{"meta":{"query_hash":"8b73c4020eea","filters":{"venue":"IEEE Transactions on Software Engineering"},"cohort_total":213,"direct_labels_cover":1,"predictions_cover":213,"exported":213,"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/8b73c4020eea","api":"https://metacan.xera.ac/api/v1/cohort?venue=IEEE+Transactions+on+Software+Engineering"},"results":[{"id":"W1899857608","doi":"10.1109/tse.2015.2431680","title":"Facilitating Coordination between Software Developers: A Study and Techniques for Timely and Efficient Recommendations","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"National Science Foundation","keywords":"Computer science; Software engineering; Software; Schedule; Software development; Software project management; Process management; Software construction; Engineering","score_opus":0.041973657220534324,"score_gpt":0.2945908783976059,"score_spread":0.2526172211770716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1899857608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13298993,0.00005234864,0.86458075,0.00010173378,0.00021115683,0.00075251266,0.000035226414,0.00127545,9.173849e-7],"genre_scores_gemma":[0.58888286,0.0000022206457,0.4107229,0.000008625611,0.000021837412,0.00029697653,0.0000032169823,0.000026878994,0.000034448567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853486,0.000040418345,0.0002880514,0.000490819,0.0003071554,0.00033867132],"domain_scores_gemma":[0.9969636,0.002235665,0.00003906807,0.0003052698,0.00023068991,0.00022565898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072709477,0.00023952039,0.00023671647,0.00046062045,0.00021642246,0.00018418822,0.00026815123,0.000087884255,0.0000015284029],"category_scores_gemma":[0.0009370289,0.0002600547,0.000040846986,0.0005290831,0.000025349478,0.00035575734,0.000015794474,0.0002773809,0.000004003536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003508791,0.00044483057,0.0068475613,0.0003468574,0.00030588565,0.000012428054,0.016149245,0.13275269,0.00034656437,0.00011307194,0.00043210792,0.8422137],"study_design_scores_gemma":[0.011055661,0.0071772696,0.029944045,0.0015340309,0.00037999623,0.00020112592,0.0056717456,0.8818067,0.04558335,0.0003964282,0.010371874,0.0058778226],"about_ca_topic_score_codex":0.000018804172,"about_ca_topic_score_gemma":0.0000028030659,"teacher_disagreement_score":0.83633584,"about_ca_system_score_codex":0.00017914503,"about_ca_system_score_gemma":0.00007255556,"threshold_uncertainty_score":0.99998516},"labels":[],"label_agreement":null},{"id":"W1963742187","doi":"10.1109/tse.2011.7","title":"Reducing Unauthorized Modification of Digital Objects","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Security and Verification in Computing","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":"Rootkit; Computer science; Operating system; Computer security; Key (lock); Kernel (algebra); Overhead (engineering); File system; Malware; Embedded system","score_opus":0.039293477207764625,"score_gpt":0.23538109404666266,"score_spread":0.19608761683889803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963742187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023933487,0.000019414858,0.9744949,0.000007849789,0.0007882678,0.0000918419,0.000004651572,0.00053422933,0.00012539844],"genre_scores_gemma":[0.84241635,0.0000040911636,0.15750691,0.0000055124333,0.00001897681,0.000013114324,7.451066e-7,0.000011623593,0.000022677006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991232,0.000012221418,0.0002650904,0.00026092623,0.00017041618,0.00016810793],"domain_scores_gemma":[0.99923486,0.0001211176,0.000075008305,0.0004291426,0.00007540265,0.00006445297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011722737,0.00012057683,0.00012856316,0.00020317362,0.00008406541,0.000048452424,0.0003745895,0.00006451578,0.000011890094],"category_scores_gemma":[0.000032199263,0.00013707875,0.00008249453,0.00045969748,0.00001681891,0.0004984007,0.0000026465761,0.00016715551,0.000017739734],"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":[0.00006830948,0.0009887305,0.00016512154,0.0003475442,0.00023280038,0.000014295042,0.031000135,0.66952133,0.01646078,0.028434807,0.000052325646,0.25271383],"study_design_scores_gemma":[0.00049400027,0.0001508076,0.0008195267,0.00017503917,0.000021099853,0.000028550872,0.0001023283,0.63114816,0.36602926,0.0004373311,0.00011103357,0.00048283092],"about_ca_topic_score_codex":0.000011147992,"about_ca_topic_score_gemma":1.801211e-7,"teacher_disagreement_score":0.8184829,"about_ca_system_score_codex":0.000041816387,"about_ca_system_score_gemma":0.000032770306,"threshold_uncertainty_score":0.5589909},"labels":[],"label_agreement":null},{"id":"W1984953175","doi":"10.1109/tse.2014.2361131","title":"Replicating and Re-Evaluating the Theory of Relative Defect-Proneness","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Polytechnique Montréal; Queen's University","funders":"","keywords":"Computer science; Context (archaeology); Software quality; Replication (statistics); Software; Source code; Software bug; Code review; Quality (philosophy); Software system; Data science; Software development; Software engineering; Statistics; Programming language","score_opus":0.02886620484135756,"score_gpt":0.2784184521015144,"score_spread":0.24955224726015685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984953175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09606728,0.00012006698,0.90277517,0.00005008825,0.00026346484,0.00019669704,0.0000021593883,0.0005072489,0.000017851864],"genre_scores_gemma":[0.88795877,0.000007733146,0.11181385,0.000021416025,0.000027972346,0.00008222136,2.5250682e-7,0.000030821808,0.000056953508],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985266,0.00013183747,0.0002703928,0.00039874844,0.00037450818,0.00029791746],"domain_scores_gemma":[0.9927702,0.0061410256,0.00006914548,0.00083902373,0.00009975751,0.00008082521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016071645,0.0001861851,0.000197576,0.00017991546,0.00019554015,0.00005954567,0.0005312462,0.00007712663,0.000006574005],"category_scores_gemma":[0.0013199045,0.00015477688,0.000101653255,0.00054837886,0.000058373702,0.00029338466,0.00001367585,0.0004602175,0.0000071652053],"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":[0.000028014967,0.00006118798,0.00081552274,0.00023665748,0.00017532635,0.0000026009043,0.0029453994,0.7514711,0.005327777,0.011408011,0.000012629122,0.22751576],"study_design_scores_gemma":[0.0008811369,0.0007403478,0.012731551,0.0005295876,0.00007842907,0.000060232625,0.00010300407,0.9183924,0.0636959,0.0018232615,0.00020116218,0.0007629909],"about_ca_topic_score_codex":0.000008488695,"about_ca_topic_score_gemma":7.450337e-7,"teacher_disagreement_score":0.7918915,"about_ca_system_score_codex":0.00005393714,"about_ca_system_score_gemma":0.000031938787,"threshold_uncertainty_score":0.6311618},"labels":[],"label_agreement":null},{"id":"W1996993752","doi":"10.1109/tse.2013.28","title":"Early Detection of Collaboration Conflicts and Risks","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Waterloo","funders":"","keywords":"Computer science; Quality (philosophy); Control (management); Source code; Open source; Code (set theory); Software engineering; Risk analysis (engineering); Computer security; Data science; Software; Programming language; Business; Set (abstract data type); Artificial intelligence","score_opus":0.01665302119978797,"score_gpt":0.24331634647688724,"score_spread":0.22666332527709926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996993752","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":[0.38300392,0.0000389313,0.6160782,0.000014545863,0.0003096836,0.00016923819,0.0000027535114,0.00038065098,0.0000021011874],"genre_scores_gemma":[0.9690109,0.000018357992,0.030778743,0.000008860704,0.000019589264,0.00009987699,2.8477717e-7,0.000022537619,0.000040852854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990069,0.000018185068,0.00020551764,0.00026137146,0.00027599375,0.00023198806],"domain_scores_gemma":[0.99886,0.00046858643,0.000036955502,0.00033844842,0.00017645909,0.000119537304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011949678,0.0001506609,0.00015245355,0.00033320003,0.00007048006,0.00011523487,0.00021684913,0.00009646935,0.000011721927],"category_scores_gemma":[0.000109136185,0.00016488032,0.000040762086,0.000648226,0.00002330111,0.0006449862,0.0000037758446,0.00024300475,0.000030931027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002446819,0.00020375328,0.002252143,0.00039309653,0.00022123907,0.000012520627,0.0034112104,0.5880362,0.18145564,0.00037651707,0.00005025589,0.22356296],"study_design_scores_gemma":[0.00094356283,0.0005223007,0.11910411,0.00014789418,0.000022057618,0.000034523677,0.000033969318,0.2763221,0.6017674,0.0000557188,0.00040782636,0.00063851784],"about_ca_topic_score_codex":0.00013712273,"about_ca_topic_score_gemma":0.0000031285435,"teacher_disagreement_score":0.586007,"about_ca_system_score_codex":0.000060336304,"about_ca_system_score_gemma":0.000023428129,"threshold_uncertainty_score":0.6723624},"labels":[],"label_agreement":null},{"id":"W2005680430","doi":"10.1109/tse.2014.2383381","title":"Range Fixes: Interactive Error Resolution for Software Configuration","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Waterloo","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Range (aeronautics); Constraint (computer-aided design); Software; Simple (philosophy); Theoretical computer science; String (physics); Programming language; Mathematics","score_opus":0.019126007936626662,"score_gpt":0.26072867292940377,"score_spread":0.2416026649927771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005680430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043659313,0.00003884315,0.9896363,0.00009451194,0.0019492271,0.0005821486,0.000031739557,0.003294522,0.0000067714036],"genre_scores_gemma":[0.720281,0.000006123234,0.27870557,0.00007659363,0.00015110057,0.00048919726,0.000008154164,0.00009328279,0.000188941],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795395,0.000051779563,0.00035370904,0.00062177907,0.00043911627,0.0005796452],"domain_scores_gemma":[0.99601877,0.0027603437,0.00006934218,0.000710711,0.00024696806,0.00019385898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043739536,0.0003369404,0.00029328608,0.000494627,0.00024180235,0.00017676914,0.00063186977,0.00017864305,0.000019150131],"category_scores_gemma":[0.0010218889,0.0003723192,0.00020738514,0.00055503275,0.000028429433,0.00081825384,0.000006386861,0.00047995726,0.000091089896],"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":[0.00008854911,0.00015974132,0.00010793959,0.00025645725,0.00012560558,0.0000061656256,0.0010366515,0.93236864,0.0011285332,0.00071887777,0.0008239441,0.063178875],"study_design_scores_gemma":[0.001923973,0.0006623947,0.0022380566,0.00035625166,0.000043092034,0.00004060067,0.00003213277,0.946726,0.037450198,0.00015389289,0.009325242,0.0010481579],"about_ca_topic_score_codex":0.000014122,"about_ca_topic_score_gemma":0.0000051333277,"teacher_disagreement_score":0.7159151,"about_ca_system_score_codex":0.00028906888,"about_ca_system_score_gemma":0.00006224626,"threshold_uncertainty_score":0.99987286},"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":"W2053107307","doi":"10.1109/tse.2013.2297712","title":"Automatic Summarization of Bug Reports","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":182,"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 the Fraser Valley; University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Task (project management); Conversation; Software bug; Software; Quality (philosophy); Natural language processing; Information retrieval; Data science; World Wide Web; Software engineering; Programming language","score_opus":0.008384848850770735,"score_gpt":0.2187966960586759,"score_spread":0.21041184720790518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053107307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05360306,0.00001895572,0.9437572,0.000018846122,0.0010277005,0.00013930496,0.0000019817874,0.0014213123,0.000011670134],"genre_scores_gemma":[0.8651474,0.0000037948053,0.13468006,0.000012570098,0.000028224948,0.000037077938,0.0000011441506,0.000031831827,0.000057869835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851584,0.000027458722,0.00036782093,0.00033525907,0.00045297007,0.00030065372],"domain_scores_gemma":[0.9981023,0.0008258144,0.00006944083,0.00077989907,0.00010442004,0.00011811703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037539552,0.00018257847,0.0002224814,0.0004141587,0.00006413193,0.000053009437,0.0003730496,0.000091753725,0.000028205743],"category_scores_gemma":[0.0004116502,0.00019916739,0.00010098138,0.00074605574,0.0000185367,0.00032796722,0.0000049240284,0.00025055793,0.000019505362],"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":[0.0000021553415,0.000098003984,0.0010662777,0.00023776437,0.00005377925,0.000019363632,0.0002399709,0.9358616,0.0021476767,0.00035303648,0.000082259525,0.05983815],"study_design_scores_gemma":[0.00027068896,0.00015502558,0.0071305544,0.00020982523,0.000016042743,0.00008205104,0.0000027899546,0.9173527,0.073622674,0.00008090753,0.0006768594,0.00039987182],"about_ca_topic_score_codex":0.000012473631,"about_ca_topic_score_gemma":9.286558e-7,"teacher_disagreement_score":0.81154436,"about_ca_system_score_codex":0.00007854993,"about_ca_system_score_gemma":0.000043020176,"threshold_uncertainty_score":0.81218106},"labels":[],"label_agreement":null},{"id":"W2065698748","doi":"10.1109/tse.2012.8","title":"Guest Editor's Introduction: International Conference on Software Engineering","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","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":"University of Waterloo","funders":"","keywords":"Computer science; Special section; Software engineering; Section (typography); Software; Library science; Programming language; Engineering; Operating system; Engineering physics","score_opus":0.017545056608538608,"score_gpt":0.24498084886590438,"score_spread":0.22743579225736577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065698748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006430954,0.00007938627,0.9478586,0.00035132517,0.046613656,0.00018833841,0.000021990718,0.004207648,0.000035993595],"genre_scores_gemma":[0.42051262,0.00011719193,0.5644477,0.00013733152,0.014215182,0.00020294805,0.000012483673,0.00011350891,0.00024102836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977868,0.00002694213,0.0003813192,0.00055048335,0.0005952129,0.00065924117],"domain_scores_gemma":[0.9982453,0.00039421662,0.000095561125,0.00083437026,0.00013303169,0.00029752072],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036592677,0.0004656898,0.00029092032,0.0005030802,0.00015849582,0.0002474869,0.00092856964,0.00022174089,0.0001528987],"category_scores_gemma":[0.0002576331,0.00050993694,0.0001714566,0.0005461313,0.000021193997,0.0015375788,0.000016799278,0.0008826916,0.00017060546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000881179,0.001054322,0.00052737485,0.00028477365,0.0006053571,0.000055318713,0.0013893103,0.89892185,0.0017986582,0.025597516,0.036317937,0.033359487],"study_design_scores_gemma":[0.001142617,0.0006094987,0.0012460966,0.0005409106,0.00010968936,0.00042222216,0.000042047413,0.20328604,0.06320588,0.000053522414,0.7263497,0.0029917813],"about_ca_topic_score_codex":0.000010021081,"about_ca_topic_score_gemma":5.656479e-7,"teacher_disagreement_score":0.6956358,"about_ca_system_score_codex":0.00025668286,"about_ca_system_score_gemma":0.000040490082,"threshold_uncertainty_score":0.99973524},"labels":[],"label_agreement":null},{"id":"W2066455950","doi":"10.1109/tse.2015.2448531","title":"Assessing the Refactorability of Software Clones","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Concordia University","funders":"","keywords":"Code refactoring; Computer science; clone (Java method); Maintainability; Programming language; Software maintenance; Code (set theory); Software evolution; Cloning (programming); Source code; Software; Software system; Software engineering; Set (abstract data type); Software construction; Biology; Genetics","score_opus":0.048312374942711414,"score_gpt":0.3005763212471097,"score_spread":0.2522639463043983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066455950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11097444,0.00011778829,0.88612646,0.00007514506,0.0013309903,0.00019298538,0.0000079537895,0.0011690058,0.000005233877],"genre_scores_gemma":[0.85546046,0.000005248028,0.14433701,0.00002081687,0.00004837179,0.000049423372,7.964526e-7,0.0000386281,0.000039213868],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978968,0.00007304712,0.000382801,0.00043226368,0.00076442375,0.0004506778],"domain_scores_gemma":[0.9962374,0.0020179185,0.00006928215,0.0011676803,0.0002789163,0.00022878795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081660645,0.00026864678,0.00028371322,0.0002656952,0.00013106888,0.00019622075,0.0010834815,0.00012507985,0.000012116061],"category_scores_gemma":[0.0010472271,0.00022083947,0.00015840634,0.0010101887,0.0000692776,0.00089657994,0.000015180199,0.00059676106,0.000032683198],"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":[0.000012164262,0.00020334906,0.0052593993,0.00017540391,0.00010867965,0.000021201606,0.0012382646,0.95661026,0.00068915595,0.00017227395,0.00022680538,0.035283044],"study_design_scores_gemma":[0.005388488,0.0016405566,0.16186035,0.0015061098,0.00022090129,0.000478443,0.000786723,0.44642168,0.3651302,0.0011273208,0.010501124,0.004938119],"about_ca_topic_score_codex":0.000040433864,"about_ca_topic_score_gemma":0.0000022548145,"teacher_disagreement_score":0.74448603,"about_ca_system_score_codex":0.00021792317,"about_ca_system_score_gemma":0.00020065412,"threshold_uncertainty_score":0.9005573},"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":"W2075639135","doi":"10.1109/tse.2014.2354043","title":"Customizing the Representation Capabilities of Process Models: Understanding the Effects of Perceived Modeling Impediments","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","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":"Western University","funders":"","keywords":"Process (computing); Computer science; Process modeling; Representation (politics); Variety (cybernetics); Process mining; Design process; Data science; Process management; Work in process; Management science; Business process modeling; Artificial intelligence; Engineering; Business process","score_opus":0.023471896139688447,"score_gpt":0.22315438599892637,"score_spread":0.19968248985923792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075639135","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":[0.26786914,0.000050308416,0.73153055,0.000044658795,0.00023162745,0.0001435847,0.0000010057698,0.000103497914,0.000025653184],"genre_scores_gemma":[0.999265,0.000020082918,0.00044290404,0.000046191755,0.00011798609,0.000054268305,0.0000019412387,0.00003627468,0.000015344744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988647,0.0000143559855,0.0003592396,0.00021981809,0.0003432792,0.00019861276],"domain_scores_gemma":[0.9990029,0.0003339898,0.00015698222,0.00028872283,0.00020787724,0.000009579023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000262216,0.00018638074,0.0002551514,0.00024645368,0.00027041417,0.000089701156,0.0002496947,0.000059246257,0.0000041629423],"category_scores_gemma":[0.00013611307,0.00012695463,0.00015519404,0.0005761114,0.00005194046,0.0007257558,0.000004177669,0.00020022181,0.0000011763688],"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":[0.00001612567,0.000030298954,0.00004038993,0.00090157066,0.00006997971,1.32102e-7,0.0007796721,0.9959903,0.0005294725,0.0005527113,0.0000015655409,0.0010877888],"study_design_scores_gemma":[0.00027405145,0.0000071926524,0.000015442418,0.00032177163,0.00022354834,5.328639e-7,0.0017988026,0.993958,0.001065812,0.0021986563,0.000002260609,0.00013392177],"about_ca_topic_score_codex":0.00027555655,"about_ca_topic_score_gemma":0.0000104760975,"teacher_disagreement_score":0.7313959,"about_ca_system_score_codex":0.000041568073,"about_ca_system_score_gemma":0.000014482373,"threshold_uncertainty_score":0.517706},"labels":[],"label_agreement":null},{"id":"W2085597081","doi":"10.1109/tse.2013.27","title":"The Impact of Classifier Configuration and Classifier Combination on Bug Localization","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":88,"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":"Classifier (UML); Computer science; Artificial intelligence; Machine learning; Random subspace method; Source code; Probabilistic classification; Quadratic classifier; Data mining; Pattern recognition (psychology); Support vector machine; Naive Bayes classifier; Programming language","score_opus":0.013915283300651619,"score_gpt":0.24821500259989007,"score_spread":0.23429971929923846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085597081","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":[0.06983369,0.000033681394,0.92896694,0.000078922174,0.00040001536,0.0003236694,0.0000036676074,0.00033849417,0.000020917825],"genre_scores_gemma":[0.9970604,0.000036362122,0.002597961,0.000013497456,0.000020577747,0.00010489079,0.0000020371142,0.000026718506,0.00013756054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987796,0.000039653747,0.00026307913,0.0002699908,0.0003662578,0.00028141728],"domain_scores_gemma":[0.99799925,0.0011930269,0.000057546353,0.00043767923,0.00020256263,0.00010990921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020554627,0.00019367172,0.00015141956,0.00025829696,0.00019362969,0.00019448031,0.0002940924,0.000108090484,0.00002341654],"category_scores_gemma":[0.00017511123,0.00015032272,0.00008908448,0.0005022263,0.00004748774,0.00049080397,0.000003806494,0.00030502057,0.000035057954],"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":[0.000017759927,0.00013998046,0.00095501496,0.000050963332,0.00010812285,0.0000019648662,0.0003616155,0.93135244,0.0028933224,0.0016807849,0.0006167897,0.06182123],"study_design_scores_gemma":[0.000556172,0.0004472799,0.050514564,0.00009630232,0.000008402156,0.000010161988,0.000016466094,0.92737395,0.020366414,0.00015829655,0.00016668712,0.00028533014],"about_ca_topic_score_codex":0.00006160021,"about_ca_topic_score_gemma":0.0000016544482,"teacher_disagreement_score":0.9272267,"about_ca_system_score_codex":0.00016419336,"about_ca_system_score_gemma":0.00005120296,"threshold_uncertainty_score":0.61299825},"labels":[],"label_agreement":null},{"id":"W2089113163","doi":"10.1109/tse.2013.29","title":"Usability through Software Design","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":64,"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":"Usability; Computer science; Usability inspection; Component-based usability testing; Usability engineering; Cognitive walkthrough; Usability goals; Software engineering; Usability lab; Heuristic evaluation; Software development; Web usability; Software; Human–computer interaction; Programming language","score_opus":0.029666864984378358,"score_gpt":0.2302247028682714,"score_spread":0.20055783788389303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089113163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008345455,0.00004337038,0.98800874,0.00014543466,0.0011242091,0.0004839661,0.0000065901027,0.0018300724,0.0000121677485],"genre_scores_gemma":[0.4443417,0.0000066635885,0.5551503,0.00014568686,0.00002451925,0.00018077294,3.79396e-7,0.000025543966,0.00012446528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981649,0.00007950705,0.0003508891,0.00059464085,0.0003246375,0.00048544406],"domain_scores_gemma":[0.9979621,0.0007319757,0.000041783125,0.0009731083,0.0001359506,0.00015505888],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024786737,0.0003090365,0.0002559831,0.00011076671,0.00018881237,0.00022472127,0.0008213368,0.00015152551,0.0002739266],"category_scores_gemma":[0.000101214166,0.00031030143,0.00017037569,0.0004960153,0.00005048621,0.0015151914,0.000006131458,0.0004420577,0.00067195797],"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":[0.000012872244,0.0003627095,0.00011114806,0.00010262448,0.00008785361,0.000007762925,0.0014378644,0.94381124,0.0013462828,0.0003167904,0.0010120622,0.051390816],"study_design_scores_gemma":[0.0015329532,0.0010859357,0.0031061657,0.0003344438,0.00007598715,0.0001143536,0.00008811808,0.59755325,0.38225627,0.00649013,0.004623675,0.0027387058],"about_ca_topic_score_codex":0.00009293313,"about_ca_topic_score_gemma":0.0000026650841,"teacher_disagreement_score":0.43599623,"about_ca_system_score_codex":0.0001607596,"about_ca_system_score_gemma":0.000058199734,"threshold_uncertainty_score":0.9999349},"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":"W2097750323","doi":"10.1109/tse.2008.26","title":"Asking and Answering Questions during a Programming Change Task","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":314,"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; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Vrije Universiteit Brussel; University of Washington","keywords":"Computer science; Programmer; Ask price; Task (project management); Key (lock); Programming language; Question answering; Code (set theory); Software engineering; World Wide Web; Data science; Information retrieval","score_opus":0.022144955307222974,"score_gpt":0.23619539299239536,"score_spread":0.2140504376851724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097750323","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":[0.23683487,0.00022723354,0.75999135,0.000035887624,0.0005073411,0.00026167673,0.0000042086544,0.002135511,0.0000019295303],"genre_scores_gemma":[0.86613,0.00011377906,0.13322803,0.000018039727,0.00010047716,0.0002908771,6.681451e-7,0.00006043636,0.00005770918],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980424,0.0000225666,0.0002655035,0.0005789819,0.00042463126,0.0006659066],"domain_scores_gemma":[0.99865884,0.00040800014,0.000035525787,0.0005555093,0.00007231702,0.00026981998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016849334,0.00031881922,0.00024563135,0.00059595465,0.00047645404,0.00013420777,0.00043649794,0.00012031965,0.0000060722236],"category_scores_gemma":[0.00012471661,0.0003694942,0.00009899366,0.00087308115,0.000047734233,0.0009153475,0.000015752641,0.00059673574,0.000021154296],"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":[0.00006483438,0.00081026467,0.020342506,0.0016864788,0.0006017269,0.0022166558,0.020042272,0.6406878,0.020523692,0.0007361962,0.000055171018,0.29223236],"study_design_scores_gemma":[0.0056684394,0.001158581,0.3850387,0.00338573,0.00014003315,0.008640049,0.00016492447,0.47892857,0.10088875,0.000049394115,0.008939574,0.0069972435],"about_ca_topic_score_codex":0.00004734652,"about_ca_topic_score_gemma":0.0000038781773,"teacher_disagreement_score":0.6292951,"about_ca_system_score_codex":0.00016787798,"about_ca_system_score_gemma":0.000039417755,"threshold_uncertainty_score":0.9998757},"labels":[],"label_agreement":null},{"id":"W2099069768","doi":"10.1109/tse.2005.106","title":"Analyzing the evolutionary history of the logical design of object-oriented software","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Alberta","funders":"","keywords":"Computer science; Software evolution; Unified Modeling Language; Object-oriented design; Software system; Class (philosophy); Programming language; Inheritance (genetic algorithm); Sequence diagram; Class diagram; Abstraction; Object-oriented programming; Sequence (biology); Software; Software engineering; Artificial intelligence; Software construction","score_opus":0.02065955642586971,"score_gpt":0.22516811738749967,"score_spread":0.20450856096162995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099069768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061683888,0.00087774807,0.9909637,0.00008248934,0.0011192417,0.00028729063,0.000009257836,0.000487829,0.000004080559],"genre_scores_gemma":[0.80994177,0.00003066129,0.18960504,0.000024426989,0.00005419869,0.00005998187,4.6078216e-7,0.00003207577,0.00025135494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981752,0.00009757753,0.00041659325,0.0003418113,0.0005885712,0.00038022458],"domain_scores_gemma":[0.9966583,0.0020032823,0.00009856803,0.0009715506,0.00018009159,0.00008816914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041971268,0.00023503779,0.00025569147,0.00027428308,0.00011692935,0.000014305272,0.0011795856,0.00011752666,0.000039954135],"category_scores_gemma":[0.00046073494,0.0001686589,0.0002413252,0.0009317167,0.00012522876,0.00028338365,0.000020352718,0.00058785215,0.000010682958],"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":[0.000011339084,0.0000936771,0.00037426126,0.00004319291,0.0000623676,0.0000021394715,0.0004358057,0.9907586,0.0009712801,0.00013201158,0.00044461212,0.006670728],"study_design_scores_gemma":[0.0012831696,0.00042940807,0.02803873,0.00060362555,0.00012548282,0.00013295711,0.000043412052,0.9085846,0.050004195,0.00006462055,0.009605684,0.0010841145],"about_ca_topic_score_codex":0.000016830225,"about_ca_topic_score_gemma":0.0000013691974,"teacher_disagreement_score":0.8037734,"about_ca_system_score_codex":0.0006216825,"about_ca_system_score_gemma":0.00025509347,"threshold_uncertainty_score":0.68777096},"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":"W2100310705","doi":"10.1109/tse.2007.70747","title":"API-Evolution Support with Diff-CatchUp","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":157,"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; Component (thermodynamics); Reuse; Software engineering; Context (archaeology); Component-based software engineering; Generality; Software evolution; Software development; Software; Programming language; Software construction","score_opus":0.014790567950770252,"score_gpt":0.23751267404951754,"score_spread":0.2227221060987473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100310705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040760515,0.000050447965,0.99063927,0.000022339897,0.0013687491,0.00018806537,0.0000055345918,0.0036225747,0.000026954645],"genre_scores_gemma":[0.42084715,0.000005430149,0.57886446,0.000029826682,0.00004389825,0.000026328133,8.7192893e-7,0.00004029434,0.00014175875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981095,0.000021627377,0.0003047554,0.00051910966,0.00039925444,0.0006457101],"domain_scores_gemma":[0.99815947,0.00078407826,0.000059983657,0.0007183695,0.00008615763,0.00019193994],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004360555,0.00034618707,0.00026986699,0.0004309167,0.00014789937,0.0000588493,0.000569866,0.00014036297,0.000012841997],"category_scores_gemma":[0.00008790194,0.00033390443,0.000105272666,0.0008541662,0.000039918003,0.00064376474,0.0000056326467,0.00050974655,0.0000491437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022252094,0.000058672143,0.000050097464,0.000038963688,0.000044660585,0.000062750085,0.000309345,0.9728192,0.0011407991,0.00087542203,0.000019856829,0.02455798],"study_design_scores_gemma":[0.009077457,0.0055756895,0.033607673,0.0013573206,0.00038670772,0.0028383585,0.00058572344,0.16524355,0.74650276,0.0036122717,0.019407704,0.011804765],"about_ca_topic_score_codex":0.00000930811,"about_ca_topic_score_gemma":0.000006060144,"teacher_disagreement_score":0.80757564,"about_ca_system_score_codex":0.0002894426,"about_ca_system_score_gemma":0.00004817174,"threshold_uncertainty_score":0.9999113},"labels":[],"label_agreement":null},{"id":"W2101198558","doi":"10.1109/32.877844","title":"Advanced exception handling mechanisms","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","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 Waterloo","funders":"","keywords":"Exception handling; Computer science; Programming language; Concurrency; Feature (linguistics); Concurrency control; Object (grammar); Artificial intelligence","score_opus":0.01509469912932844,"score_gpt":0.2357682562586422,"score_spread":0.22067355712931375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101198558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056619677,0.000067844376,0.98845625,0.000025004087,0.0014349136,0.00017859442,0.000005844426,0.004152629,0.000016942902],"genre_scores_gemma":[0.23684826,0.00006296754,0.76253605,0.000044605335,0.000026182443,0.00007887547,0.0000010065802,0.00004553281,0.0003565147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983638,0.000037307207,0.0002956815,0.0005243192,0.00030093995,0.00047794508],"domain_scores_gemma":[0.9986264,0.00050419057,0.000037431528,0.0006508984,0.000045876117,0.00013516567],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023704328,0.00031943875,0.00027062907,0.00024517218,0.00017702428,0.000080879196,0.00055376673,0.00013238248,0.0001275947],"category_scores_gemma":[0.00007787836,0.0003524982,0.00014161899,0.0005672989,0.000017459874,0.00079652277,0.0000031945715,0.00041881218,0.00015263222],"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":[0.00000689619,0.000021307203,4.5547065e-7,0.000018088867,0.000014224699,0.000006817336,0.000111684014,0.7651222,0.0021243764,0.0002659085,0.0000042618412,0.2323038],"study_design_scores_gemma":[0.003442599,0.0010509855,0.0005415715,0.00088834704,0.00009427861,0.00038113038,0.00005910229,0.51898247,0.45093548,0.013241755,0.006087593,0.0042946963],"about_ca_topic_score_codex":0.000003397773,"about_ca_topic_score_gemma":7.1323956e-7,"teacher_disagreement_score":0.4488111,"about_ca_system_score_codex":0.00013443758,"about_ca_system_score_gemma":0.000024545127,"threshold_uncertainty_score":0.9998927},"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":"W2103640219","doi":"10.1109/tse.2005.28","title":"Using origin analysis to detect merging and splitting of source code entities","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":252,"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; Context (archaeology); Source code; Code (set theory); Abstraction; Programming language; Software; Plan (archaeology); Software evolution; Software engineering; Database; Theoretical computer science; Software system; Data mining; Software construction","score_opus":0.023893764511130126,"score_gpt":0.2743728504647013,"score_spread":0.25047908595357116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103640219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29595688,0.00009147241,0.7032263,0.000017475977,0.00014727734,0.000090884045,0.000006642297,0.00046160235,0.0000014077232],"genre_scores_gemma":[0.6600162,0.000008113235,0.33984348,0.000012635838,0.00003187015,0.000013053413,2.2901321e-7,0.000025143561,0.000049319875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984098,0.000022829478,0.00032448737,0.0004177325,0.0004029805,0.00042216585],"domain_scores_gemma":[0.9985125,0.0006919536,0.000044641038,0.00048010206,0.000084903804,0.00018588729],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003312276,0.00022361374,0.00031696656,0.001217352,0.00012620183,0.000103970175,0.00040107372,0.00007153267,0.000014141792],"category_scores_gemma":[0.00013238585,0.00025817784,0.00014677591,0.0018601964,0.000022025917,0.00037993412,0.00001306029,0.00027736748,0.0000067409],"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":[0.0000024781614,0.000012420157,0.00055047177,0.00004268955,0.00019889476,0.0000026649825,0.0005367385,0.968383,0.004313224,0.000018571542,0.0000025255565,0.025936302],"study_design_scores_gemma":[0.00019921525,0.000048632046,0.001306963,0.000094905365,0.00011586592,0.000016957909,0.000025384365,0.928861,0.068418816,0.0000028052718,0.0005573595,0.00035206892],"about_ca_topic_score_codex":0.000060967803,"about_ca_topic_score_gemma":0.000015270047,"teacher_disagreement_score":0.36405927,"about_ca_system_score_codex":0.00015669035,"about_ca_system_score_gemma":0.000035871573,"threshold_uncertainty_score":0.99998707},"labels":[],"label_agreement":null},{"id":"W2104994910","doi":"10.1109/tse.2012.71","title":"Trustrace: Mining Software Repositories to Improve the Accuracy of Requirement Traceability Links","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Polytechnique Montréal","funders":"","keywords":"Traceability; Computer science; Requirements traceability; Precision and recall; Source code; Software; Data mining; Software engineering; Software development; Database; Information retrieval; Programming language; Requirement","score_opus":0.020912743124051024,"score_gpt":0.27159741001598686,"score_spread":0.25068466689193586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104994910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1624631,0.00016504752,0.8326267,0.00012901031,0.0029348147,0.00048808655,0.000017615057,0.0011726486,0.0000029921425],"genre_scores_gemma":[0.79927737,0.0000069541375,0.20015866,0.000035309615,0.00018535211,0.00020633248,7.094216e-7,0.000047623424,0.0000816725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99721766,0.00006112361,0.00059100956,0.00051061134,0.00079729466,0.000822334],"domain_scores_gemma":[0.9944418,0.0034351216,0.0001044889,0.0014667807,0.00020558057,0.00034624315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009746623,0.00036073747,0.0003396371,0.0002860356,0.00024301118,0.0001312406,0.0011207495,0.00022855013,0.000019477506],"category_scores_gemma":[0.0017503197,0.00031361266,0.00020943904,0.0010386496,0.000051033287,0.0008856194,0.000025682575,0.00086749694,0.000022636257],"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":[0.000116329,0.0010275852,0.016264254,0.0009576685,0.00050498353,0.000024116749,0.01706922,0.7101069,0.014498923,0.00034633128,0.00085141376,0.23823228],"study_design_scores_gemma":[0.001960052,0.0015297824,0.08927923,0.0009874889,0.00020834895,0.00018963452,0.0005995853,0.045072198,0.8454872,0.000047198813,0.011587366,0.003051944],"about_ca_topic_score_codex":0.00003191949,"about_ca_topic_score_gemma":0.000002223707,"teacher_disagreement_score":0.8309882,"about_ca_system_score_codex":0.0002747835,"about_ca_system_score_gemma":0.00010916388,"threshold_uncertainty_score":0.9999316},"labels":[],"label_agreement":null},{"id":"W2105246013","doi":"10.1109/tse.2002.1158289","title":"Ethical issues in empirical studies of software engineering","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":190,"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 Health and Medical Research Council; Medical Research Council; National Research Council Canada; U.S. Department of Health and Human Services; National Institutes of Health; Public Works and Government Services Canada; Canadian Psychological Association","keywords":"Empirical research; Computer science; Social software engineering; Software engineering; Popularity; Software Engineering Process Group; Software development; Software requirements; Software peer review; Personal software process; Software; Management science; Data science; Software construction; Engineering ethics; Engineering","score_opus":0.05595567562007852,"score_gpt":0.3199783701972545,"score_spread":0.264022694577176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105246013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011095642,0.0014717516,0.98383737,0.00038709436,0.0009305727,0.00018106776,0.0000076178244,0.0020844974,0.000004387809],"genre_scores_gemma":[0.5130201,0.00052875647,0.48609963,0.000106310916,0.0000532598,0.000081959326,4.805844e-7,0.00005086244,0.000058639856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797547,0.00004782125,0.0005549603,0.000498209,0.00044666976,0.0004768789],"domain_scores_gemma":[0.9972313,0.001796155,0.00007990307,0.00066496263,0.00009726648,0.00013040607],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004391433,0.00037357642,0.0005184714,0.00061775255,0.000067268105,0.000059622005,0.0006548874,0.0003414295,0.00003900442],"category_scores_gemma":[0.00079674233,0.00039254027,0.00017715039,0.0010621725,0.000036893198,0.00046499234,0.000015187459,0.0012505507,0.000023870507],"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":[0.000014161435,0.00030294096,0.0007601429,0.00052329095,0.0002069671,0.00012514193,0.0030805592,0.9711078,0.00044425298,0.0008309845,0.0010826903,0.021521114],"study_design_scores_gemma":[0.0016474741,0.00096535945,0.002724766,0.0020575542,0.000104157305,0.00024859054,0.00009593706,0.8980648,0.06431036,0.00021759322,0.026954163,0.0026092434],"about_ca_topic_score_codex":0.00001717977,"about_ca_topic_score_gemma":0.0000032940072,"teacher_disagreement_score":0.50192446,"about_ca_system_score_codex":0.00014186511,"about_ca_system_score_gemma":0.000018199116,"threshold_uncertainty_score":0.99985266},"labels":[],"label_agreement":null},{"id":"W2107024044","doi":"10.1109/tse.2006.38","title":"On the value of static analysis for fault detection in software","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":281,"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":"North Carolina State University; National Science Foundation","keywords":"Static analysis; Computer science; Fault detection and isolation; Software; Software quality; Reliability engineering; Software bug; Programmer; Software reliability testing; Fault (geology); Static program analysis; Data mining; Software development; Embedded system; Operating system; Artificial intelligence; Programming language; Engineering","score_opus":0.011465499236457887,"score_gpt":0.23584611802258723,"score_spread":0.22438061878612933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107024044","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":[0.15207186,0.0000216312,0.84674495,0.000039522263,0.0003167545,0.00034507163,0.000025751215,0.0004331777,0.0000012894031],"genre_scores_gemma":[0.9307032,0.00000315026,0.06891742,0.000020560223,0.000021669684,0.000253353,0.000002249771,0.00003368336,0.00004467371],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983383,0.000040434246,0.00037748838,0.00039197222,0.00044780923,0.00040402127],"domain_scores_gemma":[0.99495953,0.0041890866,0.00005863166,0.000632367,0.00010319441,0.000057168858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042003594,0.00022867013,0.00028668015,0.0010148389,0.00010245663,0.00006177853,0.00054130674,0.000099728626,0.000010095153],"category_scores_gemma":[0.00038833875,0.00020325842,0.00025426256,0.0023565933,0.000024067587,0.00019635499,0.0000039667157,0.00036277928,0.000007344386],"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":[0.000012135392,0.00008244313,0.00026815,0.000054148048,0.00009766696,0.0000027750966,0.00009249671,0.99429375,0.00041349325,0.0004907687,0.000014599811,0.004177556],"study_design_scores_gemma":[0.000549159,0.00022386132,0.013351086,0.00009646704,0.00007647177,0.0000040259374,0.000011824496,0.91622895,0.068607084,0.00041380106,0.00007840483,0.0003588765],"about_ca_topic_score_codex":0.00014295579,"about_ca_topic_score_gemma":0.000056459852,"teacher_disagreement_score":0.7786314,"about_ca_system_score_codex":0.00020263348,"about_ca_system_score_gemma":0.000041433123,"threshold_uncertainty_score":0.82886374},"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":"W2110431240","doi":"10.1109/tse.2002.1019484","title":"Assessing the applicability of fault-proneness models across object-oriented software projects","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":351,"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":"Universidade Federal do Rio Grande do Sul; National Science Foundation","keywords":"Computer science; Software metric; Software system; Software; Data mining; A priori and a posteriori; Multivariate adaptive regression splines; Software development; Java; Fault (geology); Software fault tolerance; Software engineering; Machine learning; Software quality; Regression analysis; Programming language","score_opus":0.04020972332741948,"score_gpt":0.2891038020238414,"score_spread":0.2488940786964219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110431240","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":[0.14022459,0.00016062346,0.85664314,0.000039748225,0.0007181707,0.0005704947,0.00002560455,0.0016113278,0.000006307781],"genre_scores_gemma":[0.9024865,0.000017641816,0.096964404,0.000022684582,0.000047573103,0.00032829147,0.0000013779745,0.00006908979,0.00006246165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968544,0.00007525433,0.00053414324,0.00077488285,0.0009133405,0.00084795634],"domain_scores_gemma":[0.9959784,0.0018802191,0.00010044645,0.0015811804,0.000274997,0.00018476868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006207087,0.0004214686,0.00041059346,0.0002419396,0.00045710022,0.00033752064,0.0013150543,0.00019723373,0.000020904401],"category_scores_gemma":[0.00036559603,0.00036534586,0.00023955574,0.0017310517,0.00013807327,0.001295111,0.000030341771,0.0008586696,0.000024443541],"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":[0.0000053119343,0.00022705666,0.00039915976,0.00022659909,0.00007011713,0.000010790589,0.002490186,0.95961106,0.000555894,0.00007936754,0.000033054872,0.036291417],"study_design_scores_gemma":[0.0006937815,0.00012942743,0.0024095231,0.00023383785,0.000023825178,0.00005525962,0.00016013,0.96159995,0.033622812,0.000048579248,0.00032607195,0.00069682236],"about_ca_topic_score_codex":0.000041891875,"about_ca_topic_score_gemma":0.000003822946,"teacher_disagreement_score":0.76226187,"about_ca_system_score_codex":0.00024481607,"about_ca_system_score_gemma":0.000080328995,"threshold_uncertainty_score":0.99987984},"labels":[],"label_agreement":null},{"id":"W2111555385","doi":"10.1109/tse.2010.70","title":"Solving the Class Responsibility Assignment Problem in Object-Oriented Analysis with Multi-Objective Genetic Algorithms","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":128,"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; Heuristics; Class (philosophy); Genetic algorithm; Cohesion (chemistry); Domain (mathematical analysis); Context (archaeology); Class diagram; Object-oriented programming; Algorithm; Machine learning; Artificial intelligence; Programming language; Mathematics; Unified Modeling Language; Software","score_opus":0.009970145975078455,"score_gpt":0.24159022935009608,"score_spread":0.23162008337501763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111555385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13949211,0.000024757805,0.85872453,0.000049555914,0.00045783215,0.00053732924,0.000010224234,0.0007003945,0.0000032719477],"genre_scores_gemma":[0.6560544,0.000003541079,0.34357318,0.000013432241,0.000021111882,0.0002533071,8.344871e-7,0.00003294712,0.00004727214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727285,0.00010190537,0.00039640313,0.00082565454,0.0007144096,0.0006887763],"domain_scores_gemma":[0.9966199,0.0016995802,0.000061574785,0.0012639827,0.00016801302,0.00018696616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008050511,0.00036325183,0.0003444222,0.0009364629,0.00022030425,0.00016496658,0.0008277119,0.00015490323,0.000018750774],"category_scores_gemma":[0.00022985622,0.00028816782,0.00017636201,0.0036968885,0.00007456829,0.00034717293,0.000015937747,0.0014725891,0.000013305071],"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":[0.00002662099,0.00019548326,0.007116697,0.000025314526,0.00027850046,0.000043927623,0.0011765469,0.98251396,0.0014988983,0.000027316339,0.000002990284,0.0070937164],"study_design_scores_gemma":[0.00082938065,0.00018154157,0.16266711,0.00005989607,0.00009038851,0.00003381018,0.000053624415,0.82396024,0.0114853885,0.000007817043,0.000107764376,0.00052303355],"about_ca_topic_score_codex":0.00015511921,"about_ca_topic_score_gemma":0.00040167483,"teacher_disagreement_score":0.5165622,"about_ca_system_score_codex":0.0003393144,"about_ca_system_score_gemma":0.00017582811,"threshold_uncertainty_score":0.999957},"labels":[],"label_agreement":null},{"id":"W2112717272","doi":"10.1109/32.935852","title":"Foundations of the trace assertion method of module interface specification","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":36,"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":"Assertion; TRACE (psycholinguistics); Computer science; Programming language; Notation; Interface (matter); Formal specification; Operating system; Arithmetic; Mathematics","score_opus":0.02656165542666112,"score_gpt":0.2678047199802575,"score_spread":0.2412430645535964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112717272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048460597,0.000039790248,0.9938407,0.000051526575,0.0008401089,0.00017082045,0.000001438106,0.00015345842,0.000056098797],"genre_scores_gemma":[0.90462667,0.000009626586,0.09512577,0.0000032748012,0.000017718345,0.00002065095,3.1696015e-7,0.000009147305,0.00018684172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992205,0.000040849496,0.00025988076,0.00017213264,0.0001874941,0.000119126074],"domain_scores_gemma":[0.99922484,0.000116536925,0.000102015314,0.0004347266,0.00009241261,0.000029448705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002123167,0.00009547349,0.00012684595,0.00010359505,0.00006986001,0.00002589109,0.0003577223,0.000054844957,0.000010956782],"category_scores_gemma":[0.000021950136,0.00007889437,0.00010521012,0.0005246454,0.000016048065,0.00023794685,0.0000025442391,0.00012932756,0.0000066263374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000097755365,0.00024510847,0.0002088872,0.00009004508,0.000070897775,6.8870986e-7,0.0013752524,0.84465545,0.02274219,0.016343895,0.000022714023,0.11423507],"study_design_scores_gemma":[0.0005313487,0.00018643138,0.005505629,0.00007064503,0.0000541558,0.000064373366,0.00010973841,0.41988635,0.56601,0.0009263517,0.006279506,0.0003754494],"about_ca_topic_score_codex":0.0000374534,"about_ca_topic_score_gemma":0.000010608146,"teacher_disagreement_score":0.8997806,"about_ca_system_score_codex":0.000048230057,"about_ca_system_score_gemma":0.000023195333,"threshold_uncertainty_score":0.32172194},"labels":[],"label_agreement":null},{"id":"W2112792171","doi":"10.1109/tse.2005.88","title":"Automatic inclusion of middleware performance attributes into architectural UML software models","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":39,"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":"Vlaamse regering; University of Ottawa","keywords":"Computer science; Middleware (distributed applications); Unified Modeling Language; Overhead (engineering); Message oriented middleware; Model transformation; Distributed computing; Software architecture; Programming paradigm; Software engineering; Software; Programming language; Artificial intelligence","score_opus":0.01152522820902501,"score_gpt":0.21113453026997295,"score_spread":0.19960930206094793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112792171","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":[0.35957122,0.00015724209,0.63843346,0.000058446552,0.00051447924,0.00021723307,0.000010273876,0.0010353645,0.0000022938443],"genre_scores_gemma":[0.75372696,0.000026342464,0.24602158,0.000042247284,0.00005860672,0.000061706,0.0000028109557,0.00002995703,0.000029803452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976914,0.000039806564,0.00065720995,0.00050602923,0.00061877747,0.00048677184],"domain_scores_gemma":[0.9983365,0.00029722627,0.00013330035,0.00089444354,0.0001713181,0.00016719826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034838883,0.00038253525,0.0004453794,0.0004036182,0.00045827418,0.000048931077,0.00090764003,0.00018329982,0.000027020764],"category_scores_gemma":[0.000045556222,0.00034612548,0.00023670566,0.0007448746,0.000056157347,0.0011663394,0.000048151414,0.0004438516,0.00004119465],"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":[0.000007987798,0.00008478206,0.00024906793,0.0004412009,0.000031852993,0.0000014937455,0.0020419236,0.72245365,0.00019028141,0.000013688019,0.000009992843,0.27447408],"study_design_scores_gemma":[0.00044895036,0.00017719158,0.00097262504,0.000506991,0.000020476169,0.00004734512,0.000011109812,0.96153337,0.03565342,0.00007284437,0.00012606582,0.00042963],"about_ca_topic_score_codex":0.00003342063,"about_ca_topic_score_gemma":0.0000097929815,"teacher_disagreement_score":0.39415574,"about_ca_system_score_codex":0.0002586522,"about_ca_system_score_gemma":0.0001034312,"threshold_uncertainty_score":0.9998991},"labels":[],"label_agreement":null},{"id":"W2116117396","doi":"10.1109/tse.2003.1237171","title":"Temporal