{"meta":{"query_hash":"7de042e048ae","filters":{"venue":"ACM Transactions on Software Engineering and Methodology"},"cohort_total":200,"direct_labels_cover":1,"predictions_cover":200,"exported":200,"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/7de042e048ae","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Software+Engineering+and+Methodology"},"results":[{"id":"W1794343297","doi":"10.1145/2699697","title":"aToucan","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":98,"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; Sequence diagram; Use Case Diagram; Class diagram; Traceability; Programming language; Unified Modeling Language; Software engineering; Completeness (order theory); Activity diagram; Class (philosophy); Requirements traceability; Consistency (knowledge bases); Requirements analysis; Artificial intelligence; Software; Requirement","score_opus":0.14914112278278302,"score_gpt":0.34295324255414494,"score_spread":0.19381211977136192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794343297","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01757313,0.00026733463,0.97969663,0.0003223206,0.00093768217,0.00008720261,0.0000026958587,0.0011050048,0.000008001969],"genre_scores_gemma":[0.10855353,0.000029640933,0.89103264,0.00009416519,0.000046752128,0.0000428321,8.9616367e-7,0.000024782512,0.00017477758],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987276,0.00012944838,0.00016187594,0.00039015274,0.00021551664,0.00037536418],"domain_scores_gemma":[0.9951756,0.003618206,0.000019100424,0.00078750204,0.00007906857,0.0003205523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009577145,0.00017759504,0.00022609693,0.00032103187,0.00006378993,0.00005003136,0.00063354755,0.00012779894,0.0000072264133],"category_scores_gemma":[0.0048146453,0.0001793031,0.00005221034,0.0004346499,0.000034987566,0.0001879805,0.000038235863,0.00038599322,0.00003029661],"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":[0.00007209157,0.0001961101,0.0032105667,0.00015952591,0.0002827427,0.00016203414,0.0040406715,0.22794583,0.0011023089,0.010576921,0.0010623161,0.7511889],"study_design_scores_gemma":[0.01802953,0.008469487,0.09919793,0.0007293546,0.00036783126,0.0074378797,0.0009870464,0.27519965,0.11441547,0.04034393,0.42462105,0.01020084],"about_ca_topic_score_codex":0.000027860175,"about_ca_topic_score_gemma":0.000001558034,"teacher_disagreement_score":0.740988,"about_ca_system_score_codex":0.000063109845,"about_ca_system_score_gemma":0.000073005154,"threshold_uncertainty_score":0.7311768},"labels":[],"label_agreement":null},{"id":"W1975286358","doi":"10.1145/1101815.1101819","title":"Reasoning about static and dynamic properties in alloy","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Formal Methods in Verification","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":"McMaster University","funders":"","keywords":"Iterated function; Computer science; Relational calculus; Formalism (music); Programming language; Calculus (dental); Theoretical computer science; Relational model; Mathematics; Relational database; Data mining","score_opus":0.06189680358928729,"score_gpt":0.3087775904416149,"score_spread":0.24688078685232762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975286358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114943646,0.00047009083,0.8839255,0.00020159144,0.00017050326,0.00008939804,0.0000010572152,0.0001954977,0.0000027149965],"genre_scores_gemma":[0.19050282,0.0002261357,0.80909735,0.000074328855,0.000007855736,0.000037673577,3.469855e-7,0.000010190896,0.00004329387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990553,0.00019657034,0.00018845318,0.00027768651,0.00007163907,0.0002103414],"domain_scores_gemma":[0.998982,0.0005756488,0.000030479729,0.00033376372,0.00002019169,0.000057876874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085400953,0.00012426007,0.00017763316,0.0002167612,0.00006554758,0.00003161424,0.00021815354,0.000084954765,0.00000232459],"category_scores_gemma":[0.000868871,0.000119878365,0.000019771182,0.00018544424,0.000039998773,0.00028853506,0.000015011268,0.0002454771,0.0000020481966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018938616,0.000041471383,0.00018815849,0.000093347364,0.000022848619,0.000003417425,0.002868249,0.09690782,0.0030457592,0.002933692,0.0000013601463,0.89387494],"study_design_scores_gemma":[0.00065177574,0.00021677054,0.023635097,0.00019183509,0.000021831029,0.00020188779,0.00010435876,0.9646369,0.0075510484,0.0007039562,0.0016468979,0.00043764492],"about_ca_topic_score_codex":0.000018304467,"about_ca_topic_score_gemma":0.000013104776,"teacher_disagreement_score":0.89343727,"about_ca_system_score_codex":0.000042731735,"about_ca_system_score_gemma":0.000017384233,"threshold_uncertainty_score":0.4888498},"labels":[],"label_agreement":null},{"id":"W1975318342","doi":"10.1145/2512207","title":"Degree-of-knowledge","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Codebase; Computer science; Robustness (evolution); Source code; Code (set theory); Code review; Point (geometry); Software; Software engineering; Software development; Static program analysis; Programming language; Set (abstract data type)","score_opus":0.11510190202852359,"score_gpt":0.3348329567299539,"score_spread":0.21973105470143028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975318342","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015254211,0.00023787892,0.983115,0.00008081983,0.0006546801,0.00007407014,0.0000020853881,0.00056420884,0.000017016962],"genre_scores_gemma":[0.27233833,0.00003165136,0.72745544,0.000019953948,0.000030437448,0.000022770882,4.752094e-7,0.00001806733,0.00008286363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988275,0.00018129237,0.00020562639,0.0003455619,0.00013151909,0.00030849312],"domain_scores_gemma":[0.989415,0.009555695,0.000028945366,0.00079421524,0.0000718728,0.00013429327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047037,0.0001669611,0.00028722346,0.00037228974,0.000063322754,0.000018386952,0.0006461279,0.00012940897,0.000009000579],"category_scores_gemma":[0.0048399107,0.00016678519,0.00007256032,0.00041388656,0.00004788109,0.00011377225,0.00003625113,0.00032480006,0.000013522068],"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":[0.000014698001,0.00009069338,0.0009826873,0.00021477639,0.000091790476,0.0000043931527,0.0008801841,0.027346231,0.0022902281,0.008353723,0.00005008373,0.9596805],"study_design_scores_gemma":[0.007076567,0.0050859284,0.22511323,0.00092061196,0.00027238706,0.0012089759,0.000113032314,0.35549515,0.27602407,0.016034955,0.10797893,0.00467615],"about_ca_topic_score_codex":0.000012012023,"about_ca_topic_score_gemma":0.0000015180952,"teacher_disagreement_score":0.95500433,"about_ca_system_score_codex":0.000022857363,"about_ca_system_score_gemma":0.000030070261,"threshold_uncertainty_score":0.68013024},"labels":[],"label_agreement":null},{"id":"W1977244105","doi":"10.1145/2559936","title":"Automated cookie collection testing","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; The King's University","funders":"","keywords":"Computer science; Web testing; Web application; Web application security; Security testing; Software engineering; World Wide Web; Web development; Web service; Operating system; Cloud computing","score_opus":0.08726401518129814,"score_gpt":0.3104312761742673,"score_spread":0.22316726099296916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977244105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032180666,0.000039363247,0.96353626,0.0001346348,0.00047656594,0.000082188715,0.0000010441934,0.032491084,0.000020795596],"genre_scores_gemma":[0.12897411,0.0000073377278,0.87072116,0.00016530689,0.00002708987,0.000039106024,7.9257796e-7,0.000019371568,0.00004571965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882925,0.00021147444,0.00019650115,0.0003805169,0.00010641842,0.0002758533],"domain_scores_gemma":[0.9926466,0.006567273,0.00005056926,0.00055574474,0.00008058334,0.00009926839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093887,0.00017938492,0.0002343313,0.00028702785,0.00021923501,0.000053322176,0.0003483219,0.00014092047,0.0000023808047],"category_scores_gemma":[0.007006174,0.00018272556,0.00004294939,0.00056949316,0.000032636697,0.00012055883,0.000020777257,0.00026991038,0.0000059900353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017827088,0.00009209381,0.0011728947,0.00010410665,0.00007010684,0.000011422791,0.0005794611,0.04225078,0.0015626374,0.0017776402,0.0010827788,0.95127827],"study_design_scores_gemma":[0.0004611598,0.0006046862,0.0045005823,0.000120728524,0.000033063498,0.0004295753,0.0000035808412,0.9754988,0.0052933423,0.010813221,0.0017483121,0.00049293786],"about_ca_topic_score_codex":0.000059782084,"about_ca_topic_score_gemma":0.0000011887824,"teacher_disagreement_score":0.95078534,"about_ca_system_score_codex":0.000033967706,"about_ca_system_score_gemma":0.000027004719,"threshold_uncertainty_score":0.8387551},"labels":[],"label_agreement":null},{"id":"W1982335236","doi":"10.1145/2594458","title":"Peer Review on Open-Source Software Projects","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":108,"is_retracted":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; Concordia University","funders":"","keywords":"Computer science; Software technical review; Technical peer review; Peer review; Quality assurance; Software peer review; Quality (philosophy); Empirical research; Software; Software quality assurance; Data science; Knowledge management; Software development; Software quality; Operations management; Engineering; Software construction; Political science","score_opus":0.1125589028151714,"score_gpt":0.34279438878182694,"score_spread":0.23023548596665555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982335236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061770465,0.000341313,0.99122226,0.00532851,0.00072964723,0.00053023885,0.000010085006,0.0011574778,0.00006274111],"genre_scores_gemma":[0.0043252883,0.0001651745,0.9883507,0.004260169,0.000065552376,0.00023021868,0.000010069952,0.000060031743,0.0025328083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99744064,0.00045925728,0.00041586865,0.0007841908,0.00043793503,0.00046209115],"domain_scores_gemma":[0.99326056,0.0044292645,0.00011420793,0.001640143,0.00037918115,0.00017662437],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031228014,0.00035062546,0.0005592023,0.0003333963,0.00037049354,0.00023210688,0.0017479806,0.00019164608,0.00003637115],"category_scores_gemma":[0.013074527,0.00033399463,0.00010290643,0.00092617853,0.000069288406,0.00039397817,0.00012881139,0.00066615286,0.00007141641],"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":[0.000023249464,0.00017887048,0.00012798968,0.0005137964,0.00011933381,0.000009008952,0.0009951096,0.015071896,0.00007933251,0.006867078,0.004165873,0.9718485],"study_design_scores_gemma":[0.001533853,0.0012243876,0.0017259226,0.0018985054,0.00013509957,0.00038725056,0.0000471508,0.0034579975,0.0024143108,0.0029104832,0.98280317,0.001461867],"about_ca_topic_score_codex":0.000038042912,"about_ca_topic_score_gemma":0.000004205609,"teacher_disagreement_score":0.9786373,"about_ca_system_score_codex":0.000057490044,"about_ca_system_score_gemma":0.0000859832,"threshold_uncertainty_score":0.9999112},"labels":[],"label_agreement":null},{"id":"W1987035533","doi":"10.1145/1391984.1391987","title":"Evaluating the benefits of context-sensitive points-to analysis using a BDD-based implementation","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":117,"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; University of Waterloo","funders":"","keywords":"Computer science; Heap (data structure); Pointer analysis; Call graph; Java; Pointer (user interface); Programming language; Paddle; Theoretical computer science; Static analysis; Artificial intelligence; Operating system","score_opus":0.22449726015584578,"score_gpt":0.4221343935073883,"score_spread":0.1976371333515425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987035533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3993142,0.0000670711,0.6001261,0.00012444517,0.00010759796,0.00013535323,0.000010033791,0.00011508352,1.0897092e-7],"genre_scores_gemma":[0.4830359,0.0000061407027,0.5168356,0.000074068135,0.000010299408,0.000023056302,0.0000014174424,0.000010228175,0.0000033005613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839276,0.0003210422,0.00028984103,0.00037413993,0.0003172285,0.00030497965],"domain_scores_gemma":[0.99092984,0.008068722,0.00006248789,0.000631003,0.0002047859,0.00010315907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015195262,0.00017104122,0.00033081905,0.00067687023,0.00019769058,0.000018899122,0.0003939428,0.00007353321,0.00000908793],"category_scores_gemma":[0.002652121,0.0001506709,0.00012838382,0.0014712373,0.000048953178,0.00010340934,0.000028703882,0.00023813982,0.0000017415606],"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":[0.000021450764,0.000018136785,0.0012804655,0.000017994571,0.00023591731,0.0000032221833,0.0016182236,0.91412735,0.0018425988,0.0001131473,0.0000016105457,0.0807199],"study_design_scores_gemma":[0.0012802416,0.0010355111,0.13420749,0.00008172186,0.0004781764,0.00014496583,0.00033005173,0.78966486,0.07207731,0.0000742774,0.000053279648,0.00057212403],"about_ca_topic_score_codex":0.00017402433,"about_ca_topic_score_gemma":0.000015063323,"teacher_disagreement_score":0.13292702,"about_ca_system_score_codex":0.00006521204,"about_ca_system_score_gemma":0.00009371436,"threshold_uncertainty_score":0.6144181},"labels":[],"label_agreement":null},{"id":"W1988506401","doi":"10.1145/2089116.2089119","title":"Weak Alphabet Merging of Partial Behavior Models","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Viewpoints; Alphabet; Property (philosophy); Process (computing); Algebraic properties; Theoretical computer science; Component (thermodynamics); Extension (predicate logic); Programming language; Mathematics","score_opus":0.13249928710046624,"score_gpt":0.34050713105717073,"score_spread":0.2080078439567045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988506401","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024760446,0.00026800984,0.9735612,0.000030854197,0.0010375748,0.00009743513,0.000004413595,0.00022944277,0.000010604074],"genre_scores_gemma":[0.22798811,0.000042563348,0.7718361,0.000018353614,0.000030162448,0.000054175543,6.986601e-7,0.000011355746,0.000018494686],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989317,0.0002129405,0.00023868283,0.0002070722,0.00011617733,0.00029343794],"domain_scores_gemma":[0.99843836,0.00080910773,0.000060121583,0.0005456544,0.000037881906,0.00010890504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011487175,0.00013285011,0.00022437768,0.00018434251,0.00006783736,0.000010400945,0.0003417429,0.000116862015,0.000007747939],"category_scores_gemma":[0.00041157007,0.00013553233,0.00006210263,0.00022438605,0.000038987033,0.00047979385,0.000019404248,0.00020641158,0.0000025352397],"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":[0.00003586503,0.0002847261,0.0007311983,0.0001257985,0.00010865476,0.0000018294604,0.0035857144,0.11871398,0.013703732,0.084369555,0.000012712176,0.7783262],"study_design_scores_gemma":[0.0017420084,0.00082326005,0.01957758,0.00015259326,0.00042471648,0.00046317608,0.0002984176,0.40950242,0.5531728,0.004545156,0.0076907193,0.0016071213],"about_ca_topic_score_codex":0.000013572487,"about_ca_topic_score_gemma":2.201751e-7,"teacher_disagreement_score":0.7767191,"about_ca_system_score_codex":0.00002035786,"about_ca_system_score_gemma":0.00001442432,"threshold_uncertainty_score":0.55268484},"labels":[],"label_agreement":null},{"id":"W2004901564","doi":"10.1145/1243987.1243989","title":"Metamodel-based model conformance and multiview consistency checking","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Model-Driven Software Engineering Techniques","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":"York University","funders":"Engineering and Physical Sciences Research Council; European Commission","keywords":"Metamodeling; Computer science; Sequence diagram; Unified Modeling Language; Conformance checking; Consistency (knowledge bases); Model checking; Programming language; Software engineering; Completeness (order theory); Applications of UML; Consistency model; Automation; Artificial intelligence; Work in process","score_opus":0.09095907436759029,"score_gpt":0.31688830244321353,"score_spread":0.22592922807562324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004901564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004352822,0.000655755,0.992981,0.00010076156,0.00023906874,0.00019393713,0.000006443269,0.0014640026,0.0000062136482],"genre_scores_gemma":[0.13174772,0.00014191348,0.8678059,0.00019698906,0.000012957445,0.00004132759,0.00000141556,0.00002913685,0.0000226324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985057,0.000054038104,0.00034828685,0.00049958314,0.00015755236,0.0004347986],"domain_scores_gemma":[0.9976428,0.0013100995,0.00006451225,0.000717151,0.00008151343,0.00018388033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014488167,0.00030113864,0.00041290926,0.0003874125,0.00014207729,0.00004150042,0.00041654607,0.0002056789,0.0000019881904],"category_scores_gemma":[0.00017974766,0.0003092532,0.000084173844,0.00027698805,0.00007969484,0.0002722557,0.00003418386,0.00042102335,0.000001372054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022688011,0.000050427487,0.00008440055,0.0002093739,0.00007271407,0.000016753687,0.00059000595,0.4659212,0.0013990442,0.028843747,0.000006154942,0.5027835],"study_design_scores_gemma":[0.0004795662,0.00012150236,0.00049740577,0.000111964924,0.0000439451,0.0000916887,0.0000043780115,0.98301667,0.011368725,0.0008819506,0.0029169463,0.00046525282],"about_ca_topic_score_codex":0.000014096247,"about_ca_topic_score_gemma":0.0000055080704,"teacher_disagreement_score":0.51709545,"about_ca_system_score_codex":0.00004513153,"about_ca_system_score_gemma":0.00004813277,"threshold_uncertainty_score":0.999936},"labels":[],"label_agreement":null},{"id":"W2014744822","doi":"10.1145/2491509.2491521","title":"Use case and task models","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Software Engineering Methodologies","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software engineering; Task (project management); Software development; Set (abstract data type); Software; Human–computer interaction; Systems engineering; Programming language","score_opus":0.1401807566114291,"score_gpt":0.3052749112876002,"score_spread":0.1650941546761711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014744822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02923549,0.00038353878,0.96831566,0.00017114739,0.0004979672,0.00018740699,0.0000060782113,0.001201422,0.000001265051],"genre_scores_gemma":[0.059860136,0.0002120597,0.93954796,0.00013507,0.000020641604,0.000102677266,7.019306e-7,0.000031291318,0.00008946276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985142,0.00023020683,0.00023298286,0.0005319511,0.00009764613,0.0003930119],"domain_scores_gemma":[0.99118596,0.007764086,0.000039101742,0.00075411116,0.00006695341,0.0001897731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005322807,0.00027568018,0.00034276364,0.00027850532,0.00014689745,0.0001064059,0.00031216748,0.00018219225,0.000005674011],"category_scores_gemma":[0.0023178922,0.00026836677,0.000054490476,0.0002553451,0.00006986339,0.0010065157,0.00005493788,0.0004073897,0.000005612636],"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":[0.000006497039,0.000025577641,0.000025093881,0.000064982574,0.00007425682,0.00018309422,0.00097491156,0.63665247,0.0012840144,0.0035714963,0.000025376965,0.35711223],"study_design_scores_gemma":[0.0029392664,0.0015449746,0.004365687,0.0002863283,0.00027071068,0.04004274,0.00053025194,0.71074206,0.015623093,0.21410258,0.0049833716,0.0045689624],"about_ca_topic_score_codex":0.00010499352,"about_ca_topic_score_gemma":0.000002670962,"teacher_disagreement_score":0.35254326,"about_ca_system_score_codex":0.000027961085,"about_ca_system_score_gemma":0.000015129449,"threshold_uncertainty_score":0.9999769},"labels":[],"label_agreement":null},{"id":"W2018414565","doi":"10.1145/2491509.2491515","title":"The value of design rationale information","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"University of British Columbia","funders":"Norges Forskningsråd","keywords":"Documentation; Computer science; Personalization; Context (archaeology); Value (mathematics); World Wide Web; Programming language","score_opus":0.07125196779048361,"score_gpt":0.29658960558982694,"score_spread":0.22533763779934335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018414565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045601786,0.00012328212,0.9940778,0.00041396962,0.00035573269,0.0002284277,0.0000015009697,0.00023680067,0.000002285367],"genre_scores_gemma":[0.06741459,0.00007782272,0.93225527,0.000047268986,0.000012633054,0.00013653039,8.090871e-7,0.000007788408,0.000047320027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913186,0.00015013525,0.00021132489,0.00012940462,0.00016849271,0.00020876793],"domain_scores_gemma":[0.9869081,0.012387773,0.000036689045,0.0004832385,0.00011803239,0.000066164896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089829287,0.00010300093,0.00012764703,0.00017305507,0.00012557085,0.000062730316,0.00047953494,0.000075031174,0.00000834172],"category_scores_gemma":[0.00422465,0.00008118398,0.000039465285,0.00028070682,0.0000415584,0.0004511535,0.000019989575,0.00020824262,0.000019729874],"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":[0.000014159905,0.000026609974,0.00015626539,0.00007086341,0.00009386898,7.9785207e-7,0.0010650837,0.5157558,0.0011845237,0.014241911,0.00025420715,0.46713594],"study_design_scores_gemma":[0.0025058212,0.0015361615,0.109912984,0.00018689901,0.00007465389,0.00033893491,0.00029584844,0.7256217,0.10423576,0.02557977,0.028211953,0.001499524],"about_ca_topic_score_codex":0.00002456709,"about_ca_topic_score_gemma":2.6516577e-7,"teacher_disagreement_score":0.46563643,"about_ca_system_score_codex":0.000022724946,"about_ca_system_score_gemma":0.000042441006,"threshold_uncertainty_score":0.5057606},"labels":[],"label_agreement":null},{"id":"W2021538299","doi":"10.1145/2377656.2377657","title":"Systematizing pragmatic software reuse","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Calgary; University of Waterloo","funders":"","keywords":"Computer science; Reuse; Variety (cybernetics); Software engineering; Task (project management); Plan (archaeology); Software development; Process (computing); Source code; Software; Metaphor; Human–computer interaction; Systems engineering; Programming language; Artificial intelligence; Engineering","score_opus":0.08412914294878511,"score_gpt":0.3257056353884473,"score_spread":0.24157649243966223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021538299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019585662,0.0010293637,0.9757826,0.0001756248,0.0014003664,0.0002494389,0.0000061601368,0.0017678877,0.0000029025405],"genre_scores_gemma":[0.14511847,0.0000515744,0.85440016,0.000070281305,0.000087779896,0.00013535061,0.0000018908445,0.00004796666,0.00008655257],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977739,0.0003312081,0.00036200212,0.00043632276,0.00031561876,0.00078096136],"domain_scores_gemma":[0.9857937,0.011961641,0.00006141305,0.0017551903,0.00007752276,0.00035051737],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021173998,0.00031071962,0.00044246708,0.0005004659,0.00018075206,0.00008124815,0.0011474115,0.00021416406,0.000017786886],"category_scores_gemma":[0.017358782,0.0003039832,0.00010525766,0.0005900145,0.000039172483,0.00056111487,0.00010228948,0.0005839415,0.000055621378],"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":[0.00012083907,0.0011954897,0.030009706,0.0099565135,0.0019105923,0.00021104152,0.029920792,0.2036221,0.008564903,0.020746654,0.0016402383,0.6921011],"study_design_scores_gemma":[0.02277628,0.0074614235,0.36186954,0.013539341,0.0023819972,0.029261917,0.0028997213,0.20022428,0.157251,0.020795098,0.15355273,0.027986677],"about_ca_topic_score_codex":0.000015594664,"about_ca_topic_score_gemma":6.2418803e-7,"teacher_disagreement_score":0.6641145,"about_ca_system_score_codex":0.000101970174,"about_ca_system_score_gemma":0.000039891205,"threshold_uncertainty_score":0.99994123},"labels":[],"label_agreement":null},{"id":"W2034102118","doi":"10.1145/990010.990011","title":"Multi-valued symbolic model-checking","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":188,"is_retracted":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":"Model checking; Computer science; CTL*; Computation tree logic; Theoretical computer science; Generalization; Kripke structure; Symbolic trajectory evaluation; Abstraction model checking; Class (philosophy); Temporal logic; Extension (predicate logic); Algorithm; Programming language; Artificial intelligence; Mathematics","score_opus":0.153068929282084,"score_gpt":0.34476235356119034,"score_spread":0.19169342427910635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034102118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048210174,0.0001561692,0.9936835,0.000029477063,0.0006603024,0.000110036424,0.0000019919457,0.0005229053,0.00001459115],"genre_scores_gemma":[0.02937076,0.000073148105,0.9702734,0.00011527309,0.000010683296,0.00005001451,5.15514e-7,0.00002132489,0.000084918924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986447,0.00033299153,0.00021910202,0.0003929144,0.00011053112,0.0002997348],"domain_scores_gemma":[0.9985283,0.00054663635,0.000044624794,0.00072828034,0.000045830988,0.000106308486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001316452,0.00017905785,0.00022980876,0.00022836402,0.00014009586,0.000034452736,0.00039472387,0.00015457101,0.0000049894775],"category_scores_gemma":[0.0019502031,0.00018508562,0.00006556287,0.00030278464,0.000034172022,0.00022635677,0.000012073854,0.0003251522,0.0000067627884],"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":[0.00001356667,0.00011614282,0.00006414621,0.00008457895,0.00008624662,0.000006141932,0.002275815,0.70824534,0.008840775,0.14364566,0.000007039942,0.13661455],"study_design_scores_gemma":[0.00048407287,0.0000849484,0.00050413556,0.00002652259,0.000027458058,0.00012461927,0.000028265094,0.9607433,0.034095403,0.0027027528,0.0008280523,0.00035047822],"about_ca_topic_score_codex":0.0000056705658,"about_ca_topic_score_gemma":6.7269906e-7,"teacher_disagreement_score":0.25249794,"about_ca_system_score_codex":0.000038376515,"about_ca_system_score_gemma":0.000034364508,"threshold_uncertainty_score":0.7547572},"labels":[],"label_agreement":null},{"id":"W2039822794","doi":"10.1145/1767751.1767754","title":"Clone region descriptors","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":70,"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":"clone (Java method); Computer science; Cloning (programming); Source code; Software maintenance; Software; Code refactoring; Code (set theory); Software system; Programming language; Biology; Genetics; Gene","score_opus":0.08537287773891615,"score_gpt":0.3123188283960462,"score_spread":0.22694595065713002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039822794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09008585,0.00008325452,0.9062918,0.0003131572,0.001998522,0.00010185429,0.0000015998036,0.0011205783,0.0000034257378],"genre_scores_gemma":[0.24034974,0.000042646938,0.7592668,0.000067829074,0.00006449406,0.00004384235,7.692102e-7,0.000027008353,0.00013690672],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986498,0.00009517692,0.00018760092,0.0004689509,0.00017776064,0.0004207545],"domain_scores_gemma":[0.99440736,0.0042938455,0.000025908708,0.0009967608,0.000064236694,0.0002118986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007005509,0.0002083949,0.0002389386,0.0003960692,0.0001284492,0.000060492515,0.0007108529,0.0002194748,0.000013875932],"category_scores_gemma":[0.0042546247,0.00021150502,0.000073851195,0.00044239318,0.00005826716,0.00022290976,0.000035091838,0.00090897916,0.000017162303],"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":[0.00005890441,0.00021942619,0.0046172696,0.00020724976,0.00023242368,0.0001869228,0.001882942,0.025641097,0.041029852,0.014234884,0.00046538393,0.91122365],"study_design_scores_gemma":[0.009528761,0.004255283,0.25814125,0.00055749435,0.00035471868,0.012315039,0.00025781398,0.11879338,0.35106912,0.020438995,0.2154189,0.008869229],"about_ca_topic_score_codex":0.00002688422,"about_ca_topic_score_gemma":0.0000038387548,"teacher_disagreement_score":0.9023544,"about_ca_system_score_codex":0.000026473252,"about_ca_system_score_gemma":0.000038418442,"threshold_uncertainty_score":0.86249244},"labels":[],"label_agreement":null},{"id":"W2052401040","doi":"10.1145/2685613","title":"Conditional Commitments","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Multi-Agent Systems and Negotiation","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":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Model checking; Computation tree logic; Scalability; Theoretical computer science; Software engineering; Programming language","score_opus":0.08299718159182957,"score_gpt":0.3041286519701256,"score_spread":0.22113147037829606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052401040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007371547,0.000033406734,0.99127996,0.00018441745,0.0008063282,0.00006861667,0.0000038635153,0.00024288247,0.000008951062],"genre_scores_gemma":[0.31034502,0.000011191694,0.6893076,0.00017461927,0.000044188804,0.00002504662,0.0000040493474,0.0000070438246,0.00008129317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992473,0.00016416928,0.00013510452,0.00021889883,0.00008982249,0.00014467351],"domain_scores_gemma":[0.9983637,0.0011846751,0.00003085721,0.00032672143,0.000024429546,0.000069632944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046757987,0.0000997462,0.00014448332,0.000118510325,0.00010173754,0.00002259106,0.00020770282,0.00007506758,0.000014501369],"category_scores_gemma":[0.00029191552,0.00009675774,0.000039329123,0.00009415729,0.000014177394,0.00011678417,0.000008368253,0.00012273887,0.000017750208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003669617,0.00032648013,0.0017820789,0.0002517721,0.00035949488,0.000011686195,0.003504909,0.18792439,0.0060918992,0.10316413,0.0007386647,0.6958078],"study_design_scores_gemma":[0.0073090536,0.0017895582,0.18726654,0.0002806629,0.00018347944,0.0007133687,0.00014206127,0.5350417,0.03376409,0.025962958,0.2049708,0.0025757328],"about_ca_topic_score_codex":0.0000120426475,"about_ca_topic_score_gemma":0.0000014512456,"teacher_disagreement_score":0.69323206,"about_ca_system_score_codex":0.000016008475,"about_ca_system_score_gemma":0.000007257663,"threshold_uncertainty_score":0.39456663},"labels":[],"label_agreement":null},{"id":"W2055098550","doi":"10.1145/2430536.2430538","title":"Views","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Division of Computing and Communication Foundations","keywords":"Computer science; Concurrency; Programming language; Compiler; Debugging; Distributed computing","score_opus":0.08723794299725363,"score_gpt":0.3124842067430095,"score_spread":0.22524626374575585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055098550","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013670071,0.00014754264,0.99666834,0.00035777807,0.00027522558,0.00009906063,5.343601e-7,0.0010561221,0.000028387287],"genre_scores_gemma":[0.017838197,0.000088173576,0.9814885,0.00029204928,0.000016875389,0.000053161166,5.321209e-7,0.000009642838,0.00021285417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992627,0.000108375025,0.00014351886,0.00024392486,0.00006032991,0.00018118379],"domain_scores_gemma":[0.998614,0.0008027624,0.000025835092,0.00043944866,0.000040420688,0.00007751895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030110378,0.00011484713,0.00015956175,0.00015466817,0.000084974046,0.00004608794,0.00035155605,0.00008386768,0.000023038532],"category_scores_gemma":[0.0002986062,0.0001074523,0.00004232034,0.00018832409,0.000017709117,0.0001563485,0.000016500406,0.00017487495,0.000027232601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030667313,0.000053413216,0.000065255655,0.000035419074,0.000045944616,0.000003448207,0.00062238413,0.11154244,0.0007720319,0.0044894563,0.00075610686,0.88161105],"study_design_scores_gemma":[0.0015811287,0.001098037,0.008995376,0.00018918845,0.00006552847,0.00055458804,0.000064496984,0.83609986,0.041504424,0.030566052,0.07713283,0.0021484667],"about_ca_topic_score_codex":0.000020049947,"about_ca_topic_score_gemma":4.1079485e-7,"teacher_disagreement_score":0.87946254,"about_ca_system_score_codex":0.000011485405,"about_ca_system_score_gemma":0.000010526854,"threshold_uncertainty_score":0.43817776},"labels":[],"label_agreement":null},{"id":"W2056488032","doi":"10.1145/1391984.1391985","title":"Unit-level test adequacy criteria for visual dataflow languages and a testing methodology","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Dataflow; Context (archaeology); Unit testing; Visual programming language; Empirical research; Software engineering; Programming language; Software","score_opus":0.3232977272659157,"score_gpt":0.41639520446411027,"score_spread":0.09309747719819456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056488032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015872458,0.0003192727,0.97847074,0.00019784154,0.0002826361,0.00019282413,0.000037394304,0.004624269,0.0000025681354],"genre_scores_gemma":[0.07256598,0.00006208932,0.9268639,0.00023530642,0.000065070795,0.00010875635,0.000007245993,0.000035765403,0.000055890127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830157,0.00029962536,0.00028596737,0.0005947637,0.00010022213,0.00041784812],"domain_scores_gemma":[0.96762776,0.031476114,0.00007014266,0.00056556414,0.00011473251,0.0001456635],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013894971,0.0002790582,0.00043149004,0.00034561526,0.00033066943,0.000044976918,0.00044083624,0.00020029182,0.00000319793],"category_scores_gemma":[0.021633742,0.00027908024,0.000056709545,0.00036425915,0.00011293839,0.00021160909,0.00005969472,0.00032498728,0.0000013028518],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006858348,0.0002459822,0.0048478665,0.0003812986,0.00014504106,0.00010976783,0.0027438134,0.0012956124,0.010267869,0.0008979223,0.000571897,0.9784244],"study_design_scores_gemma":[0.010434689,0.0148896435,0.120083295,0.0015566432,0.00084529497,0.02888515,0.0004930165,0.607833,0.1213767,0.07241214,0.013196362,0.007994033],"about_ca_topic_score_codex":0.00010405933,"about_ca_topic_score_gemma":0.0000032022858,"teacher_disagreement_score":0.9704303,"about_ca_system_score_codex":0.000017754384,"about_ca_system_score_gemma":0.000055964225,"threshold_uncertainty_score":0.99996614},"labels":[],"label_agreement":null},{"id":"W2056899516","doi":"10.1145/2491509.2491520","title":"Using a functional size measurement procedure to evaluate the quality of models in MDD environments","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Model-Driven Software Engineering 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":"Université du Québec","funders":"","keywords":"Computer science; Correctness; Consistency (knowledge bases); Quality (philosophy); Quality assurance; Reliability engineering; Software quality; Software quality assurance; Software; Artificial intelligence; Software development; Algorithm; Programming language","score_opus":0.2607569112903205,"score_gpt":0.3488981002180973,"score_spread":0.08814118892777678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056899516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045602214,0.00008959185,0.953275,0.00022215085,0.00018171877,0.00042621745,0.0000031917298,0.0001987505,0.0000011125006],"genre_scores_gemma":[0.32432994,0.0000128611,0.6753724,0.00007467437,0.000008616247,0.0001780402,2.2780891e-7,0.000013877236,0.000009342027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.00026856404,0.00038102272,0.00038914243,0.00038887846,0.00027396384],"domain_scores_gemma":[0.998176,0.0009403831,0.00004856493,0.0006663045,0.00007724838,0.000091537804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019497465,0.00020314753,0.0003032039,0.00018920653,0.00006327327,0.000020485384,0.0004483829,0.00011542028,0.000011015812],"category_scores_gemma":[0.00043995914,0.00017126885,0.00006905676,0.00030495573,0.000032308442,0.00022637169,0.000044269567,0.0002850498,0.000002400773],"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":[0.00001394089,0.0000568836,0.000106229934,0.00005260571,0.00004598451,5.481613e-7,0.00060915604,0.94763017,0.018203769,0.0025233882,0.000008059685,0.030749274],"study_design_scores_gemma":[0.0015193041,0.00046432187,0.07170616,0.00036169443,0.00008403998,0.00008330041,0.000049253813,0.8680887,0.038448624,0.017090416,0.00096489827,0.0011392542],"about_ca_topic_score_codex":0.00013116855,"about_ca_topic_score_gemma":0.0000066794105,"teacher_disagreement_score":0.27872774,"about_ca_system_score_codex":0.00013037484,"about_ca_system_score_gemma":0.00004696561,"threshold_uncertainty_score":0.69841415},"labels":[],"label_agreement":null},{"id":"W2068726498","doi":"10.1145/839268.839270","title":"Feature specification and automated conflict detection","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Formal