018190724,"teacher_disagreement_score":0.3280153,"about_ca_system_score_codex":0.000042703432,"about_ca_system_score_gemma":0.00006530585,"threshold_uncertainty_score":0.7497962},"labels":[],"label_agreement":null},{"id":"W87402359","doi":"10.1007/978-3-642-41533-3_19","title":"Model Checking of UML-RT Models Using Lazy Composition","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Unified Modeling Language; Composition (language); Computer science; Programming language; Model checking; Linguistics; Philosophy; Software","score_opus":0.06041695663218916,"score_gpt":0.2775955526916666,"score_spread":0.21717859605947742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W87402359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002953781,0.00019638144,0.99506825,0.00011689659,0.00042164742,0.000328988,0.000003832264,0.0016771049,0.0018915064],"genre_scores_gemma":[0.36390075,0.000007937376,0.6356226,0.00030737682,0.00009114742,0.000004282173,0.0000021204535,0.00002536234,0.000038422404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966793,0.000028395436,0.00062060903,0.00118298,0.00093972095,0.00054896873],"domain_scores_gemma":[0.997229,0.0003372233,0.00047537097,0.0013902888,0.00044035123,0.00012779488],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000731945,0.00048571682,0.00060373265,0.00086396275,0.00021076847,0.00033008904,0.002672267,0.00033855165,0.000006105044],"category_scores_gemma":[0.000054866596,0.0004688455,0.00014257821,0.00048725546,0.00052690477,0.0009523671,0.0013323766,0.0006166947,0.0000055671676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021966393,0.000027417585,0.000028136092,0.00005751589,0.0000073979486,0.0000123901045,0.00047256882,0.75701153,0.00093557464,0.022662425,0.000034801637,0.21874808],"study_design_scores_gemma":[0.000060746497,0.000036805348,0.0000040678833,0.0005383918,0.000004953419,0.00003459582,8.932856e-9,0.573627,0.0013896105,0.42402124,0.000002770765,0.00027982355],"about_ca_topic_score_codex":0.000111168425,"about_ca_topic_score_gemma":0.0000042240576,"teacher_disagreement_score":0.4013588,"about_ca_system_score_codex":0.0002776106,"about_ca_system_score_gemma":0.00045741504,"threshold_uncertainty_score":0.9997763},"labels":[],"label_agreement":null},{"id":"W965529893","doi":"","title":"Application of model-based approach for testing dynamic systems","year":2011,"lang":"pl","type":"article","venue":"Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software; Fiscal year; Computer science; Aeronautics; Computer security; Engineering; Reliability engineering; Operations research; Business; Operating system","score_opus":0.07333272393979344,"score_gpt":0.29645735117785654,"score_spread":0.2231246272380631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W965529893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023566457,0.0026896468,0.9711466,0.00011197584,0.00066268287,0.004421284,0.00075951056,0.014749336,0.0031023484],"genre_scores_gemma":[0.5403923,0.000032924298,0.4578908,0.00016486587,0.00008833545,0.000980774,0.0001284354,0.00021274967,0.00010883819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9888011,0.000579394,0.0033846705,0.0031233004,0.0016956464,0.0024158633],"domain_scores_gemma":[0.98724264,0.0028399506,0.0030589206,0.004454781,0.0017192791,0.00068445277],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.003723329,0.0016833397,0.002208027,0.0008954995,0.0009608684,0.0004058404,0.0047692778,0.0014687425,0.000011326628],"category_scores_gemma":[0.0020192,0.0017764673,0.00076075835,0.0025572705,0.0008612156,0.0009705236,0.0009189929,0.0013700782,0.000044148328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024311217,0.014363084,0.022048704,0.032104705,0.003724877,0.00019640947,0.023070531,0.27410203,0.04149196,0.21501355,0.043681003,0.32777202],"study_design_scores_gemma":[0.0016576751,0.0011247274,0.0007281352,0.00087649486,0.0005091214,0.00007405216,0.00011169598,0.97658986,0.0019114709,0.014199684,0.00041416165,0.0018028967],"about_ca_topic_score_codex":0.0006761791,"about_ca_topic_score_gemma":0.0000086306,"teacher_disagreement_score":0.7024878,"about_ca_system_score_codex":0.0009790997,"about_ca_system_score_gemma":0.0021805437,"threshold_uncertainty_score":0.99982756},"labels":[],"label_agreement":null},{"id":"W989621208","doi":"10.1016/j.scico.2015.07.005","title":"Signature required: Making Simulink data flow and interfaces explicit","year":2015,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Signature (topology); Reuse; Documentation; Interface (matter); Generalization; Software engineering; Software; Automotive industry; Comprehension; Program comprehension; Programming language; Software system; Operating system","score_opus":0.08808852585487233,"score_gpt":0.3382831394588602,"score_spread":0.25019461360398787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W989621208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01476371,0.0004232416,0.98094165,0.0003448288,0.0004993378,0.00018840544,0.0000013663689,0.00274932,0.00008815049],"genre_scores_gemma":[0.47778016,0.0000012903834,0.5220833,0.000063878055,0.000060467788,0.000002241073,0.0000010023238,0.0000048715315,0.0000027931753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977244,0.00004684046,0.0002994811,0.00082948,0.0006596282,0.0004401323],"domain_scores_gemma":[0.99775064,0.00020246813,0.00018480378,0.0013796313,0.00030622171,0.00017622276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022601874,0.00017555855,0.00022497062,0.0002591664,0.00018134213,0.00065967214,0.0037385423,0.000061114,3.6396133e-7],"category_scores_gemma":[0.00047163776,0.00015304142,0.0000212156,0.0010753301,0.00041849702,0.0019232143,0.0037995263,0.00018089658,0.00000238817],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030592707,0.00003540419,0.00059589994,0.000024982395,0.0000047168974,0.000009534359,0.0019767135,0.00028297486,0.00017788664,0.001591745,0.0013667335,0.99393034],"study_design_scores_gemma":[0.00015885783,0.00025179292,0.00013162369,0.00024620662,0.0000046046152,0.00005275644,0.00003472819,0.9843355,0.001107819,0.012267433,0.0011736223,0.00023505579],"about_ca_topic_score_codex":0.000018973109,"about_ca_topic_score_gemma":0.000001331196,"teacher_disagreement_score":0.9936953,"about_ca_system_score_codex":0.00003656023,"about_ca_system_score_gemma":0.00022590249,"threshold_uncertainty_score":0.6947204},"labels":[],"label_agreement":null}]}