logic query checking: a tool for model exploration","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":67,"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; Temporal logic; Model checking; Kripke structure; Theoretical computer science; Query optimization; Computation tree logic; Linear temporal logic; Interval temporal logic; Query language; Set (abstract data type); Programming language; Information retrieval","score_opus":0.05622366089218801,"score_gpt":0.2785760117045132,"score_spread":0.22235235081232518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116117396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001168264,0.000018108467,0.9967959,0.000026194286,0.00089992513,0.00033125482,0.0000063870616,0.0007340842,0.00001989177],"genre_scores_gemma":[0.2911915,0.000005216846,0.7083837,0.000049057162,0.00001593222,0.00024800186,0.0000012896887,0.000019483556,0.00008585965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989728,0.000029053295,0.00025208652,0.0003157709,0.00017791081,0.00025238242],"domain_scores_gemma":[0.99927706,0.00010647689,0.00005316676,0.00042508854,0.000080564474,0.000057663845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003882326,0.00017133506,0.00013934915,0.0001774914,0.00013907418,0.00008302315,0.00025991,0.000099336874,0.0000036658967],"category_scores_gemma":[0.000108610904,0.00018657792,0.0001047273,0.0003299566,0.000010941278,0.0010330372,0.0000011029255,0.00017462758,0.000011238383],"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":[0.000005544655,0.000045171495,0.0000033113145,0.0000337616,0.000010220092,5.7048453e-7,0.00022837799,0.96522975,0.0009111373,0.026355172,0.000019656514,0.007157341],"study_design_scores_gemma":[0.00022627295,0.00006420879,0.000007647496,0.000023370234,0.000007775653,0.0000071054524,0.000008358098,0.9439422,0.053620555,0.0012675811,0.00059312605,0.00023181213],"about_ca_topic_score_codex":0.0000014139827,"about_ca_topic_score_gemma":5.7658787e-7,"teacher_disagreement_score":0.2900232,"about_ca_system_score_codex":0.00011175569,"about_ca_system_score_gemma":0.00005803399,"threshold_uncertainty_score":0.7608427},"labels":[],"label_agreement":null},{"id":"W2118604270","doi":"10.1109/tse.2012.28","title":"The Effects of Test-Driven Development on External Quality and Productivity: A Meta-Analysis","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":125,"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":"Productivity; Moderation; Computer science; Meta-analysis; Quality (philosophy); Task (project management); Quality management; Statistics; Operations management; Mathematics; Engineering; Economics","score_opus":0.03296412813828898,"score_gpt":0.27103694364331116,"score_spread":0.23807281550502218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118604270","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":[0.11137239,0.00023871283,0.8874235,0.0000882387,0.00021454568,0.00034863836,0.0000025417512,0.00031038077,0.0000010144352],"genre_scores_gemma":[0.922069,0.000014142507,0.077355176,0.000015921563,0.000013793772,0.00037016315,2.03064e-7,0.000020480744,0.0001410799],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99827164,0.00006194322,0.0003250908,0.00043724215,0.00056685973,0.00033723164],"domain_scores_gemma":[0.99287444,0.006070905,0.00006373722,0.0007380167,0.00012332741,0.00012954602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043071722,0.00023544094,0.0004466796,0.00035095602,0.00017386765,0.00013691233,0.00049095915,0.0000585321,0.000010129786],"category_scores_gemma":[0.0006691841,0.000173231,0.00028631202,0.0008606971,0.000038802606,0.00026534614,0.000011174405,0.00033500628,0.000016479902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000206554,0.00078001124,0.004005379,0.0008802923,0.044821974,0.00002414845,0.002123591,0.80841434,0.015989462,0.00040759495,0.00006506162,0.122467496],"study_design_scores_gemma":[0.0011000971,0.00082578167,0.3601316,0.00015238718,0.0093153035,0.000030816518,0.000020292955,0.10054896,0.5255178,0.0001284179,0.0005093136,0.001719215],"about_ca_topic_score_codex":0.000037549213,"about_ca_topic_score_gemma":0.0000057458246,"teacher_disagreement_score":0.81069666,"about_ca_system_score_codex":0.00007593399,"about_ca_system_score_gemma":0.00004326058,"threshold_uncertainty_score":0.70641553},"labels":[],"label_agreement":null},{"id":"W2120738100","doi":"10.1109/tse.2006.102","title":"Empirical Analysis of Object-Oriented Design Metrics for Predicting High and Low Severity Faults","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":349,"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":"Larner College of Medicine, University of Vermont; University of Alberta","keywords":"Computer science; Fault (geology); Data mining; Software fault tolerance; Empirical research; Object-oriented programming; Machine learning; Reliability engineering; Logistic regression; Artificial intelligence; Fault tolerance; Distributed computing; Engineering; Statistics; Mathematics; Programming language","score_opus":0.018279048185542823,"score_gpt":0.260653268209901,"score_spread":0.24237422002435816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120738100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18332925,0.00005301817,0.8153101,0.000012742826,0.00034003644,0.0002675075,0.000055060056,0.0006317287,5.339396e-7],"genre_scores_gemma":[0.716551,0.0000058425358,0.2832935,0.000006417043,0.00002500205,0.00006883435,0.0000045609754,0.000024029672,0.000020831836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982151,0.000035317662,0.0003825156,0.0004892266,0.00046009698,0.0004177406],"domain_scores_gemma":[0.9958394,0.0033224174,0.000063116815,0.00045414874,0.00019624508,0.00012466416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044592077,0.00023731416,0.00039723364,0.0013635777,0.00012177811,0.00005064592,0.00033541664,0.00013736142,0.000003890198],"category_scores_gemma":[0.00040433585,0.00025769023,0.00018744527,0.003636731,0.000028904735,0.00028656074,0.000007590305,0.00027988883,0.0000010630952],"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":[0.000016986833,0.00010170838,0.0055664442,0.0000898923,0.00030825703,0.0000046268115,0.00013256178,0.9905794,0.00037048262,0.000036588986,0.000028991815,0.002764005],"study_design_scores_gemma":[0.0004703211,0.00013957334,0.042573314,0.00004085741,0.00018636358,0.0000054848824,0.0000053838226,0.9349554,0.021300716,0.000013804186,0.000041927193,0.00026686536],"about_ca_topic_score_codex":0.000083788625,"about_ca_topic_score_gemma":0.0000064175597,"teacher_disagreement_score":0.5332218,"about_ca_system_score_codex":0.00013800884,"about_ca_system_score_gemma":0.000055711793,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W2120755390","doi":"10.1109/tse.2014.2387172","title":"Extracting Development Tasks to Navigate Software Documentation","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":80,"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":"Documentation; Software documentation; Computer science; Internal documentation; Software engineering; Software development; Application programming interface; Technical documentation; Software; Task (project management); World Wide Web; Software construction; Programming language; Systems engineering; Engineering","score_opus":0.013513800978778162,"score_gpt":0.25689729459795757,"score_spread":0.2433834936191794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120755390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048727553,0.00002012303,0.9465781,0.000057232202,0.0017430501,0.00031110825,0.0000037635325,0.002551158,0.000007938209],"genre_scores_gemma":[0.5250834,0.0000022719203,0.47436833,0.00009538353,0.00007550249,0.0001672257,0.0000024871185,0.00005700826,0.00014839569],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973997,0.000041213527,0.00042767657,0.0006895308,0.00072016503,0.0007217386],"domain_scores_gemma":[0.99743146,0.0012348897,0.00005403814,0.00073353865,0.0001544787,0.00039160412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054673845,0.00037242792,0.0002646723,0.000562022,0.00028656793,0.00030711896,0.0008138456,0.00012618236,0.00004187797],"category_scores_gemma":[0.0005880454,0.00042418277,0.00010567779,0.0009741087,0.000012861539,0.00078618224,0.000015462425,0.0005724994,0.00045162617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009297736,0.000074507545,0.00035360406,0.000095371455,0.00005659615,0.000013870685,0.0010637821,0.76560163,0.001548896,0.00007293494,0.00012731283,0.23098217],"study_design_scores_gemma":[0.0033900435,0.001008214,0.030527776,0.001970186,0.00007747424,0.0002333139,0.00009476128,0.2348867,0.667148,0.00015170571,0.054978482,0.0055333283],"about_ca_topic_score_codex":0.0000171886,"about_ca_topic_score_gemma":0.0000039640345,"teacher_disagreement_score":0.6655991,"about_ca_system_score_codex":0.0003636133,"about_ca_system_score_gemma":0.00008478144,"threshold_uncertainty_score":0.999821},"labels":[],"label_agreement":null},{"id":"W2122581326","doi":"10.1109/tse.2008.36","title":"Do Crosscutting Concerns Cause Defects?","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":238,"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; University of Calgary","funders":"","keywords":"Computer science; Harm; Process (computing); Code (set theory); Measure (data warehouse); Source code; Degree (music); Software engineering; Risk analysis (engineering); Reliability engineering; Data mining; Programming language; Law; Engineering","score_opus":0.03323913553247372,"score_gpt":0.26905700605010585,"score_spread":0.23581787051763214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122581326","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":[0.1747102,0.00012240869,0.8213046,0.000016320722,0.0011619204,0.00016752984,0.0000089381865,0.0024947082,0.0000133525555],"genre_scores_gemma":[0.9278547,0.00004720075,0.07155356,0.000041017698,0.00010945449,0.00008644051,8.0340544e-7,0.00007016918,0.00023661762],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776936,0.00002722325,0.00029965496,0.0005999978,0.0005959309,0.0007078602],"domain_scores_gemma":[0.9975423,0.0011325348,0.000039003124,0.00089385756,0.00011516601,0.00027711075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021470529,0.0003314667,0.0002651214,0.00041394128,0.00036250034,0.00015449649,0.000821415,0.00014332822,0.000044568056],"category_scores_gemma":[0.00025102124,0.00036653556,0.00018343299,0.000952673,0.000054615244,0.00059752114,0.000010563956,0.00069295336,0.00020378774],"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":[0.0000103757375,0.0001275868,0.0037253113,0.00009465466,0.00013540348,0.0004589142,0.0014093561,0.98449147,0.0014726688,0.0002540436,0.00039401083,0.0074262065],"study_design_scores_gemma":[0.0067351325,0.0014113252,0.058949903,0.0012858737,0.00014620791,0.0039149337,0.00010298504,0.50455725,0.39915308,0.0001123978,0.016510764,0.007120183],"about_ca_topic_score_codex":0.000020422533,"about_ca_topic_score_gemma":0.0000014594028,"teacher_disagreement_score":0.75314456,"about_ca_system_score_codex":0.00022715268,"about_ca_system_score_gemma":0.000109825356,"threshold_uncertainty_score":0.99987864},"labels":[],"label_agreement":null},{"id":"W2128089903","doi":"10.1109/32.917521","title":"Design, construction, and application of a generic visual language generation environment","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Model-Driven Software Engineering 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":"Centre For Cold Ocean Resources Engineering","funders":"","keywords":"Computer science; Programming language; Compiler; Visual programming language; Visual language; Grammar; Parsing; Artificial intelligence","score_opus":0.010869366349029446,"score_gpt":0.21358298539060863,"score_spread":0.2027136190415792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128089903","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015958577,0.000097120785,0.98278624,0.000014168587,0.00015480284,0.00024147067,0.0000030927465,0.00074376166,7.8709155e-7],"genre_scores_gemma":[0.37471345,0.00007165437,0.6250676,0.000010504039,0.000023592213,0.00008676958,0.0000015161429,0.000016505379,0.000008411845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990828,0.00002126893,0.00023183801,0.00030682862,0.00019067827,0.00016657617],"domain_scores_gemma":[0.9994664,0.000048151174,0.00005580298,0.00032946834,0.000029393468,0.00007078858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000120114884,0.00017200805,0.00015490364,0.00021568226,0.000064649656,0.00002830627,0.00016932697,0.00008409242,0.0000064334113],"category_scores_gemma":[0.0000022174204,0.00019453517,0.000042058244,0.00025160506,0.000026710435,0.00024640028,0.000004223015,0.00013248729,0.0000047317844],"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":[0.0000033082479,0.000041071326,0.000033397922,0.000017546423,0.000019645468,0.0000031222548,0.00023562582,0.7299545,0.040953394,0.0005230607,0.0000054126353,0.22820996],"study_design_scores_gemma":[0.00015486873,0.00008752246,0.000091058,0.000016127917,0.000012125027,0.00006577611,0.0000027680233,0.85808486,0.14047746,0.000010115776,0.00079888717,0.00019844371],"about_ca_topic_score_codex":0.000013286333,"about_ca_topic_score_gemma":5.6765157e-7,"teacher_disagreement_score":0.35875487,"about_ca_system_score_codex":0.00008263838,"about_ca_system_score_gemma":0.000015905634,"threshold_uncertainty_score":0.7932914},"labels":[],"label_agreement":null},{"id":"W2129603121","doi":"10.1109/tse.2005.15","title":"Toward formalizing domain modeling semantics in language syntax","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":80,"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; Metamodeling; Unified Modeling Language; Business domain; Modeling language; Domain model; Domain engineering; Domain (mathematical analysis); Programming language; Domain analysis; Object Constraint Language; Semantics (computer science); Software engineering; Syntax; Applications of UML; Natural language processing; Business rule; Software development; Domain knowledge; Business process; Component-based software engineering; Work in process","score_opus":0.009961354837146816,"score_gpt":0.21386160839263096,"score_spread":0.20390025355548413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129603121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14157407,0.0001276407,0.85705733,0.00019644448,0.00034942495,0.00010241004,0.000003834652,0.0005517225,0.000037136444],"genre_scores_gemma":[0.77397716,0.00001378607,0.22564593,0.00024927262,0.000062468935,0.00001968184,0.000001001437,0.000021150496,0.000009516013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987849,0.00001668496,0.00026342916,0.00030915334,0.00023339731,0.00039242793],"domain_scores_gemma":[0.9993998,0.00008373462,0.000027823608,0.00037125775,0.000024418394,0.00009300222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014226067,0.00020710046,0.00017595718,0.00036888738,0.00008380206,0.00008028011,0.00048605815,0.00008305724,0.000008722488],"category_scores_gemma":[0.0000025165377,0.00021496414,0.00008738634,0.00054505345,0.0000048600577,0.00056729506,0.00000682629,0.00035864636,0.000027572694],"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":[0.000004223102,0.00003924931,0.00001015761,0.000056977377,0.000014019334,0.000020077452,0.0066940747,0.97749335,0.00067445694,0.00036949033,9.719467e-7,0.014622984],"study_design_scores_gemma":[0.00032646785,0.000026338379,0.000015970632,0.00015294581,0.000006882694,0.00003518442,0.0002861548,0.986039,0.012373749,0.00003995516,0.00041695414,0.00028040758],"about_ca_topic_score_codex":0.00008704594,"about_ca_topic_score_gemma":0.00018165894,"teacher_disagreement_score":0.63240314,"about_ca_system_score_codex":0.00008350455,"about_ca_system_score_gemma":0.00002278213,"threshold_uncertainty_score":0.8765983},"labels":[],"label_agreement":null},{"id":"W2130400275","doi":"10.1109/32.888631","title":"A learning agent that assists the browsing of software libraries","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Machine Learning and Algorithms","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":"University of Ottawa","funders":"","keywords":"Computer science; Software; Similarity (geometry); World Wide Web; Information retrieval; Human–computer interaction; Artificial intelligence; Programming language","score_opus":0.010120749815697744,"score_gpt":0.20454357418451105,"score_spread":0.1944228243688133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130400275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02564545,0.0001442536,0.9725419,0.00010757671,0.00048377615,0.00008886048,0.0000033190556,0.0009387464,0.00004611805],"genre_scores_gemma":[0.85527605,0.00003559106,0.14340846,0.00006255615,0.000052770847,0.000021286663,0.0000010922298,0.00003254321,0.0011096349],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881524,0.000062645835,0.00021316938,0.00028973844,0.00032273168,0.0002964997],"domain_scores_gemma":[0.99903125,0.00039434392,0.000056193832,0.00041281982,0.000026671469,0.0000787169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017903469,0.00020402182,0.00019264637,0.00013013423,0.00032208636,0.00016292746,0.00053474185,0.0000699933,0.00014059411],"category_scores_gemma":[0.000035114743,0.00016657781,0.00015546275,0.0004344527,0.00003760928,0.0004025277,0.000004685171,0.0005972088,0.000033757984],"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":[0.0000041277426,0.000029341672,0.00014867068,0.000028246053,0.000031459054,0.0000061345477,0.0009058417,0.6918964,0.000042879325,0.000043355896,0.000024288267,0.30683932],"study_design_scores_gemma":[0.0008806198,0.00041856087,0.007080815,0.0005960979,0.000071644106,0.00014637856,0.00011892709,0.94084567,0.024176316,0.00010734939,0.024508726,0.0010488942],"about_ca_topic_score_codex":0.000031215153,"about_ca_topic_score_gemma":0.0000012189096,"teacher_disagreement_score":0.8296306,"about_ca_system_score_codex":0.000031350257,"about_ca_system_score_gemma":0.00003746763,"threshold_uncertainty_score":0.67928463},"labels":[],"label_agreement":null},{"id":"W2131878172","doi":"10.1109/tse.2003.1237169","title":"Template semantics for model-based notations","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":58,"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":"University of Waterloo; University of Minnesota","keywords":"Computer science; Notation; Semantics (computer science); Programming language; Operational semantics; Structuring; Denotational semantics; Action semantics; Variety (cybernetics); Well-founded semantics; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.028663676038960133,"score_gpt":0.2666123737194766,"score_spread":0.23794869768051646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131878172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007026584,0.000009890624,0.9974793,0.000029948678,0.00087057694,0.00025345696,0.00001594608,0.00061845296,0.000019767347],"genre_scores_gemma":[0.2735963,0.0000017885382,0.72612953,0.000052105624,0.0000074897243,0.00013072613,9.2302326e-7,0.000020196714,0.000060976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991351,0.000020193653,0.0002037461,0.00025237794,0.00015144233,0.0002371802],"domain_scores_gemma":[0.99914426,0.00022360875,0.000039165512,0.00042928377,0.00008937951,0.0000743194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023566464,0.00014554407,0.00011580089,0.00019482167,0.00017146103,0.00006128138,0.00025775,0.00007448246,0.000003946092],"category_scores_gemma":[0.00008476161,0.0001657915,0.000098546276,0.000355752,0.000012231513,0.0003179533,5.4054345e-7,0.0001520046,0.000012570602],"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":[0.0000023501543,0.00003614781,0.0000016273676,0.00003275106,0.000009416787,3.8371633e-7,0.00008197996,0.9842075,0.0005375054,0.0118705565,0.000016442578,0.0032033084],"study_design_scores_gemma":[0.00023603185,0.000039678074,0.000009199332,0.00002133146,0.000011240194,0.0000037373945,0.000002540429,0.92076933,0.07776257,0.00021876217,0.0007524141,0.00017318269],"about_ca_topic_score_codex":8.313676e-7,"about_ca_topic_score_gemma":6.323684e-7,"teacher_disagreement_score":0.2728936,"about_ca_system_score_codex":0.00007065873,"about_ca_system_score_gemma":0.000067323796,"threshold_uncertainty_score":0.6760781},"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":"W2138201395","doi":"10.1109/tse.2003.1214324","title":"An investigation of graph-based class integration test order strategies","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":116,"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; Goddard Space Flight Center","keywords":"Computer science; Dependency (UML); Dependency graph; Inheritance (genetic algorithm); Class (philosophy); Theoretical computer science; Graph; Context (archaeology); Artificial intelligence","score_opus":0.01487302891763947,"score_gpt":0.2431641625133235,"score_spread":0.22829113359568404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138201395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08326185,0.000021651838,0.9151504,0.000022265029,0.0004498011,0.00016992088,0.000008414185,0.00090954173,0.000006157941],"genre_scores_gemma":[0.7795987,0.000003191349,0.22027332,0.000017660184,0.000011512729,0.00005391142,0.0000029969792,0.000029288103,0.000009439376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99855876,0.000052336225,0.0002993612,0.00036594932,0.00041765097,0.0003059722],"domain_scores_gemma":[0.9979714,0.0009469551,0.00005198283,0.00063349574,0.00024130725,0.00015484865],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030408558,0.00023261135,0.00018814675,0.0005797732,0.00008867598,0.00013475741,0.0004247872,0.00012582292,0.00001786701],"category_scores_gemma":[0.00025643254,0.000247731,0.00007901688,0.00144943,0.000045992532,0.0008941394,0.0000010873795,0.00037414313,0.000009417229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031838456,0.00007077827,0.0007799749,0.00006306383,0.000016921405,0.00000365073,0.00027761483,0.9750621,0.01984728,0.0016679561,0.000012193949,0.0021952863],"study_design_scores_gemma":[0.00059913745,0.0005045141,0.004828121,0.0001735389,0.000017080858,0.00001299005,0.0000740145,0.41722134,0.5757294,0.00023250541,0.00007627637,0.00053106685],"about_ca_topic_score_codex":0.000021119042,"about_ca_topic_score_gemma":0.000008764611,"teacher_disagreement_score":0.69633687,"about_ca_system_score_codex":0.00009296293,"about_ca_system_score_gemma":0.00022825906,"threshold_uncertainty_score":0.9999975},"labels":[],"label_agreement":null},{"id":"W2142033303","doi":"10.1109/32.888627","title":"Management of performance requirements for information systems","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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 Toronto","funders":"","keywords":"Computer science; Non-functional requirement; System requirements; Software engineering; Requirements analysis; Requirements management; Process (computing); Domain (mathematical analysis); Requirements engineering; Systems engineering; Information system; Functional requirement; Variety (cybernetics); Software system; Software; Engineering; Software construction; Artificial intelligence","score_opus":0.010316117302928352,"score_gpt":0.21488042325859766,"score_spread":0.2045643059556693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142033303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03823887,0.000030301868,0.95966226,0.0000055290475,0.0010520496,0.0004969135,0.000013363677,0.00038172383,0.00011901332],"genre_scores_gemma":[0.9514524,0.00008365615,0.048012167,0.000010855213,0.0000173004,0.00022380552,0.0000024892975,0.000009822477,0.00018749901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989375,0.0000077698505,0.00039470248,0.00016864827,0.00026581495,0.00022560207],"domain_scores_gemma":[0.99933505,0.000048565966,0.00005731162,0.00042856982,0.000078691955,0.00005183006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022447057,0.0001435614,0.00016572147,0.00014484486,0.00010191859,0.000046505804,0.00033248676,0.00006402928,0.0000106931475],"category_scores_gemma":[0.0000020198827,0.00013699151,0.000087362656,0.00032194087,0.0000112502385,0.0011193226,0.0000016245621,0.00008346508,0.00004868741],"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":[0.00002250017,0.000047187787,0.000058793492,0.0011635461,0.00006310826,5.0506924e-7,0.00021048565,0.76901853,0.000011230773,0.0002947224,0.000023452218,0.22908595],"study_design_scores_gemma":[0.0020239116,0.0005522959,0.0025329764,0.001376997,0.000064289066,0.00002514413,0.000057833637,0.94533795,0.012964888,0.000009552847,0.03432772,0.0007264131],"about_ca_topic_score_codex":0.0000052221503,"about_ca_topic_score_gemma":7.5497155e-8,"teacher_disagreement_score":0.91321355,"about_ca_system_score_codex":0.000078647856,"about_ca_system_score_gemma":0.000016086142,"threshold_uncertainty_score":0.5586352},"labels":[],"label_agreement":null},{"id":"W2145386371","doi":"10.1109/tse.2011.29","title":"Does Socio-Technical Congruence Have an Effect on Software Build Success? A Study of Coordination in a Software Project","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":135,"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":"Congruence (geometry); IBM; Computer science; Software; Knowledge management; Psychology; Programming language; Social psychology","score_opus":0.018081194288832585,"score_gpt":0.26614485705394325,"score_spread":0.24806366276511066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145386371","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":[0.40433854,0.0000047123626,0.59293777,0.000014760781,0.0004991516,0.00108806,0.0000275212,0.0010855884,0.000003888385],"genre_scores_gemma":[0.8817129,0.0000014989713,0.11745596,0.00003979908,0.00003059204,0.00063453,0.0000056628064,0.000077982426,0.000041080046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99646646,0.00022089337,0.00086273375,0.001054038,0.0007770532,0.00061880343],"domain_scores_gemma":[0.9970998,0.0008651224,0.00023797745,0.001331093,0.0003184617,0.00014754021],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078421074,0.00056714553,0.0006507847,0.001240215,0.00025588428,0.00013431071,0.0014002781,0.00029680645,0.000027201579],"category_scores_gemma":[0.0004027006,0.00047888182,0.00017356678,0.0019307175,0.00009137354,0.0013998814,0.000026290774,0.0009781369,0.00001491755],"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":[0.0011121093,0.022939172,0.35232568,0.0014985747,0.0009118874,0.00070839986,0.05644858,0.37138593,0.003565253,0.0015209039,0.00024123256,0.18734229],"study_design_scores_gemma":[0.031682912,0.05880408,0.5415117,0.006338779,0.0009208568,0.00040416265,0.0050914395,0.097822554,0.2423603,0.0012509653,0.000558785,0.013253485],"about_ca_topic_score_codex":0.00070395303,"about_ca_topic_score_gemma":0.0004671423,"teacher_disagreement_score":0.47737435,"about_ca_system_score_codex":0.0003637408,"about_ca_system_score_gemma":0.0001580465,"threshold_uncertainty_score":0.9997663},"labels":[],"label_agreement":null},{"id":"W2145512597","doi":"10.1109/tse.2010.91","title":"Work Item Tagging: Communicating Concerns in Collaborative Software Development","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorization; Software development; Knowledge management; Mechanism (biology); Work (physics); Domain (mathematical analysis); Software; Vocabulary; Empirical research; Open-source software development; World Wide Web; Software engineering; Data science; Human–computer interaction; Artificial intelligence","score_opus":0.018162273126256012,"score_gpt":0.26037683232553865,"score_spread":0.24221455919928264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145512597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11581391,0.00007783273,0.8807294,0.000074269294,0.001201718,0.00033458957,0.0000071622276,0.0017497158,0.0000114329105],"genre_scores_gemma":[0.6098884,0.000008231807,0.38970795,0.000041389238,0.000035518453,0.00019796181,0.0000022101347,0.0000526211,0.000065747154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975475,0.000050740804,0.00050283916,0.0005976993,0.0005570312,0.00074416597],"domain_scores_gemma":[0.9955272,0.0028231698,0.000072642295,0.001145441,0.00017690728,0.00025465764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005389688,0.0003962262,0.00035054417,0.0006320588,0.00025779527,0.00021572212,0.001465651,0.00021839995,0.00003761364],"category_scores_gemma":[0.00070570863,0.00045201284,0.000087304004,0.0022346396,0.00005438224,0.0005359051,0.000029933215,0.0017651379,0.00007803919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004501667,0.0005450653,0.02175576,0.0002472074,0.00021677028,0.00017495902,0.011579401,0.7984946,0.0040644435,0.00055223645,0.00029592804,0.16202861],"study_design_scores_gemma":[0.010545283,0.00079749164,0.15988626,0.0048224214,0.00008580922,0.0003011003,0.000766564,0.23850417,0.46100014,0.00012284743,0.111748576,0.011419327],"about_ca_topic_score_codex":0.000019266876,"about_ca_topic_score_gemma":0.000049986036,"teacher_disagreement_score":0.5599904,"about_ca_system_score_codex":0.00029895717,"about_ca_system_score_gemma":0.0002836911,"threshold_uncertainty_score":0.9997932},"labels":[],"label_agreement":null},{"id":"W2147386665","doi":"10.1109/tse.2012.70","title":"A large-scale empirical study of just-in-time quality assurance","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":699,"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; Polytechnique Montréal","funders":"","keywords":"Computer science; Software quality assurance; Quality assurance; Source lines of code; Quality (philosophy); Software quality; Code review; Scale (ratio); Software; Empirical research; Software quality analyst; Software bug; Data science; Software engineering; Software development; Operations management; Engineering","score_opus":0.03357803100855729,"score_gpt":0.3186450643686469,"score_spread":0.28506703336008965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147386665","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":[0.4709621,0.00003521477,0.528027,0.000009744618,0.00037976663,0.00018523702,0.0000067363912,0.00039136707,0.0000028275995],"genre_scores_gemma":[0.97035414,0.000003844004,0.029371869,0.000017173365,0.00004497297,0.00009999869,5.231033e-7,0.000037598373,0.00006989297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99755025,0.00009868422,0.00047876997,0.00040068824,0.00075189676,0.00071973406],"domain_scores_gemma":[0.99733377,0.0015052294,0.00005054292,0.0008143466,0.000076267395,0.00021985068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010124106,0.00025243108,0.0003892574,0.00046849955,0.00006686229,0.000042133903,0.0007570104,0.000118486474,0.000031773314],"category_scores_gemma":[0.00022685387,0.00027229814,0.000115061564,0.0012466001,0.000015433887,0.0005652808,0.000013433881,0.0005516079,0.000068626774],"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":[0.000050051654,0.0060125184,0.34286726,0.00030286235,0.00015006553,0.000026776623,0.017190106,0.62935245,0.0013255338,0.000026629556,0.00015778225,0.0025379334],"study_design_scores_gemma":[0.0033716161,0.00061525643,0.9062577,0.0002398083,0.000035341825,0.00003427537,0.00043062412,0.07069996,0.016530855,0.0000061533096,0.0005715288,0.0012068837],"about_ca_topic_score_codex":0.00002314978,"about_ca_topic_score_gemma":0.00001388559,"teacher_disagreement_score":0.56339043,"about_ca_system_score_codex":0.00016181041,"about_ca_system_score_gemma":0.00004563351,"threshold_uncertainty_score":0.99997294},"labels":[],"label_agreement":null},{"id":"W2150853641","doi":"10.1109/tse.2011.65","title":"WAM—The Weighted Average Method for Predicting the Performance of Systems with Bursts of Customer Sessions","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"University of Calgary","funders":"","keywords":"Computer science; Benchmark (surveying); Queueing theory; Workload; Markov chain; Sizing; Benchmarking; Machine learning","score_opus":0.013726318271697586,"score_gpt":0.22237533266721862,"score_spread":0.20864901439552103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150853641","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":[0.1139313,0.000058775488,0.8843565,0.000012042726,0.0008827972,0.00052222714,0.0000157029,0.00020651707,0.000014157579],"genre_scores_gemma":[0.91335845,0.000015347505,0.086316906,0.000008063021,0.000030497558,0.00020261327,4.353109e-7,0.000020041125,0.000047654634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987582,0.000050597013,0.00040152186,0.00024202745,0.00029527475,0.0002523927],"domain_scores_gemma":[0.99825823,0.0006295586,0.00016009898,0.00070335023,0.00019766051,0.00005107306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063141994,0.00018318096,0.0002626667,0.00012258478,0.00024340836,0.000018619075,0.0005980856,0.00008354604,0.000004787403],"category_scores_gemma":[0.000017017874,0.00009814362,0.000120802106,0.00054414687,0.000052797153,0.00029976855,0.0000052012333,0.00025330376,0.0000025004929],"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":[0.000104624654,0.00019046401,0.003509012,0.0013430289,0.0002932542,0.0000014310796,0.007905665,0.97214156,0.0006888661,0.00029640793,0.000037858335,0.013487833],"study_design_scores_gemma":[0.00046963952,0.00034930222,0.002194115,0.0006065645,0.00007271394,0.000045771634,0.0001442044,0.9402777,0.055346534,0.000003405042,0.00026610185,0.00022394434],"about_ca_topic_score_codex":0.00007812869,"about_ca_topic_score_gemma":0.0000024221474,"teacher_disagreement_score":0.79942715,"about_ca_system_score_codex":0.000038315316,"about_ca_system_score_gemma":0.00006702094,"threshold_uncertainty_score":0.40021807},"labels":[],"label_agreement":null},{"id":"W2151187574","doi":"10.1109/tse.2004.1274044","title":"An empirical study of open-source and closed-source software products","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":317,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Dynamics (Canada)","funders":"University of Calgary","keywords":"Computer science; Open source; Empirical research; Open source software; Metric (unit); Software; Modular design; Software development; Software engineering; Empirical evidence; Creativity; Data science; Knowledge management; Marketing; Programming language; Statistics; Business; Mathematics","score_opus":0.021155778114453634,"score_gpt":0.2799976163484172,"score_spread":0.25884183823396356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151187574","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":[0.39356175,0.000017071688,0.6046465,0.00008747511,0.0002720605,0.00057219504,0.000007580161,0.00083299313,0.0000023757002],"genre_scores_gemma":[0.7678757,0.0000021250355,0.23176678,0.00008427274,0.000039141676,0.000096090385,0.0000019887952,0.00006583788,0.00006810222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99750787,0.00006749688,0.0005692577,0.0009021492,0.00051656226,0.0004366657],"domain_scores_gemma":[0.9977788,0.00023466072,0.00013163032,0.0013691038,0.0002731862,0.00021264546],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039045623,0.0003828611,0.00043926967,0.00048093306,0.00033360114,0.00038010158,0.0015664544,0.00013189847,0.0000092932305],"category_scores_gemma":[0.00012854178,0.00041006925,0.000060430535,0.0018873117,0.000060034577,0.0015232649,0.000041659987,0.00054341025,0.000014726223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028087039,0.002325225,0.0022698548,0.00008172757,0.00012360472,0.000026436772,0.00864637,0.9418992,0.0007399764,0.00011195143,0.000043154003,0.043704405],"study_design_scores_gemma":[0.06972248,0.042836342,0.24371773,0.004320185,0.0016627029,0.0034538775,0.013209462,0.19701566,0.3598849,0.0021743558,0.0389611,0.023041213],"about_ca_topic_score_codex":0.00016926137,"about_ca_topic_score_gemma":0.0000262549,"teacher_disagreement_score":0.74488354,"about_ca_system_score_codex":0.0001345034,"about_ca_system_score_gemma":0.00015507151,"threshold_uncertainty_score":0.99983513},"labels":[],"label_agreement":null},{"id":"W2151877107","doi":"10.1109/tse.2004.69","title":"A cognitive-based mechanism for constructing software inspection teams","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Alberta","funders":"","keywords":"Computer science; Software inspection; Mechanism (biology); Process (computing); Selection (genetic algorithm); Software; Cognition; Artificial intelligence; Software engineering; Software development; Software quality","score_opus":0.015596019644818788,"score_gpt":0.24884721502036167,"score_spread":0.23325119537554287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151877107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036616456,0.000022396858,0.955688,0.000060690185,0.0017472723,0.00065746653,0.00005857689,0.005146658,0.0000025032884],"genre_scores_gemma":[0.59706104,0.0000027909384,0.4024071,0.000066552246,0.00006500642,0.00031643824,0.0000038792773,0.00006450698,0.000012690553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976992,0.000019780144,0.0003594245,0.0007057971,0.0005103614,0.0007054493],"domain_scores_gemma":[0.9972621,0.0016073424,0.00006675434,0.0005044157,0.0003247143,0.00023466231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026947612,0.0003937712,0.00030609441,0.0006461634,0.00035171083,0.00019373775,0.00053117913,0.0001983103,0.000009468832],"category_scores_gemma":[0.0007988379,0.00045704684,0.00024331144,0.00090009364,0.00004553702,0.0005367535,0.0000060286357,0.00059222686,0.00003299841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005101072,0.00026683425,0.00020916386,0.00030627666,0.00015426512,0.000040355753,0.00042192658,0.9688183,0.0022132231,0.0035079864,0.000014817921,0.023995861],"study_design_scores_gemma":[0.009708157,0.0014680788,0.0007324265,0.0017079111,0.00013169913,0.00031594012,0.0001952417,0.18208553,0.7989333,0.0018946184,0.00018849695,0.0026385842],"about_ca_topic_score_codex":0.000029867479,"about_ca_topic_score_gemma":0.0000068167396,"teacher_disagreement_score":0.7967201,"about_ca_system_score_codex":0.0005067972,"about_ca_system_score_gemma":0.00026323093,"threshold_uncertainty_score":0.9997881},"labels":[],"label_agreement":null},{"id":"W2159484301","doi":"10.1109/tse.2008.74","title":"Enhanced Modeling and Solution of Layered Queueing Networks","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; IBM (Canada); Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Queueing theory; Distributed computing; Layered queueing network; Dependability; Control reconfiguration; Canonical form; Queue; Representation (politics); Theoretical computer science; Computer network","score_opus":0.012426582439109008,"score_gpt":0.20113252693447015,"score_spread":0.18870594449536113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159484301","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":[0.25834882,0.00007388391,0.74064016,0.00000644392,0.0004889486,0.000092651106,0.0000013719176,0.0003443612,0.0000033232914],"genre_scores_gemma":[0.9559241,0.00012107887,0.043858323,0.000010952122,0.00003075923,0.000021652133,4.955225e-7,0.000013532469,0.000019096922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990414,0.000016334081,0.0002776742,0.0002660749,0.00017207404,0.00022645702],"domain_scores_gemma":[0.9994091,0.00008828375,0.00004400294,0.00031752387,0.000070413895,0.000070695954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014243886,0.00014695586,0.00020065566,0.00013525297,0.00016496902,0.00001532448,0.00018140131,0.000101517784,0.0000023324676],"category_scores_gemma":[0.0000117423415,0.00014628257,0.00007560891,0.00030062092,0.000023720577,0.00039651545,0.0000036113036,0.0002038408,0.0000026260666],"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":[0.000005671961,0.000023285062,0.000055809378,0.000047905098,0.000015942156,0.0000016455481,0.0003870757,0.98905885,0.0017950379,0.000023475957,0.0000012028905,0.008584093],"study_design_scores_gemma":[0.00021185873,0.000046273868,0.000271256,0.00009822956,0.0000050548424,0.000026312133,0.0000050304607,0.9854125,0.013760347,0.0000043847303,0.000007833233,0.00015094083],"about_ca_topic_score_codex":0.000035141537,"about_ca_topic_score_gemma":0.0000023757452,"teacher_disagreement_score":0.6975753,"about_ca_system_score_codex":0.00004711323,"about_ca_system_score_gemma":0.00003080785,"threshold_uncertainty_score":0.59652305},"labels":[],"label_agreement":null},{"id":"W2163165845","doi":"10.1109/tse.2009.30","title":"Engineering of Framework-Specific Modeling Languages","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":50,"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; Software engineering; Model-driven architecture; Domain-specific language; Reverse engineering; Domain (mathematical analysis); Modeling language; Programming language; Software development; Software","score_opus":0.024973816079868247,"score_gpt":0.26647242826469514,"score_spread":0.24149861218482688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163165845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004297242,0.0005247446,0.99171656,0.00003194188,0.0008843714,0.00013245232,0.0000064527408,0.002399099,0.0000071468066],"genre_scores_gemma":[0.4182955,0.00007194594,0.58152306,0.000020518888,0.00003955004,0.000011718906,4.2497348e-7,0.000025833691,0.000011428852],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983691,0.00002206305,0.000389326,0.00044612034,0.000324507,0.00044887565],"domain_scores_gemma":[0.998214,0.00074407225,0.000055571396,0.0007893108,0.00007753525,0.00011950814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024814074,0.00033242145,0.00037128764,0.00044530942,0.00006459352,0.000049916143,0.00069487136,0.00017649108,0.000009735668],"category_scores_gemma":[0.00021864443,0.0003672595,0.00017480951,0.00071051635,0.000012430141,0.00047646055,0.000005083174,0.00059311755,0.000012610052],"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":[0.0000044721264,0.00003571666,0.0000010848582,0.000030430108,0.000020324189,0.000011805362,0.00024598264,0.96434176,0.00332287,0.0024104961,0.000004796036,0.029570285],"study_design_scores_gemma":[0.00030300923,0.00018000117,0.00010171456,0.0004646554,0.000015974234,0.000037831673,0.000027802995,0.9179389,0.07905703,0.0009305071,0.00018297852,0.0007595817],"about_ca_topic_score_codex":0.000001945739,"about_ca_topic_score_gemma":9.49361e-8,"teacher_disagreement_score":0.41399825,"about_ca_system_score_codex":0.000096361815,"about_ca_system_score_gemma":0.000021073949,"threshold_uncertainty_score":0.9998779},"labels":[],"label_agreement":null},{"id":"W2167003754","doi":"10.1109/32.910857","title":"Design of multi-invariant data structures for robust shared accesses in multiprocessor systems","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Distributed systems and fault tolerance","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; Invariant (physics); Data structure; Multiprocessing; Fault tolerance; Algorithm; Distributed computing; Parallel computing; Theoretical computer science; Programming language; Mathematics","score_opus":0.07999694562695671,"score_gpt":0.27546634039445494,"score_spread":0.19546939476749825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167003754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006188183,0.00024481333,0.9970671,0.000011593125,0.0008691617,0.00058317225,0.00034422008,0.0002602479,8.8142497e-7],"genre_scores_gemma":[0.66885155,0.000033424094,0.33088213,0.0000070747565,0.000028214725,0.00013494508,0.0000150067535,0.00002219012,0.000025453257],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985599,0.00002700177,0.00043177154,0.00047181794,0.00020413678,0.0003054072],"domain_scores_gemma":[0.9986274,0.00030432345,0.00009984558,0.00078197074,0.00011492006,0.00007153752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026419546,0.0002079691,0.00031221038,0.0002107704,0.00007119061,0.00013391773,0.0011554023,0.00010517949,0.0000029542848],"category_scores_gemma":[0.000067243374,0.00020346619,0.00004532131,0.0005602295,0.0000119163215,0.00080255454,0.000007295697,0.00015589427,0.0000017252344],"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":[0.000018881676,0.000081779166,0.000030046418,0.0002201067,0.00002925001,0.000009690186,0.00014791008,0.99486154,0.0005909451,0.00004878347,0.000036784128,0.0039242506],"study_design_scores_gemma":[0.0008085303,0.00003812344,0.0002657204,0.00023159831,0.00000950235,0.000020615935,0.000023894507,0.996413,0.0016675553,0.0000026222392,0.00029989955,0.00021897088],"about_ca_topic_score_codex":0.00009294103,"about_ca_topic_score_gemma":0.000016992191,"teacher_disagreement_score":0.66823274,"about_ca_system_score_codex":0.000052422703,"about_ca_system_score_gemma":0.000062543855,"threshold_uncertainty_score":0.8297111},"labels":[],"label_agreement":null},{"id":"W2167110832","doi":"10.1109/32.852742","title":"Validating the ISO/IEC 15504 measure of software requirements analysis process capability","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Software measurement; Process (computing); Software engineering; Process capability; Software Engineering Process Group; Software; Software quality; Software development process; Reliability engineering; Systems engineering; Software development; Work in process; Engineering; Operations management; Operating system","score_opus":0.021389347909023807,"score_gpt":0.26770558990715365,"score_spread":0.24631624199812985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167110832","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":[0.19581184,0.00007526466,0.80247843,0.000039468367,0.00027610236,0.0003023753,0.000026756861,0.0009809285,0.000008863103],"genre_scores_gemma":[0.95185316,0.000012656801,0.047782354,0.000023974953,0.00003871198,0.00013899083,0.0000031824823,0.0000484872,0.00009847591],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996799,0.00008990979,0.0006082199,0.00072077307,0.001148094,0.0006340315],"domain_scores_gemma":[0.99664754,0.0012474059,0.000092434966,0.0015423563,0.00028556006,0.00018470087],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008854444,0.0003773469,0.00046702157,0.0004978569,0.00027619372,0.00013421064,0.0014735693,0.0001471017,0.00022891986],"category_scores_gemma":[0.00047303294,0.0003297083,0.0003914223,0.0035196312,0.000073750816,0.00060312083,0.000009028393,0.0006577607,0.000035898778],"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":[0.000012739477,0.00012367763,0.0031282918,0.00013582135,0.00047322703,0.0000062950285,0.0008939954,0.96121705,0.00023800107,0.000011265712,0.000013716409,0.033745904],"study_design_scores_gemma":[0.0028157546,0.0006375018,0.07129069,0.001012189,0.0015422014,0.00009953447,0.00023443905,0.73043674,0.18731752,0.00024149992,0.0008108713,0.0035610266],"about_ca_topic_score_codex":0.00007957713,"about_ca_topic_score_gemma":0.000012979071,"teacher_disagreement_score":0.75604135,"about_ca_system_score_codex":0.00021222081,"about_ca_system_score_gemma":0.000117891286,"threshold_uncertainty_score":0.9999155},"labels":[],"label_agreement":null},{"id":"W2169782617","doi":"10.1109/tse.2002.1158285","title":"An operational process for goal-driven definition of measures","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":148,"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; Set (abstract data type); Process (computing); Verifiable secret sharing; Software engineering; Management science; Programming language","score_opus":0.03966221107474621,"score_gpt":0.26917200462530516,"score_spread":0.22950979355055895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169782617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028847791,0.000043498272,0.96966845,0.000032705037,0.00038928082,0.00027761667,0.000038577386,0.0006960212,0.0000060849543],"genre_scores_gemma":[0.8056252,0.000009916543,0.19405036,0.000016794582,0.000041219817,0.00020715033,0.0000033301758,0.000029894303,0.000016141525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986837,0.00001643087,0.00024607134,0.000334211,0.00043009795,0.00028948995],"domain_scores_gemma":[0.9986978,0.00049651763,0.00003200185,0.00040140562,0.00024955775,0.00012269213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015223825,0.00017642639,0.00017495184,0.00030887246,0.00011275189,0.000066093016,0.00049442204,0.000091330076,0.000026469206],"category_scores_gemma":[0.00013826626,0.00019366604,0.0000959257,0.0004450576,0.000019866795,0.00061329734,0.0000015117549,0.00020373311,0.00001389849],"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":[0.00000812354,0.00018570277,0.00016385078,0.00011106539,0.000038830123,0.0000021546805,0.0004903788,0.98844004,0.0027974534,0.00058486045,0.000040016585,0.0071375514],"study_design_scores_gemma":[0.0007254668,0.00040168117,0.0008906596,0.00010720084,0.000016068394,0.00002307041,0.000012555493,0.9357293,0.06141457,0.00010143463,0.00017471943,0.0004032304],"about_ca_topic_score_codex":0.000004388235,"about_ca_topic_score_gemma":0.0000017846489,"teacher_disagreement_score":0.7767774,"about_ca_system_score_codex":0.00007161567,"about_ca_system_score_gemma":0.000033947563,"threshold_uncertainty_score":0.78974724},"labels":[],"label_agreement":null},{"id":"W2247133547","doi":"10.1109/tse.2015.2449319","title":"A Tool-Supported Methodology for Validation and Refinement of Early-Stage Domain Models","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Model-Driven Software Engineering 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":"Computer science; Domain (mathematical analysis); Unified Modeling Language; Class diagram; Software engineering; Domain model; Subject-matter expert; Set (abstract data type); Process (computing); Model-driven architecture; Domain engineering; Modeling language; Domain analysis; Use Case Diagram; Metamodeling; Requirements engineering; Artificial intelligence; Domain knowledge; Programming language; Software development; Software; Expert system","score_opus":0.08578734900011618,"score_gpt":0.2873067031678123,"score_spread":0.20151935416769612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247133547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047050215,0.000029322799,0.9511269,0.00002979864,0.00034731114,0.0003943588,0.00003627591,0.0009825528,0.0000032689031],"genre_scores_gemma":[0.26201046,0.0000066697503,0.737713,0.0000129273885,0.000012754124,0.00017136856,0.0000024721114,0.00002727831,0.000043055017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871576,0.000043316886,0.0003645102,0.00036779649,0.00023935505,0.0002692418],"domain_scores_gemma":[0.9989299,0.00023481992,0.00008101339,0.00048094906,0.00015336505,0.00011990996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006640073,0.00021895884,0.00029736306,0.00031608852,0.000044178792,0.000034017252,0.00030262212,0.00012895597,0.0000027217475],"category_scores_gemma":[0.000019751995,0.00024005292,0.00008941282,0.00027465035,0.000021322901,0.00032579387,0.000008099705,0.00016643007,9.641449e-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":[0.0000327277,0.000058853115,0.000018371367,0.00011250204,0.0000644562,0.000002945486,0.0013136932,0.9486762,0.002223444,0.025314879,0.000039905903,0.022141978],"study_design_scores_gemma":[0.001286525,0.00071848667,0.000063055624,0.000120526354,0.000046444227,0.000031415613,0.000012785918,0.85737324,0.13309777,0.0033944985,0.0032252064,0.0006300231],"about_ca_topic_score_codex":0.00002983774,"about_ca_topic_score_gemma":0.0000012436745,"teacher_disagreement_score":0.21496025,"about_ca_system_score_codex":0.0000908443,"about_ca_system_score_gemma":0.00005533468,"threshold_uncertainty_score":0.97890735},"labels":[],"label_agreement":null},{"id":"W2316930373","doi":"10.1109/tse.2016.2550458","title":"Developer