Methods in Verification","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 Ottawa","funders":"","keywords":"Computer science; Feature (linguistics); Model checking; Formal specification; Formal methods; Specification language; Extractor; Field (mathematics); Software engineering; Programming language; Data mining","score_opus":0.0813120162940838,"score_gpt":0.3161018302563561,"score_spread":0.23478981396227228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068726498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008814172,0.00025702943,0.98894477,0.00012468689,0.000701615,0.000121394536,0.000001879047,0.0010206626,0.000013763382],"genre_scores_gemma":[0.05730532,0.00017202583,0.9423321,0.000054766417,0.000014863839,0.000034615674,8.9772124e-7,0.000012993263,0.00007245467],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998958,0.00031316094,0.0001307601,0.00033607116,0.00008169855,0.00018030513],"domain_scores_gemma":[0.9986043,0.0007574012,0.000046912646,0.00046468247,0.000046247886,0.00008047326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008583867,0.000141384,0.00016220604,0.00020108339,0.00013542744,0.000043181604,0.0001694351,0.00017000466,0.0000032535922],"category_scores_gemma":[0.0012145846,0.00014439783,0.000029185394,0.00030119746,0.00003702195,0.00021341689,0.000006170497,0.00026321897,0.0000038506387],"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":[0.00004417855,0.00007896351,0.000121431636,0.00014118239,0.00011238986,0.0000063546236,0.0018332012,0.014152778,0.048138056,0.0455482,0.00006183551,0.88976145],"study_design_scores_gemma":[0.0018492043,0.00086198415,0.033544473,0.000090749265,0.00012340248,0.0016418828,0.00019595366,0.34397697,0.4955776,0.0031721005,0.117600754,0.0013648983],"about_ca_topic_score_codex":0.000004200977,"about_ca_topic_score_gemma":0.0000010207618,"teacher_disagreement_score":0.8883965,"about_ca_system_score_codex":0.000030484049,"about_ca_system_score_gemma":0.000013053052,"threshold_uncertainty_score":0.58883727},"labels":[],"label_agreement":null},{"id":"W2090908516","doi":"10.1145/2430536.2430539","title":"Facilitating the transition from use case models to analysis models","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":114,"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":"Pearl Therapeutics; Fonds National de la Recherche Luxembourg","keywords":"Use Case Diagram; Computer science; Ambiguity; Set (abstract data type); Unified Modeling Language; Sequence diagram; Class diagram; Class (philosophy); Quality (philosophy); Data mining; Natural language processing; Artificial intelligence; Programming language; Software","score_opus":0.15956612434369744,"score_gpt":0.31830746037286617,"score_spread":0.15874133602916873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090908516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21139473,0.000078856945,0.7872245,0.00036001584,0.00017294106,0.00023664345,0.00003384933,0.00049794227,5.510651e-7],"genre_scores_gemma":[0.4366783,0.000012404915,0.56298864,0.00012316664,0.000014513792,0.00014398221,0.0000029878413,0.000014744845,0.000021238526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982251,0.00028538718,0.00027301515,0.00056805165,0.00022659314,0.00042188776],"domain_scores_gemma":[0.982613,0.01596568,0.000024954183,0.0010475587,0.00012342859,0.00022536579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067638955,0.00023881027,0.00033248233,0.00053455884,0.00021558962,0.0001878812,0.0005500845,0.00013720087,0.00002069003],"category_scores_gemma":[0.001295267,0.0002016954,0.00014983462,0.0011417854,0.00003272743,0.00081561983,0.000034166787,0.00043950407,0.000014499726],"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":[0.0000043932137,0.0000147574665,0.000013183932,0.000008766952,0.00022960456,0.00002961185,0.004522451,0.95390034,0.0002203712,0.00020815112,0.000010890036,0.040837485],"study_design_scores_gemma":[0.0001731923,0.000074314776,0.0006123971,0.000014637818,0.00011669227,0.00013522184,0.00023302424,0.994874,0.00043106804,0.0030322503,0.0000377395,0.00026548258],"about_ca_topic_score_codex":0.0023305535,"about_ca_topic_score_gemma":0.00004452548,"teacher_disagreement_score":0.22528358,"about_ca_system_score_codex":0.000053041407,"about_ca_system_score_gemma":0.000021259251,"threshold_uncertainty_score":0.8224899},"labels":[],"label_agreement":null},{"id":"W2095443555","doi":"10.1145/363516.363523","title":"Proof linking","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Correctness; Bytecode; Programming language; Code (set theory); Implementation; Modular design; Distributed computing; Java; Set (abstract data type)","score_opus":0.0799470620929626,"score_gpt":0.3050163120891167,"score_spread":0.22506924999615413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095443555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012061008,0.00016271255,0.98655397,0.00028513517,0.00038790115,0.00006211019,0.0000010429899,0.00045620144,0.000029896806],"genre_scores_gemma":[0.101160556,0.00006330212,0.89834994,0.00021493442,0.000047212387,0.000017250199,7.8599186e-7,0.000009250524,0.00013679503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918216,0.00010239048,0.00015196332,0.00029128135,0.00007801302,0.00019419653],"domain_scores_gemma":[0.99829745,0.0011471986,0.000019940822,0.0004467955,0.000022791488,0.00006582191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004588872,0.00010813539,0.00013854745,0.00011153221,0.00014997766,0.00004133448,0.00037190825,0.0000951539,0.00004732029],"category_scores_gemma":[0.00017585729,0.000113356575,0.00004304065,0.00023358804,0.000020947795,0.00013016014,0.0000080751815,0.0002511673,0.000014811871],"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":[0.000005437557,0.000026001931,0.000025360418,0.00002462696,0.000020331088,0.0000032114788,0.0008758584,0.042644434,0.00015178687,0.00288325,0.000008008397,0.9533317],"study_design_scores_gemma":[0.0027314343,0.0010893822,0.0076400694,0.0004951074,0.00012182226,0.0013843916,0.00013504377,0.6450867,0.063252315,0.029566208,0.24594525,0.0025522523],"about_ca_topic_score_codex":0.0000067487194,"about_ca_topic_score_gemma":5.5542296e-7,"teacher_disagreement_score":0.95077944,"about_ca_system_score_codex":0.000014845435,"about_ca_system_score_gemma":0.000016766715,"threshold_uncertainty_score":0.4622547},"labels":[],"label_agreement":null},{"id":"W2113351233","doi":"10.1145/2000791.2000794","title":"Reducing the effort of bug report triage","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of British Columbia","funders":"","keywords":"Computer science; Process (computing); Variety (cybernetics); Key (lock); Recommender system; Software engineering; Software; Software development; Triage; Data science; World Wide Web; Artificial intelligence; Computer security","score_opus":0.13501545347678479,"score_gpt":0.32812057111168713,"score_spread":0.19310511763490235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113351233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06724524,0.0001792267,0.93112254,0.00008416865,0.0008070321,0.00014148334,0.000002072825,0.00040449674,0.00001375433],"genre_scores_gemma":[0.3030848,0.00004296764,0.6966525,0.000018619796,0.000028105726,0.000043591845,5.704381e-7,0.000019066496,0.00010978932],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986462,0.000121282355,0.00032606674,0.0003697575,0.00019263421,0.00034406412],"domain_scores_gemma":[0.9941271,0.0044124653,0.00006446449,0.001220968,0.00007015421,0.000104841005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00204098,0.00016744237,0.00028076803,0.00026161986,0.0000970383,0.000016372294,0.0007557723,0.00011895839,0.000018386541],"category_scores_gemma":[0.004332288,0.00013299286,0.000096277,0.0004545469,0.00007149817,0.00013184092,0.00004169164,0.00041483965,0.0000034108396],"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":[0.00031057687,0.00064956874,0.01576137,0.00089334726,0.0014270705,0.0009817758,0.02528349,0.113869056,0.013619695,0.012152846,0.00039885254,0.8146524],"study_design_scores_gemma":[0.0044597783,0.003029096,0.4282827,0.0006962584,0.00043467153,0.010894158,0.00047585918,0.030220123,0.49480307,0.009284347,0.014340571,0.0030793555],"about_ca_topic_score_codex":0.00009647654,"about_ca_topic_score_gemma":0.0000012624122,"teacher_disagreement_score":0.811573,"about_ca_system_score_codex":0.000026789085,"about_ca_system_score_gemma":0.000053849028,"threshold_uncertainty_score":0.54232913},"labels":[],"label_agreement":null},{"id":"W2116357421","doi":"10.1145/13487689.13487691","title":"Topology analysis of software dependencies","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"McGill University","funders":"","keywords":"Computer science; Intuition; Source code; Task (project management); Static program analysis; Set (abstract data type); Dependency (UML); Software; Program analysis; Fuzzy logic; Programming language; Software engineering; Data mining; Theoretical computer science; Software development; Artificial intelligence; Systems engineering","score_opus":0.09963517125290641,"score_gpt":0.32526599820654656,"score_spread":0.22563082695364015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116357421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13099815,0.00032888504,0.86754405,0.00009153236,0.00037337106,0.00007880594,0.000012454698,0.0005710417,0.0000016797355],"genre_scores_gemma":[0.2861755,0.00014955524,0.71348023,0.000039312323,0.000018118228,0.000029440846,0.0000026591663,0.000017242082,0.000087932174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9983335,0.00017464967,0.00032284562,0.00049094635,0.0002606793,0.00041739162],"domain_scores_gemma":[0.98984575,0.008833106,0.000055500775,0.000992144,0.00012124792,0.00015221968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064005994,0.00022385726,0.0005792675,0.0012841003,0.00013732696,0.000012949679,0.00077226845,0.00020643623,0.000036946192],"category_scores_gemma":[0.0039497614,0.00022834167,0.00019721211,0.0016263435,0.00013266644,0.00016606579,0.000052128264,0.00039586483,0.000005245089],"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":[0.00008868562,0.0003282572,0.053956177,0.00027252536,0.0044827824,0.00024907629,0.005820803,0.75441647,0.003353229,0.0035227803,0.00013967107,0.17336954],"study_design_scores_gemma":[0.002853747,0.0021405432,0.84294397,0.00013236415,0.0018124325,0.0021039254,0.00023300307,0.074555725,0.06256704,0.0020256115,0.0057997624,0.002831861],"about_ca_topic_score_codex":0.00007832718,"about_ca_topic_score_gemma":0.0000073728665,"teacher_disagreement_score":0.7889878,"about_ca_system_score_codex":0.000042774074,"about_ca_system_score_gemma":0.00006719055,"threshold_uncertainty_score":0.9311503},"labels":[],"label_agreement":null},{"id":"W2133363731","doi":"10.1145/2000799.2000805","title":"Recommending Adaptive Changes for Framework Evolution","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":98,"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":"Code refactoring; Computer science; Software evolution; Software engineering; Open source; Simple (philosophy); Software development; Programming language; Software","score_opus":0.20430693453139503,"score_gpt":0.3413837973744098,"score_spread":0.1370768628430148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133363731","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021315808,0.00022488662,0.9952228,0.00018714303,0.0011430362,0.00022945942,0.000009685949,0.00084820244,0.000003221372],"genre_scores_gemma":[0.13536441,0.000043301796,0.8641992,0.00005611996,0.000058775422,0.00021408878,7.655772e-7,0.000028423285,0.00003490344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876004,0.00010654743,0.00015247989,0.0004388435,0.00011378372,0.00042830574],"domain_scores_gemma":[0.9913923,0.0077893925,0.000033382566,0.0005789166,0.00007190955,0.00013409788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085187453,0.00019440563,0.00024158282,0.0003939397,0.0001444924,0.00002410922,0.0005135794,0.00020352389,0.000013994588],"category_scores_gemma":[0.003760497,0.00020427238,0.00006908419,0.00035746043,0.00003199789,0.00015825278,0.000029309798,0.00039273794,0.000005324936],"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":[0.00022665563,0.00020768709,0.0010591272,0.00028813706,0.00043433497,0.000021439937,0.0077233613,0.01324788,0.0010875004,0.08308913,0.00014722413,0.8924675],"study_design_scores_gemma":[0.0090023065,0.018225513,0.14691527,0.0024582169,0.000711483,0.0015818657,0.0018078663,0.3076406,0.15329894,0.31211737,0.036560744,0.009679784],"about_ca_topic_score_codex":0.000023063065,"about_ca_topic_score_gemma":0.0000032320243,"teacher_disagreement_score":0.88278776,"about_ca_system_score_codex":0.00008389274,"about_ca_system_score_gemma":0.00002600231,"threshold_uncertainty_score":0.8329986},"labels":[],"label_agreement":null},{"id":"W2153546999","doi":"10.1145/1189748.1189751","title":"Representing concerns in source code","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":215,"is_retracted":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; McGill University","funders":"","keywords":"Computer science; Software engineering; Source code; Task (project management); Software; Separation of concerns; Software development; Software system; Code (set theory); Programming language; Systems engineering","score_opus":0.10964718519581704,"score_gpt":0.3609016914329558,"score_spread":0.25125450623713874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153546999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084448874,0.00020072602,0.913884,0.00013363494,0.0004938357,0.00011005227,0.0000017558132,0.00072038325,0.0000067650144],"genre_scores_gemma":[0.3119009,0.000032708485,0.6877734,0.000052485673,0.000045134904,0.000018659388,6.331785e-7,0.000024448516,0.00015161384],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99832416,0.00011508831,0.00029013478,0.00050071575,0.0001980553,0.00057187607],"domain_scores_gemma":[0.9883568,0.010666407,0.000031578955,0.00074410933,0.000043993627,0.00015706941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023630622,0.00018369756,0.0002628414,0.0005576328,0.0000794861,0.00004143256,0.0006048612,0.00016374151,0.000008968913],"category_scores_gemma":[0.00530116,0.00020107217,0.000058608166,0.00064685696,0.0000430524,0.00017096684,0.000048166483,0.0006082646,0.000008268017],"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":[0.00006070112,0.0001272492,0.022371484,0.00015841893,0.00010511474,0.00021617551,0.0033225971,0.29170787,0.0044768257,0.001869537,0.000048669215,0.6755354],"study_design_scores_gemma":[0.00908503,0.0015702883,0.50347066,0.00094741443,0.00011424521,0.0022279765,0.0009865093,0.22648242,0.1699024,0.004343239,0.075707056,0.0051627816],"about_ca_topic_score_codex":0.00007858968,"about_ca_topic_score_gemma":0.000022038177,"teacher_disagreement_score":0.6703726,"about_ca_system_score_codex":0.000073237694,"about_ca_system_score_gemma":0.00002933144,"threshold_uncertainty_score":0.8199485},"labels":[],"label_agreement":null},{"id":"W2165688098","doi":"10.1145/941566.941569","title":"Static analysis to support the evolution of exception structure in object-oriented systems","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":170,"is_retracted":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; Exception handling; Java; Control flow; Programming language; Software engineering; Control flow analysis; Object-oriented programming; Robustness (evolution); Static analysis; Static program analysis; Source code; Program code; Information flow; Software; Software development; Programming paradigm; Procedural programming; Inductive programming","score_opus":0.04314179430167696,"score_gpt":0.31228285955602275,"score_spread":0.2691410652543458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165688098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15396307,0.00009557915,0.8451443,0.00004578409,0.00042195574,0.00018965802,0.00001095983,0.0001277927,9.166245e-7],"genre_scores_gemma":[0.68849725,0.00000991028,0.31139973,0.000011204214,0.000006459251,0.00003891381,0.0000015183474,0.000009428069,0.000025557745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9984809,0.0003705095,0.00028898285,0.00033726354,0.00022547784,0.00029682068],"domain_scores_gemma":[0.9957826,0.0033187976,0.00004091901,0.00068270764,0.00008427608,0.0000906743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011911114,0.00015117807,0.00031024966,0.0009524371,0.000057318954,0.000023290339,0.00035513926,0.000106605425,0.000011567091],"category_scores_gemma":[0.0030482437,0.00012808663,0.0000686196,0.0023052902,0.000027118258,0.00010724719,0.000014128467,0.0003005349,0.0000019756812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001049514,0.000025469195,0.003498797,0.000057772024,0.00016790238,0.0000037785055,0.0012349081,0.9841444,0.0011808978,0.0024536522,0.000007497642,0.0072144666],"study_design_scores_gemma":[0.004307031,0.0035667939,0.66668,0.00035765252,0.001212568,0.0005587829,0.0025625655,0.28286818,0.024729213,0.0042551737,0.0061441655,0.0027579179],"about_ca_topic_score_codex":0.00017131091,"about_ca_topic_score_gemma":0.000033807763,"teacher_disagreement_score":0.7012762,"about_ca_system_score_codex":0.00015541735,"about_ca_system_score_gemma":0.000066206645,"threshold_uncertainty_score":0.5223221},"labels":[],"label_agreement":null},{"id":"W2271850540","doi":"10.1145/2789209","title":"Test Case Prioritization Using Extended Digraphs","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regression testing; Test case; Test suite; Digraph; Model-based testing; Machine learning; Prioritization; Data mining; Test (biology); Hidden Markov model; Fault detection and isolation; Artificial intelligence; Reliability engineering; Software; Regression analysis; Software development","score_opus":0.15832191192600087,"score_gpt":0.3445707515609084,"score_spread":0.18624883963490751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271850540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01071556,0.00020699885,0.98207814,0.00007110158,0.00045176258,0.000098269535,0.0000044798085,0.006370334,0.000003349034],"genre_scores_gemma":[0.18744797,0.000014091406,0.81238496,0.00007509612,0.000025845966,0.000016937898,9.2142284e-7,0.00001795322,0.000016250517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893683,0.0001308564,0.00019575054,0.00036286475,0.00011901479,0.0002547112],"domain_scores_gemma":[0.9963054,0.0027879884,0.00004630916,0.00057909393,0.00010629598,0.00017489932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076398224,0.00017821371,0.00021421656,0.00030616767,0.00013677994,0.00005865407,0.00026926686,0.00013354626,0.0000012950677],"category_scores_gemma":[0.0044877157,0.00018280285,0.000048302074,0.00043939424,0.000037851754,0.00020964176,0.000023769377,0.00023519326,0.0000017653983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003353971,0.00033727312,0.002589054,0.00014688638,0.00011482696,0.0014484108,0.0035078977,0.053712863,0.0012936757,0.0021610924,0.0003763495,0.93427813],"study_design_scores_gemma":[0.00289408,0.0022091265,0.0020484044,0.00043547497,0.0002654431,0.057590727,0.00017156136,0.82499737,0.016171195,0.08820202,0.0025033401,0.0025112594],"about_ca_topic_score_codex":0.00009683441,"about_ca_topic_score_gemma":0.0000023124078,"teacher_disagreement_score":0.93176687,"about_ca_system_score_codex":0.000045255398,"about_ca_system_score_gemma":0.000055512326,"threshold_uncertainty_score":0.74544835},"labels":[],"label_agreement":null},{"id":"W2291690114","doi":"10.1145/2824234","title":"Type-Based Call Graph Construction Algorithms for Scala","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scala; Computer science; Bytecode; Programming language; Compiler; Call graph; Java bytecode; Graph; Algorithm; Java; Theoretical computer science; Java applet; Java annotation","score_opus":0.12323723367273838,"score_gpt":0.3188342743765967,"score_spread":0.19559704070385836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291690114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005806069,0.00020082721,0.99616706,0.0001471096,0.0022688687,0.00018266116,0.0000026679172,0.00044298224,0.0000072019084],"genre_scores_gemma":[0.06806958,0.000010395121,0.9316314,0.00007490145,0.00006362174,0.0000614364,0.000003675615,0.0000136496765,0.00007136356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990947,0.000112055444,0.00016339312,0.00030118757,0.00009483102,0.00023381232],"domain_scores_gemma":[0.9984884,0.00085233187,0.00003911954,0.0003549338,0.00012292204,0.00014227687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007199561,0.00013827703,0.00021281415,0.00017507916,0.000085819906,0.000038934668,0.00024014385,0.0001441323,0.0000014544892],"category_scores_gemma":[0.000548845,0.00012725132,0.00006703504,0.0002503416,0.000046277633,0.00009555217,0.0000070201404,0.00014524232,0.0000043256427],"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":[0.000094755815,0.00011417958,0.0003486568,0.0001697066,0.0001551076,0.000011756458,0.00093447097,0.050895967,0.00038775415,0.037464384,0.0002658081,0.90915745],"study_design_scores_gemma":[0.015533827,0.009010972,0.001840313,0.00011521937,0.0005612161,0.0019650701,0.00065919827,0.3992483,0.04546076,0.18129505,0.34013078,0.0041792863],"about_ca_topic_score_codex":0.000036478188,"about_ca_topic_score_gemma":0.0000038630374,"teacher_disagreement_score":0.90497816,"about_ca_system_score_codex":0.000027647899,"about_ca_system_score_gemma":0.00006073213,"threshold_uncertainty_score":0.5189158},"labels":[],"label_agreement":null},{"id":"W2395760792","doi":"10.1145/2876441","title":"Understanding JavaScript Event-Based Interactions with Clematis","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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 British Columbia","funders":"Intel Corporation","keywords":"Computer science; JavaScript; Program comprehension; Event (particle physics); Software engineering; Web application; Visualization; Asynchronous communication; Programming language; Human–computer interaction; Software; Software system; Artificial intelligence; World Wide Web","score_opus":0.1857356358688734,"score_gpt":0.3321283856873676,"score_spread":0.14639274981849418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395760792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045996513,0.000050584094,0.9926646,0.0010424791,0.00057966687,0.00013639274,0.000008121008,0.000915415,0.0000031117575],"genre_scores_gemma":[0.40555355,0.000017173403,0.59415615,0.000055200337,0.000020001944,0.00005985487,5.5439676e-7,0.000025902305,0.00011164242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855745,0.00015109399,0.00020462812,0.00045605103,0.00021996224,0.00041083017],"domain_scores_gemma":[0.9902299,0.008745217,0.000037589554,0.0007545894,0.000057942354,0.00017475041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000591163,0.00022143857,0.00024976407,0.0004781718,0.00014887434,0.000055451812,0.00046139985,0.00009284834,0.000036210433],"category_scores_gemma":[0.001723053,0.00016162136,0.00006862222,0.00044163127,0.00006155178,0.00031870953,0.000020302055,0.00030031858,0.000015177459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036713874,0.000501545,0.007313859,0.00062287546,0.0011523557,0.00025456093,0.0021411888,0.41837677,0.023293694,0.02576685,0.00081807695,0.51939106],"study_design_scores_gemma":[0.036295258,0.013608614,0.10061678,0.009883072,0.0010326805,0.00656065,0.0012222035,0.3632661,0.35509774,0.0270546,0.07136419,0.013998106],"about_ca_topic_score_codex":0.000013116501,"about_ca_topic_score_gemma":0.000009307301,"teacher_disagreement_score":0.50539297,"about_ca_system_score_codex":0.0001922949,"about_ca_system_score_gemma":0.00006543873,"threshold_uncertainty_score":0.65907276},"labels":[],"label_agreement":null},{"id":"W2409613233","doi":"10.1145/2904904","title":"Multi-Step Learning and Adaptive Search for Learning Complex Model Transformations from Examples","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transformation (genetics); Model transformation; Context (archaeology); Process (computing); Consistency (knowledge bases); Artificial intelligence; Theoretical computer science; Machine learning; Programming language","score_opus":0.17202754829192649,"score_gpt":0.3368951754105206,"score_spread":0.16486762711859412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409613233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046957056,0.00013248077,0.99308205,0.00019467117,0.00009796683,0.00028153474,0.00004998499,0.0014645795,0.0000010536453],"genre_scores_gemma":[0.084476,0.00024980388,0.9149394,0.000024359219,0.000016399581,0.00016043232,0.0000066244734,0.000039491733,0.00008749463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985148,0.00018812204,0.00026984885,0.0005116375,0.00012930158,0.00038629555],"domain_scores_gemma":[0.9959508,0.0034345638,0.00004253323,0.000329981,0.00009245866,0.00014962812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006446384,0.0002639275,0.0003485575,0.00028942863,0.0002692068,0.000045005017,0.000338005,0.00018330573,0.000005953497],"category_scores_gemma":[0.00019593071,0.00023247095,0.000084529536,0.00015084962,0.0000646242,0.00033234037,0.000033081287,0.0003971967,0.0000017167966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003331055,0.000030785275,0.0001179827,0.000047695463,0.000093839604,0.0000015891401,0.0018304478,0.35513365,0.012258824,0.0055062394,0.0000065534086,0.6249391],"study_design_scores_gemma":[0.00079596025,0.0002556922,0.00052544323,0.000086553264,0.00003167504,0.000020743077,0.00003180229,0.98825866,0.0043232786,0.00046818404,0.0048514334,0.00035060113],"about_ca_topic_score_codex":0.000047189147,"about_ca_topic_score_gemma":0.000007080352,"teacher_disagreement_score":0.633125,"about_ca_system_score_codex":0.00005139838,"about_ca_system_score_gemma":0.000031030075,"threshold_uncertainty_score":0.947989},"labels":[],"label_agreement":null},{"id":"W2475137645","doi":"10.1145/2932631","title":"Multi-Criteria Code Refactoring Using Search-Based Software Engineering","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":137,"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":"Japan Society for the Promotion of Science","keywords":"Code refactoring; Computer science; Consistency (knowledge bases); Software quality; Benchmark (surveying); Software engineering; Search-based software engineering; Code smell; Software; Class (philosophy); Source code; Code (set theory); Software development; Software design; Programming language; Artificial intelligence","score_opus":0.17718848535030324,"score_gpt":0.36867093108150445,"score_spread":0.1914824457312012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475137645","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080024436,0.00021668304,0.9160522,0.00016391429,0.0012480876,0.00021824379,0.000038692877,0.0020375291,1.8267636e-7],"genre_scores_gemma":[0.17448775,0.000043081865,0.8251285,0.000045431498,0.00008108306,0.000055126326,0.0000018084152,0.00009577648,0.00006141499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969705,0.00023775894,0.00043034554,0.000944794,0.000405426,0.0010112176],"domain_scores_gemma":[0.9882786,0.00971868,0.000052347008,0.0013815045,0.00015288213,0.00041598314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013317469,0.00049202243,0.0005328429,0.0008629909,0.00020730976,0.000113882634,0.0010900926,0.000313165,0.0000337659],"category_scores_gemma":[0.008020875,0.00043502412,0.00016467854,0.0006789198,0.000082054445,0.0004748186,0.00009694022,0.0006302201,0.000018797287],"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":[0.00011012898,0.00026349223,0.006862972,0.0007087921,0.0004058084,0.00021624922,0.0009959618,0.59529096,0.2192747,0.0003605007,0.000030133642,0.17548029],"study_design_scores_gemma":[0.0069466466,0.001012523,0.046705514,0.0018924492,0.00016039569,0.0007425662,0.00004847202,0.64281994,0.28867304,0.00014002556,0.0069978484,0.0038605796],"about_ca_topic_score_codex":0.000043471082,"about_ca_topic_score_gemma":0.0000028698641,"teacher_disagreement_score":0.17161971,"about_ca_system_score_codex":0.0002762409,"about_ca_system_score_gemma":0.00013319009,"threshold_uncertainty_score":0.99981016},"labels":[],"label_agreement":null},{"id":"W2570857834","doi":"10.1145/2990497","title":"Generating API Call Rules from Version History and Stack Overflow Posts","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"Concordia University","funders":"","keywords":"Computer science; Android (operating system); Application programming interface; Cluster analysis; World Wide Web; Precision and recall; Set (abstract data type); Baseline (sea); Information retrieval; Operating system; Programming language; Machine learning","score_opus":0.08205151378663754,"score_gpt":0.30898722927561467,"score_spread":0.22693571548897712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570857834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24495813,0.0009061289,0.7525883,0.00014567896,0.0009735481,0.00006952114,0.000016353595,0.00033986842,0.0000025051029],"genre_scores_gemma":[0.12425254,0.00020020483,0.8751961,0.00006892461,0.00008115394,0.000019516689,0.000004212949,0.00002861924,0.0001487393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986622,0.000116222276,0.00017187367,0.0005254853,0.0001854658,0.00033877115],"domain_scores_gemma":[0.99481994,0.0037592459,0.00005321233,0.0011293356,0.00005377149,0.00018449184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056560675,0.00021513851,0.00027496222,0.00019470869,0.00031574062,0.00011319049,0.00069342257,0.00017755257,0.000018579738],"category_scores_gemma":[0.003527179,0.00022761468,0.000053409196,0.000044832454,0.00008056818,0.0003516882,0.000094022085,0.00043694582,0.000011035554],"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":[0.00013470773,0.00016492206,0.010300453,0.00035146743,0.0005152538,0.00024088666,0.0049279546,0.07871324,0.058783438,0.0010587695,0.0012213443,0.8435876],"study_design_scores_gemma":[0.0067713344,0.0015956493,0.4023952,0.0007732263,0.0002711784,0.00054868456,0.00013187186,0.4741397,0.041601654,0.0020624292,0.065716505,0.0039926018],"about_ca_topic_score_codex":0.00035732513,"about_ca_topic_score_gemma":0.000010348668,"teacher_disagreement_score":0.83959496,"about_ca_system_score_codex":0.00012662784,"about_ca_system_score_gemma":0.000050595718,"threshold_uncertainty_score":0.9281857},"labels":[],"label_agreement":null},{"id":"W2805382256","doi":"10.1145/3196831","title":"An Empirical Study of Meta- and Hyper-Heuristic Search for Multi-Objective Release Planning","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Calgary","funders":"Engineering and Physical Sciences Research Council; Dalian University of Technology; Core Research for Evolutional Science and Technology; Universiteit Utrecht; University College London","keywords":"Computer science; Heuristics; Heuristic; Meta heuristic; Variety (cybernetics); Genetic algorithm; Machine learning; Empirical research; Search algorithm; Beam search; Artificial intelligence; Mathematical optimization; Data mining; Algorithm; Mathematics; Statistics","score_opus":0.2711195274073803,"score_gpt":0.4358261630705214,"score_spread":0.1647066356631411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805382256","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.382091,0.00013760575,0.61713636,0.000020057765,0.00015397511,0.0002440458,0.000007447069,0.00020936622,1.67474e-7],"genre_scores_gemma":[0.49177697,0.000005996,0.5080647,0.000013575426,0.000025406955,0.00008488896,6.06806e-7,0.00001856278,0.000009285015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831134,0.0003231372,0.00024483236,0.0005775567,0.0001858458,0.00035727053],"domain_scores_gemma":[0.9911369,0.0077806865,0.000031319694,0.0006691677,0.0001893529,0.00019258534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012704084,0.00021314886,0.000458843,0.00043232428,0.00016679485,0.000036393343,0.00043807933,0.0001239041,0.0000040350997],"category_scores_gemma":[0.002718983,0.00019653609,0.00006721289,0.0003734072,0.00009432169,0.00016852809,0.00003687307,0.00033961792,9.2113805e-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":[0.0011705324,0.0042214217,0.06486815,0.0011240587,0.0055970447,0.00011801511,0.08559067,0.4355066,0.010745441,0.000516987,0.000063782725,0.39047727],"study_design_scores_gemma":[0.0081074955,0.02360309,0.26525313,0.0001320515,0.0015124129,0.0004543816,0.0025171184,0.6529715,0.042460885,0.00043209956,0.00071896875,0.0018368457],"about_ca_topic_score_codex":0.000054450782,"about_ca_topic_score_gemma":0.00000487908,"teacher_disagreement_score":0.38864043,"about_ca_system_score_codex":0.000026491069,"about_ca_system_score_gemma":0.00004315948,"threshold_uncertainty_score":0.80145085},"labels":[],"label_agreement":null},{"id":"W2807405309","doi":"10.1145/3196883","title":"Inferring Extended Probabilistic Finite-State Automaton Models from Software Executions","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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 Alberta","funders":"","keywords":"Computer science; Probabilistic automaton; Probabilistic logic; Automaton; Finite-state machine; Reinforcement learning; Decidability; Theoretical computer science; Software; Inference; Deterministic automaton; Flexibility (engineering); Büchi automaton; Deterministic finite automaton; Artificial intelligence; Programming language; Machine learning; Mathematics","score_opus":0.08968027278245541,"score_gpt":0.31906479794928544,"score_spread":0.22938452516683003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807405309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03966339,0.00020449645,0.9558517,0.00012878595,0.001046382,0.00025817406,0.00004714768,0.002795775,0.0000041639755],"genre_scores_gemma":[0.24473113,0.000050355196,0.7547882,0.000075056494,0.000077124765,0.00013264595,0.00000675143,0.00005207219,0.00008666875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745136,0.00022924137,0.00040514354,0.0008749005,0.0003246274,0.00071475096],"domain_scores_gemma":[0.9866677,0.0113547165,0.00006033727,0.0014116899,0.00019899476,0.00030656328],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076456123,0.00039006677,0.00044519003,0.00055362424,0.0003107887,0.00012870187,0.000985591,0.00023684216,0.000034376942],"category_scores_gemma":[0.007149576,0.00041072504,0.00011910877,0.0007224624,0.00015550111,0.00049866596,0.00010698074,0.00073261245,0.000043027383],"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":[0.000054024917,0.0001782846,0.00029962533,0.00014437595,0.0002672343,0.000084186046,0.0035170184,0.778366,0.00074034923,0.00219314,0.00006733601,0.21408838],"study_design_scores_gemma":[0.0016375282,0.0009167134,0.012213687,0.00036818226,0.00011269196,0.0002681361,0.00005577976,0.91708076,0.009925597,0.053534403,0.0022073984,0.001679121],"about_ca_topic_score_codex":0.00015210404,"about_ca_topic_score_gemma":0.000019376705,"teacher_disagreement_score":0.21240926,"about_ca_system_score_codex":0.000121912744,"about_ca_system_score_gemma":0.00012592375,"threshold_uncertainty_score":0.9998345},"labels":[],"label_agreement":null},{"id":"W3010215199","doi":"10.1145/3375633","title":"Visualizing Distributed System Executions","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":41,"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; U.S. Air Force; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association; U.S. Air Force Academy; National Science Foundation","keywords":"Computer science; Timestamp; Process (computing); Distributed computing; Software; Theoretical computer science; Programming language; Real-time computing","score_opus":0.0773188187625623,"score_gpt":0.2982571631356249,"score_spread":0.2209383443730626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010215199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011083545,0.00017205764,0.9856799,0.0006698409,0.0006850348,0.00013677782,0.000020953392,0.0015474384,0.0000044570284],"genre_scores_gemma":[0.4586187,0.00002536793,0.5410916,0.00015132141,0.00005168884,0.00003920657,0.0000036715837,0.000012089909,0.000006316022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873185,0.00016758639,0.0002760556,0.00042291672,0.00012526699,0.00027629622],"domain_scores_gemma":[0.99814874,0.0010548052,0.000045316923,0.00049741875,0.000055006283,0.00019872491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046370522,0.00018046619,0.0003072254,0.00009654738,0.00019599314,0.00004244766,0.00042262176,0.00014268413,0.000004402856],"category_scores_gemma":[0.0006884747,0.00016625876,0.00008971596,0.00045297455,0.00003257583,0.00019428505,0.00002776892,0.0002814612,0.000020889462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022811108,0.00038135157,0.004164648,0.0044082655,0.00095625594,0.0001755783,0.015640296,0.41036263,0.007325304,0.03989307,0.0008824366,0.5155821],"study_design_scores_gemma":[0.0056064185,0.0029367455,0.020984082,0.0010750528,0.00047992883,0.001703744,0.0025636607,0.83170843,0.043462195,0.0010058763,0.08430057,0.0041733137],"about_ca_topic_score_codex":0.000014597203,"about_ca_topic_score_gemma":4.8894196e-7,"teacher_disagreement_score":0.51140875,"about_ca_system_score_codex":0.00005010866,"about_ca_system_score_gemma":0.000033503304,"threshold_uncertainty_score":0.6779835},"labels":[],"label_agreement":null},{"id":"W3040857534","doi":"10.1145/3385187","title":"Predicting Node Failures in an Ultra-Large-Scale Cloud Computing