Micro Interaction Metrics for Software Defect Prediction","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Waterloo","funders":"Ministry of Education, Science and Technology; Neurosciences Research Foundation","keywords":"Computer science; Eclipse; Leverage (statistics); Software quality assurance; Software quality; Software bug; Software; Software metric; Software engineering; Source code; Software development; Task (project management); Plug-in; Machine learning; Operating system; Systems engineering","score_opus":0.0218172345002419,"score_gpt":0.25171140673187403,"score_spread":0.22989417223163214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316930373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013751158,0.000080102756,0.9795155,0.00008207253,0.003240561,0.00048216904,0.000086876265,0.0027592452,0.0000023391408],"genre_scores_gemma":[0.54811984,0.00004601073,0.45071763,0.00004546884,0.00014046188,0.00045844878,0.0000040143914,0.0001005088,0.00036762422],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777305,0.000030143174,0.0003917169,0.0006957263,0.00046554158,0.0006438468],"domain_scores_gemma":[0.99552625,0.0032312695,0.000058396978,0.00069582707,0.00027248953,0.00021575885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040695647,0.00035666832,0.00026767407,0.00094628485,0.00020453951,0.00014413094,0.0006619834,0.00019869581,0.000031077492],"category_scores_gemma":[0.0011173579,0.00030653938,0.00028966382,0.0011286709,0.000023769784,0.0010081922,0.000010018072,0.0003422431,0.000105448795],"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":[0.00015786343,0.00044234004,0.004060572,0.00051613396,0.0007250589,0.000036660553,0.00065198506,0.29721797,0.02674831,0.00030955664,0.0030329127,0.6661006],"study_design_scores_gemma":[0.006996764,0.0017755692,0.015751021,0.0018270117,0.00022863512,0.0004690783,0.0000384999,0.09855083,0.80375797,0.00023503388,0.066569135,0.003800469],"about_ca_topic_score_codex":0.000006330372,"about_ca_topic_score_gemma":0.0000021846836,"teacher_disagreement_score":0.77700967,"about_ca_system_score_codex":0.0005843522,"about_ca_system_score_gemma":0.000105691855,"threshold_uncertainty_score":0.99993867},"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":"W2472584751","doi":"10.1109/tse.2016.2586066","title":"A Study of Causes and Consequences of Client-Side JavaScript Bugs","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"Unobtrusive JavaScript; JavaScript; Computer science; Rich Internet application; Document Object Model; Web application; Programmer; World Wide Web; Client-side; Ajax; Programming language; Web page","score_opus":0.024017693639851897,"score_gpt":0.2549549340538039,"score_spread":0.23093724041395203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472584751","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":[0.45683882,0.00005325614,0.54251367,0.000013899843,0.0002361021,0.00013240919,0.000007679585,0.0002029819,0.000001206679],"genre_scores_gemma":[0.98369974,0.000037684047,0.01613783,0.000004466272,0.000010597066,0.00004497971,7.1337745e-8,0.00002104734,0.000043589174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862,0.000031823485,0.00033589668,0.0003366935,0.00040559654,0.00027002188],"domain_scores_gemma":[0.9979614,0.0012440359,0.00005769537,0.0005113275,0.00011603611,0.00010952622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022054483,0.000179526,0.00027478006,0.00040478643,0.000046380024,0.000023055029,0.00041332343,0.000059535672,0.000007821934],"category_scores_gemma":[0.00021851715,0.00014452523,0.000060425587,0.00046637762,0.000084158484,0.00031107862,0.000009225827,0.00014362462,0.000004196602],"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":[0.00017345996,0.0033647662,0.08588569,0.001309791,0.001618647,0.00031084145,0.01612196,0.36410964,0.33961275,0.0014444897,0.00016240806,0.18588555],"study_design_scores_gemma":[0.003649484,0.0025757768,0.06416176,0.0010027436,0.00008883815,0.00014583151,0.0004149955,0.0028312572,0.92382526,0.00010310238,0.00019189772,0.0010090723],"about_ca_topic_score_codex":0.0000669126,"about_ca_topic_score_gemma":0.000008352074,"teacher_disagreement_score":0.5842125,"about_ca_system_score_codex":0.000047525242,"about_ca_system_score_gemma":0.000052608022,"threshold_uncertainty_score":0.5893568},"labels":[],"label_agreement":null},{"id":"W2474835145","doi":"10.1109/tse.2016.2584050","title":"An Empirical Comparison of Model Validation Techniques for Defect Prediction Models","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":566,"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; Japan Society for the Promotion of Science; Japan Society for the Promotion of Science London; Compute Canada","keywords":"Computer science; Variance (accounting); Context (archaeology); Cross-validation; Model validation; Sample (material); Data mining; Predictive modelling; Software bug; Software; Machine learning","score_opus":0.054222375516789025,"score_gpt":0.33031650944663127,"score_spread":0.2760941339298422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474835145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02838135,0.00001809275,0.96894145,0.00003086786,0.00028419882,0.00038584945,0.00006864707,0.0018876537,0.0000019166343],"genre_scores_gemma":[0.66541225,0.000005783577,0.33431286,0.000004862213,0.0000252649,0.00019072914,0.0000020724794,0.000031411146,0.000014812295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984806,0.000025202638,0.0003582603,0.00042500335,0.00038680856,0.00032412427],"domain_scores_gemma":[0.9981589,0.00084586965,0.000053290205,0.00062261935,0.00018619132,0.00013315029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032120655,0.00020425132,0.0002466572,0.00041908107,0.00008337912,0.00004312172,0.0004915613,0.00015327879,0.0000029695125],"category_scores_gemma":[0.00010356916,0.00017827652,0.00016569378,0.0003574999,0.000022763375,0.0009693491,0.0000037239968,0.0001737507,0.0000026505147],"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":[0.000016893313,0.00013144045,0.00032238677,0.000051108607,0.00002859238,2.9149922e-7,0.00021067112,0.95596105,0.0106143085,0.00015807174,0.00005540389,0.03244981],"study_design_scores_gemma":[0.00020997146,0.00025047184,0.000103820246,0.00007659016,0.0000114633385,0.000002492684,0.0000020231535,0.7427968,0.25618532,0.00018762735,0.00002553545,0.00014788682],"about_ca_topic_score_codex":0.0000030282629,"about_ca_topic_score_gemma":6.2545274e-7,"teacher_disagreement_score":0.63703084,"about_ca_system_score_codex":0.00016851055,"about_ca_system_score_gemma":0.00006566503,"threshold_uncertainty_score":0.7269905},"labels":[],"label_agreement":null},{"id":"W2517486838","doi":"10.11368/tse.19.1","title":"Self－rewetting溶液を用いた自励振動型ヒートパイプの性能向上に関する研究(ブタノールとペンタノールの場合)","year":2011,"lang":"ja","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Thermodynamic Systems and Engines","field":"Engineering","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 Toronto","funders":"","keywords":"Computer science; Programming language; Software engineering","score_opus":0.012023827778058813,"score_gpt":0.19080057488631014,"score_spread":0.1787767471082513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517486838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016896416,0.001206894,0.9663224,0.000006748027,0.008547329,0.00058054994,0.00014529173,0.0049521634,0.001342186],"genre_scores_gemma":[0.88783926,0.0004453095,0.10981108,0.00003148678,0.00041657203,0.0001794628,0.000005956304,0.000519995,0.0007508691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650407,0.000040861218,0.0009246013,0.0007920011,0.00046888329,0.0012695929],"domain_scores_gemma":[0.9980688,0.00022396256,0.000115773924,0.0010052439,0.000109579094,0.00047664426],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023226521,0.0011050025,0.00082472985,0.00063760707,0.0002669507,0.0000760389,0.0005446761,0.0005796431,0.0006444353],"category_scores_gemma":[0.000027570957,0.0012783664,0.00050006015,0.00081545435,0.000046484914,0.0005367537,0.0000046947825,0.0011949034,0.0007946764],"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":[0.00004946009,0.0003527522,0.00002592809,0.0014145885,0.0009586238,0.00014442939,0.0050785746,0.9765253,0.0014339669,0.00027145282,0.00011110422,0.013633831],"study_design_scores_gemma":[0.0025401611,0.00055518374,0.0006791625,0.0021664626,0.0007385636,0.00035433506,0.0006690933,0.92904216,0.0427829,0.00007405859,0.015892362,0.004505576],"about_ca_topic_score_codex":0.0000801054,"about_ca_topic_score_gemma":0.000012133074,"teacher_disagreement_score":0.87094283,"about_ca_system_score_codex":0.00051013584,"about_ca_system_score_gemma":0.000047069003,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W2530596726","doi":"10.1109/tse.2017.2671865","title":"Measuring the Impact of Code Dependencies on Software Architecture Recovery Techniques","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":86,"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; Ontario Ministry of Research, Innovation and Science; National Science Foundation","keywords":"Computer science; Granularity; Architecture; Software; Software architecture; Software architecture description; Implementation; Reference architecture; Graph; Code (set theory); Distributed computing; Software engineering; Theoretical computer science; Programming language","score_opus":0.027883247811874713,"score_gpt":0.27180466622482546,"score_spread":0.24392141841295076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530596726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051819388,0.00006962892,0.94563305,0.000058175425,0.000623576,0.00034263695,0.00005455071,0.0013816471,0.000017332612],"genre_scores_gemma":[0.8970051,0.000038494483,0.10257242,0.000015348563,0.00008381834,0.000113904636,0.0000010589237,0.0000731476,0.000096744894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977251,0.00004720876,0.00034071837,0.00052981236,0.00075557904,0.0006015318],"domain_scores_gemma":[0.99587595,0.0014132751,0.00013932156,0.0022423435,0.0001634804,0.00016562644],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053300953,0.00041538593,0.00036443435,0.000476551,0.00058150664,0.0003494449,0.002403043,0.00018063675,0.000015808753],"category_scores_gemma":[0.0010446681,0.00031920205,0.0004256678,0.00033496914,0.00009261843,0.00054408156,0.000030744464,0.0010309747,0.000025580659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035596197,0.00008631419,0.000536146,0.000078783494,0.0001702975,0.000025103522,0.00030041614,0.93534434,0.0016248456,0.00003334404,0.00010071159,0.06166412],"study_design_scores_gemma":[0.0018663207,0.003080876,0.09742565,0.0030101642,0.000120936566,0.00046895395,0.000043340337,0.048316106,0.8405192,0.001091621,0.0007654407,0.0032913946],"about_ca_topic_score_codex":0.00013640842,"about_ca_topic_score_gemma":0.000015989894,"teacher_disagreement_score":0.8870282,"about_ca_system_score_codex":0.00029830227,"about_ca_system_score_gemma":0.00015150788,"threshold_uncertainty_score":0.99992603},"labels":[],"label_agreement":null},{"id":"W2530824252","doi":"10.1109/tse.2016.2616306","title":"A Framework for Evaluating the Results of the SZZ Approach for Identifying Bug-Introducing Changes","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":190,"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; Queen's University; McGill University","funders":"","keywords":"Implementation; Computer science; Task (project management); Software bug; Software implementation; Software; Software engineering; Programming language; Systems engineering","score_opus":0.07051700283867052,"score_gpt":0.3266203963305439,"score_spread":0.2561033934918734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530824252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004667803,0.000082873165,0.9914617,0.00066502066,0.0015635892,0.0010431311,0.00006781726,0.00044698437,0.0000010777034],"genre_scores_gemma":[0.50612706,0.000006554711,0.49290648,0.00002240727,0.00014878498,0.00063920964,5.7003604e-7,0.00004280135,0.00010614648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980446,0.000047935617,0.00034269178,0.0005311647,0.0005154744,0.0005181143],"domain_scores_gemma":[0.99088633,0.0075813294,0.00010837185,0.0011410372,0.00021462269,0.00006831199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014415777,0.00022977755,0.00022752672,0.00018852926,0.0003369165,0.00009435783,0.0012229889,0.000117301606,0.000001877041],"category_scores_gemma":[0.0031797967,0.00013491808,0.00023124306,0.00064888335,0.00004602055,0.00020911456,0.000017284538,0.00030365065,0.0000017101363],"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":[0.00012993262,0.00010707758,0.000054487016,0.00056056597,0.00021227481,4.9159706e-7,0.0020184324,0.86178946,0.021963134,0.0017340505,0.0002008449,0.11122925],"study_design_scores_gemma":[0.002674009,0.00066227105,0.0011265711,0.0014965186,0.00010646742,0.00002780169,0.00009754912,0.66554004,0.32575032,0.0009617663,0.0007490365,0.00080765964],"about_ca_topic_score_codex":0.0000075715284,"about_ca_topic_score_gemma":0.0000019589652,"teacher_disagreement_score":0.50145924,"about_ca_system_score_codex":0.00014209574,"about_ca_system_score_gemma":0.000070659575,"threshold_uncertainty_score":0.55017996},"labels":[],"label_agreement":null},{"id":"W2579161546","doi":"10.1109/tse.2017.2654244","title":"Using Natural Language Processing to Automatically Detect Self-Admitted Technical Debt","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":220,"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":"Technical debt; Computer science; Debt; Quality (philosophy); Bad debt; Code (set theory); Finance; Software development; Business; Software; Programming language; Set (abstract data type)","score_opus":0.016474308440274747,"score_gpt":0.29079089578154826,"score_spread":0.2743165873412735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579161546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08798596,0.00009536758,0.9067763,0.00006335347,0.0007876182,0.00030722166,0.000004036925,0.0039719907,0.000008159311],"genre_scores_gemma":[0.5739614,0.0000012199744,0.42584834,0.00002890352,0.00004797145,0.000042771433,2.1800585e-7,0.00004429615,0.000024917224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776185,0.00002291046,0.00031166495,0.0005905143,0.000610117,0.00070293597],"domain_scores_gemma":[0.9977298,0.0004289049,0.0000615068,0.0013268255,0.0001218495,0.00033112417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003114274,0.0003404778,0.0002975339,0.0004576987,0.0005745204,0.00067314506,0.0016559747,0.00015780109,0.00000997057],"category_scores_gemma":[0.0006496295,0.00035439432,0.00013916216,0.0005112952,0.000029710483,0.0007875952,0.000032752192,0.0007480875,0.000063702995],"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":[0.000041401785,0.00031399264,0.0005875853,0.0006197973,0.00020692633,0.00051603734,0.0019178475,0.5819237,0.07366839,0.00009364095,0.00008710389,0.34002355],"study_design_scores_gemma":[0.00044534443,0.00010939905,0.008917673,0.00038113783,0.000027472515,0.00019098348,0.000007772595,0.9474352,0.041650254,0.0000071454297,0.000111359055,0.00071624666],"about_ca_topic_score_codex":0.000023817927,"about_ca_topic_score_gemma":0.0000072036396,"teacher_disagreement_score":0.4859754,"about_ca_system_score_codex":0.00034898007,"about_ca_system_score_gemma":0.00013726766,"threshold_uncertainty_score":0.9998908},"labels":[],"label_agreement":null},{"id":"W2754109047","doi":"10.1109/tse.2017.2750682","title":"Expanding Queries for Code Search Using Semantically Related API Class-names","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":50,"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; Identifier; Programming language; Class (philosophy); Information retrieval; Natural language; Java; Code (set theory); Natural language user interface; World Wide Web; Natural language processing; Artificial intelligence","score_opus":0.039927966108913644,"score_gpt":0.30923921623353773,"score_spread":0.2693112501246241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754109047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096984975,0.000052611784,0.8994897,0.0001318651,0.0015358853,0.00039153505,0.000027306172,0.0013769933,0.000009124822],"genre_scores_gemma":[0.77491367,0.000016995347,0.2246003,0.000013525115,0.0000646756,0.00008214213,0.0000013533619,0.00007986002,0.00022746065],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976071,0.000026852887,0.00037044994,0.00064825447,0.0005324103,0.00081493735],"domain_scores_gemma":[0.99687773,0.0012594647,0.00006882782,0.0013613844,0.00018471834,0.0002478672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054170925,0.00034029942,0.00034875263,0.00044352235,0.0009667573,0.00069989805,0.001364867,0.00020860168,0.000016689337],"category_scores_gemma":[0.0006262621,0.00037432372,0.00021643972,0.00029804945,0.000093417075,0.0010390223,0.000024503903,0.0006311646,0.000025412213],"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":[0.00003617348,0.00011103796,0.0012470104,0.00033692963,0.00023587645,0.0000637339,0.0009453671,0.9721352,0.0101693375,0.0016402741,0.00006136446,0.013017718],"study_design_scores_gemma":[0.0010810735,0.0001927361,0.0027806002,0.00043998644,0.000038347833,0.000092114584,0.00003270604,0.91389203,0.07991841,0.00010503393,0.0005947493,0.00083220424],"about_ca_topic_score_codex":0.0000310496,"about_ca_topic_score_gemma":0.0000048784004,"teacher_disagreement_score":0.6779287,"about_ca_system_score_codex":0.0002591216,"about_ca_system_score_gemma":0.00013174601,"threshold_uncertainty_score":0.9998709},"labels":[],"label_agreement":null},{"id":"W2757354086","doi":"10.1109/tse.2017.2756043","title":"A Study of Social Interactions in Open Source Component Use","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Open Source Software Innovations","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":"Component (thermodynamics); Computer science; Open source; Java; Component-based software engineering; World Wide Web; Data science; Software; Software engineering; Software development; Programming language","score_opus":0.05336126301455479,"score_gpt":0.3085463286686244,"score_spread":0.2551850656540696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757354086","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":[0.36467415,7.298422e-7,0.6341883,0.000069233785,0.00048995967,0.00037754132,0.000008064926,0.00017141113,0.000020596552],"genre_scores_gemma":[0.96418244,5.318895e-7,0.035369046,0.000022106238,0.000022468685,0.00013723626,8.505396e-7,0.000030093437,0.00023521192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9985847,0.000044264154,0.00044460953,0.00039228608,0.0002752181,0.0002589502],"domain_scores_gemma":[0.99833053,0.0002589005,0.00018878354,0.0010443651,0.00011752392,0.000059866325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024105646,0.00019958855,0.00030515285,0.00041852545,0.0005696103,0.0006944351,0.0019447308,0.000048601418,0.000019088713],"category_scores_gemma":[0.00008483757,0.0002298781,0.00007723474,0.0004392315,0.000033480952,0.0020494568,0.000055655877,0.00044703842,0.000017135111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010573241,0.007675548,0.022472244,0.00008522531,0.0004904698,0.000121552664,0.03473357,0.86441463,0.0016266733,0.0024538208,0.00035172416,0.06546879],"study_design_scores_gemma":[0.011638438,0.001122326,0.79213256,0.00078318134,0.00015544957,0.00012296451,0.0032096796,0.16585955,0.011948276,0.00011645662,0.0100238435,0.0028873035],"about_ca_topic_score_codex":0.0007863556,"about_ca_topic_score_gemma":0.00039718373,"teacher_disagreement_score":0.7696603,"about_ca_system_score_codex":0.00013322089,"about_ca_system_score_gemma":0.00004775962,"threshold_uncertainty_score":0.9374157},"labels":[],"label_agreement":null},{"id":"W2757935660","doi":"10.1109/tse.2017.2755005","title":"Revisiting the Performance Evaluation of Automated Approaches for the Retrieval of Duplicate Issue Reports","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"","keywords":"Computer science; Information retrieval; Eclipse; Categorical variable; Software; Notation; Data mining; Machine learning; Programming language","score_opus":0.059809278371222435,"score_gpt":0.29953603310299953,"score_spread":0.2397267547317771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757935660","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":[0.13033177,0.00015781753,0.86778986,0.00016911671,0.00058431015,0.00058236765,0.0000054367556,0.00037521488,0.000004085429],"genre_scores_gemma":[0.98161024,0.000022072301,0.018092157,0.0000034539353,0.00008177593,0.00013594238,7.192915e-7,0.000025017718,0.000028615095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983641,0.00003108786,0.00038166484,0.00028165843,0.0006910512,0.00025047464],"domain_scores_gemma":[0.99633396,0.0014668679,0.00024003038,0.0015794478,0.00033941388,0.0000403031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026067821,0.00015389948,0.00019654751,0.00011352407,0.00043289704,0.000100472964,0.0009705554,0.00006945519,0.000005181417],"category_scores_gemma":[0.001232031,0.0001089399,0.00012637461,0.00027488326,0.00006984731,0.00033543218,0.000012789663,0.00024628657,0.0000018524313],"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":[0.000008937129,0.000014481735,0.00023651749,0.00014864332,0.00007031999,6.546788e-7,0.0002441562,0.9342889,0.0007511694,0.000027203876,0.00001674759,0.064192235],"study_design_scores_gemma":[0.00018323965,0.000036217265,0.01487548,0.00013111865,0.00004699894,0.000017119843,0.000009287509,0.9140632,0.070408255,0.0000049353052,0.00011828241,0.00010583566],"about_ca_topic_score_codex":0.000012715577,"about_ca_topic_score_gemma":3.5035623e-7,"teacher_disagreement_score":0.8512785,"about_ca_system_score_codex":0.000071686874,"about_ca_system_score_gemma":0.00009113093,"threshold_uncertainty_score":0.44424403},"labels":[],"label_agreement":null},{"id":"W2760127551","doi":"10.1109/tse.2017.2757480","title":"On the Use of Hidden Markov Model to Predict the Time to Fix Bugs","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Hidden Markov model; Software bug; Software regression; Context (archaeology); Software; Markov model; Predictive modelling; Data mining; Software engineering; Software development; Markov chain; Data science; Software quality; Machine learning; Artificial intelligence; Programming language","score_opus":0.03385569789076816,"score_gpt":0.2492526278261282,"score_spread":0.21539692993536003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760127551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043209285,0.000005486452,0.95405465,0.0012570227,0.00042065993,0.0004994829,0.000044549426,0.00049631804,0.000012519115],"genre_scores_gemma":[0.8648068,0.0000039189986,0.13271707,0.00030972727,0.00005482607,0.0002357885,4.6868183e-7,0.000065214364,0.0018062172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982593,0.000029092256,0.00023546434,0.00040085881,0.0006343971,0.00044089227],"domain_scores_gemma":[0.9951444,0.002238317,0.000044641783,0.0022597248,0.00011162191,0.00020127067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037495143,0.00024799453,0.00020365714,0.00024724475,0.00040906313,0.00034872247,0.0022194525,0.00007970109,0.000046633668],"category_scores_gemma":[0.00101434,0.00017557632,0.0001341188,0.00035672064,0.000037496695,0.0003827492,0.00003700428,0.00046294808,0.0002694891],"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":[0.000016326818,0.000035303503,0.000018570352,0.000014924617,0.00004315349,0.0000042112406,0.00032913798,0.98021096,0.0005749994,0.00009932994,0.0029416739,0.015711425],"study_design_scores_gemma":[0.00019405501,0.00019239499,0.002351719,0.00020746278,0.000014732752,0.00000824494,0.000002443018,0.9846115,0.010601271,0.000025816706,0.0014611897,0.00032916592],"about_ca_topic_score_codex":0.000032273416,"about_ca_topic_score_gemma":0.0000026261148,"teacher_disagreement_score":0.8215975,"about_ca_system_score_codex":0.000109305416,"about_ca_system_score_gemma":0.00006197169,"threshold_uncertainty_score":0.71597946},"labels":[],"label_agreement":null},{"id":"W2793823312","doi":"10.1109/tse.2018.2810895","title":"Asymmetric Release Planning: Compromising Satisfaction against Dissatisfaction","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Computer science; Completeness (order theory); Categorical variable; Feature (linguistics); Customer satisfaction; Stakeholder; Product (mathematics); Quality (philosophy); Process management; Operations research; Machine learning; Marketing; Mathematics; Business","score_opus":0.016881603055118155,"score_gpt":0.25352717358529264,"score_spread":0.2366455705301745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793823312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032644585,0.00008162581,0.96064186,0.00004552879,0.0023436556,0.00020649676,0.0000070192473,0.0039576194,0.000071622904],"genre_scores_gemma":[0.7323624,0.00003152034,0.26727068,0.00007403568,0.00014432221,0.000037897997,0.0000016372994,0.000043365926,0.00003415685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982891,0.000038921557,0.00033721846,0.00052448356,0.00038559453,0.00042465204],"domain_scores_gemma":[0.99847555,0.00047354147,0.0001083338,0.0006437895,0.0001130871,0.00018572567],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024851214,0.00032830937,0.00023491237,0.00066658045,0.0003388153,0.00023729072,0.000376395,0.00016891623,0.000021069778],"category_scores_gemma":[0.00011610439,0.00036180633,0.00012458004,0.0011947106,0.000031068197,0.0011653214,0.0000064697247,0.00054449966,0.00007968589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054156244,0.00012775123,0.0011366303,0.00010401059,0.00015502746,0.00005496527,0.0005712269,0.41429773,0.0027964085,0.00056504045,0.00086165906,0.57927537],"study_design_scores_gemma":[0.0011881461,0.00096332905,0.029842395,0.0006126515,0.00008923344,0.00020939685,0.000028283797,0.8148505,0.13399775,0.00017678596,0.016014347,0.00202716],"about_ca_topic_score_codex":0.000052805884,"about_ca_topic_score_gemma":0.00000331717,"teacher_disagreement_score":0.6997178,"about_ca_system_score_codex":0.00021367148,"about_ca_system_score_gemma":0.000039740207,"threshold_uncertainty_score":0.9998834},"labels":[],"label_agreement":null},{"id":"W2799550433","doi":"10.1109/tse.2018.2829722","title":"Integrative Double Kaizen Loop (IDKL): Towards a Culture of Continuous Learning and Sustainable Improvements for Software Organizations","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","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 Alberta","funders":"","keywords":"Kaizen; Computer science; Software deployment; Process management; Productivity; Process (computing); Lean manufacturing; Workforce; Knowledge management; Operations management; Software engineering; Engineering","score_opus":0.007300316526246086,"score_gpt":0.24891636095248693,"score_spread":0.24161604442624085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799550433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028732687,0.00012683282,0.9946286,0.00003035001,0.0003966166,0.00054163055,0.000018635757,0.0013639681,0.000020090345],"genre_scores_gemma":[0.38246712,0.00006886678,0.61564904,0.00003267314,0.00006758358,0.000184371,0.0000064631154,0.00006008357,0.0014637879],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986776,0.000019325103,0.00029092698,0.0003991686,0.00019730128,0.0004156455],"domain_scores_gemma":[0.9983794,0.00026243838,0.00011665742,0.00029736978,0.00083574007,0.00010838753],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002580301,0.00028078674,0.0002962635,0.00025122415,0.00030319102,0.00014538053,0.00035928842,0.00015045593,0.00001828933],"category_scores_gemma":[0.00034246827,0.00026657447,0.00007422839,0.0009293605,0.000048501875,0.0006909073,0.000017760922,0.000332434,0.0000028657373],"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":[0.001341662,0.002492139,0.0025700987,0.0054700864,0.0044670077,0.0001343194,0.08205369,0.2263454,0.03734149,0.047000762,0.007820497,0.5829629],"study_design_scores_gemma":[0.0077031404,0.008151406,0.0004217099,0.001211461,0.0005908477,0.00020820533,0.0027233032,0.17968796,0.7195861,0.0017565589,0.07443751,0.0035218378],"about_ca_topic_score_codex":0.000076899356,"about_ca_topic_score_gemma":0.0000037318932,"teacher_disagreement_score":0.68224454,"about_ca_system_score_codex":0.00009159081,"about_ca_system_score_gemma":0.00009682415,"threshold_uncertainty_score":0.99997866},"labels":[],"label_agreement":null},{"id":"W2803395207","doi":"10.1109/tse.2018.2838131","title":"Use and Misuse of Continuous Integration Features: An Empirical Study of Projects That (Mis)Use Travis CI","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":77,"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; Software deployment; Feature (linguistics); Software; Source code; Code (set theory); Software engineering; Programming language","score_opus":0.05555397349595297,"score_gpt":0.30736840377452834,"score_spread":0.25181443027857536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803395207","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":[0.50107473,0.000009387364,0.4981999,0.0000044520903,0.0001792178,0.0002637944,0.000011654257,0.00025657157,2.933436e-7],"genre_scores_gemma":[0.95537186,0.000008825227,0.044467345,0.000009200633,0.000030094776,0.000038002494,0.000001634674,0.000038284546,0.000034751392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9983541,0.00006903851,0.00031998134,0.0004646243,0.00048744318,0.0003048241],"domain_scores_gemma":[0.9977973,0.0009907141,0.00006911601,0.00071012747,0.0002764522,0.00015625334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002465663,0.00025406675,0.0003293353,0.00052885094,0.000077933735,0.00015042904,0.00040944162,0.00012823488,0.0000049917326],"category_scores_gemma":[0.0003404942,0.00024408624,0.00006879495,0.0006990136,0.00008098253,0.0010401295,0.0000070454266,0.0003727455,0.0000018822961],"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":[0.001063226,0.012398689,0.23705314,0.0015196173,0.0016834537,0.00028640527,0.20614417,0.29020828,0.060135245,0.00017796588,0.0009102443,0.18841957],"study_design_scores_gemma":[0.0036950302,0.008764592,0.50096154,0.0007844088,0.00016371728,0.00014030946,0.0019826298,0.14232658,0.33947912,0.000010537494,0.0001890089,0.0015025357],"about_ca_topic_score_codex":0.00020833661,"about_ca_topic_score_gemma":0.00007355481,"teacher_disagreement_score":0.45429716,"about_ca_system_score_codex":0.00006053942,"about_ca_system_score_gemma":0.00005282797,"threshold_uncertainty_score":0.99535483},"labels":[],"label_agreement":null},{"id":"W2803893519","doi":"10.1109/tse.2018.2836450","title":"Automatically Categorizing Software Technologies","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"McGill University","funders":"","keywords":"Computer science; Categorization; Software; Taxonomy (biology); Domain (mathematical analysis); Phrase; Software engineering; Programming language; Natural language processing; Artificial intelligence","score_opus":0.013858434838389265,"score_gpt":0.24211322902831106,"score_spread":0.22825479418992178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803893519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009862662,0.000074539734,0.9729411,0.000121048826,0.0016561319,0.00023429592,0.0000073701403,0.015088635,0.000014240973],"genre_scores_gemma":[0.593047,0.0000101354135,0.40658382,0.00003270005,0.0000689871,0.000096209034,6.5381874e-7,0.000056937046,0.000103502345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997529,0.00002230172,0.0003592404,0.0006663765,0.00060884503,0.0008142408],"domain_scores_gemma":[0.9973199,0.0010677831,0.000043797303,0.0011959904,0.00020374403,0.0001688012],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002859925,0.00038080857,0.0002980381,0.00070309034,0.00028961475,0.00023773935,0.0014000318,0.00023943504,0.000040322055],"category_scores_gemma":[0.0007272593,0.0003958175,0.00014565335,0.001424613,0.000109740926,0.00063178357,0.00002287717,0.0006962441,0.0004459377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047618254,0.0006571848,0.0018393294,0.00069440535,0.00061036844,0.00035659008,0.0025577804,0.29017138,0.007950512,0.005056173,0.0022904912,0.68776816],"study_design_scores_gemma":[0.0018902081,0.0016088824,0.005512482,0.0008749799,0.000077305696,0.00047553383,0.0001175934,0.54566365,0.42847794,0.0011492249,0.0105090225,0.0036431497],"about_ca_topic_score_codex":0.000011506271,"about_ca_topic_score_gemma":0.000002756585,"teacher_disagreement_score":0.684125,"about_ca_system_score_codex":0.00026100362,"about_ca_system_score_gemma":0.00011219609,"threshold_uncertainty_score":0.9998494},"labels":[],"label_agreement":null},{"id":"W2885308680","doi":"10.1109/tse.2018.2861735","title":"Leveraging Historical Associations between Requirements and Source Code to Identify Impacted Classes","year":2018,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"McGill University","funders":"National Science Foundation","keywords":"Computer science; Set (abstract data type); Class (philosophy); Code smell; Intuition; Similarity (geometry); Semantic similarity; Source code; Data mining; Locality; Software; Information retrieval; Artificial intelligence; Software development; Software quality; Programming language","score_opus":0.05722962105556756,"score_gpt":0.32059560617191873,"score_spread":0.2633659851163512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885308680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117285065,0.00008930782,0.87693965,0.0001879436,0.0026067311,0.0004566318,0.000112210015,0.0023194598,0.0000030020028],"genre_scores_gemma":[0.8679714,0.000027553335,0.13084832,0.000056752735,0.00041493218,0.00017160922,0.00001932622,0.00014689266,0.00034318477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9962863,0.00007553498,0.00063141977,0.001162076,0.0009978495,0.0008468657],"domain_scores_gemma":[0.9963616,0.0014735764,0.00013405085,0.0011741351,0.00029088516,0.0005657518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000611505,0.0005948015,0.0006518176,0.0011259784,0.00031598556,0.00057251385,0.001261489,0.0004624808,0.000014911786],"category_scores_gemma":[0.00076936785,0.0007248829,0.00021429882,0.0008846544,0.000026370493,0.00041167473,0.00011646023,0.0015671519,0.00006452099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001764161,0.00023963932,0.01646167,0.00058949855,0.0011335246,0.000050397128,0.0038372024,0.9439356,0.0012774806,0.000015729944,0.0045992257,0.027842391],"study_design_scores_gemma":[0.0039178045,0.0014711122,0.64513916,0.0053535327,0.00094646367,0.00010906876,0.00006633629,0.26741916,0.036550697,0.0005116324,0.027768606,0.010746431],"about_ca_topic_score_codex":0.00017250872,"about_ca_topic_score_gemma":0.000008046773,"teacher_disagreement_score":0.75068635,"about_ca_system_score_codex":0.0026670108,"about_ca_system_score_gemma":0.00020308577,"threshold_uncertainty_score":0.99952024},"labels":[],"label_agreement":null},{"id":"W2904680236","doi":"10.1109/tse.2018.2884911","title":"A Study of Feature Scattering in the Linux Kernel","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","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 Waterloo","funders":"Vetenskapsrådet; Deutsche Forschungsgemeinschaft","keywords":"Code refactoring; Computer science; Feature (linguistics); Kernel (algebra); Code (set theory); Scattering; Software; Source code; Computer engineering; Operating system; Programming language; Optics; Physics; Set (abstract data type)","score_opus":0.033980790524803246,"score_gpt":0.284294568658101,"score_spread":0.25031377813329775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904680236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13952272,0.000031208256,0.85884106,0.000037168,0.0008036417,0.00025042877,0.0000022080228,0.0005066634,0.000004873871],"genre_scores_gemma":[0.7102443,0.000003596876,0.28957772,0.00003176751,0.000044786117,0.000060009068,1.1621799e-7,0.000019345805,0.000018351582],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871093,0.000079551726,0.0002530338,0.00034974315,0.00029919896,0.0003075242],"domain_scores_gemma":[0.9982719,0.00079992396,0.000050548388,0.0007766337,0.000060756473,0.000040283063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045019752,0.00022126421,0.00024161386,0.00031818877,0.00008607262,0.000044157914,0.0009375027,0.00008177967,0.0000028476338],"category_scores_gemma":[0.00012861355,0.00018480862,0.00007006247,0.00084058463,0.00003748793,0.00030140567,0.000008597694,0.00046206827,0.000008122902],"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":[0.000010863842,0.00023808406,0.00013341758,0.000036209865,0.00003451834,0.000030821906,0.007862787,0.9761752,0.00084284233,0.00007934535,0.000022778104,0.014533128],"study_design_scores_gemma":[0.016283136,0.016640846,0.15626886,0.0031905838,0.00040391003,0.0013559988,0.0114976335,0.4298736,0.3485219,0.0029308833,0.0036839226,0.009348734],"about_ca_topic_score_codex":0.000014457649,"about_ca_topic_score_gemma":0.000015368243,"teacher_disagreement_score":0.57072157,"about_ca_system_score_codex":0.000059143913,"about_ca_system_score_gemma":0.000019412448,"threshold_uncertainty_score":0.7536277},"labels":[],"label_agreement":null},{"id":"W2909172538","doi":"10.1109/tse.2019.2891758","title":"The Impact of Correlated Metrics on the Interpretation of Defect Models","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"Australian Research Council","keywords":"Consistency (knowledge bases); Ranking (information retrieval); Interpretation (philosophy); Computer science; Metric (unit); Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics; Programming language","score_opus":0.014277181931630203,"score_gpt":0.2477259451862916,"score_spread":0.2334487632546614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909172538","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":[0.18962926,0.00007837362,0.80931515,0.000012219197,0.000491519,0.00024732077,0.000007930679,0.00020278915,0.000015466838],"genre_scores_gemma":[0.99628,0.000026485104,0.0035794855,0.000004358802,0.000006544725,0.000028082037,4.5779706e-7,0.00002675548,0.00004784348],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987307,0.00004848371,0.0002847062,0.0002167602,0.00045376847,0.00026555825],"domain_scores_gemma":[0.9935035,0.0054487027,0.00007557564,0.0007644931,0.00015237999,0.000055342094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004765686,0.00017628202,0.00019446696,0.00035205815,0.00007234103,0.000048202142,0.0007616205,0.00007854841,0.000010923706],"category_scores_gemma":[0.00031862746,0.000110585264,0.00030210053,0.0013060686,0.000027807486,0.00023342675,0.000006554667,0.00045182306,0.000020878062],"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":[0.000021314449,0.000034898476,0.000124693,0.000020426853,0.0001161587,5.844882e-7,0.00028354625,0.9922028,0.0004010091,0.00043937928,0.000019213507,0.0063359686],"study_design_scores_gemma":[0.00017173182,0.00029196538,0.0010414744,0.00009966643,0.000009291133,0.0000042204097,0.000008951563,0.9875055,0.01069144,0.00005886351,0.000005087831,0.00011178455],"about_ca_topic_score_codex":0.00003851951,"about_ca_topic_score_gemma":6.735598e-7,"teacher_disagreement_score":0.8066507,"about_ca_system_score_codex":0.00014923532,"about_ca_system_score_gemma":0.00006818798,"threshold_uncertainty_score":0.4509536},"labels":[],"label_agreement":null},{"id":"W2909755202","doi":"10.1109/tse.2019.2893171","title":"Too Many User-Reviews! What Should App Developers Look at First?","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":86,"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":"Polytechnique Montréal","keywords":"Key (lock); Computer science; Android (operating system); Mobile apps; World Wide Web; App store; Set (abstract data type); Android app; Star (game theory); Mobile device; Multimedia; Computer security","score_opus":0.023871746814439637,"score_gpt":0.2479435287887195,"score_spread":0.22407178197427988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909755202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024598908,0.0010066597,0.9680219,0.00023233348,0.0034283882,0.00065582676,0.000005854711,0.0020368004,0.000013291502],"genre_scores_gemma":[0.64823955,0.0027961007,0.33175123,0.0009950144,0.00022863444,0.0008303535,0.000010712994,0.00038221374,0.01476621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971682,0.000032956556,0.0004479049,0.00082920433,0.0006923667,0.00082941056],"domain_scores_gemma":[0.99731505,0.0009132207,0.000053329393,0.0013186319,0.00009370307,0.000306082],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042161858,0.00048236715,0.0004625597,0.00048583708,0.00019742006,0.00037376038,0.0012563207,0.0002118927,0.00024343416],"category_scores_gemma":[0.000111693575,0.0004961715,0.0002579628,0.0010281245,0.00002651982,0.0016230855,0.000029476563,0.0006960617,0.002399477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024397477,0.00014935619,0.0013289215,0.00063042046,0.00017026979,0.00006622896,0.0010462163,0.9350082,0.0011113666,0.00022733737,0.0032292302,0.057008054],"study_design_scores_gemma":[0.0029118713,0.00057934434,0.008008819,0.0025718384,0.000085708874,0.0003486542,0.000092843045,0.21209714,0.065920874,0.000019616458,0.70303935,0.0043239654],"about_ca_topic_score_codex":0.000013025967,"about_ca_topic_score_gemma":0.000007579325,"teacher_disagreement_score":0.72291106,"about_ca_system_score_codex":0.00059641886,"about_ca_system_score_gemma":0.00007609196,"threshold_uncertainty_score":0.999749},"labels":[],"label_agreement":null},{"id":"W2914489208","doi":"10.1109/tse.2019.2897300","title":"Which Commits Can Be CI Skipped?","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Concordia University","funders":"","keywords":"Commit; Computer science; Process (computing); Java; Software engineering; Database; Programming language","score_opus":0.012768036516850528,"score_gpt":0.2325881247438001,"score_spread":0.2198200882269496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914489208","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":[0.07099088,0.0000370011,0.92418486,0.00026897,0.0019343862,0.00029377904,0.000027071534,0.0022158695,0.000047151538],"genre_scores_gemma":[0.95023346,0.000014086321,0.048788875,0.00011068737,0.000054819153,0.000074513264,0.000002889748,0.000075176315,0.0006455001],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977489,0.000029342787,0.0002792378,0.00059983786,0.00064701936,0.000695644],"domain_scores_gemma":[0.9974179,0.0009613012,0.00003303606,0.0011672046,0.00015276695,0.0002677825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025772364,0.00033551865,0.00028925552,0.0004910098,0.000121622565,0.00016856742,0.0010536674,0.00016063712,0.00012872156],"category_scores_gemma":[0.00013406207,0.0003717973,0.00013184622,0.0013383994,0.000014339957,0.00039368984,0.000012201926,0.0007838575,0.00039457803],"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":[0.000009254141,0.00013196719,0.0017968148,0.00015994384,0.00011265494,0.000023610899,0.00051232165,0.9851211,0.0020171576,0.0003992648,0.00047674956,0.009239188],"study_design_scores_gemma":[0.0035906069,0.0009713472,0.020501487,0.0007460045,0.00006424951,0.0003067097,0.000065018554,0.78888756,0.15402526,0.000072300056,0.026974626,0.0037948228],"about_ca_topic_score_codex":0.00004058128,"about_ca_topic_score_gemma":0.000022665416,"teacher_disagreement_score":0.87924254,"about_ca_system_score_codex":0.00022806032,"about_ca_system_score_gemma":0.00010983937,"threshold_uncertainty_score":0.9998734},"labels":[],"label_agreement":null},{"id":"W2940499664","doi":"10.1109/tse.2019.2912962","title":"The Mutation and Injection Framework: Evaluating Clone Detection Tools with Mutation Analysis","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"clone (Java method); Computer science; Java; Benchmark (surveying); Mutation; Precision and recall; Mutation testing; Programming language; Data mining; Artificial intelligence; Genetics; Biology; Gene","score_opus":0.014663928079709844,"score_gpt":0.26347687219838184,"score_spread":0.248812944118672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940499664","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":[0.35515434,0.00004035121,0.6436356,0.000020683365,0.00038381704,0.00024389986,0.0000018127097,0.0005180746,0.0000014328946],"genre_scores_gemma":[0.93643636,0.000012393133,0.063304804,0.000011699975,0.000030650448,0.00012113467,0.000001937094,0.00002998143,0.000051024545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834234,0.00005773522,0.00024326524,0.00044800725,0.0005724802,0.00033617284],"domain_scores_gemma":[0.99661607,0.0025556213,0.000068527996,0.0005056005,0.00016589517,0.000088265784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005646098,0.00020859885,0.00018270523,0.0005151419,0.00032657568,0.00040904176,0.00024231979,0.00011481587,0.000007961732],"category_scores_gemma":[0.0002963447,0.00017559176,0.0000842795,0.0020292725,0.000022228382,0.00076182274,0.0000047349154,0.0005155924,0.000023134744],"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":[0.000018338307,0.000013308316,0.0004317987,0.000024806846,0.0001865429,0.0000047580274,0.00033232916,0.8906045,0.0004920451,0.000059403013,4.03956e-7,0.10783175],"study_design_scores_gemma":[0.00036475412,0.00051365764,0.02078946,0.000070787326,0.000116974115,0.000095959535,0.000063046384,0.96731156,0.010296298,0.000050084265,0.000019282594,0.00030813852],"about_ca_topic_score_codex":0.000028707513,"about_ca_topic_score_gemma":0.000017893546,"teacher_disagreement_score":0.581282,"about_ca_system_score_codex":0.00018585361,"about_ca_system_score_gemma":0.0000396551,"threshold_uncertainty_score":0.7160424},"labels":[],"label_agreement":null},{"id":"W2946233956","doi":"10.1109/tse.2019.2918520","title":"Characterizing Crowds to Better Optimize Worker Recommendation in Crowdsourced Testing","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"York University","funders":"National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Crowds; Crowdsourcing; Task (project management); Context (archaeology); Software bug; Relevance (law); Test (biology); Machine learning; Software; Data science; Computer security; World Wide Web; Engineering","score_opus":0.01883341979320734,"score_gpt":0.24014374368048746,"score_spread":0.2213103238872801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946233956","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":[0.28742594,0.000005048821,0.7101633,0.00020423609,0.00096774177,0.0003144034,0.000003979471,0.00089814723,0.000017231578],"genre_scores_gemma":[0.721045,0.000001478677,0.2783916,0.00023297753,0.0000503746,0.00012005063,0.0000020561586,0.000060832695,0.00009560864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791145,0.000036731315,0.00038924426,0.0006423721,0.00034397724,0.00067621097],"domain_scores_gemma":[0.9977195,0.001313503,0.00004176852,0.0006379824,0.00008392373,0.00020328553],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043504342,0.0003115529,0.00029019028,0.0008795836,0.000079001446,0.00022486405,0.0006213834,0.00013359345,0.000101305435],"category_scores_gemma":[0.00027106036,0.00036350262,0.00008877985,0.0017003573,0.000007510534,0.0006911882,0.000016358556,0.00069252704,0.00036188803],"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":[0.00001702829,0.00006637619,0.0051583904,0.000055991004,0.000027275428,0.000016636115,0.00056357484,0.91944075,0.012029872,0.000007105806,0.000035103447,0.0625819],"study_design_scores_gemma":[0.0021861123,0.00041517182,0.120854594,0.0012071008,0.000015359752,0.000074459036,0.000040104318,0.807573,0.062552884,0.000011373069,0.0031017135,0.0019680923],"about_ca_topic_score_codex":0.000022820988,"about_ca_topic_score_gemma":0.0000017397902,"teacher_disagreement_score":0.43361908,"about_ca_system_score_codex":0.00031804343,"about_ca_system_score_gemma":0.00004422693,"threshold_uncertainty_score":0.9998817},"labels":[],"label_agreement":null},{"id":"W2950127321","doi":"10.1109/tse.2019.2921343","title":"What Do Programmers Discuss About Blockchain? A Case Study on the Use of Balanced LDA and the Reference Architecture of a Domain to Capture Online Discussions About Blockchain Platforms Across Stack Exchange Communities","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Blockchain Technology Applications and Security","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":"Queen's University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Popularity; Domain (mathematical analysis); Blockchain; Stack (abstract data type); Architecture; Data science; World Wide Web; Data mining; Computer security; Operating system","score_opus":0.025508109890508716,"score_gpt":0.259146886751046,"score_spread":0.2336387768605373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950127321","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":[0.62819237,0.00010148406,0.36942768,0.0005641559,0.00012856576,0.001288596,0.00014953173,0.00014722014,4.288418e-7],"genre_scores_gemma":[0.9907961,0.000056038414,0.008442488,0.00010693318,0.000010352441,0.00050752563,0.0000024332478,0.000028436532,0.000049694685],"study_design_codex":"simulation_or_modeling","study_design_gemma":"qualitative","domain_scores_codex":[0.998354,0.00009904586,0.00042552323,0.00038616048,0.00033006587,0.0004051728],"domain_scores_gemma":[0.997082,0.0009705649,0.00014630792,0.0015957399,0.00010453719,0.000100884594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004751317,0.0003416427,0.00044469145,0.00020581813,0.00040419723,0.00014636433,0.0008666875,0.00016603727,0.0000061493856],"category_scores_gemma":[0.000026093017,0.00018407793,0.00012289171,0.00082274555,0.0002582067,0.000115439114,0.000058857215,0.0009685593,0.000001248064],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036484716,0.0022551776,0.0007058323,0.00035463012,0.0005887778,0.000072647636,0.32938516,0.5493177,0.00037572993,0.007462993,0.000020969726,0.109095514],"study_design_scores_gemma":[0.015712632,0.0048734094,0.0072920793,0.0054218606,0.00041299246,0.0016325152,0.58871037,0.3614736,0.00519934,0.0024068994,0.002965147,0.0038991582],"about_ca_topic_score_codex":0.00046781995,"about_ca_topic_score_gemma":0.001519224,"teacher_disagreement_score":0.36260375,"about_ca_system_score_codex":0.000042596086,"about_ca_system_score_gemma":0.00002613267,"threshold_uncertainty_score":0.75064796},"labels":[],"label_agreement":null},{"id":"W2951710749","doi":"10.1109/tse.2019.2924006","title":"Locating Latent Design Information in Developer Discussions: A Study on Pull Requests","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Toronto; Université de Montréal; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Maintainability; Classifier (UML); Documentation; Software engineering; Software design; Machine learning; Software; Robustness (evolution); Source lines of code; Artificial intelligence; Data mining; Software development; Programming language","score_opus":0.021608475185581517,"score_gpt":0.24979844873978285,"score_spread":0.22818997355420134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951710749","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":[0.14977847,0.000009726406,0.84787446,0.000046991703,0.0007095112,0.0007853212,0.0000020232587,0.00078860385,0.0000049060654],"genre_scores_gemma":[0.9357022,0.0000035232054,0.06390392,0.00003970402,0.000013624945,0.00024058853,0.0000011596164,0.000032420503,0.00006283903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980788,0.000070509835,0.0004136089,0.0003852527,0.0005752785,0.0004765364],"domain_scores_gemma":[0.9982188,0.0008550312,0.000043076947,0.0006739296,0.00008318661,0.00012600586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006191518,0.00027540993,0.00023060589,0.00082600914,0.00008203361,0.00016830543,0.0005951493,0.000100047735,0.000017568527],"category_scores_gemma":[0.00024314215,0.00025109175,0.000059285372,0.0011339772,0.000007401381,0.0011991885,0.000010391025,0.0006390987,0.0004082344],"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":[0.000014158972,0.00016205334,0.0022595956,0.000040691502,0.000019473246,0.000013406694,0.0015957127,0.9824625,0.000112935995,0.000035473167,0.000011991947,0.013272004],"study_design_scores_gemma":[0.0031728295,0.001598329,0.13757394,0.0011052847,0.00001809398,0.000046007757,0.00034025687,0.84095424,0.013165872,0.000029990644,0.00033504114,0.0016601007],"about_ca_topic_score_codex":0.000029777577,"about_ca_topic_score_gemma":0.0000033505269,"teacher_disagreement_score":0.7859238,"about_ca_system_score_codex":0.0003791806,"about_ca_system_score_gemma":0.00008830401,"threshold_uncertainty_score":0.99999416},"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":"W2958385005","doi":"10.1109/tse.2019.2927908","title":"Methodological Principles for Reproducible Performance Evaluation in Cloud Computing","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":87,"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":"Electronic Components and Systems for European Leadership; Deutsche Forschungsgemeinschaft; Stiftelsen för Strategisk Forskning; Knowledge Foundation; Oracle; National Science Foundation","keywords":"Cloud computing; Computer science; Data science; Benchmark (surveying); Set (abstract data type); Systematic review; Open research; Domain (mathematical analysis); Field (mathematics); World Wide Web; MEDLINE","score_opus":0.08977160147076024,"score_gpt":0.29942080426299666,"score_spread":0.20964920279223642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958385005","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":[0.41462815,0.000023419221,0.58368653,0.00003866043,0.0009667381,0.00036239365,4.4673143e-7,0.0002676773,0.000025997379],"genre_scores_gemma":[0.7764046,0.000002116761,0.22331594,0.00003372277,0.00006164775,0.00004009936,5.134095e-7,0.000012488211,0.00012884894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848056,0.000071366725,0.00029166116,0.00057398755,0.00028000306,0.00030239671],"domain_scores_gemma":[0.9987148,0.00055955804,0.00005752099,0.0005644802,0.00006140577,0.000042238415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022758609,0.00015369961,0.0002037571,0.00022526544,0.00009413321,0.000055273245,0.00037978846,0.00006522561,0.000007264222],"category_scores_gemma":[0.00010082973,0.00014903728,0.000091273796,0.00042921153,0.000007314476,0.000047858117,0.000009920716,0.00022537053,0.000019762092],"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":[0.0000068031604,0.000039418854,0.00021493217,0.000058710328,0.000011565741,5.541682e-7,0.0002262923,0.9150657,0.00010661277,0.0001751629,0.000005726971,0.08408849],"study_design_scores_gemma":[0.00045864913,0.000113499416,0.002688666,0.00011857842,0.000007620431,0.0000047035,0.000013170576,0.9918884,0.0038100753,0.000015853451,0.0006975029,0.00018329332],"about_ca_topic_score_codex":0.0000049622477,"about_ca_topic_score_gemma":8.9027964e-7,"teacher_disagreement_score":0.36177644,"about_ca_system_score_codex":0.00013551093,"about_ca_system_score_gemma":0.000026527785,"threshold_uncertainty_score":0.6077564},"labels":[],"label_agreement":null},{"id":"W2964175311","doi":"10.1109/tse.2018.2868349","title":"Debugging Static Analysis","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Universität Paderborn; École Polytechnique Fédérale de Lausanne; Heinz Nixdorf Stiftung; Deutsche Forschungsgemeinschaft","keywords":"Static analysis; Debugging; Computer science; Debugger; Static program analysis; Programming language; Program analysis; Algorithmic program debugging; Software bug; Source code; Data-flow analysis; Call graph; Code (set theory); Tracing; Taint checking; Software engineering; Data flow diagram; Database; Software; Software development","score_opus":0.013345475541958063,"score_gpt":0.25049080371884513,"score_spread":0.23714532817688708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964175311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021801608,0.000029404473,0.9746188,0.00004667463,0.0008681915,0.00011878541,0.00000746706,0.0024960176,0.0000130698],"genre_scores_gemma":[0.8002258,0.0000046108435,0.1994331,0.00005440001,0.000065974695,0.000043893848,9.385336e-7,0.00003322093,0.00013804578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981763,0.000024612886,0.0002559399,0.0004994583,0.0004886591,0.00055504806],"domain_scores_gemma":[0.99794155,0.000834801,0.000030509345,0.0008467757,0.00013526471,0.00021108998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002592899,0.00024491185,0.00025497214,0.0011047154,0.00018300852,0.00016608082,0.0007325265,0.000082494946,0.000101828],"category_scores_gemma":[0.00015018793,0.00026459052,0.00019701022,0.0030115382,0.000037828704,0.00042910708,0.000006631692,0.00035425328,0.00023441645],"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":[0.0000078057155,0.000092245486,0.0009792723,0.000050581457,0.00087181537,0.000038909697,0.0007387497,0.96787846,0.0005485599,0.00021072268,0.00019765303,0.028385205],"study_design_scores_gemma":[0.00034497835,0.00019593803,0.0068931826,0.00005988786,0.0001648857,0.000022125056,0.000008285806,0.9638431,0.026709873,0.000031566717,0.0011048078,0.00062134233],"about_ca_topic_score_codex":0.000022491397,"about_ca_topic_score_gemma":0.000007915267,"teacher_disagreement_score":0.7784242,"about_ca_system_score_codex":0.00016023664,"about_ca_system_score_gemma":0.000058518683,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W2972246936","doi":"10.1109/tse.2019.2938525","title":"Enabling Good Work Habits in Software Developers through Reflective Goal-Setting","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","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":"University of British Columbia","funders":"","keywords":"Computer science; Work (physics); Productivity; Reflection (computer programming); Goal setting; Knowledge management; Set (abstract data type); Software; Domain (mathematical analysis); Psychology; Engineering","score_opus":0.07449546207864395,"score_gpt":0.34146741393617197,"score_spread":0.26697195185752803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972246936","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":[0.34301764,0.00003572565,0.6550204,0.00007258588,0.0009537627,0.00033109507,0.000012097697,0.00031981894,0.00023687974],"genre_scores_gemma":[0.9418832,0.000011239306,0.05548292,0.00023075474,0.00003697557,0.00007984491,0.000003516795,0.00004276957,0.0022287888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99725217,0.000048597547,0.00071608066,0.0005177768,0.00097104994,0.0004943372],"domain_scores_gemma":[0.99823993,0.000916246,0.00012938277,0.0004541662,0.00016559007,0.000094667084],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008760084,0.00029956512,0.00034031854,0.0005997991,0.0001725515,0.00024460722,0.00052566355,0.0001446952,0.00026600534],"category_scores_gemma":[0.00029300962,0.0002830833,0.00017467783,0.002246183,0.000020356687,0.0015276688,0.000008704208,0.0005394267,0.0010121774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089842215,0.00011384995,0.023692982,0.000050490864,0.000064393935,0.000019416793,0.0065397657,0.8960249,0.00032030453,0.00012572385,0.00046944292,0.07248888],"study_design_scores_gemma":[0.018458523,0.001324305,0.60566825,0.0055985507,0.00045689655,0.00012439591,0.03364582,0.071456745,0.06787104,0.0015020967,0.18141715,0.0124762505],"about_ca_topic_score_codex":0.00002129219,"about_ca_topic_score_gemma":0.000020853511,"teacher_disagreement_score":0.82456815,"about_ca_system_score_codex":0.00026189568,"about_ca_system_score_gemma":0.000065939006,"threshold_uncertainty_score":0.99996215},"labels":[],"label_agreement":null},{"id":"W2973035781","doi":"10.1109/tse.2019.2948910","title":"CrySL: An Extensible Approach to Validating the Correct Usage of Cryptographic APIs","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Heinz Nixdorf Stiftung","keywords":"Computer science; Cryptography; Java; Android (operating system); Programming language; Algorithm; Operating system","score_opus":0.011485362405329838,"score_gpt":0.22432560316352004,"score_spread":0.2128402407581902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973035781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024116646,0.0000150867145,0.97332263,0.000012688735,0.00065753976,0.00042781953,0.000005718207,0.0013787553,0.000063124724],"genre_scores_gemma":[0.61171913,0.0000039232195,0.38806096,0.000055773497,0.000014263561,0.000073895055,3.0339592e-7,0.000025134346,0.000046614252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99868894,0.00004082392,0.00026775833,0.0004242602,0.0002970971,0.0002811047],"domain_scores_gemma":[0.9985764,0.00022242729,0.000068409165,0.0009159852,0.00011737142,0.0000994148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027924692,0.00020526796,0.00021501094,0.00038510084,0.00012029861,0.00006808712,0.0006770172,0.00007522016,0.000016425052],"category_scores_gemma":[0.00003300324,0.00018153945,0.00012116028,0.0011709601,0.000019734081,0.0005323455,0.000007822448,0.00033102022,0.000019504925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009072866,0.00010507395,0.00002940102,0.00005938721,0.000027318749,0.000001134515,0.00066481356,0.9302857,0.032182835,0.00054398295,0.000020292737,0.03607099],"study_design_scores_gemma":[0.00034178083,0.0005419364,0.0005828126,0.00016062558,0.000024014164,0.000071991504,0.00013265872,0.2943238,0.7019898,0.00016222255,0.00097157573,0.00069678033],"about_ca_topic_score_codex":0.000020924299,"about_ca_topic_score_gemma":0.0000016796914,"teacher_disagreement_score":0.66980696,"about_ca_system_score_codex":0.00004614891,"about_ca_system_score_gemma":0.00002285097,"threshold_uncertainty_score":0.74029636},"labels":[],"label_agreement":null},{"id":"W2973296283","doi":"10.1109/tse.2019.2941880","title":"Studying the Impact of Noises in Build Breakage Data","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Computer science; Replicate; Breakage; Server; Troubleshooting; Timeout; Data mining; Data science; World Wide Web; Statistics; Operating system","score_opus":0.028169490543929115,"score_gpt":0.2874072299796261,"score_spread":0.25923773943569695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973296283","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":[0.31337062,0.000067591165,0.68562335,0.000015279089,0.00038427336,0.00023280857,0.00002279856,0.00027816318,0.000005114007],"genre_scores_gemma":[0.984499,0.000016129346,0.015348266,0.0000063546363,0.000022616658,0.00002576647,0.0000018403842,0.000034164324,0.000045911664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984145,0.000034070523,0.00028812548,0.0004423622,0.0004142564,0.00040667225],"domain_scores_gemma":[0.9963319,0.0016072748,0.00003965042,0.0018917915,0.000051877927,0.000077560995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049197697,0.00021572788,0.00025095703,0.00040314958,0.00004797727,0.000075295575,0.0020006874,0.000070528054,0.000033130113],"category_scores_gemma":[0.00016106575,0.00016983175,0.00011168451,0.0011035117,0.00002004415,0.00060659484,0.000032552794,0.0005302523,0.000043604305],"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":[0.000007315232,0.00009291428,0.009051546,0.000048128764,0.00006435036,0.000008921363,0.00031899736,0.9827649,0.0011366794,0.000019979783,0.000044564957,0.0064417063],"study_design_scores_gemma":[0.0011697368,0.0003452893,0.16190284,0.00037805407,0.000016530226,0.000052946918,0.000044986802,0.82564086,0.00962032,0.000015181557,0.00016397718,0.0006492631],"about_ca_topic_score_codex":0.00026721158,"about_ca_topic_score_gemma":0.000008892246,"teacher_disagreement_score":0.67112833,"about_ca_system_score_codex":0.00014900883,"about_ca_system_score_gemma":0.00009597482,"threshold_uncertainty_score":0.69255376},"labels":[],"label_agreement":null},{"id":"W2975871742","doi":"10.1109/tse.2019.2942301","title":"Smart Contract Development: Challenges and Opportunities","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":706,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"National Key Research and Development Program of China; Nanjing University; National Natural Science Foundation of China","keywords":"Computer science; Software engineering; Engineering management; Computer security; Data science; Engineering","score_opus":0.02204994130856623,"score_gpt":0.20349607014277102,"score_spread":0.1814461288342048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975871742","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":[0.05753681,0.00086134736,0.9401736,0.00023286059,0.00022724859,0.00012700191,0.0000018259054,0.0007585922,0.00008070104],"genre_scores_gemma":[0.9523152,0.000670037,0.046765603,0.00006352091,0.0000060694383,0.000062843574,4.052469e-7,0.0000114334825,0.000104853614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933577,0.0000069959297,0.00013019762,0.00025493314,0.00009516889,0.00017694515],"domain_scores_gemma":[0.99945253,0.000103946666,0.000022623406,0.00033313045,0.000027366494,0.000060373397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010798924,0.00012552163,0.0001267174,0.00015660984,0.00008322925,0.000028231303,0.00023411949,0.00009994495,0.00001313268],"category_scores_gemma":[0.0000029163057,0.00013300045,0.000026763686,0.00007687453,0.000017685532,0.00017198027,0.000003731507,0.00020698977,0.00003151705],"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":[0.0000038468547,0.0001110346,0.000040217023,0.00011991035,0.00007944066,0.000009274915,0.0016305577,0.0030903886,0.00028083698,0.058012087,0.000011034428,0.93661135],"study_design_scores_gemma":[0.0046147276,0.0008106662,0.024955451,0.0009557256,0.000093022,0.0006473911,0.00067291444,0.4734213,0.1616306,0.0026078792,0.324752,0.004838313],"about_ca_topic_score_codex":0.0000023324296,"about_ca_topic_score_gemma":0.000003834386,"teacher_disagreement_score":0.93177307,"about_ca_system_score_codex":0.000025652023,"about_ca_system_score_gemma":0.000028457465,"threshold_uncertainty_score":0.54236007},"labels":[],"label_agreement":null},{"id":"W2989443621","doi":"10.1109/tse.2019.2952130","title":"An Empirical Study of Dependency Downgrades in the npm Ecosystem","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"","keywords":"Computer science; Downgrade; Dependency (UML); Software versioning; Reuse; Software; Software engineering; Computer security; Operating system","score_opus":0.01786606815314012,"score_gpt":0.28024781358299794,"score_spread":0.2623817454298578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989443621","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":[0.5047135,0.000012534496,0.49437875,0.0000095275,0.00032149264,0.00032103382,0.0000028245026,0.00023816725,0.0000021803085],"genre_scores_gemma":[0.99269646,0.0000022001266,0.0071241963,0.000012694323,0.000021063805,0.00010470013,4.294662e-7,0.00002709379,0.000011130127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981056,0.00011100243,0.00034199865,0.00042497006,0.0006576073,0.000358814],"domain_scores_gemma":[0.9976236,0.0011108408,0.00003520762,0.0010899125,0.000056617468,0.00008379784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055179995,0.0002079014,0.00025533992,0.0004812475,0.000051176932,0.000085310916,0.0012943976,0.00008793367,0.000018021252],"category_scores_gemma":[0.000052372445,0.0001714434,0.00007883105,0.0010844453,0.000007231881,0.00043878274,0.0000052810465,0.0005450798,0.000040432988],"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":[0.000010432978,0.00089582667,0.04856831,0.00009702742,0.00003881383,0.000036007554,0.004831792,0.94151527,0.00038442275,0.000029485831,0.000008357371,0.0035842375],"study_design_scores_gemma":[0.0036216648,0.004387059,0.45477262,0.00037343317,0.00004277147,0.000169356,0.0019407459,0.5223728,0.01065431,0.00003890362,0.00024522893,0.0013811309],"about_ca_topic_score_codex":0.00004523639,"about_ca_topic_score_gemma":0.00004914201,"teacher_disagreement_score":0.48798302,"about_ca_system_score_codex":0.000094297124,"about_ca_system_score_gemma":0.00004692397,"threshold_uncertainty_score":0.6991259},"labels":[],"label_agreement":null},{"id":"W2995892549","doi":"10.1109/tse.2019.2960357","title":"Effects of Personality Traits on Pull Request Acceptance","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":48,"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":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big Five personality traits; Personality; Human–computer interaction; Software engineering; Psychology; Social psychology","score_opus":0.012923066489828869,"score_gpt":0.26799891989481184,"score_spread":0.25507585340498296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995892549","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":[0.72481537,0.00014464858,0.2700217,0.00007140614,0.0027985265,0.00036897467,0.00009093763,0.00028927973,0.0013991222],"genre_scores_gemma":[0.99647164,0.000010824477,0.0013278621,0.0003605013,0.000088435765,0.000072204086,0.0000027301203,0.00004566433,0.0016201534],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985825,0.00006747263,0.0002803925,0.00046138404,0.00022501167,0.00038327044],"domain_scores_gemma":[0.99891436,0.000532065,0.00006738329,0.0003339509,0.0000408177,0.000111395166],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015652405,0.00026449864,0.00035257562,0.0001786797,0.000046145185,0.000011114761,0.00022252068,0.00022422726,0.0016516633],"category_scores_gemma":[0.000015759635,0.0002726215,0.00021411077,0.00026451124,0.000040349176,0.00008616602,6.658028e-7,0.0005109106,0.0004006673],"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":[0.006473106,0.016163277,0.009470013,0.0075362856,0.006041018,0.0005849624,0.040111315,0.16427037,0.18076962,0.041161787,0.009111768,0.5183065],"study_design_scores_gemma":[0.011578177,0.00471725,0.86503303,0.0014679413,0.000406209,0.00021672712,0.00041458113,0.0010039535,0.07347764,0.00011614771,0.03857666,0.0029917003],"about_ca_topic_score_codex":0.00004996063,"about_ca_topic_score_gemma":0.0000072678267,"teacher_disagreement_score":0.855563,"about_ca_system_score_codex":0.000058539987,"about_ca_system_score_gemma":0.000017287206,"threshold_uncertainty_score":0.9999726},"labels":[],"label_agreement":null},{"id":"W2999284478","doi":"10.1109/tse.2020.2966994","title":"<i>checsdm</i>: A Method for Ensuring Consistency in Heterogeneous Safety-Critical System Design","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Model-Driven Software Engineering 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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Consistency (knowledge bases); Set (abstract data type); Engineering design process; Component (thermodynamics); Software engineering; Programming language; Artificial intelligence; Engineering","score_opus":0.028589741221183025,"score_gpt":0.25684404679384637,"score_spread":0.22825430557266335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999284478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007552598,0.00011232859,0.9942408,0.00018508515,0.0005956668,0.0006987403,0.000034616132,0.0040538325,0.0000034049963],"genre_scores_gemma":[0.26972342,0.000007954732,0.7297232,0.00010464861,0.0000448192,0.00032618782,8.807151e-7,0.000065224325,0.0000036612457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976899,0.00008975795,0.00059008505,0.0007384064,0.0003008147,0.0005910123],"domain_scores_gemma":[0.9979116,0.0011123581,0.000047548143,0.0005462429,0.00010074539,0.0002815293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045476464,0.00039920252,0.00049834116,0.00029529157,0.0001276898,0.000096746466,0.00066407624,0.00019361504,0.0000037878542],"category_scores_gemma":[0.00006804958,0.000467941,0.00022954619,0.0005871976,0.00002226056,0.0003238566,0.000010248799,0.00046638958,0.000011117886],"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":[0.000034892433,0.000042614804,0.0000028532543,0.0003865259,0.00003799414,0.00006885445,0.00040544008,0.97195107,0.0011915978,0.00557071,0.000018203807,0.020289259],"study_design_scores_gemma":[0.00043852994,0.00019965535,0.0000056895383,0.0002716944,0.000023865194,0.000100925725,0.0000047758217,0.95283663,0.044178966,0.000023237533,0.0014412409,0.0004747669],"about_ca_topic_score_codex":0.000009630934,"about_ca_topic_score_gemma":0.000001107154,"teacher_disagreement_score":0.26964787,"about_ca_system_score_codex":0.00026843484,"about_ca_system_score_gemma":0.00007466555,"threshold_uncertainty_score":0.99977726},"labels":[],"label_agreement":null},{"id":"W3001461005","doi":"10.1109/tse.2020.2967380","title":"A Machine Learning Approach to Improve the Detection of CI Skip Commits","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":62,"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":"Commit; Computer science; Machine learning; Facilitator; Decision tree; Artificial intelligence; Tree (set theory); Software; Popularity; Data mining; Software engineering; Database; Operating system","score_opus":0.01601098347251498,"score_gpt":0.21960679703534175,"score_spread":0.20359581356282677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001461005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006108216,0.000093321025,0.99179405,0.00015925814,0.00040365526,0.0003357616,0.000011861271,0.0010803139,0.000013534316],"genre_scores_gemma":[0.9474005,0.0000089302175,0.052256573,0.000085484746,0.000058351237,0.000106890635,7.656833e-7,0.000044163055,0.000038331433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984755,0.000045543657,0.00026331976,0.00041032082,0.0004473735,0.00035792054],"domain_scores_gemma":[0.99853307,0.0006460756,0.00004109757,0.00047377555,0.00008900461,0.00021695886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002558493,0.00022458605,0.0002226806,0.00021222697,0.00015361236,0.000077177785,0.0008056341,0.00008169539,0.0000051472643],"category_scores_gemma":[0.0003537076,0.00019795843,0.00012851543,0.0012705774,0.000019429128,0.00020052626,0.000015863634,0.0008055991,0.000037828668],"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":[0.000013770926,0.00004674064,0.000055550325,0.00009288327,0.00004653775,0.000002293574,0.0009309185,0.9565238,0.010810979,0.000041390846,0.0000098225255,0.03142532],"study_design_scores_gemma":[0.000338326,0.0003213311,0.00050402194,0.000035356887,0.000014460891,0.000014778516,0.000020941308,0.8918658,0.10454018,0.000003081102,0.0020429215,0.00029879235],"about_ca_topic_score_codex":0.000028624801,"about_ca_topic_score_gemma":0.0000011925165,"teacher_disagreement_score":0.9412923,"about_ca_system_score_codex":0.00007773478,"about_ca_system_score_gemma":0.000031636268,"threshold_uncertainty_score":0.8072511},"labels":[],"label_agreement":null},{"id":"W3002536493","doi":"10.1109/tse.2020.2968061","title":"<i>MoMIT</i>: Porting a JavaScript Interpreter on a Quarter Coin","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Parallel Computing and Optimization 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":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Porting; JavaScript; Interpreter; Programming language; Unobtrusive JavaScript; Quarter (Canadian coin); Operating system; Software engineering; World Wide Web; Rich Internet application; Software","score_opus":0.01290825836886121,"score_gpt":0.2126756645624824,"score_spread":0.1997674061936212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002536493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001337362,0.0000185528,0.9947602,0.00040352592,0.00047594696,0.00013786367,0.0000041493936,0.0027499404,0.00011243526],"genre_scores_gemma":[0.7537269,0.000004239011,0.24470554,0.0014238879,0.000048126985,0.000027391045,7.0928655e-7,0.000024830544,0.00003839627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876046,0.000028010743,0.0003006357,0.00041507726,0.00021848048,0.00027734716],"domain_scores_gemma":[0.99927974,0.00011934989,0.000060638005,0.00034054994,0.000043973138,0.00015572534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010560058,0.00021964559,0.00019745411,0.00015585037,0.00010294802,0.00012529524,0.00044580028,0.00007884029,0.000019456755],"category_scores_gemma":[0.000036312354,0.00022890503,0.00013976161,0.00038171932,0.000010568777,0.00025972386,0.0000049329,0.00037627123,0.00006721953],"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":[0.000024208082,0.00007690252,0.000020957967,0.00004629665,0.000053137905,0.000032333704,0.0020288527,0.97864914,0.00093367853,0.00026142749,0.002103805,0.01576924],"study_design_scores_gemma":[0.00026396764,0.00027825346,0.000024373461,0.00011982835,0.000007952535,0.000014420993,0.000010658578,0.9795861,0.01792779,0.000011999209,0.0014310795,0.0003235804],"about_ca_topic_score_codex":0.000004000226,"about_ca_topic_score_gemma":3.221253e-7,"teacher_disagreement_score":0.7523895,"about_ca_system_score_codex":0.000046197718,"about_ca_system_score_gemma":0.000023206701,"threshold_uncertainty_score":0.93344766},"labels":[],"label_agreement":null},{"id":"W3006039974","doi":"10.1109/tse.2020.2973997","title":"ConfigMiner: Identifying the Appropriate Configuration Options for Config-Related User Questions by Mining Online Forums","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"","keywords":"Computer science; Task (project management); Rank (graph theory); Software; State (computer science); World Wide Web; Information retrieval; Data science; Programming language; Engineering; Systems engineering","score_opus":0.02648402744795977,"score_gpt":0.26287446803427095,"score_spread":0.23639044058631117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006039974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077631264,0.00023576761,0.986453,0.0015527622,0.0010310411,0.0008293312,0.00020625736,0.0019238566,0.0000048515244],"genre_scores_gemma":[0.8862028,0.00006138868,0.112071544,0.00034195237,0.00013555457,0.0005787153,0.00007947467,0.00011523834,0.00041332433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978012,0.000050954095,0.00051541324,0.00060894055,0.00044389773,0.00057962706],"domain_scores_gemma":[0.99726105,0.0015997287,0.000089283356,0.0005606972,0.00022452242,0.00026472946],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030469598,0.00035137788,0.0002917842,0.00020837529,0.00045143973,0.00033261318,0.0008537208,0.00017640936,0.00004102441],"category_scores_gemma":[0.00050116144,0.00032935783,0.00020949196,0.0009145046,0.000052233278,0.0005991596,0.000010073856,0.0006171382,0.000041456802],"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":[0.00003129496,0.00019155203,0.000050999955,0.00020722538,0.00035308686,0.000011162905,0.002455434,0.95476824,0.0197293,0.003558089,0.0030062273,0.015637364],"study_design_scores_gemma":[0.001649657,0.00031500176,0.00043090666,0.00021947296,0.00009737074,0.00004128991,0.0001777305,0.95210904,0.028632447,0.000053122283,0.015378697,0.000895256],"about_ca_topic_score_codex":0.00001828883,"about_ca_topic_score_gemma":0.0000040729947,"teacher_disagreement_score":0.87843966,"about_ca_system_score_codex":0.000109576205,"about_ca_system_score_gemma":0.0000935552,"threshold_uncertainty_score":0.99991584},"labels":[],"label_agreement":null},{"id":"W3014214759","doi":"10.1109/tse.2020.2983399","title":"Studying Ad Library Integration Strategies of Top Free-to-Download Apps","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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":"Download; Computer science; World Wide Web; App store; Mobile apps; Revenue; Set (abstract data type)","score_opus":0.013909002787377889,"score_gpt":0.21969032033219593,"score_spread":0.20578131754481804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014214759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034460973,0.00004307584,0.9928558,0.00022358725,0.0003295785,0.00026142993,0.00002810708,0.002781987,0.000030352201],"genre_scores_gemma":[0.6294402,0.000016480768,0.37034333,0.0000907873,0.000018496932,0.000059554997,9.593143e-7,0.000017462344,0.000012767938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893963,0.000018017072,0.00028500814,0.00034328442,0.0002217682,0.00019229986],"domain_scores_gemma":[0.99921525,0.00011177133,0.0000553975,0.00043512386,0.000048658294,0.00013382341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048594273,0.00019276397,0.0002077444,0.00024893138,0.00006966834,0.00009170932,0.0005946574,0.00007085314,0.000022018761],"category_scores_gemma":[0.00003829699,0.0002066213,0.00008896366,0.00075903896,0.0000131279885,0.0013484225,0.000011812654,0.00029654478,0.000018977575],"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":[0.000039836348,0.000121886646,0.000007960635,0.00014610028,0.000060566577,0.000015336818,0.0028030816,0.72532094,0.052576005,0.0011966389,0.00047928514,0.21723236],"study_design_scores_gemma":[0.0002804583,0.00050382176,0.00007056277,0.00013822847,0.000012428919,0.000007826343,0.00027403457,0.0453169,0.95119756,0.00021803875,0.0016045622,0.00037559643],"about_ca_topic_score_codex":0.000004267864,"about_ca_topic_score_gemma":0.0000013665959,"teacher_disagreement_score":0.89862156,"about_ca_system_score_codex":0.00003349082,"about_ca_system_score_gemma":0.000043745928,"threshold_uncertainty_score":0.8425772},"labels":[],"label_agreement":null},{"id":"W3017224552","doi":"10.1109/tse.2020.2984086","title":"Detecting Developers’ Task Switches and Types","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","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 British Columbia","funders":"","keywords":"Computer science; Task (project management); Software engineering; Programming language; Systems engineering","score_opus":0.14610293055338866,"score_gpt":0.3287958043560832,"score_spread":0.18269287380269453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017224552","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":[0.2542293,0.000024165096,0.74504656,0.00020126761,0.0001864314,0.00006733546,0.0000073563165,0.00020413031,0.000033455657],"genre_scores_gemma":[0.9885912,0.000007934392,0.010777946,0.00034538718,0.00003184848,0.000012023686,4.9275496e-7,0.000013099167,0.00022005016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989589,0.00000945335,0.00026757896,0.00021653087,0.00039340035,0.00015412767],"domain_scores_gemma":[0.99940956,0.00024325424,0.000041850428,0.00012059178,0.000060293758,0.00012446512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024529969,0.00012519295,0.00013856894,0.00017466056,0.00014123041,0.00016982907,0.00018702577,0.000044791683,0.00013400576],"category_scores_gemma":[0.00018853864,0.000109681976,0.00005688237,0.00049274304,0.000013834216,0.0004522769,0.000003288072,0.00017091545,0.0002021728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096271724,0.000057283294,0.0044318642,0.0000945784,0.00014324872,0.000022452718,0.013882451,0.36148718,0.00735739,0.00017271616,0.0013371226,0.61091745],"study_design_scores_gemma":[0.004225894,0.0008622086,0.06897438,0.00033359416,0.0004173835,0.00008781836,0.011043545,0.54986215,0.12112516,0.00019935818,0.23867747,0.004191023],"about_ca_topic_score_codex":0.0000036928755,"about_ca_topic_score_gemma":0.0000033938422,"teacher_disagreement_score":0.73436195,"about_ca_system_score_codex":0.00001960156,"about_ca_system_score_gemma":0.000014095315,"threshold_uncertainty_score":0.44727013},"labels":[],"label_agreement":null},{"id":"W3025537827","doi":"10.1109/tse.2021.3087087","title":"Generating Unit Tests for Documentation","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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","keywords":"Documentation; Internal documentation; Unit testing; Computer science; Software documentation; Redundancy (engineering); Artifact (error); Source code; Software engineering; Software; Database; Programming language; Operating system; Software development; Artificial intelligence; Software development process; Software construction","score_opus":0.03303154572484931,"score_gpt":0.29791213454178017,"score_spread":0.2648805888169309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025537827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035799697,0.00024824386,0.9561712,0.00004578489,0.0049719107,0.0006740469,0.000048266167,0.0020393652,0.0000014710034],"genre_scores_gemma":[0.36182815,0.000043388984,0.63661665,0.000052057505,0.00024742764,0.0008964552,0.0000389303,0.000111504065,0.00016543022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973547,0.000040664298,0.00046236315,0.0009604147,0.00057037815,0.0006114948],"domain_scores_gemma":[0.99653435,0.0016393763,0.000090324844,0.0011531136,0.00037745765,0.00020537718],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034781796,0.00050151284,0.00041324986,0.0005593693,0.00020209474,0.00081037835,0.0009775696,0.0003543637,0.000028612782],"category_scores_gemma":[0.00047916066,0.0006169257,0.00031469602,0.00058597553,0.000016000651,0.0005061524,0.000033943325,0.0011400306,0.000015837071],"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":[0.0000032070077,0.000054499644,0.000053570482,0.00039717098,0.00011115368,0.000016651135,0.00032247146,0.9846123,0.0010985784,0.000028005694,0.00008138844,0.013221001],"study_design_scores_gemma":[0.00067612226,0.00012496847,0.0005529234,0.0007654697,0.0000578888,0.000029022398,0.000026856076,0.9486277,0.047463153,0.00003865812,0.0005079666,0.0011292446],"about_ca_topic_score_codex":0.000029211322,"about_ca_topic_score_gemma":0.000008441354,"teacher_disagreement_score":0.32602847,"about_ca_system_score_codex":0.00032201307,"about_ca_system_score_gemma":0.00028929493,"threshold_uncertainty_score":0.9996282},"labels":[],"label_agreement":null},{"id":"W3032170634","doi":"10.1109/tse.2020.2998503","title":"Automatic Generation of Acceptance Test Cases From Use Case Specifications: An NLP-Based Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":85,"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 Research Council; European Commission","keywords":"Computer science; Executable; Test case; Software requirements specification; Acceptance testing; Software engineering; Test script; System under test; Conformance testing; Test Management Approach; Test (biology); Formal specification; Reliability engineering; Software; Software system; Programming language; Machine learning; Software construction","score_opus":0.11804880023702771,"score_gpt":0.2662858943771059,"score_spread":0.1482370941400782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032170634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21156387,0.000044706107,0.7865786,0.00003847632,0.00022650593,0.00025115145,0.00011295276,0.0011831583,5.7806193e-7],"genre_scores_gemma":[0.6297883,0.000004134465,0.36997566,0.000037707836,0.000068979905,0.00007500227,0.00001245392,0.00003404828,0.000003720381],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982739,0.000044589106,0.00039631483,0.0005747571,0.00041569257,0.0002947636],"domain_scores_gemma":[0.9966721,0.001998691,0.00007012616,0.00085047184,0.00014026022,0.0002683754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012065191,0.0002639647,0.00026160225,0.00025341354,0.00012677613,0.00019118538,0.0005619222,0.000105721505,0.00004782086],"category_scores_gemma":[0.00068879605,0.00029769435,0.0001054215,0.0009754817,0.000030741296,0.0009773287,0.0000049289306,0.00034660555,0.000018857969],"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":[0.000004132359,0.00024028447,0.0003534129,0.000085378124,0.00003221177,0.00020051505,0.000512941,0.9812691,0.005698903,0.000028633896,0.000053265303,0.011521196],"study_design_scores_gemma":[0.0002810891,0.00014807418,0.0010015042,0.000034550678,0.000017498041,0.00009515045,0.000019457608,0.9585655,0.03950661,0.0000010054199,0.00005321874,0.0002763759],"about_ca_topic_score_codex":0.00008665669,"about_ca_topic_score_gemma":0.000007809109,"teacher_disagreement_score":0.41822442,"about_ca_system_score_codex":0.00011020724,"about_ca_system_score_gemma":0.00009392604,"threshold_uncertainty_score":0.99994755},"labels":[],"label_agreement":null},{"id":"W3037099619","doi":"10.1109/tse.2020.3004525","title":"Why Do Software Developers Use Static Analysis Tools? A User-Centered Study of Developer Needs and Motivations","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":76,"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":"Heinz Nixdorf Stiftung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Usability; Software engineering; Software development; Software; Static program analysis; Secure coding; World Wide Web; Human–computer interaction; Software security assurance; Computer security; Programming language; Information security","score_opus":0.04324661639113619,"score_gpt":0.24984638888479016,"score_spread":0.20659977249365397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037099619","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":[0.38235328,0.000018562952,0.6164743,0.00009547416,0.00012200522,0.00030539092,0.000029782708,0.0006009834,2.2193926e-7],"genre_scores_gemma":[0.8158083,0.000013584005,0.1838715,0.00014676862,0.000013357507,0.00007468584,0.0000040489317,0.000050287614,0.000017459935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99768573,0.00006467209,0.0005375687,0.00060744287,0.0006434188,0.00046114085],"domain_scores_gemma":[0.99702716,0.0016642928,0.00007356765,0.00063537806,0.0002668685,0.00033274086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018153276,0.00037516953,0.00050909584,0.0011999002,0.00016111784,0.00034656687,0.0006826133,0.000100824014,0.00002644635],"category_scores_gemma":[0.00086592435,0.0003979458,0.00014569389,0.0050886907,0.0000325149,0.0011958706,0.000027935786,0.00045826382,0.000008395072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024444056,0.0002562952,0.04315663,0.00013968801,0.0013316434,0.000028443237,0.009378243,0.9388109,0.00025177698,0.000028953786,0.00012673915,0.006466252],"study_design_scores_gemma":[0.006964894,0.002209157,0.56758153,0.0005455625,0.0016195327,0.0000531877,0.0031067936,0.39867082,0.011197791,0.000010021385,0.004054509,0.0039861985],"about_ca_topic_score_codex":0.000075577045,"about_ca_topic_score_gemma":0.000021085483,"teacher_disagreement_score":0.5401401,"about_ca_system_score_codex":0.00012059976,"about_ca_system_score_gemma":0.000096971315,"threshold_uncertainty_score":0.99984723},"labels":[],"label_agreement":null},{"id":"W3042598532","doi":"10.1109/tse.2020.3008850","title":"Execution of Partial State Machine Models","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Model-Driven Software Engineering 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; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Partial evaluation; Static analysis; Execution model; Unified Modeling Language; Programming language; Program transformation; Model transformation; Semantics (computer science); Software; Overhead (engineering); Source code; Software development; Transformation (genetics); Artificial intelligence","score_opus":0.019574979642059568,"score_gpt":0.20920851662593612,"score_spread":0.18963353698387655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042598532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023735357,0.000057558296,0.9942137,0.00009158459,0.00033501274,0.0002013426,0.000041818515,0.0026805333,0.0000048861175],"genre_scores_gemma":[0.5579688,0.000022145194,0.44186834,0.00004973553,0.00001788802,0.000034224446,0.0000013439766,0.000028608581,0.000008915643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985926,0.00002056486,0.00036189213,0.00039371342,0.00033422583,0.0002970132],"domain_scores_gemma":[0.99915266,0.00006554079,0.00006481621,0.0004566801,0.00007300984,0.0001872968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000106660664,0.00025447155,0.0002781475,0.00017666818,0.000051462408,0.00003587255,0.00053831114,0.00008607043,0.000010622472],"category_scores_gemma":[0.0000059514896,0.00028328312,0.00014489071,0.00050824863,0.000018753482,0.00056777586,0.000008038039,0.0003391222,0.000011017616],"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":[0.000010715461,0.00003819932,0.000004577047,0.00006162098,0.000030416053,0.000007563926,0.0004816154,0.96980745,0.0015418868,0.0024965666,0.00003225591,0.025487166],"study_design_scores_gemma":[0.0002009715,0.00012979163,0.000013624256,0.00004967107,0.000010325271,0.000006266195,6.2819043e-7,0.8980612,0.10009263,0.00007623832,0.0011127987,0.00024583048],"about_ca_topic_score_codex":0.000018221459,"about_ca_topic_score_gemma":5.5359874e-7,"teacher_disagreement_score":0.5555953,"about_ca_system_score_codex":0.00006148515,"about_ca_system_score_gemma":0.000035362897,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W3088218866","doi":"10.1109/tse.2020.3025732","title":"Automated Generation of Consistent Graph Models With Multiplicity Reasoning","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Model-Driven Software Engineering 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":"McGill University","funders":"Nemzeti Kutatási, Fejlesztési és Innovaciós Alap; Natural Sciences and Engineering Research Council of Canada; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Innovációs és Technológiai Minisztérium; Emberi Eroforrások Minisztériuma","keywords":"Computer science; Solver; Theoretical computer science; Predicate abstraction; Graph; Abstraction; Programming language; Model checking","score_opus":0.030861502862934462,"score_gpt":0.2177657069829095,"score_spread":0.18690420411997505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088218866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012214203,0.00003223089,0.98087865,0.00004726106,0.00015984592,0.00026516322,0.000017746837,0.0063814465,0.0000034476943],"genre_scores_gemma":[0.5005982,0.0000068803474,0.4992746,0.000036293146,0.00001345785,0.00004175846,0.0000016466156,0.00002508825,0.0000020794935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986081,0.00002288348,0.00032455503,0.00043813835,0.00034150446,0.00026483185],"domain_scores_gemma":[0.9990892,0.00006480909,0.00008149016,0.00045566304,0.00013970704,0.00016917386],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009728057,0.00027310962,0.0002966741,0.00019742275,0.00007936661,0.00004849684,0.00039094535,0.00010566827,0.0000032726298],"category_scores_gemma":[0.000007369164,0.00027512645,0.00011215948,0.0006402903,0.000024635072,0.00049770914,0.0000058037776,0.00028752402,0.00000276378],"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":[0.000008734667,0.000038079124,0.000012977744,0.000056554778,0.000053844255,0.000008141177,0.0004340631,0.9888047,0.004291499,0.0024363531,0.000035302248,0.0038197627],"study_design_scores_gemma":[0.00027173097,0.00015414001,0.000033889184,0.00010178117,0.000018050914,0.000014287737,0.0000016854548,0.9224831,0.07657055,0.000006422901,0.00008065463,0.0002637235],"about_ca_topic_score_codex":0.000020630276,"about_ca_topic_score_gemma":0.000002135184,"teacher_disagreement_score":0.48838398,"about_ca_system_score_codex":0.000067945504,"about_ca_system_score_gemma":0.00004598199,"threshold_uncertainty_score":0.9999701},"labels":[],"label_agreement":null},{"id":"W3091299024","doi":"10.1109/tse.2020.3027255","title":"Comparing Block-Based Programming Models for Two-Armed Robots","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Teaching and Learning Programming","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 British Columbia","funders":"","keywords":"Computer science; Robot; Human–computer interaction; Task (project management); Block (permutation group theory); Robotics; Programming by demonstration; Artificial intelligence; Inductive programming; Programming paradigm; Software engineering; Programming language; Systems engineering; Engineering","score_opus":0.039325971948369134,"score_gpt":0.24808900354820956,"score_spread":0.20876303159984044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091299024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003353882,0.000043688986,0.99240947,0.0002435772,0.0004987584,0.00037692214,0.00000261488,0.003068519,0.0000025871875],"genre_scores_gemma":[0.5479286,3.4090243e-7,0.45178002,0.000096485644,0.00004897996,0.00010587053,0.0000013414978,0.000031630763,0.0000067794376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841726,0.00003187132,0.00027423634,0.0005164219,0.00025590797,0.00050428277],"domain_scores_gemma":[0.9990209,0.0002938766,0.00006125504,0.00032302018,0.000057439946,0.00024355149],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021719893,0.00026805978,0.0002735032,0.00015685911,0.0002965869,0.00024023495,0.00052930875,0.00007480913,0.0000015426912],"category_scores_gemma":[0.00004651002,0.00029995013,0.00020212353,0.00044756505,0.000015352438,0.00035100445,0.0000042782713,0.0005297566,0.000008860925],"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":[0.000010903318,0.00004826084,0.000019922532,0.000077182995,0.000028811066,0.0000040173263,0.00069089636,0.899415,0.00011797702,0.00014223423,0.0000082170145,0.09943657],"study_design_scores_gemma":[0.00080211554,0.00015119642,0.000013588279,0.000091586655,0.000022682058,0.000005415035,0.000014869665,0.9930254,0.0027795702,0.0000043863492,0.002753973,0.00033522098],"about_ca_topic_score_codex":0.000017377923,"about_ca_topic_score_gemma":0.0000026197897,"teacher_disagreement_score":0.5445747,"about_ca_system_score_codex":0.00007156194,"about_ca_system_score_gemma":0.00005351024,"threshold_uncertainty_score":0.9999453},"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":"W3111275476","doi":"10.1109/tse.2021.3078384","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":106,"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":"Chatbot; Computer science; IBM; Natural language understanding; Natural language; Task (project management); Software; Data science; Artificial intelligence; Software engineering; World Wide Web; Natural language processing; Programming language; Engineering","score_opus":0.0374386258312366,"score_gpt":0.29901288892110517,"score_spread":0.2615742630898686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111275476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12581848,0.0006317081,0.8712961,0.000015551146,0.0011693609,0.00028128206,0.00002398965,0.00076256064,9.746337e-7],"genre_scores_gemma":[0.84465903,0.000009598366,0.1550711,0.000010649176,0.00003873936,0.00009895856,0.0000073238475,0.000061944644,0.000042651012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978154,0.0000110440915,0.0005032845,0.0005299294,0.00047978148,0.00066056347],"domain_scores_gemma":[0.99681216,0.0023471068,0.00006313984,0.00053561,0.000096543685,0.00014542618],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027222998,0.00033168303,0.0004944089,0.0006905418,0.00008296878,0.00008984734,0.00051730656,0.00016473541,0.000011893535],"category_scores_gemma":[0.000766188,0.000377216,0.00021334291,0.0012566352,0.000019031786,0.00043110058,0.000014935536,0.0006546523,0.000005072938],"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":[0.000029030612,0.00020002433,0.0030534249,0.0006776905,0.00011852568,0.00006960763,0.0024059485,0.98172057,0.005136516,0.00057748327,0.000024304096,0.0059868935],"study_design_scores_gemma":[0.0018020314,0.00017881759,0.0032722983,0.0010189668,0.000026557285,0.000059652237,0.0004011731,0.77214974,0.22013722,0.0000308308,0.00007803629,0.0008446582],"about_ca_topic_score_codex":0.00001091441,"about_ca_topic_score_gemma":0.000017653843,"teacher_disagreement_score":0.71884054,"about_ca_system_score_codex":0.0004506119,"about_ca_system_score_gemma":0.00011696963,"threshold_uncertainty_score":0.999868},"labels":[],"label_agreement":null},{"id":"W3114491449","doi":"10.1109/tse.2020.3045914","title":"Revisiting Test Impact Analysis in Continuous Testing From the Perspective of Code Dependencies","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Concordia University","funders":"","keywords":"Computer science; Test Management Approach; Code coverage; Test case; Test (biology); Test harness; Source code; Software quality; Test suite; Regression testing; Code (set theory); Programming language; Reliability engineering; Software development; Software; Software construction; Machine learning; Set (abstract data type); Engineering","score_opus":0.02543541439253849,"score_gpt":0.26515398316104255,"score_spread":0.23971856876850406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114491449","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":[0.14296237,0.0001960245,0.8558899,0.00017033433,0.00007956605,0.00014972239,0.0000712944,0.00047541107,0.0000053536264],"genre_scores_gemma":[0.9331804,0.000008011162,0.06666402,0.000034492074,0.000060085986,0.000021434753,0.0000011394671,0.000027061576,0.0000033457488],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829817,0.00004544234,0.0003649644,0.0004675132,0.00044597586,0.00037795],"domain_scores_gemma":[0.9910739,0.008012618,0.000075923905,0.0005015786,0.00020038088,0.00013558788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003142227,0.00023755571,0.00041016794,0.0003172594,0.000085308864,0.00010484686,0.0008209971,0.00007422941,0.000019421946],"category_scores_gemma":[0.0032965783,0.0002048885,0.00023288398,0.0036647404,0.000029749717,0.00029498615,0.000013389404,0.0006224095,0.000009189644],"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":[0.000007099982,0.000030189745,0.04412807,0.000019884426,0.0002353573,0.000027009704,0.0019206567,0.94799674,0.0018940078,0.000020476366,0.000005591852,0.003714903],"study_design_scores_gemma":[0.00046017088,0.00017581151,0.16385448,0.00020694408,0.00013757842,0.00000933322,0.00035342685,0.82084346,0.013483766,0.000018785931,0.0000132654195,0.00044299147],"about_ca_topic_score_codex":0.00072047324,"about_ca_topic_score_gemma":0.000028099174,"teacher_disagreement_score":0.79021806,"about_ca_system_score_codex":0.00022468927,"about_ca_system_score_gemma":0.00008915721,"threshold_uncertainty_score":0.8355111},"labels":[],"label_agreement":null},{"id":"W3118614203","doi":"10.1109/tse.2020.3048335","title":"Accelerating Continuous Integration by Caching Environments and Inferring Dependencies","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; McGill University","funders":"Mitacs","keywords":"Computer science; Acceleration; Service (business); Dependency (UML); Task (project management); Distributed computing; Process (computing); Software; Software engineering; Operating system; Systems