Platform","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","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":"Queen's University; York University","funders":"","keywords":"Cloud computing; DevOps; Computer science; Scalability; Context (archaeology); Node (physics); Scale (ratio); Data science; Software; Distributed computing; Computer security; Software engineering; Database; Operating system; Engineering","score_opus":0.059029380876341735,"score_gpt":0.2962129620419633,"score_spread":0.23718358116562155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040857534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3042375,0.00007125481,0.69417274,0.00030770552,0.0005289706,0.000111287416,0.000005412237,0.00056218915,0.00000291996],"genre_scores_gemma":[0.55589485,0.000015612419,0.44377348,0.00020603486,0.00008260309,0.000010523169,0.000001893878,0.000013015586,0.000001983467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983358,0.00015816595,0.00038178015,0.0005522365,0.0001471354,0.0004249215],"domain_scores_gemma":[0.9978524,0.0013550682,0.000057919606,0.00049593137,0.000041476284,0.00019720249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009870712,0.00021630111,0.0003658854,0.00015380974,0.000168324,0.00005087033,0.0005231633,0.00019549724,0.0000054543157],"category_scores_gemma":[0.00061947777,0.00020637909,0.00007112562,0.00042854765,0.000030909083,0.0004013952,0.000021002543,0.00054073863,0.000005321632],"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":[0.00012073066,0.00024972818,0.09134114,0.0007276478,0.00010057362,0.000039462717,0.039526615,0.6670648,0.0028955422,0.00037898967,0.000025009247,0.19752975],"study_design_scores_gemma":[0.003128602,0.001252601,0.04595749,0.00034167714,0.000059780774,0.00024196359,0.0020711692,0.92149293,0.02105964,0.0004810311,0.0025378913,0.0013752442],"about_ca_topic_score_codex":0.000042712712,"about_ca_topic_score_gemma":0.000024359237,"teacher_disagreement_score":0.2544281,"about_ca_system_score_codex":0.00003696635,"about_ca_system_score_gemma":0.000034340057,"threshold_uncertainty_score":0.84158945},"labels":[],"label_agreement":null},{"id":"W3081249378","doi":"10.1145/3487567","title":"A Tale of Two Cities: Software Developers Working from Home during the COVID-19 Pandemic","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":207,"is_retracted":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":"Pandemic; Work (physics); Thematic analysis; Coronavirus disease 2019 (COVID-19); Productivity; Space (punctuation); Narrative; Computer science; Data science; Public relations; Qualitative research; Sociology; Political science; Economic growth; Medicine; Engineering; Social science","score_opus":0.11270580278257773,"score_gpt":0.30246146702617105,"score_spread":0.1897556642435933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081249378","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":[0.38216528,0.0002671079,0.61651164,0.00026774444,0.0004173986,0.00007822239,0.0000074925624,0.00027090064,0.000014213274],"genre_scores_gemma":[0.6354893,0.00010839849,0.3628628,0.0011117137,0.00014386326,0.0000789219,0.000017604392,0.000033889264,0.00015352474],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99893177,0.00007036796,0.00029117358,0.00031993954,0.00011972187,0.00026704615],"domain_scores_gemma":[0.9979349,0.0015325295,0.00010379592,0.00031602188,0.00009496362,0.000017837427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074159453,0.0001948338,0.00032084028,0.00022501523,0.00038606732,0.000032281263,0.0002735607,0.00019190996,0.00009661147],"category_scores_gemma":[0.0024755711,0.00017406377,0.00007293243,0.00067102804,0.00017741155,0.00012325292,0.00006743035,0.00045548787,0.0000044595645],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053332595,0.00038324945,0.5078822,0.002429436,0.0031296285,0.000276539,0.016799575,0.054898784,0.011471835,0.04205107,0.0002669139,0.35987747],"study_design_scores_gemma":[0.018485634,0.00016696549,0.3844613,0.0014803099,0.0018492084,0.00093131466,0.039804306,0.0019616408,0.03666692,0.23058888,0.27624035,0.007363165],"about_ca_topic_score_codex":0.00013701894,"about_ca_topic_score_gemma":0.000053246702,"teacher_disagreement_score":0.3525143,"about_ca_system_score_codex":0.00007766263,"about_ca_system_score_gemma":0.000077010576,"threshold_uncertainty_score":0.70981145},"labels":[],"label_agreement":null},{"id":"W3094649757","doi":"10.1145/3432690","title":"Are Multi-Language Design Smells Fault-Prone? An Empirical Study","year":2021,"lang":"en","type":"preprint","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code smell; Computer science; Software design; Software engineering; Systems design; Software design pattern; Programming language; Software development; Software quality; Software","score_opus":0.233044127550916,"score_gpt":0.413159084720781,"score_spread":0.180114957169865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094649757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20543341,0.0007073804,0.7899691,0.00009075425,0.0015297874,0.00068822765,0.000018197994,0.0015629568,1.9126924e-7],"genre_scores_gemma":[0.18027546,0.000066667446,0.8189271,0.00008751015,0.000090824775,0.00037194917,0.000010151598,0.000099586185,0.00007076919],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948342,0.0015692877,0.00053885486,0.0017666162,0.00050159177,0.0007894711],"domain_scores_gemma":[0.98831666,0.007973518,0.00011260539,0.0029422012,0.00020888705,0.00044610476],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023488833,0.0007105377,0.0010211489,0.0007687611,0.0001906467,0.00032580018,0.0019486651,0.0007214806,0.00002560799],"category_scores_gemma":[0.007091926,0.00075343845,0.00020724944,0.00060994364,0.00006543314,0.00026712703,0.00037435032,0.0025533333,0.000010575298],"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":[0.00004824495,0.0012802738,0.0054718684,0.00040837363,0.000591914,0.00072876515,0.013610494,0.8992616,0.0006379766,0.0000041700546,0.000033695236,0.07792261],"study_design_scores_gemma":[0.0063803955,0.0034127133,0.3357247,0.0012146119,0.00072827237,0.0011043727,0.0070382506,0.6181984,0.018971344,0.0002490195,0.00047977272,0.006498127],"about_ca_topic_score_codex":0.00009587202,"about_ca_topic_score_gemma":0.000023932198,"teacher_disagreement_score":0.33025286,"about_ca_system_score_codex":0.00016841234,"about_ca_system_score_gemma":0.00020171051,"threshold_uncertainty_score":0.9997478},"labels":[],"label_agreement":null},{"id":"W3117161066","doi":"10.1145/3412378","title":"An Empirical Study of Developer Discussions in the Gitter Platform","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Popularity; Computer science; Thread (computing); World Wide Web; Psychology","score_opus":0.18110658069790245,"score_gpt":0.38313018133306537,"score_spread":0.20202360063516292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117161066","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":[0.36049053,0.000018034505,0.63829684,0.0008339252,0.00008607354,0.00013775757,0.0000015655345,0.00013481594,4.7408182e-7],"genre_scores_gemma":[0.66502327,0.0000054919346,0.33472154,0.00017896293,0.000018476781,0.00003809419,5.480661e-7,0.000011026287,0.000002605988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99868286,0.0002545363,0.00023848307,0.0003519756,0.0002181347,0.00025401713],"domain_scores_gemma":[0.9949995,0.004224678,0.00002039926,0.0006058091,0.000032149364,0.000117448646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007927699,0.00014964759,0.00024266768,0.00020597584,0.000068044355,0.00003084582,0.000902358,0.000088107336,0.0000075118082],"category_scores_gemma":[0.0017470053,0.000102327154,0.000038299946,0.00070948753,0.000027459671,0.00019653715,0.000031727934,0.00050589285,0.0000028011586],"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":[0.00017402509,0.001549209,0.088953786,0.0002432866,0.00026914297,0.00019674,0.17609866,0.39585894,0.0027344183,0.0005383467,0.000167768,0.33321565],"study_design_scores_gemma":[0.00305362,0.0047905087,0.91802216,0.000081397804,0.00006852817,0.00018363917,0.005333788,0.06097558,0.0034021195,0.00046942077,0.0025867126,0.0010325438],"about_ca_topic_score_codex":0.000020595944,"about_ca_topic_score_gemma":0.000008121457,"teacher_disagreement_score":0.82906836,"about_ca_system_score_codex":0.000016878497,"about_ca_system_score_gemma":0.000029886893,"threshold_uncertainty_score":0.41727802},"labels":[],"label_agreement":null},{"id":"W3131995106","doi":"10.1145/3434279","title":"Are Comments on Stack Overflow Well Organized for Easy Retrieval by Developers?","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Queen's University; University of Manitoba; Concordia University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Classifier (UML); Information retrieval; Obsolescence; Artificial intelligence; Machine learning; Mechanism (biology); Point (geometry); Data mining; Data science","score_opus":0.08626475335032763,"score_gpt":0.32677058681156684,"score_spread":0.24050583346123922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131995106","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024519335,0.00026801214,0.9727126,0.0005836776,0.0010191484,0.00021499004,0.000054333254,0.00062441,0.000003493187],"genre_scores_gemma":[0.031377047,0.00012136872,0.96696603,0.00058015145,0.000051141775,0.0000562438,0.00001657804,0.000066553315,0.0007648803],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99810004,0.00020095793,0.00025602375,0.0006562932,0.00026691795,0.00051978434],"domain_scores_gemma":[0.9897098,0.0089922035,0.000055858258,0.0008517582,0.00018075672,0.00020963883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076273066,0.00028142316,0.0004028937,0.00021671977,0.00018066092,0.00008597262,0.00057529367,0.00022045014,0.0000385668],"category_scores_gemma":[0.008006842,0.0003005813,0.00009645779,0.0005685399,0.000030881307,0.00014586451,0.000046293244,0.0004950873,0.000020662035],"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":[0.0027135739,0.0034327938,0.011052784,0.0034510877,0.004547044,0.0009763558,0.0057948045,0.27593783,0.0976175,0.005965861,0.038743507,0.54976684],"study_design_scores_gemma":[0.011442578,0.0023113443,0.018746758,0.0006419664,0.0001991175,0.0005579815,0.0002948342,0.025379533,0.64887357,0.0012402525,0.28700608,0.0033059793],"about_ca_topic_score_codex":0.000004718222,"about_ca_topic_score_gemma":0.0000014208654,"teacher_disagreement_score":0.55125606,"about_ca_system_score_codex":0.000122844,"about_ca_system_score_gemma":0.00008478731,"threshold_uncertainty_score":0.9999446},"labels":[],"label_agreement":null},{"id":"W3133170989","doi":"10.1145/3428076","title":"Facet-oriented Modelling","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Forskningsrådet om Hälsa, Arbetsliv och Välfärd","keywords":"Metamodeling; Computer science; Model transformation; Reuse; Software engineering; Model-driven architecture; Programming language; Modeling language; Software product line; Unified Modeling Language; Software; Software development; Artificial intelligence","score_opus":0.08379540016638565,"score_gpt":0.295710145808132,"score_spread":0.21191474564174634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133170989","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003314727,0.00035865797,0.99328315,0.00021222785,0.0006749089,0.00009041459,0.000007344425,0.0020540112,0.000004570868],"genre_scores_gemma":[0.012152451,0.00019375233,0.9872565,0.00012165038,0.000029514105,0.00005416534,0.0000038717385,0.000033950826,0.00015411834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852,0.00013838678,0.0002489083,0.0005664809,0.00016170455,0.00036451078],"domain_scores_gemma":[0.9980727,0.00066635065,0.00003422814,0.0009675795,0.00011016432,0.00014899991],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004302162,0.00024548548,0.00032184506,0.00022805214,0.00011341954,0.0000451891,0.0004161022,0.00019162917,0.000012430017],"category_scores_gemma":[0.00015213457,0.0002720216,0.00009882764,0.00044240864,0.000026240878,0.00021201692,0.000046506764,0.00044694927,0.000006414302],"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":[0.0000049663727,0.000053145824,0.000023095448,0.000056766723,0.00007532407,0.000054175984,0.00051893666,0.77723557,0.0016640467,0.038537994,0.0000252123,0.18175076],"study_design_scores_gemma":[0.00077080063,0.00023558331,0.00024096195,0.000170558,0.00006819984,0.00067569653,0.000019621724,0.810871,0.08494255,0.0037115957,0.09720146,0.0010919821],"about_ca_topic_score_codex":0.000012163217,"about_ca_topic_score_gemma":0.0000010754626,"teacher_disagreement_score":0.18065879,"about_ca_system_score_codex":0.000046521316,"about_ca_system_score_gemma":0.00004905301,"threshold_uncertainty_score":0.9999732},"labels":[],"label_agreement":null},{"id":"W3134742627","doi":"10.1145/3431726","title":"Developing Cost-Effective Blockchain-Powered Applications","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Database transaction; Blockchain; Computer science; Smart contract; Flexibility (engineering); Transaction processing; Function (biology); Computer security; Unit price; Business; Database; Economics; Microeconomics","score_opus":0.051364331351637454,"score_gpt":0.3085804697335149,"score_spread":0.2572161383818774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134742627","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027441697,0.00055631634,0.99368733,0.0014696717,0.00020432232,0.00051775563,0.000008829729,0.0008009428,0.000010679432],"genre_scores_gemma":[0.05016787,0.00015409233,0.9475025,0.00031119576,0.000023235207,0.0017650661,0.000003529494,0.000015484105,0.00005704501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878323,0.0001356794,0.00019583532,0.0005259042,0.00008058714,0.00027873387],"domain_scores_gemma":[0.997121,0.0017565388,0.000041207186,0.00087571295,0.000118869895,0.00008668972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040040555,0.00017475411,0.00024946613,0.00019399454,0.0002534992,0.000030105355,0.000447851,0.00022299106,0.000008410342],"category_scores_gemma":[0.00039217746,0.00019218985,0.00006430527,0.0006752594,0.00005724444,0.000046162273,0.000048278256,0.00040052456,0.000010620454],"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":[0.000004126781,0.00007639649,0.00003562913,0.00003899014,0.00009473639,0.000012246431,0.00031713635,0.003357322,0.0010834546,0.16508995,0.000010249845,0.82987976],"study_design_scores_gemma":[0.003114535,0.00043862034,0.006600628,0.00018589829,0.00024255792,0.0024919664,0.0005139294,0.048438635,0.30701783,0.18152528,0.446648,0.0027821013],"about_ca_topic_score_codex":0.0000059029526,"about_ca_topic_score_gemma":0.000008074474,"teacher_disagreement_score":0.82709765,"about_ca_system_score_codex":0.0000568652,"about_ca_system_score_gemma":0.00007032733,"threshold_uncertainty_score":0.78372747},"labels":[],"label_agreement":null},{"id":"W3159568147","doi":"10.1145/3439769","title":"Automatic API Usage Scenario Documentation from Technical Q&amp;A Sites","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Polytechnique Montréal; University of Saskatchewan; University of Calgary","funders":"","keywords":"Documentation; Computer science; Internal documentation; Software documentation; Code (set theory); Application programming interface; World Wide Web; Coding (social sciences); Software engineering; Information retrieval; Software; Programming language; Software development; Software development process; Set (abstract data type); Software construction","score_opus":0.09554814590246685,"score_gpt":0.34831518452753624,"score_spread":0.2527670386250694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159568147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10530038,0.00044371036,0.89211535,0.00032272085,0.00050050725,0.00010074571,0.000010249118,0.0012037569,0.0000025513375],"genre_scores_gemma":[0.0971808,0.00010198564,0.9023282,0.00010345016,0.000043788998,0.000060104467,0.000016910151,0.000028291446,0.0001364675],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982625,0.00024453926,0.00027360077,0.0005760372,0.00026262057,0.00038067618],"domain_scores_gemma":[0.9898239,0.008938451,0.000033898003,0.00095328817,0.000080440965,0.00017004622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006204599,0.00022259956,0.00031357785,0.0002599735,0.00012740114,0.00013414622,0.00051154615,0.00019413355,0.00015343752],"category_scores_gemma":[0.0048154145,0.00023801223,0.000090760055,0.000577949,0.000042099782,0.00029856878,0.00006028517,0.00051497365,0.000049452683],"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":[0.00003437294,0.0004002766,0.0040152227,0.00036146733,0.00051243865,0.00038545695,0.0028876667,0.08049059,0.11153361,0.001982328,0.0004415512,0.796955],"study_design_scores_gemma":[0.009292007,0.0015704501,0.3334592,0.0014073609,0.0007282453,0.0048925783,0.00036824195,0.22497268,0.3436637,0.025545284,0.047096495,0.0070037656],"about_ca_topic_score_codex":0.000046775294,"about_ca_topic_score_gemma":0.000019626108,"teacher_disagreement_score":0.78995126,"about_ca_system_score_codex":0.00008991303,"about_ca_system_score_gemma":0.00007639908,"threshold_uncertainty_score":0.9705857},"labels":[],"label_agreement":null},{"id":"W3161148246","doi":"10.1145/3440757","title":"Predicting Performance Anomalies in Software Systems at Run-time","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","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":"IBM (Canada); Thompson Rivers University; Queen's University","funders":"","keywords":"Computer science; Baseline (sea); Precision and recall; Anomaly detection; Software; Recall; Anomaly (physics); Data mining; Software system; Machine learning; Real-time computing; Artificial intelligence; Operating system","score_opus":0.037587398814696533,"score_gpt":0.26188482445949596,"score_spread":0.22429742564479943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161148246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40091908,0.0007067738,0.59682375,0.00006139614,0.00090174365,0.00010855963,0.0000064844367,0.0004664991,0.000005707578],"genre_scores_gemma":[0.34496132,0.00031695698,0.65382683,0.00007215821,0.00007186301,0.000110172696,0.000006459156,0.000031482363,0.0006027178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979862,0.00028553288,0.00044868418,0.0006203381,0.00019871995,0.00046053316],"domain_scores_gemma":[0.99668276,0.002139213,0.00007071988,0.0008866529,0.00009876235,0.0001218696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010769569,0.000261471,0.00047133036,0.00024818195,0.00022493683,0.000059321854,0.00041951868,0.0002446628,0.00001698092],"category_scores_gemma":[0.0010586343,0.0002535907,0.00008642936,0.0005500342,0.000048496542,0.00035742714,0.00007185155,0.00038754204,0.0000291799],"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":[0.00010272997,0.0002670818,0.22206439,0.002120038,0.0002504009,0.00018528539,0.0046680593,0.5495487,0.0027005088,0.00022974193,0.000073417265,0.21778964],"study_design_scores_gemma":[0.0053434833,0.0014495515,0.3316766,0.0025071723,0.00019699485,0.005991844,0.00060173473,0.58864397,0.043786656,0.00038008371,0.01580919,0.0036127232],"about_ca_topic_score_codex":0.000038340415,"about_ca_topic_score_gemma":0.000010622896,"teacher_disagreement_score":0.21417692,"about_ca_system_score_codex":0.00013841054,"about_ca_system_score_gemma":0.000084983505,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W3162893202","doi":"10.1145/3447808","title":"How Should I Improve the UI of My App?","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Digital Marketing and Social Media","field":"Social Sciences","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":"Queen's University; Thompson Rivers University","funders":"","keywords":"Computer science; App store; Download; World Wide Web; Mobile apps; Perception; Internet privacy; User interface; Interface (matter); Human–computer interaction; Psychology","score_opus":0.10058065079683723,"score_gpt":0.33634803244965955,"score_spread":0.23576738165282232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162893202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05026668,0.0006571811,0.94095325,0.0052354597,0.0018902883,0.00013740097,0.000023124318,0.00023495217,0.00060166686],"genre_scores_gemma":[0.7979555,0.0006235017,0.19627564,0.0002442832,0.00025419163,0.000046074852,0.0000026116256,0.000026821635,0.0045713517],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898314,0.00037887305,0.000111121364,0.00016823129,0.00014624884,0.00021237772],"domain_scores_gemma":[0.9945376,0.005053404,0.000033981254,0.00021677188,0.00008206615,0.000076198485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011146981,0.00008976162,0.000200671,0.000045457582,0.00020948144,0.000043150114,0.00015668978,0.0001414373,0.000016076658],"category_scores_gemma":[0.008703862,0.00007506995,0.00008499504,0.00022912007,0.00018035159,0.000069063666,0.000007721779,0.00024057136,8.3852115e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037955066,0.00008723789,0.00023811037,0.00010037844,0.00017059047,0.000011224805,0.016825791,0.0005994582,0.0024817965,0.009703886,0.00011454498,0.96962905],"study_design_scores_gemma":[0.0022788942,0.0007050619,0.0074653863,0.00036154088,0.00067345105,0.00006398226,0.083595924,0.00028448022,0.056228623,0.022979714,0.8236226,0.0017403531],"about_ca_topic_score_codex":0.000103677354,"about_ca_topic_score_gemma":0.00008037155,"teacher_disagreement_score":0.96788865,"about_ca_system_score_codex":0.000018989887,"about_ca_system_score_gemma":0.000084098196,"threshold_uncertainty_score":0.99964625},"labels":[],"label_agreement":null},{"id":"W3184231327","doi":"10.1145/3447876","title":"An Empirical Study of the Impact of Data Splitting Decisions on the Performance of AIOps Solutions","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; École de Technologie Supérieure; Polytechnique Montréal; Queen's University","funders":"","keywords":"Computer science; Concept drift; Leakage (economics); Cloud computing; Data mining; Context (archaeology); Data science; TRACE (psycholinguistics); Data stream mining","score_opus":0.25840458878557626,"score_gpt":0.41697853064057805,"score_spread":0.1585739418550018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184231327","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":[0.4734015,0.000017386998,0.52633107,0.00004940678,0.000052943917,0.000062068364,0.00004313125,0.00004154245,9.623911e-7],"genre_scores_gemma":[0.5791912,0.000018860315,0.42076272,0.000007676166,0.000004333511,0.0000063199277,0.0000020857676,0.0000048848947,0.0000018995466],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986985,0.00043030368,0.00028413913,0.0002864558,0.00014996562,0.00015063521],"domain_scores_gemma":[0.99233097,0.0049189785,0.000092691655,0.002529755,0.000090732785,0.000036860423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012802304,0.0001090522,0.00023958922,0.000105590276,0.00012482915,0.000010659799,0.0014448971,0.000060440037,0.000004706066],"category_scores_gemma":[0.0021573007,0.00006819873,0.000061548104,0.00051928044,0.000065594155,0.00017426682,0.0001577104,0.00026174352,1.7123901e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012156897,0.0038352942,0.035930436,0.000112640926,0.0008398703,0.000009968004,0.012243101,0.23291692,0.022808412,0.0016020789,0.00030099048,0.6892787],"study_design_scores_gemma":[0.0013790688,0.0072006756,0.54005444,0.0007024916,0.00034077404,0.0002914001,0.0018704082,0.34124562,0.10475373,0.0012607101,0.00020558068,0.0006951144],"about_ca_topic_score_codex":0.00006921813,"about_ca_topic_score_gemma":0.0000087431235,"teacher_disagreement_score":0.6885836,"about_ca_system_score_codex":0.000014968256,"about_ca_system_score_gemma":0.00008928108,"threshold_uncertainty_score":0.27810636},"labels":[],"label_agreement":null},{"id":"W3203911409","doi":"10.1145/3465403","title":"CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Programming language; Semantics (computer science); Information retrieval; Natural language processing","score_opus":0.08444068339043621,"score_gpt":0.3254469426044706,"score_spread":0.2410062592140344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203911409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026840143,0.000071885624,0.97214204,0.0004359035,0.0002754653,0.00003149114,0.000035626363,0.00016249107,0.0000049643495],"genre_scores_gemma":[0.22739647,0.00006392599,0.7723173,0.00012313203,0.000018377006,0.0000061357127,0.000008211489,0.000013382537,0.000053042648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986451,0.0002875068,0.00028346872,0.0003753559,0.00017780733,0.00023071987],"domain_scores_gemma":[0.9970193,0.0020287333,0.00006268761,0.000744144,0.00005162985,0.00009350573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000974135,0.00015040238,0.00033362003,0.00019668035,0.00008455741,0.000032543878,0.00031837402,0.00010715902,0.000024807285],"category_scores_gemma":[0.0009481684,0.00015103168,0.00011582915,0.0004236758,0.000035936573,0.00008687891,0.00002868154,0.00031914702,0.0000022428528],"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":[0.00005660092,0.00031564874,0.0016391919,0.00033838314,0.00044292674,0.00024553324,0.0015809567,0.82831526,0.02255533,0.0018221135,0.00009979725,0.14258823],"study_design_scores_gemma":[0.0011877802,0.00043156772,0.0021745746,0.0003798483,0.00028949723,0.00021053125,0.00019786299,0.86411583,0.12676862,0.0009961968,0.00248377,0.00076389883],"about_ca_topic_score_codex":0.000037653022,"about_ca_topic_score_gemma":0.000014310111,"teacher_disagreement_score":0.20055634,"about_ca_system_score_codex":0.000020076377,"about_ca_system_score_gemma":0.00008877402,"threshold_uncertainty_score":0.6158893},"labels":[],"label_agreement":null},{"id":"W3203969037","doi":"10.1145/3470006","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Institut de Valorisation des Données","keywords":"Computer science; Metamodeling; Graph; Fault detection and isolation; Precision and recall; Construct (python library); Artificial intelligence; Deep learning; Artificial neural network; Machine learning; Software; Process (computing); Data mining; Software engineering; Theoretical computer science; Programming language","score_opus":0.08467335479524384,"score_gpt":0.3304131342028107,"score_spread":0.24573977940756686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203969037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05815283,0.00030524103,0.93943554,0.00007355867,0.0005763309,0.00026017881,0.0000028125007,0.0011928058,6.961164e-7],"genre_scores_gemma":[0.20234293,0.00005829395,0.79732466,0.000018934403,0.000028035622,0.00016943963,0.000005160486,0.00003044264,0.000022110838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998506,0.00018350866,0.00027496266,0.00041456654,0.00017774502,0.00044320914],"domain_scores_gemma":[0.99529034,0.003920874,0.00003741829,0.0004520511,0.00015993776,0.00013940882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071358227,0.00020908863,0.00027805014,0.00037375113,0.00031126334,0.00010548053,0.000299211,0.00017652145,0.000007292343],"category_scores_gemma":[0.0027797208,0.00023143638,0.00014089275,0.0007691299,0.000030832307,0.00030466105,0.000015782198,0.00046461844,0.0000024116766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005621251,0.00004349812,0.000056853398,0.0001930896,0.000086073145,0.0000066949765,0.000779035,0.22968996,0.0037312864,0.0001792065,5.0470743e-7,0.7652282],"study_design_scores_gemma":[0.0008128026,0.00033432763,0.0010400394,0.00009883134,0.00007732527,0.0004986106,0.00013871843,0.9637273,0.030389449,0.0009361421,0.001474694,0.00047173933],"about_ca_topic_score_codex":0.000012029276,"about_ca_topic_score_gemma":0.000008983628,"teacher_disagreement_score":0.76475644,"about_ca_system_score_codex":0.000070542505,"about_ca_system_score_gemma":0.000053672375,"threshold_uncertainty_score":0.9437702},"labels":[],"label_agreement":null},{"id":"W3209468076","doi":"10.1145/3530785","title":"On Wasted Contributions: Understanding the Dynamics of Contributor-Abandoned Pull Requests–A Mixed-Methods Study of 10 Large Open-Source Projects","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Carleton University; Concordia University","funders":"","keywords":"Computer science; Open source; Dynamics (music); Open source software; Management science; Operations research; Software; Economics; Sociology; Engineering; Programming language","score_opus":0.08502718441017452,"score_gpt":0.3720169809182515,"score_spread":0.286989796508077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209468076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06250479,0.00015906045,0.9352018,0.00019935588,0.0006392864,0.00089971913,0.000106463296,0.00028711546,0.0000023711789],"genre_scores_gemma":[0.7846876,0.000014758576,0.21480417,0.000026123731,0.000010976597,0.00031611114,0.000009840637,0.000033760913,0.0000966779],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960183,0.0020585887,0.00049801316,0.0005255041,0.00041111847,0.000488482],"domain_scores_gemma":[0.9746596,0.023755256,0.00016291236,0.0011529407,0.00016834404,0.00010093744],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062296283,0.0002543326,0.00059973256,0.0005101024,0.00047953776,0.00005515216,0.0015776842,0.000111522226,0.000026340456],"category_scores_gemma":[0.009136603,0.00022582112,0.00009811614,0.0012087743,0.000067097426,0.00014763547,0.0003013004,0.0008307709,6.3734416e-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":[0.0010441403,0.0030236032,0.0011915518,0.0003195352,0.0013900527,0.000052453528,0.011637604,0.84994066,0.002240482,0.06694833,0.000203311,0.06200829],"study_design_scores_gemma":[0.039326068,0.03426814,0.013549307,0.0007042861,0.00094360806,0.0009611695,0.037180617,0.8096212,0.03523298,0.019137641,0.005142118,0.003932873],"about_ca_topic_score_codex":0.00009770384,"about_ca_topic_score_gemma":0.000019768795,"teacher_disagreement_score":0.7221828,"about_ca_system_score_codex":0.00037952268,"about_ca_system_score_gemma":0.00011819132,"threshold_uncertainty_score":0.9992099},"labels":[],"label_agreement":null},{"id":"W3211925781","doi":"10.1145/3491211","title":"An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; University of Saskatchewan; Concordia University; University of Calgary","funders":"","keywords":"Computer science; Sentiment analysis; Software; Majority rule; Artificial intelligence; Machine learning; Empirical research; Detector; Data mining","score_opus":0.0814680668414065,"score_gpt":0.3610115127954521,"score_spread":0.2795434459540456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211925781","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":[0.46197155,0.000048391794,0.5370426,0.0000031613722,0.0003095055,0.0004171982,0.00009985208,0.00010771668,2.4605116e-8],"genre_scores_gemma":[0.70731795,0.0000028233042,0.29240024,0.000002847474,0.000009893187,0.00022996744,0.000009497179,0.00002545705,0.0000013470351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976015,0.0008576874,0.0003924439,0.0004697349,0.0003845737,0.00029407587],"domain_scores_gemma":[0.9866105,0.011886661,0.00009849531,0.0011968508,0.00011118587,0.00009632719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028702898,0.00020991536,0.00048011634,0.00036856276,0.00015476943,0.000020106056,0.0008719307,0.000086270724,0.000003538603],"category_scores_gemma":[0.0032968787,0.00019902569,0.00010303289,0.00068028504,0.000035001205,0.00028187092,0.00010197445,0.00038194313,7.496275e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028948864,0.00076020765,0.0016684423,0.0005159131,0.00018740456,0.0000036114943,0.0011648872,0.916549,0.045980323,0.000026987509,0.0000014693237,0.032852262],"study_design_scores_gemma":[0.0047292216,0.0109375855,0.1655333,0.0001794009,0.0002537319,0.00016829801,0.0006876738,0.100141846,0.71609926,0.00021412158,0.00026807585,0.000787482],"about_ca_topic_score_codex":0.00005360524,"about_ca_topic_score_gemma":0.0000048598845,"teacher_disagreement_score":0.81640714,"about_ca_system_score_codex":0.00008922373,"about_ca_system_score_gemma":0.000067766494,"threshold_uncertainty_score":0.8116032},"labels":[],"label_agreement":null},{"id":"W3211945175","doi":"10.1145/3488269","title":"Towards a Consistent Interpretation of AIOps Models","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Consistency (knowledge bases); Interpretation (philosophy); Computer science; Machine learning; Randomness; Consistency model; Artificial intelligence; Hyperparameter; Data mining; Econometrics; Statistics; Algorithm; Mathematics; Correctness","score_opus":0.09577591198243182,"score_gpt":0.316722677026575,"score_spread":0.22094676504414315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211945175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010767775,0.00017010841,0.99782765,0.000282966,0.00023699473,0.000056683082,0.000014916184,0.00031374002,0.000020150632],"genre_scores_gemma":[0.2043355,0.000110159854,0.7953929,0.000090090725,0.0000043994787,0.000026414798,0.0000042596307,0.0000065818613,0.000029702236],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991991,0.00013534613,0.00020408878,0.00025650626,0.000087820525,0.000117121424],"domain_scores_gemma":[0.998484,0.00072343927,0.0000472393,0.00058032596,0.00012033126,0.000044646218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033286994,0.00009400652,0.00019542674,0.0001345042,0.00003301829,0.000016782205,0.00025442487,0.00008276553,0.0000054611614],"category_scores_gemma":[0.0006452624,0.000098929384,0.000051187304,0.00023051893,0.000030996183,0.00018974375,0.000021163196,0.00014291577,9.713511e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022770151,0.00009831651,0.000014722834,0.00013883827,0.0001035873,0.000010990785,0.0015448686,0.050390124,0.01718625,0.05618871,0.000036165093,0.87426466],"study_design_scores_gemma":[0.00061791367,0.00027357403,0.0011311434,0.00017158568,0.00006722621,0.00033027923,0.00013680292,0.452937,0.5096563,0.032527372,0.0016794341,0.00047135903],"about_ca_topic_score_codex":0.000008072182,"about_ca_topic_score_gemma":0.0000012929029,"teacher_disagreement_score":0.8737933,"about_ca_system_score_codex":0.000022634058,"about_ca_system_score_gemma":0.00005656571,"threshold_uncertainty_score":0.40342233},"labels":[],"label_agreement":null},{"id":"W4205529760","doi":"10.1145/3502297","title":"Automated, Cost-effective, and Update-driven App Testing","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Centre National de la Recherche Scientifique; European Commission","keywords":"Computer science; Dependability; Oracle; Code coverage; Random testing; Android (operating system); Model-based testing; Test case; Cyclomatic complexity; Automation; Source code; Code (set theory); Test suite; Random oracle; Set (abstract data type); Software engineering; Distributed computing; Programming language; Machine learning; Software; Operating system; Encryption","score_opus":0.07249387697246641,"score_gpt":0.3145700562029212,"score_spread":0.24207617923045482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205529760","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072882213,0.00020533559,0.9714318,0.00017480724,0.00037602562,0.0003398768,0.00001107915,0.020168627,0.000004215806],"genre_scores_gemma":[0.13223872,0.000017789174,0.8669199,0.00022624858,0.000014770749,0.0005412533,0.000002128078,0.000023875284,0.000015324778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858165,0.00031597016,0.00018080814,0.00048065453,0.00013519713,0.00030570023],"domain_scores_gemma":[0.9937447,0.0055480124,0.00005342846,0.0005027465,0.00004240261,0.000108744985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362151,0.00019869095,0.00026246958,0.00029861947,0.00043262777,0.00005062777,0.0004202733,0.00007643141,0.000005814848],"category_scores_gemma":[0.0018799568,0.00021458021,0.000039991533,0.00048199054,0.0000453842,0.00012440058,0.00011068765,0.0004797727,0.000001913093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016301023,0.00006181917,0.001283349,0.000058806545,0.00005839098,0.00004247413,0.00051478035,0.072244704,0.00047880557,0.0005569091,0.00033100988,0.92435265],"study_design_scores_gemma":[0.0011216921,0.0012141243,0.008178595,0.00009766944,0.00008809091,0.0026213862,0.00003709484,0.96314836,0.002003675,0.008555774,0.01187808,0.0010554666],"about_ca_topic_score_codex":0.00004707457,"about_ca_topic_score_gemma":6.966669e-7,"teacher_disagreement_score":0.92329717,"about_ca_system_score_codex":0.000054292526,"about_ca_system_score_gemma":0.000027992406,"threshold_uncertainty_score":0.8750327},"labels":[],"label_agreement":null},{"id":"W4210455774","doi":"10.1145/3490489","title":"NPC: <u>N</u> euron <u>P</u> ath <u>C</u> overage via Characterizing Decision Logic of Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; JST-Mirai Program; National Satellite of Excellence in Trustworthy Software Systems, National University of Singapore; National Research Foundation; Bộ Giáo dục và Ðào tạo; Ministry of Education - Singapore; National Research Foundation Singapore; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Path (computing); Machine learning; Artificial neural network; Graph; Deep neural networks; Decision tree; Mirroring; Theoretical computer