engineering","score_opus":0.018451724986903898,"score_gpt":0.2205484944750087,"score_spread":0.20209676948810482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118614203","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":[0.10647356,0.00009970351,0.89213914,0.00008998692,0.00023042307,0.00015894976,0.000007472808,0.00079665985,0.0000041093713],"genre_scores_gemma":[0.9394301,0.000027688606,0.060284205,0.000106874584,0.000037236656,0.000044684733,0.000001810339,0.000037723912,0.000029629233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857163,0.000024314591,0.00024033782,0.0004503217,0.0003608256,0.0003525498],"domain_scores_gemma":[0.9989034,0.0005685715,0.000035158446,0.00025088922,0.000018876644,0.0002231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014746696,0.00024385352,0.0002002542,0.00013545962,0.00017515747,0.0002440634,0.00037426577,0.00009072296,0.000010563992],"category_scores_gemma":[0.00028322014,0.00026903764,0.000054285658,0.00029648916,0.00001766242,0.000739042,0.000013370166,0.00057262904,0.000018855046],"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":[0.0000106638845,0.00006424927,0.0021500974,0.00011645367,0.000092297436,0.000035331712,0.002881813,0.82990164,0.07588861,0.00012325613,0.00010529797,0.088630304],"study_design_scores_gemma":[0.0007475851,0.00025724413,0.0025731935,0.00015834061,0.000019893507,0.00003410245,0.0000768225,0.79116714,0.20320813,0.0000071655695,0.0009450286,0.0008053215],"about_ca_topic_score_codex":0.00002148309,"about_ca_topic_score_gemma":0.0000013178917,"teacher_disagreement_score":0.8329566,"about_ca_system_score_codex":0.000097431854,"about_ca_system_score_gemma":0.000018979868,"threshold_uncertainty_score":0.99997616},"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":"W3120403074","doi":"10.1109/tse.2021.3101818","title":"Combining Genetic Programming and Model Checking to Generate Environment Assumptions","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Evolutionary Algorithms and Applications","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":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; H2020 Excellent Science; Fonds National de la Recherche Luxembourg","keywords":"Component (thermodynamics); Computer science; Spurious relationship; Soundness; Flexibility (engineering); Benchmark (surveying); Genetic programming; Software; State (computer science); Artificial intelligence; Machine learning; Algorithm; Programming language; Mathematics","score_opus":0.01687721823519412,"score_gpt":0.22193729267168105,"score_spread":0.20506007443648694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120403074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037161645,0.00034178642,0.96092534,0.00014384814,0.00043171985,0.00042430693,0.000026373697,0.0005425692,0.0000023833718],"genre_scores_gemma":[0.34159747,0.00013816833,0.6575085,0.000046302306,0.000040879564,0.0005659912,0.0000075146886,0.000034540608,0.000060616676],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981495,0.000020608695,0.00034018402,0.00083345553,0.00028813886,0.00036811712],"domain_scores_gemma":[0.9988366,0.00006578551,0.00006491358,0.0007455483,0.000051453426,0.00023574856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011217147,0.00034999102,0.00027333017,0.00023857094,0.00032219698,0.00033770094,0.0004332411,0.00018158797,0.0000068343575],"category_scores_gemma":[0.0000054393126,0.0004353379,0.00012897074,0.00023938976,0.000019930045,0.0001752437,0.00005714732,0.000663642,0.000011512099],"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":[5.2101757e-7,0.000079640056,0.000008014719,0.000049557242,0.00004515283,0.000006306982,0.00048195728,0.97264224,0.00046320356,0.000099015655,0.000005028653,0.026119381],"study_design_scores_gemma":[0.000115189505,0.000024922263,0.00037024962,0.00017213108,0.000035845664,0.000023135606,0.000016450083,0.9972289,0.001308784,0.000043278153,0.0002162253,0.00044486538],"about_ca_topic_score_codex":0.00001376333,"about_ca_topic_score_gemma":0.0000022993056,"teacher_disagreement_score":0.30443582,"about_ca_system_score_codex":0.00018606456,"about_ca_system_score_gemma":0.00009169854,"threshold_uncertainty_score":0.99980986},"labels":[],"label_agreement":null},{"id":"W3127656560","doi":"10.1109/tse.2021.3055123","title":"Deprecation of Packages and Releases in Software Ecosystems: A Case Study on NPM","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Notation; Software; Code (set theory); Programming language; Software engineering; Information retrieval; World Wide Web; Arithmetic; Mathematics; Set (abstract data type)","score_opus":0.01918480495773581,"score_gpt":0.2594253268007716,"score_spread":0.24024052184303582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127656560","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":[0.46297258,0.00012220272,0.536143,0.00000867701,0.00024370757,0.00019077637,0.000009724074,0.00030838136,9.1626094e-7],"genre_scores_gemma":[0.97366506,0.00002562358,0.026087787,0.000009060186,0.000020137462,0.00012537051,0.0000011579887,0.000038900394,0.000026888045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99829894,0.00008466665,0.00037036027,0.000541891,0.00038664846,0.00031748402],"domain_scores_gemma":[0.9972203,0.0017631447,0.0000458897,0.00071165856,0.00013062757,0.00012843055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027271855,0.00024069438,0.00031395257,0.00055746234,0.00007857987,0.00008068495,0.00025077397,0.00009615996,0.000007155922],"category_scores_gemma":[0.00049206195,0.00026984187,0.000071429895,0.0010060626,0.00001525309,0.0003134345,0.000010369785,0.00040111793,0.0000074552654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003762337,0.0019596694,0.0413812,0.0008301274,0.0002527932,0.0064884564,0.006486697,0.87774795,0.0015859135,0.000070862414,0.000054339314,0.06310439],"study_design_scores_gemma":[0.014915533,0.0059802374,0.21150035,0.0062437374,0.00030581956,0.01851615,0.008164779,0.33718273,0.3902835,0.00012513722,0.0006797326,0.0061023072],"about_ca_topic_score_codex":0.00015374161,"about_ca_topic_score_gemma":0.00015389895,"teacher_disagreement_score":0.5405652,"about_ca_system_score_codex":0.00014009798,"about_ca_system_score_gemma":0.000088743946,"threshold_uncertainty_score":0.9999754},"labels":[],"label_agreement":null},{"id":"W3132847876","doi":"10.1109/tse.2021.3060918","title":"Studying Duplicate Logging Statements and Their Relationships With Code Clones","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Logging; Code (set theory); Programming language; Database; Software engineering; Ecology","score_opus":0.040146525901182346,"score_gpt":0.26808989881282014,"score_spread":0.2279433729116378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132847876","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":[0.12675348,0.00016029179,0.8715592,0.00009666518,0.00024353428,0.00015336156,0.0000128234615,0.0010153687,0.0000052715495],"genre_scores_gemma":[0.9015534,0.000044034583,0.09810003,0.000025292587,0.000019939338,0.00008103437,0.0000021840156,0.000046937508,0.0001271706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848396,0.000049460996,0.00022728175,0.0005261565,0.0002966864,0.00041645093],"domain_scores_gemma":[0.9979808,0.0011259298,0.000033091106,0.0005766439,0.0001129309,0.00017063857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003068354,0.0002550991,0.00020990531,0.00025933963,0.0002980692,0.00020266978,0.0002982404,0.00007039555,0.0000064716896],"category_scores_gemma":[0.000104727405,0.00023749749,0.00004845879,0.00069402234,0.000025724605,0.00061035936,0.000012460657,0.0005849266,0.000014326913],"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":[0.000015761996,0.00017418526,0.007623129,0.00020922361,0.0002686055,0.00013803985,0.0020678183,0.9691911,0.0020193632,0.00027832732,0.000043273747,0.017971212],"study_design_scores_gemma":[0.0046881572,0.00061043527,0.0938223,0.0014740136,0.000114929564,0.0010285953,0.0009913476,0.6831982,0.20454755,0.00029045984,0.0059017185,0.0033322982],"about_ca_topic_score_codex":0.000007835027,"about_ca_topic_score_gemma":0.000010558351,"teacher_disagreement_score":0.7747999,"about_ca_system_score_codex":0.00010426298,"about_ca_system_score_gemma":0.00006952613,"threshold_uncertainty_score":0.96848667},"labels":[],"label_agreement":null},{"id":"W3133304533","doi":"10.1109/tse.2021.3058985","title":"A Study of C/C++ Code Weaknesses on Stack Overflow","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":48,"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; Polytechnique Montréal; University of Manitoba; Concordia University; Huawei Technologies (Canada)","funders":"","keywords":"Notation; Computer science; Code (set theory); Stack (abstract data type); Programming language; Mathematical notation; Software; Theoretical computer science; Mathematics; Arithmetic","score_opus":0.02446365343770417,"score_gpt":0.26541750701339983,"score_spread":0.24095385357569565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133304533","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":[0.29983684,0.00004150505,0.6984506,0.000019580728,0.00080351374,0.00016360208,0.000015408947,0.00066066446,0.000008239607],"genre_scores_gemma":[0.97318524,0.000016325479,0.02644163,0.000021575052,0.000035185934,0.000076456454,9.604538e-7,0.000050087623,0.00017255369],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979761,0.000047030648,0.0003232278,0.00054386334,0.0007083091,0.00040145408],"domain_scores_gemma":[0.9972559,0.0013052246,0.000039783154,0.0010756142,0.00017562439,0.00014783988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017991851,0.00026517725,0.00031286693,0.00037900492,0.00009277453,0.000088155866,0.0005912341,0.000088257315,0.000040703897],"category_scores_gemma":[0.00026586305,0.00029156666,0.00011810221,0.0012001826,0.000015193908,0.00027812313,0.000010803065,0.0004850907,0.0000414482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015609528,0.001037542,0.0006261266,0.00009592081,0.00013703204,0.00019585076,0.0010238327,0.9895487,0.001127787,0.00011258392,0.00007657841,0.0060024657],"study_design_scores_gemma":[0.0069749514,0.0044740434,0.038982127,0.001265102,0.00014678674,0.00029909707,0.00094711717,0.15302683,0.7883785,0.000057896923,0.00257567,0.0028719069],"about_ca_topic_score_codex":0.000013789214,"about_ca_topic_score_gemma":0.000012810845,"teacher_disagreement_score":0.83652186,"about_ca_system_score_codex":0.00012326118,"about_ca_system_score_gemma":0.000116355615,"threshold_uncertainty_score":0.9999536},"labels":[],"label_agreement":null},{"id":"W3134221463","doi":"10.1109/tse.2021.3064953","title":"Uncovering the Benefits and Challenges of Continuous Integration Practices","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":60,"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":"Computer science; Context (archaeology); Best practice; Suite; Process (computing); Software; Process management; Quality (philosophy); Knowledge management; Software development; Software development process; Data science; Software engineering; Business; Management","score_opus":0.032604655657231134,"score_gpt":0.25456562614295214,"score_spread":0.221960970485721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134221463","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":[0.071406394,0.004128553,0.9231414,0.000347798,0.0005339604,0.00009968272,0.0000050317813,0.00032835838,0.000008814946],"genre_scores_gemma":[0.9572959,0.0018668623,0.04070342,0.000017448912,0.000032289998,0.000035898607,4.3284945e-7,0.000022186776,0.000025542278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989364,0.000035350167,0.00019758254,0.0003047517,0.0003077674,0.00021815738],"domain_scores_gemma":[0.997426,0.0017961281,0.00008022261,0.00048031675,0.00015131352,0.0000660474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002762338,0.00015356396,0.00017168905,0.00013472361,0.000088226334,0.00009601186,0.0003103977,0.00006996076,0.0000055447003],"category_scores_gemma":[0.00063342473,0.0001331709,0.000060550025,0.00040004816,0.000023038298,0.00042724673,0.000009948462,0.00032983685,0.0000039128604],"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":[0.000010756708,0.00011791072,0.0002828274,0.00026387963,0.00014301394,0.000033570617,0.0017781316,0.5454191,0.004014266,0.0034181143,0.00001536937,0.44450307],"study_design_scores_gemma":[0.0017711603,0.000664061,0.038092468,0.0017936549,0.00012775871,0.0007662913,0.00095181394,0.16580021,0.7833431,0.00023723625,0.004859565,0.0015927213],"about_ca_topic_score_codex":0.00001713329,"about_ca_topic_score_gemma":0.000014959689,"teacher_disagreement_score":0.88588953,"about_ca_system_score_codex":0.000041257328,"about_ca_system_score_gemma":0.000053102878,"threshold_uncertainty_score":0.5430552},"labels":[],"label_agreement":null},{"id":"W3136085434","doi":"10.1109/tse.2021.3066330","title":"Continuously Managing NFRs: Opportunities and Challenges in Practice","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":28,"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":"Maintainability; Computer science; Agile software development; Software; Risk analysis (engineering); Software engineering; Process management; Engineering; Business","score_opus":0.040420160785735494,"score_gpt":0.2368191328294542,"score_spread":0.1963989720437187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136085434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007206269,0.0037006584,0.9860699,0.0014121083,0.00083934964,0.0001068188,0.0000024744202,0.00050380593,0.0001585979],"genre_scores_gemma":[0.892708,0.015918022,0.090854734,0.00021901345,0.000053007596,0.00007855948,8.8006175e-7,0.000031570216,0.00013620997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988699,0.00005194086,0.00024372256,0.0003772673,0.00019769906,0.00025945238],"domain_scores_gemma":[0.99893636,0.0004325723,0.000037788548,0.0004147818,0.00009355993,0.000084947926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033343176,0.00016605807,0.00020474633,0.00018513403,0.00008188688,0.00010369103,0.0001792319,0.0000836983,0.000005869335],"category_scores_gemma":[0.00006795694,0.00017521181,0.000050996536,0.00025655047,0.000019440331,0.00094519457,0.0000063542384,0.00026081357,0.000008063831],"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":[0.000027591263,0.00038161303,0.00038387405,0.0011352849,0.0001761622,0.00092257035,0.006210209,0.110798694,0.00014361467,0.004279982,0.000042075833,0.87549835],"study_design_scores_gemma":[0.01068044,0.0015324597,0.02709817,0.007980063,0.00042524704,0.007976495,0.023020113,0.5893746,0.053136364,0.0010278731,0.26952323,0.008224923],"about_ca_topic_score_codex":0.000015960613,"about_ca_topic_score_gemma":0.000011786388,"teacher_disagreement_score":0.8952152,"about_ca_system_score_codex":0.000063268715,"about_ca_system_score_gemma":0.000060740702,"threshold_uncertainty_score":0.71449304},"labels":[],"label_agreement":null},{"id":"W3144273096","doi":"10.1109/tse.2021.3068901","title":"On the Untriviality of Trivial Packages: An Empirical Study of npm JavaScript Packages","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University; Concordia University","funders":"","keywords":"Computer science; JavaScript; Programming language; Empirical research; Software engineering","score_opus":0.0341506444947318,"score_gpt":0.29139461396325345,"score_spread":0.2572439694685216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144273096","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":[0.44585767,0.000024354295,0.5530416,0.000049568513,0.00053193705,0.00020256013,0.000016094667,0.00027328904,0.0000029534688],"genre_scores_gemma":[0.9921668,0.000010405021,0.007581692,0.00003496109,0.00004855124,0.000065550754,0.0000014170606,0.00004249572,0.000048118367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99736696,0.00022809855,0.0005062296,0.0005582357,0.0009250509,0.00041541105],"domain_scores_gemma":[0.99491507,0.0030599718,0.00007688013,0.0015242712,0.00025998356,0.00016380417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065421395,0.0002937585,0.00042956744,0.00031910138,0.00012850967,0.00007855886,0.00092769274,0.00012443261,0.00005491297],"category_scores_gemma":[0.0007596868,0.00024967585,0.00019195973,0.0013839052,0.000051536765,0.00029460492,0.000016973163,0.0006570798,0.000010975067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001244017,0.00677467,0.009841063,0.0003715215,0.0007372037,0.00022240936,0.0104110725,0.9448087,0.0076140803,0.0007613702,0.00056503987,0.017768461],"study_design_scores_gemma":[0.0070883376,0.006921196,0.17225677,0.0008294731,0.0002800398,0.00013251073,0.0019978108,0.12336941,0.6834859,0.00040048064,0.00070386555,0.0025342007],"about_ca_topic_score_codex":0.000039546805,"about_ca_topic_score_gemma":0.000017345872,"teacher_disagreement_score":0.82143927,"about_ca_system_score_codex":0.00010306995,"about_ca_system_score_gemma":0.00014345268,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W3148779029","doi":"10.1109/tse.2020.2988396","title":"A3: Assisting Android API Migrations Using Code Examples","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Android (operating system); Computer science; Documentation; Application programming interface; Source code; World Wide Web; Java; Operating system","score_opus":0.051130970689089575,"score_gpt":0.26172621043122185,"score_spread":0.2105952397421323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148779029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031226186,0.00018074126,0.9651491,0.00017353676,0.0006164315,0.0001981015,0.00003273779,0.0024185868,0.000004595515],"genre_scores_gemma":[0.69280916,0.000011204707,0.30686414,0.00009427991,0.00010312345,0.00003641406,0.0000019224633,0.00005509336,0.000024675533],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979891,0.000033551536,0.00034013626,0.0005922145,0.00050183554,0.00054316624],"domain_scores_gemma":[0.9979861,0.0009814366,0.00004689397,0.0005323755,0.00010245557,0.00035073733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018396102,0.0003066235,0.00026762657,0.00029324665,0.00027403276,0.00024189292,0.0007111119,0.00011532844,0.000032371765],"category_scores_gemma":[0.0004167848,0.00035224337,0.00014922862,0.0011825778,0.000026098645,0.000586871,0.000011630421,0.00058880495,0.000057954305],"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":[0.0000045957077,0.000040454088,0.00029771388,0.00007627805,0.000054938875,0.000033131353,0.0005345621,0.98231304,0.0060084076,0.00007878585,0.000113897026,0.01044418],"study_design_scores_gemma":[0.00038699474,0.00010364549,0.0010694185,0.00013468844,0.000023054488,0.00005419704,0.000018759898,0.9687724,0.02724702,0.000009060962,0.0016214846,0.0005592799],"about_ca_topic_score_codex":0.00002264588,"about_ca_topic_score_gemma":0.0000049976625,"teacher_disagreement_score":0.66158295,"about_ca_system_score_codex":0.00016142937,"about_ca_system_score_gemma":0.000103485945,"threshold_uncertainty_score":0.99989295},"labels":[],"label_agreement":null},{"id":"W3152301934","doi":"10.1109/tse.2021.3070269","title":"Software Batch Testing to Save Build Test Resources and to Reduce Feedback Time","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Commit; Test case; Test (biology); Reliability engineering; Database; Machine learning","score_opus":0.015497159235501757,"score_gpt":0.23784210009981144,"score_spread":0.22234494086430967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152301934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123801604,0.00010933559,0.87271565,0.00042600714,0.0005291929,0.00029172475,0.00003428763,0.0020806713,0.00001152207],"genre_scores_gemma":[0.36061427,0.0000066479397,0.6378374,0.00022844884,0.00013466792,0.00012924273,0.0000016920246,0.000108397275,0.0009392003],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970938,0.000036009733,0.00037533187,0.0010245531,0.00064169563,0.00082859286],"domain_scores_gemma":[0.9939859,0.003960755,0.00003249859,0.0010060235,0.00032010203,0.0006947441],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003238425,0.00042675063,0.00037740933,0.00054987235,0.00026552592,0.00041581367,0.00075925083,0.00015257348,0.00004193266],"category_scores_gemma":[0.0034788966,0.00050333916,0.00009830579,0.002520146,0.000023877436,0.00037767598,0.000052464944,0.00062112877,0.00033577142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018417802,0.00020328234,0.002305233,0.00022286225,0.00010104781,0.00028615075,0.001689305,0.8396984,0.03909521,0.000019342993,0.00126763,0.11509317],"study_design_scores_gemma":[0.0032397844,0.0024300846,0.10675252,0.0043431916,0.00016290689,0.0021569428,0.0001947315,0.18635707,0.6456618,0.00009395066,0.04150978,0.007097288],"about_ca_topic_score_codex":0.00003056922,"about_ca_topic_score_gemma":0.0000052906084,"teacher_disagreement_score":0.6533413,"about_ca_system_score_codex":0.0002267119,"about_ca_system_score_gemma":0.00012695522,"threshold_uncertainty_score":0.99974185},"labels":[],"label_agreement":null},{"id":"W3153182107","doi":"10.1109/tse.2021.3073773","title":"On the Relationship Between the Developer’s Perceptible Race and Ethnicity and the Evaluation of Contributions in OSS","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Hate Speech and Cyberbullying Detection","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 Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Ethnic group; Race (biology); Diversity (politics); White (mutation); Empirical research; Computer science; Open source software; Software; Data science; Sociology; Mathematics; Gender studies; Statistics","score_opus":0.04667324933384913,"score_gpt":0.28521615133311873,"score_spread":0.23854290199926959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153182107","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":[0.384363,0.00019724818,0.6138562,0.0008068576,0.00025620506,0.00044147394,0.000014012368,0.000058462327,0.000006557314],"genre_scores_gemma":[0.99662966,0.00009370292,0.0029593932,0.000041089395,0.00002668302,0.00021225816,0.0000035468495,0.000012937597,0.000020722347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826086,0.00046193143,0.00031240552,0.00034134006,0.0004436277,0.00017982433],"domain_scores_gemma":[0.9955473,0.0035538615,0.00009358568,0.0005666878,0.00019859987,0.00003996253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026530928,0.00019705296,0.0002441955,0.00014208329,0.00037141808,0.00016653021,0.0003462382,0.00018692853,0.000008086269],"category_scores_gemma":[0.00081257324,0.00012188514,0.00008661253,0.00046793607,0.00010207883,0.00012885898,0.000022938046,0.001237842,0.0000020389414],"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":[0.000031839234,0.000055302036,0.0013845743,0.000105170875,0.00015558967,0.0000017897612,0.007437002,0.95781356,0.0000981706,0.0042399396,0.000024704466,0.028652374],"study_design_scores_gemma":[0.0029909655,0.00011566186,0.39483994,0.0014730558,0.00046769498,0.000043708424,0.00068949524,0.5852584,0.007802969,0.005405179,0.00007543496,0.00083743304],"about_ca_topic_score_codex":0.000153977,"about_ca_topic_score_gemma":0.000094343195,"teacher_disagreement_score":0.61226666,"about_ca_system_score_codex":0.00014734664,"about_ca_system_score_gemma":0.0001662797,"threshold_uncertainty_score":0.5377876},"labels":[],"label_agreement":null},{"id":"W3156363234","doi":"10.1109/tse.2020.3023955","title":"PerfJIT: Test-Level Just-in-Time Prediction for Performance Regression Introducing Commits","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Concordia University","funders":"","keywords":"Commit; Computer science; Regression; Machine learning; Regression analysis; Regression testing; Test (biology); Artificial intelligence; Performance prediction; Linear regression; Code (set theory); Data mining; Statistics; Database; Software; Set (abstract data type); Programming language; Software system; Mathematics","score_opus":0.02316888172101865,"score_gpt":0.22436103631883705,"score_spread":0.20119215459781842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156363234","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":[0.109335974,0.000039797724,0.88792145,0.00026317232,0.0009845977,0.0004565727,0.00004447429,0.0009487269,0.000005246599],"genre_scores_gemma":[0.9306482,0.00003315564,0.068674885,0.00013965344,0.00021388255,0.00016421368,0.0000047559042,0.000037228932,0.000084019724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819607,0.00002219003,0.0004411816,0.0005949545,0.00034014136,0.00040548923],"domain_scores_gemma":[0.9987562,0.00041636397,0.0000679714,0.0004983884,0.00009942234,0.00016168227],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035258758,0.0002773084,0.0003082701,0.00019844528,0.00021879312,0.0000800721,0.0005559166,0.00015596802,0.000013565868],"category_scores_gemma":[0.00015321629,0.00025729503,0.00012865466,0.0006584282,0.000018813218,0.0007536393,0.000008125789,0.0004229586,0.00006256537],"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":[0.0000758587,0.0002104823,0.0070166267,0.0008669316,0.000034454883,0.000005089087,0.0021897946,0.9203896,0.0028468396,0.000008632999,0.0006258177,0.065729894],"study_design_scores_gemma":[0.00091090915,0.00042210083,0.006629386,0.0003924925,0.000016343418,0.00001633032,0.000017494789,0.966293,0.024043897,0.0000022160918,0.0009031984,0.0003526545],"about_ca_topic_score_codex":0.0000050438025,"about_ca_topic_score_gemma":8.7483437e-7,"teacher_disagreement_score":0.82131225,"about_ca_system_score_codex":0.00016336596,"about_ca_system_score_gemma":0.000062179446,"threshold_uncertainty_score":0.9999879},"labels":[],"label_agreement":null},{"id":"W3162606549","doi":"10.1109/tse.2021.3081171","title":"Context-Aware Personalized Crowdtesting Task Recommendation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Mobile Crowdsensing and Crowdsourcing","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":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Context (archaeology); Human–computer interaction; World Wide Web; Data science; Software engineering; Systems engineering","score_opus":0.013921702004545542,"score_gpt":0.21737926802816468,"score_spread":0.20345756602361914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162606549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007638204,0.00007701898,0.989564,0.00022333213,0.0012281131,0.00008412049,0.000010242594,0.0011195954,0.000055348653],"genre_scores_gemma":[0.9239711,0.00001264091,0.07520932,0.00028825094,0.000067231806,0.000028199322,0.000006623719,0.000036214376,0.00038039664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864006,0.000050479437,0.00026873715,0.0004790333,0.00020917578,0.00035252655],"domain_scores_gemma":[0.9988776,0.00036291056,0.000054841024,0.00041659272,0.00015395513,0.00013414345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018120505,0.00022613048,0.00021452316,0.000146565,0.0003002481,0.00023475039,0.00022104471,0.000096588556,0.00008783234],"category_scores_gemma":[0.00008031553,0.00026413106,0.00014871394,0.0005449879,0.000019610081,0.00037717784,0.0000066939656,0.0003781563,0.00004710636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015128571,0.00022197743,0.00007616022,0.00020166003,0.00016496574,0.00019524802,0.002158184,0.2604903,0.014731877,0.00079551834,0.00057734374,0.72037166],"study_design_scores_gemma":[0.0016114535,0.00011739459,0.0002074014,0.00066628034,0.00006261648,0.0006082026,0.00037109386,0.7999273,0.18099034,0.00007376265,0.01414662,0.0012175266],"about_ca_topic_score_codex":0.000014628521,"about_ca_topic_score_gemma":0.0000069525563,"teacher_disagreement_score":0.9163329,"about_ca_system_score_codex":0.00012264025,"about_ca_system_score_gemma":0.00008923561,"threshold_uncertainty_score":0.9999811},"labels":[],"label_agreement":null},{"id":"W3163202066","doi":"10.1109/tse.2021.3082068","title":"An Empirical Study of Type-Related Defects in Python Projects","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Python (programming language); Computer science; Programming language; Artificial intelligence","score_opus":0.025406470675922346,"score_gpt":0.2945407086543776,"score_spread":0.26913423797845526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163202066","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":[0.5163841,0.00003352632,0.482531,0.0000053562626,0.00044076674,0.00015953608,0.0000011656922,0.00044233867,0.000002154039],"genre_scores_gemma":[0.9796572,0.0000061933265,0.020189296,0.000009287319,0.000014054411,0.00004789592,0.00000116206,0.00004288311,0.000032043823],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822974,0.0000921057,0.00033956114,0.00051407854,0.00044894524,0.00037557294],"domain_scores_gemma":[0.9982844,0.000604029,0.000029727034,0.0007940101,0.00015268209,0.00013516286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026967903,0.00020789003,0.00027769007,0.0005376117,0.000047656173,0.00005512087,0.00045999853,0.00012452937,0.000016533659],"category_scores_gemma":[0.00023125524,0.00023246581,0.000066558074,0.0024076866,0.000012460007,0.00035540588,0.0000075878315,0.0005592165,0.000015221786],"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":[0.000013005874,0.0013081303,0.017454686,0.000074248106,0.000053113345,0.0002602431,0.0030024184,0.9711639,0.0028446075,0.000014023731,0.000011246453,0.0038003589],"study_design_scores_gemma":[0.004672013,0.0034592645,0.24725275,0.0005214025,0.000059331098,0.0002203007,0.00064232317,0.6090955,0.13233107,0.00003708325,0.00013299737,0.0015759631],"about_ca_topic_score_codex":0.000028160184,"about_ca_topic_score_gemma":0.000027431566,"teacher_disagreement_score":0.46327305,"about_ca_system_score_codex":0.00013438021,"about_ca_system_score_gemma":0.0001594265,"threshold_uncertainty_score":0.94796807},"labels":[],"label_agreement":null},{"id":"W3167387776","doi":"10.1109/tse.2021.3083715","title":"LogAssist: Assisting Log Analysis Through Log Summarization","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Polytechnique Montréal; Concordia University","funders":"","keywords":"Computer science; Automatic summarization; Workflow; Debugging; Event (particle physics); Information retrieval; Data mining; Programming language; Database","score_opus":0.013454505144419968,"score_gpt":0.23017273441904804,"score_spread":0.21671822927462808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167387776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008568943,0.000108346234,0.98844385,0.000087022694,0.001543952,0.00009990248,0.000013474014,0.0010692414,0.00006528049],"genre_scores_gemma":[0.8385032,0.000033984168,0.16099395,0.000116234594,0.00006300619,0.00003817664,0.00001146729,0.000021833746,0.00021816912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818987,0.000054633452,0.0004118876,0.0006033161,0.00036736322,0.00037292545],"domain_scores_gemma":[0.99845356,0.00032108685,0.0000808037,0.0008434422,0.00020282478,0.00009829106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022939454,0.0002657026,0.00037518196,0.00025419015,0.0002739386,0.00015920079,0.00037084363,0.00016695925,0.000056376226],"category_scores_gemma":[0.00008961248,0.00025245873,0.00034768233,0.0025546807,0.000022509783,0.000670776,0.0000076064994,0.00032889715,0.000052502728],"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":[0.000003971909,0.00013392142,0.004149628,0.000112966656,0.00046424585,0.000041335243,0.0003848039,0.97957706,0.00031459745,0.00023983249,0.00006664304,0.014510975],"study_design_scores_gemma":[0.0011875791,0.00015519632,0.0298125,0.00032901106,0.00091388763,0.0001342684,0.00009854229,0.8839656,0.07611509,0.00016448203,0.005398187,0.0017256237],"about_ca_topic_score_codex":0.000031578154,"about_ca_topic_score_gemma":0.000022955948,"teacher_disagreement_score":0.82993424,"about_ca_system_score_codex":0.00017929805,"about_ca_system_score_gemma":0.00010601524,"threshold_uncertainty_score":0.9999928},"labels":[],"label_agreement":null},{"id":"W3170417470","doi":"10.1109/tse.2021.3124332","title":"AI-Enabled Automation for Completeness Checking of Privacy Policies","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Privacy policy; Completeness (order theory); General Data Protection Regulation; Information privacy; Privacy software; Privacy by Design; Privacy law; Computer security; Data Protection Act 1998","score_opus":0.03746098878162252,"score_gpt":0.3041413051598377,"score_spread":0.2666803163782152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170417470","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":[0.040878035,0.00014600709,0.954762,0.00029288718,0.0020755613,0.0008906497,0.00025137045,0.00068460294,0.000018912622],"genre_scores_gemma":[0.9611787,0.00017570952,0.037694782,0.00005467756,0.00030304573,0.0003921834,0.00008763518,0.000056686815,0.000056573463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982049,0.00008529575,0.0004692888,0.00042424086,0.0004241877,0.00039209743],"domain_scores_gemma":[0.9984815,0.0003020449,0.00019377617,0.0005700617,0.00034693145,0.000105692176],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005282048,0.00028379663,0.0004610938,0.00036714622,0.00046129446,0.00020152432,0.0005515407,0.00041532033,0.000048593618],"category_scores_gemma":[0.00045718736,0.00035149403,0.0003033048,0.000381407,0.00006986603,0.00038260847,0.00002403979,0.0005943108,0.0000022698712],"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":[0.00010891609,0.0005914418,0.0001313565,0.0052644415,0.00062593305,0.000006003992,0.041148126,0.92068887,0.0050740954,0.0017245251,0.0005176851,0.024118638],"study_design_scores_gemma":[0.0072236448,0.0007617965,0.007446149,0.013464909,0.0021615128,0.00003574529,0.012703984,0.45498714,0.3986964,0.009275057,0.08469329,0.008550383],"about_ca_topic_score_codex":0.0021696053,"about_ca_topic_score_gemma":0.000300647,"teacher_disagreement_score":0.92030066,"about_ca_system_score_codex":0.00034749825,"about_ca_system_score_gemma":0.00037333686,"threshold_uncertainty_score":0.9998937},"labels":[],"label_agreement":null},{"id":"W3173415420","doi":"10.1109/tse.2021.3092692","title":"An Experience Report on Producing Verifiable Builds for Large-Scale Commercial Systems","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Reliability and Analysis Research","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":"York University; Huawei Technologies (Canada)","funders":"","keywords":"Toolchain; Verifiable secret sharing; Computer science; Software engineering; Process (computing); TRACE (psycholinguistics); Code (set theory); Software; Notation; Programming language; Theoretical computer science; Set (abstract data type)","score_opus":0.019071393867009387,"score_gpt":0.28494894857246433,"score_spread":0.26587755470545493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173415420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05915898,0.000060774262,0.93842775,0.000073327596,0.0013230665,0.00027084074,0.000026978321,0.0006509307,0.0000073836877],"genre_scores_gemma":[0.90162075,0.000015912863,0.0974132,0.000062502775,0.00015425977,0.00036560913,0.000012034584,0.00003645412,0.00031926183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976586,0.00006207681,0.00038043922,0.00085953326,0.00051011593,0.0005292224],"domain_scores_gemma":[0.9977643,0.00036937968,0.000051150102,0.0013295211,0.00028172965,0.0002039018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005666261,0.00022132446,0.00031161096,0.00019808105,0.0003926388,0.00030399364,0.00052733644,0.000120863515,0.000017394144],"category_scores_gemma":[0.00018586287,0.00023584127,0.00019002768,0.0008251245,0.000018126677,0.00054047967,0.000006147263,0.0003509243,0.000012699002],"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":[0.000019329163,0.0005260607,0.00029147405,0.00016430265,0.000058126872,0.000104801,0.0013755418,0.98758614,0.0018183114,0.00021363556,0.00010313382,0.007739155],"study_design_scores_gemma":[0.00063729857,0.00031577662,0.0006341088,0.0002492036,0.00003064666,0.00017146066,0.00023877833,0.8860283,0.100975886,0.000018326666,0.010042803,0.0006574086],"about_ca_topic_score_codex":0.000045231296,"about_ca_topic_score_gemma":0.000013098543,"teacher_disagreement_score":0.84246176,"about_ca_system_score_codex":0.00015679712,"about_ca_system_score_gemma":0.00014785078,"threshold_uncertainty_score":0.9617328},"labels":[],"label_agreement":null},{"id":"W3187068675","doi":"10.1109/tse.2021.3099532","title":"What Makes Agile Software Development Agile?","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":87,"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 Calgary","funders":"European Regional Development Fund; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Christian Doppler Forschungsgesellschaft; Bundesministerium für Digitalisierung und Wirtschaftsstandort; Science Foundation Ireland; Ministerio de Ciencia, Innovación y Universidades; Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung","keywords":"Agile software development; Extreme programming practices; Computer science; Agile Unified Process; Lean software development; Software development; Software; Agile usability engineering; Process management; Process (computing); Software development process; Empirical research; Software engineering; Knowledge management; Engineering management; Engineering","score_opus":0.016053542016305346,"score_gpt":0.23468772974138075,"score_spread":0.2186341877250754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187068675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00397549,0.0008223358,0.9868106,0.00012757804,0.0038019968,0.00015680886,0.0000069093426,0.004286204,0.000012068348],"genre_scores_gemma":[0.09894333,0.00036177188,0.89937365,0.00027124817,0.00008775509,0.00015789461,0.000007727683,0.00008149075,0.0007151356],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978738,0.000038281687,0.0004011005,0.0006702066,0.00047284877,0.0005437536],"domain_scores_gemma":[0.99801254,0.00062136026,0.00007316171,0.00090114743,0.00017544672,0.00021632481],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002404745,0.0004008151,0.00031041467,0.0002750965,0.00024667627,0.00060850626,0.0006719906,0.000185897,0.00011886915],"category_scores_gemma":[0.00012983267,0.00045045308,0.00017386289,0.00080688455,0.000017248127,0.0018922862,0.000017347014,0.00058023894,0.00012236276],"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":[0.00001729398,0.00045744574,0.00010892012,0.00036817955,0.0003621421,0.000604023,0.0020927188,0.4615483,0.0022104327,0.00078064384,0.0013561773,0.5300937],"study_design_scores_gemma":[0.0009249193,0.00019698252,0.0009385581,0.0012885224,0.00008100164,0.0006935001,0.0001287842,0.032571543,0.7075327,0.00018081711,0.25291106,0.0025515992],"about_ca_topic_score_codex":0.0000054051184,"about_ca_topic_score_gemma":0.000005798309,"teacher_disagreement_score":0.70532227,"about_ca_system_score_codex":0.00017872915,"about_ca_system_score_gemma":0.00018035341,"threshold_uncertainty_score":0.9997947},"labels":[],"label_agreement":null},{"id":"W3196126762","doi":"10.1109/tse.2021.3106247","title":"Dependency Smells in JavaScript Projects","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":51,"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; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code smell; Computer science; Dependency (UML); Commit; JavaScript; Code refactoring; Dependency graph; Software engineering; Security bug; World Wide Web; Popularity; Computer security; Data science; Software; Software development; Software quality; Software security assurance; Database; Programming language; Information security","score_opus":0.018662997445303465,"score_gpt":0.2381131029342694,"score_spread":0.21945010548896593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196126762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043638412,0.00022433046,0.953329,0.000054529773,0.0014320513,0.00017780875,0.000005335685,0.0011117358,0.000026789472],"genre_scores_gemma":[0.87504065,0.00004649759,0.12426049,0.000052375253,0.000041958232,0.00010573531,0.0000012825102,0.00004970414,0.0004012922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99793136,0.000040839557,0.00029906174,0.0006098809,0.00051291665,0.00060595555],"domain_scores_gemma":[0.9982406,0.0006520613,0.000021704842,0.00080802443,0.00011040756,0.00016720446],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024305764,0.00025917945,0.000245571,0.0005340423,0.00007170553,0.0001446179,0.00060727063,0.00013761445,0.000051154253],"category_scores_gemma":[0.00027753948,0.0003047257,0.0001238555,0.0016221526,0.000013064605,0.000519379,0.000010370776,0.0007010798,0.00011785681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000106403495,0.00045360526,0.003134943,0.0002658175,0.00009642276,0.0013135484,0.0012548402,0.93593675,0.0050959555,0.00042124707,0.00019561073,0.051820625],"study_design_scores_gemma":[0.0032643466,0.00036129897,0.030049348,0.0010676534,0.000035672547,0.000807669,0.00012162756,0.3396421,0.6172516,0.0002073518,0.0044430215,0.002748335],"about_ca_topic_score_codex":0.000027034226,"about_ca_topic_score_gemma":0.00002047218,"teacher_disagreement_score":0.83140224,"about_ca_system_score_codex":0.00024383812,"about_ca_system_score_gemma":0.00021492675,"threshold_uncertainty_score":0.9999405},"labels":[],"label_agreement":null},{"id":"W3199338376","doi":"10.1109/tse.2021.3112503","title":"How Templated Requirements Specifications Inhibit Creativity in Software Engineering","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","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":"Dalhousie University","funders":"","keywords":"Computer science; Formality; Creativity; Coding (social sciences); Software engineering; Requirements engineering; Software; Engineering design process; Software requirements specification; Stakeholder; TRIZ; Software requirements; Software design; Human–computer interaction; Software development; Programming language; Artificial intelligence; Psychology","score_opus":0.04554699575861654,"score_gpt":0.25256362273964506,"score_spread":0.20701662698102852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199338376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009971773,0.0002088639,0.9852282,0.00025224595,0.0010251104,0.00025092784,0.000027046599,0.003021348,0.000014491734],"genre_scores_gemma":[0.5373809,0.000091759954,0.4619907,0.000041265146,0.0000526437,0.00013587493,0.000008478153,0.000063129344,0.00023526928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777156,0.00004911574,0.00041779634,0.00073884573,0.00044139448,0.0005812775],"domain_scores_gemma":[0.99779224,0.00078607,0.00009004079,0.0010009466,0.0001380687,0.00019262075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029949239,0.0004274259,0.00037493426,0.0005532386,0.00014085522,0.00041396808,0.0005839431,0.00021854581,0.00003500857],"category_scores_gemma":[0.00049758673,0.0005117061,0.00016955072,0.0017258755,0.000016469234,0.0013352768,0.000017460601,0.0007880309,0.000022863363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024829807,0.0007791593,0.0017780169,0.00039642153,0.00026682726,0.00068052864,0.0009130319,0.94345033,0.011491184,0.0027227865,0.00043456515,0.0370623],"study_design_scores_gemma":[0.0029901087,0.00043091754,0.014395854,0.0021552616,0.00014751423,0.00070448767,0.00011052239,0.35399994,0.559473,0.00025036169,0.06081108,0.004530969],"about_ca_topic_score_codex":0.000022680273,"about_ca_topic_score_gemma":0.000013060931,"teacher_disagreement_score":0.5894504,"about_ca_system_score_codex":0.00030585742,"about_ca_system_score_gemma":0.00010103293,"threshold_uncertainty_score":0.99973345},"labels":[],"label_agreement":null},{"id":"W3204491293","doi":"10.1109/tse.2021.3115772","title":"Characterizing and Mitigating Self-Admitted Technical Debt in Build Systems","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Technical debt; Software engineering; Operating system; Software; Software development","score_opus":0.009912218925696303,"score_gpt":0.22976416783745449,"score_spread":0.2198519489117582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204491293","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":[0.1981704,0.00025312524,0.7992113,0.000059797338,0.0006420232,0.00015281852,0.0000047264894,0.0015000677,0.0000056991103],"genre_scores_gemma":[0.8763486,0.00004832565,0.12334776,0.000032595068,0.000043802538,0.000105492596,0.0000013188799,0.0000443095,0.000027756123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981438,0.000046535526,0.00035300804,0.0005655043,0.00037019013,0.00052096474],"domain_scores_gemma":[0.998132,0.0010260086,0.00003258552,0.0005296486,0.000085085936,0.00019470748],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030310798,0.0002530493,0.000288358,0.0003972051,0.00010290768,0.0002418083,0.00035884153,0.0001607062,0.0000053816357],"category_scores_gemma":[0.0002454148,0.00029897978,0.00007009012,0.0010946017,0.00001538211,0.00044624758,0.000015087696,0.00073083356,0.0000135899],"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":[0.000023480266,0.00080400694,0.018166352,0.0018936242,0.0003228468,0.0021935601,0.002729587,0.75749224,0.17620803,0.0019657346,0.00006771844,0.038132798],"study_design_scores_gemma":[0.0020413029,0.00021961053,0.067242935,0.002180165,0.000040956304,0.0017786741,0.00010311557,0.77594686,0.14692809,0.000027166438,0.0014874836,0.00200366],"about_ca_topic_score_codex":0.000019372728,"about_ca_topic_score_gemma":0.000004482485,"teacher_disagreement_score":0.67817825,"about_ca_system_score_codex":0.000217544,"about_ca_system_score_gemma":0.0000935046,"threshold_uncertainty_score":0.99994624},"labels":[],"label_agreement":null},{"id":"W3207487452","doi":"10.1109/tse.2021.3117966","title":"Pluto: Exposing Vulnerabilities in Inter-Contract Scenarios","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Blockchain Technology Applications and Security","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 Waterloo","funders":"","keywords":"Computer science; Reachability; Pluto; Symbolic execution; Computer security; Smart contract; Vulnerability (computing); False positive paradox; Fuzz testing; Programming language; Artificial intelligence; Theoretical computer science; Software","score_opus":0.008612286267831283,"score_gpt":0.21405317482825034,"score_spread":0.20544088856041906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207487452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086510114,0.00012835342,0.9118881,0.0002240457,0.00040363363,0.00009854719,0.000004163531,0.00072414236,0.00001886796],"genre_scores_gemma":[0.89384407,0.0000174576,0.105897,0.00007926757,0.000014872236,0.00009399946,6.703778e-7,0.000014014106,0.00003864345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896276,0.00001942016,0.00024453143,0.00038375813,0.00011399542,0.00027554223],"domain_scores_gemma":[0.9990617,0.00021629668,0.000025094665,0.0005882079,0.000053849268,0.000054853703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013423778,0.00015557231,0.00017680168,0.00022571694,0.00010830128,0.00007233595,0.0003447721,0.00013885464,0.000025856438],"category_scores_gemma":[0.000035930203,0.00017948366,0.000080368496,0.0005947338,0.000025126496,0.00023928445,0.0000057960583,0.0005393181,0.000014597424],"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":[0.000012875206,0.00097422267,0.00072112895,0.00015404684,0.00010841319,0.000228163,0.00427111,0.62480414,0.0075649065,0.030482084,0.00006302272,0.3306159],"study_design_scores_gemma":[0.0011451169,0.00012405487,0.002057578,0.00035614677,0.000019527395,0.00024102457,0.00019789321,0.76484424,0.22568148,0.001599241,0.0027586964,0.0009749741],"about_ca_topic_score_codex":0.00003401926,"about_ca_topic_score_gemma":0.00007951817,"teacher_disagreement_score":0.80733395,"about_ca_system_score_codex":0.00012720693,"about_ca_system_score_gemma":0.00006043034,"threshold_uncertainty_score":0.73191315},"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":"W4212906466","doi":"10.1109/tse.2022.3152148","title":"An Empirical Study of Yanked Releases in the Rust Package Registry","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Huawei Technologies (Canada); University of Alberta","funders":"University of Alberta","keywords":"Computer science; Rust (programming language); Software versioning; Dependency (UML); Software package; Code (set theory); Software release life cycle; Software; Software engineering; Operating system; World Wide Web; Database; Programming language; Software development; Software quality","score_opus":0.024242124774664125,"score_gpt":0.28821594235437353,"score_spread":0.2639738175797094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212906466","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":[0.448713,0.000019823552,0.55045074,0.000028695971,0.00025260155,0.00022451727,0.000009412898,0.00029974742,0.000001469741],"genre_scores_gemma":[0.9922105,0.0000027616277,0.007365766,0.00003878911,0.000023545432,0.00030639634,0.0000014767314,0.00003112243,0.00001960637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.997937,0.0001815119,0.00031039756,0.00041691703,0.00080700906,0.00034715564],"domain_scores_gemma":[0.9974466,0.0011563173,0.000041485462,0.0012322202,0.00003871856,0.00008468826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005706231,0.00018904314,0.00021076603,0.00043488902,0.00019539308,0.00006648388,0.0015174487,0.000045373537,0.000032473847],"category_scores_gemma":[0.00012209844,0.00017767819,0.000079705605,0.0015549599,0.00001998346,0.00026217577,0.000013458004,0.0008751864,0.000004236066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001938653,0.0014032488,0.005700928,0.00003083904,0.000028548133,0.00013131798,0.004706809,0.9844118,0.0002388504,0.00001900621,0.000104260886,0.0032050258],"study_design_scores_gemma":[0.008073694,0.01162929,0.48145455,0.0002328786,0.00012541232,0.0007084271,0.012711396,0.4666667,0.010915831,0.00007241462,0.0042660087,0.003143415],"about_ca_topic_score_codex":0.000093001385,"about_ca_topic_score_gemma":0.000014328285,"teacher_disagreement_score":0.5434975,"about_ca_system_score_codex":0.00015400708,"about_ca_system_score_gemma":0.000066973924,"threshold_uncertainty_score":0.72455066},"labels":[],"label_agreement":null},{"id":"W4213075374","doi":"10.1109/tse.2018.2872711","title":"An Interactive and Dynamic Search-Based Approach to Software Refactoring Recommendations","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":64,"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":"Ford Motor Company","keywords":"Code refactoring; Computer science; Software; Software engineering; Software evolution; Software quality; Software system; Set (abstract data type); Process (computing); Merge (version control); Software metric; Software development; Programming language; Software construction; Information retrieval","score_opus":0.0253112702250691,"score_gpt":0.27451925036300423,"score_spread":0.24920798013793513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213075374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01949062,0.00002289593,0.97673064,0.00042613127,0.0004343342,0.00038249395,0.000043075856,0.002465929,0.0000038758544],"genre_scores_gemma":[0.604772,0.0000046111195,0.39486146,0.00016979415,0.000030118848,0.00009206004,0.0000061323044,0.0000535728,0.000010259363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978303,0.000060427803,0.00027968897,0.0008375265,0.00044225308,0.0005498524],"domain_scores_gemma":[0.9976391,0.0008461513,0.000028382654,0.00064434164,0.0001234554,0.0007185295],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021073385,0.0003418995,0.00027484688,0.0004979824,0.00021277393,0.00028738333,0.00079243747,0.00011147402,0.000015609077],"category_scores_gemma":[0.00027457418,0.00039000635,0.000089440655,0.0011241612,0.000024804827,0.00085882086,0.000016523707,0.0008072147,0.000040463434],"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":[0.000022837521,0.00012402913,0.00014683453,0.00010184353,0.0000464375,0.000009140759,0.0017361183,0.96363425,0.0013394341,0.000033893513,0.00003601174,0.032769136],"study_design_scores_gemma":[0.00053062435,0.00042665887,0.0018614075,0.00012557434,0.000014206763,0.000016709439,0.000082048384,0.9840009,0.011611411,0.000004537685,0.00067203416,0.0006538619],"about_ca_topic_score_codex":0.000018185458,"about_ca_topic_score_gemma":0.0000018150462,"teacher_disagreement_score":0.5852814,"about_ca_system_score_codex":0.0002576934,"about_ca_system_score_gemma":0.000089432746,"threshold_uncertainty_score":0.99985516},"labels":[],"label_agreement":null},{"id":"W4214643715","doi":"10.1109/tse.2022.3154672","title":"An Empirical Study on Log Level Prediction for Multi-Component Systems","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Component (thermodynamics); Interpretability; Computer science; Logging; Component-based software engineering; Data mining; Leverage (statistics); Software; Software system; Machine learning; Operating system","score_opus":0.05913968027635651,"score_gpt":0.29785239876476993,"score_spread":0.2387127184884134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214643715","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":[0.1886212,0.000016945813,0.8048009,0.000016909196,0.004283687,0.0010341202,0.00012815578,0.0010973586,7.1995885e-7],"genre_scores_gemma":[0.98049283,0.0000011795526,0.017773772,0.0000388105,0.00008863476,0.0015060811,0.0000066753405,0.000035827674,0.00005621101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998041,0.00010449023,0.00040008244,0.00060944294,0.0005043505,0.00034068816],"domain_scores_gemma":[0.99873793,0.0002117612,0.000061648345,0.00077878236,0.00007511705,0.00013473367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005837306,0.00024731865,0.00026558377,0.00029397316,0.0005926306,0.0000904778,0.0005649877,0.000072154115,0.000006358082],"category_scores_gemma":[0.000014474298,0.00024186319,0.00014007669,0.00041640465,0.000011141998,0.00033726098,0.0000063836314,0.00042018874,0.000012106101],"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":[0.00003496469,0.0013599906,0.0018682979,0.000055524346,0.00005129996,0.0000051362913,0.0012679523,0.9926628,0.00012725276,0.000010084309,0.00007053505,0.0024861775],"study_design_scores_gemma":[0.0013810759,0.0021664652,0.016030325,0.000033380475,0.000025141551,0.00003199449,0.0003569928,0.97818273,0.0006107562,0.0000016420983,0.000843748,0.00033574784],"about_ca_topic_score_codex":0.00003433027,"about_ca_topic_score_gemma":0.0000022795862,"teacher_disagreement_score":0.7918716,"about_ca_system_score_codex":0.00038617424,"about_ca_system_score_gemma":0.000058341255,"threshold_uncertainty_score":0.98628944},"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":"W4225878264","doi":"10.1109/tse.2022.3162985","title":"Static Profiling of Alloy Models","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Correctness; Modeling language; Natural language processing; Profiling (computer programming); Matching (statistics); Programming language; Software; Artificial intelligence; Data science; Software engineering","score_opus":0.02111579023518419,"score_gpt":0.23700404072038123,"score_spread":0.21588825048519703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225878264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030741109,0.00004942201,0.9671638,0.00003177577,0.0007809006,0.00022494406,0.000029793835,0.0009721364,0.000006126553],"genre_scores_gemma":[0.7812342,0.0000057270117,0.21843545,0.000023409882,0.000011370324,0.00018773682,0.0000013851808,0.000037971724,0.00006276525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823326,0.000037836555,0.00029267848,0.00035878897,0.0006903711,0.0003870725],"domain_scores_gemma":[0.9984485,0.000719537,0.000043532833,0.0006092387,0.00006795907,0.000111234054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003327317,0.00018593908,0.0002123019,0.00047561733,0.00016108474,0.00003575176,0.00080816593,0.000037980317,0.00004313539],"category_scores_gemma":[0.00005931165,0.00022274103,0.000118651325,0.0009275086,0.000015675809,0.00036035664,0.000017240416,0.0005554723,0.000007668086],"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":[0.000005550107,0.00007478189,0.000031940377,0.00006497886,0.00003568533,0.000013423961,0.00031433086,0.99478966,0.0015109198,0.0005905847,0.000028999997,0.002539138],"study_design_scores_gemma":[0.00030567127,0.00017637161,0.00007599926,0.000029632023,0.00000850344,0.00003085882,0.000028554774,0.9617394,0.037051443,0.00010491014,0.00017272333,0.00027591336],"about_ca_topic_score_codex":0.000014613384,"about_ca_topic_score_gemma":3.1349546e-7,"teacher_disagreement_score":0.75049305,"about_ca_system_score_codex":0.00019224215,"about_ca_system_score_gemma":0.00009769243,"threshold_uncertainty_score":0.9083116},"labels":[],"label_agreement":null},{"id":"W4226137778","doi":"10.1109/tse.2022.3201209","title":"Flakify: A Black-Box, Language Model-Based Predictor for Flaky Tests","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Mitacs; Canada Research Chairs; Western Canada Research Grid; Compute Canada","keywords":"Computer science; Debugging; Code coverage; Code (set theory); Set (abstract data type); Source code; White-box testing; Programming language; Software; Overhead (engineering); Black box; Test (biology); Machine learning; Artificial intelligence; Software development; Software construction","score_opus":0.013714965914711835,"score_gpt":0.24877966200787097,"score_spread":0.23506469609315914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226137778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027581153,0.00006694455,0.9677375,0.0000905668,0.0010285876,0.0005997883,0.00018728708,0.0027041642,0.0000040064638],"genre_scores_gemma":[0.787229,0.0000016261013,0.21117085,0.000092611415,0.00006244829,0.0010240381,0.000009407239,0.00008939544,0.00032063777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772,0.000030926534,0.00028774884,0.0006157823,0.00068449724,0.00066106237],"domain_scores_gemma":[0.9975183,0.0012391191,0.000041353578,0.0008935883,0.00008429398,0.00022334098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036372192,0.00031577543,0.00025849734,0.00057497487,0.00033267427,0.000107808075,0.0010628948,0.00008419794,0.000048648744],"category_scores_gemma":[0.00019285727,0.00037635287,0.00022831054,0.0008831326,0.00002737217,0.00028421884,0.000016679114,0.0006556029,0.000020277303],"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":[0.000019515992,0.00011047385,0.000034704855,0.00009179872,0.00003732978,0.00001962381,0.00053717615,0.99440575,0.0012626726,0.00007815384,0.0003563368,0.0030464425],"study_design_scores_gemma":[0.0007840076,0.00022406019,0.00011980142,0.00003215539,0.000015208358,0.0000132341,0.00001762621,0.9863634,0.011110751,0.000019614676,0.0009075382,0.00039257854],"about_ca_topic_score_codex":0.000008133142,"about_ca_topic_score_gemma":0.0000022901827,"teacher_disagreement_score":0.75964785,"about_ca_system_score_codex":0.0004042498,"about_ca_system_score_gemma":0.0002182465,"threshold_uncertainty_score":0.99986887},"labels":[],"label_agreement":null},{"id":"W4247801608","doi":"10.1109/tse.2021.3109563","title":"Analyzing Android Taint Analysis Tools: FlowDroid, Amandroid, and DroidSafe","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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; Rendering (computer graphics); Android (operating system); Set (abstract data type); Data mining; Information retrieval; Artificial intelligence; Programming language; Operating system","score_opus":0.008880119046626464,"score_gpt":0.2199095884629682,"score_spread":0.21102946941634174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247801608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013765318,0.00027701305,0.9835922,0.00007722881,0.00035815756,0.000117782816,0.000017135042,0.0017791402,0.000016030393],"genre_scores_gemma":[0.67455506,0.00015773474,0.3249791,0.00006470305,0.00002751657,0.000053334854,0.0000032589785,0.000028427055,0.00013085445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825615,0.0000339415,0.00035532596,0.0006957612,0.0002688276,0.00038996775],"domain_scores_gemma":[0.998604,0.0002473409,0.00006436796,0.0007443289,0.00014818081,0.00019175692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018933337,0.00029205153,0.00038800918,0.00070434145,0.00022490168,0.0002620155,0.0003086098,0.00012346402,0.000031977914],"category_scores_gemma":[0.0000689829,0.00033831035,0.00025646412,0.0023370741,0.000026525404,0.000869441,0.000012738781,0.00041856917,0.00000970189],"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":[0.000014797691,0.0001384639,0.0002948202,0.00008247844,0.0008667075,0.00024226856,0.00035245172,0.829439,0.00865847,0.00083419896,0.00002878289,0.15904759],"study_design_scores_gemma":[0.00081614475,0.00018953449,0.0023847655,0.00012602896,0.00049003935,0.00034830067,0.00006864479,0.49996167,0.49092212,0.00040370066,0.0028707979,0.0014182401],"about_ca_topic_score_codex":0.000009231891,"about_ca_topic_score_gemma":0.000027208183,"teacher_disagreement_score":0.6607898,"about_ca_system_score_codex":0.00011781036,"about_ca_system_score_gemma":0.000044337517,"threshold_uncertainty_score":0.9999069},"labels":[],"label_agreement":null},{"id":"W4285121201","doi":"10.1109/tse.2022.3188005","title":"Automated Generation and Evaluation of JMH Microbenchmark Suites From Unit Tests","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Concordia University","funders":"","keywords":"Computer science; Unit testing; Programming language; Eclipse; Software; Operating system","score_opus":0.023174269775778533,"score_gpt":0.2505865902937494,"score_spread":0.2274123205179709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285121201","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":[0.5130058,0.00012603973,0.4856916,0.000011310819,0.00058958883,0.00014367014,0.000025384541,0.00040479287,0.0000017938114],"genre_scores_gemma":[0.977937,0.000008533674,0.021873718,0.000016677994,0.000026003652,0.00010402779,0.000012979914,0.000011857714,0.000009243907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987985,0.00008938498,0.00025421084,0.00027927302,0.0004374624,0.00014117827],"domain_scores_gemma":[0.9991788,0.00023561294,0.00006390141,0.0003464402,0.00012938536,0.000045836277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005375441,0.00012746415,0.00014699303,0.00018506558,0.000204311,0.00003522435,0.0002095166,0.000047394897,0.00006202367],"category_scores_gemma":[0.000037023496,0.00013453508,0.000049020167,0.00044897242,0.000014266989,0.00027883117,0.00000698027,0.00016937708,0.0000033854817],"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":[0.0000040823907,0.000074062664,0.0013273449,0.000032773987,0.000038665872,9.444437e-7,0.00064746203,0.9634128,0.014412922,0.000014340512,0.000063862004,0.019970728],"study_design_scores_gemma":[0.00037936086,0.00007629703,0.01171314,0.000025352965,0.0000309217,0.000010134382,0.000020265534,0.9633403,0.024133831,0.000012060621,0.000101991536,0.00015633782],"about_ca_topic_score_codex":0.000087431086,"about_ca_topic_score_gemma":0.000009087946,"teacher_disagreement_score":0.46493113,"about_ca_system_score_codex":0.000114161434,"about_ca_system_score_gemma":0.00008105818,"threshold_uncertainty_score":0.54861814},"labels":[],"label_agreement":null},{"id":"W4285169595","doi":"10.1109/tse.2022.3175752","title":"Annotative Software Product Line Analysis Using Variability-Aware Datalog","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","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 Toronto","funders":"General Motors of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Datalog; Computer science; Programming language; Software product line; Java; Software; Product (mathematics); Pointer (user interface); Inference; Software engineering; Theoretical computer science; Software development; Artificial intelligence","score_opus":0.03845076192181567,"score_gpt":0.28467542222655134,"score_spread":0.24622466030473567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285169595","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00438357,0.00009812464,0.98946726,0.000030991272,0.001953408,0.0003804133,0.00031699022,0.0033679688,0.0000012507711],"genre_scores_gemma":[0.2726507,0.000006501305,0.7268958,0.00005315633,0.00005535195,0.00018523008,0.000025720017,0.000063294705,0.0000642417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996543,0.0003082904,0.0005552647,0.001203776,0.00069335196,0.00069633924],"domain_scores_gemma":[0.9957624,0.0020994593,0.00014644572,0.001645487,0.00016476176,0.00018146052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001114638,0.0005144215,0.0006407017,0.0010858907,0.0006482409,0.00010353464,0.0013297563,0.00008580781,0.000077907025],"category_scores_gemma":[0.0007010414,0.00059700647,0.00035994686,0.004354131,0.000052787313,0.0008577203,0.0000644564,0.0011176073,0.000008371096],"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":[0.000013730878,0.00011728974,0.00007066069,0.000049117807,0.00039696132,0.000036904465,0.0005064485,0.98910475,0.00036117533,0.00007172433,0.000012357244,0.009258855],"study_design_scores_gemma":[0.00064855546,0.00033165023,0.00046761453,0.000046692105,0.0005413958,0.00013585601,0.00011286381,0.98076177,0.013879362,0.0005911847,0.0008080577,0.0016749931],"about_ca_topic_score_codex":0.000023084314,"about_ca_topic_score_gemma":0.0000024803398,"teacher_disagreement_score":0.26826712,"about_ca_system_score_codex":0.0006770881,"about_ca_system_score_gemma":0.0001468098,"threshold_uncertainty_score":0.99964815},"labels":[],"label_agreement":null},{"id":"W4285194931","doi":"10.1109/tse.2022.3177228","title":"SCS-Gan: Learning Functionality-Agnostic Stylometric Representations for Source Code Authorship Verification","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Authorship Attribution and Profiling","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Source code; Code (set theory); Set (abstract data type); Task (project management); Benchmark (surveying); Malware; Artificial intelligence; Adversarial system; Representation (politics); Information retrieval; Machine learning; Natural language processing; Programming language; Computer security","score_opus":0.03621979625623392,"score_gpt":0.2699609822255617,"score_spread":0.23374118596932777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285194931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050480273,0.000076858065,0.9911576,0.00032599177,0.0016820879,0.00038884385,0.00006579357,0.0012405706,0.000014254361],"genre_scores_gemma":[0.9386199,0.0000057247084,0.059191197,0.0000927512,0.00007030037,0.0006671936,0.000043339707,0.00003822661,0.0012713693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813426,0.00015562924,0.00034928898,0.00052825705,0.00046754815,0.00036503046],"domain_scores_gemma":[0.9978354,0.0013618212,0.00010862801,0.00042369845,0.00012442158,0.00014601901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008756905,0.00019486052,0.00017544981,0.0006429685,0.0012577581,0.00012248216,0.0004449919,0.000078484976,0.00011641169],"category_scores_gemma":[0.0004280901,0.0002476356,0.00017174352,0.0019062755,0.000017298042,0.00034738122,0.000008019891,0.00074325164,0.000031016905],"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":[0.000017862567,0.00006934605,0.0001266525,0.00002935024,0.000032908694,0.0000013992117,0.00053774816,0.98845655,0.0005117213,0.00165592,0.00007910574,0.008481458],"study_design_scores_gemma":[0.00070579565,0.00027317184,0.0013248175,0.000025713682,0.000055036668,0.000042360592,0.00018987317,0.9566229,0.010001257,0.00027013535,0.029943034,0.00054593064],"about_ca_topic_score_codex":0.000011880785,"about_ca_topic_score_gemma":0.0000012631416,"teacher_disagreement_score":0.9335719,"about_ca_system_score_codex":0.0002761015,"about_ca_system_score_gemma":0.00008560176,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W4288391571","doi":"10.1109/tse.2022.3194640","title":"FalsifAI: Falsification of AI-Enabled Hybrid Control Systems Guided by Time-Aware Coverage Criteria","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","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 Alberta","funders":"","keywords":"Computer science; Correctness; Robustness (evolution); Artificial neural network; Notation; Context (archaeology); Hybrid system; Semantics (computer science); Artificial intelligence; Model checking; Theoretical computer science; Programming language; Machine learning","score_opus":0.007528728385960206,"score_gpt":0.225826501456591,"score_spread":0.2182977730706308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288391571","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":[0.007274268,0.00007239712,0.98952395,0.00009025399,0.0016483847,0.00039867798,0.00020700671,0.0007689262,0.000016118667],"genre_scores_gemma":[0.99138564,0.0000041509857,0.007828046,0.00008789248,0.000040448864,0.00020636927,0.000019028203,0.000051320305,0.00037712592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979693,0.00018565451,0.0005029825,0.00046448808,0.0005321717,0.00034534984],"domain_scores_gemma":[0.9986311,0.00034091098,0.0001625612,0.00064838934,0.00011892607,0.00009811047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004648542,0.00026046325,0.00037106997,0.000281272,0.0003528175,0.00010618893,0.0007641048,0.000056675985,0.00012355445],"category_scores_gemma":[0.000052117397,0.00031274714,0.00013691984,0.0004923893,0.000018949724,0.00049874146,0.000013019294,0.00059225276,0.000018766088],"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":[0.000018311946,0.00010345891,0.00001628393,0.0000588056,0.000058701968,0.000012481288,0.00013120838,0.9905532,0.0065105096,0.00011634598,0.0011715101,0.001249156],"study_design_scores_gemma":[0.001033117,0.0001277793,0.000027437776,0.00003809905,0.000029113386,0.000043294287,0.000017461363,0.9912822,0.005065442,0.000014050765,0.002006992,0.00031496034],"about_ca_topic_score_codex":0.00007117319,"about_ca_topic_score_gemma":2.370359e-7,"teacher_disagreement_score":0.98411137,"about_ca_system_score_codex":0.00025413395,"about_ca_system_score_gemma":0.000072356605,"threshold_uncertainty_score":0.99993247},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4296338325","doi":"10.1109/tse.2022.3207428","title":"Code Cloning in Smart Contracts on the Ethereum Platform: An Extended Replication Study","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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":"University of Waterloo; Université de Montréal; McGill University","funders":"","keywords":"Solidity; Computer science; Cloning (programming); clone (Java method); Context (archaeology); Code (set theory); Granularity; Source code; Software engineering; Programming language; Code reuse; Source lines of code; Replication (statistics); Software; Mathematics","score_opus":0.026244746252368042,"score_gpt":0.26745966406046645,"score_spread":0.2412149178080984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296338325","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":[0.14301507,0.000008096969,0.854526,0.00008230124,0.00040412083,0.00057025667,0.0000083957275,0.0013731448,0.000012636104],"genre_scores_gemma":[0.9770319,0.0000032117634,0.021752326,0.00017214725,0.000014826331,0.00094611605,0.000001101639,0.0000337476,0.000044615797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998469,0.00008954678,0.00028252442,0.0005348187,0.0003591906,0.0002649258],"domain_scores_gemma":[0.9983251,0.00036771302,0.00007456112,0.0011348936,0.000037273065,0.00006045571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006791062,0.00018616646,0.00015451873,0.00030708348,0.000394497,0.00006739286,0.0006351527,0.00004446623,0.000026347689],"category_scores_gemma":[0.000059806647,0.00017897581,0.000055517,0.00068572926,0.000011426964,0.0004771539,0.000009281369,0.0008087409,0.000005494363],"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":[0.00004677295,0.0005850948,0.000040127485,0.000005250514,0.000022671831,0.000024535699,0.0017049538,0.94178456,0.0025035797,0.0008432236,0.000016256727,0.05242296],"study_design_scores_gemma":[0.0022719041,0.0043834937,0.011158444,0.000121948404,0.000035583384,0.00018161802,0.0017500318,0.76204664,0.20996824,0.0014087191,0.0050533754,0.001620008],"about_ca_topic_score_codex":0.000040807707,"about_ca_topic_score_gemma":0.000044440425,"teacher_disagreement_score":0.83401686,"about_ca_system_score_codex":0.00030410325,"about_ca_system_score_gemma":0.00003139598,"threshold_uncertainty_score":0.7298422},"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":"W4312614778","doi":"10.1109/tse.2022.3222160","title":"Studying the Interplay Between the Durations and Breakages of Continuous Integration Builds","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University; University of Toronto; University of Ottawa","funders":"","keywords":"Computer science; Context (archaeology); World Wide Web; Data science; Information retrieval","score_opus":0.013719677836531744,"score_gpt":0.2563637641058254,"score_spread":0.24264408626929365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312614778","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":[0.13195536,0.000091753485,0.8665931,0.0003088966,0.00046536172,0.00025864545,0.000022402972,0.00030177223,0.000002710583],"genre_scores_gemma":[0.9919397,0.000009920106,0.0077612973,0.000028005845,0.00003496742,0.00014763787,0.0000013494874,0.000021559094,0.0000555223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987937,0.000083418716,0.0002535879,0.00024070806,0.00040755057,0.0002210156],"domain_scores_gemma":[0.9970095,0.0023247402,0.00005043318,0.0005047257,0.00006262272,0.00004797954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005397529,0.0001512103,0.00015978157,0.00020771784,0.0005055117,0.00010453006,0.0007263178,0.000031962983,0.000013969391],"category_scores_gemma":[0.00014504508,0.000109336936,0.000073988194,0.00068586925,0.00004754882,0.00021824907,0.000028171107,0.0006419948,0.0000019587917],"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":[0.00001399442,0.00012779738,0.0038942571,0.000058781447,0.00027598144,0.000010796894,0.008577232,0.85953057,0.0025927064,0.0009936813,0.0002829271,0.12364127],"study_design_scores_gemma":[0.0031292408,0.0024944078,0.2135948,0.00050866423,0.00037244224,0.0006389618,0.0042842138,0.64561963,0.11786075,0.00041069134,0.008541714,0.0025444909],"about_ca_topic_score_codex":0.000043100594,"about_ca_topic_score_gemma":0.0000042136367,"teacher_disagreement_score":0.8599844,"about_ca_system_score_codex":0.000085669315,"about_ca_system_score_gemma":0.00003577515,"threshold_uncertainty_score":0.4458631},"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":"W4313142332","doi":"10.1109/tse.2022.3220740","title":"A Comprehensive Investigation of the Impact of Class Overlap on Software Defect Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Class (philosophy); Software; Data mining; Rank (graph theory); Feature (linguistics); Machine learning; Identification (biology); Artificial intelligence; Mathematics","score_opus":0.018022052625698195,"score_gpt":0.24269995323414043,"score_spread":0.22467790060844223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313142332","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":[0.41403133,0.00003656492,0.58451504,0.000011470818,0.00066747464,0.0002580931,0.00010961461,0.0003689718,0.0000014832376],"genre_scores_gemma":[0.98991746,0.0000055584414,0.009820537,0.000019530944,0.000025354724,0.00013626074,0.000004158061,0.000045166416,0.000025948462],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787366,0.00011942646,0.0003873116,0.00039580287,0.0008823552,0.00034145213],"domain_scores_gemma":[0.99750644,0.0011942721,0.00012918808,0.00089811586,0.00016039812,0.000111581634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024619626,0.00026529262,0.00028910395,0.0004973583,0.00022975568,0.000028626213,0.0008263916,0.00008245023,0.000029838424],"category_scores_gemma":[0.00017927476,0.0002374483,0.00046781186,0.0015486374,0.00005736394,0.00024481298,0.000027880353,0.0007743549,0.0000042386337],"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":[0.000025192108,0.000076361655,0.0055758245,0.00007860965,0.00011941005,0.000002546499,0.00042486587,0.9885891,0.0034649281,0.00004663794,0.000100640784,0.0014958709],"study_design_scores_gemma":[0.0022179834,0.003130219,0.38449842,0.00052065565,0.00009169698,0.0001359114,0.000095161995,0.48174846,0.12610686,0.00014521583,0.00034069078,0.00096872915],"about_ca_topic_score_codex":0.00007932048,"about_ca_topic_score_gemma":8.5475597e-7,"teacher_disagreement_score":0.5758862,"about_ca_system_score_codex":0.00052596396,"about_ca_system_score_gemma":0.00019731767,"threshold_uncertainty_score":0.96828604},"labels":[],"label_agreement":null},{"id":"W4319663674","doi":"10.1109/tse.2023.3243522","title":"Black-Box Testing of Deep Neural Networks through Test Case Diversity","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":86,"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; Black box; Artificial neural network; White-box testing; Test (biology); Diversity (politics); Software testing; Artificial intelligence; Machine learning; Software engineering; Software; Programming language; Software development; Software construction","score_opus":0.02156941011280877,"score_gpt":0.23671552213532804,"score_spread":0.21514611202251926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319663674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034015562,0.000012355265,0.9632514,0.000026934156,0.0009935932,0.000113659575,0.0000056826702,0.0015662982,0.000014524808],"genre_scores_gemma":[0.8525928,0.0000028930062,0.14726643,0.00002184247,0.00006177479,0.0000066162183,8.70671e-7,0.000026420788,0.000020334286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987153,0.000031163727,0.00024871243,0.00035759076,0.0002586013,0.0003886458],"domain_scores_gemma":[0.9978503,0.0014803975,0.00007828081,0.00042742857,0.000080019905,0.00008355877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001961297,0.00021337719,0.00021744153,0.00019464498,0.00040817712,0.00004466133,0.0004964725,0.000098568846,0.000009963758],"category_scores_gemma":[0.0002457732,0.00024209314,0.0001096887,0.0015788795,0.00004402843,0.00053980085,0.000041586736,0.0005398779,0.000014834069],"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":[0.000002302276,0.000024857061,0.00087731716,0.000032407315,0.00002061389,0.00044209554,0.0008086603,0.98279,0.000036535755,0.000037170066,0.000007645405,0.0149204],"study_design_scores_gemma":[0.00022630196,0.00006405742,0.0005094325,0.000033590655,0.000021016074,0.00018504457,0.000050837367,0.9981755,0.000488847,0.000015531441,0.000009390241,0.00022042294],"about_ca_topic_score_codex":0.0001056903,"about_ca_topic_score_gemma":0.000009903293,"teacher_disagreement_score":0.81857723,"about_ca_system_score_codex":0.00006825513,"about_ca_system_score_gemma":0.000012624156,"threshold_uncertainty_score":0.9872272},"labels":[],"label_agreement":null},{"id":"W4320005455","doi":"10.1109/tse.2023.3242588","title":"Trace Diagnostics for Signal-Based Temporal Properties","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Formal Methods in Verification","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":"McMaster University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"TRACE (psycholinguistics); Computer science; Digital subscriber line; Property (philosophy); Context (archaeology); Domain-specific language; Specification language; Complement (music); Medical diagnosis; SIGNAL (programming language); Programming language; Root cause; Theoretical computer science; Reliability engineering","score_opus":0.04247656139871854,"score_gpt":0.2590470647484599,"score_spread":0.21657050334974137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320005455","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043017445,0.00003734828,0.9922747,0.00008273414,0.0010676476,0.00034529783,0.000019374449,0.0018687317,0.0000023987393],"genre_scores_gemma":[0.39347574,0.000008544849,0.60600334,0.000035483718,0.00003331652,0.00032476272,0.000002012465,0.000026886068,0.00008988351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999019,0.000021358504,0.0002047572,0.00026777375,0.00020249197,0.00028457172],"domain_scores_gemma":[0.9990647,0.00040163027,0.00003487847,0.00035212128,0.00007247366,0.00007422628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029009138,0.0001552396,0.00013056438,0.00025478707,0.00014703524,0.00007528396,0.00036683696,0.000076440454,0.0000043926975],"category_scores_gemma":[0.000110862835,0.0001571763,0.00009751433,0.00063816365,0.000017604676,0.00031166335,0.0000015578406,0.00016103267,0.000042341235],"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":[0.000010642779,0.00004458601,0.000014382365,0.000113630565,0.000014801146,0.0000031355762,0.0002063041,0.9684201,0.0012117168,0.0003892057,0.00016017674,0.029411329],"study_design_scores_gemma":[0.00021481437,0.00010745684,0.00014748264,0.00006437371,0.000008704857,0.000002145679,0.000008415174,0.869149,0.12801549,0.000025570425,0.0020555435,0.0002009707],"about_ca_topic_score_codex":0.0000055738487,"about_ca_topic_score_gemma":0.0000013778279,"teacher_disagreement_score":0.389174,"about_ca_system_score_codex":0.00006720798,"about_ca_system_score_gemma":0.00005546428,"threshold_uncertainty_score":0.6409463},"labels":[],"label_agreement":null},{"id":"W4323530087","doi":"10.1109/tse.2023.3253700","title":"SLocator: Localizing the Origin of SQL Queries in Database-Backed Web Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Computer science; Database; Stored procedure; SQL; Query by Example; SQL injection; Programming language; Information retrieval; Web search query","score_opus":0.016398805950189235,"score_gpt":0.24398300974008116,"score_spread":0.22758420378989191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323530087","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":[0.03160973,0.00007740488,0.9663869,0.0001088645,0.00059664674,0.0003430754,0.000027025018,0.0008414616,0.000008882442],"genre_scores_gemma":[0.98903656,0.000093031005,0.010350099,0.000027289543,0.000036858357,0.00037769254,0.0000040284544,0.00002082418,0.00005362263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874914,0.000031522937,0.0003591352,0.00030780266,0.00026640252,0.00028599126],"domain_scores_gemma":[0.998625,0.00039714455,0.000051561146,0.00081557507,0.00005477988,0.000055966793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042979416,0.0001632984,0.00019720195,0.00030169458,0.00013508846,0.00003646434,0.0005821549,0.00007377521,0.000007070787],"category_scores_gemma":[0.00001900221,0.00013164134,0.0000881779,0.0018646461,0.000053171767,0.00034720873,0.000008237995,0.00027746463,0.000081686034],"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":[0.00001682578,0.00018306471,0.0030951414,0.00072712795,0.0000776479,0.000012828663,0.0018926531,0.95368797,0.0026146607,0.002003945,0.0005163199,0.035171844],"study_design_scores_gemma":[0.0012367201,0.00014100167,0.0046315133,0.0007293341,0.0000411353,0.00004691294,0.00046811425,0.9076099,0.05144118,0.00015052054,0.032484688,0.0010190201],"about_ca_topic_score_codex":0.000057256362,"about_ca_topic_score_gemma":0.000032607295,"teacher_disagreement_score":0.95742685,"about_ca_system_score_codex":0.00008390864,"about_ca_system_score_gemma":0.000103175764,"threshold_uncertainty_score":0.53681785},"labels":[],"label_agreement":null},{"id":"W4324291633","doi":"10.1109/tse.2023.3256939","title":"New Techniques for Static Symmetry Breaking in Many-Sorted Finite Model Finding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Machine Learning and Algorithms","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; University of British Columbia","funders":"","keywords":"Computer science; Symmetry breaking; Correctness; Theoretical computer science; sort; Symmetry (geometry); Context (archaeology); Inference; Algorithm; Mathematics; Artificial intelligence; Physics","score_opus":0.017929932504266763,"score_gpt":0.26386151031678046,"score_spread":0.24593157781251368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324291633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018759774,0.000008086534,0.9951562,0.00008053617,0.0003772,0.0002023665,0.00001175406,0.0022755913,0.000012258781],"genre_scores_gemma":[0.33142784,0.000010584141,0.6677558,0.000043811786,0.00004788479,0.0000940404,0.0000035247201,0.0000406682,0.000575889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887323,0.000013268716,0.00023419244,0.00032942754,0.00017818392,0.00037170545],"domain_scores_gemma":[0.99912953,0.00045580318,0.000037060057,0.0002711317,0.000022488928,0.00008395727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023391475,0.00018138395,0.00018001827,0.00072167267,0.00010901107,0.00008934643,0.0003287078,0.00007812324,0.0000041737762],"category_scores_gemma":[0.00005086315,0.00020253783,0.00009219098,0.0010502351,0.000004683089,0.0002720828,0.000004398675,0.0003477769,0.000013895617],"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":[0.0000020546406,0.0000116988995,0.000015931924,0.00004871881,0.000010692256,0.0000055833407,0.0002369701,0.84642017,0.00012400211,0.00028556606,0.000048572543,0.15279004],"study_design_scores_gemma":[0.00022849982,0.000050075163,0.00008711365,0.00015966246,0.000006217571,0.000004431193,0.000007108324,0.9955756,0.003182017,0.00022379367,0.00025705076,0.00021841281],"about_ca_topic_score_codex":0.000041553936,"about_ca_topic_score_gemma":0.000003990452,"teacher_disagreement_score":0.32955185,"about_ca_system_score_codex":0.000074507654,"about_ca_system_score_gemma":0.000049530354,"threshold_uncertainty_score":0.8259253},"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":"W4364321651","doi":"10.1109/tse.2023.3265855","title":"Identifying Concepts in Software Projects","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"","keywords":"Computer science; Documentation; Software engineering; Domain (mathematical analysis); Software project management; Software development; Software; Domain analysis; Data science; Software construction; Programming language","score_opus":0.03530785764332117,"score_gpt":0.2955445288280574,"score_spread":0.2602366711847362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364321651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081982374,0.00006040899,0.9107885,0.00003932864,0.0016364295,0.00033025956,0.0000095913,0.0051490315,0.0000040919876],"genre_scores_gemma":[0.90555537,0.000032828535,0.09359878,0.00003569329,0.00006032307,0.00029623712,0.0000035546227,0.000087761844,0.0003294288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973705,0.000040201063,0.00036640925,0.000687675,0.0006562508,0.0008789903],"domain_scores_gemma":[0.997552,0.0013715817,0.000035141613,0.0007741294,0.00007513195,0.00019201452],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046241458,0.0003273713,0.00029341923,0.0014402204,0.00017055077,0.00026647057,0.0009281342,0.00016156877,0.000024352723],"category_scores_gemma":[0.00044733033,0.00037904535,0.00014043055,0.0035272487,0.000035342127,0.0007228811,0.000017972718,0.0007497772,0.00045173487],"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":[0.0000094829575,0.00009492502,0.0027990898,0.00026663972,0.000055781315,0.0003865325,0.0022739551,0.96071357,0.0009944532,0.00015555037,0.00036592752,0.031884104],"study_design_scores_gemma":[0.0052718553,0.00061930297,0.11834723,0.0026241494,0.000045791196,0.0002940067,0.0003613038,0.7545984,0.10813247,0.00038406195,0.004610685,0.0047108023],"about_ca_topic_score_codex":0.000035639747,"about_ca_topic_score_gemma":0.00001115593,"teacher_disagreement_score":0.823573,"about_ca_system_score_codex":0.00027570777,"about_ca_system_score_gemma":0.0001367521,"threshold_uncertainty_score":0.9998661},"labels":[],"label_agreement":null},{"id":"W4367016230","doi":"10.1109/tse.2023.3269804","title":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Reinforcement Learning in Robotics","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":"Cisco Systems (Canada); École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Software testing; Software engineering; Programming language; Software","score_opus":0.04544628432889011,"score_gpt":0.25729172732987793,"score_spread":0.21184544300098782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367016230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006383811,0.00000454791,0.99573284,0.000021951795,0.00046346424,0.00045737118,0.0000010239257,0.0026209138,0.000059490463],"genre_scores_gemma":[0.5927373,0.0000024442102,0.40645197,0.00004813849,0.00003526558,0.0001880706,0.000011498064,0.000047875074,0.00047743018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981533,0.00002727279,0.00031084352,0.00042309138,0.00046717547,0.0006182844],"domain_scores_gemma":[0.99866116,0.00060632935,0.000059637172,0.00041978504,0.00011157522,0.0001414871],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041313615,0.00024589663,0.0001909584,0.0004949536,0.00037661835,0.00016689989,0.0005319753,0.00008985886,0.000008817609],"category_scores_gemma":[0.00016708871,0.00027594468,0.0001393434,0.001272861,0.000018576846,0.00028122857,0.000008164444,0.00044293734,0.00006013378],"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":[0.0000053053222,0.000016045393,0.00006023975,0.00013081527,0.000033676853,0.000004336891,0.0002360686,0.99352336,0.00018093796,0.000051373234,0.000025788651,0.005732055],"study_design_scores_gemma":[0.0004786784,0.00019253552,0.00009300671,0.00006190662,0.000012921474,0.0000031336235,0.000023047585,0.9951137,0.003417718,0.0000014754692,0.00032459715,0.00027733404],"about_ca_topic_score_codex":0.000006494386,"about_ca_topic_score_gemma":1.3126994e-7,"teacher_disagreement_score":0.59209895,"about_ca_system_score_codex":0.00015520862,"about_ca_system_score_gemma":0.00006328034,"threshold_uncertainty_score":0.99996924},"labels":[],"label_agreement":null},{"id":"W4375928762","doi":"10.1109/tse.2023.3272631","title":"Discovering Reusable Functional Features in Legacy Object-Oriented Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Software Engineering Methodologies","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":"Université du Québec à Montréal; Concordia University; École de Technologie Supérieure; Collège de Bois-de-Boulogne","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Code refactoring; Programming language; Java; Object-oriented programming; Software design pattern; Reuse; Inheritance (genetic algorithm); Set (abstract data type); Delegation; Software engineering; Software","score_opus":0.0242138522624414,"score_gpt":0.2522181008092857,"score_spread":0.22800424854684428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375928762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01357709,0.00014135419,0.97646904,0.00003308696,0.005189747,0.00023171386,0.000011602247,0.004332104,0.000014242357],"genre_scores_gemma":[0.69215816,0.000072075294,0.3062152,0.000025283818,0.00013293844,0.00031374712,0.000007981772,0.000093330695,0.0009812627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997977,0.00005486581,0.00035135105,0.0005827469,0.00040965682,0.0006243843],"domain_scores_gemma":[0.9980595,0.0010760782,0.000048654623,0.00065120496,0.00005279221,0.00011173198],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041940436,0.0003296451,0.00032435692,0.00083573855,0.00014244061,0.00016859172,0.00047501535,0.00014278574,0.000005242259],"category_scores_gemma":[0.0002861379,0.00035494196,0.00011866386,0.0021447742,0.0000216867,0.0012203917,0.000014261199,0.00061914086,0.000068536494],"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":[0.000009165467,0.000023929611,0.000037179307,0.000067652094,0.000025457859,0.000048852075,0.00023181061,0.9955589,0.00079508836,0.00079440913,0.00010490343,0.0023026627],"study_design_scores_gemma":[0.0027786517,0.00037844412,0.021543583,0.0013316935,0.00004446078,0.00032031027,0.00061444123,0.9239909,0.039881475,0.000542733,0.0054474357,0.003125887],"about_ca_topic_score_codex":0.0000438275,"about_ca_topic_score_gemma":0.0000071803306,"teacher_disagreement_score":0.6785811,"about_ca_system_score_codex":0.0002734313,"about_ca_system_score_gemma":0.000054551652,"threshold_uncertainty_score":0.99989027},"labels":[],"label_agreement":null},{"id":"W4379409284","doi":"10.1109/tse.2023.3282981","title":": A Semantics-Guided Safety Enhancement Framework for AI-Enabled Cyber-Physical Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","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":"University of Alberta","funders":"JST-Mirai Program; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Artificial intelligence; Cyber-physical system; Robotics; Modular design; Flexibility (engineering); Redundancy (engineering); Machine learning; Robot; Programming language","score_opus":0.015201457747041808,"score_gpt":0.24747335626861416,"score_spread":0.23227189852157235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379409284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009837464,0.00009102601,0.9754257,0.000046612015,0.0065766606,0.001107565,0.00013044722,0.006746941,0.00003754544],"genre_scores_gemma":[0.9685565,0.000058635505,0.0284299,0.000023601235,0.00053366047,0.001518277,0.000028285169,0.0003621115,0.0004889773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760216,0.000018402385,0.00064020406,0.00047114555,0.0003858251,0.0008822629],"domain_scores_gemma":[0.99816954,0.00080724224,0.000045382167,0.0006645984,0.00009526119,0.00021796502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002794522,0.0005652191,0.00062606594,0.0005112405,0.0001704041,0.000101503574,0.0003130698,0.00027114456,0.00002150333],"category_scores_gemma":[0.00006480272,0.00065190723,0.00031534996,0.0009779319,0.000019503941,0.00021223823,0.0000035323853,0.0006165321,0.0002874648],"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":[0.000012729603,0.000036709334,0.0000038016665,0.00083854556,0.00027690866,0.000009443727,0.00035246057,0.9937795,0.0020131967,0.00097400707,0.0007064415,0.0009962865],"study_design_scores_gemma":[0.0005901903,0.00007487028,0.000057002282,0.0006539992,0.00008180653,0.000018148605,0.00004892657,0.9655024,0.01733971,0.000049739967,0.014828054,0.0007551956],"about_ca_topic_score_codex":0.000009917299,"about_ca_topic_score_gemma":8.589882e-7,"teacher_disagreement_score":0.9587191,"about_ca_system_score_codex":0.00050507765,"about_ca_system_score_gemma":0.000039603874,"threshold_uncertainty_score":0.9995932},"labels":[],"label_agreement":null},{"id":"W4380520359","doi":"10.1109/tse.2023.3285743","title":"STRE: An Automated Approach to Suggesting App Developers When to Stop Reading Reviews","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; China Postdoctoral Science Foundation","keywords":"Computer science; Reading (process); Upload; Categorization; World Wide Web; Complement (music); Data science; Artificial intelligence","score_opus":0.039493449767354936,"score_gpt":0.2921104368037568,"score_spread":0.2526169870364019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380520359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024108132,0.000028381442,0.95924586,0.00008875985,0.00086943724,0.00074194284,0.000012689836,0.014885724,0.000019045681],"genre_scores_gemma":[0.25237057,0.000017851406,0.7461631,0.0001440822,0.00009181639,0.0006235931,0.000009539802,0.00013573743,0.00044375638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696386,0.000066088935,0.00046947986,0.0009266295,0.00060997077,0.0009639961],"domain_scores_gemma":[0.9974847,0.00062636746,0.00003649685,0.0010652135,0.00012088875,0.00066635164],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009805808,0.00041916542,0.00041500438,0.0012714679,0.00025582887,0.00028149603,0.0012804099,0.00013576812,0.000009425934],"category_scores_gemma":[0.00075052865,0.00045785087,0.00011209147,0.003818159,0.000011683964,0.0006097136,0.000027305085,0.00053366536,0.00060407235],"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":[0.000004513137,0.00004748931,0.0000604777,0.0001234569,0.000027750808,0.000019040031,0.0027024427,0.95672345,0.0013746045,0.000043259846,0.0014762101,0.037397295],"study_design_scores_gemma":[0.00037727575,0.00023421284,0.003100956,0.00057120225,0.0000185465,0.000058886926,0.00010673554,0.97630864,0.00848548,0.0000062559493,0.009408232,0.0013235513],"about_ca_topic_score_codex":0.000039228868,"about_ca_topic_score_gemma":0.0000032419673,"teacher_disagreement_score":0.22826242,"about_ca_system_score_codex":0.0003550573,"about_ca_system_score_gemma":0.00009341602,"threshold_uncertainty_score":0.99978733},"labels":[],"label_agreement":null},{"id":"W4381304075","doi":"10.1109/tse.2023.3281275","title":"Multi-Granularity Detector for Vulnerability Fixes","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Queen's University","funders":"National Research Foundation Singapore; National University of Singapore","keywords":"Computer science; Commit; Granularity; Vulnerability (computing); Source code; Software; Python (programming language); Code (set theory); Data mining; Computer security; Database; Operating system; Programming language","score_opus":0.03505384984562248,"score_gpt":0.28615123860887126,"score_spread":0.2510973887632488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381304075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049910303,0.00002825645,0.94271314,0.00006061838,0.0016035079,0.00047935089,0.00005876861,0.0051455623,5.1403447e-7],"genre_scores_gemma":[0.7082132,0.000008865254,0.29096624,0.000020847458,0.00005918285,0.0004966644,0.0000037105324,0.000058377955,0.00017289873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980123,0.000029372246,0.00027807592,0.000616424,0.00038832787,0.00067547336],"domain_scores_gemma":[0.9965098,0.0022967397,0.000025503983,0.0008331732,0.00012609789,0.00020869469],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005596007,0.00027989986,0.00025359023,0.00050391094,0.00024380347,0.00013144764,0.00075754477,0.00014960823,0.000013733958],"category_scores_gemma":[0.0006898623,0.00030559194,0.00022948535,0.0013040877,0.000026980311,0.00036636784,0.000009101852,0.00046781538,0.00011527139],"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":[0.000020250123,0.0001657713,0.0007087398,0.00033997238,0.000096848344,0.000022795697,0.00039044328,0.9594986,0.0062495247,0.00007111499,0.00030410165,0.03213183],"study_design_scores_gemma":[0.0010152287,0.00016719609,0.014192681,0.00007352116,0.000014942151,0.000013027675,0.000007845957,0.9166115,0.06543197,0.00004558631,0.0017884035,0.0006380979],"about_ca_topic_score_codex":0.000018216557,"about_ca_topic_score_gemma":0.000007424411,"teacher_disagreement_score":0.6583029,"about_ca_system_score_codex":0.0001646289,"about_ca_system_score_gemma":0.00006090445,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null},{"id":"W4382203557","doi":"10.1109/tse.2023.3289808","title":"Self-Admitted Technical Debt in Ethereum Smart Contracts: A Large-Scale Exploratory Study","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Blockchain Technology Applications and Security","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Technical debt; Computer science; Workaround; Context (archaeology); Code (set theory); Implementation; Data science; Software engineering; Software development; Programming language; Software","score_opus":0.009701457661906625,"score_gpt":0.2289408710523694,"score_spread":0.21923941339046277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382203557","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":[0.20430273,0.000027741373,0.7904112,0.00012838654,0.0002487054,0.00042554,0.00000768797,0.0044392864,0.000008781816],"genre_scores_gemma":[0.9643494,0.0000226189,0.034802742,0.000054200314,0.000013340344,0.0007091504,0.0000011281011,0.00002929885,0.000018113604],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984964,0.00004156344,0.00031522408,0.0004962514,0.00021638075,0.00043418127],"domain_scores_gemma":[0.9988113,0.00023550107,0.000035845293,0.0007780017,0.00004618996,0.00009315059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004760677,0.00020675085,0.00023779679,0.0005504623,0.00015020912,0.00004271491,0.0006171416,0.00022030475,0.00000769398],"category_scores_gemma":[0.000023212462,0.00022668717,0.00007529474,0.0019457645,0.000017708004,0.0002089083,0.000011993973,0.00071291404,0.000112121146],"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":[0.00024095991,0.043787636,0.031266823,0.0008437856,0.00160108,0.0021654763,0.08308182,0.6358181,0.018259685,0.023387453,0.0027504312,0.15679674],"study_design_scores_gemma":[0.004629752,0.0007552002,0.02672066,0.00017625607,0.000073634685,0.000074217474,0.0017356657,0.93945897,0.013812432,0.00076670194,0.0099958535,0.0018006349],"about_ca_topic_score_codex":0.000009729257,"about_ca_topic_score_gemma":0.00022835236,"teacher_disagreement_score":0.76004666,"about_ca_system_score_codex":0.000117071206,"about_ca_system_score_gemma":0.00004791949,"threshold_uncertainty_score":0.9244035},"labels":[],"label_agreement":null},{"id":"W4382318094","doi":"10.1109/tse.2023.3288901","title":"NLP-Based Automated Compliance Checking of Data Processing Agreements Against GDPR","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Access Control and Trust","field":"Social Sciences","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; Fonds National de la Recherche Luxembourg","keywords":"Computer science; Table (database); General Data Protection Regulation; Ambiguity; Software; Glossary; Compliance (psychology); Information retrieval; Software engineering; Database; Data Protection Act 1998; Computer security; Programming language","score_opus":0.09377241932177718,"score_gpt":0.3490663702075247,"score_spread":0.25529395088574747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318094","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":[0.026307737,0.00006173871,0.9698002,0.00010797163,0.0005331926,0.00023396469,0.00012071635,0.0026765824,0.0001579446],"genre_scores_gemma":[0.9925578,0.000027624972,0.0071370513,0.000040794588,0.000057360372,0.000026675754,0.000027232321,0.000029495488,0.000095937496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867225,0.000028637105,0.00025667367,0.0002845405,0.00040430878,0.00035356503],"domain_scores_gemma":[0.99925065,0.00016254159,0.00008191868,0.00032642786,0.000087758475,0.00009071505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003373022,0.00014454458,0.00019828824,0.0002148098,0.00038586723,0.00006398593,0.0005180663,0.00008417412,0.000032655687],"category_scores_gemma":[0.000063674954,0.00015899936,0.000056941986,0.0010016126,0.0000641285,0.00049855094,0.0000041574863,0.00015670614,0.000030506713],"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":[0.00002439721,0.00013618388,0.00061389024,0.00035019693,0.00008995602,0.000019068875,0.0014423081,0.8118091,0.001259037,0.000025580943,0.00023633665,0.1839939],"study_design_scores_gemma":[0.0006827332,0.000021074702,0.001979903,0.00057959236,0.000044498567,3.2226333e-7,0.000301262,0.9910432,0.0021468534,0.0000060983402,0.002873193,0.00032125204],"about_ca_topic_score_codex":0.00014218793,"about_ca_topic_score_gemma":0.000105870735,"teacher_disagreement_score":0.96625006,"about_ca_system_score_codex":0.00007342731,"about_ca_system_score_gemma":0.00013313084,"threshold_uncertainty_score":0.6483806},"labels":[],"label_agreement":null},{"id":"W4386212357","doi":"10.1109/tse.2023.3307243","title":"ADPTriage: Approximate Dynamic Programming for Bug Triage","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Toronto Metropolitan University","funders":"","keywords":"Computer science; Triage; Markov decision process; Process (computing); Software bug; Software regression; Task (project management); Software; Pipeline (software); Software engineering; Markov process; Software development; Programming language; Software quality; Systems