science","score_opus":0.039775669112155874,"score_gpt":0.2872848317002451,"score_spread":0.24750916258808922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210455774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021246033,0.00019409611,0.97610635,0.00019214941,0.0017845192,0.00012816956,0.0000038052156,0.00034188974,0.0000030145056],"genre_scores_gemma":[0.4561408,0.000020650441,0.5435538,0.00018490224,0.00003717035,0.000025116824,0.0000031635936,0.000022342147,0.000012036778],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796647,0.00054182525,0.00036079044,0.00051258417,0.0002429458,0.00037535623],"domain_scores_gemma":[0.9958001,0.0032437153,0.00013999139,0.0006787845,0.000038598344,0.000098860575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001120089,0.00024098688,0.00039945255,0.00031397876,0.00035233077,0.000026909083,0.000783697,0.000106438114,0.000056008408],"category_scores_gemma":[0.0006981738,0.0002582361,0.00012135541,0.0005090213,0.00003640595,0.00022555137,0.00017189348,0.000932238,9.679522e-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":[0.000040639126,0.000027689204,0.000095854426,0.000013239202,0.000023162327,0.000019364454,0.00033138078,0.73218757,0.0006120712,0.000453669,0.0000012955553,0.26619405],"study_design_scores_gemma":[0.0004793111,0.0003966028,0.002820571,0.000012636742,0.000030888765,0.00026389622,0.000029670437,0.99381423,0.00029002296,0.00068996113,0.00088204164,0.00029018102],"about_ca_topic_score_codex":0.000022926895,"about_ca_topic_score_gemma":0.0000019395425,"teacher_disagreement_score":0.43489477,"about_ca_system_score_codex":0.00006510452,"about_ca_system_score_gemma":0.000014479489,"threshold_uncertainty_score":0.999987},"labels":[],"label_agreement":null},{"id":"W4210647952","doi":"10.1145/3506695","title":"An Empirical Study of the Impact of Hyperparameter Tuning and Model Optimization on the Performance Properties of Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":198,"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 Alberta; Concordia University","funders":"","keywords":"Hyperparameter; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Inference; Hyperparameter optimization; Pruning; Deep learning; Support vector machine","score_opus":0.09199875935483277,"score_gpt":0.3210991654779176,"score_spread":0.22910040612308485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210647952","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":[0.48150855,0.000029252766,0.5182699,0.000030176267,0.000026967686,0.00011622214,9.924167e-7,0.000017848457,1.1440984e-7],"genre_scores_gemma":[0.81890506,0.000012214236,0.18099077,0.00002236297,0.0000036429767,0.000057255333,2.2256948e-7,0.0000072437733,0.0000012443344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917996,0.000268885,0.00017839392,0.00017143258,0.000095615105,0.00010570137],"domain_scores_gemma":[0.998641,0.00074404944,0.00007805795,0.00047926573,0.000033391378,0.000024248313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000303055,0.00009238294,0.00016494417,0.00006758331,0.00017595089,0.0000053469817,0.00036596303,0.00002694887,0.0000012807106],"category_scores_gemma":[0.000081059785,0.000057052588,0.00003903421,0.00031257252,0.000053514803,0.000088381654,0.000041692743,0.00025010962,7.638315e-9],"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":[0.000025509942,0.000081895945,0.00057876646,0.000005526494,0.000018518354,5.4497814e-8,0.0013680224,0.9850713,0.0006353149,0.00001698926,2.0915361e-7,0.012197881],"study_design_scores_gemma":[0.000129801,0.0006124711,0.0020879398,0.000005055383,0.000014770987,0.000011270202,0.00010461237,0.99625343,0.0007022023,0.000025788262,3.9234212e-7,0.000052240026],"about_ca_topic_score_codex":0.000009879298,"about_ca_topic_score_gemma":8.223881e-7,"teacher_disagreement_score":0.3373965,"about_ca_system_score_codex":0.000014263399,"about_ca_system_score_gemma":0.000008894861,"threshold_uncertainty_score":0.23265369},"labels":[],"label_agreement":null},{"id":"W4210772589","doi":"10.1145/3511887","title":"Towards Robustness of Deep Program Processing Models—Detection, Estimation, and Enhancement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":58,"is_retracted":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; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Robustness (evolution); Computer science; Source code; Source lines of code; Computer engineering; Machine learning; Artificial intelligence; Data mining; Software; Programming language","score_opus":0.048802842295263535,"score_gpt":0.3117413535294528,"score_spread":0.26293851123418926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210772589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004048022,0.00029129712,0.99423087,0.00007610066,0.00026750023,0.00025200032,0.0000027255207,0.0008291482,0.0000023361035],"genre_scores_gemma":[0.2885004,0.000035887395,0.71102744,0.000017407601,0.0000065881873,0.0003894841,8.121725e-7,0.000011847679,0.0000101377],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998953,0.00011976972,0.00024515588,0.00034457445,0.00015536128,0.00018214365],"domain_scores_gemma":[0.99917376,0.00027473771,0.000086058215,0.00032270022,0.00008525456,0.000057512036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004968109,0.00014453927,0.0002208801,0.0002794178,0.00026287072,0.00002233235,0.00024824069,0.00005852279,0.000006319774],"category_scores_gemma":[0.00018829595,0.00016034198,0.000034927827,0.00043069897,0.00004343105,0.0002833786,0.000051200754,0.0002697755,7.789501e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009043136,0.000030960095,4.4358714e-7,0.000045770197,0.000009154267,5.3971957e-7,0.000253717,0.40882817,0.0004147949,0.0001295562,3.320485e-7,0.59027755],"study_design_scores_gemma":[0.00023075883,0.0005435452,0.00003834805,0.000015576752,0.000019589143,0.00014073061,0.000069418325,0.9499051,0.04485534,0.0036239086,0.0003662766,0.00019138063],"about_ca_topic_score_codex":0.000010913241,"about_ca_topic_score_gemma":0.0000019576325,"teacher_disagreement_score":0.59008616,"about_ca_system_score_codex":0.000056943118,"about_ca_system_score_gemma":0.000028446564,"threshold_uncertainty_score":0.6538556},"labels":[],"label_agreement":null},{"id":"W4214849268","doi":"10.1145/3494516","title":"Buddy Stacks: Protecting Return Addresses with Efficient Thread-Local Storage and Runtime Re-Randomization","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Security and Verification in Computing","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":"Huawei Technologies (Canada)","funders":"Australian Research Council","keywords":"Computer science; Thread (computing); Pointer (user interface); Operating system; Call stack; Embedded system; Parallel computing; Computer hardware; Stack (abstract data type)","score_opus":0.05372739604091537,"score_gpt":0.2789406530306056,"score_spread":0.22521325698969025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214849268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06653862,0.00027009804,0.9320357,0.00021261552,0.00032426877,0.0002375391,0.000005587478,0.00037247813,0.0000031021982],"genre_scores_gemma":[0.52332664,0.000016696269,0.476453,0.000061104074,0.000019631763,0.00009321471,0.000002051136,0.0000133592375,0.000014313608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985611,0.00042953293,0.00019558391,0.0004231086,0.00017358379,0.00021708783],"domain_scores_gemma":[0.9971611,0.0022562628,0.00007562983,0.00038765892,0.000050044477,0.00006931094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012795711,0.00015252356,0.00022155773,0.00019931357,0.00065155234,0.0000577461,0.0002719907,0.000060067643,0.00001271449],"category_scores_gemma":[0.00045063964,0.00014851602,0.000030641142,0.00040182925,0.000049722355,0.00010017768,0.00004749133,0.0005064754,4.5115337e-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":[0.000116876436,0.00005619855,0.000056362755,0.000063879444,0.000048649526,0.000008492492,0.0041828095,0.9457206,0.0002680463,0.00094696635,0.000005173549,0.048525915],"study_design_scores_gemma":[0.003562158,0.0010509221,0.0010338046,0.0001224417,0.00008738776,0.00061293534,0.0018926273,0.9806956,0.006602874,0.0006631816,0.002894398,0.0007816533],"about_ca_topic_score_codex":0.000027775737,"about_ca_topic_score_gemma":0.000002694204,"teacher_disagreement_score":0.456788,"about_ca_system_score_codex":0.000047918995,"about_ca_system_score_gemma":0.000037860733,"threshold_uncertainty_score":0.60563076},"labels":[],"label_agreement":null},{"id":"W4220958110","doi":"10.1145/3487571","title":"Context- and Fairness-Aware In-Process Crowdworker Recommendation","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Mobile Crowdsensing and Crowdsourcing","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":"York University","funders":"National Key Research and Development Program of China; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Youth Innovation Promotion Association; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Popularity; Process (computing); Context (archaeology); Matching (statistics); Task (project management); Ranking (information retrieval); Recommender system; Software bug; Software; World Wide Web; Machine learning; Psychology","score_opus":0.0526966237025728,"score_gpt":0.2985543421583204,"score_spread":0.24585771845574758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220958110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09450905,0.00016143074,0.9039378,0.0005799676,0.00048900023,0.00008654939,0.0000050495173,0.0002263871,0.000004753652],"genre_scores_gemma":[0.8406336,0.000033166598,0.15893868,0.0002443972,0.000014538678,0.00007258345,0.0000030108977,0.000015454812,0.00004459256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988349,0.00024524622,0.00019394008,0.0003984623,0.00008997215,0.00023745376],"domain_scores_gemma":[0.99836993,0.0011902516,0.00004024091,0.000302915,0.00002573915,0.00007094782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008158898,0.00014640838,0.00021911287,0.00027024015,0.00027137282,0.00004453491,0.00022182091,0.00006594466,0.000027855449],"category_scores_gemma":[0.00023344126,0.00016331536,0.000032555956,0.00034430472,0.000027587603,0.00015173286,0.000038551672,0.00043755543,8.9861373e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033429747,0.00005569202,0.00084275566,0.00006404047,0.000030201221,0.000018462286,0.0027756745,0.08314765,0.00025308868,0.00071360037,0.000022069955,0.91204333],"study_design_scores_gemma":[0.011873093,0.0031497567,0.04370317,0.0006244107,0.0002708086,0.005406515,0.01660987,0.78655684,0.021720743,0.025286715,0.07912317,0.0056749373],"about_ca_topic_score_codex":0.000043041222,"about_ca_topic_score_gemma":0.000011119763,"teacher_disagreement_score":0.9063684,"about_ca_system_score_codex":0.000043306816,"about_ca_system_score_gemma":0.000024923025,"threshold_uncertainty_score":0.6659807},"labels":[],"label_agreement":null},{"id":"W4221142711","doi":"10.1145/3638243","title":"Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State of the Practice","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"Université de Montréal; Polytechnique Montréal","funders":"Université de Montréal; McMaster University; McGill University","keywords":"Workflow; Executable; Computer science; Domain (mathematical analysis); Software engineering; Subject-matter expert; Key (lock); Automation; Software; Data science; Domain engineering; Artificial intelligence; Knowledge management; Software development; Expert system; Component-based software engineering; Engineering; Programming language; Database","score_opus":0.20623520377135818,"score_gpt":0.4093535291417279,"score_spread":0.20311832537036972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221142711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022145344,0.0004279395,0.97323984,0.001518922,0.0022383498,0.00023536205,0.000034658653,0.00015699772,0.0000025822308],"genre_scores_gemma":[0.047189582,0.00015425691,0.9520117,0.00012538313,0.000055280798,0.00004327936,0.0000016375387,0.000017982109,0.00040087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787444,0.0005723436,0.00038900634,0.00045316142,0.00043219395,0.000278827],"domain_scores_gemma":[0.92473966,0.07400774,0.0001505382,0.0009309833,0.00012238746,0.000048666458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010192004,0.00013244821,0.00023416195,0.00023274083,0.0004847324,0.00010169125,0.0008480439,0.000060344326,0.000020130348],"category_scores_gemma":[0.024200017,0.00007830077,0.0001310837,0.0013466036,0.00017016259,0.00009486589,0.00008563215,0.00043382213,0.000009007726],"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":[0.00006216094,0.0000152378825,0.000043894208,0.000008456302,0.00006744925,0.0000013448251,0.0022823825,0.5468854,0.00014738715,0.006982749,0.00030754865,0.44319603],"study_design_scores_gemma":[0.00055971404,0.0001656314,0.002113741,0.000102115475,0.00008823622,0.00002885482,0.00425795,0.040569082,0.00071501086,0.056327034,0.89480317,0.00026946893],"about_ca_topic_score_codex":0.000016716784,"about_ca_topic_score_gemma":0.0000033173746,"teacher_disagreement_score":0.8944956,"about_ca_system_score_codex":0.000016324047,"about_ca_system_score_gemma":0.000018811881,"threshold_uncertainty_score":0.9840196},"labels":[],"label_agreement":null},{"id":"W4224214784","doi":"10.1145/3511598","title":"An Empirical Study on Data Distribution-Aware Test Selection for Deep Learning Enhancement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Retraining; Computer science; Artificial intelligence; Machine learning; Selection (genetic algorithm); Test data; Artificial neural network; Software deployment; Metric (unit); Data mining; Data set; Test set; Process (computing); Model selection; Deep learning; Distribution (mathematics); Set (abstract data type); Empirical research; Statistics; Mathematics; Engineering","score_opus":0.12392267985852783,"score_gpt":0.38876204613595167,"score_spread":0.2648393662774238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224214784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015580451,0.000023436647,0.9829394,0.0002634234,0.0002625925,0.00043429033,0.000059189977,0.0004368734,3.0028633e-7],"genre_scores_gemma":[0.49606165,0.0000111286,0.5029699,0.00009045655,0.000041883904,0.00066987413,0.00010854934,0.000017261595,0.000029277495],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850214,0.00026202615,0.00019123302,0.0006499662,0.00014348661,0.00025118203],"domain_scores_gemma":[0.99562395,0.00339508,0.00005180684,0.0008043034,0.000040674622,0.00008421118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006482058,0.00015169017,0.00017748166,0.00009816579,0.0007210692,0.00002907281,0.00070988486,0.000042429725,0.000009700846],"category_scores_gemma":[0.0005155624,0.00016603584,0.0000301459,0.00044031203,0.000014655976,0.00017518016,0.00006345774,0.0004545787,0.0000015203746],"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":[0.00003667355,0.0006674354,0.0012724008,0.000010560537,0.000041884698,0.0000016351673,0.0005973113,0.8083981,0.00072161516,0.00016337294,0.000045829398,0.18804318],"study_design_scores_gemma":[0.0009443067,0.0054059518,0.0057420395,0.0000074110385,0.000071913884,0.00007012738,0.0004330742,0.96110296,0.001751128,0.00053703587,0.023451958,0.00048208633],"about_ca_topic_score_codex":0.0000052305168,"about_ca_topic_score_gemma":0.0000058329297,"teacher_disagreement_score":0.4804812,"about_ca_system_score_codex":0.00009180562,"about_ca_system_score_gemma":0.000019233908,"threshold_uncertainty_score":0.6770745},"labels":[],"label_agreement":null},{"id":"W4224287853","doi":"10.1145/3508479","title":"Just-In-Time Defect Prediction on JavaScript Projects: A Replication Study","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"Queen's University","funders":"National Natural Science Foundation of China; National Research Foundation Singapore","keywords":"JavaScript; Computer science; Java; Unobtrusive JavaScript; Machine learning; Artificial intelligence; Replication (statistics); Java Programming Language; Natural language processing; Software engineering; Programming language; Rich Internet application","score_opus":0.10556455715455794,"score_gpt":0.3332004721546199,"score_spread":0.22763591500006197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224287853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25009552,0.00007616013,0.74777526,0.00011436005,0.00052756106,0.00053883117,0.000012123662,0.000857188,0.000003038229],"genre_scores_gemma":[0.7172199,0.000022123395,0.28097907,0.000109536355,0.00004369131,0.0013423096,0.0000072287867,0.000050718623,0.00022543683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9974254,0.00059048954,0.0002929982,0.00087275374,0.00042548872,0.0003928913],"domain_scores_gemma":[0.99441904,0.003932112,0.000041036998,0.0014678081,0.00004028674,0.00009972846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027939288,0.00021815613,0.000285561,0.0008540689,0.00023212234,0.000047971793,0.00079532654,0.00008326146,0.000022835264],"category_scores_gemma":[0.0032965597,0.00024170947,0.00008289549,0.0010318677,0.000018960727,0.00015997197,0.00008137375,0.000814827,0.000011524225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002618648,0.0017260688,0.017144285,0.00012724812,0.00029102253,0.0001212612,0.008028093,0.7979816,0.0024867987,0.0003994202,0.0002630596,0.17116924],"study_design_scores_gemma":[0.014264229,0.029544171,0.57302934,0.0003279083,0.00038691243,0.0019334966,0.0024946793,0.33824202,0.012432261,0.0014122619,0.021864021,0.004068676],"about_ca_topic_score_codex":0.00005201304,"about_ca_topic_score_gemma":0.0000021310098,"teacher_disagreement_score":0.5558851,"about_ca_system_score_codex":0.00024447573,"about_ca_system_score_gemma":0.000056089175,"threshold_uncertainty_score":0.9856626},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4225143092","doi":"10.1145/3533021","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Field (mathematics); Machine learning; Data mining; Artificial intelligence; Set (abstract data type); Data field; Software; Mathematics","score_opus":0.3306833255399733,"score_gpt":0.4220707860804389,"score_spread":0.09138746054046559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225143092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003516193,0.00016807271,0.99535877,0.00022941822,0.00021108949,0.00017547769,0.00019406037,0.00013723939,0.000009670572],"genre_scores_gemma":[0.29686266,0.000055593173,0.7024347,0.00009472036,0.0000108851955,0.00009923197,0.00018292986,0.000012479184,0.00024675843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983908,0.00036783918,0.000404708,0.0003978476,0.0002475862,0.0001912311],"domain_scores_gemma":[0.99391234,0.0053124633,0.000078216566,0.00063031766,0.000024620285,0.000042032807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005326908,0.00009919571,0.00030119144,0.00035483149,0.00014039484,0.00001883535,0.00071715965,0.00006303361,0.000053219243],"category_scores_gemma":[0.004852156,0.00008775925,0.000048684553,0.0004366402,0.00002259414,0.00012277426,0.00012441057,0.00035242477,5.0618513e-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":[0.00009696207,0.000111046225,0.00012560481,0.000057461028,0.000044952674,0.0000024974968,0.00065658905,0.9154909,0.000033208238,0.0008473601,0.00021756567,0.08231585],"study_design_scores_gemma":[0.00077335804,0.00022526475,0.00029985566,0.0000051987563,0.000039900013,0.000023901353,0.00090095244,0.96240747,0.00011190363,0.002630606,0.032416694,0.00016490715],"about_ca_topic_score_codex":0.000098790944,"about_ca_topic_score_gemma":0.000016622393,"teacher_disagreement_score":0.29334646,"about_ca_system_score_codex":0.000022831644,"about_ca_system_score_gemma":0.000020058358,"threshold_uncertainty_score":0.5808835},"labels":[],"label_agreement":null},{"id":"W4225163285","doi":"10.1145/3522587","title":"There’s no Such Thing as a Free Lunch: Lessons Learned from Exploring the Overhead Introduced by the Greenkeeper Dependency Bot in Npm","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Computer science; Dependency (UML); Overhead (engineering); Process (computing); Computer security; Pipeline (software); Action (physics); Software; Software engineering; Risk analysis (engineering); Process management","score_opus":0.17598726110486262,"score_gpt":0.33581605162678857,"score_spread":0.15982879052192595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225163285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19146061,0.00082811556,0.8008426,0.0047672177,0.0013583332,0.00024054365,0.000030739593,0.0004657474,0.0000061340406],"genre_scores_gemma":[0.7362334,0.00043990748,0.2609726,0.00046491256,0.00017940388,0.0011610441,0.000009253377,0.00010154003,0.00043795363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968441,0.0009042315,0.00032751556,0.0007573855,0.0005314188,0.0006353478],"domain_scores_gemma":[0.9818986,0.015954126,0.000053267428,0.001924088,0.000054357868,0.00011556416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026162958,0.00030473561,0.00034613707,0.00027668613,0.0005903894,0.000116816394,0.0024160948,0.000103539736,0.000099470526],"category_scores_gemma":[0.0056458656,0.00023736019,0.00011499049,0.0007917978,0.000063298765,0.0002987924,0.0003119506,0.0019654345,0.000015774087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022979568,0.0003073474,0.0017877083,0.00008334593,0.0005059034,0.00013555013,0.024693478,0.36052758,0.011035305,0.0033207706,0.00091298623,0.5964602],"study_design_scores_gemma":[0.025191246,0.0072368267,0.18921952,0.0010476264,0.0008823743,0.0033384885,0.01789392,0.32410207,0.081470005,0.124175794,0.21248336,0.012958758],"about_ca_topic_score_codex":0.0015657279,"about_ca_topic_score_gemma":0.00007491162,"teacher_disagreement_score":0.58350146,"about_ca_system_score_codex":0.00017420082,"about_ca_system_score_gemma":0.00009628856,"threshold_uncertainty_score":0.96792674},"labels":[],"label_agreement":null},{"id":"W4280562623","doi":"10.1145/3529318","title":"Testing Feedforward Neural Networks Training Programs","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Debugging; Hyperparameter; Artificial neural network; Machine learning; Artificial intelligence; Software; Deep neural networks; Training (meteorology); Deep learning; Test data; Software engineering; Programming language","score_opus":0.1199166601035608,"score_gpt":0.30557276794227944,"score_spread":0.18565610783871866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280562623","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012107315,0.000103365026,0.98520815,0.00020660697,0.0012916483,0.00012642404,0.0000012943827,0.0009487499,0.000006454764],"genre_scores_gemma":[0.36492407,0.0000018494469,0.6347962,0.0001026654,0.000051785773,0.000075532414,0.0000018598754,0.000020476578,0.000025532281],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983522,0.00039626446,0.00021479474,0.0004413713,0.00016920977,0.00042610287],"domain_scores_gemma":[0.9966026,0.0027538172,0.00006471489,0.00044611024,0.000028962964,0.00010380906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011399346,0.00019238543,0.00026317145,0.00019787553,0.0005564573,0.000053659776,0.00064142124,0.00007248984,0.000013255009],"category_scores_gemma":[0.0011357486,0.00021317386,0.00007092976,0.00063799013,0.000034062905,0.00016378771,0.000097196666,0.000988218,6.3184626e-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":[0.000005277064,0.000010182058,0.00014343623,0.000005663767,0.00001630712,0.0000110966685,0.00063002744,0.6088197,0.000030300227,0.0002649167,0.0000010366241,0.39006203],"study_design_scores_gemma":[0.00031488694,0.00030664194,0.0007965143,0.000010486054,0.00002237314,0.00035495602,0.00020509968,0.9963505,0.000014955956,0.00032066877,0.0010421491,0.00026071764],"about_ca_topic_score_codex":0.00002724339,"about_ca_topic_score_gemma":0.0000010143174,"teacher_disagreement_score":0.3898013,"about_ca_system_score_codex":0.000051456525,"about_ca_system_score_gemma":0.000027852902,"threshold_uncertainty_score":0.86929774},"labels":[],"label_agreement":null},{"id":"W4282033849","doi":"10.1145/3542944","title":"Towards Learning Generalizable Code Embeddings Using Task-agnostic Graph Convolutional Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Concordia University","funders":"","keywords":"Computer science; Source code; Downstream (manufacturing); Graph; Benchmarking; Code (set theory); Abstract syntax; Embedding; Task (project management); Artificial intelligence; Syntax; Theoretical computer science; Programming language","score_opus":0.07716174346765048,"score_gpt":0.31820709951536275,"score_spread":0.24104535604771227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282033849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028984671,0.00076775247,0.9677242,0.000115821735,0.0012899975,0.0001474193,0.000015544965,0.0009529143,0.0000016894031],"genre_scores_gemma":[0.23197088,0.000086864435,0.7674868,0.00010620759,0.00006477505,0.00011452458,0.000008925,0.000047167658,0.000113842165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766415,0.00042569687,0.00028203562,0.0006130066,0.00037554355,0.0006395507],"domain_scores_gemma":[0.9946135,0.004514094,0.000057424426,0.00054274674,0.000078214405,0.0001940039],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014344231,0.0002684337,0.0003422294,0.00054490496,0.0006691351,0.00007006585,0.00076348626,0.00012595652,0.00006615728],"category_scores_gemma":[0.0022411535,0.00031717497,0.00011773215,0.0009161876,0.000059099202,0.00019506115,0.00014876097,0.0011654978,0.0000026599826],"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":[0.000012886602,0.000030214755,0.00042353748,0.000024045567,0.00006902117,0.000024861705,0.00028325693,0.98901826,0.0005309579,0.00070663664,0.000039826427,0.008836485],"study_design_scores_gemma":[0.0005618735,0.00031058953,0.0014967088,0.000027647922,0.000041638927,0.00060974696,0.000048823826,0.9884799,0.00048380607,0.00049212936,0.0069433954,0.0005037421],"about_ca_topic_score_codex":0.000107495565,"about_ca_topic_score_gemma":0.0000015260645,"teacher_disagreement_score":0.20298621,"about_ca_system_score_codex":0.00019098182,"about_ca_system_score_gemma":0.00010572752,"threshold_uncertainty_score":0.99992806},"labels":[],"label_agreement":null},{"id":"W4283323653","doi":"10.1145/3544790","title":"Toward More Efficient Statistical Debugging with Abstraction Refinement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Office of Naval Research; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; National Science Foundation","keywords":"Debugging; Computer science; Algorithmic program debugging; Abstraction; Programming language; Pruning; Discriminative model; Software engineering; Machine learning","score_opus":0.07935506400377887,"score_gpt":0.3095148429020107,"score_spread":0.23015977889823183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283323653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063918293,0.00008663412,0.98712695,0.00052350835,0.00035850628,0.00012473846,0.0000141272885,0.005368729,0.000004986016],"genre_scores_gemma":[0.26329795,0.0000060098787,0.73634857,0.00016065703,0.000011977306,0.00013402024,0.0000038340577,0.000017554092,0.000019462737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986384,0.00015710252,0.00019670809,0.000448713,0.00025673152,0.000302352],"domain_scores_gemma":[0.9969836,0.00231218,0.000053653745,0.0005104115,0.000037998576,0.00010217881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007447452,0.00018522413,0.00021688761,0.00025985632,0.00033222753,0.00003808599,0.00035919854,0.000050880164,0.000027064225],"category_scores_gemma":[0.0005104965,0.00017569173,0.00003730339,0.00030877814,0.000039014558,0.000057521214,0.000049257185,0.00048338983,0.0000017485116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008148706,0.00019694622,0.0002006106,0.000080879465,0.00009565078,0.00011800372,0.0015820382,0.61358434,0.00020808131,0.002275776,0.00030117884,0.38127497],"study_design_scores_gemma":[0.0040839524,0.006481241,0.0201584,0.0003280176,0.00043440424,0.0077139204,0.00054933224,0.9129737,0.00818372,0.015292321,0.020279462,0.0035215353],"about_ca_topic_score_codex":0.00006889672,"about_ca_topic_score_gemma":7.603506e-7,"teacher_disagreement_score":0.37775344,"about_ca_system_score_codex":0.000096514355,"about_ca_system_score_gemma":0.000051157,"threshold_uncertainty_score":0.7164501},"labels":[],"label_agreement":null},{"id":"W4284962442","doi":"10.1145/3546941","title":"Estimating Probabilistic Safe WCET Ranges of Real-Time Systems at Design Stages","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Real-Time Systems Scheduling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; Université du Luxembourg","keywords":"Computer science; Probabilistic logic; Worst-case execution time; Scheduling (production processes); Task (project management); Set (abstract data type); Execution time; Point (geometry); Real-time computing; Distributed computing; Mathematical optimization; Artificial intelligence; Programming language; Systems engineering","score_opus":0.07499825737973446,"score_gpt":0.29155091299379854,"score_spread":0.21655265561406406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284962442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022777924,0.0002914059,0.97509223,0.00006109589,0.00092743756,0.00038253985,0.000018029617,0.00044027748,0.0000090668345],"genre_scores_gemma":[0.087158814,0.00001826475,0.91230005,0.000007945617,0.000030671632,0.00021255366,0.0000027078706,0.00002993154,0.00023905374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739116,0.0010873105,0.00044679118,0.00048013913,0.00026150316,0.00033310844],"domain_scores_gemma":[0.9929574,0.005955323,0.00016146149,0.0007617345,0.00006289232,0.00010118521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026869052,0.00021924985,0.00051470136,0.00028850595,0.00029380037,0.00003669367,0.00059319194,0.000087695174,0.000027298878],"category_scores_gemma":[0.0010749383,0.0002277572,0.00007858717,0.00037350866,0.000041977484,0.00014985986,0.00007796393,0.00027767202,0.00000529386],"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":[0.000022522185,0.000027219812,0.00002260723,0.00021337552,0.0000618464,0.00001076367,0.00083319924,0.97919893,0.01225448,0.00032439618,0.000018071074,0.007012611],"study_design_scores_gemma":[0.00081384694,0.00076472486,0.00033412807,0.0001650032,0.00009453288,0.0007802627,0.00015644402,0.9882744,0.007267309,0.00046147613,0.00031567534,0.00057218753],"about_ca_topic_score_codex":0.00012474835,"about_ca_topic_score_gemma":7.0529137e-7,"teacher_disagreement_score":0.06438089,"about_ca_system_score_codex":0.00013830517,"about_ca_system_score_gemma":0.000061996376,"threshold_uncertainty_score":0.9287669},"labels":[],"label_agreement":null},{"id":"W4285394558","doi":"10.1145/3546945","title":"Assessing the Alignment between the Information Needs of Developers and the Documentation of Programming Languages: A Case Study on Rust","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Documentation; Computer science; Technical documentation; Application programming interface; World Wide Web; Internal documentation; Set (abstract data type); Baseline (sea); Software engineering; Information retrieval; Programming language; Software development; Software","score_opus":0.0778948728389709,"score_gpt":0.3699735239963255,"score_spread":0.2920786511573546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285394558","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":[0.39467096,0.00005272422,0.6046076,0.00024822028,0.000073660645,0.00029685174,0.000002296306,0.000047179998,5.256958e-7],"genre_scores_gemma":[0.900213,0.000007032331,0.09952904,0.000038117134,0.0000075933985,0.00019330389,0.0000010877884,0.00000695007,0.000003842263],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99870986,0.00054164644,0.0002497737,0.00009559322,0.0002547025,0.0001484408],"domain_scores_gemma":[0.9900439,0.009408448,0.00007820702,0.00040269337,0.000040190218,0.000026583266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029470914,0.00010433453,0.00016995364,0.0002138606,0.00032924683,0.000072604664,0.00037503452,0.000027106356,0.0000022728264],"category_scores_gemma":[0.0009775136,0.00006170666,0.00003584849,0.0005391135,0.00007919771,0.00022305611,0.000067172776,0.00032653843,1.6523754e-7],"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":[0.000042083724,0.00008075553,0.004570402,0.00009321121,0.00033158448,0.00001605865,0.11743307,0.14401256,0.00007106596,0.0007372022,0.0000063235025,0.7326057],"study_design_scores_gemma":[0.012353226,0.004745602,0.17048112,0.0002550015,0.00086248654,0.0038129208,0.7659271,0.026806006,0.008034971,0.00046634892,0.00481593,0.0014393433],"about_ca_topic_score_codex":0.00024358263,"about_ca_topic_score_gemma":0.0000018532271,"teacher_disagreement_score":0.73116636,"about_ca_system_score_codex":0.000039961626,"about_ca_system_score_gemma":0.00003282438,"threshold_uncertainty_score":0.25323337},"labels":[],"label_agreement":null},{"id":"W4285794979","doi":"10.1145/3549542","title":"Is My Transaction Done Yet? An Empirical Study of Transaction Processing Times in the Ethereum Blockchain Platform","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Database transaction; Computer science; Transaction processing system; Blockchain; Transaction processing; Online transaction processing; Distributed transaction; Transaction cost; Computer security; Database; Business; Finance","score_opus":0.07742992799670803,"score_gpt":0.3326076058421708,"score_spread":0.25517767784546275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285794979","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":[0.41808978,0.000076410615,0.58073115,0.00061170623,0.00008837499,0.00023797742,0.000004661983,0.00015864627,0.000001302166],"genre_scores_gemma":[0.87754893,0.000016127653,0.12191954,0.00014248834,0.000008333994,0.00033957383,0.0000014009073,0.000014441354,0.000009154291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824107,0.00043098346,0.0003471044,0.0004669014,0.00023468427,0.00027927084],"domain_scores_gemma":[0.9982745,0.0008644889,0.00007892472,0.00069612276,0.000034833894,0.000051130177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018731194,0.00018531957,0.00030327053,0.00042053437,0.00037970033,0.000020905964,0.0007287504,0.00015512484,0.000023229404],"category_scores_gemma":[0.00005444748,0.00016624105,0.0000632236,0.000931094,0.00005359971,0.00013416923,0.000013826465,0.00086935045,4.3189775e-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":[0.00020696248,0.0039100708,0.0009631036,0.000120336306,0.00015370104,0.000019494086,0.10752653,0.17753275,0.0016981811,0.0010487945,0.000017437502,0.70680267],"study_design_scores_gemma":[0.011072767,0.01417346,0.032210603,0.00011558583,0.0005876803,0.0018376121,0.074471235,0.8059274,0.022262936,0.02785406,0.0067743636,0.0027122716],"about_ca_topic_score_codex":0.00012866205,"about_ca_topic_score_gemma":0.00006571979,"teacher_disagreement_score":0.70409036,"about_ca_system_score_codex":0.00006646071,"about_ca_system_score_gemma":0.000041424617,"threshold_uncertainty_score":0.67791134},"labels":[],"label_agreement":null},{"id":"W4286485305","doi":"10.1145/3550271","title":"Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":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; Université du Luxembourg","keywords":"Computer science; Cluster analysis; Retraining; Black box; Deep neural networks; Artificial intelligence; Machine learning; Artificial neural network; Feature (linguistics); Root (linguistics); Root cause; Pattern recognition (psychology); Reliability engineering","score_opus":0.037010912796732284,"score_gpt":0.30333438913844046,"score_spread":0.26632347634170817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286485305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013571545,0.00006847094,0.98544735,0.00037665496,0.00027878067,0.00007699127,0.000012147051,0.00015995771,0.000008102322],"genre_scores_gemma":[0.4433632,0.000022114453,0.5565005,0.000056899513,0.000011823807,0.000008739206,0.0000028013353,0.00001006408,0.000023857809],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867797,0.00037701128,0.00018542164,0.00041111888,0.00016060812,0.00018786934],"domain_scores_gemma":[0.996607,0.0028501668,0.00008395717,0.00036411828,0.000023521588,0.000071254406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001109311,0.00016096508,0.0003258088,0.0005673286,0.0002842367,0.000022631055,0.00020386578,0.00009556683,0.000020391555],"category_scores_gemma":[0.0005997974,0.00017591046,0.00006912712,0.0006579805,0.000050627033,0.00011865473,0.00004996445,0.0006688587,9.9950725e-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":[0.00006143429,0.000015889531,0.00042440573,0.000037028374,0.00010807855,0.000006406145,0.0010599467,0.92593163,0.0005137939,0.00018233215,0.0000014105358,0.07165764],"study_design_scores_gemma":[0.00050235837,0.00027489982,0.0104453,0.00002162647,0.00017903392,0.00005080654,0.0002258781,0.9870867,0.00046396223,0.00007892297,0.00046033002,0.0002101422],"about_ca_topic_score_codex":0.000029754332,"about_ca_topic_score_gemma":0.000006607719,"teacher_disagreement_score":0.42979163,"about_ca_system_score_codex":0.000043009986,"about_ca_system_score_gemma":0.000019118148,"threshold_uncertainty_score":0.717342},"labels":[],"label_agreement":null},{"id":"W4286488146","doi":"10.1145/3550270","title":"Parameter Coverage for Testing of Autonomous Driving Systems under Uncertainty","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; JST-Mirai Program; European Regional Development Fund; Japan Science and Technology Agency; University of Waterloo; Exploratory Research for Advanced Technology; Science Foundation Ireland","keywords":"Computer science; Correctness; Heuristics; Trustworthiness; Process (computing); Cover (algebra); Operations research; Reliability engineering; Mathematical optimization; Risk analysis (engineering); Algorithm; Computer security","score_opus":0.10734772623091261,"score_gpt":0.3267423154097948,"score_spread":0.21939458917888222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286488146","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047853246,0.00017561267,0.9510717,0.00010569228,0.00036723408,0.00018923823,0.000019913878,0.00021616883,0.0000012189192],"genre_scores_gemma":[0.4478139,0.000011368639,0.5519018,0.000031937805,0.000012545471,0.0001633597,0.000002100307,0.000010981441,0.000051997653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985334,0.00034369595,0.0002794736,0.00037564998,0.00018400639,0.00028372632],"domain_scores_gemma":[0.98333883,0.01590977,0.00006571726,0.0005229283,0.00008742582,0.00007530549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016103655,0.00013078765,0.00032977303,0.0002630632,0.00026543846,0.00003567729,0.00047375078,0.00006436862,0.000008000967],"category_scores_gemma":[0.0029137349,0.00013388325,0.0001142335,0.0004825775,0.000036562713,0.000088345856,0.00005402951,0.000313057,4.2202475e-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":[0.000009086564,0.0000411814,0.0002271737,0.00007705827,0.00007115202,0.0000015448672,0.00016700807,0.9334105,0.00046621225,0.00074416667,0.0000039006786,0.06478102],"study_design_scores_gemma":[0.0006212847,0.0006940136,0.0009816682,0.000040280964,0.000064758555,0.00010126102,0.00016523007,0.98951334,0.0010351263,0.0035688258,0.0028710295,0.00034319537],"about_ca_topic_score_codex":0.000105493404,"about_ca_topic_score_gemma":0.0000016576896,"teacher_disagreement_score":0.39996067,"about_ca_system_score_codex":0.000086542015,"about_ca_system_score_gemma":0.00007531814,"threshold_uncertainty_score":0.54596007},"labels":[],"label_agreement":null},{"id":"W4287378204","doi":"10.1145/3533700","title":"The Co-evolution of the WordPress Platform and Its Plugins","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal; Queen's University","funders":"","keywords":"Plug-in; Computer science; Software; World Wide Web; Software engineering; Operating system","score_opus":0.05189968053057521,"score_gpt":0.2961285702044682,"score_spread":0.244228889673893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287378204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01510076,0.0005269924,0.98320407,0.00028859312,0.00047022215,0.00013713237,0.000008414242,0.00026057684,0.000003235343],"genre_scores_gemma":[0.66031736,0.00013677392,0.33920994,0.000047690446,0.000011410841,0.00013423996,2.5659182e-7,0.000011681563,0.00013065492],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927974,0.00014074276,0.00012461362,0.0001882563,0.00011823148,0.00014839592],"domain_scores_gemma":[0.99782646,0.0016483389,0.000055074495,0.00041154728,0.000027697015,0.000030891784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057626906,0.000090717534,0.00011590109,0.00009382603,0.0005101147,0.000012651096,0.00045028885,0.000042704985,0.0000027756446],"category_scores_gemma":[0.00037686876,0.00006680091,0.000040810715,0.00026421895,0.000047049285,0.00010814849,0.000064232736,0.00033548052,1.8384071e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011476581,0.00008581316,0.0002108151,0.000099232944,0.00015474747,0.000004785275,0.0023650862,0.18933879,0.015960509,0.067233905,0.000099791054,0.72433174],"study_design_scores_gemma":[0.0025338822,0.0022735877,0.018578943,0.00013064868,0.00017660853,0.0019097357,0.0013891797,0.12339233,0.5870754,0.06371917,0.19713975,0.0016807519],"about_ca_topic_score_codex":0.000010060092,"about_ca_topic_score_gemma":0.000003929531,"teacher_disagreement_score":0.722651,"about_ca_system_score_codex":0.000055765744,"about_ca_system_score_gemma":0.000022693917,"threshold_uncertainty_score":0.39234415},"labels":[],"label_agreement":null},{"id":"W4288363128","doi":"10.1145/3306607","title":"Status Quo in Requirements Engineering","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Bundesministerium für Wissenschaft, Forschung und Wirtschaft; Eesti Teadusagentuur; Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung","keywords":"Computer science; Requirements engineering; Context (archaeology); Non-functional requirement; Process (computing); Management science; Requirements elicitation; Empirical research; Status quo; Software engineering; Software development; Software; Engineering; Software construction","score_opus":0.08131317937373102,"score_gpt":0.32950755697898276,"score_spread":0.24819437760525176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288363128","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05038486,0.00028283597,0.9470535,0.000110646826,0.0009675346,0.00017851056,0.0000033383112,0.0010085965,0.000010163177],"genre_scores_gemma":[0.16110215,0.00020313585,0.8384516,0.00007993611,0.000019507615,0.00004822896,0.0000014892875,0.000028604127,0.00006529963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985655,0.00008632813,0.00026679892,0.00045658633,0.00015086624,0.0004739384],"domain_scores_gemma":[0.9968091,0.0022662843,0.00004464957,0.00072968233,0.000026999187,0.00012326404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007491313,0.00023566048,0.00030704317,0.0004671409,0.000035247507,0.000051920197,0.0004690724,0.00016465328,0.000025596806],"category_scores_gemma":[0.0008674719,0.00025229287,0.000060016326,0.00045508766,0.000010414622,0.00043242166,0.000038060876,0.00048049729,0.000018838049],"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":[0.00008331933,0.0002182829,0.009497006,0.0005045619,0.00022149915,0.0000892187,0.0020977648,0.64125866,0.007453082,0.0126537625,0.0000632033,0.3258596],"study_design_scores_gemma":[0.008034631,0.00359686,0.1281446,0.0015309387,0.00018504212,0.00093861576,0.00022865928,0.5731083,0.052877866,0.0059895916,0.2190528,0.0063120765],"about_ca_topic_score_codex":0.00006413155,"about_ca_topic_score_gemma":0.0000027718786,"teacher_disagreement_score":0.31954753,"about_ca_system_score_codex":0.00007292988,"about_ca_system_score_gemma":0.000028392338,"threshold_uncertainty_score":0.9999929},"labels":[],"label_agreement":null},{"id":"W4293235851","doi":"10.1145/3517193","title":"Bash in the Wild: Language Usage, Code Smells, and Bugs","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Security and Verification in Computing","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scripting language; Programming language; Unix; Software","score_opus":0.07204278200437231,"score_gpt":0.31282443255324427,"score_spread":0.24078165054887196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293235851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06888196,0.00040884773,0.9294396,0.00073578075,0.0003156258,0.00007553064,0.000006088084,0.00012831685,0.000008261048],"genre_scores_gemma":[0.50178844,0.00005806246,0.4974373,0.00061037514,0.000019931244,0.000045055545,0.0000013829682,0.0000068718773,0.000032574488],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898237,0.0003799972,0.00012840753,0.0002489331,0.0001013373,0.00015895665],"domain_scores_gemma":[0.9970285,0.0025327613,0.00002471541,0.00037360398,0.000008372011,0.00003202425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012664534,0.000087657376,0.000118098855,0.00014747572,0.00022924198,0.00003496426,0.00044210593,0.000038634775,0.000011980784],"category_scores_gemma":[0.00024480402,0.000081282466,0.000024639206,0.00032288127,0.000024536821,0.00007170132,0.000036753674,0.00039299877,8.614764e-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":[0.000036280395,0.00023958711,0.00090840744,0.000118388925,0.00007375808,0.00007921386,0.0624819,0.17395517,0.0013389149,0.019237734,0.00018749763,0.74134314],"study_design_scores_gemma":[0.0049730195,0.0017228835,0.047114708,0.00014977962,0.00014953065,0.0040587666,0.014257102,0.7029016,0.007670799,0.012204571,0.20218197,0.0026152716],"about_ca_topic_score_codex":0.000039140174,"about_ca_topic_score_gemma":0.000007432993,"teacher_disagreement_score":0.73872787,"about_ca_system_score_codex":0.000018315372,"about_ca_system_score_gemma":0.00001539804,"threshold_uncertainty_score":0.3314603},"labels":[],"label_agreement":null},{"id":"W4293452506","doi":"10.1145/3560263","title":"TokenAware: Accurate and Efficient Bookkeeping Recognition for Token Smart Contracts","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Key Research and Development Program of China; Natural Science Foundation of Sichuan Province; National Natural Science Foundation of China","keywords":"Bookkeeping; Security token; Computer science; Overhead (engineering); Distributed computing; Transfer (computing); Artificial intelligence; Computer security; Programming language; Operating system; Accounting","score_opus":0.06725597527650143,"score_gpt":0.288131035906911,"score_spread":0.2208750606304096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293452506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052245907,0.00031884323,0.94538605,0.0009705943,0.00032532107,0.00029883007,0.000034369852,0.0004177109,0.0000023522161],"genre_scores_gemma":[0.319953,0.00006546372,0.67905414,0.00029055917,0.0000132711875,0.00058756355,0.0000063812213,0.000011977144,0.000017618046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990422,0.00010957397,0.00017477151,0.00036977683,0.00006950134,0.00023416313],"domain_scores_gemma":[0.9976413,0.0018441662,0.000050335715,0.0003594004,0.00003978254,0.00006499344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081964384,0.00012494356,0.0001892695,0.00019790827,0.00046005766,0.000024667675,0.0002730802,0.00009270008,0.000006678497],"category_scores_gemma":[0.00037372453,0.00014090646,0.00004376127,0.00020651352,0.0000372739,0.00005780339,0.000045528304,0.00031935645,8.72607e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006479121,0.00016236534,0.000038994167,0.00007792838,0.000109051754,0.000006919781,0.001328382,0.048665717,0.0017432817,0.0114795435,0.00006439997,0.9362586],"study_design_scores_gemma":[0.005723753,0.0021441206,0.0040231794,0.000092368966,0.0002915907,0.0015376603,0.0007274473,0.78732747,0.03419569,0.049533572,0.11221583,0.0021873207],"about_ca_topic_score_codex":0.000013748874,"about_ca_topic_score_gemma":0.0000021486,"teacher_disagreement_score":0.9340713,"about_ca_system_score_codex":0.000026592774,"about_ca_system_score_gemma":0.00002173802,"threshold_uncertainty_score":0.57459986},"labels":[],"label_agreement":null},{"id":"W4296132134","doi":"10.1145/3563214","title":"Video Game Bad Smells: What They Are and How Developers Perceive Them","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Game Developer; Video game development; Video game; Code smell; Relevance (law); Game design; Game development tool; Game testing; Animation; World Wide Web; Software; Game art design; Software development; Game design document; Multimedia; Data science; Software quality","score_opus":0.08737181515015419,"score_gpt":0.29583185583088095,"score_spread":0.20846004068072677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296132134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088440016,0.0008099191,0.90743685,0.0016144825,0.00086187373,0.00016606768,0.000010741641,0.00065867195,0.0000013964343],"genre_scores_gemma":[0.43709904,0.000668364,0.5615782,0.00018932058,0.000031450225,0.00017182302,0.0000020979553,0.000043374406,0.0002163369],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99804616,0.0003651651,0.00015409729,0.0006439554,0.0003029224,0.00048772056],"domain_scores_gemma":[0.9926773,0.0062999264,0.000040542654,0.0007257836,0.00006277038,0.00019369782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011787603,0.00027370258,0.00034515595,0.00035033032,0.00030835313,0.00020077795,0.0007565146,0.000112393325,0.000036354864],"category_scores_gemma":[0.0019142972,0.00028064998,0.00007464866,0.00042245566,0.000056422985,0.00047087035,0.00014174075,0.0007955303,0.0000057034913],"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":[0.00009703103,0.00016194377,0.004046535,0.00028559586,0.00047847803,0.00022111525,0.020795414,0.20930369,0.0023583286,0.0014864102,0.0002408644,0.7605246],"study_design_scores_gemma":[0.014212228,0.005672868,0.41828156,0.0015360222,0.0007042307,0.017251225,0.03500832,0.19753818,0.028945506,0.013289264,0.25398797,0.013572628],"about_ca_topic_score_codex":0.000019676161,"about_ca_topic_score_gemma":0.0000036391868,"teacher_disagreement_score":0.74695194,"about_ca_system_score_codex":0.00011090889,"about_ca_system_score_gemma":0.00005864162,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W4296592009","doi":"10.1145/3563210","title":"Arachne: Search-Based Repair of Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Debiasing; Deep neural networks; Convolutional neural network; Retraining; Artificial neural network; Artificial intelligence; Machine learning","score_opus":0.04776573394678502,"score_gpt":0.2979497318344487,"score_spread":0.25018399788766366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296592009","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060146716,0.00017233311,0.9922385,0.00016714998,0.0007654322,0.00008859033,0.0000027267722,0.0005480436,0.0000025484414],"genre_scores_gemma":[0.42005143,0.000002424524,0.5797929,0.000086843414,0.000017439994,0.000023760373,0.0000015284006,0.000012476035,0.000011161926],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984292,0.00059281755,0.00020651049,0.00033377402,0.00017466099,0.00026302875],"domain_scores_gemma":[0.9965532,0.00271762,0.000050916413,0.0005748296,0.00003195917,0.00007151643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011042944,0.00013767205,0.00024263834,0.0002449567,0.000238494,0.000010569001,0.0005334977,0.00006645496,0.000036357404],"category_scores_gemma":[0.0005589506,0.00015247615,0.00010929853,0.00044518165,0.000048470785,0.000090091926,0.000050841256,0.00074603746,3.674529e-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":[0.00002343821,0.000024971332,0.0002068548,0.000019464002,0.000024561783,0.0000108549375,0.00021421013,0.91241705,0.000048669604,0.00053908944,0.0000017870726,0.08646905],"study_design_scores_gemma":[0.00028742576,0.00022454852,0.00081147696,0.0000038283797,0.000017324717,0.00004512754,0.000040874187,0.9979015,0.00017357613,0.000074688425,0.00028596932,0.00013365102],"about_ca_topic_score_codex":0.000028242881,"about_ca_topic_score_gemma":0.000001267635,"teacher_disagreement_score":0.41403678,"about_ca_system_score_codex":0.00003994895,"about_ca_system_score_gemma":0.000022386566,"threshold_uncertainty_score":0.6217797},"labels":[],"label_agreement":null},{"id":"W4307811455","doi":"10.1145/3569935","title":"Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-based Safety-critical Systems","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; European Commission; Université du Luxembourg","keywords":"Debugging; Computer science; Hazard; Software engineering; Programming language","score_opus":0.04752392328673987,"score_gpt":0.3100093273240562,"score_spread":0.26248540403731635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307811455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042168662,0.00019995819,0.95655006,0.00019411731,0.0005777696,0.000120164164,0.000006221583,0.00018218301,8.696197e-7],"genre_scores_gemma":[0.65205926,0.000002734343,0.3478548,0.000026722395,0.000008444998,0.00003200348,0.0000017975319,0.00001160328,0.0000026425137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984057,0.00056745356,0.00029397075,0.00032353125,0.00018810577,0.00022121504],"domain_scores_gemma":[0.99307454,0.0064792815,0.000056556182,0.00029828932,0.00002948645,0.00006184172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014062694,0.00014017957,0.00029016502,0.00047216506,0.00017749953,0.00001147263,0.00026700489,0.00007037001,0.000006010145],"category_scores_gemma":[0.0017063272,0.00016329129,0.000041343785,0.00035499432,0.000027775703,0.00011662624,0.00003198261,0.00043020133,1.8449248e-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":[0.000036989335,0.000027117052,0.0009248362,0.000097438875,0.000012877433,0.000007379144,0.0001964871,0.98637867,0.00019793984,0.0007109422,2.3509354e-7,0.01140907],"study_design_scores_gemma":[0.0007336373,0.00011828044,0.0018609187,0.00006278528,0.000017998662,0.00002107783,0.000054083255,0.9962466,0.0004437736,0.00013649993,0.0001421022,0.00016224962],"about_ca_topic_score_codex":0.000054047407,"about_ca_topic_score_gemma":0.0000028624445,"teacher_disagreement_score":0.6098906,"about_ca_system_score_codex":0.00009651111,"about_ca_system_score_gemma":0.00006122661,"threshold_uncertainty_score":0.6658826},"labels":[],"label_agreement":null},{"id":"W4307812665","doi":"10.1145/3569934","title":"What Is the Intended Usage Context of This Model? An Exploratory Study of Pre-Trained Models on Various Model Repositories","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering 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":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reuse; Benchmark (surveying); Leverage (statistics); Software engineering; Software; Machine learning; Artificial intelligence; Domain engineering; Code reuse; Context (archaeology); Software development; Software construction; Programming language","score_opus":0.1167313584876961,"score_gpt":0.33314403356947164,"score_spread":0.21641267508177553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307812665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18977745,0.00018305576,0.80877095,0.00011371024,0.0005582678,0.00033548454,0.000022795934,0.0002373989,9.0151e-7],"genre_scores_gemma":[0.78743047,0.00005431525,0.21204674,0.000086498025,0.000010767248,0.0002559171,0.0000015902018,0.00003183779,0.00008187946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769235,0.00052419014,0.00042105885,0.00055204553,0.0004973747,0.00031297823],"domain_scores_gemma":[0.99421966,0.0039023268,0.00009898693,0.00152165,0.00015259134,0.000104772094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684671,0.00024972128,0.00044453418,0.00037738972,0.00025267905,0.000049667924,0.0011926347,0.000094018025,0.0000057073617],"category_scores_gemma":[0.0005995353,0.00022015745,0.000096911936,0.00049230515,0.00007462773,0.00056118413,0.00012414178,0.00069508835,2.3257432e-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":[0.000107207205,0.0003066486,0.000010558094,0.00003576123,0.000110344874,0.0000050816175,0.05563957,0.9319705,0.00079788984,0.00067880895,0.00001200926,0.010325665],"study_design_scores_gemma":[0.000575676,0.0015490117,0.00005413363,0.00002669226,0.000041102507,0.000026696622,0.0032263761,0.9871623,0.0053019966,0.0018021679,0.000017001808,0.00021686491],"about_ca_topic_score_codex":0.000052400406,"about_ca_topic_score_gemma":0.000007701169,"teacher_disagreement_score":0.59765303,"about_ca_system_score_codex":0.00007824258,"about_ca_system_score_gemma":0.00010370225,"threshold_uncertainty_score":0.897776},"labels":[],"label_agreement":null},{"id":"W4309529433","doi":"10.1145/3571848","title":"On the Discoverability of npm Vulnerabilities in Node.js Projects","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Concordia University","funders":"","keywords":"Discoverability; Computer science; Dependency (UML); Vulnerability (computing); Computer security; World Wide Web; Software engineering","score_opus":0.0900358588716811,"score_gpt":0.3147622559724983,"score_spread":0.2247263971008172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309529433","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":[0.29644912,0.00007230217,0.7023129,0.00045781315,0.00034589833,0.00018830289,0.000012975649,0.00015786021,0.0000028261022],"genre_scores_gemma":[0.80800486,0.000013057802,0.19154504,0.000076790835,0.000009589653,0.00028599362,9.236641e-7,0.000016593543,0.000047137943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99810445,0.00062306924,0.0002522839,0.0004102013,0.00029217883,0.00031780085],"domain_scores_gemma":[0.97808814,0.020839788,0.000034074787,0.00095323456,0.000032930755,0.000051833806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023045728,0.0001653259,0.00027107674,0.00034857666,0.00015989113,0.000020685786,0.00077149743,0.000058899514,0.000037869973],"category_scores_gemma":[0.006331637,0.0001379572,0.00007477274,0.00065606943,0.00007159529,0.00010139941,0.00008410603,0.0008063027,0.0000011985697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085401494,0.00025517904,0.002918536,0.0001401135,0.000059475977,0.000013273811,0.004223341,0.9543895,0.00064905564,0.009985748,0.000040426818,0.027239962],"study_design_scores_gemma":[0.0107586,0.014405953,0.37407342,0.0008106324,0.00018310975,0.0010283547,0.006122495,0.33085316,0.15511583,0.09046359,0.010031673,0.0061531677],"about_ca_topic_score_codex":0.000096553624,"about_ca_topic_score_gemma":0.0000053252093,"teacher_disagreement_score":0.6235363,"about_ca_system_score_codex":0.00011579658,"about_ca_system_score_gemma":0.00007454517,"threshold_uncertainty_score":0.75800186},"labels":[],"label_agreement":null},{"id":"W4311938462","doi":"10.1145/3571852","title":"Open Source License Inconsistencies on GitHub","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"License; Open source; Computer science; Source code; Open source software; MIT License; Code (set theory); Software; Computer security; World Wide Web; Software engineering; Database; Operating system; Programming language; Set (abstract data type)","score_opus":0.10022283026906519,"score_gpt":0.31426406166282855,"score_spread":0.21404123139376335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311938462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011654794,0.00006742683,0.9851596,0.0013052437,0.0008165664,0.0003011997,0.000018699517,0.00062688196,0.000049608363],"genre_scores_gemma":[0.070126645,0.000014843,0.9265319,0.0016140749,0.000030007608,0.00034791324,0.000004319648,0.000035562476,0.0012947102],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981703,0.0004414221,0.00029315066,0.00055827835,0.0002020862,0.0003347299],"domain_scores_gemma":[0.9955968,0.003098851,0.00008053519,0.0010632495,0.000051930667,0.00010859561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014451519,0.00022011493,0.00032835198,0.00042280066,0.0007087304,0.00014829518,0.0017222641,0.000078956444,0.00008713117],"category_scores_gemma":[0.0012180766,0.00023624519,0.000075070086,0.00087300525,0.000051826773,0.00027401515,0.00032232175,0.0006567475,0.000023744846],"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":[0.00011098365,0.00039372916,0.00030688907,0.000043124448,0.00018462128,0.00004418932,0.006965929,0.33454078,0.0010130437,0.016803853,0.0013333402,0.63825953],"study_design_scores_gemma":[0.0027064544,0.002647306,0.004396914,0.0000862221,0.00010542533,0.0012649226,0.0013898601,0.015918382,0.0052307025,0.0055471617,0.9587705,0.0019361322],"about_ca_topic_score_codex":0.00007322609,"about_ca_topic_score_gemma":0.000005421191,"teacher_disagreement_score":0.95743716,"about_ca_system_score_codex":0.00009331117,"about_ca_system_score_gemma":0.00007199328,"threshold_uncertainty_score":0.9633799},"labels":[],"label_agreement":null},{"id":"W4317209725","doi":"10.1145/3576037","title":"I Depended on You and You Broke Me: An Empirical Study of Manifesting Breaking Changes in Client Packages","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Software versioning; Breaking strength; Change impact analysis; Dependency (UML); Software; Software engineering; Operating system","score_opus":0.14032214583660246,"score_gpt":0.3833204554910334,"score_spread":0.24299830965443092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317209725","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":[0.55941814,0.000036879912,0.4396023,0.00010703418,0.00025961772,0.00015165524,0.000002871042,0.00042065428,8.1932694e-7],"genre_scores_gemma":[0.8473065,0.000059099315,0.15244953,0.000023448025,0.000027359483,0.00007122757,0.0000016582246,0.00003093591,0.000030270416],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980929,0.00033146425,0.0002667479,0.0006022261,0.00027169436,0.00043497025],"domain_scores_gemma":[0.99363697,0.005495153,0.00004201084,0.0006368598,0.000048389673,0.00014064566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016399537,0.00022436846,0.00037098033,0.0008958239,0.00009699225,0.000043603777,0.00042117824,0.00014152481,0.0000026670662],"category_scores_gemma":[0.0027781487,0.00022639178,0.00003158546,0.00087187253,0.00003348166,0.00014560303,0.00006923995,0.00048800668,0.0000020248785],"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":[0.00016484856,0.0010949366,0.16061006,0.0005511068,0.00026685774,0.0006001728,0.02982617,0.3291128,0.0050662262,0.00040631334,0.000015771398,0.47228473],"study_design_scores_gemma":[0.0031028679,0.004943208,0.8898568,0.00033217177,0.0000670847,0.00047785664,0.002400435,0.089590944,0.007544104,0.00046143666,0.00019242917,0.0010306612],"about_ca_topic_score_codex":0.00010743688,"about_ca_topic_score_gemma":0.00006911282,"teacher_disagreement_score":0.72924674,"about_ca_system_score_codex":0.000038792037,"about_ca_system_score_gemma":0.000024089242,"threshold_uncertainty_score":0.92319894},"labels":[],"label_agreement":null},{"id":"W4319296048","doi":"10.1145/3579640","title":"<scp>Katana</scp> : Dual Slicing Based Context for Learning Bug Fixes","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Program slicing; Debugging; Leverage (statistics); Slicing; Context (archaeology); Program comprehension; Software; Statement (logic); Software engineering; Programming language; Artificial intelligence; Software system; World Wide Web","score_opus":0.0980160634797238,"score_gpt":0.31874940585467515,"score_spread":0.22073334237495135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319296048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011221275,0.00012091245,0.97171956,0.00023962167,0.0005533971,0.00017949542,0.000010275913,0.015951471,0.000003964952],"genre_scores_gemma":[0.13928589,0.000027478436,0.85997945,0.00022193418,0.000047880727,0.00015419035,0.000008486399,0.00003922333,0.00023546435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846286,0.00018271485,0.00024450553,0.0005010058,0.0001353594,0.00047355655],"domain_scores_gemma":[0.978791,0.02044156,0.000061511324,0.0005040626,0.000081577455,0.00012026844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013961601,0.00023558257,0.00033145733,0.00048364804,0.00031667715,0.00007057812,0.00038538707,0.00017354243,0.0000017208101],"category_scores_gemma":[0.010178397,0.00024482646,0.00011407614,0.00058501115,0.000040627554,0.00013601387,0.000029180923,0.00039135377,0.000008219636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019526527,0.00006662147,0.0014220094,0.00032317382,0.00014759049,0.0000462757,0.0025060868,0.21384183,0.001393289,0.0012582314,0.0034931004,0.77548224],"study_design_scores_gemma":[0.002051758,0.0015983623,0.0047864364,0.00046786162,0.0001402141,0.00024549256,0.0002537874,0.9093024,0.024176085,0.014401397,0.04181937,0.00075681007],"about_ca_topic_score_codex":0.000047109374,"about_ca_topic_score_gemma":0.0000029448747,"teacher_disagreement_score":0.77472544,"about_ca_system_score_codex":0.000030298183,"about_ca_system_score_gemma":0.000047313137,"threshold_uncertainty_score":0.9983734},"labels":[],"label_agreement":null},{"id":"W4319451761","doi":"10.1145/3583564","title":"Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Hong Kong University of Science and Technology; University of Waterloo; Cisco Systems","keywords":"Computer science; Artificial intelligence; Task (project management); Image (mathematics); Machine learning; Markov chain; Fitness function; Artificial neural network; Pattern recognition (psychology); Data mining; Genetic algorithm","score_opus":0.1374384112985051,"score_gpt":0.34852953556130783,"score_spread":0.21109112426280274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319451761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013316612,0.000017941764,0.98510575,0.00037805544,0.0005685728,0.00019021652,0.000015767724,0.00040464883,0.0000024186636],"genre_scores_gemma":[0.26680526,0.000011197007,0.7330029,0.000018145343,0.000011307129,0.00006936484,0.000003013313,0.000015128661,0.00006369971],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909174,0.0001579284,0.00019942879,0.00025177648,0.00009412884,0.00020499132],"domain_scores_gemma":[0.9958057,0.0034955118,0.00006756735,0.0005296271,0.000061003506,0.00004061085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058777793,0.00011578386,0.0001909476,0.00019718659,0.00021783778,0.000018599152,0.00056916603,0.000095546704,0.0000022994664],"category_scores_gemma":[0.0011153929,0.00010059575,0.00008847838,0.0005560675,0.000049713082,0.00014986409,0.000035831643,0.00024775253,0.0000011478364],"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":[0.0000058277888,0.000015505511,0.000049938495,0.00003745665,0.000028016006,6.5989656e-7,0.0006059855,0.97483844,0.005618596,0.0036668817,0.000016682745,0.015115996],"study_design_scores_gemma":[0.00042628168,0.000051535582,0.0027792638,0.00004520805,0.000058094225,0.000012216743,0.000070626455,0.9848506,0.008170486,0.003035307,0.000322937,0.00017744309],"about_ca_topic_score_codex":0.000012788583,"about_ca_topic_score_gemma":0.0000017177674,"teacher_disagreement_score":0.25348866,"about_ca_system_score_codex":0.000021837424,"about_ca_system_score_gemma":0.000031475145,"threshold_uncertainty_score":0.41021758},"labels":[],"label_agreement":null},{"id":"W4319594569","doi":"10.1145/3583566","title":"COMET: Coverage-guided Model Generation For Deep Learning Library Testing","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Comet; Computer science; Layer (electronics); Set (abstract data type); Test set; Artificial intelligence; Machine learning; Algorithm; Data mining; Programming language; Chemistry","score_opus":0.21094581494621803,"score_gpt":0.3372706176748377,"score_spread":0.12632480272861965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319594569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051857023,0.00008061553,0.9763682,0.00021463513,0.00038600902,0.00016254156,0.000005722479,0.017590472,0.0000060855045],"genre_scores_gemma":[0.05716598,0.0000573755,0.9421505,0.0001781405,0.00006846637,0.00014743478,0.000014430401,0.000041102252,0.00017658056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987992,0.0001234289,0.0002268874,0.00042828333,0.00010103721,0.00032117788],"domain_scores_gemma":[0.9931397,0.0062516467,0.00005366887,0.00041132155,0.00005647064,0.000087236935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007956628,0.00018408301,0.00023712682,0.0003953178,0.0002916865,0.000087163324,0.00034537094,0.00014001068,0.0000017078946],"category_scores_gemma":[0.004808644,0.00019523471,0.00006671017,0.0006426124,0.000020333297,0.00027739664,0.000035052384,0.0002798914,0.0000038318126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042321853,0.000011779248,0.00022810599,0.000045468387,0.000020813202,0.000003839242,0.00026972126,0.7225696,0.0009941804,0.00046235518,0.00039563465,0.27499428],"study_design_scores_gemma":[0.00021153712,0.00014309832,0.00018064995,0.000029468096,0.000014816655,0.000042436477,0.0000025086265,0.98696196,0.0020899037,0.009750651,0.00036212028,0.00021086106],"about_ca_topic_score_codex":0.0000067673404,"about_ca_topic_score_gemma":2.703156e-7,"teacher_disagreement_score":0.2747834,"about_ca_system_score_codex":0.000018946977,"about_ca_system_score_gemma":0.000035289522,"threshold_uncertainty_score":0.796144},"labels":[],"label_agreement":null},{"id":"W4319964781","doi":"10.1145/3579642","title":"A Survey on Automated Driving System Testing: Landscapes and Trends","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Vehicular Ad Hoc Networks (VANETs)","field":"Engineering","cited_by":123,"is_retracted":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; Basic Research Program of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Context (archaeology); Software deployment; Test strategy; Integration testing; Data science; Systems engineering; Software engineering; Risk analysis (engineering); Software; Engineering","score_opus":0.06982938188292201,"score_gpt":0.28702639865301505,"score_spread":0.21719701677009304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319964781","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":[0.4764831,0.00025669447,0.5126362,0.000026227835,0.0007781046,0.00009970911,0.000044871307,0.009651915,0.000023208617],"genre_scores_gemma":[0.91908926,0.000087109314,0.080513604,0.0000114671375,0.000056664987,0.000046246518,0.000031205334,0.000091359885,0.00007307609],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998728,0.00019274224,0.0002264566,0.00031441962,0.000107733176,0.00043068494],"domain_scores_gemma":[0.9951551,0.0043233065,0.000021713184,0.0003221739,0.000028127448,0.00014960204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000925022,0.00026884692,0.0003738697,0.00050458324,0.00011555828,0.00003361365,0.00012208436,0.00020642954,0.0000053520366],"category_scores_gemma":[0.00075626373,0.0002753377,0.000045452973,0.00079887925,0.000020315596,0.00005315647,0.000009959665,0.00037259795,0.000014070796],"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":[0.0000077384775,0.0000061020614,0.00069305877,0.000107591346,0.000093588744,0.000023514904,0.00011010727,0.95405245,0.0003650793,0.000012020944,0.00015956984,0.044369187],"study_design_scores_gemma":[0.00032991037,0.00010393283,0.09261673,0.00014803038,0.000043078497,0.00009097006,0.000029800996,0.9056569,0.0002775487,0.000004966076,0.00041480592,0.00028336493],"about_ca_topic_score_codex":0.000035152934,"about_ca_topic_score_gemma":0.000045626122,"teacher_disagreement_score":0.44260615,"about_ca_system_score_codex":0.00004655188,"about_ca_system_score_gemma":0.0000071953714,"threshold_uncertainty_score":0.9999699},"labels":[],"label_agreement":null},{"id":"W4322717938","doi":"10.1145/3624742","title":"Stress Testing Control Loops in Cyber-physical Systems","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Reliability and Analysis Research","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":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Knut och Alice Wallenbergs Stiftelse; Lunds Universitet; European Commission","keywords":"Leverage (statistics); Computer science; Cyber-physical system; Software; Stress testing (software); Control (management); Control system; Control engineering; Systems engineering; Engineering; Artificial intelligence","score_opus":0.10009437022392521,"score_gpt":0.3358311838909224,"score_spread":0.23573681366699722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322717938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101771615,0.00009513474,0.89693165,0.0001809663,0.00025154228,0.00011743543,0.000010036407,0.0006388652,0.0000027418662],"genre_scores_gemma":[0.7863253,0.000043412172,0.21337035,0.000025509748,0.00005256109,0.00010006243,0.000002091106,0.000016694737,0.00006406198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835205,0.00037484383,0.00022370981,0.0004389648,0.00019804141,0.00041240363],"domain_scores_gemma":[0.9878367,0.011419573,0.000027414915,0.0005344105,0.00006667048,0.00011519821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012278004,0.00015540652,0.0003622176,0.0004962876,0.00009993202,0.00006444022,0.00045776353,0.000111377485,0.0000016236617],"category_scores_gemma":[0.0036574192,0.00014842462,0.00007371672,0.0014382623,0.000041405587,0.00014072342,0.000026170486,0.00042981398,0.000020287252],"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":[0.000010806136,0.00008388864,0.0036418024,0.00012754613,0.00007250603,0.000051887957,0.0005379163,0.85163724,0.0006825081,0.0007784195,0.000007522193,0.14236796],"study_design_scores_gemma":[0.0007655548,0.00019332719,0.017492691,0.00012307477,0.000028392413,0.000043580094,0.00012294063,0.9788823,0.0007459168,0.0009903074,0.00028097304,0.0003309411],"about_ca_topic_score_codex":0.00016456771,"about_ca_topic_score_gemma":0.0000069184584,"teacher_disagreement_score":0.6845536,"about_ca_system_score_codex":0.000040118353,"about_ca_system_score_gemma":0.000038279715,"threshold_uncertainty_score":0.60525805},"labels":[],"label_agreement":null},{"id":"W4362721716","doi":"10.1145/3591870","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; National Key Research and Development Program of China; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Transformer; Convolutional neural network; Computer security; Software deployment; Computer engineering; Machine learning; Real-time computing; Software engineering; Electrical