engineering","score_opus":0.019948979039290816,"score_gpt":0.2724453377257305,"score_spread":0.25249635868643966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386212357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011431117,0.000050449577,0.97827244,0.00008621564,0.0018305088,0.0008921995,0.00003423143,0.007400998,0.0000018315116],"genre_scores_gemma":[0.6517085,0.000033659155,0.3457638,0.000023780985,0.000090340334,0.0015543236,0.000014289727,0.00015084913,0.0006604979],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758047,0.000023451626,0.000353173,0.0006534993,0.00047980223,0.00090960466],"domain_scores_gemma":[0.9969578,0.0018816458,0.000043359563,0.0007972028,0.00010426175,0.00021577648],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063141534,0.0003355829,0.00030762565,0.0008555346,0.0002349556,0.00023618841,0.0008632572,0.00015268654,0.000009262717],"category_scores_gemma":[0.00041964525,0.00036873372,0.0002484938,0.0020448456,0.000021512451,0.00045641957,0.000010943477,0.00046245768,0.000120529316],"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":[0.000035333363,0.00012542236,0.000060057602,0.00048261214,0.00014709358,0.000060653263,0.00056333106,0.8319673,0.0013297963,0.00024106127,0.00033943885,0.16464792],"study_design_scores_gemma":[0.0014736638,0.00024887407,0.00069566997,0.0001609091,0.000025344725,0.00003052889,0.000021171552,0.98043925,0.010551877,0.000066719884,0.0055407705,0.0007451966],"about_ca_topic_score_codex":0.0000054689194,"about_ca_topic_score_gemma":0.0000017990578,"teacher_disagreement_score":0.6402773,"about_ca_system_score_codex":0.00023872886,"about_ca_system_score_gemma":0.00007251968,"threshold_uncertainty_score":0.99987644},"labels":[],"label_agreement":null},{"id":"W4386825342","doi":"10.1109/tse.2023.3313875","title":"A Grounded Theory of Cross-Community SECOs: Feedback Diversity Versus Synchronization","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Grounded theory; Computer science; Synchronization (alternating current); Diversity (politics); Terabyte; Upstream (networking); Data science; World Wide Web; Operating system; Qualitative research; Computer network; Sociology","score_opus":0.039422114663781684,"score_gpt":0.27669226271369296,"score_spread":0.23727014804991128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386825342","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":[0.22836015,0.000019264315,0.76834244,0.000007672814,0.0012483104,0.00013194342,0.000018034354,0.0018581359,0.000014072616],"genre_scores_gemma":[0.9890117,0.000019355186,0.010714617,0.0000068953786,0.000027943468,0.000027582555,0.0000052396736,0.000037585647,0.00014906174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984515,0.00009446618,0.00024367885,0.00029001734,0.0004987599,0.00042158214],"domain_scores_gemma":[0.9961151,0.0027200629,0.000045675286,0.000823925,0.00017054216,0.00012471357],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007397419,0.00021821736,0.00021502623,0.0005477788,0.0004641973,0.00010104864,0.0010142821,0.00013140177,0.000036792466],"category_scores_gemma":[0.00041888532,0.0002549354,0.00013877156,0.0018380577,0.000063338266,0.0008249665,0.000055655142,0.0006616641,0.00010136815],"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":[0.000078115394,0.00016223024,0.00069670065,0.00025028456,0.00016314533,0.000017122913,0.0017083634,0.9749824,0.00026546716,0.00070479146,0.00006935548,0.020902028],"study_design_scores_gemma":[0.010667985,0.0016472711,0.2261026,0.0007880268,0.00014779485,0.000055311197,0.00046983387,0.68515277,0.06999796,0.0015945673,0.00047451459,0.002901355],"about_ca_topic_score_codex":0.00005083094,"about_ca_topic_score_gemma":0.000008656568,"teacher_disagreement_score":0.7606516,"about_ca_system_score_codex":0.0002397921,"about_ca_system_score_gemma":0.00005805148,"threshold_uncertainty_score":0.9999903},"labels":[],"label_agreement":null},{"id":"W4388469715","doi":"10.1109/tse.2023.3327575","title":"Identifying the Hazard Boundary of ML-Enabled Autonomous Systems Using Cooperative Coevolutionary Search","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Reliability and Analysis Research","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 Ottawa","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Computer science; Boundary (topology); Hazard; Context (archaeology); Component (thermodynamics); Genetic algorithm; Artificial intelligence; Metaheuristic; Machine learning; Algorithm; Mathematics","score_opus":0.03903614166885182,"score_gpt":0.2854306910932624,"score_spread":0.24639454942441058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388469715","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":[0.07473881,0.00029635467,0.92317986,0.000061901264,0.0007115393,0.0002751079,0.000024048328,0.0007071718,0.0000052093474],"genre_scores_gemma":[0.98767734,0.00008149367,0.011832711,0.000011157299,0.000048306792,0.00006368299,0.0000032616013,0.00002867629,0.00025339646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978389,0.00015580459,0.00040629803,0.00041993632,0.0007059787,0.00047308372],"domain_scores_gemma":[0.99796945,0.0009261783,0.00005000125,0.00066251954,0.00028320128,0.00010867886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009325526,0.00019734002,0.00029576462,0.00054699666,0.0005909922,0.00025754553,0.0007470491,0.00009842812,0.000016188023],"category_scores_gemma":[0.000084088555,0.00016803964,0.0001976475,0.0025671138,0.00010601015,0.0004924188,0.000020983038,0.0005173591,0.00006343061],"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":[0.0000056921967,0.000042559306,0.00008249682,0.00012595377,0.00012649506,0.000015832378,0.0006026134,0.9953357,0.0016876586,0.00022077783,0.000045976278,0.0017082616],"study_design_scores_gemma":[0.0001775983,0.000047836525,0.00050495984,0.00014001117,0.000022215541,0.000025946232,0.00018204883,0.9933731,0.0051014074,0.000021106154,0.0002198311,0.00018395527],"about_ca_topic_score_codex":0.0001565075,"about_ca_topic_score_gemma":0.0000049602622,"teacher_disagreement_score":0.91293854,"about_ca_system_score_codex":0.00025400482,"about_ca_system_score_gemma":0.00031885153,"threshold_uncertainty_score":0.68524575},"labels":[],"label_agreement":null},{"id":"W4388623088","doi":"10.1109/tse.2023.3331254","title":"Concretization of Abstract Traffic Scene Specifications Using Metaheuristic Search","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","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":"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; Context (archaeology); Scalability; Constraint (computer-aided design); Metaheuristic; Set (abstract data type); Real-time computing; Artificial intelligence; Programming language; Database","score_opus":0.04044585752119628,"score_gpt":0.23861477820355717,"score_spread":0.1981689206823609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388623088","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":[0.35454667,0.000047254536,0.6430252,0.000008039361,0.00028733347,0.000116722316,0.000059229435,0.001892046,0.000017458833],"genre_scores_gemma":[0.9916367,0.000095272095,0.008107599,0.0000023522334,0.00002609789,0.000020935331,0.000013160996,0.00006578831,0.000032076307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990639,0.000008542651,0.00032080128,0.00017621176,0.00015508648,0.00027544625],"domain_scores_gemma":[0.99941695,0.00017453874,0.00002451694,0.00027495832,0.000048163685,0.00006089295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014758663,0.00017333656,0.00021454514,0.00047113476,0.00009632416,0.000010653099,0.0001474683,0.00015971115,0.000095688534],"category_scores_gemma":[0.000016348386,0.00020777796,0.00009380304,0.00087459385,0.00005052713,0.00010770572,0.0000010995126,0.00035404574,0.0000954294],"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":[0.0000051681855,0.000015156133,0.000015329157,0.00008763666,0.00006532957,0.000004510233,0.000101742364,0.9807527,0.011156107,0.000039484235,0.000017752825,0.0077390615],"study_design_scores_gemma":[0.00019806025,0.000021209815,0.0023851173,0.000062638064,0.000044384327,0.000009772158,0.00004426022,0.9247775,0.072076574,0.000005344771,0.00015368727,0.00022142916],"about_ca_topic_score_codex":0.000004963649,"about_ca_topic_score_gemma":0.0000021599756,"teacher_disagreement_score":0.63709,"about_ca_system_score_codex":0.000102457394,"about_ca_system_score_gemma":0.000033065364,"threshold_uncertainty_score":0.847294},"labels":[],"label_agreement":null},{"id":"W4388758252","doi":"10.1109/tse.2023.3332568","title":"Properties and Styles of Software Technology Tutorials","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; JavaScript; Python (programming language); Documentation; Software; TypeScript; Java; Resource (disambiguation); World Wide Web; Software engineering; Information retrieval; Programming language","score_opus":0.025863080000366374,"score_gpt":0.23587883220421202,"score_spread":0.21001575220384563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388758252","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":[0.14738713,0.00018871472,0.84806854,0.000069087764,0.00072171964,0.0001831697,0.000010515813,0.0033698557,0.0000012500404],"genre_scores_gemma":[0.9273437,0.000086690256,0.07221307,0.0000070410624,0.00004264383,0.00012013404,7.242379e-7,0.00004738292,0.00013856543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99847716,0.000018353065,0.000289368,0.00040470096,0.000376893,0.00043353767],"domain_scores_gemma":[0.99846536,0.00069809734,0.000037807014,0.0005776507,0.00011607443,0.00010501827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002766319,0.00022546585,0.000290676,0.0010970741,0.000103940794,0.00006108929,0.0005470748,0.00016196804,0.0000065128875],"category_scores_gemma":[0.00053606124,0.00022439126,0.00007171314,0.0017752984,0.00006805245,0.00030651852,0.000018615285,0.0003354053,0.00003993127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003526349,0.00018724958,0.0051692105,0.0012370822,0.00034450387,0.00010711279,0.0016305218,0.82503754,0.03492029,0.0017229619,0.00041530532,0.12919293],"study_design_scores_gemma":[0.002003989,0.0008976329,0.014527702,0.0013725415,0.00006709662,0.00018608797,0.00019710841,0.11209403,0.86229277,0.00039150708,0.0039252387,0.0020442824],"about_ca_topic_score_codex":0.000010348801,"about_ca_topic_score_gemma":0.0000011001048,"teacher_disagreement_score":0.8273725,"about_ca_system_score_codex":0.000057937297,"about_ca_system_score_gemma":0.00006181934,"threshold_uncertainty_score":0.915041},"labels":[],"label_agreement":null},{"id":"W4391164126","doi":"10.1109/tse.2024.3358258","title":"Multi-Language Software Development: Issues, Challenges, and Solutions","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Manitoba","funders":"Office of Naval Research","keywords":"Computer science; Interoperability; World Wide Web; Software development; Software; Software engineering; Programming language; Data science","score_opus":0.03412181408304442,"score_gpt":0.26704306635803715,"score_spread":0.23292125227499272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391164126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027838016,0.025927091,0.9644851,0.00013015355,0.001346303,0.00021832813,0.000014488246,0.0050915005,0.0000032148428],"genre_scores_gemma":[0.31644848,0.0012055462,0.68118364,0.000026470078,0.00010321367,0.00020534247,0.0000040535433,0.000117083735,0.00070618116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781823,0.000027075836,0.00029086892,0.0007394226,0.00043887296,0.0006855395],"domain_scores_gemma":[0.99827546,0.00078711443,0.000016183363,0.0005994021,0.000058447422,0.00026336464],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035074924,0.0003637226,0.00024245642,0.0006733082,0.00022381052,0.000272052,0.0005382744,0.00016576207,0.000024672187],"category_scores_gemma":[0.00016276092,0.00039141194,0.00009687585,0.00060223654,0.000035042154,0.0006548186,0.000020841358,0.00068047945,0.00017517313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006248489,0.00020547232,0.000037359918,0.0011273844,0.0003409718,0.0003975457,0.0112570785,0.077337764,0.00114052,0.0008019677,0.00027270117,0.907075],"study_design_scores_gemma":[0.0021829996,0.0004294298,0.014902087,0.003546895,0.00012000171,0.001061347,0.0003392986,0.8413184,0.03423101,0.00007979067,0.097180404,0.004608288],"about_ca_topic_score_codex":0.000013732153,"about_ca_topic_score_gemma":0.000011300442,"teacher_disagreement_score":0.9024667,"about_ca_system_score_codex":0.00020949873,"about_ca_system_score_gemma":0.00012385561,"threshold_uncertainty_score":0.9998538},"labels":[],"label_agreement":null},{"id":"W4391164257","doi":"10.1109/tse.2024.3358283","title":"Tracking the Evolution of Static Code Warnings: The State-of-the-Art and a Better Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; Static analysis; Static program analysis; Code (set theory); Workflow; Tracking (education); Source code; Software engineering; Software; Tracking system; Software evolution; Code smell; Programming language; Software development; Artificial intelligence; Software quality; Database; Software construction","score_opus":0.011706816219258082,"score_gpt":0.22705450869958402,"score_spread":0.21534769248032593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391164257","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":[0.07878472,0.0004697713,0.9193983,0.00020506413,0.00054980937,0.00025612031,0.000014753859,0.00031886913,0.0000025928732],"genre_scores_gemma":[0.9811691,0.000016634564,0.018572424,0.000017019469,0.000020891046,0.00006832626,3.086027e-7,0.000031276693,0.00010404373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869704,0.00005407749,0.0002620074,0.00027085343,0.00044874623,0.00026725003],"domain_scores_gemma":[0.9977044,0.0016042917,0.00003723967,0.00054611044,0.00006445275,0.00004349563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005022607,0.00016592217,0.00015093105,0.00018252758,0.00013317238,0.000112553644,0.00064112834,0.000044540076,0.0000029229275],"category_scores_gemma":[0.00012183008,0.00009951101,0.00011233409,0.00091926765,0.000092164846,0.00026866116,0.00001339936,0.00057999685,0.000004188368],"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":[0.000005282159,0.000041191426,0.0002744622,0.00049344735,0.00013756599,0.0000032064313,0.0059768585,0.95026994,0.001406924,0.00021077287,0.00015032281,0.041030005],"study_design_scores_gemma":[0.0001622813,0.000064789834,0.0047773016,0.00036395292,0.00003994769,0.000054481898,0.00006530925,0.9821112,0.011219543,0.00015077287,0.0007845606,0.00020583735],"about_ca_topic_score_codex":0.000025757296,"about_ca_topic_score_gemma":0.00000303522,"teacher_disagreement_score":0.90238434,"about_ca_system_score_codex":0.000119434495,"about_ca_system_score_gemma":0.0000788952,"threshold_uncertainty_score":0.4057941},"labels":[],"label_agreement":null},{"id":"W4391559702","doi":"10.1109/tse.2024.3363223","title":"DynAMICS: A Tool-Based Method for the Specification and Dynamic Detection of Android Behavioral Code Smells","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code smell; Computer science; Android (operating system); Source code; Software; Code (set theory); Software quality; Programming language; Artificial intelligence; Software engineering; Software development; Operating system","score_opus":0.01749395245963264,"score_gpt":0.29060479010718,"score_spread":0.27311083764754734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391559702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011958022,0.00032026772,0.9854585,0.0001032808,0.00089497626,0.0004255355,0.000074842246,0.0007642624,3.0719767e-7],"genre_scores_gemma":[0.7772757,0.000025522702,0.22242256,0.000005132901,0.000018677907,0.0001778896,0.0000023409348,0.000035963716,0.000036266432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887645,0.000021610073,0.0002386182,0.00037212466,0.00024959346,0.0002416152],"domain_scores_gemma":[0.9970705,0.0023332175,0.000026074078,0.00043770808,0.00007817905,0.000054321503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042046496,0.00017588383,0.0001559914,0.000357078,0.00010584646,0.00014407706,0.00031365818,0.00008999733,0.0000035530586],"category_scores_gemma":[0.000058989954,0.00015819332,0.000119013646,0.0005944907,0.000027051576,0.00024073765,0.0000035387488,0.00030409655,0.000003255995],"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":[0.000021633734,0.000060417027,0.000022547163,0.0003363249,0.0000679147,0.0000045630827,0.00024525102,0.66799706,0.01523914,0.00024481947,0.000006073017,0.31575423],"study_design_scores_gemma":[0.00018327162,0.00012910643,0.00067713275,0.00008266502,0.000033909593,0.000017779297,0.000009372779,0.95940226,0.039100654,0.00002879388,0.0001781066,0.00015691914],"about_ca_topic_score_codex":0.000019845016,"about_ca_topic_score_gemma":0.00002241348,"teacher_disagreement_score":0.7653176,"about_ca_system_score_codex":0.00020605628,"about_ca_system_score_gemma":0.000053472748,"threshold_uncertainty_score":0.6450936},"labels":[],"label_agreement":null},{"id":"W4391759551","doi":"10.1109/tse.2024.3362921","title":"Measuring and Characterizing (Mis)compliance of the Android Permission System","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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 Saskatchewan","funders":"","keywords":"Permission; Computer science; Android (operating system); Computer security; Operating system; Software engineering","score_opus":0.02234690032524389,"score_gpt":0.22126373324136642,"score_spread":0.19891683291612253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391759551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015118896,0.00025386724,0.9816741,0.000031345528,0.0010497543,0.0001482078,0.0000060748926,0.0017061646,0.000011626466],"genre_scores_gemma":[0.94840086,0.000018370612,0.051438857,0.000010597615,0.000023442957,0.000035161105,9.178621e-8,0.000022172735,0.000050435603],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991534,0.00001608374,0.00019401957,0.000285038,0.00019351611,0.0001579584],"domain_scores_gemma":[0.9994328,0.00009747285,0.000034131866,0.0003449573,0.000037748898,0.000052888983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117722266,0.00014373635,0.00013647761,0.00014909207,0.00012612525,0.00007767814,0.0002724256,0.000054995675,0.0000016710043],"category_scores_gemma":[0.0000123552745,0.000119248994,0.0000790148,0.00040797048,0.000018245924,0.0004130004,0.000005772146,0.00026366618,0.0000028411635],"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":[0.000017963912,0.00006058728,0.000053581378,0.0036721104,0.00011314751,0.000048171503,0.0016568693,0.07814191,0.4147998,0.0022744604,0.000024543704,0.49913684],"study_design_scores_gemma":[0.000091328664,0.00003980456,0.0006111138,0.0022484711,0.000013511684,0.00020700166,0.000020313542,0.19675964,0.7987745,0.000020168203,0.0009820826,0.00023206795],"about_ca_topic_score_codex":0.0000035399644,"about_ca_topic_score_gemma":3.8281152e-7,"teacher_disagreement_score":0.93328196,"about_ca_system_score_codex":0.000099181656,"about_ca_system_score_gemma":0.000021427773,"threshold_uncertainty_score":0.4862833},"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":"W4392121835","doi":"10.1109/tse.2024.3366753","title":"Factoring Expertise, Workload, and Turnover Into Code Review Recommendation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Techniques and Practices","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":"Computer science; Factoring; Workload; Code (set theory); Programming language; Software engineering; Parallel computing; Operating system; Accounting","score_opus":0.0172653523531208,"score_gpt":0.2706072422291304,"score_spread":0.2533418898760096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392121835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036986877,0.010908136,0.9829627,0.00060467795,0.0016815494,0.00017665728,0.0000060242305,0.003277795,0.000012566931],"genre_scores_gemma":[0.5052743,0.014254903,0.4793702,0.00042271873,0.00015684887,0.00025392883,0.0000040530595,0.00010153704,0.00016154035],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891925,0.000019090372,0.00024726382,0.00041409727,0.00017058574,0.00022973906],"domain_scores_gemma":[0.99907786,0.00042989152,0.000027676993,0.00032522235,0.000030595653,0.00010877999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023443128,0.00023261235,0.00018963582,0.00022042463,0.00009384013,0.00024688678,0.0002483569,0.00008662777,0.000049497066],"category_scores_gemma":[0.000053928783,0.00023210078,0.00008394981,0.0005163236,0.0000096558415,0.001073868,0.0000070142955,0.00042103181,0.000024937399],"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":[0.000004225636,0.000033740835,0.000013704216,0.0015331965,0.00009439992,0.000029672567,0.0008544699,0.010531259,0.0004761661,0.000333873,0.0010279744,0.9850673],"study_design_scores_gemma":[0.0004057904,0.00030449446,0.00024187745,0.01640403,0.00015704556,0.0003579276,0.000013496199,0.3808211,0.029776005,0.0002148873,0.56934017,0.0019631775],"about_ca_topic_score_codex":0.000016738928,"about_ca_topic_score_gemma":0.000002230467,"teacher_disagreement_score":0.98310417,"about_ca_system_score_codex":0.00012437103,"about_ca_system_score_gemma":0.000023693188,"threshold_uncertainty_score":0.9464795},"labels":[],"label_agreement":null},{"id":"W4394711492","doi":"10.1109/tse.2024.3387840","title":"Characterizing Timeout Builds in Continuous Integration","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","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","funders":"","keywords":"Timeout; Computer science; Programming language; Distributed computing; Computer network","score_opus":0.010545663966579999,"score_gpt":0.20854615975799312,"score_spread":0.19800049579141313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394711492","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":[0.08724609,0.00014942716,0.91033936,0.00018128543,0.00097049616,0.00008137524,0.0000039442384,0.0009494186,0.000078617384],"genre_scores_gemma":[0.9977275,0.00002100795,0.0013940772,0.00020311003,0.00036328172,0.000049767372,0.000012228646,0.000055855704,0.00017315336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990211,0.0000027683595,0.00026678637,0.00030410403,0.00016711064,0.00023811831],"domain_scores_gemma":[0.9997047,0.00004753367,0.000031131603,0.00014183065,0.0000629263,0.000011833344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016351514,0.00020664833,0.00020683344,0.00084373093,0.00007489208,0.00038501612,0.00011567056,0.00009102108,0.00009420415],"category_scores_gemma":[0.000024836243,0.00020397808,0.000116072915,0.0010025044,0.000010330727,0.001019988,0.0000017880116,0.00034160828,0.00019688462],"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":[0.00003640001,0.00016953258,0.00024416498,0.0010236297,0.00013183519,0.0000950358,0.00037026848,0.67038643,0.00964228,0.0008179225,0.00014508286,0.31693742],"study_design_scores_gemma":[0.00020710607,0.0000063869734,0.0002694718,0.00092426204,0.000094258925,0.0000053020217,0.000062831365,0.9911517,0.0021432047,0.00006428316,0.0046712835,0.00039994283],"about_ca_topic_score_codex":0.00014502033,"about_ca_topic_score_gemma":0.000020771535,"teacher_disagreement_score":0.91048145,"about_ca_system_score_codex":0.00005816573,"about_ca_system_score_gemma":0.00001504571,"threshold_uncertainty_score":0.8317985},"labels":[],"label_agreement":null},{"id":"W4398187606","doi":"10.1109/tse.2024.3402157","title":"A Lean Simulation Framework for Stress Testing IoT Cloud Systems","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Digital Transformation in Industry","field":"Engineering","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":"Stem Cell Network; University of Ottawa","funders":"","keywords":"Computer science; Cloud computing; Stress testing (software); Cloud testing; Internet of Things; Software engineering; Distributed computing; Embedded system; Operating system; Cloud computing security","score_opus":0.03102711421944842,"score_gpt":0.2550498836915008,"score_spread":0.22402276947205235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398187606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008277949,0.0002450227,0.9796476,0.0000055079045,0.0062304367,0.00042167844,0.00031819032,0.004719227,0.00013441121],"genre_scores_gemma":[0.96838695,0.0000056170065,0.030709244,0.0000057374123,0.00041653492,0.00023177177,0.000009970001,0.00015168231,0.00008247855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988485,0.000004396853,0.0003694141,0.00022443672,0.00020804365,0.00034519323],"domain_scores_gemma":[0.99831593,0.0012945575,0.000014994685,0.0002097975,0.00005886932,0.00010587161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010004391,0.0002750304,0.00019152342,0.00028519158,0.0000915112,0.00025521542,0.00012670162,0.00023653175,0.000016965196],"category_scores_gemma":[0.000056431396,0.00031531026,0.00012036823,0.00053791166,0.0000124159415,0.0003265134,5.332001e-7,0.0005331574,0.00005006445],"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":[0.0000035270284,0.0000130654425,0.0000052130335,0.0009894051,0.00008271242,0.0000036224696,0.00017881446,0.9854407,0.00006991513,0.0007562211,0.000050533687,0.012406294],"study_design_scores_gemma":[0.00011810595,0.000039660536,0.000007800187,0.001391614,0.00003835231,0.000009607968,0.00006070665,0.9923974,0.0030650727,0.00008142715,0.0024528874,0.00033731727],"about_ca_topic_score_codex":0.000002847985,"about_ca_topic_score_gemma":4.759316e-7,"teacher_disagreement_score":0.960109,"about_ca_system_score_codex":0.00018999353,"about_ca_system_score_gemma":0.000021490607,"threshold_uncertainty_score":0.9999299},"labels":[],"label_agreement":null},{"id":"W4399768519","doi":"10.1109/tse.2024.3411928","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","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":"University of Alberta","funders":"Japan Society for the Promotion of Science; JST-Mirai Program; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Programming language; Modeling language; Software engineering; Data science; Natural language processing; Software","score_opus":0.013074621913195335,"score_gpt":0.2445529802957176,"score_spread":0.23147835838252226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399768519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013322844,0.00016836869,0.9960296,0.000079005076,0.00058585894,0.00015725724,0.00007543527,0.0015653017,0.0000068679333],"genre_scores_gemma":[0.5401459,0.0000023927068,0.45966786,0.000036914185,0.000024287408,0.00003646128,0.000002018094,0.000018885887,0.00006530474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988404,0.000009663312,0.00017290717,0.00044861273,0.00020096051,0.000327447],"domain_scores_gemma":[0.99906147,0.00028647794,0.000015811458,0.0005034332,0.000037416215,0.0000954171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014311606,0.00018311196,0.00019372218,0.0005569106,0.00009824716,0.00014110927,0.00036549542,0.00012065951,0.000011037592],"category_scores_gemma":[0.000010641735,0.00019790603,0.00031558028,0.0009683956,0.000005163326,0.00040207308,0.0000027668777,0.00029887073,0.000006578998],"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":[0.000003078969,0.000024526957,5.8864083e-7,0.000059235124,0.0001661653,0.000010048913,0.00077509746,0.9724391,0.000038520087,0.022543654,0.0000073780798,0.003932577],"study_design_scores_gemma":[0.00013551422,0.000018121962,6.7219565e-7,0.00007246695,0.00014890783,0.0000010872047,0.00002021402,0.9974283,0.0010785746,0.00081965054,0.00007039687,0.00020611778],"about_ca_topic_score_codex":0.000009035994,"about_ca_topic_score_gemma":0.0000064401574,"teacher_disagreement_score":0.5388136,"about_ca_system_score_codex":0.00012764001,"about_ca_system_score_gemma":0.00007753411,"threshold_uncertainty_score":0.8070374},"labels":[],"label_agreement":null},{"id":"W4400079181","doi":"10.1109/tse.2024.3419919","title":"A Scalable t-Wise Coverage Estimator: Algorithms and Applications","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Statistical Methods and Inference","field":"Mathematics","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; Algorithm; Scalability; Estimator; Database; Mathematics; Statistics","score_opus":0.028333731620727668,"score_gpt":0.3048803617272769,"score_spread":0.27654663010654923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400079181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005048832,0.00018928926,0.99786246,0.000026899586,0.00029229056,0.000205632,0.00011424253,0.0007093959,0.000094937655],"genre_scores_gemma":[0.11334692,0.00007047396,0.88571614,0.000021856082,0.00007288547,0.00030020933,0.0000013541885,0.00005779076,0.00041238178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925876,0.000012117495,0.00017806825,0.00023990066,0.00012913212,0.00018202137],"domain_scores_gemma":[0.9983939,0.0012784747,0.000011657516,0.00018196212,0.000025421288,0.00010857227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001241037,0.00015016545,0.00015860963,0.00011029572,0.00009461343,0.00008789144,0.00006333902,0.00006832766,0.00011597814],"category_scores_gemma":[0.00007666039,0.0001441155,0.00004992924,0.00022709613,0.00002594086,0.00008507452,0.0000012947738,0.0002538844,0.000042277792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012551075,0.00022696084,0.000014846139,0.0018323535,0.00021251022,0.000049367856,0.0003295091,0.021471689,0.000857943,0.13997175,0.00096394727,0.83405656],"study_design_scores_gemma":[0.00063331577,0.00021961499,0.00014848186,0.0010627664,0.00034639478,0.00018573417,0.000043459986,0.86316556,0.011076013,0.09251386,0.02943467,0.0011701486],"about_ca_topic_score_codex":0.0000051645184,"about_ca_topic_score_gemma":5.9545954e-7,"teacher_disagreement_score":0.8416939,"about_ca_system_score_codex":0.000043217315,"about_ca_system_score_gemma":0.0000236561,"threshold_uncertainty_score":0.587686},"labels":[],"label_agreement":null},{"id":"W4400276346","doi":"10.1109/tse.2024.3422369","title":"Characterizing the Prevalence, Distribution, and Duration of Stale Reviewer Recommendations","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Species Distribution and Climate Change","field":"Environmental 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":"Computer science; Duration (music)","score_opus":0.014897566962101812,"score_gpt":0.23222201763170797,"score_spread":0.21732445066960615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400276346","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":[0.12820499,0.0005145763,0.8676697,0.000814631,0.0011317631,0.0003057956,0.0009643593,0.0002638453,0.000130318],"genre_scores_gemma":[0.99775404,0.0014074859,0.00026291437,0.000044821285,0.000021153963,0.000060737842,0.00004315935,0.000012135184,0.00039356935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942225,0.000014759273,0.0001805964,0.0001482526,0.00012346887,0.00011064487],"domain_scores_gemma":[0.99971133,0.000087011635,0.00002529729,0.00012576622,0.000014425712,0.00003616096],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014715153,0.000088651046,0.00007329753,0.00002239201,0.00011706224,0.00004059734,0.00006428467,0.000032630942,0.006345957],"category_scores_gemma":[0.000029397921,0.000070640584,0.00004788899,0.00026711682,0.000048006274,0.00020456678,0.0000025862385,0.000122028665,0.00008785226],"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":[0.00016471016,0.0014708999,0.008334234,0.010678394,0.00080792507,0.000035922996,0.011750161,0.031771865,0.17845179,0.010022901,0.10011415,0.64639705],"study_design_scores_gemma":[0.00045942914,0.00020072909,0.08038487,0.001279586,0.00029764237,0.00007384788,0.00063632446,0.016468469,0.06500744,0.000039862476,0.83428603,0.0008657867],"about_ca_topic_score_codex":0.000009056319,"about_ca_topic_score_gemma":0.0000067276546,"teacher_disagreement_score":0.86954904,"about_ca_system_score_codex":0.00013978798,"about_ca_system_score_gemma":0.0000042875963,"threshold_uncertainty_score":0.9945624},"labels":[],"label_agreement":null},{"id":"W4400351643","doi":"10.1109/tse.2024.3423712","title":"Revisiting the Performance of Deep Learning-Based Vulnerability Detection on Realistic Datasets","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Network Security and Intrusion Detection","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":"Computer science; Vulnerability (computing); Artificial intelligence; Deep learning; Data science; Machine learning; Computer security","score_opus":0.009199555430048047,"score_gpt":0.2236496439675864,"score_spread":0.21445008853753836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400351643","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":[0.04398535,0.00007893289,0.9540475,0.000053458807,0.0010785563,0.000114913884,0.000012036783,0.0006233879,0.0000058750684],"genre_scores_gemma":[0.9973282,0.000030431342,0.0024396693,0.000029669203,0.00011156624,0.000032095202,0.000003832015,0.000016153535,0.00000833668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893504,0.000073649906,0.0002413237,0.00030987378,0.00025485083,0.00018528434],"domain_scores_gemma":[0.9988531,0.0006071308,0.00004105834,0.00041576495,0.00003817474,0.000044788732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046668414,0.00014780574,0.00012296488,0.00017244965,0.00027742097,0.00009636647,0.0002626897,0.00006878704,0.000021423146],"category_scores_gemma":[0.00005865927,0.00012265917,0.000093308605,0.000661991,0.000024935905,0.00028146082,0.0000029824228,0.0006618651,0.000020543464],"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":[0.000013059496,0.000010446194,0.0000021074718,0.00011693217,0.000009950309,0.0000017763238,0.00006523359,0.75690883,0.0003086404,0.000040854135,0.0000029735113,0.24251921],"study_design_scores_gemma":[0.00006903216,0.00017479023,0.00018045104,0.0002280433,0.000013888149,0.000010327094,0.0000030103224,0.94925755,0.048596717,0.0000068215527,0.0013399794,0.00011940032],"about_ca_topic_score_codex":0.000016832257,"about_ca_topic_score_gemma":0.0000053928297,"teacher_disagreement_score":0.9533429,"about_ca_system_score_codex":0.000091627495,"about_ca_system_score_gemma":0.000018650067,"threshold_uncertainty_score":0.5001896},"labels":[],"label_agreement":null},{"id":"W4400647264","doi":"10.1109/tse.2024.3428324","title":"Towards Efficient Fine-Tuning of Language Models With Organizational Data for Automated Software Review","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"","keywords":"Computer science; Software engineering; Software; Programming language; Data science","score_opus":0.024687243253182226,"score_gpt":0.27963316747094596,"score_spread":0.25494592421776374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400647264","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000923429,0.0037928584,0.9890337,0.000086554945,0.00054623786,0.0005027704,0.000341067,0.004771214,0.0000021865644],"genre_scores_gemma":[0.2998173,0.0001527795,0.69950855,0.000039690716,0.00005544447,0.00014282294,0.00008954907,0.00012552773,0.00006836892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980215,0.00001947648,0.00034757328,0.00063230784,0.0005933425,0.00038581475],"domain_scores_gemma":[0.9974506,0.0010220116,0.000037980346,0.001145082,0.00021753568,0.00012682554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004178314,0.00027973737,0.00032105364,0.0003932631,0.000084262305,0.000108958826,0.0011295337,0.0000840685,0.000024570167],"category_scores_gemma":[0.00035419955,0.00025616595,0.0000857755,0.0015500662,0.000025237154,0.0004699941,0.00002462636,0.00031761162,0.000011318262],"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":[0.0000054141033,0.000048479542,0.000004449031,0.002621303,0.00011317042,0.000023502607,0.00024602137,0.9868396,0.00020730095,0.00027479732,0.00045093286,0.009165066],"study_design_scores_gemma":[0.00021439322,0.000082262995,0.000026833779,0.0029128352,0.000048856222,0.00004837097,0.0000051238208,0.9932243,0.0028823647,0.0000075982516,0.00025953955,0.00028748295],"about_ca_topic_score_codex":0.000011538539,"about_ca_topic_score_gemma":0.0000017161992,"teacher_disagreement_score":0.29889387,"about_ca_system_score_codex":0.0001251596,"about_ca_system_score_gemma":0.00029535062,"threshold_uncertainty_score":0.99998903},"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":"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":"W4401211363","doi":"10.1109/tse.2024.3436623","title":"Long Live the Image: On Enabling Resilient Production Database Containers for Microservice Applications","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Queen's University; Queen's University Belfast","keywords":"Computer science; Production (economics); Database; Microservices; Software engineering; World Wide Web; Operating system; Cloud computing","score_opus":0.010017254744161024,"score_gpt":0.24516179219632728,"score_spread":0.23514453745216626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401211363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061077713,0.00043423238,0.98824,0.0006271044,0.0022263215,0.001122448,0.00004347969,0.001195456,0.0000031845218],"genre_scores_gemma":[0.93648064,0.00014857,0.059920322,0.00018131429,0.0004763658,0.0023467115,0.000017642873,0.00006803313,0.00036038214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985987,0.000023053188,0.00026956399,0.0005815101,0.0002308,0.0002963866],"domain_scores_gemma":[0.99844134,0.0005017784,0.00003416225,0.0008189941,0.00013287821,0.000070820846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044257485,0.0002101808,0.00014065222,0.00019011271,0.00036710777,0.00022428078,0.00044701152,0.00006965188,0.000004956965],"category_scores_gemma":[0.0000393527,0.00016043849,0.00013860848,0.000630422,0.000029931258,0.00054483884,0.000005155835,0.00035017458,0.0000921911],"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":[0.000080314305,0.0003165678,0.000042231135,0.0026102546,0.00024114153,0.000014677791,0.0031105662,0.8608724,0.013757895,0.0011246456,0.0017762416,0.116053075],"study_design_scores_gemma":[0.0011213758,0.00056748133,0.00048798724,0.0023323926,0.00024126445,0.00020967596,0.0005864553,0.6095884,0.3070217,0.00015474489,0.075950995,0.0017375523],"about_ca_topic_score_codex":0.000022937675,"about_ca_topic_score_gemma":0.000010146017,"teacher_disagreement_score":0.9303729,"about_ca_system_score_codex":0.0001802046,"about_ca_system_score_gemma":0.00007916079,"threshold_uncertainty_score":0.6542492},"labels":[],"label_agreement":null},{"id":"W4401328698","doi":"10.1109/tse.2024.3438119","title":"AddressWatcher: Sanitizer-Based Localization of Memory Leak Fixes","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Data Storage Technologies","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; Hand sanitizer; Leak; Memory leak; Embedded system; Leak detection; Programming language; Memory management; Overlay; Engineering","score_opus":0.0139245237817579,"score_gpt":0.23100124283280993,"score_spread":0.21707671905105203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401328698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053956016,0.00037668302,0.9944922,0.00005305737,0.0008322036,0.000112653266,0.000046400408,0.003536072,0.000011169261],"genre_scores_gemma":[0.8055951,0.000026306281,0.19420826,0.000030227053,0.000016947608,0.000040834086,0.0000037992163,0.000029361105,0.000049167396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990532,0.000011030016,0.00020935641,0.00031398368,0.00021786704,0.00019459357],"domain_scores_gemma":[0.9991263,0.00024636625,0.000026985861,0.00051598693,0.000045250046,0.000039076323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000796122,0.00016681668,0.00015374584,0.00034472274,0.00005630489,0.000057241916,0.00043673336,0.00009731905,0.000023187355],"category_scores_gemma":[0.000038193106,0.0001732092,0.00008214099,0.00072879845,0.000042338106,0.000521636,0.0000043912764,0.0002499887,0.000025033884],"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":[0.0000025637319,0.00002744724,0.0000015349256,0.00015304776,0.000021731365,0.000019664756,0.00009946757,0.94497925,0.0012902439,0.0005037773,0.00013304746,0.05276823],"study_design_scores_gemma":[0.0001441032,0.00007522472,0.0000063140897,0.00028424332,0.000015890084,0.000009086682,0.000021697735,0.6966931,0.30027285,0.00014650167,0.0020940374,0.00023689297],"about_ca_topic_score_codex":0.000008700923,"about_ca_topic_score_gemma":0.000005165594,"teacher_disagreement_score":0.80505556,"about_ca_system_score_codex":0.000086401335,"about_ca_system_score_gemma":0.00005097267,"threshold_uncertainty_score":0.7063266},"labels":[],"label_agreement":null},{"id":"W4401537664","doi":"10.1109/tse.2024.3443741","title":"Predicting the First Response Latency of Maintainers and Contributors in Pull Requests","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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; Concordia University","funders":"","keywords":"Computer science; Latency (audio); Parallel computing; Telecommunications","score_opus":0.005120476108220783,"score_gpt":0.2077019446545747,"score_spread":0.20258146854635392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401537664","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":[0.3627081,0.0002735379,0.63559365,0.00023762161,0.00070427713,0.00014292049,0.0000066545417,0.00033116064,0.000002085477],"genre_scores_gemma":[0.9972082,0.00004851553,0.0026247106,0.000019104833,0.00002098361,0.000042341508,2.202588e-7,0.000013278762,0.000022658292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902254,0.0000401065,0.00028986137,0.0002593103,0.0001699358,0.00021825277],"domain_scores_gemma":[0.9986893,0.0008934415,0.000025568446,0.00031226454,0.00003450061,0.00004494679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008218868,0.00013401557,0.00015497403,0.00022243716,0.00008244454,0.000061624254,0.00023521259,0.00007950867,0.0000026411174],"category_scores_gemma":[0.00009020693,0.000099323566,0.000064026826,0.0005956168,0.00003503083,0.00031747995,0.0000044127723,0.00030012714,0.0000039165498],"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":[0.00029389875,0.00017979753,0.034427736,0.0020096847,0.00022420156,0.0001845984,0.0144242095,0.8990997,0.0011226883,0.0013545554,0.00011571959,0.046563208],"study_design_scores_gemma":[0.00084408274,0.00040769397,0.0586993,0.002316121,0.000040173618,0.00017740561,0.00016125,0.9245999,0.009690968,0.00014569986,0.002327166,0.00059023546],"about_ca_topic_score_codex":0.00007129892,"about_ca_topic_score_gemma":0.000021350843,"teacher_disagreement_score":0.6345001,"about_ca_system_score_codex":0.000105115345,"about_ca_system_score_gemma":0.000057709574,"threshold_uncertainty_score":0.40502974},"labels":[],"label_agreement":null},{"id":"W4402040489","doi":"10.1109/tse.2024.3452595","title":"RLocator: Reinforcement Learning for Bug Localization","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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 Calgary; University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Software bug; Programming language; Software engineering; Human–computer interaction; Machine learning; Software","score_opus":0.014284326079011332,"score_gpt":0.2518457570048798,"score_spread":0.23756143092586848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402040489","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055932725,0.00022873581,0.9930002,0.000051720246,0.0020074444,0.00032334818,0.0000028923344,0.0038194756,0.000006830852],"genre_scores_gemma":[0.95006394,0.000035072193,0.048735693,0.000030484158,0.00010807198,0.00030070436,0.000005099408,0.00007465146,0.00064627867],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984784,0.000013223705,0.00024862122,0.0004515373,0.00037231867,0.00043587267],"domain_scores_gemma":[0.9984454,0.0009523821,0.000015902177,0.00036803627,0.0000822684,0.00013603423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002671457,0.00022622658,0.0001555662,0.0004989707,0.00016638175,0.0002814524,0.00038940323,0.000102944956,0.000022909822],"category_scores_gemma":[0.00014759503,0.00024555318,0.00014172102,0.00079930684,0.000012998219,0.00047736426,0.0000047708195,0.00041507732,0.0000868772],"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":[0.0000036086305,0.000013038035,0.000019259567,0.00021565941,0.000047970283,0.000008048114,0.00022770897,0.98195446,0.00019130496,0.0005273877,0.0002387742,0.016552808],"study_design_scores_gemma":[0.00016961934,0.000127983,0.00003047886,0.00018649487,0.000011878018,0.0000141893615,0.0000052087785,0.9695449,0.013128478,0.00001847644,0.016493997,0.0002683365],"about_ca_topic_score_codex":0.0000068251243,"about_ca_topic_score_gemma":6.3343356e-7,"teacher_disagreement_score":0.9495046,"about_ca_system_score_codex":0.00025566082,"about_ca_system_score_gemma":0.00008201172,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4402661245","doi":"10.1109/tse.2024.3461657","title":"D<sup>3</sup>: Differential Testing of Distributed Deep Learning With Model Generation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","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":"York University","funders":"Division of Computing and Communication Foundations","keywords":"Computer science; Artificial intelligence; Programming language","score_opus":0.014824459603576702,"score_gpt":0.21919131723217236,"score_spread":0.20436685762859566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402661245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043802597,0.00004322062,0.95444965,0.000016413707,0.00031612808,0.000105130566,0.000008481061,0.0012519252,0.0000064252863],"genre_scores_gemma":[0.7221721,0.000002713999,0.27766442,0.0000033235015,0.000065542445,0.000019754592,0.0000062180266,0.00003418205,0.00003173492],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870485,0.000034121902,0.00025805435,0.00040330825,0.0003233165,0.0002763375],"domain_scores_gemma":[0.99923855,0.0002957774,0.000045561086,0.00026357837,0.00008110652,0.00007543873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001215492,0.00023146685,0.00020122941,0.00024947413,0.00017723696,0.00014784285,0.00028831122,0.00008793383,0.000011381262],"category_scores_gemma":[0.000070086135,0.0002213683,0.000080171834,0.000733219,0.000021888534,0.0005115815,0.000006426994,0.0006532473,0.000005706796],"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":[0.0000049349574,0.000021238253,0.000033809687,0.000070813374,0.000048374528,0.00001180505,0.00047884765,0.97263855,0.0015853556,0.00028656033,0.000002195312,0.024817493],"study_design_scores_gemma":[0.0001821153,0.000085814616,0.000030877687,0.00015840781,0.000035902067,0.000021336216,0.000012131257,0.9947996,0.0044092867,0.000010370353,0.000024151537,0.00022997284],"about_ca_topic_score_codex":0.000011525626,"about_ca_topic_score_gemma":0.0000014735606,"teacher_disagreement_score":0.6783695,"about_ca_system_score_codex":0.000100120844,"about_ca_system_score_gemma":0.000057704194,"threshold_uncertainty_score":0.9027138},"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":"W4403210636","doi":"10.1109/tse.2024.3475375","title":"Exploring the Effectiveness of LLMs in Automated Logging Statement Generation: An Empirical Study","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Semantic Web and Ontologies","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":"Basic and Applied Basic Research Foundation of Guangdong Province; Science Foundation Ireland","keywords":"Computer science; Logging; Statement (logic); Empirical research; Data science; Software engineering; Computer security; Risk analysis (engineering); Business; Forestry; Statistics; Political science","score_opus":0.07912131087874133,"score_gpt":0.3136969886310401,"score_spread":0.2345756777522988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403210636","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":[0.46181244,0.000036477388,0.53648585,0.000013096964,0.0008087074,0.00014970751,8.918411e-7,0.00069193135,9.11737e-7],"genre_scores_gemma":[0.99202096,0.000008750509,0.0077577257,0.000006116665,0.00002339699,0.00016758207,4.734003e-7,0.000012729552,0.0000022587872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989716,0.0001406024,0.00023742732,0.00027880006,0.000197137,0.00017444273],"domain_scores_gemma":[0.99908894,0.00053076807,0.000013717251,0.00031261076,0.000022998585,0.00003093681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007140248,0.00012851538,0.00015162703,0.00023398941,0.00006458874,0.000100369514,0.00027004952,0.000023882314,0.0000020436385],"category_scores_gemma":[0.000016084368,0.00009865395,0.000046039248,0.0005244485,0.000012061189,0.0005705753,0.000003978053,0.00018466936,0.00000363955],"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":[0.000007518367,0.00016981937,0.0005884747,0.000107654145,0.000048845854,0.000045628156,0.0028438088,0.9849925,0.0013806426,0.00008205773,0.0000038436697,0.009729191],"study_design_scores_gemma":[0.00021179745,0.00020983967,0.026655128,0.00014592268,0.000013161692,0.000008392686,0.00020390561,0.95196503,0.02041298,0.000009697886,0.000022572665,0.0001415793],"about_ca_topic_score_codex":0.00004724019,"about_ca_topic_score_gemma":0.000024833134,"teacher_disagreement_score":0.5302085,"about_ca_system_score_codex":0.00008764043,"about_ca_system_score_gemma":0.000036405963,"threshold_uncertainty_score":0.40229914},"labels":[],"label_agreement":null},{"id":"W4403511313","doi":"10.1109/tse.2024.3482984","title":"TEASMA: A Practical Methodology for Test Adequacy Assessment of Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","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":"Huawei Technologies (Canada); University of Ottawa","funders":"Huawei Technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland","keywords":"Computer science; Artificial neural network; Test (biology); Artificial intelligence; Machine learning; Reliability engineering; Software engineering; Engineering","score_opus":0.03694737320835111,"score_gpt":0.34241031545145006,"score_spread":0.30546294224309894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403511313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029581098,0.00006203168,0.99570787,0.00024149523,0.0026201464,0.00024399497,0.000007966265,0.00081324,0.00000745375],"genre_scores_gemma":[0.4809994,0.0000030384517,0.518791,0.000020853351,0.0000800355,0.000062472296,0.0000012876519,0.000024974697,0.000016932447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863476,0.00008417285,0.00031936972,0.00041692093,0.00020597196,0.00033880005],"domain_scores_gemma":[0.99379236,0.005660551,0.000052608983,0.000341661,0.00006442017,0.00008838277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055919937,0.00020761817,0.00027358814,0.0002473292,0.00010073612,0.000086709,0.00033148675,0.00013323693,0.000017164895],"category_scores_gemma":[0.00033794294,0.00021000036,0.0001841938,0.0005053582,0.000027732036,0.00045515262,0.00000754153,0.0007292984,0.0000020564314],"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":[0.000005360199,0.000047579582,0.000024115234,0.00009228244,0.000056407483,0.000017876582,0.000112795635,0.94208175,0.00034957164,0.0031316213,0.000007356603,0.054073304],"study_design_scores_gemma":[0.00020416096,0.00017217919,0.0001485849,0.000046158417,0.000050639403,0.000060590515,0.00000901636,0.9982512,0.0005528188,0.000053978896,0.00026245648,0.00018823853],"about_ca_topic_score_codex":0.0000056096005,"about_ca_topic_score_gemma":0.0000019476836,"teacher_disagreement_score":0.4807036,"about_ca_system_score_codex":0.00010364695,"about_ca_system_score_gemma":0.000064717125,"threshold_uncertainty_score":0.8563566},"labels":[],"label_agreement":null},{"id":"W4403635895","doi":"10.1109/tse.2024.3484586","title":"Refactoring-Aware Block Tracking in Commit History","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Database Systems and