engineering","score_opus":0.13330348676148915,"score_gpt":0.33313640744718626,"score_spread":0.1998329206856971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362721716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01214244,0.000026750668,0.9848694,0.00050292676,0.0008870606,0.0002851647,0.000008897476,0.0012746161,0.000002712334],"genre_scores_gemma":[0.14304084,0.000022494954,0.856556,0.000041876432,0.000055866738,0.00016882771,0.000008691548,0.000035148772,0.00007026116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985356,0.00012588472,0.00026542926,0.0005185905,0.00013233961,0.00042220065],"domain_scores_gemma":[0.99427813,0.005057681,0.000062451785,0.0003945451,0.00010531797,0.000101858415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010063215,0.00021961138,0.00028035865,0.00032900934,0.00029909416,0.000038208498,0.0003930135,0.00017067144,0.000004179595],"category_scores_gemma":[0.0018628222,0.00023010252,0.00008337463,0.00082580844,0.000040118244,0.00024224936,0.000016535576,0.00035691497,0.000005800728],"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":[0.000018713328,0.000012475073,0.00011888865,0.00006283162,0.000032995005,0.0000032770174,0.0005231001,0.64837235,0.0010077293,0.00017241167,0.000006759119,0.34966844],"study_design_scores_gemma":[0.0005854437,0.00018879949,0.0027294222,0.000045707442,0.00005184824,0.000044038163,0.00012721757,0.9915492,0.0028455681,0.0008696761,0.0005929464,0.0003701259],"about_ca_topic_score_codex":0.000036153528,"about_ca_topic_score_gemma":0.0000036803744,"teacher_disagreement_score":0.34929833,"about_ca_system_score_codex":0.000047385372,"about_ca_system_score_gemma":0.000033474018,"threshold_uncertainty_score":0.9383309},"labels":[],"label_agreement":null},{"id":"W4366825753","doi":"10.1145/3593802","title":"Predicting the Change Impact of Resolving Defects by Leveraging the Topics of Issue Reports in Open Source Software Systems","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Toronto; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Leverage (statistics); Data science; Open source; Metric (unit); Source code; Software bug; Change impact analysis; Eclipse; Data mining; Software; Information retrieval; Machine learning","score_opus":0.11775826133334773,"score_gpt":0.35457027254143647,"score_spread":0.23681201120808876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366825753","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":[0.21795547,0.00076061237,0.7799122,0.0001603254,0.00051545247,0.00040953569,0.000009118219,0.00027632513,9.68833e-7],"genre_scores_gemma":[0.9004078,0.00018244084,0.09882524,0.000027200778,0.00008776706,0.00026474782,0.0000046164196,0.00005111825,0.00014906088],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9981249,0.00037262926,0.00043271587,0.00038837956,0.000260469,0.00042089005],"domain_scores_gemma":[0.9883119,0.010361575,0.0001271294,0.0010507324,0.00007848905,0.00007019615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033425735,0.00019362972,0.0003898825,0.00033038223,0.00014217396,0.00007164321,0.0011159716,0.00012724321,0.0000034983802],"category_scores_gemma":[0.006429914,0.00013709346,0.0000985313,0.0011514171,0.000058522397,0.00022634848,0.00018916305,0.0005086436,8.6300037e-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":[0.000028247194,0.00005848364,0.08546045,0.0005428164,0.00023185724,0.000053263168,0.012665598,0.80398196,0.0015186727,0.00006832191,0.00031896573,0.095071375],"study_design_scores_gemma":[0.0026421084,0.001859372,0.53174585,0.0030281867,0.00021060645,0.0015518297,0.002477542,0.42539665,0.01663802,0.0008151987,0.0116376085,0.001997008],"about_ca_topic_score_codex":0.001769538,"about_ca_topic_score_gemma":0.000009474324,"teacher_disagreement_score":0.6824523,"about_ca_system_score_codex":0.000070223716,"about_ca_system_score_gemma":0.00006487571,"threshold_uncertainty_score":0.7697672},"labels":[],"label_agreement":null},{"id":"W4376505229","doi":"10.1145/3597208","title":"An Empirical Study on GitHub Pull Requests’ Reactions","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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; École de Technologie Supérieure","funders":"","keywords":"Computer science; Leverage (statistics); Source code; Set (abstract data type); Code review; Open source; Software; Empirical research; Code (set theory); Process (computing); Static program analysis; Software engineering; World Wide Web; Software development; Programming language; Artificial intelligence","score_opus":0.16806167547143225,"score_gpt":0.40876858222722956,"score_spread":0.2407069067557973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376505229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21310371,0.000018787016,0.7826081,0.00036106564,0.0008060211,0.00022195526,0.0000062284907,0.0028706812,0.0000034811042],"genre_scores_gemma":[0.54976416,0.000042822772,0.44947904,0.00010298394,0.00009470415,0.00021476195,0.0000053095455,0.00006267753,0.00023356617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99761003,0.0004273669,0.000292773,0.0007679894,0.00034094762,0.000560885],"domain_scores_gemma":[0.9900975,0.008033966,0.000031368072,0.0014749867,0.00007511094,0.0002870562],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016821385,0.00027913458,0.00033108404,0.0009412392,0.00022903652,0.000094655625,0.00082317664,0.00018648525,0.00001212399],"category_scores_gemma":[0.003736985,0.000279658,0.00008044556,0.0013908673,0.000040348772,0.00028530267,0.000037353268,0.0007809347,0.00009463774],"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":[0.00017199156,0.0020063417,0.028059449,0.00021427358,0.0006069946,0.0006532467,0.010307784,0.6426526,0.0055587674,0.0014582401,0.0008611592,0.30744916],"study_design_scores_gemma":[0.0033363434,0.009950085,0.85947764,0.00021293644,0.00013780346,0.0006341665,0.001069271,0.092662565,0.008557026,0.0026411423,0.018781263,0.0025397802],"about_ca_topic_score_codex":0.00003666237,"about_ca_topic_score_gemma":0.0000043003115,"teacher_disagreement_score":0.83141816,"about_ca_system_score_codex":0.00007916639,"about_ca_system_score_gemma":0.000052299758,"threshold_uncertainty_score":0.99996555},"labels":[],"label_agreement":null},{"id":"W4379014622","doi":"10.1145/3603110","title":"Dependency Update Strategies and Package Characteristics","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Concordia University","funders":"","keywords":"Computer science; Dependency (UML); Software versioning; Software engineering; Dilemma; Software; Programming language","score_opus":0.07638883686026998,"score_gpt":0.32458871075136997,"score_spread":0.2481998738911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379014622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112039685,0.00018029267,0.88546634,0.00023721678,0.0005392995,0.000089429006,0.0000113807655,0.0014348131,0.0000015304581],"genre_scores_gemma":[0.37687248,0.0008474851,0.62200314,0.000051169834,0.00004356503,0.000053907923,0.0000059017543,0.00003487061,0.00008748963],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986526,0.0001119232,0.00019409513,0.00044106285,0.00017001537,0.00043033264],"domain_scores_gemma":[0.9950166,0.0041342187,0.000025580186,0.0006165061,0.00004473362,0.00016237973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076172344,0.00020513801,0.000264038,0.0004399788,0.00013121236,0.0001566053,0.00043984014,0.00014562899,0.000009612121],"category_scores_gemma":[0.0018865472,0.00021000665,0.00004230942,0.0005577572,0.000048382386,0.00036165307,0.00005849011,0.00041788077,0.000035106335],"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":[0.00004094301,0.00007777262,0.0030980115,0.00056457194,0.00027962445,0.0003527997,0.0025280833,0.017838228,0.0058755577,0.014734666,0.0001704225,0.95443934],"study_design_scores_gemma":[0.004353899,0.0020140687,0.77667147,0.0005513795,0.0002443916,0.0023346432,0.0011234455,0.13155074,0.023994613,0.025623923,0.026594933,0.0049424963],"about_ca_topic_score_codex":0.000011636687,"about_ca_topic_score_gemma":0.0000016454173,"teacher_disagreement_score":0.9494968,"about_ca_system_score_codex":0.00002081745,"about_ca_system_score_gemma":0.00004682791,"threshold_uncertainty_score":0.85638225},"labels":[],"label_agreement":null},{"id":"W4382987313","doi":"10.1145/3607186","title":"What Constitutes the Deployment and Runtime Configuration System? An Empirical Study on OpenStack Projects","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering 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":"Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software deployment; Computer science; Configuration Management (ITSM); Software configuration management; Operating system; Software; Leverage (statistics); System deployment; Software system; Software construction","score_opus":0.1711848459207054,"score_gpt":0.38614101168772763,"score_spread":0.21495616576702223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382987313","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":[0.296515,0.000077733595,0.70061404,0.0004021315,0.0008460288,0.0005082015,0.0000026170148,0.0010329982,0.0000012818712],"genre_scores_gemma":[0.9071554,0.000097386015,0.09216553,0.00010061432,0.000052533713,0.00031545572,0.0000034919315,0.00003350623,0.00007611955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9981819,0.000427174,0.00022021754,0.0005507823,0.0002712068,0.00034875824],"domain_scores_gemma":[0.9925278,0.006453357,0.000029491594,0.00078908773,0.00006333456,0.00013692066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016287056,0.00021908026,0.00027053387,0.00034941,0.00027332266,0.00028559996,0.00048281485,0.000104033796,0.0000022844945],"category_scores_gemma":[0.0012955143,0.00016949621,0.00003550401,0.0005774726,0.00006872305,0.00043682425,0.00004723686,0.00038728688,0.000019878158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033805007,0.0012647541,0.019860588,0.00090437103,0.0013343294,0.0006858453,0.054604862,0.472658,0.0039699697,0.007407131,0.00061103585,0.43636107],"study_design_scores_gemma":[0.009470234,0.014797548,0.56567633,0.0014805791,0.00049945485,0.0018882833,0.03001657,0.33160898,0.030848939,0.00068167585,0.008914789,0.0041166325],"about_ca_topic_score_codex":0.000025788988,"about_ca_topic_score_gemma":0.000005300338,"teacher_disagreement_score":0.6106404,"about_ca_system_score_codex":0.00005262614,"about_ca_system_score_gemma":0.000053555304,"threshold_uncertainty_score":0.69118553},"labels":[],"label_agreement":null},{"id":"W4383067302","doi":"10.1145/3607179","title":"A Systematic Review of Automated Query Reformulations in Source Code Search","year":2023,"lang":"en","type":"review","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Computer science; Information retrieval; Query expansion; Web search query; Vocabulary; Term (time); Weighting; Software; Data mining; Search engine; Programming language","score_opus":0.17950256895553524,"score_gpt":0.4152454057738076,"score_spread":0.23574283681827235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383067302","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014401654,0.4907337,0.5072277,0.00001528329,0.00016446682,0.00068358297,0.000021233174,0.0011522549,2.746475e-7],"genre_scores_gemma":[0.000002163194,0.75901055,0.24027923,0.000014400229,0.000012129925,0.00049235683,0.000012778008,0.0000780596,0.00009832358],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9960702,0.0010431809,0.001286322,0.00066539494,0.00039873846,0.0005361394],"domain_scores_gemma":[0.9742009,0.023676459,0.00018562423,0.0016654066,0.00011949707,0.00015213285],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0039430475,0.0004617585,0.0027988937,0.001700045,0.000063248284,0.000032137155,0.0012984072,0.00042150525,0.0000038778735],"category_scores_gemma":[0.014827919,0.00040742243,0.0003701055,0.0025324752,0.000045972163,0.00013141347,0.00009448705,0.0010666165,0.000028627826],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.593933e-7,0.0000267717,8.7303624e-7,0.9338694,0.00023400167,0.000019377872,0.00012527175,0.006590283,4.910623e-7,0.000090077105,0.000008486739,0.059033986],"study_design_scores_gemma":[0.00020904042,0.000119393124,0.000013500798,0.9780133,0.0005332358,0.00030951796,0.0000130023145,0.014807805,0.000008811128,0.000027148346,0.0053035985,0.0006416975],"about_ca_topic_score_codex":0.000043666736,"about_ca_topic_score_gemma":0.0000041895296,"teacher_disagreement_score":0.26827684,"about_ca_system_score_codex":0.0002083543,"about_ca_system_score_gemma":0.000259398,"threshold_uncertainty_score":0.99983776},"labels":[],"label_agreement":null},{"id":"W4383555717","doi":"10.1145/3607185","title":"Programming by Example Made Easy","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Impact Fund; National Science Foundation","keywords":"Computer science; Usability; Domain (mathematical analysis); Table (database); Exploit; Constraint programming; Domain-specific language; Software engineering; Range (aeronautics); Programming language; Theoretical computer science; Data mining; Human–computer interaction; Mathematical optimization","score_opus":0.10711553213041111,"score_gpt":0.3310986989582408,"score_spread":0.22398316682782968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383555717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018604424,0.00021988223,0.97690654,0.0002523379,0.0006495657,0.00015951166,0.0000079112215,0.0031980348,0.0000018171837],"genre_scores_gemma":[0.034176003,0.00012761817,0.9646584,0.000062562845,0.000043929587,0.00017931002,0.000008423795,0.000050635474,0.00069313735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982724,0.00013425921,0.00020200806,0.00054387166,0.00023487468,0.0006125587],"domain_scores_gemma":[0.9925035,0.0064469813,0.000023367982,0.00078199274,0.00004278703,0.00020135721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010655755,0.00021884576,0.00025748453,0.00045645342,0.00014846034,0.000079253,0.00068907393,0.00016107809,0.0000116059455],"category_scores_gemma":[0.0025332493,0.00023018922,0.00007229794,0.0010670453,0.00004057239,0.00018753887,0.000052729483,0.00045775654,0.000056108045],"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":[0.000016792277,0.00007912382,0.0008833778,0.00019449659,0.00015939744,0.00006449783,0.001139469,0.044131517,0.0067520114,0.0012155398,0.0010589913,0.94430476],"study_design_scores_gemma":[0.0050133914,0.0024866352,0.0528101,0.0004670351,0.00017101876,0.0011907166,0.00034526194,0.13968165,0.09230994,0.0043538394,0.6961189,0.00505155],"about_ca_topic_score_codex":0.000060669703,"about_ca_topic_score_gemma":0.0000011875962,"teacher_disagreement_score":0.9392532,"about_ca_system_score_codex":0.000043378837,"about_ca_system_score_gemma":0.000030838477,"threshold_uncertainty_score":0.9386844},"labels":[],"label_agreement":null},{"id":"W4385222146","doi":"10.1145/3585005","title":"<i>ArchRepair</i> : Block-Level Architecture-Oriented Repairing for Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program","keywords":"Computer science; Robustness (evolution); Block (permutation group theory); Deep neural networks; Overfitting; Architecture; Artificial neural network; Artificial intelligence; Network architecture; Machine learning; Retraining; Distributed computing; Computer engineering; Computer architecture; Computer network","score_opus":0.06776237405796683,"score_gpt":0.31016859040160144,"score_spread":0.24240621634363463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385222146","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037743582,0.000082731494,0.99158436,0.00047973837,0.0016306071,0.00022721286,0.000005860526,0.0022131517,0.0000019786953],"genre_scores_gemma":[0.07830527,0.000019898735,0.9211399,0.00015210887,0.00013235395,0.00011213346,0.000006757504,0.000042566484,0.00008900281],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982362,0.00023309767,0.0002643494,0.00058286265,0.00013735655,0.00054616225],"domain_scores_gemma":[0.9935014,0.0055943113,0.00005698397,0.00065957214,0.00005414584,0.00013358588],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011461363,0.00024564308,0.00031630488,0.00036880566,0.00030423925,0.000035128083,0.0005120676,0.00016386728,0.0000025480958],"category_scores_gemma":[0.0022922882,0.0002510593,0.0001489714,0.0006983148,0.000045180597,0.00012842829,0.000065787615,0.000592434,0.0000021917172],"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":[0.000024550185,0.000008588307,0.00004805446,0.000030800325,0.0000423806,0.000009910017,0.00041569196,0.8133362,0.00007946782,0.00050998066,0.000010651472,0.18548371],"study_design_scores_gemma":[0.00049067545,0.00014905371,0.00054487865,0.000020352243,0.00002998581,0.000098485085,0.000027094584,0.9950495,0.00021686924,0.0005832395,0.0025231598,0.00026671196],"about_ca_topic_score_codex":0.000015671116,"about_ca_topic_score_gemma":0.000007626085,"teacher_disagreement_score":0.18521701,"about_ca_system_score_codex":0.000031559048,"about_ca_system_score_gemma":0.000016996277,"threshold_uncertainty_score":0.99999416},"labels":[],"label_agreement":null},{"id":"W4386031629","doi":"10.1145/3617171","title":"<scp>StubCoder</scp> : Automated Generation and Repair of Stub Code for Mock Objects","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Hong Kong University of Science and Technology; Impact Fund; National Science Foundation","keywords":"Stub (electronics); Computer science; Unit testing; Regression testing; Leverage (statistics); Test case; Programming language; Software; Software development; Artificial intelligence; Engineering; Structural engineering; Machine learning; Software construction","score_opus":0.12252016812216412,"score_gpt":0.3394841656674571,"score_spread":0.21696399754529297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386031629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047828432,0.00017542786,0.93096876,0.000056164055,0.00033742664,0.0001881508,0.000021623866,0.020422237,0.0000017792055],"genre_scores_gemma":[0.08577038,0.00009740872,0.91381526,0.000050283514,0.000025322537,0.000110636596,0.0000068705926,0.000023366887,0.000100443154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988977,0.000120952354,0.00023671915,0.00038694462,0.00009879504,0.00025888853],"domain_scores_gemma":[0.99328816,0.0060394304,0.0000584181,0.00045104168,0.000087307024,0.00007564911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009393048,0.00016362593,0.0002827594,0.00034693594,0.00013779584,0.000025372032,0.00021714522,0.00014562183,3.001151e-7],"category_scores_gemma":[0.0043067993,0.00016706248,0.00006831203,0.00043161062,0.00003677633,0.00011073469,0.000026372056,0.00013799699,8.549983e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066336324,0.0004977217,0.0053698835,0.0029448615,0.0011850841,0.000079363366,0.019332321,0.38994044,0.0450244,0.0065177903,0.034471698,0.49457008],"study_design_scores_gemma":[0.0004578548,0.00049301155,0.0030454341,0.00007782199,0.000052308846,0.000078908335,0.000029846184,0.9724969,0.017616209,0.0045252005,0.00097150926,0.00015497977],"about_ca_topic_score_codex":0.000019939951,"about_ca_topic_score_gemma":0.000004148839,"teacher_disagreement_score":0.5825565,"about_ca_system_score_codex":0.000015628471,"about_ca_system_score_gemma":0.00003164868,"threshold_uncertainty_score":0.681261},"labels":[],"label_agreement":null},{"id":"W4386136237","doi":"10.1145/3617168","title":"Faire: Repairing Fairness of Neural Networks via Neuron Condition Synthesis","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation; Bộ Giáo dục và Ðào tạo; Ministry of Education - Singapore; National Research Foundation Singapore; Canadian Institute for Advanced Research","keywords":"Computer science; Deep neural networks; Retraining; Robustness (evolution); Overhead (engineering); Trustworthiness; Artificial intelligence; Machine learning; Artificial neural network; Computer security; Programming language","score_opus":0.04843400212564353,"score_gpt":0.30030590532651313,"score_spread":0.2518719032008696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386136237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026303392,0.00004175801,0.97128177,0.00020102652,0.0010462888,0.00008347779,0.0000022966253,0.0010378663,0.0000021266114],"genre_scores_gemma":[0.62464255,0.00002888616,0.37518784,0.00002786096,0.00003778905,0.000029617344,0.0000019919494,0.000020874759,0.000022554183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986228,0.00032894575,0.00025044996,0.00037971305,0.00012769285,0.00029044313],"domain_scores_gemma":[0.9947975,0.0044991556,0.00007683462,0.000517787,0.00003770143,0.00007101096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008037666,0.00017176928,0.00029890786,0.0003152734,0.0001348467,0.000019634976,0.00040355374,0.00013676204,0.000007631288],"category_scores_gemma":[0.0015307936,0.00018326247,0.000089173125,0.00062228774,0.000047451067,0.00021628538,0.000044005345,0.00038871515,0.0000027750332],"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":[0.000010240939,0.000008302918,0.00013726599,0.000038706,0.000026063863,0.000012480487,0.00014458745,0.8442815,0.0003064643,0.00031743635,0.000004177499,0.1547128],"study_design_scores_gemma":[0.00018098834,0.000086390726,0.0056624156,0.000037072965,0.0000344835,0.00006347401,0.000020292273,0.9913351,0.0018493484,0.0004759718,0.00006124227,0.00019322561],"about_ca_topic_score_codex":0.000029470966,"about_ca_topic_score_gemma":0.0000017616304,"teacher_disagreement_score":0.5983392,"about_ca_system_score_codex":0.000018524332,"about_ca_system_score_gemma":0.000010831781,"threshold_uncertainty_score":0.7473226},"labels":[],"label_agreement":null},{"id":"W4386191524","doi":"10.1145/3617176","title":"Probabilistic Safe WCET Estimation for Weakly Hard Real-time Systems at Design Stages","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Real-Time Systems Scheduling","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":"Natural Sciences and Engineering Research Council of Canada; Mitacs; European Commission; Université du Luxembourg","keywords":"Computer science; Leverage (statistics); Probabilistic logic; Worst-case execution time; Scheduling (production processes); Reliability engineering; Execution time; Distributed computing; Mathematical optimization; Machine learning; Artificial intelligence","score_opus":0.11398602655715183,"score_gpt":0.31539242308225535,"score_spread":0.2014063965251035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386191524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008556117,0.00007686365,0.9878433,0.00017487456,0.0010511292,0.0007726759,0.000022518036,0.0014978843,0.000004647444],"genre_scores_gemma":[0.015188409,0.000059756603,0.9830529,0.000010991386,0.000054502645,0.0005057611,0.000013397617,0.000044823548,0.0010694629],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796844,0.00043458422,0.00039583773,0.0005769669,0.00017900643,0.00044519175],"domain_scores_gemma":[0.9910396,0.007902862,0.000096265525,0.00072913227,0.000094405186,0.00013775309],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024460251,0.00025077455,0.00044302232,0.0003657962,0.00024253156,0.00010394423,0.00043336794,0.00019233332,0.0000053289345],"category_scores_gemma":[0.0020635354,0.0002498106,0.00009050381,0.00046893972,0.000032362484,0.00026443577,0.00002737564,0.00015904257,0.00006912823],"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":[0.000026620888,0.000013601363,0.000007643896,0.00030497115,0.000065311215,0.0000061784403,0.0004371785,0.9744939,0.00910243,0.0008166385,0.00016263314,0.01456289],"study_design_scores_gemma":[0.00044423973,0.00029567143,0.00054414355,0.00014124023,0.00005505995,0.00012897406,0.000029340557,0.99315095,0.0035048963,0.0008148451,0.0005287185,0.00036191518],"about_ca_topic_score_codex":0.000046531422,"about_ca_topic_score_gemma":0.0000011411697,"teacher_disagreement_score":0.018657053,"about_ca_system_score_codex":0.00012383015,"about_ca_system_score_gemma":0.000058072426,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4386442953","doi":"10.1145/3617172","title":"On the Caching Schemes to Speed Up Program Reduction","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reduction (mathematics); Debugging; Compiler; Cache; Parallel computing; Process (computing); ENCODE; Memory footprint; Encoding (memory); Compile time; Computation; Theoretical computer science; Computer engineering; Algorithm; Programming language; Artificial intelligence","score_opus":0.1289523923715804,"score_gpt":0.35603718592683653,"score_spread":0.22708479355525613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386442953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04509002,0.000020191053,0.9355958,0.0016198803,0.0009033249,0.0002492549,0.0000019429092,0.016514782,0.000004770838],"genre_scores_gemma":[0.15202692,0.000016529366,0.8473761,0.00022641216,0.00004227526,0.00013081418,0.0000014154589,0.00002316275,0.00015635302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882126,0.00017044051,0.00015809218,0.0003944431,0.00014395923,0.00031183078],"domain_scores_gemma":[0.9953255,0.0038078397,0.000029390309,0.0007012476,0.00004163644,0.00009438429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011388606,0.00017245121,0.0001767402,0.00035876274,0.0002559603,0.00007199566,0.00047738926,0.000097986784,0.0000035714195],"category_scores_gemma":[0.0036887173,0.00013716971,0.00006104656,0.00082586054,0.000029153709,0.000084685744,0.00003322637,0.00036655524,0.000026853531],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019833353,0.00004596597,0.00002780976,0.000030718944,0.0000488365,0.000008740358,0.0012035167,0.038831577,0.0011190743,0.004454753,0.0020372241,0.9521719],"study_design_scores_gemma":[0.0027356953,0.008335557,0.010523158,0.0019254443,0.0002963012,0.0016812615,0.0004703902,0.49243787,0.16402136,0.24685949,0.06540162,0.005311852],"about_ca_topic_score_codex":0.000028858542,"about_ca_topic_score_gemma":4.8693556e-7,"teacher_disagreement_score":0.9468601,"about_ca_system_score_codex":0.000029797628,"about_ca_system_score_gemma":0.000020364687,"threshold_uncertainty_score":0.5593618},"labels":[],"label_agreement":null},{"id":"W4386830495","doi":"10.1145/3624740","title":"<i>LoGenText-Plus</i> : Improving Neural Machine Translation Based Logging Texts Generation with Syntactic Templates","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"Polytechnique Montréal; University of Waterloo","funders":"","keywords":"Computer science; Logging; Source code; Code (set theory); Context (archaeology); Template; Natural language processing; Artificial intelligence; Database; Programming language; Set (abstract data type)","score_opus":0.09871842548096321,"score_gpt":0.3114374323806604,"score_spread":0.2127190068996972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386830495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035429858,0.00032331594,0.96117145,0.00047509134,0.00051548,0.00023719414,0.000010975683,0.0018358009,8.580362e-7],"genre_scores_gemma":[0.5265961,0.000021393682,0.47312692,0.00006466868,0.000039364837,0.000074683536,0.000015104965,0.000037478945,0.00002424484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818,0.00019049403,0.00025152272,0.0005941603,0.00027232248,0.00051155477],"domain_scores_gemma":[0.99402726,0.0050915526,0.000046580273,0.0006213979,0.000060286744,0.00015291478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009104239,0.00028403001,0.00029408035,0.00067704025,0.00024179483,0.00010363679,0.00041501533,0.0001464945,0.000008522271],"category_scores_gemma":[0.0009393745,0.00026744558,0.0000703983,0.0008764622,0.000036922935,0.00035325802,0.000019958241,0.00048284305,0.0000112159805],"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":[0.000031691678,0.000020982268,0.0004582646,0.00013569288,0.000051446328,0.00004554043,0.00030252815,0.7443212,0.008171146,0.000033772754,0.000010216069,0.24641748],"study_design_scores_gemma":[0.0006929615,0.00024782654,0.0020130274,0.000038654103,0.00003135293,0.0001586052,0.000011816103,0.98714453,0.009076698,0.000023718692,0.00023803419,0.0003227932],"about_ca_topic_score_codex":0.00005435848,"about_ca_topic_score_gemma":0.000011293828,"teacher_disagreement_score":0.4911663,"about_ca_system_score_codex":0.00007512358,"about_ca_system_score_gemma":0.00006751144,"threshold_uncertainty_score":0.99997777},"labels":[],"label_agreement":null},{"id":"W4386845625","doi":"10.1145/3624739","title":"Understanding the Helpfulness of Stale Bot for Pull-Based Development: An Empirical Study of 20 Large Open-Source Projects","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Open Source Software Innovations","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":"Helpfulness; Computer science; Abandonment (legal); Process (computing); Workflow; Process management; Code refactoring; Risk analysis (engineering); Business; Operating system; Database; Psychology","score_opus":0.3482458636295181,"score_gpt":0.39795572836972043,"score_spread":0.049709864740202336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386845625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15601508,0.000007298221,0.8425969,0.0002295435,0.00020285716,0.00067805004,0.000018084196,0.00025112423,0.0000010877745],"genre_scores_gemma":[0.54609793,6.962708e-7,0.45356566,0.00005210815,0.000007664864,0.00020886054,0.0000066280904,0.000020824356,0.00003960798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848807,0.00028789084,0.00038161833,0.0003778031,0.00016454037,0.00030007254],"domain_scores_gemma":[0.9949882,0.0040496704,0.000109720335,0.0006707662,0.00012430064,0.000057335936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023066974,0.00016300059,0.00033306485,0.00038594354,0.0003270156,0.00005211414,0.00097156083,0.00009306503,0.0000037652387],"category_scores_gemma":[0.0008610788,0.00013860033,0.000043611377,0.0013474956,0.00004578882,0.00021116536,0.000078923724,0.00020461954,7.2012557e-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":[0.00043421955,0.0033627208,0.012400239,0.0008389099,0.0009143626,0.00001577272,0.09932986,0.7790606,0.0020836575,0.005791457,0.00026917752,0.095499024],"study_design_scores_gemma":[0.035122234,0.017794164,0.07343703,0.0010250647,0.00088990305,0.00019158635,0.09391068,0.5973399,0.12629072,0.013896408,0.03469413,0.0054081692],"about_ca_topic_score_codex":0.000018746981,"about_ca_topic_score_gemma":0.000049573955,"teacher_disagreement_score":0.39008287,"about_ca_system_score_codex":0.000046592013,"about_ca_system_score_gemma":0.00014727155,"threshold_uncertainty_score":0.56519574},"labels":[],"label_agreement":null},{"id":"W4386889431","doi":"10.1145/3624745","title":"Search-Based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; McMaster University","keywords":"Fitness function; Computer science; Domain (mathematical analysis); Software; Set (abstract data type); Function (biology); Search-based software engineering; Software engineering; Artificial intelligence; Machine learning; Data mining; Software system; Programming language; Software construction; Genetic algorithm","score_opus":0.09860297203966012,"score_gpt":0.31119659442560965,"score_spread":0.21259362238594953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386889431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03720156,0.00008710573,0.94110364,0.00046977994,0.0002795826,0.00016418794,0.00003240039,0.020659843,0.0000018816519],"genre_scores_gemma":[0.04909941,0.00001832913,0.9503654,0.00020854683,0.000021889331,0.0001106276,0.000021763031,0.000044443303,0.00010957929],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981062,0.0002621122,0.00030354905,0.00062362716,0.00020500585,0.00049953186],"domain_scores_gemma":[0.98972404,0.0092220465,0.000050262293,0.00065340707,0.0001402629,0.00021000381],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094355346,0.00029222376,0.0003499792,0.00046309317,0.00038222322,0.00011932747,0.00044768935,0.00021068809,0.000005561503],"category_scores_gemma":[0.005557699,0.0002969432,0.000059121874,0.0011001762,0.000101817815,0.00015983869,0.00006013044,0.00042703544,0.0000131372235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003570678,0.0001547302,0.0062517086,0.000401967,0.00017483026,0.00009126534,0.0006904894,0.1939349,0.005271782,0.00030831376,0.0030831967,0.7896011],"study_design_scores_gemma":[0.0010276651,0.00072916126,0.012071197,0.00027486635,0.00009057206,0.00025580547,0.000020497402,0.97561926,0.005052044,0.0033120087,0.00059782976,0.0009491062],"about_ca_topic_score_codex":0.000056647452,"about_ca_topic_score_gemma":0.0000020683149,"teacher_disagreement_score":0.788652,"about_ca_system_score_codex":0.000038295806,"about_ca_system_score_gemma":0.000088943794,"threshold_uncertainty_score":0.99994826},"labels":[],"label_agreement":null},{"id":"W4387735187","doi":"10.1145/3628159","title":"Generation-based Differential Fuzzing for Deep Learning Libraries","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Fuzz testing; Computer science; Context (archaeology); Task (project management); Machine learning; Artificial intelligence; Deep learning; Benchmark (surveying); Software engineering; Software; Programming language","score_opus":0.14059899809814053,"score_gpt":0.32340425284178986,"score_spread":0.18280525474364934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387735187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003663086,0.00006648527,0.9819157,0.00026672683,0.0006297991,0.00012127646,0.0000032453916,0.013332745,9.469452e-7],"genre_scores_gemma":[0.13744475,0.000015985208,0.86215746,0.000085986496,0.00006850307,0.00014559683,0.000012251384,0.000025007712,0.000044463017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989687,0.000123654,0.00016999632,0.0003569888,0.000091466536,0.0002891776],"domain_scores_gemma":[0.99368,0.0058231223,0.000037569713,0.00034863112,0.00003763375,0.00007304002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004813405,0.00016239313,0.00020598892,0.0003478197,0.00031736237,0.00009894692,0.0003042371,0.00012434035,0.0000037828775],"category_scores_gemma":[0.002561527,0.00016609656,0.000077979785,0.00036186754,0.000028994406,0.00013689318,0.000018964212,0.00023014122,0.0000031607665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002917692,0.00004951024,0.00051302067,0.00016945391,0.00009126016,0.00001130847,0.0011274552,0.3252201,0.0028969443,0.006522725,0.0004763269,0.6628927],"study_design_scores_gemma":[0.00035133664,0.00024086259,0.00048354975,0.00003724261,0.000024694644,0.00001541059,0.000008718038,0.9807503,0.0070693884,0.009779502,0.0009468533,0.0002920987],"about_ca_topic_score_codex":0.0000081991075,"about_ca_topic_score_gemma":9.818601e-7,"teacher_disagreement_score":0.66260064,"about_ca_system_score_codex":0.000020922149,"about_ca_system_score_gemma":0.000028640658,"threshold_uncertainty_score":0.67732215},"labels":[],"label_agreement":null},{"id":"W4387869001","doi":"10.1145/3630009","title":"The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Snippet; Artificial intelligence; Code (set theory); Code generation; Machine learning; Artificial neural network; Construct (python library); Set (abstract data type); Programming language; Natural language processing","score_opus":0.10990026194072332,"score_gpt":0.33788673840129657,"score_spread":0.22798647646057324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387869001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007885613,0.0010593155,0.98131025,0.008152857,0.0007229608,0.00030684262,0.0000065978006,0.0005548663,6.753113e-7],"genre_scores_gemma":[0.40788215,0.0013112411,0.5884432,0.0003679638,0.00030088,0.0007014197,0.000012803539,0.00008448571,0.000895864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857205,0.00040400753,0.00018238118,0.0003158757,0.00015955167,0.000366144],"domain_scores_gemma":[0.97000587,0.029289829,0.000033456763,0.00055058737,0.00005253809,0.000067721296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030939737,0.0001623971,0.0001775583,0.000113398455,0.00098078,0.00018443193,0.00057704456,0.00008452837,0.000001180219],"category_scores_gemma":[0.0070851706,0.000090632326,0.00007242699,0.00040592282,0.00013616831,0.00009402546,0.000048930353,0.0005322013,0.000002152582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008102532,0.000012186163,0.00027227,0.0000555452,0.00015886255,0.00000521852,0.0021322668,0.433626,0.001625769,0.0064531756,0.00023616584,0.5553415],"study_design_scores_gemma":[0.0007295101,0.00010608046,0.0014718283,0.000010155502,0.000027632133,0.00008168417,0.000043411528,0.9784437,0.0008498167,0.0007515137,0.017332729,0.00015196],"about_ca_topic_score_codex":0.000024948671,"about_ca_topic_score_gemma":0.000010914585,"teacher_disagreement_score":0.55518955,"about_ca_system_score_codex":0.000018755632,"about_ca_system_score_gemma":0.000023466448,"threshold_uncertainty_score":0.8482123},"labels":[],"label_agreement":null},{"id":"W4388848588","doi":"10.1145/3631972","title":"Improving Automated Program Repair with Domain Adaptation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Adaptation (eye); Software engineering; Domain (mathematical analysis)","score_opus":0.07110201268549876,"score_gpt":0.31706774702128526,"score_spread":0.2459657343357865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388848588","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006462396,0.000030180025,0.8142383,0.00010960389,0.00018320188,0.00017015202,0.0000019430813,0.17880225,0.000001948538],"genre_scores_gemma":[0.022467613,0.000013219212,0.9771716,0.000055565186,0.00001652538,0.00020702778,0.0000040405835,0.000027899123,0.000036502784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880886,0.0001369851,0.00017622835,0.0004206297,0.00013518197,0.00032212248],"domain_scores_gemma":[0.9972019,0.0020298804,0.000048573416,0.0005716604,0.000058543526,0.00008945129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008231703,0.00018006617,0.00020482416,0.00036563195,0.00016130877,0.000049558606,0.00028371927,0.000118559474,9.809571e-7],"category_scores_gemma":[0.0010055475,0.00016138174,0.000053858137,0.0008254279,0.000037680602,0.00015930022,0.00002145214,0.00023758918,0.0000061551286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003875078,0.00008893695,0.00045895643,0.00016740798,0.000109135646,0.000094298615,0.0018759413,0.06487897,0.00027080788,0.0005948008,0.00046998216,0.930952],"study_design_scores_gemma":[0.00032554823,0.0006509062,0.0026814546,0.00008047886,0.00002252906,0.00018180997,0.000029832896,0.9925557,0.0004087041,0.002198415,0.0005607963,0.00030382242],"about_ca_topic_score_codex":0.00007030285,"about_ca_topic_score_gemma":0.0000035098903,"teacher_disagreement_score":0.9306482,"about_ca_system_score_codex":0.000028306196,"about_ca_system_score_gemma":0.00004121796,"threshold_uncertainty_score":0.65809566},"labels":[],"label_agreement":null},{"id":"W4389386408","doi":"10.1145/3635708","title":"Learning-based Relaxation of Completeness Requirements for Data Entry Forms","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"BNP Paribas Cardif; Université du Luxembourg","keywords":"Completeness (order theory); Computer science; Field (mathematics); Artificial intelligence; Machine learning; Data mining","score_opus":0.5502892581731978,"score_gpt":0.47503419077972964,"score_spread":0.07525506739346821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389386408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01276107,0.000023376644,0.98567957,0.0004934619,0.00046014058,0.00020194426,0.00020655082,0.00016899484,0.0000049018863],"genre_scores_gemma":[0.25692028,0.00009761665,0.74102,0.00023010236,0.00003721582,0.000108654254,0.0005859643,0.000032313426,0.00096781744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984218,0.000245747,0.000425925,0.00040122197,0.00030714352,0.00019815637],"domain_scores_gemma":[0.989589,0.009231166,0.00013215735,0.0009060179,0.00008907444,0.000052582713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006153193,0.000105710715,0.00027162954,0.00039476555,0.00012956395,0.000029208353,0.0006504996,0.0000785886,0.00002881877],"category_scores_gemma":[0.013746993,0.000091026464,0.000056638695,0.00050166104,0.0000448981,0.00020604902,0.00004927591,0.00012226493,0.000013287241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023182311,0.00009413299,0.00060494547,0.00025632454,0.00015805975,0.00000242771,0.00048672434,0.39017555,0.0007389207,0.0015426031,0.0017333111,0.6039752],"study_design_scores_gemma":[0.00491807,0.001738249,0.019814517,0.0002289346,0.00040773652,0.0000110992805,0.0022539285,0.46508914,0.009232403,0.028667258,0.46668822,0.00095046137],"about_ca_topic_score_codex":0.00002136789,"about_ca_topic_score_gemma":0.000010492121,"teacher_disagreement_score":0.6030247,"about_ca_system_score_codex":0.000012788165,"about_ca_system_score_gemma":0.00002208521,"threshold_uncertainty_score":0.99456066},"labels":[],"label_agreement":null},{"id":"W4390051453","doi":"10.1145/3638246","title":"Test Generation Strategies for Building Failure Models and Explaining Spurious Failures","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering 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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spurious relationship; Computer science; Test (biology); Machine learning; Surrogate model; Test case; Reliability engineering; Artificial intelligence; Engineering","score_opus":0.13746197668598853,"score_gpt":0.34626461896241467,"score_spread":0.20880264227642614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390051453","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0482391,0.00019411591,0.9492288,0.00044575607,0.00035512878,0.0002097918,0.000012943536,0.0013138052,5.350679e-7],"genre_scores_gemma":[0.30834287,0.00008097518,0.6912599,0.000024036583,0.00006529803,0.00016300769,0.0000042944716,0.000028436643,0.000031133084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864155,0.00006825423,0.00019890071,0.0005049099,0.00015092072,0.000435481],"domain_scores_gemma":[0.990461,0.008895342,0.000027746843,0.0004246066,0.0000680262,0.0001232863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087462104,0.00021507822,0.00025232328,0.00050370645,0.00023789647,0.00018193026,0.00033802493,0.00016159481,0.0000017974935],"category_scores_gemma":[0.002442514,0.00022622461,0.00005313505,0.00046428468,0.000035950543,0.00049179874,0.000037860245,0.00028502042,0.0000022537504],"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":[0.000008378643,0.000017603184,0.000084414016,0.00015827634,0.00006486614,0.000014066695,0.0017645216,0.8968477,0.014060029,0.008473975,0.0001405063,0.07836566],"study_design_scores_gemma":[0.00073959975,0.00038748642,0.0006678272,0.00007296526,0.000029489174,0.00014628434,0.0002870038,0.9804311,0.0076502855,0.0068778633,0.0021727465,0.000537355],"about_ca_topic_score_codex":0.000018370496,"about_ca_topic_score_gemma":0.00000684179,"teacher_disagreement_score":0.26010376,"about_ca_system_score_codex":0.000029677158,"about_ca_system_score_gemma":0.000050661565,"threshold_uncertainty_score":0.9225172},"labels":[],"label_agreement":null},{"id":"W4390838289","doi":"10.1145/3640331","title":"Method-level Bug Prediction: Problems and Promises","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Software bug; Java; Class (philosophy); Software; Software regression; Granularity; Predictive modelling; Data science; Data mining; Machine learning; Software engineering; Artificial intelligence; Software development; Software quality; Programming language","score_opus":0.13377957027849616,"score_gpt":0.33783300584779025,"score_spread":0.2040534355692941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390838289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004587601,0.0021249724,0.98951787,0.00048963475,0.0009716522,0.00022879355,0.000026772885,0.0020490047,0.000003688321],"genre_scores_gemma":[0.02586551,0.0003605185,0.97310364,0.00003760088,0.00008206664,0.00017097102,0.0000022652641,0.000042457727,0.00033499568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983263,0.00017001465,0.00023562713,0.0006738312,0.00020468848,0.00038953478],"domain_scores_gemma":[0.99193335,0.007254753,0.000015536323,0.00055258034,0.000052610125,0.00019118893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013123691,0.0002476199,0.00027768366,0.0004913732,0.00012599333,0.0001682419,0.00038978487,0.00018279185,0.000013845331],"category_scores_gemma":[0.0014249762,0.00023487462,0.00006573477,0.0005667481,0.000043384887,0.00032892413,0.000048593814,0.0005860392,0.000008997785],"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":[0.000018040491,0.000059726157,0.00041662322,0.0010859738,0.00034307747,0.000074647796,0.0025532304,0.07685511,0.0030992616,0.0038134656,0.00016543598,0.9115154],"study_design_scores_gemma":[0.0026720264,0.002425461,0.040757265,0.0017888313,0.00038213778,0.006432719,0.00014188926,0.72854614,0.030421453,0.014467096,0.16896643,0.0029985725],"about_ca_topic_score_codex":0.000022327373,"about_ca_topic_score_gemma":0.000001800041,"teacher_disagreement_score":0.9085168,"about_ca_system_score_codex":0.000047358164,"about_ca_system_score_gemma":0.000055644756,"threshold_uncertainty_score":0.9577909},"labels":[],"label_agreement":null},{"id":"W4391110914","doi":"10.1145/3641847","title":"Battling against Protocol Fuzzing: Protecting Networked Embedded Devices from Dynamic Fuzzers","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Protocol (science); Computer security; Obfuscation; Encryption; Code (set theory); Overhead (engineering); Embedded system; Operating system; Programming language; Software; Set (abstract data type)","score_opus":0.050501100712676196,"score_gpt":0.33744814811419427,"score_spread":0.28694704740151805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391110914","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016283432,0.00015486246,0.98711765,0.00012354867,0.0008170839,0.005509784,0.000007650677,0.004634673,0.000006414496],"genre_scores_gemma":[0.03450336,0.000020120144,0.9499143,0.00009535966,0.00007003236,0.0153044695,0.000002235319,0.00005117307,0.000038966853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817157,0.00025666828,0.00033260157,0.0007138481,0.00014462782,0.00038068308],"domain_scores_gemma":[0.99620605,0.0029755642,0.000061181185,0.00059757783,0.00004858327,0.00011104294],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007965041,0.00029138138,0.00030580568,0.00038255902,0.00024243254,0.0001509952,0.0004715889,0.00020897995,0.000007879031],"category_scores_gemma":[0.0007085421,0.00029133956,0.000104205996,0.00058236904,0.000037105834,0.00042762744,0.000039166778,0.0008372442,0.0000066609914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025097805,0.000019278095,0.000005828471,0.00019905657,0.00009780596,0.000030681236,0.00075717823,0.10497768,0.006743821,0.00018944501,0.0000062378285,0.8869479],"study_design_scores_gemma":[0.0009049413,0.00059396744,0.00018490631,0.0012813216,0.00008894698,0.00021270009,0.00026304196,0.8727355,0.08018305,0.01236515,0.029678175,0.001508322],"about_ca_topic_score_codex":0.000015614745,"about_ca_topic_score_gemma":0.000011906034,"teacher_disagreement_score":0.8854396,"about_ca_system_score_codex":0.00009626182,"about_ca_system_score_gemma":0.000049309394,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W4391136370","doi":"10.1145/3641541","title":"Learning Failure-Inducing Models for Testing Software-Defined Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; Science Foundation Ireland","keywords":"Computer science; Software testing; Software engineering; Software; Programming language","score_opus":0.08763148271628124,"score_gpt":0.29222353392917,"score_spread":0.20459205121288876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391136370","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013142665,0.0016627712,0.9913774,0.00027416786,0.001703401,0.00025611828,0.0000063272023,0.0034011998,0.000004318486],"genre_scores_gemma":[0.1048759,0.00010185666,0.89429873,0.00013399322,0.00021797683,0.00017829996,0.000006247811,0.000079948986,0.00010702877],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774104,0.00016778111,0.00038454297,0.00086288544,0.00015669003,0.0006870483],"domain_scores_gemma":[0.98427516,0.014817056,0.000054910906,0.0005734317,0.0000992028,0.00018022013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012770592,0.00037777316,0.00045271305,0.00038814286,0.0003803593,0.00023883094,0.0005205642,0.0003170196,0.000004961932],"category_scores_gemma":[0.0025844728,0.00037651896,0.00017728044,0.00081545673,0.000038103593,0.0003704324,0.000046861132,0.00086772855,0.000004444103],"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":[0.000008492663,0.000009413383,0.00002527822,0.00008297127,0.00006655804,0.0000102255,0.00028466774,0.65630776,0.000059910286,0.0027205348,0.000043190146,0.34038103],"study_design_scores_gemma":[0.0003428526,0.0003568791,0.000060779985,0.00026199393,0.00007398643,0.00018541868,0.00002709847,0.9845549,0.00019478645,0.009494428,0.0039686062,0.00047827233],"about_ca_topic_score_codex":0.000029551475,"about_ca_topic_score_gemma":0.000004389921,"teacher_disagreement_score":0.33990276,"about_ca_system_score_codex":0.00006169785,"about_ca_system_score_gemma":0.00007399729,"threshold_uncertainty_score":0.9998687},"labels":[],"label_agreement":null},{"id":"W4391444574","doi":"10.1145/3641543","title":"Beyond Fidelity: Explaining Vulnerability Localization of Learning-Based Detectors","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Fidelity; Vulnerability (computing); Detector; Computer security; Telecommunications","score_opus":0.04447907595058553,"score_gpt":0.31488102608238366,"score_spread":0.27040195013179813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391444574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007770755,0.00025499248,0.99015313,0.00010628904,0.00086346484,0.000077647186,0.0000023034904,0.00076663075,0.0000047782783],"genre_scores_gemma":[0.5044384,0.000009033744,0.495467,0.000024036568,0.000020213736,0.00001233472,0.0000017580121,0.000014392614,0.000012793925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985184,0.00043806364,0.00027174942,0.00041686962,0.00014532772,0.00020958869],"domain_scores_gemma":[0.99459535,0.004845299,0.000044112065,0.00039211282,0.000054439875,0.00006865957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013922516,0.00016631646,0.0002571427,0.00032116615,0.00013524567,0.000039534876,0.00028244234,0.00014289981,0.000018593611],"category_scores_gemma":[0.0029786355,0.00016869049,0.000082232036,0.00050994375,0.000054291802,0.0001895516,0.00002111834,0.0005862278,0.0000019805354],"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":[0.000009156186,0.000010241326,0.00017823456,0.00012264155,0.000027191323,0.0000046212604,0.0005268434,0.8857512,0.00031738495,0.0008904562,0.000001276942,0.11216076],"study_design_scores_gemma":[0.0001766605,0.00016310129,0.0001952921,0.00007770793,0.000029920877,0.000015788815,0.000038342056,0.9920622,0.005093803,0.0010764727,0.000896433,0.00017428685],"about_ca_topic_score_codex":0.000028343586,"about_ca_topic_score_gemma":0.0000026763482,"teacher_disagreement_score":0.49666768,"about_ca_system_score_codex":0.000044187815,"about_ca_system_score_gemma":0.000057699493,"threshold_uncertainty_score":0.6878999},"labels":[],"label_agreement":null},{"id":"W4391614448","doi":"10.1145/3643671","title":"Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","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":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; Université du Luxembourg","keywords":"Computer science; Cluster analysis; Artificial intelligence; Data mining; Software engineering","score_opus":0.08917448517718657,"score_gpt":0.349973502449047,"score_spread":0.26079901727186044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391614448","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010417055,0.0003747014,0.9971748,0.00027483018,0.0003981367,0.0000715727,0.00001065175,0.00063939486,0.00001419184],"genre_scores_gemma":[0.30435258,0.000011410474,0.6955246,0.00003468781,0.000020700596,0.000010642831,0.000005304784,0.000018853252,0.000021257485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984315,0.00021231038,0.0003819241,0.00051037123,0.00015539315,0.0003084743],"domain_scores_gemma":[0.9965872,0.0027674187,0.00007945335,0.00046618326,0.000039881645,0.000059830054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011969166,0.00020648284,0.00044895973,0.00057385955,0.0001399209,0.00007457799,0.00042808897,0.00013265481,0.000020880578],"category_scores_gemma":[0.00083785586,0.00020322815,0.0001898665,0.0014050899,0.000067387446,0.0003453462,0.00003623984,0.00045083842,0.0000011652172],"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":[0.000011054266,0.000013658403,0.000049366336,0.00019884882,0.0002637138,0.00001007069,0.0014934934,0.8489786,0.00026023635,0.0007725127,9.340198e-7,0.1479475],"study_design_scores_gemma":[0.00013350484,0.000049130587,0.0003860801,0.00007029708,0.000385865,0.000015984508,0.00009784224,0.99677914,0.001236854,0.00022548274,0.00042580676,0.00019401991],"about_ca_topic_score_codex":0.000034877474,"about_ca_topic_score_gemma":0.000009415133,"teacher_disagreement_score":0.30331087,"about_ca_system_score_codex":0.00004330109,"about_ca_system_score_gemma":0.00006480154,"threshold_uncertainty_score":0.8287403},"labels":[],"label_agreement":null},{"id":"W4391614764","doi":"10.1145/3644388","title":"DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Black box; Artificial neural network; Artificial intelligence; Deep neural networks; Machine learning; Test (biology)","score_opus":0.0672593941211773,"score_gpt":0.31481957568626506,"score_spread":0.24756018156508774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391614764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002063585,0.00059376843,0.9861279,0.00008165612,0.0006214374,0.00030228554,0.0000064511496,0.012057963,0.0000021509095],"genre_scores_gemma":[0.15537937,0.000029208319,0.8440926,0.000089898014,0.00008365029,0.000236933,0.0000046523796,0.00004022201,0.00004348699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998518,0.00012562031,0.00022193171,0.0006458594,0.00009242849,0.00039615345],"domain_scores_gemma":[0.99214107,0.0072510005,0.000032398835,0.00038974578,0.00007945255,0.00010632608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007457686,0.00026317753,0.0002825395,0.0003564174,0.00018719949,0.00012645725,0.00035626293,0.00022444018,0.0000015643705],"category_scores_gemma":[0.002091928,0.00025675242,0.0001265354,0.00057944603,0.000053459025,0.00020522186,0.000021754127,0.0004898547,0.0000011573505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019349767,0.00011586762,0.00025423727,0.00019810328,0.000113356495,0.000008329506,0.0009808593,0.44980103,0.00015252084,0.00067480723,0.0001240089,0.54755753],"study_design_scores_gemma":[0.00020957178,0.00030967325,0.00025317277,0.00003457642,0.00004708979,0.00020090745,0.000008963939,0.9966417,0.00072517886,0.0010928365,0.00020896494,0.0002673716],"about_ca_topic_score_codex":0.000025518633,"about_ca_topic_score_gemma":0.0000027973,"teacher_disagreement_score":0.54729015,"about_ca_system_score_codex":0.0000643727,"about_ca_system_score_gemma":0.000026175549,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4392347631","doi":"10.1145/3649598","title":"Communicating Study Design Trade-offs in Software Engineering","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; University of Victoria; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland; European Commission; National Science Foundation","keywords":"Computer science; Work (physics); Reflection (computer programming); Process (computing); Risk analysis (engineering); Management science; Strengths and weaknesses; Engineering ethics; Psychology; Business; Engineering; Social psychology","score_opus":0.12728410333757412,"score_gpt":0.3491946088004384,"score_spread":0.22191050546286428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392347631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028431121,0.0017374925,0.9655984,0.00020589317,0.0009244714,0.0004738316,0.000005238757,0.0026228363,7.211469e-7],"genre_scores_gemma":[0.32819286,0.00008848475,0.6713652,0.0000263641,0.00003559448,0.00020142399,0.000001324307,0.000064976375,0.000023763376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972718,0.00044324296,0.00046929903,0.00080173416,0.00031426098,0.0006996983],"domain_scores_gemma":[0.9768971,0.021507064,0.000026605008,0.0013407947,0.000030281497,0.0001981049],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026136995,0.00040805337,0.0004974058,0.0011047476,0.00012800557,0.00019330949,0.001277395,0.00022268364,0.000010056588],"category_scores_gemma":[0.005913824,0.00043245085,0.0001083181,0.0013797869,0.000037224694,0.00038987328,0.00010208149,0.0014050027,0.000013740863],"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":[0.000027831742,0.00028571702,0.0025596363,0.00043323217,0.00028602008,0.00037105667,0.0073435144,0.7370549,0.00095006794,0.00061945396,0.00004377628,0.25002483],"study_design_scores_gemma":[0.0031956313,0.002568156,0.07828748,0.0016948594,0.00019295984,0.0012213693,0.0005939334,0.89418244,0.007426985,0.00086014,0.0064778794,0.0032981664],"about_ca_topic_score_codex":0.00005445901,"about_ca_topic_score_gemma":0.0000063740317,"teacher_disagreement_score":0.29976174,"about_ca_system_score_codex":0.00016603648,"about_ca_system_score_gemma":0.00008881828,"threshold_uncertainty_score":0.9998127},"labels":[],"label_agreement":null},{"id":"W4392593558","doi":"10.1145/3649597","title":"Lessons Learned from Developing a Sustainability Awareness Framework for Software Engineering Using Design Science","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Green IT and Sustainability","field":"Engineering","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":"Vector Institute","funders":"Engineering and Physical Sciences Research Council","keywords":"Sustainability; Computer science; Process (computing); Work (physics); Process management; Engineering management; Sustainable development; Knowledge management; Management science; Risk analysis (engineering); Software engineering; Engineering; Business","score_opus":0.2091774411769321,"score_gpt":0.38913597300434755,"score_spread":0.17995853182741545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392593558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0978571,0.0009869417,0.89692307,0.00020937598,0.0015496914,0.00046578713,0.00005946188,0.0019483261,2.2013792e-7],"genre_scores_gemma":[0.27066278,0.00007423461,0.72888863,0.000015527778,0.00008775531,0.00016457301,0.0000052268233,0.00009326706,0.00000798351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976339,0.000105223626,0.00040272193,0.0008105474,0.00020569087,0.0008419428],"domain_scores_gemma":[0.99031526,0.008547464,0.000023919554,0.0006702606,0.00022886778,0.00021423455],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017475227,0.00044816124,0.0005336754,0.0005897655,0.0003619496,0.00016596499,0.0004131527,0.00036888325,0.000012197502],"category_scores_gemma":[0.008822516,0.0004846108,0.00015844517,0.000976762,0.00015326963,0.0003420686,0.00003084868,0.00072053954,0.0000015235623],"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":[0.000035957204,0.000016086502,0.00014501471,0.0010827719,0.00013563172,0.00001545503,0.0010711763,0.8882631,0.0014948214,0.0020447336,0.0000033191027,0.1056919],"study_design_scores_gemma":[0.0005752236,0.00017966062,0.002253466,0.00074182416,0.00032844048,0.00006990538,0.0008223039,0.8906966,0.028254732,0.0717225,0.0027288191,0.0016265078],"about_ca_topic_score_codex":0.000085403466,"about_ca_topic_score_gemma":0.0000047464086,"teacher_disagreement_score":0.1728057,"about_ca_system_score_codex":0.0007729075,"about_ca_system_score_gemma":0.00049753085,"threshold_uncertainty_score":0.99976057},"labels":[],"label_agreement":null},{"id":"W4396773582","doi":"10.1145/3664606","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Alberta","funders":"National Research Foundation Singapore","keywords":"Computer science; Syntax; Abstract syntax tree; Abstract syntax; Programming language; Semantics (computer science); Syntax error; Artificial intelligence; Natural language processing; Code (set theory); Source code","score_opus":0.12010431418201437,"score_gpt":0.3292689790807466,"score_spread":0.20916466489873223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396773582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092113815,0.0018158911,0.9031916,0.00037586616,0.00065985037,0.00012457882,0.000014800356,0.0017008687,0.0000026834573],"genre_scores_gemma":[0.32703725,0.00020268577,0.67248774,0.000043819276,0.000043205666,0.00004156076,0.0000013731278,0.0000360527,0.0001063211],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984082,0.00013838845,0.00025245908,0.00056728034,0.00020309478,0.0004306012],"domain_scores_gemma":[0.99047303,0.008758945,0.000019359995,0.00050745206,0.000048440284,0.00019276436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010345179,0.00025850968,0.0002968393,0.00044585086,0.0001544051,0.00017821038,0.00037950682,0.0001752276,0.000004529952],"category_scores_gemma":[0.0025360924,0.00026216035,0.000059950133,0.0004510288,0.00012891492,0.00040486341,0.00004736915,0.00064894883,0.0000033177305],"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":[0.000014272454,0.000038392936,0.00019176857,0.0018531292,0.00037437773,0.00010931556,0.014952563,0.77610284,0.0062191444,0.021354903,0.00007028299,0.17871903],"study_design_scores_gemma":[0.00023598995,0.00016453235,0.00050012325,0.00043666828,0.00004604606,0.00043297734,0.00015903523,0.98355496,0.0063655507,0.006844719,0.00078015105,0.0004792241],"about_ca_topic_score_codex":0.000035889403,"about_ca_topic_score_gemma":0.00000427817,"teacher_disagreement_score":0.23492342,"about_ca_system_score_codex":0.000050419414,"about_ca_system_score_gemma":0.00006862812,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W4396871622","doi":"10.1145/3664599","title":"On the Model Update Strategies for Supervised Learning in AIOps Solutions","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Polytechnique Montréal; Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.11905621126172586,"score_gpt":0.32602654953751875,"score_spread":0.2069703382757929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396871622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037019218,0.00018152191,0.99337894,0.0012345284,0.00022071024,0.00014594036,0.0000225181,0.0011058934,0.000008004225],"genre_scores_gemma":[0.16891043,0.00009731297,0.83062905,0.00011082402,0.000011208151,0.00017915321,0.0000045121187,0.000016957496,0.000040540566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990749,0.00012351773,0.00014663184,0.00032861,0.00006766911,0.00025869432],"domain_scores_gemma":[0.99551725,0.0039973203,0.00001219636,0.00041855813,0.000019403884,0.000035272606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009473041,0.00013883795,0.00014928977,0.0002620701,0.00013749531,0.00011941924,0.00043317888,0.00009244747,0.0000036729737],"category_scores_gemma":[0.00058350764,0.000112597736,0.00005469739,0.00027101653,0.00003202237,0.00024062861,0.000023223774,0.0004149623,0.0000029248363],"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":[0.000014336378,0.000028888593,0.0000025674578,0.00006876118,0.00004347544,0.000006231137,0.0013332013,0.55382055,0.00072844344,0.2960643,0.00030200987,0.14758724],"study_design_scores_gemma":[0.00011220212,0.00014793484,0.000022759186,0.00008807711,0.000014595707,0.000019634941,0.000079960475,0.9510198,0.00086337054,0.045901626,0.001570493,0.0001595362],"about_ca_topic_score_codex":0.000014458473,"about_ca_topic_score_gemma":0.000007129744,"teacher_disagreement_score":0.39719927,"about_ca_system_score_codex":0.00002976514,"about_ca_system_score_gemma":0.0000677378,"threshold_uncertainty_score":0.45916024},"labels":[],"label_agreement":null},{"id":"W4396871671","doi":"10.1145/3664601","title":"Testing Updated Apps by Adapting Learned Models","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Computer science; Correctness; Adaptation (eye); Software; Software inspection; Software performance testing; Machine learning; Software engineering; Human–computer interaction; Software development; Software quality; Operating system; Software construction; Programming language","score_opus":0.1504107154579445,"score_gpt":0.32533558583462185,"score_spread":0.17492487037667737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396871671","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015173838,0.0011612372,0.97401685,0.0002777055,0.00047356656,0.00009113009,0.000007733946,0.022437379,0.000017029053],"genre_scores_gemma":[0.1220973,0.00003867004,0.8775322,0.00011895673,0.000029011919,0.000041885407,0.0000037809382,0.000037305173,0.000100924364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984988,0.00015573496,0.0002443892,0.0005950379,0.00013730247,0.00036873893],"domain_scores_gemma":[0.9937888,0.005451973,0.000030515275,0.0005581787,0.00005436626,0.000116212446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010145092,0.00023750284,0.00025532415,0.00029706556,0.00016516619,0.00014824719,0.00046509667,0.00016775892,0.0000043910113],"category_scores_gemma":[0.001732681,0.00023594644,0.00006323133,0.00065020483,0.00003525448,0.00030808846,0.000035860816,0.0005202289,0.000006924128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005658148,0.00002794928,0.000020609457,0.00008147678,0.00006339031,0.000029953197,0.00044943014,0.03542572,0.0018059883,0.0015599903,0.0009931903,0.9595367],"study_design_scores_gemma":[0.00016849159,0.00023823166,0.000046352994,0.0002748262,0.00004074526,0.00036533992,0.000009838456,0.95856214,0.003474042,0.033093996,0.0032415877,0.0004843929],"about_ca_topic_score_codex":0.000069800975,"about_ca_topic_score_gemma":4.1309144e-7,"teacher_disagreement_score":0.95905226,"about_ca_system_score_codex":0.000038331367,"about_ca_system_score_gemma":0.000044070668,"threshold_uncertainty_score":0.96216166},"labels":[],"label_agreement":null},{"id":"W4399601886","doi":"10.1145/3672457","title":"<i>GIST</i> : Generated Inputs Sets Transferability in Deep Learning","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Scratch; Test set; GiST; Testability; Test (biology); Set (abstract data type); Artificial intelligence; Property (philosophy); Artificial neural network; Machine learning; Transfer of learning; Data mining; Reliability engineering; Programming language","score_opus":0.04779516566455851,"score_gpt":0.31123246473109833,"score_spread":0.26343729906653984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399601886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03212128,0.0005659097,0.96474695,0.0004717308,0.0009844042,0.00010210352,0.000001732152,0.0009976539,0.000008236391],"genre_scores_gemma":[0.42182374,0.000080326994,0.577918,0.000064750326,0.000026078598,0.000026077178,0.000002103397,0.00002117869,0.000037781414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981737,0.0005189678,0.00026729374,0.0005796716,0.00012394317,0.0003364366],"domain_scores_gemma":[0.9967943,0.0026894524,0.000016217911,0.00038216842,0.000027043567,0.000090863185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012579607,0.00021588354,0.0002973863,0.0003674011,0.000116138996,0.00007916122,0.0003682734,0.00018477895,0.000017428452],"category_scores_gemma":[0.0010025454,0.00022214017,0.00007346048,0.0006935068,0.000039152244,0.00026522073,0.000021054284,0.001104523,0.0000068983763],"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":[0.000009907412,0.000017074648,0.00017291403,0.00007740519,0.000028755298,0.000043044856,0.0014073388,0.7082142,0.0007948376,0.000695565,0.0000012750086,0.28853768],"study_design_scores_gemma":[0.0005327291,0.00020663952,0.0024302106,0.00012465141,0.000035683526,0.00017804025,0.000037581398,0.98721933,0.002827532,0.0015128319,0.0043842187,0.0005105318],"about_ca_topic_score_codex":0.00004123545,"about_ca_topic_score_gemma":0.000019075882,"teacher_disagreement_score":0.38970247,"about_ca_system_score_codex":0.00007139752,"about_ca_system_score_gemma":0.000040238123,"threshold_uncertainty_score":0.9058613},"labels":[],"label_agreement":null},{"id":"W4399619591","doi":"10.1145/3672449","title":"An Empirical Study on the Characteristics of Database Access Bugs in Java Applications","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Database; SQL; Java; Database schema; Stored procedure; Query by Example; View; Commit; Database model; Database design; World Wide Web; Programming language; Web search query","score_opus":0.16223068351507128,"score_gpt":0.4138237030113616,"score_spread":0.2515930194962903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399619591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052035023,0.00005990022,0.94482696,0.00030855872,0.0001919388,0.00025454175,0.000018772236,0.002302598,0.0000017240727],"genre_scores_gemma":[0.61005265,0.000019021727,0.38960946,0.00009780752,0.000019983521,0.00018109688,0.0000024804974,0.000013028454,0.000004466948],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99884033,0.000254499,0.00023900793,0.00038309966,0.00011752061,0.00016555694],"domain_scores_gemma":[0.99294806,0.0060236384,0.000029322842,0.0009097428,0.000033400425,0.000055844324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011421186,0.00014204666,0.0002091479,0.00032468405,0.00007228038,0.000076102544,0.0007359617,0.00007136938,0.0000035275398],"category_scores_gemma":[0.000812518,0.00011003682,0.00003540812,0.00057719514,0.00003834155,0.00016161971,0.000033256827,0.00038744946,0.000002133665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050401508,0.0013984486,0.01793093,0.00029725218,0.00014684362,0.00007815703,0.005931817,0.0047509,0.0009242333,0.004573623,0.0002764047,0.963641],"study_design_scores_gemma":[0.002064476,0.007250251,0.4665651,0.00193771,0.00046959423,0.0006046954,0.0005873355,0.43674102,0.01837249,0.052878823,0.009243886,0.0032846236],"about_ca_topic_score_codex":0.000046523826,"about_ca_topic_score_gemma":0.0000025068202,"teacher_disagreement_score":0.96035635,"about_ca_system_score_codex":0.000021596741,"about_ca_system_score_gemma":0.00004091522,"threshold_uncertainty_score":0.44871712},"labels":[],"label_agreement":null},{"id":"W4400480621","doi":"10.1145/3678168","title":"Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality","year":2024,"lang":"en","type":"preprint","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Cloud Computing and Resource Management","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":"Huawei Technologies (Canada); University of Alberta","funders":"University of Alberta","keywords":"Computer science; Artificial intelligence; Quality (philosophy); Deep learning; Software; Machine learning; Programming language; Physics","score_opus":0.10399543823728415,"score_gpt":0.3530575879943977,"score_spread":0.24906214975711355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400480621","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":[0.34785745,0.00082695246,0.6498109,0.00023403404,0.00059781066,0.00018816192,0.000016872822,0.00046437903,0.0000034594666],"genre_scores_gemma":[0.6526646,0.00016528921,0.34671965,0.000043366595,0.00008474834,0.000039316936,0.0000037516122,0.00005048369,0.00022876545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975719,0.00061237166,0.00042052378,0.0007950447,0.00024680683,0.0003533513],"domain_scores_gemma":[0.99375623,0.0050022057,0.00015046356,0.0009303019,0.000058336198,0.000102455146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023739445,0.00041715373,0.0006210634,0.00045571354,0.00025136428,0.00012738934,0.0007492667,0.00025643298,0.0000036858225],"category_scores_gemma":[0.0013056427,0.0002933189,0.00027836332,0.0003223614,0.000081856066,0.000012465822,0.00047285762,0.0019827902,0.0000023995183],"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":[0.00002499583,0.000049060032,0.00039789767,0.00038023872,0.00045193202,0.000009964553,0.0025046726,0.79974663,0.000078875295,0.00023080606,0.000013709798,0.19611122],"study_design_scores_gemma":[0.002262217,0.0035606017,0.059875682,0.0033335676,0.0009203267,0.00035495905,0.0007196028,0.9085407,0.0017313187,0.014032458,0.0015469311,0.0031216156],"about_ca_topic_score_codex":0.00049258623,"about_ca_topic_score_gemma":0.0000040494874,"teacher_disagreement_score":0.3048072,"about_ca_system_score_codex":0.000081859034,"about_ca_system_score_gemma":0.00004681625,"threshold_uncertainty_score":0.9999519},"labels":[],"label_agreement":null},{"id":"W4400652308","doi":"10.1145/3678172","title":"A Disruptive Research Playbook for Studying Disruptive Innovations","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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 Victoria","funders":"","keywords":"Computer science; Disruptive technology; Transformative learning; Framing (construction); Disruptive innovation; Emerging technologies; Software; Generative grammar; Data science; Empirical research; Management science; Artificial intelligence; Sociology; Engineering","score_opus":0.25035296368953364,"score_gpt":0.4320521837769804,"score_spread":0.18169922008744677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400652308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009375312,0.00072580675,0.9861923,0.00067832065,0.0011515208,0.0005334598,0.00003669362,0.0013002568,0.0000063425096],"genre_scores_gemma":[0.1828338,0.0000640131,0.8156891,0.000041396685,0.00011709679,0.00077629933,0.0000050184717,0.00005662928,0.00041663984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773777,0.00023437421,0.00027643677,0.0007564809,0.00033749983,0.000657472],"domain_scores_gemma":[0.9674499,0.03142735,0.000016553357,0.0007007201,0.00025461396,0.0001508392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028709776,0.00023967461,0.00028978352,0.0012309097,0.00033867502,0.00021238903,0.0006792759,0.00017693585,0.000008422667],"category_scores_gemma":[0.0064022904,0.00023510882,0.00009967405,0.0016299849,0.00009740323,0.00035617748,0.00007180408,0.00096806075,0.000018729981],"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":[0.00012866214,0.000280178,0.00040073038,0.0011938956,0.0010271362,0.00016152246,0.01796687,0.065778464,0.0043440065,0.12727483,0.0010428997,0.7804008],"study_design_scores_gemma":[0.0059695104,0.008286358,0.025305208,0.003184643,0.00041954697,0.0015949084,0.0032104766,0.6155519,0.043776724,0.080616616,0.20613784,0.0059463005],"about_ca_topic_score_codex":0.0000144432925,"about_ca_topic_score_gemma":0.0000023377784,"teacher_disagreement_score":0.77445453,"about_ca_system_score_codex":0.00015875456,"about_ca_system_score_gemma":0.00014061692,"threshold_uncertainty_score":0.95874596},"labels":[],"label_agreement":null},{"id":"W4400685466","doi":"10.1145/3676961","title":"SimClone: Detecting Tabular Data Clones Using Value Similarity","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Computer science; Data mining; Header; Software; Visualization; clone (Java method); Similarity (geometry); Margin (machine learning); Artificial intelligence; Image (mathematics); Machine