Queries","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; Commit; Block (permutation group theory); Programming language; Software engineering; Database; Software","score_opus":0.01952255369704392,"score_gpt":0.23632262482171681,"score_spread":0.2168000711246729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403635895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002386479,0.0008315978,0.9921325,0.000024274726,0.0031319687,0.000102160695,0.000019618716,0.0013426142,0.00002879531],"genre_scores_gemma":[0.9448854,0.000041379306,0.054540705,0.000028351873,0.00007942139,0.000056769648,0.0000017090938,0.00004151032,0.0003247947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888563,0.000016098842,0.00024791685,0.00037659906,0.00019526748,0.00027851487],"domain_scores_gemma":[0.99928415,0.00017691393,0.000018766146,0.00041794454,0.000023646318,0.00007860398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001236709,0.00019442369,0.0001768858,0.0003446471,0.00005289571,0.000047381916,0.00022666766,0.00007093706,0.00002044205],"category_scores_gemma":[0.000010833788,0.00020493558,0.00008657445,0.0003664133,0.000013488863,0.0008476884,0.000003497808,0.00043855267,0.000040242507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010839127,0.00013050665,0.00007558871,0.0008207686,0.000091820475,0.00059318915,0.0036565075,0.87503344,0.0024897687,0.012055268,0.0006924294,0.104349844],"study_design_scores_gemma":[0.0006004955,0.00016181005,0.0005171154,0.0026282594,0.000026624055,0.00021876748,0.00009816381,0.4113582,0.020470308,0.000055319335,0.5623627,0.0015022615],"about_ca_topic_score_codex":0.000042205324,"about_ca_topic_score_gemma":0.000027095242,"teacher_disagreement_score":0.94249886,"about_ca_system_score_codex":0.0004979281,"about_ca_system_score_gemma":0.000063470856,"threshold_uncertainty_score":0.8357031},"labels":[],"label_agreement":null},{"id":"W4403918536","doi":"10.1109/tse.2024.3488525","title":"AIM: Automated Input Set Minimization for Metamorphic Security Testing","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"H2020 European Research Council; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Science Foundation Ireland; Université du Luxembourg; University of Ottawa","keywords":"Computer science; Set (abstract data type); Minification; Programming language; Theoretical computer science; Software engineering; Data mining; Algorithm","score_opus":0.02010568178901174,"score_gpt":0.25042375612891415,"score_spread":0.23031807433990242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403918536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013223885,0.0001571477,0.97476393,0.00005926089,0.0029697518,0.00039639228,0.000044074117,0.008379225,0.0000063605135],"genre_scores_gemma":[0.8489635,0.000008706614,0.15062489,0.000034517965,0.00009069974,0.00019545085,0.000005921922,0.00003695378,0.00003935668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856883,0.000024435036,0.0003459679,0.00048929447,0.00023698117,0.0003344669],"domain_scores_gemma":[0.9986245,0.00068758364,0.000035337696,0.00042456793,0.00013118371,0.00009683445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032867715,0.00023941045,0.00022282182,0.0003056319,0.0001836457,0.00021375738,0.00032329673,0.0001423343,0.000007761038],"category_scores_gemma":[0.00010282935,0.00022628305,0.0001516687,0.0010838289,0.000016567092,0.00068188406,0.0000048497554,0.00026193744,0.000042972362],"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":[0.0000075057264,0.0000624114,0.00008035035,0.0010980191,0.0001216724,0.000013399418,0.0010983525,0.967375,0.00035808532,0.00016323118,0.00066647027,0.028955502],"study_design_scores_gemma":[0.0001773455,0.0000842716,0.000112308204,0.00025669322,0.000031516505,0.00003794769,0.000006891933,0.9927573,0.0049797487,0.00007722114,0.001213886,0.00026485228],"about_ca_topic_score_codex":0.000011211446,"about_ca_topic_score_gemma":0.0000014315622,"teacher_disagreement_score":0.8357396,"about_ca_system_score_codex":0.00012976212,"about_ca_system_score_gemma":0.0001042234,"threshold_uncertainty_score":0.92275554},"labels":[],"label_agreement":null},{"id":"W4404102001","doi":"10.1109/tse.2024.3491496","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","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":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Software engineering","score_opus":0.01605624727510781,"score_gpt":0.25027956476942625,"score_spread":0.23422331749431843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404102001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002550437,0.00013137983,0.9943503,0.000023972676,0.0027754323,0.00032788448,0.0000014474513,0.002061277,0.000073257026],"genre_scores_gemma":[0.6131497,0.000020352525,0.3860597,0.000009637735,0.0001684929,0.0001408016,0.0000031871687,0.00005144694,0.00039670384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998347,0.000028150906,0.00031157403,0.0005350021,0.00032886452,0.0004494149],"domain_scores_gemma":[0.9990811,0.00037901,0.000037780334,0.00033883867,0.000046986206,0.000116280346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032799004,0.0002786597,0.00021128441,0.00032032694,0.00034081846,0.00024796513,0.00046705612,0.000112211266,0.000014035708],"category_scores_gemma":[0.00006394016,0.0003007189,0.0001988654,0.0005472695,0.000012598634,0.0005918661,0.000009684108,0.0007181081,0.000017901366],"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":[0.000010005335,0.00001591549,0.000019581206,0.00016503502,0.00008058507,0.000008184721,0.0006327659,0.95645684,0.000082378225,0.00042992522,0.000007503228,0.042091258],"study_design_scores_gemma":[0.00026748527,0.0000718774,0.000038540347,0.00013969118,0.000029175726,0.000013627091,0.000033477078,0.99551755,0.0014285216,0.000008901276,0.0021504485,0.00030072426],"about_ca_topic_score_codex":0.000008319195,"about_ca_topic_score_gemma":2.033895e-7,"teacher_disagreement_score":0.61289465,"about_ca_system_score_codex":0.0002904454,"about_ca_system_score_gemma":0.00004277338,"threshold_uncertainty_score":0.9999445},"labels":[],"label_agreement":null},{"id":"W4404317069","doi":"10.1109/tse.2024.3470368","title":"Scoping Software Engineering for AI: The TSE Perspective","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Reinforcement Learning in Robotics","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; University of Alberta; Queen's University; University of Toronto","funders":"","keywords":"Computer science; Software engineering; Perspective (graphical); Software development; Software; Programming language; Artificial intelligence","score_opus":0.013694603385929241,"score_gpt":0.25763863923195046,"score_spread":0.24394403584602123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404317069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015571564,0.0004408632,0.9925846,0.0002926887,0.0032400724,0.0005796221,0.0000097175225,0.0026874326,0.000009302154],"genre_scores_gemma":[0.5478389,0.000058958227,0.44999886,0.00027351972,0.00037057998,0.0005647391,0.0000028735744,0.00017598267,0.0007155758],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838483,0.000014779666,0.00028649796,0.00049295294,0.0003299551,0.00049100566],"domain_scores_gemma":[0.9981085,0.0010861016,0.000029719391,0.00055663835,0.00011781626,0.00010119823],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024796466,0.00031008304,0.00020761736,0.00032117666,0.0002627008,0.0004981641,0.0006504456,0.0001065934,0.00001748213],"category_scores_gemma":[0.00018227765,0.00027450183,0.00024113167,0.0006763317,0.00002216433,0.00063731,0.000008562674,0.0006413088,0.00005036776],"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":[0.0000025760373,0.00001094269,0.0000023279465,0.00026923127,0.000089701665,0.000008806268,0.0008359654,0.99357617,0.00009763076,0.003206676,0.000092824375,0.0018071622],"study_design_scores_gemma":[0.00016807314,0.00009428107,0.000018891506,0.0010026821,0.000032032658,0.000028801343,0.000036537192,0.9927422,0.0036039688,0.000029546734,0.0018948532,0.00034816482],"about_ca_topic_score_codex":0.0000082167735,"about_ca_topic_score_gemma":0.0000012433494,"teacher_disagreement_score":0.5476832,"about_ca_system_score_codex":0.00031761595,"about_ca_system_score_gemma":0.0001145047,"threshold_uncertainty_score":0.99997073},"labels":[],"label_agreement":null},{"id":"W4404609282","doi":"10.1109/tse.2024.3504286","title":"On Inter-Dataset Code Duplication and Data Leakage in Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","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":"Dalhousie University; McGill University","funders":"","keywords":"Computer science; Programming language; Code (set theory); Software bug; Data mining; Software","score_opus":0.025993329642164737,"score_gpt":0.2756331319817165,"score_spread":0.24963980233955177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404609282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008487405,0.0001805354,0.98947793,0.0001056322,0.00037855707,0.00010633735,0.0007817365,0.00047597045,0.000005905858],"genre_scores_gemma":[0.9559272,0.000028030163,0.043786306,0.00007981462,0.000022536105,0.000022814951,0.00007978183,0.000019229463,0.000034282002],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903804,0.000012684975,0.0001582677,0.0004799076,0.00012457554,0.00018654118],"domain_scores_gemma":[0.99894166,0.00015196571,0.000010342837,0.0008380847,0.0000066125385,0.000051338484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020076368,0.00012418251,0.000100081656,0.00023626574,0.00003663964,0.00012185469,0.00046622232,0.000053710697,0.0000073821866],"category_scores_gemma":[0.000012281307,0.00013019053,0.000018724788,0.00023404474,0.0000054443735,0.0007055975,0.000014047559,0.00029687615,0.000021518583],"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":[0.0000044884873,0.000067636574,0.000003953826,0.0001284681,0.000023019642,0.000057284866,0.0012748191,0.92692304,0.00041002582,0.0040782313,0.0003186795,0.066710375],"study_design_scores_gemma":[0.00012256934,0.000015747086,0.00001334587,0.00014129364,0.000004724828,0.00001076835,0.000012988851,0.99813676,0.0006579716,0.00009312145,0.00066455937,0.00012614208],"about_ca_topic_score_codex":0.000031341104,"about_ca_topic_score_gemma":0.00005287107,"teacher_disagreement_score":0.9474398,"about_ca_system_score_codex":0.000055684024,"about_ca_system_score_gemma":0.000017082222,"threshold_uncertainty_score":0.53090155},"labels":[],"label_agreement":null},{"id":"W4404986931","doi":"10.1109/tse.2025.3631361","title":"Portus: Linking Alloy with SMT-based Finite Model Finding","year":2025,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Aluminum Alloy Microstructure Properties","field":"Engineering","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 British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Alloy; Computer science; Business; Materials science; Metallurgy","score_opus":0.014437106030476488,"score_gpt":0.20637909203541166,"score_spread":0.19194198600493517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404986931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015719038,0.00042161444,0.9767015,0.000015445798,0.002034558,0.0005554991,0.0004406516,0.0040425304,0.0000691879],"genre_scores_gemma":[0.8356336,0.00008357341,0.16301818,0.00007828433,0.00010162636,0.0003249185,0.00006700812,0.00029107256,0.00040176013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974572,0.00001819669,0.00060814305,0.0007485208,0.00044097993,0.00072696846],"domain_scores_gemma":[0.99839705,0.00031315497,0.000085060194,0.0009101022,0.0001215378,0.000173091],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00013921446,0.0010251688,0.0007336681,0.00082468847,0.00017832177,0.00017788271,0.00057108095,0.0007141144,0.000040273968],"category_scores_gemma":[0.000025556326,0.0010618456,0.00031903488,0.00038440258,0.0000526708,0.00017484883,0.00001262858,0.0024687005,0.000014629057],"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":[0.000033909375,0.000024223582,0.000022897872,0.0015747087,0.00035108966,0.000025224303,0.00034987953,0.9944524,0.0010419985,0.0000051212605,0.000033562384,0.0020849875],"study_design_scores_gemma":[0.00044612688,0.000037148355,0.000011524306,0.002583146,0.00022298195,0.00000678901,0.000013974929,0.95993584,0.0353624,0.0000142371155,0.00029283614,0.0010729802],"about_ca_topic_score_codex":0.000017199462,"about_ca_topic_score_gemma":0.000024528288,"teacher_disagreement_score":0.8199145,"about_ca_system_score_codex":0.0005581541,"about_ca_system_score_gemma":0.0002891408,"threshold_uncertainty_score":0.99983263},"labels":[],"label_agreement":null},{"id":"W4405968021","doi":"10.1109/tse.2024.3519464","title":"<i>Look Before You Leap:</i> An Exploratory Study of Uncertainty Analysis for Large Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"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; Japan Science and Technology Agency; Japan Society for the Promotion of Science","keywords":"Computer science; Exploratory analysis; Programming language; Exploratory research; Data science; Software engineering","score_opus":0.016702405548157565,"score_gpt":0.25202852066838805,"score_spread":0.2353261151202305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405968021","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":[0.19860962,0.000035770783,0.8003576,0.000010514366,0.00030081093,0.0002871543,0.000033812208,0.00036072754,0.0000040063615],"genre_scores_gemma":[0.95528823,0.0000017149981,0.04438305,0.000044247456,0.000017218888,0.00014916169,0.0000035553994,0.000015289514,0.000097534394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877656,0.000028302626,0.00031102126,0.00042022017,0.00020378084,0.00026010332],"domain_scores_gemma":[0.99892265,0.00009206712,0.00004571494,0.00077603315,0.00009581858,0.00006771117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025295318,0.000177552,0.00029983057,0.00054137333,0.000111839916,0.00004171937,0.00048670825,0.00007036226,0.0000033989468],"category_scores_gemma":[0.000010039476,0.0001874365,0.00017119209,0.0009297749,0.0000060389243,0.0004528079,0.00000613116,0.00016910463,6.640481e-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":[0.000006990511,0.0002764965,0.00007231625,0.00003888214,0.0002576154,0.000002170189,0.0065932865,0.9876061,0.00009021084,0.00055021764,0.0000031938448,0.0045025246],"study_design_scores_gemma":[0.00057657994,0.00014566872,0.000044016495,0.000025231871,0.00016992456,3.4461513e-7,0.0012359483,0.99629813,0.0012578882,0.000071088856,0.00002535301,0.00014980449],"about_ca_topic_score_codex":0.000052539497,"about_ca_topic_score_gemma":0.0004076682,"teacher_disagreement_score":0.75667864,"about_ca_system_score_codex":0.00007382341,"about_ca_system_score_gemma":0.000049939597,"threshold_uncertainty_score":0.76434386},"labels":[],"label_agreement":null},{"id":"W4406610975","doi":"10.1109/tse.2025.3531210","title":"Mecha: A Neural-Symbolic Open-Set Homogeneous Decision Fusion Approach for Zero-Day Malware Similarity Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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":"Blackberry (Canada); Defence Research and Development Canada; Queen's University","funders":"","keywords":"Computer science; Malware; Similarity (geometry); Zero (linguistics); Set (abstract data type); Artificial intelligence; Homogeneous; Data mining; Artificial neural network; Open set; Machine learning; Algorithm; Pattern recognition (psychology); Programming language; Computer security; Mathematics","score_opus":0.015176685173244877,"score_gpt":0.26193065863628473,"score_spread":0.24675397346303984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406610975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016965759,0.00007571757,0.99238855,0.000036938607,0.0015570335,0.0013952293,0.00005124417,0.0027755345,0.00002315409],"genre_scores_gemma":[0.53798956,0.000027015214,0.4609263,0.00011331599,0.000024200239,0.0007513006,0.000004308455,0.000040379873,0.0001236179],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779326,0.000052805608,0.0004594824,0.0009132021,0.00029783463,0.00048343057],"domain_scores_gemma":[0.9980973,0.00049560866,0.0000949109,0.00096983847,0.00020675229,0.000135606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003947506,0.00041184123,0.00039221015,0.0007093152,0.00056897855,0.00028024244,0.0012007685,0.00028134344,0.0000074325358],"category_scores_gemma":[0.000119930955,0.0004489328,0.00023474291,0.0011387627,0.000022826174,0.00084454956,0.00004213946,0.00051563093,0.0000052802716],"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":[0.00008518337,0.0001564351,0.000003108341,0.00010990933,0.000047865644,0.000006839332,0.0001037132,0.530019,0.008753506,0.00029487823,0.00012755908,0.460292],"study_design_scores_gemma":[0.0007835022,0.00023234116,0.000067569745,0.00011013962,0.000039134495,0.0000521889,0.0000111349955,0.63998604,0.35398164,0.0012722296,0.002922172,0.00054191775],"about_ca_topic_score_codex":0.000025246594,"about_ca_topic_score_gemma":0.000013585897,"teacher_disagreement_score":0.53629297,"about_ca_system_score_codex":0.0003159544,"about_ca_system_score_gemma":0.000060025985,"threshold_uncertainty_score":0.9997963},"labels":[],"label_agreement":null},{"id":"W4406858164","doi":"10.1109/tse.2025.3533972","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","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":"Computer science; Software engineering; Workflow; Programming language; Foundation (evidence); World Wide Web; Database","score_opus":0.04758252356410681,"score_gpt":0.30707135548683356,"score_spread":0.25948883192272676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406858164","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":[0.5921766,0.000014232959,0.4071506,0.000023664805,0.000242476,0.00029223436,0.0000035299302,0.000050749906,0.000045891415],"genre_scores_gemma":[0.99806875,0.0000067116994,0.0012081424,0.000051216542,0.000016441534,0.00018683262,0.0000041674484,0.000019691337,0.0004380319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904567,0.00007285094,0.00032347828,0.00021135858,0.00021023196,0.00013642969],"domain_scores_gemma":[0.99934566,0.00017897676,0.00004107976,0.0003228392,0.00008133853,0.000030085377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033592424,0.00014976862,0.00017795089,0.00031558477,0.00015745223,0.00002133335,0.00012225473,0.00007886003,0.00015485016],"category_scores_gemma":[0.000016324086,0.00013160231,0.00003925494,0.00029242432,0.00003797116,0.00014332242,0.0000014821013,0.00023481897,0.000011153133],"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":[0.00006874269,0.00039984158,0.00012162213,0.000031921867,0.00011489953,2.9058373e-7,0.026969653,0.9606627,0.0004932235,0.0005260315,0.00004346957,0.010567592],"study_design_scores_gemma":[0.0036734187,0.0015270453,0.011063985,0.00047466398,0.00031889937,0.0000018638387,0.02696354,0.94291526,0.012098779,0.0001417798,0.00014347018,0.00067731726],"about_ca_topic_score_codex":0.00001038281,"about_ca_topic_score_gemma":0.00006030173,"teacher_disagreement_score":0.40594244,"about_ca_system_score_codex":0.000039723647,"about_ca_system_score_gemma":0.000044199343,"threshold_uncertainty_score":0.53665864},"labels":[],"label_agreement":null},{"id":"W4406858280","doi":"10.1109/tse.2025.3534027","title":"Recovering Traceability Links Between Code and Documentation: A Retrospective","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Traceability; Documentation; Computer science; Code (set theory); Programming language; Software engineering","score_opus":0.011972415143162336,"score_gpt":0.26600079791641557,"score_spread":0.25402838277325324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406858280","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":[0.12414319,0.00008009912,0.87308073,0.00013966717,0.00067614164,0.00024619687,0.000018624947,0.0015984287,0.000016946673],"genre_scores_gemma":[0.9070561,0.000028845026,0.09253242,0.00003353379,0.00003919476,0.00008899284,0.0000011070458,0.00002380546,0.00019599995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9984229,0.00003038003,0.00028489865,0.00058067933,0.00030947904,0.00037162314],"domain_scores_gemma":[0.9980499,0.0011396701,0.000028833028,0.0005604782,0.000088678324,0.00013245342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034626495,0.00023997156,0.00026446383,0.00041970384,0.00017777964,0.00021356638,0.00040955053,0.0001910032,0.000015969335],"category_scores_gemma":[0.00022714959,0.00027668034,0.00008845617,0.00092782965,0.000033916407,0.0006136669,0.000011484263,0.00086048635,0.000012927602],"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":[0.00006137517,0.00031603366,0.13946271,0.0009751146,0.0008609254,0.00006064908,0.002635325,0.65248305,0.0014898332,0.0021503684,0.0004096848,0.19909489],"study_design_scores_gemma":[0.002590965,0.0004957991,0.7678327,0.00082793104,0.00011890831,0.000040328734,0.000058722788,0.17254981,0.050521772,0.0010853844,0.0021846842,0.0016930016],"about_ca_topic_score_codex":0.000026045856,"about_ca_topic_score_gemma":0.0000055686223,"teacher_disagreement_score":0.7829129,"about_ca_system_score_codex":0.000368203,"about_ca_system_score_gemma":0.00006559329,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W4407098050","doi":"10.1109/tse.2025.3535938","title":"One Sentence Can Kill the Bug: Auto-Replay Mobile App Crashes From One-Sentence Overviews","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection 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":"Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Sentence; Natural language processing; Artificial intelligence; Speech recognition","score_opus":0.012259137582422999,"score_gpt":0.23431890563110322,"score_spread":0.22205976804868022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407098050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053244024,0.00024950673,0.9888349,0.00025954598,0.001429728,0.00053622865,0.000051772473,0.0032860574,0.000027831962],"genre_scores_gemma":[0.7601523,0.00024192114,0.23774876,0.0005638394,0.000062123385,0.0006759172,0.0000028411932,0.000043744218,0.00050854654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980192,0.00005007817,0.00042059258,0.00069124385,0.00039217543,0.0004266929],"domain_scores_gemma":[0.9979245,0.00052113266,0.000093673836,0.0012264684,0.00012687434,0.00010736459],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018200997,0.00032805206,0.00032009103,0.00026790996,0.00032848245,0.00014897354,0.0010623084,0.00013093172,0.000031514177],"category_scores_gemma":[0.00006178235,0.0003211383,0.00018314787,0.0010034472,0.00006331848,0.0004896158,0.00002188965,0.00063200656,0.000030919182],"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":[0.0000374396,0.0005353627,0.00014902475,0.00019291039,0.00034771432,0.000026299494,0.0013913683,0.6268812,0.04000215,0.0008394914,0.00048597986,0.3291111],"study_design_scores_gemma":[0.0008217151,0.00027498702,0.003674914,0.0011877705,0.0001339222,0.000028595776,0.00014935576,0.17936264,0.7884535,0.0019166269,0.022532925,0.0014630577],"about_ca_topic_score_codex":0.00042137658,"about_ca_topic_score_gemma":0.00013813673,"teacher_disagreement_score":0.7548279,"about_ca_system_score_codex":0.00024734891,"about_ca_system_score_gemma":0.00007918656,"threshold_uncertainty_score":0.99992406},"labels":[],"label_agreement":null},{"id":"W4407361541","doi":"10.1109/tse.2025.3540549","title":"Search-Based DNN Testing and Retraining With GAN-Enhanced Simulations","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Parallel Computing and Optimization 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; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; European Space Agency; Science Foundation Ireland; Université du Luxembourg","keywords":"Computer science; Retraining; Artificial intelligence; Machine learning; Distributed computing; Computer architecture; Computer engineering","score_opus":0.01589608177396644,"score_gpt":0.24175184292689342,"score_spread":0.225855761152927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407361541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006136669,0.000017875585,0.9917147,0.00006229807,0.00011233972,0.00012734716,0.000002856227,0.0017230603,0.00010281644],"genre_scores_gemma":[0.5617683,0.0000010336137,0.43812138,0.000054787703,0.0000051064717,0.000008795743,3.5459493e-7,0.0000079748725,0.000032301912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991913,0.000019474532,0.00015224355,0.00029054584,0.00013945729,0.00020699472],"domain_scores_gemma":[0.9988992,0.00064800825,0.00002451603,0.00026598937,0.00010375898,0.000058493646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110081484,0.00014328638,0.00012537524,0.00032268983,0.00023724372,0.00011431944,0.00019410174,0.00005593456,0.000002807885],"category_scores_gemma":[0.000062975414,0.00014552857,0.000025724019,0.0008841905,0.000024927,0.00018408528,0.000002321367,0.00024315827,0.0000010709333],"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":[0.0000032977389,0.000016726659,0.000045522353,0.000024185367,0.000012538947,0.0000017842129,0.00009104101,0.98459375,0.0005247397,0.000056953693,0.000006036983,0.014623422],"study_design_scores_gemma":[0.00023633022,0.00006291848,0.00021288816,0.00022560022,0.000007075709,0.0000023917246,0.0000039217834,0.95110583,0.04795453,0.000019848354,0.000022255494,0.0001463834],"about_ca_topic_score_codex":0.000007601075,"about_ca_topic_score_gemma":0.000001580853,"teacher_disagreement_score":0.55563164,"about_ca_system_score_codex":0.000052185063,"about_ca_system_score_gemma":0.00008544981,"threshold_uncertainty_score":0.5934483},"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":"W4408703448","doi":"10.1109/tse.2025.3553383","title":"Do Experts Agree About Smelly Infrastructure?","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Tracheal and airway disorders","field":"Medicine","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; McGill University","funders":"","keywords":"Computer science; Software engineering; Data science; Engineering management; Engineering","score_opus":0.006346365505415781,"score_gpt":0.23733527887889327,"score_spread":0.2309889133734775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408703448","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":[0.10172908,0.00046436628,0.8954013,0.00016661797,0.0009983052,0.00021491297,0.000013701368,0.0005806663,0.00043105875],"genre_scores_gemma":[0.98941934,0.000095989984,0.00869091,0.00033370176,0.000054301272,0.000049714545,0.0000035627481,0.00003311692,0.0013193521],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99908715,0.0000063332277,0.00021193476,0.00025715903,0.0001694172,0.00026802564],"domain_scores_gemma":[0.9994708,0.000074439056,0.000017845437,0.00027714812,0.000043864573,0.0001159577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000038488237,0.00020968891,0.00023616405,0.00026873694,0.00009142328,0.000023146149,0.00008373864,0.00013238606,0.00021258385],"category_scores_gemma":[0.000021427126,0.00019688936,0.00015526683,0.00036275556,0.000025344274,0.00007453611,9.248537e-7,0.00033133506,0.000023015695],"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":[0.00030510387,0.0005161546,0.0026965244,0.0009083511,0.0005542276,0.00007008236,0.0011327936,0.39725757,0.008089727,0.00032899587,0.004296629,0.5838438],"study_design_scores_gemma":[0.024883585,0.002342373,0.33540437,0.008752333,0.0020409191,0.00048065488,0.0023161203,0.04858698,0.23734616,0.00070873427,0.33203334,0.005104459],"about_ca_topic_score_codex":0.000013297866,"about_ca_topic_score_gemma":0.000004264796,"teacher_disagreement_score":0.88769025,"about_ca_system_score_codex":0.00008696467,"about_ca_system_score_gemma":0.00006519981,"threshold_uncertainty_score":0.80289155},"labels":[],"label_agreement":null},{"id":"W4409771286","doi":"10.1109/tse.2025.3563121","title":"Testing CPS With Design Assumptions-Based Metamorphic Relations and Genetic Programming","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Evolutionary Algorithms and Applications","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":"HORIZON EUROPE European Innovation Council; Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; Science Foundation Ireland","keywords":"Computer science; Genetic programming; Programming language; Software engineering; Artificial intelligence","score_opus":0.01636564723815365,"score_gpt":0.2155209431462641,"score_spread":0.19915529590811046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409771286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018966545,0.00013405457,0.9964948,0.0002426925,0.00010815297,0.00034225214,0.0000039847428,0.0007675651,0.00000980077],"genre_scores_gemma":[0.30198994,0.000002410995,0.69759846,0.000030634077,0.00000893576,0.0002728383,7.3437644e-7,0.000011331631,0.00008473471],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999079,0.000024215722,0.00018931023,0.00034368518,0.00014504488,0.00021873841],"domain_scores_gemma":[0.9990232,0.00043996412,0.000035944824,0.00033477557,0.000091002585,0.00007512296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098976125,0.00016539634,0.00012214112,0.00029494823,0.0004087484,0.0001090316,0.00020059707,0.000058706573,0.0000044544167],"category_scores_gemma":[0.000023284541,0.00016474546,0.00003816111,0.0011307904,0.00003409833,0.00023787862,0.0000026616942,0.0002308408,0.000008372981],"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":[0.0000020740583,0.00007039552,0.00022719459,0.000021804375,0.00003406523,0.0000044078097,0.000026078202,0.9625281,0.00025704005,0.00060800597,0.000017604594,0.03620324],"study_design_scores_gemma":[0.0003284605,0.00008833686,0.012711813,0.0001379702,0.00005842032,0.00003046331,0.0000053744693,0.98446625,0.0012879681,0.00011400862,0.0005320268,0.00023893078],"about_ca_topic_score_codex":0.000010294799,"about_ca_topic_score_gemma":0.0000024384021,"teacher_disagreement_score":0.30009326,"about_ca_system_score_codex":0.000065286586,"about_ca_system_score_gemma":0.00011541034,"threshold_uncertainty_score":0.67181253},"labels":[],"label_agreement":null},{"id":"W4409916786","doi":"10.1109/tse.2025.3565387","title":"Question Selection for Multimodal Code Search Synthesis Using Probabilistic Version Spaces","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Natural Language Processing 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":"National Natural Science Foundation of China","keywords":"Computer science; Selection (genetic algorithm); Probabilistic logic; Modal; Programming language; Code (set theory); Theoretical computer science; Artificial intelligence; Set (abstract data type)","score_opus":0.01307841608488208,"score_gpt":0.2768731439809722,"score_spread":0.2637947278960901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409916786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010362985,0.0000985412,0.9870195,0.000076738004,0.00047975068,0.00035318572,0.000012989127,0.0015945532,0.0000017680089],"genre_scores_gemma":[0.46234113,0.0000029672615,0.5375101,0.000012162483,0.000015083359,0.00006779472,6.2591045e-7,0.00001160928,0.000038555143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903935,0.000031013806,0.00016148783,0.00034924818,0.00017260817,0.0002462903],"domain_scores_gemma":[0.9992193,0.00034394543,0.000029912058,0.00021105031,0.00015086209,0.000044918495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002418502,0.00016392728,0.00014664233,0.00039846092,0.0002451794,0.00013787547,0.00028781773,0.00012123817,0.0000033559495],"category_scores_gemma":[0.00014457473,0.00017193078,0.00007921747,0.0006045286,0.000016641017,0.0004128578,0.0000041503877,0.00023930428,0.0000021931812],"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":[0.00004701831,0.0001320667,0.00003802775,0.00050037605,0.000053295473,0.0000020526677,0.00016332539,0.8952281,0.024963073,0.0017883983,0.000038596027,0.07704568],"study_design_scores_gemma":[0.000112828835,0.000036253372,0.000013655124,0.0002973729,0.000024225832,0.0000070138617,0.000004581032,0.75249106,0.24661073,0.00019935177,0.000058448102,0.00014448415],"about_ca_topic_score_codex":0.000080994105,"about_ca_topic_score_gemma":0.000009890844,"teacher_disagreement_score":0.45197815,"about_ca_system_score_codex":0.00038683572,"about_ca_system_score_gemma":0.00009627091,"threshold_uncertainty_score":0.70111334},"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":"W4411232430","doi":"10.1109/tse.2025.3579574","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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; University of Waterloo","funders":"","keywords":"Computer science; Chunking (psychology); Programming language; Software engineering; Artificial intelligence; Natural language processing","score_opus":0.010397706086851791,"score_gpt":0.2798341540061944,"score_spread":0.26943644791934257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411232430","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":[0.24138345,0.00034991198,0.75642645,0.000010650387,0.00045712295,0.00019114003,0.000003787364,0.0011738033,0.0000036775275],"genre_scores_gemma":[0.96378016,0.00006997816,0.035524942,0.00002491327,0.000021465583,0.000067411456,0.0000035167634,0.000046046698,0.00046153425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982689,0.000034908448,0.00028100962,0.000643924,0.00030075997,0.0004704908],"domain_scores_gemma":[0.99857795,0.0007457249,0.000036597503,0.0004419129,0.000091965674,0.000105839514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003500855,0.00028865744,0.00023742393,0.00062544394,0.00040553854,0.0005758811,0.00034736493,0.00015353585,0.000008348741],"category_scores_gemma":[0.00021321008,0.0003308295,0.000062739484,0.00094939134,0.00007490072,0.0006083957,0.000023264523,0.0006092213,0.0000064262367],"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":[0.000013050704,0.000032638898,0.0071886685,0.00032350712,0.00007073182,0.00002947143,0.0012500186,0.9477327,0.0021440526,0.000112080605,0.000008551792,0.041094564],"study_design_scores_gemma":[0.0005982673,0.00007303674,0.032340128,0.00017852537,0.000014954152,0.000052908003,0.000026708181,0.96124727,0.004644106,0.000018389164,0.0004119896,0.0003936946],"about_ca_topic_score_codex":0.00015770107,"about_ca_topic_score_gemma":0.000009735791,"teacher_disagreement_score":0.72239673,"about_ca_system_score_codex":0.0001621136,"about_ca_system_score_gemma":0.000059510803,"threshold_uncertainty_score":0.99991435},"labels":[],"label_agreement":null},{"id":"W4413822387","doi":"10.1109/tse.2025.3603897","title":"A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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":"Microservices; Computer science; Software engineering; Artificial intelligence; Data science; Machine learning; Programming language; Operating system; Cloud computing","score_opus":0.010631439464268127,"score_gpt":0.22710151134741663,"score_spread":0.2164700718831485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413822387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012986356,0.048490558,0.9472644,0.00007211174,0.0009120314,0.001480969,0.000021911152,0.00045508108,0.000004323615],"genre_scores_gemma":[0.84096813,0.0036945562,0.15186855,0.00032254643,0.000067671404,0.0025244255,0.000011230477,0.00006080098,0.000482065],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983523,0.00007742246,0.0006973588,0.0003923116,0.00021420709,0.0002664381],"domain_scores_gemma":[0.998457,0.00054515747,0.00014019023,0.0005770274,0.0002084181,0.00007221632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007888739,0.00025283475,0.0006074947,0.00033951254,0.0001562628,0.00011379686,0.0005226549,0.00011768047,6.0151876e-7],"category_scores_gemma":[0.00016881332,0.00021147922,0.00022065558,0.0011926227,0.000008270386,0.00026583698,0.0000066809557,0.0002912902,0.000003817308],"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":[0.000007427437,0.000051881478,0.00006766097,0.6477897,0.00013392548,0.0000012010634,0.00093622063,0.34902936,0.00014905138,0.0002181171,0.000024320694,0.0015911057],"study_design_scores_gemma":[0.0002783379,0.00012568502,0.00003619613,0.39360708,0.000094084964,0.000024205674,0.00006491575,0.6011473,0.0040163267,0.000005586439,0.00026664016,0.0003336356],"about_ca_topic_score_codex":0.000016693439,"about_ca_topic_score_gemma":0.0000028552265,"teacher_disagreement_score":0.8396695,"about_ca_system_score_codex":0.00008863559,"about_ca_system_score_gemma":0.00005029083,"threshold_uncertainty_score":0.86238724},"labels":[],"label_agreement":null},{"id":"W4413925951","doi":"10.1109/tse.2025.3605442","title":"Towards Explainable Vulnerability Detection With Large Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","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":"York University","funders":"","keywords":"Computer science; Vulnerability (computing); Data science; Programming language; Software engineering; Natural language processing; Computer security","score_opus":0.00918862300238798,"score_gpt":0.22338367195039308,"score_spread":0.2141950489480051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413925951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027341755,0.000052662326,0.97070503,0.000036365367,0.0005595986,0.00016525228,0.000005032075,0.0010279369,0.00010633615],"genre_scores_gemma":[0.87122977,0.0000033646809,0.1283796,0.000058048594,0.000016749316,0.00008039846,3.7060568e-7,0.000012989137,0.00021869698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989266,0.00002179012,0.0001689926,0.0003840963,0.00019201025,0.00030650818],"domain_scores_gemma":[0.99921465,0.000072277304,0.000020484233,0.000574078,0.000056294513,0.00006220785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019566463,0.0001691687,0.00015273789,0.00022146483,0.00017331757,0.000079007805,0.00030432924,0.00007843224,0.000008435583],"category_scores_gemma":[0.000013203381,0.00016333554,0.0000648363,0.0005149167,0.000008237618,0.00054151757,0.0000044903372,0.00031377852,0.0000050387216],"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":[0.000007946941,0.000051060568,0.00000537201,0.00005439647,0.000024903793,0.0000070643637,0.00049952924,0.95390964,0.00047795713,0.000996291,0.0000029875382,0.043962836],"study_design_scores_gemma":[0.0003540664,0.00004221194,0.00004480776,0.00006404697,0.000011779985,0.000007613873,0.000055550652,0.9463788,0.052514907,0.00017605549,0.00016329021,0.00018683508],"about_ca_topic_score_codex":0.00006781905,"about_ca_topic_score_gemma":0.00003901618,"teacher_disagreement_score":0.84388804,"about_ca_system_score_codex":0.00016395241,"about_ca_system_score_gemma":0.000059918955,"threshold_uncertainty_score":0.666063},"labels":[],"label_agreement":null},{"id":"W4414165847","doi":"10.1109/tse.2025.3603009","title":"Identifying Reusable Services in Legacy Object-Oriented Systems: A Type-Sensitive Identification Approach","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Service-Oriented Architecture and Web Services","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; École de Technologie Supérieure","funders":"Canada Research Chairs","keywords":"Identification (biology); Legacy system; Service (business); sync; Service-oriented architecture; Software; Software maintenance","score_opus":0.00791555203849998,"score_gpt":0.22490668429062846,"score_spread":0.2169911322521285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414165847","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":[0.042130776,0.00023283578,0.9540487,0.000029318828,0.0023349593,0.00035769353,0.0000063428706,0.00068455253,0.00017485277],"genre_scores_gemma":[0.9718215,0.000024304496,0.027640188,0.00012172922,0.00003716719,0.00009837371,0.000010508725,0.000024164925,0.00022205635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982214,0.0000614112,0.0004324089,0.0006133427,0.0002945655,0.00037687295],"domain_scores_gemma":[0.998837,0.00016425709,0.000081308535,0.00068646873,0.00015849392,0.00007246097],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002557007,0.00026586503,0.00026814747,0.0008482187,0.00018250747,0.0003469092,0.00060598936,0.00012742638,0.000002065943],"category_scores_gemma":[0.0000066873754,0.00028528873,0.00008209561,0.0024633622,0.000012070721,0.0009892182,0.000013104941,0.00039707072,0.000031381274],"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":[0.000039971783,0.0002455916,0.00012695788,0.0011954478,0.00015215475,0.00003010448,0.0054507465,0.9789099,0.0046383496,0.0041648448,0.000013968521,0.0050319554],"study_design_scores_gemma":[0.0010574964,0.000068871,0.0025445719,0.0014270877,0.00007415534,0.00005475905,0.0023508193,0.9449434,0.045119677,0.00009569372,0.00151324,0.0007502098],"about_ca_topic_score_codex":0.00043856513,"about_ca_topic_score_gemma":0.00008310063,"teacher_disagreement_score":0.9296907,"about_ca_system_score_codex":0.00015247276,"about_ca_system_score_gemma":0.00006240562,"threshold_uncertainty_score":0.99995995},"labels":[],"label_agreement":null},{"id":"W4414322174","doi":"10.1109/tse.2025.3610540","title":"Diagnosing Unknown Attacks in Smart Homes Using Abductive Reasoning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Network Security and Intrusion Detection","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":"Trinity College","funders":"Science Foundation Ireland","keywords":"Smart card; Key (lock); Abductive reasoning; Data integrity; Home automation","score_opus":0.009391897563815026,"score_gpt":0.23669312742569332,"score_spread":0.22730122986187828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414322174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08794699,0.000199244,0.9089107,0.000043184362,0.0022786807,0.00013549076,0.0000014393485,0.00045506647,0.000029228864],"genre_scores_gemma":[0.90692157,0.0000694607,0.09277268,0.00007525014,0.00004807055,0.000033091714,4.043071e-7,0.000017194443,0.000062262174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988274,0.00003881267,0.00026126453,0.00038581592,0.00016434374,0.0003223367],"domain_scores_gemma":[0.9992839,0.0002526112,0.000038316564,0.0003194612,0.00004822205,0.000057490117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019040765,0.00019174305,0.00020665627,0.0005755111,0.0002110023,0.000117716576,0.00027496103,0.00011706021,0.000011372314],"category_scores_gemma":[0.000040866016,0.0002233295,0.00009184337,0.0013165221,0.000019340918,0.00061932096,0.0000066128546,0.00047163304,0.0000066797675],"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":[0.000010367792,0.00007524019,0.00019794093,0.000040175473,0.00003147949,0.000014939639,0.00040135626,0.95039,0.0005531807,0.0015423888,0.000025473091,0.04671746],"study_design_scores_gemma":[0.00045570225,0.00005569636,0.0009982463,0.0008971065,0.000018348192,0.000022235577,0.000029684501,0.9667364,0.028495334,0.00021651918,0.0016880626,0.00038668644],"about_ca_topic_score_codex":0.000084800384,"about_ca_topic_score_gemma":0.000044284145,"teacher_disagreement_score":0.8189746,"about_ca_system_score_codex":0.000269776,"about_ca_system_score_gemma":0.000055197084,"threshold_uncertainty_score":0.9107112},"labels":[],"label_agreement":null},{"id":"W4414348545","doi":"10.1109/tse.2025.3611329","title":"DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks for Image Analysis","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Image Processing and 3D Reconstruction","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":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland; General Motors Corporation","keywords":"Artificial neural network; Image (mathematics); Pattern recognition (psychology); Test (biology); Image processing; Differential (mechanical device)","score_opus":0.01220046323444045,"score_gpt":0.22245420945146246,"score_spread":0.210253746217022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414348545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003546826,0.000040495863,0.99518234,0.000011434849,0.0006698469,0.000253311,0.000014443771,0.00027725266,0.000004056835],"genre_scores_gemma":[0.5359986,7.0207227e-7,0.46380296,0.000006427059,0.000048502552,0.0001070072,0.000006706163,0.00000799975,0.000021131387],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911404,0.000009598511,0.00026956378,0.0003105018,0.0000864364,0.00020989116],"domain_scores_gemma":[0.9991144,0.00039501453,0.00007134076,0.00021349468,0.0001711072,0.00003466699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009124303,0.0001521667,0.00022764779,0.00038233638,0.00020597717,0.00011812959,0.00019928365,0.000076842996,9.877451e-7],"category_scores_gemma":[0.00007895888,0.0001561041,0.00020187933,0.0009459483,0.00002000056,0.0002483491,0.0000022082745,0.00012351216,6.918125e-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":[0.000005365441,0.00006400288,0.000059228674,0.0001319917,0.00011299983,1.3200612e-7,0.000040392926,0.8732749,0.0039706277,0.000024165967,0.0000042270226,0.12231196],"study_design_scores_gemma":[0.00032656142,0.000048357095,0.000103979306,0.00001624548,0.00022506695,0.0000036317276,0.000005271381,0.9776283,0.021501094,0.000008951327,0.0000021897633,0.0001303681],"about_ca_topic_score_codex":0.000004111302,"about_ca_topic_score_gemma":0.0000023467971,"teacher_disagreement_score":0.53245175,"about_ca_system_score_codex":0.00003620666,"about_ca_system_score_gemma":0.000022191862,"threshold_uncertainty_score":0.6365741},"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":"W4415481257","doi":"10.1109/tse.2025.3624631","title":"Contrasting the Hyperparameter Tuning Impact Across Software Defect Prediction Scenarios","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Toronto Metropolitan University","funders":"","keywords":"Hyperparameter; Software; Hyperparameter optimization; Software quality assurance; Software bug; Scope (computer science); Quality (philosophy)","score_opus":0.015967407007470576,"score_gpt":0.2777652525143255,"score_spread":0.2617978455068549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415481257","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":[0.12911165,0.0012831232,0.8580884,0.00011754834,0.007100849,0.0011756081,0.00029809348,0.0028184108,0.0000063375246],"genre_scores_gemma":[0.96831495,0.00012190401,0.029945273,0.00015663488,0.00027630464,0.00038766765,0.0000073206347,0.00019718574,0.0005927699],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929148,0.00025739832,0.0012512841,0.0017193911,0.0013448923,0.0025122233],"domain_scores_gemma":[0.9873373,0.009110777,0.00019192233,0.002331874,0.0005174103,0.0005107491],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0018356547,0.0012903814,0.00095263077,0.0009614452,0.0018820527,0.001558907,0.0022792104,0.0006678204,0.00009158876],"category_scores_gemma":[0.002861162,0.0011569193,0.0012901877,0.0038215602,0.00025070622,0.001281074,0.00006535887,0.003664474,0.00012803149],"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":[0.000077950266,0.00018887085,0.004432985,0.0003358506,0.0009681905,0.00005157444,0.0014852772,0.89887613,0.00074612617,0.000013263602,0.00020003969,0.092623726],"study_design_scores_gemma":[0.0019951751,0.0005580035,0.024228875,0.0025087965,0.00033555165,0.00021149853,0.0001217263,0.96078366,0.00699668,0.000018779128,0.0008640563,0.0013771788],"about_ca_topic_score_codex":0.000161091,"about_ca_topic_score_gemma":0.000013796362,"teacher_disagreement_score":0.8392033,"about_ca_system_score_codex":0.0015075302,"about_ca_system_score_gemma":0.0006595899,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W4415821354","doi":"10.1109/tse.2025.3627891","title":"Causes and Canonicalization of Unreproducible Builds in Java","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","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":"Artifact (error); Java; Software; Taxonomy (biology); Focus (optics); Identification (biology); Software development; Legacy system","score_opus":0.014029697954729706,"score_gpt":0.2637907972674899,"score_spread":0.2497610993127602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415821354","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":[0.08579025,0.0014939301,0.91001844,0.00013340164,0.0017721995,0.000413955,0.000021326141,0.00034721714,0.000009257074],"genre_scores_gemma":[0.97611994,0.00053054973,0.022737393,0.000028433153,0.00002861127,0.0000713231,0.0000010394373,0.000047687467,0.0004350161],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971238,0.00006835462,0.00074765465,0.0009790657,0.00046189514,0.0006192565],"domain_scores_gemma":[0.99718535,0.0012987775,0.0000703247,0.0010941017,0.00019417412,0.00015725048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006450187,0.00040142183,0.00052758836,0.0016526433,0.000105899104,0.00012225602,0.00057913736,0.00027600408,0.000027117718],"category_scores_gemma":[0.0007767206,0.0004936675,0.00011385417,0.0032323645,0.000097320735,0.00043884627,0.000019440344,0.00074853783,0.000006028215],"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":[0.000027317348,0.00023764778,0.0050667585,0.00090413576,0.000110762434,0.000019949264,0.0005826041,0.96710134,0.0012807233,0.0004215273,0.000056990462,0.024190225],"study_design_scores_gemma":[0.0027063002,0.0005042702,0.070899904,0.004776864,0.00013738291,0.00004154367,0.00006114675,0.7041575,0.21361758,0.0000893011,0.0015687629,0.0014394985],"about_ca_topic_score_codex":0.0003169976,"about_ca_topic_score_gemma":0.000053266,"teacher_disagreement_score":0.8903297,"about_ca_system_score_codex":0.00032022002,"about_ca_system_score_gemma":0.00042778964,"threshold_uncertainty_score":0.9997515},"labels":[],"label_agreement":null},{"id":"W4417439110","doi":"10.1109/tse.2025.3645143","title":"CARE: Context Aware Root Cause Identification Using Distributed Traces and Profiling Metrics","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","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; Brock University; University of Alberta","funders":"","keywords":"Root cause; Observability; Root cause analysis; Profiling (computer programming); Root (linguistics); Identification (biology); Benchmark (surveying)","score_opus":0.01619043411345925,"score_gpt":0.2561327355253319,"score_spread":0.23994230141187264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417439110","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":[0.2103347,0.003152658,0.7797479,0.000044811586,0.00514628,0.00077940297,0.00017302558,0.000619973,0.0000012602978],"genre_scores_gemma":[0.9882842,0.0002167915,0.011179175,0.000025701196,0.00007094684,0.000098566496,0.0000147477795,0.00004669398,0.00006322541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964413,0.00010628355,0.0010936613,0.0011349405,0.00054181146,0.0006820151],"domain_scores_gemma":[0.9973978,0.0005653185,0.00022384316,0.0010304408,0.00055753265,0.000225086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054025854,0.00062044256,0.0006405548,0.0009550994,0.0008738081,0.0005961728,0.0005882094,0.0004507956,0.000007911851],"category_scores_gemma":[0.00016697406,0.0006728652,0.00025607186,0.0030058355,0.000114388065,0.0011239038,0.00001592427,0.00082394667,0.0000123273885],"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":[0.00006555527,0.00030261884,0.008498264,0.0040525054,0.0005562584,0.000026204756,0.0027702958,0.81286937,0.001064893,0.00014209325,0.000027349693,0.1696246],"study_design_scores_gemma":[0.0011262125,0.00013331379,0.004353305,0.0014738626,0.0004621345,0.000043451044,0.00072775845,0.9177999,0.072555736,0.000012310363,0.00035035913,0.000961651],"about_ca_topic_score_codex":0.00012892234,"about_ca_topic_score_gemma":0.000029401137,"teacher_disagreement_score":0.77794945,"about_ca_system_score_codex":0.00078480004,"about_ca_system_score_gemma":0.00038116254,"threshold_uncertainty_score":0.9995723},"labels":[],"label_agreement":null}]}