learning","score_opus":0.549696504884526,"score_gpt":0.4849508565192975,"score_spread":0.06474564836522856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400685466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019102538,0.0011075753,0.9766895,0.00047750835,0.001892082,0.00012793219,0.0001900513,0.0004058137,0.000007009971],"genre_scores_gemma":[0.120691255,0.00015430944,0.87860125,0.00021182167,0.00012195122,0.00001045791,0.000019974581,0.000032651722,0.00015630123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973462,0.00057116704,0.0004746813,0.0008655053,0.00042145548,0.00032096653],"domain_scores_gemma":[0.98677385,0.011328391,0.000049390124,0.0016777267,0.000052055544,0.000118587865],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00823037,0.00020710708,0.00035782103,0.00046951816,0.00024308261,0.00026424433,0.0009938305,0.00015274106,0.00008419241],"category_scores_gemma":[0.0116965845,0.00018171356,0.00008206233,0.00070417416,0.00006942535,0.000524469,0.00014674795,0.00046163387,0.000028081171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004344147,0.00006273903,0.000076519595,0.00022685176,0.00032094464,0.000086981374,0.00085015566,0.19737811,0.0016414718,0.003315311,0.0004023531,0.7955951],"study_design_scores_gemma":[0.0006260757,0.00025050694,0.00081041275,0.00029379642,0.0007064644,0.00028246173,0.0016946119,0.61605173,0.005319016,0.03222547,0.34060052,0.0011389129],"about_ca_topic_score_codex":0.00015104449,"about_ca_topic_score_gemma":0.000025980904,"teacher_disagreement_score":0.7944562,"about_ca_system_score_codex":0.000033954268,"about_ca_system_score_gemma":0.00004291626,"threshold_uncertainty_score":0.99662834},"labels":[],"label_agreement":null},{"id":"W4400934506","doi":"10.1145/3680463","title":"An Empirical Study of Testing Machine Learning in the Wild","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","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":"Queen's University; York University; Polytechnique Montréal","funders":"","keywords":"Computer science; White-box testing; Regression testing; Oracle; Test strategy; Workflow; Quality assurance; Machine learning; Software reliability testing; Manual testing; Software quality; Empirical research; Non-regression testing; Software performance testing; Software engineering; Artificial intelligence; Software testing; Software; Software system; Software construction; Software development; Database; Programming language","score_opus":0.1074213531816717,"score_gpt":0.370455849240389,"score_spread":0.2630344960587173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400934506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16763058,0.00014425101,0.83141166,0.00015495495,0.0002629766,0.00009541404,5.6238497e-7,0.00029632324,0.000003245156],"genre_scores_gemma":[0.57212114,0.000004274119,0.4278005,0.000026032283,0.000018926388,0.0000132142395,3.5369416e-7,0.000009347805,0.000006196258],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835217,0.0007828331,0.00021277514,0.00033220573,0.00013768811,0.00018233832],"domain_scores_gemma":[0.9927317,0.0067903283,0.000026164236,0.0003952949,0.000020270978,0.000036241043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018193594,0.0001320767,0.00020311117,0.0002851225,0.00010202136,0.000047583395,0.0005174559,0.00007182019,0.000003173845],"category_scores_gemma":[0.00182242,0.00010295554,0.000030419538,0.0007248658,0.000022982924,0.00017956193,0.000020746333,0.000866452,8.9614247e-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":[0.000006558609,0.0000900351,0.0065649156,0.00003320345,0.000022413076,0.00003502746,0.0076433434,0.81092286,0.00014365112,0.000151376,7.030007e-7,0.1743859],"study_design_scores_gemma":[0.00032760398,0.0011138662,0.014209314,0.000058178444,0.00003362363,0.00012650689,0.00066320744,0.98259884,0.000062928564,0.00033990064,0.0002880776,0.00017796732],"about_ca_topic_score_codex":0.00012515215,"about_ca_topic_score_gemma":0.000016865702,"teacher_disagreement_score":0.40449056,"about_ca_system_score_codex":0.00001691945,"about_ca_system_score_gemma":0.000024451969,"threshold_uncertainty_score":0.41984054},"labels":[],"label_agreement":null},{"id":"W4401021697","doi":"10.1145/3680470","title":"Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Green IT and Sustainability","field":"Engineering","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","funders":"","keywords":"Computer science; Energy consumption; Granularity; Energy accounting; Energy (signal processing); Efficient energy use; Instrumentation (computer programming); Deep learning; Work (physics); Artificial intelligence; Operating system; Mechanical engineering; Electrical engineering; Engineering","score_opus":0.05270298121953904,"score_gpt":0.2806003900837206,"score_spread":0.22789740886418158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401021697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016938413,0.004149367,0.9766953,0.00006894893,0.0009306287,0.000059048743,0.0000030467068,0.0011297247,0.000025542797],"genre_scores_gemma":[0.8920755,0.00035945678,0.10716467,0.00002316919,0.00007129956,0.00012168492,0.0000058616924,0.00007420513,0.000104187886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846715,0.0001805897,0.00033675588,0.00039189347,0.00017198554,0.0004516021],"domain_scores_gemma":[0.9985158,0.0010350333,0.000012571053,0.00029563013,0.00005480354,0.000086195665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008134051,0.0002984579,0.00037701617,0.00033741895,0.00008961453,0.000037969512,0.00014584219,0.00022308146,0.000031738316],"category_scores_gemma":[0.000558004,0.00031294057,0.00010573608,0.0004625571,0.00003165285,0.00014887753,0.000009901659,0.00049096276,0.0000019239542],"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":[0.000026203264,0.000030424582,0.00015444876,0.0006217302,0.00015940893,0.000063080064,0.0021297913,0.712135,0.0046569714,0.0012969896,0.000010582713,0.27871534],"study_design_scores_gemma":[0.0028891754,0.00086601084,0.0038639188,0.0016477432,0.00048388902,0.00038662393,0.0029054116,0.69986314,0.13527103,0.019006612,0.12888837,0.003928078],"about_ca_topic_score_codex":0.00031195045,"about_ca_topic_score_gemma":0.0006913448,"teacher_disagreement_score":0.87513703,"about_ca_system_score_codex":0.000228828,"about_ca_system_score_gemma":0.000041831692,"threshold_uncertainty_score":0.9999323},"labels":[],"label_agreement":null},{"id":"W4401047823","doi":"10.1145/3680468","title":"Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Evolutionary algorithm; Population; Evolutionary robotics; Domain knowledge","score_opus":0.12685296961192286,"score_gpt":0.3405972594143513,"score_spread":0.21374428980242846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401047823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005557078,0.0007651869,0.9841644,0.000114898074,0.0011612342,0.00025181173,0.0000032651803,0.012969781,0.000013670252],"genre_scores_gemma":[0.12530477,0.000034169225,0.87402195,0.000034994853,0.000057570946,0.00021064004,0.000004288781,0.000025862713,0.0003057269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874574,0.00009632128,0.00026722605,0.0003901248,0.00013619485,0.0003643716],"domain_scores_gemma":[0.99042857,0.008982731,0.00002805123,0.00036815138,0.00009480803,0.00009767777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010293993,0.00018742544,0.00022298915,0.00040548368,0.00024309436,0.00013840354,0.00033036174,0.00013413673,0.000001707372],"category_scores_gemma":[0.002859866,0.00018461476,0.00006940481,0.00041270687,0.000031423748,0.00021954626,0.000031198302,0.0004037939,0.000004841588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011226152,0.000014446324,0.000120845194,0.0005860868,0.000081410595,0.000013806776,0.0008091304,0.6531241,0.00018037256,0.004245945,0.00031830807,0.3404943],"study_design_scores_gemma":[0.00015737278,0.0004478839,0.00017432695,0.00032313645,0.000025011956,0.0002834617,0.000016700613,0.98969346,0.00046891067,0.0011589122,0.0069838753,0.00026694758],"about_ca_topic_score_codex":0.00006891335,"about_ca_topic_score_gemma":2.3601935e-7,"teacher_disagreement_score":0.34022737,"about_ca_system_score_codex":0.000114439106,"about_ca_system_score_gemma":0.0001509167,"threshold_uncertainty_score":0.7528372},"labels":[],"label_agreement":null},{"id":"W4401123839","doi":"10.1145/3680472","title":"MULTICR: Predicting Merged and Abandoned Code Changes in Modern Code Review Using Multi-Objective Search","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Code review; Code (set theory); Machine learning; Eclipse; Process (computing); Artificial intelligence; Software quality; Interoperability; Genetic programming; Search-based software engineering; Data mining; Software engineering; Software; Software development; Software development process; Programming language; World Wide Web","score_opus":0.15337003444371033,"score_gpt":0.38079161845485976,"score_spread":0.22742158401114942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401123839","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05988699,0.019201266,0.91897285,0.0003036054,0.0004898114,0.0003576877,0.000024329365,0.000763112,3.6925226e-7],"genre_scores_gemma":[0.17779359,0.005955978,0.8159422,0.00006654488,0.000038492763,0.00010777268,0.0000021290027,0.00005506844,0.000038230424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790204,0.00033670815,0.0002787036,0.0007277379,0.00023025904,0.00052452623],"domain_scores_gemma":[0.99263126,0.006611885,0.000021455955,0.0005018106,0.000069236245,0.00016438201],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001961953,0.00027590492,0.00045131778,0.000659961,0.00011498608,0.00007769947,0.00037175615,0.00016796515,0.0000046975074],"category_scores_gemma":[0.0029387847,0.00027783995,0.000060446037,0.0007583944,0.000058770867,0.00024019092,0.00006886549,0.00082481414,0.0000018668068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006527308,0.00015962508,0.0034950909,0.007691488,0.00047216655,0.00030322964,0.010527253,0.2976177,0.019256692,0.0001864457,0.000011888012,0.6602131],"study_design_scores_gemma":[0.00063765433,0.0001313245,0.0037003995,0.0023245355,0.000053763513,0.00027598275,0.00005485647,0.98731,0.0048707603,0.000063447274,0.00018317129,0.00039413347],"about_ca_topic_score_codex":0.00011625328,"about_ca_topic_score_gemma":0.0000692673,"teacher_disagreement_score":0.68969226,"about_ca_system_score_codex":0.00011541244,"about_ca_system_score_gemma":0.000071810086,"threshold_uncertainty_score":0.9999674},"labels":[],"label_agreement":null},{"id":"W4401635770","doi":"10.1145/3688841","title":"An Exploratory Study on Machine Learning Model Management","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Calgary; Concordia University","funders":"","keywords":"Documentation; Computer science; Software versioning; Software engineering; Automation; Code refactoring; Knowledge management; Data science; Process management; Software; Engineering","score_opus":0.10743960691064752,"score_gpt":0.35192113569131234,"score_spread":0.24448152878066481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401635770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04163521,0.00031726967,0.9546192,0.000078916106,0.0006385975,0.00022501076,0.000004264713,0.0024769744,0.000004500735],"genre_scores_gemma":[0.4782219,0.00006894397,0.5213235,0.00003292789,0.000026069672,0.00012983073,0.0000016610362,0.000042857417,0.00015231346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818385,0.00027535358,0.00019518439,0.0006973616,0.0002736287,0.00037465332],"domain_scores_gemma":[0.9962017,0.002740029,0.000012675335,0.0008460813,0.000028899307,0.0001706328],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013606726,0.000255229,0.0002376097,0.0007083096,0.00014076309,0.00013548289,0.00062391564,0.000097081815,0.0000068875415],"category_scores_gemma":[0.00043480535,0.00025033994,0.00006184314,0.0005137897,0.000020622365,0.0002878561,0.000040505885,0.00078422035,0.000024227502],"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":[0.000015153884,0.00014597477,0.00012288181,0.00009308777,0.00013355586,0.00011649904,0.002682626,0.8539284,0.00023584488,0.001107948,0.00000975748,0.1414083],"study_design_scores_gemma":[0.0004725548,0.0012600467,0.0012073014,0.00009623895,0.00004896882,0.000049121598,0.00022876108,0.99350595,0.00093371357,0.0005815494,0.0011444465,0.00047131995],"about_ca_topic_score_codex":0.0000053215235,"about_ca_topic_score_gemma":0.000001960427,"teacher_disagreement_score":0.43658668,"about_ca_system_score_codex":0.00006959657,"about_ca_system_score_gemma":0.000025545121,"threshold_uncertainty_score":0.9999949},"labels":[],"label_agreement":null},{"id":"W4401635890","doi":"10.1145/3688838","title":"History-Driven Fuzzing for Deep Learning Libraries","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"","keywords":"Fuzz testing; Computer science; Heuristic; Artificial intelligence; Set (abstract data type); Machine learning; Natural language processing; Programming language; Software","score_opus":0.06773932218144975,"score_gpt":0.29855303110614345,"score_spread":0.23081370892469372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401635890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004905063,0.0021769644,0.993121,0.00030724547,0.0022970827,0.00010390887,0.0000012471519,0.0014897945,0.000012217374],"genre_scores_gemma":[0.03438346,0.00007055617,0.9649102,0.00006768798,0.000108410226,0.00005924436,0.0000023044593,0.000036985697,0.000361141],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988785,0.00015886065,0.00016892994,0.00042879532,0.0000861159,0.00027881918],"domain_scores_gemma":[0.99459773,0.004979262,0.00002648955,0.00029511875,0.000025325076,0.00007607701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053535827,0.0001744863,0.00022486,0.0002886657,0.000163709,0.00008142636,0.00037295267,0.00013483001,0.000017491535],"category_scores_gemma":[0.0015263963,0.00018061728,0.000095161144,0.00018771301,0.0000401505,0.00039085763,0.000029490862,0.00056575716,0.000005226678],"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":[0.000013144932,0.000008183489,0.000028808598,0.00016301514,0.00008147241,0.000013730084,0.0024713073,0.59580076,0.0003971323,0.02356124,0.00003345202,0.37742773],"study_design_scores_gemma":[0.00027167352,0.00020963028,0.00013228648,0.00009534123,0.000057817153,0.0000869044,0.00006611987,0.8775653,0.0005021601,0.0027470216,0.117909335,0.00035638193],"about_ca_topic_score_codex":0.000006819412,"about_ca_topic_score_gemma":9.1862285e-7,"teacher_disagreement_score":0.37707135,"about_ca_system_score_codex":0.00008673824,"about_ca_system_score_gemma":0.000049016624,"threshold_uncertainty_score":0.7365359},"labels":[],"label_agreement":null},{"id":"W4401724691","doi":"10.1145/3688842","title":"My Fuzzers Won’t Build: An Empirical Study of Fuzzing Build Failures","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Software engineering; Software bug; Context (archaeology); Software; Set (abstract data type); Operating system; Programming language","score_opus":0.09234755339412065,"score_gpt":0.36974165303234796,"score_spread":0.2773940996382273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401724691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10270327,0.00036559044,0.88809365,0.00029208596,0.00058175216,0.00014873008,0.0000037579114,0.0078088455,0.0000023291545],"genre_scores_gemma":[0.4357216,0.000014023222,0.56412226,0.000043239765,0.000027010363,0.00003465624,6.8713945e-7,0.000020637448,0.000015887801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825394,0.000360489,0.0002828536,0.0006057197,0.00019039321,0.00030660746],"domain_scores_gemma":[0.9944891,0.0044657914,0.000037694965,0.0008215825,0.000053835673,0.0001320173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011969456,0.00024235119,0.00035768753,0.0005427864,0.00013757848,0.0000852885,0.000594044,0.00015883228,0.00000523212],"category_scores_gemma":[0.001060373,0.0002280647,0.00008090747,0.0005916672,0.00004892909,0.00025973274,0.000040368195,0.00055225036,0.0000026453713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043728294,0.0005913611,0.0038787564,0.0003255652,0.0003270332,0.00012337836,0.012316614,0.03363759,0.0011434406,0.00082007836,0.00053296186,0.9462595],"study_design_scores_gemma":[0.008248434,0.038473587,0.06312873,0.004005428,0.0021101625,0.0051155905,0.004831299,0.66131186,0.046831585,0.09532479,0.06015806,0.010460442],"about_ca_topic_score_codex":0.00012203223,"about_ca_topic_score_gemma":0.000006466406,"teacher_disagreement_score":0.93579906,"about_ca_system_score_codex":0.000033464978,"about_ca_system_score_gemma":0.000051095383,"threshold_uncertainty_score":0.93002087},"labels":[],"label_agreement":null},{"id":"W4402048137","doi":"10.1145/3690631","title":"T-Rec: Fine-Grained Language-Agnostic Program Reduction Guided by Lexical Syntax","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Syntax; Programming language; Reduction (mathematics); Natural language processing; Abstract syntax tree; Artificial intelligence","score_opus":0.0649629231789791,"score_gpt":0.3495486032377718,"score_spread":0.2845856800587927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402048137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005930984,0.0011444557,0.96911067,0.0008399004,0.0010136374,0.000198845,0.00001139707,0.021743802,0.000006282328],"genre_scores_gemma":[0.11304548,0.000055345376,0.88632566,0.00006646891,0.00006866483,0.00017264223,0.0000091547245,0.00003289638,0.00022371435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854696,0.00016497115,0.00024719627,0.0005555986,0.00014498868,0.000340305],"domain_scores_gemma":[0.99619925,0.0030303844,0.000026649166,0.00057334005,0.000040955605,0.00012939658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000678729,0.00023692768,0.00025699066,0.00029903513,0.00011968849,0.00012494353,0.00038705484,0.0001867301,0.000010880982],"category_scores_gemma":[0.0024392044,0.00022534606,0.000094565396,0.00051056145,0.000055503595,0.0001707942,0.00002490656,0.00044675916,0.000010744283],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008112876,0.00007486794,0.00001069497,0.00012717165,0.00006906418,0.000044553322,0.00066384696,0.0015838912,0.0024547332,0.00056613405,0.0058990438,0.9884979],"study_design_scores_gemma":[0.0029190423,0.006974622,0.0013347093,0.0035144568,0.0009113926,0.014531721,0.00016012901,0.5994504,0.18901128,0.07109649,0.103821725,0.006274058],"about_ca_topic_score_codex":0.00009482848,"about_ca_topic_score_gemma":0.0000013023906,"teacher_disagreement_score":0.9822238,"about_ca_system_score_codex":0.00004923537,"about_ca_system_score_gemma":0.000044223034,"threshold_uncertainty_score":0.9189345},"labels":[],"label_agreement":null},{"id":"W4402215615","doi":"10.1145/3691628","title":"A Large-Scale Study of IoT Security Weaknesses and Vulnerabilities in the Wild","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Internet of Things; Scale (ratio); Strengths and weaknesses; Computer security; Data science; Cartography","score_opus":0.03387503586808571,"score_gpt":0.2963998230558209,"score_spread":0.2625247871877352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402215615","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":[0.42662498,0.00057633314,0.57208794,0.00037782872,0.00007927973,0.00011167977,0.0000039376637,0.00013675373,0.0000012538154],"genre_scores_gemma":[0.8725244,0.00008061116,0.12723191,0.000031950058,0.000007630456,0.00011275502,2.4947553e-7,0.0000052429314,0.0000052959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914855,0.00019360575,0.00016212622,0.0002846044,0.000067214976,0.00014389439],"domain_scores_gemma":[0.9971845,0.0022946086,0.000014308393,0.00046798727,0.000017453733,0.000021152315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010337726,0.000101288264,0.00018089128,0.00020927232,0.00008518341,0.000024129686,0.00031772634,0.000101268386,0.0000021392896],"category_scores_gemma":[0.00017527022,0.000078724755,0.000024484663,0.00041967997,0.000057944093,0.000050786923,0.000024430272,0.0003775319,3.2625275e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057123932,0.0028801532,0.005540957,0.0012930155,0.0003834195,0.000066182096,0.34792778,0.014988725,0.00057319197,0.18454899,0.00008301607,0.44165745],"study_design_scores_gemma":[0.005425117,0.006397474,0.05887527,0.0006354895,0.00050581875,0.0016069156,0.08817181,0.4490559,0.008844658,0.3453261,0.03260223,0.0025531983],"about_ca_topic_score_codex":0.000052861655,"about_ca_topic_score_gemma":0.00011841995,"teacher_disagreement_score":0.44589937,"about_ca_system_score_codex":0.000007581816,"about_ca_system_score_gemma":0.000012931091,"threshold_uncertainty_score":0.32103026},"labels":[],"label_agreement":null},{"id":"W4402216867","doi":"10.1145/3691627","title":"Reputation Gaming in Crowd Technical Knowledge Sharing","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Mobile Crowdsensing and Crowdsourcing","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":"York University; Polytechnique Montréal","funders":"","keywords":"Computer science; Reputation; Knowledge management","score_opus":0.06536044955787561,"score_gpt":0.3277611355513543,"score_spread":0.26240068599347866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402216867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029531352,0.0011178532,0.9673213,0.00015283332,0.00079750083,0.00007708823,9.106683e-7,0.00097164966,0.00002951366],"genre_scores_gemma":[0.46945757,0.00004706672,0.5302897,0.00002364876,0.000033267857,0.000024830206,6.828645e-7,0.000017460328,0.00010578944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879014,0.000094569594,0.00024002892,0.00052500895,0.00007552061,0.00027475276],"domain_scores_gemma":[0.9975746,0.0018700578,0.00001604434,0.0004458516,0.000022177965,0.00007125672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010534917,0.00015691912,0.0002059669,0.00048278354,0.00008439151,0.00012218818,0.00027937186,0.00014935531,0.000004231778],"category_scores_gemma":[0.00059860444,0.00016261463,0.00006274699,0.000565298,0.000027176733,0.00021197704,0.000030003144,0.0004753067,0.000008688024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000948477,0.00005027657,0.000105439656,0.00026427893,0.000036232108,0.00010377428,0.0027819239,0.08723536,0.008902818,0.007071885,0.000021652388,0.8934169],"study_design_scores_gemma":[0.0009292016,0.00041056803,0.0070889443,0.0019002473,0.00009028557,0.001915761,0.00022043627,0.9403961,0.023969822,0.009568327,0.012142563,0.0013677592],"about_ca_topic_score_codex":0.00002005701,"about_ca_topic_score_gemma":0.000011490921,"teacher_disagreement_score":0.89204913,"about_ca_system_score_codex":0.00007027144,"about_ca_system_score_gemma":0.000033258235,"threshold_uncertainty_score":0.6631232},"labels":[],"label_agreement":null},{"id":"W4402483878","doi":"10.1145/3696002","title":"A Novel Refactoring and Semantic Aware Abstract Syntax Tree Differencing Tool and a Benchmark for Evaluating the Accuracy of Diff Tools","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Code refactoring; Computer science; Benchmark (surveying); Abstract syntax tree; Abstract syntax; Programming language; Syntax; Software engineering; Tree (set theory); Semantics (computer science); Artificial intelligence; Software","score_opus":0.18087197980816785,"score_gpt":0.3856275967855456,"score_spread":0.20475561697737774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402483878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3470789,0.0006883722,0.65131897,0.00013417738,0.0003136634,0.00023041504,0.000017605378,0.00021757008,3.424239e-7],"genre_scores_gemma":[0.61004484,0.000116383795,0.38965923,0.000009967894,0.000031597214,0.00009772035,0.0000012958678,0.000023055112,0.00001592897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985498,0.0000725995,0.0003115646,0.0005068163,0.00020413735,0.0003550813],"domain_scores_gemma":[0.96035874,0.03895337,0.000043763936,0.0004957179,0.00006340636,0.00008500915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015349642,0.00023773394,0.00033859038,0.0002789102,0.00016696549,0.00017859793,0.00035557413,0.00012853561,0.0000031731824],"category_scores_gemma":[0.009136548,0.00018843023,0.000078076664,0.00029770486,0.000057103374,0.00031108156,0.000061311635,0.000445967,3.2065677e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037609232,0.000033546014,0.0004251386,0.0015545287,0.00023764538,0.000007884793,0.0029591904,0.0101547,0.0547181,0.0007613643,0.0000040382556,0.92910624],"study_design_scores_gemma":[0.0022581217,0.0018476546,0.2245303,0.0027169157,0.00042642557,0.000998624,0.00043704355,0.73067003,0.031413134,0.0024906227,0.00064352463,0.0015675827],"about_ca_topic_score_codex":0.000042684627,"about_ca_topic_score_gemma":0.0000046987752,"teacher_disagreement_score":0.9275387,"about_ca_system_score_codex":0.000041755906,"about_ca_system_score_gemma":0.000056628705,"threshold_uncertainty_score":0.99920994},"labels":[],"label_agreement":null},{"id":"W4402516053","doi":"10.1145/3695989","title":"Non-Flaky and Nearly Optimal Time-Based Treatment of Asynchronous Wait Web Tests","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Asynchronous communication; Web application; World Wide Web; Computer network","score_opus":0.04587187782534556,"score_gpt":0.3016080723484287,"score_spread":0.2557361945230831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402516053","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03617386,0.001001693,0.9580816,0.00017012387,0.00025129944,0.0001209851,0.000011482216,0.004185811,0.0000031393702],"genre_scores_gemma":[0.23839651,0.00007297598,0.7613836,0.000023805813,0.000019552252,0.000040342537,0.0000015576662,0.000019749326,0.000041930525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990086,0.00006875843,0.00019264282,0.00040966467,0.00009009286,0.00023026302],"domain_scores_gemma":[0.9957834,0.0035991778,0.00002655485,0.00045977818,0.000034838675,0.00009628425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034120918,0.00020931856,0.0003151806,0.00031689112,0.00007370742,0.000058404665,0.00020384189,0.00013048615,0.000006415947],"category_scores_gemma":[0.00030690155,0.000188587,0.00007675681,0.0002767466,0.000062563035,0.00010590183,0.00001253318,0.00014679447,0.0000048640063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003734067,0.00015690927,0.00035995443,0.00027375904,0.00015654972,0.000077100936,0.0010487707,0.024913596,0.003549477,0.0001909977,0.00011832438,0.9691172],"study_design_scores_gemma":[0.0010052031,0.0045755925,0.0023353181,0.00048066818,0.0001738186,0.00048462936,0.000006078808,0.957886,0.028247269,0.0015626076,0.0025443707,0.0006984536],"about_ca_topic_score_codex":0.000041981268,"about_ca_topic_score_gemma":9.836835e-7,"teacher_disagreement_score":0.9684188,"about_ca_system_score_codex":0.00004403935,"about_ca_system_score_gemma":0.00008967437,"threshold_uncertainty_score":0.7690355},"labels":[],"label_agreement":null},{"id":"W4402516515","doi":"10.1145/3695995","title":"Deep API Sequence Generation via Golden Solution Samples and API Seeds","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Sequence (biology); Programming language; Biology","score_opus":0.13558136938960888,"score_gpt":0.31603201239977097,"score_spread":0.1804506430101621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402516515","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008110547,0.0013252104,0.9890715,0.00042927498,0.00052265235,0.000044979544,0.000010957618,0.00048336195,0.0000015534038],"genre_scores_gemma":[0.20725851,0.0003357485,0.79215074,0.00006135036,0.000076349475,0.00001996139,0.000013659645,0.000012174529,0.00007151783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998959,0.00013357602,0.0001648427,0.0004427337,0.00009375791,0.00020609985],"domain_scores_gemma":[0.99856555,0.0009253141,0.000019259143,0.0003786686,0.000026869846,0.00008431875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060180767,0.00015007296,0.00018787789,0.00027962466,0.00014400715,0.00013105794,0.00021610242,0.000112377624,0.0000072165626],"category_scores_gemma":[0.00024767048,0.00014514713,0.000050727027,0.00033945768,0.00003875736,0.00032474866,0.000021615475,0.00021644925,0.0000065647077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034977954,0.000015449352,0.00004243393,0.00009399525,0.00014006693,0.000016118602,0.0011128656,0.029830864,0.031851757,0.0018310861,0.000044779077,0.9350171],"study_design_scores_gemma":[0.00012122086,0.00010101888,0.0003168703,0.000048613838,0.00009737802,0.00024130693,0.000026060925,0.9906324,0.004585893,0.00075735856,0.002807489,0.00026435844],"about_ca_topic_score_codex":0.000081905026,"about_ca_topic_score_gemma":0.000017948098,"teacher_disagreement_score":0.96080154,"about_ca_system_score_codex":0.000029115958,"about_ca_system_score_gemma":0.000023277416,"threshold_uncertainty_score":0.59189284},"labels":[],"label_agreement":null},{"id":"W4402860132","doi":"10.1145/3697014","title":"ZigZagFuzz: Interleaved Fuzzing of Program Options and Files","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"Samsung; Hanyang University","keywords":"Fuzz testing; Computer science; Programming language; Software","score_opus":0.08854984899731846,"score_gpt":0.34345537315099234,"score_spread":0.25490552415367385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402860132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00658927,0.0013785925,0.9831352,0.00018638145,0.00038061535,0.000115260955,0.0000067501455,0.008202528,0.000005352024],"genre_scores_gemma":[0.14909342,0.00017190358,0.85057896,0.000025056986,0.000016893733,0.000062200634,0.0000011604076,0.000015702713,0.000034706234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911356,0.000092569586,0.00019452481,0.00033563963,0.0000756357,0.00018809682],"domain_scores_gemma":[0.99641985,0.0030772781,0.000023963685,0.00037198703,0.000035999692,0.00007090285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052492117,0.0001482481,0.00021656562,0.00033280288,0.00007102237,0.00006721029,0.00024083488,0.000105710926,0.0000034041798],"category_scores_gemma":[0.0008699887,0.00013996693,0.000058011978,0.00030969625,0.00006485175,0.00014215278,0.000030116686,0.00026481884,0.0000012447821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035281853,0.00003474136,0.00006664998,0.00019969589,0.00005649789,0.000008809383,0.00083963637,0.0008568038,0.00051104155,0.0030418488,0.000080732105,0.9943],"study_design_scores_gemma":[0.0016868174,0.0055262013,0.011337717,0.0052340147,0.0005787519,0.0037450478,0.00023047677,0.71175325,0.046278525,0.18271828,0.027636932,0.00327398],"about_ca_topic_score_codex":0.000026717886,"about_ca_topic_score_gemma":0.0000010853727,"teacher_disagreement_score":0.99102604,"about_ca_system_score_codex":0.000014298667,"about_ca_system_score_gemma":0.000024082281,"threshold_uncertainty_score":0.57076854},"labels":[],"label_agreement":null},{"id":"W4403604523","doi":"10.1145/3672448","title":"Understanding Test Convention Consistency as a Dimension of Test Quality","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Consistency (knowledge bases); Dimension (graph theory); Quality (philosophy); Reliability engineering; Artificial intelligence; Mathematics; Engineering","score_opus":0.22788467896783968,"score_gpt":0.37761842431744,"score_spread":0.14973374534960035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403604523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0154416505,0.0006391564,0.9817725,0.0002717464,0.0008199531,0.00013263467,0.0000139325075,0.00089867355,0.000009782948],"genre_scores_gemma":[0.6310542,0.000104962266,0.36865464,0.000019246618,0.00001791204,0.000021207523,0.0000017201146,0.000021038994,0.000105063766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856335,0.00013606249,0.00032873405,0.00044768714,0.00023421452,0.00028997238],"domain_scores_gemma":[0.97024035,0.028965313,0.00003516346,0.00057343376,0.00006495762,0.00012075807],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013842371,0.00018492047,0.00029942958,0.00046124318,0.00009240827,0.000057944988,0.00031180316,0.00015043202,0.000019059242],"category_scores_gemma":[0.010250605,0.00018540896,0.00010634563,0.0006088142,0.00007915039,0.00019897064,0.000031792726,0.00040164482,0.000012887597],"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":[0.00016162179,0.0013992228,0.017170383,0.0085732555,0.0014501719,0.00056577136,0.01022121,0.08911382,0.2795537,0.26771373,0.0004980623,0.32357904],"study_design_scores_gemma":[0.007895525,0.01140254,0.113908045,0.007780372,0.00090760796,0.004858965,0.0017920514,0.37455335,0.36206096,0.09427913,0.013519772,0.0070416993],"about_ca_topic_score_codex":0.00004136064,"about_ca_topic_score_gemma":0.0000021940348,"teacher_disagreement_score":0.61561257,"about_ca_system_score_codex":0.000111769674,"about_ca_system_score_gemma":0.0000865195,"threshold_uncertainty_score":0.99808645},"labels":[],"label_agreement":null},{"id":"W4404002909","doi":"10.1145/3702980","title":"Trained without My Consent: Detecting Code Inclusion in Language Models Trained on Code","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Code (set theory); Inclusion (mineral); Programming language; Physics","score_opus":0.10487511590320443,"score_gpt":0.33703465410834965,"score_spread":0.23215953820514523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404002909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0821235,0.00040797147,0.91522515,0.0006614222,0.00058767153,0.00015277047,0.000011232706,0.000809609,0.000020693904],"genre_scores_gemma":[0.53740066,0.00003202147,0.46231306,0.00012327064,0.00002798087,0.00002632609,0.0000010697888,0.000019827092,0.000055793727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839103,0.00023750492,0.00029176916,0.000572686,0.00016786341,0.00033916376],"domain_scores_gemma":[0.9962127,0.0031551875,0.000026030222,0.00049050554,0.000018629893,0.00009694895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012278556,0.0002226504,0.00030541344,0.00047410943,0.0001511909,0.0000683422,0.0004059064,0.0001712808,0.000005821735],"category_scores_gemma":[0.00065027684,0.00021817538,0.00007540735,0.00035546123,0.00002749918,0.00022371198,0.000074515665,0.0005583577,0.000002862496],"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":[0.000028968983,0.00003684718,0.000007679268,0.00015189344,0.000042952564,0.00008812597,0.016192518,0.59171826,0.00665621,0.0035589915,0.000002299471,0.38151526],"study_design_scores_gemma":[0.0005616405,0.000119427765,0.000044811917,0.0002656864,0.000019759316,0.000121948506,0.00019983905,0.98734367,0.005153067,0.0057036686,0.0001839777,0.00028252107],"about_ca_topic_score_codex":0.00006364122,"about_ca_topic_score_gemma":0.00007467045,"teacher_disagreement_score":0.45527714,"about_ca_system_score_codex":0.00007700581,"about_ca_system_score_gemma":0.00006136093,"threshold_uncertainty_score":0.8896934},"labels":[],"label_agreement":null},{"id":"W4404060023","doi":"10.1145/3702983","title":"Repairs and Breaks Prediction for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program","keywords":"Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Data science","score_opus":0.04038717887472058,"score_gpt":0.2922085178703729,"score_spread":0.2518213389956523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404060023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096805283,0.00067983405,0.9958494,0.00034913188,0.00048666567,0.00017157287,0.000008470888,0.001484417,0.0000024801752],"genre_scores_gemma":[0.17698802,0.00016975362,0.82240057,0.00007089451,0.000062836705,0.0002266059,0.0000022646752,0.000014680608,0.000064353255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993097,0.000036590267,0.0001347127,0.00032885346,0.00003829909,0.00015181226],"domain_scores_gemma":[0.9985947,0.0010386166,0.000014034968,0.00026629807,0.00002252129,0.00006384698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031372014,0.00010647289,0.00011821451,0.0001407679,0.00013438812,0.00005909238,0.00012619431,0.000114021364,0.0000022669342],"category_scores_gemma":[0.000088113055,0.00010418368,0.00005560277,0.00019856244,0.000025557125,0.00013609535,0.00001072251,0.0001879597,4.2732012e-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":[0.00000736028,0.000010702304,0.000013605165,0.000052719362,0.00003684942,0.0000016451093,0.00015777697,0.032507967,0.00019049426,0.006355327,0.000045704342,0.96061987],"study_design_scores_gemma":[0.00008886668,0.00017291124,0.0003014168,0.00001459684,0.000028047843,0.0001674341,0.00001012174,0.98698026,0.0005969357,0.0016906966,0.009835837,0.00011290161],"about_ca_topic_score_codex":0.000007361347,"about_ca_topic_score_gemma":0.0000016835817,"teacher_disagreement_score":0.960507,"about_ca_system_score_codex":0.000015244661,"about_ca_system_score_gemma":0.0000062248173,"threshold_uncertainty_score":0.42484874},"labels":[],"label_agreement":null},{"id":"W4404060074","doi":"10.1145/3702979","title":"ZS4C: Zero-Shot Synthesis of Compilable Code for Incomplete Code Snippets Using LLMs","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Queen's University; University of Windsor; University of Manitoba","funders":"","keywords":"Computer science; Code (set theory); Zero (linguistics); Programming language; Linguistics","score_opus":0.1333233069938429,"score_gpt":0.3604581061756769,"score_spread":0.22713479918183402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404060074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018336974,0.0017764912,0.99431396,0.00017535688,0.00064675877,0.00015572087,0.00010784815,0.0009876948,0.0000024854392],"genre_scores_gemma":[0.1004014,0.000057212314,0.8993571,0.000049005503,0.000028068844,0.000047408903,0.0000018843599,0.000028278835,0.000029630088],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99886334,0.00010230721,0.0002605074,0.00039695785,0.00010826339,0.00026863342],"domain_scores_gemma":[0.9950095,0.004376253,0.00004565299,0.00043474158,0.0000691482,0.0000647498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007549759,0.00018612143,0.00035473486,0.00033839617,0.00010637956,0.00005739094,0.00048964226,0.0001447818,0.0000064721885],"category_scores_gemma":[0.00082098873,0.00017625964,0.00009797798,0.00034444313,0.0000527549,0.00020602868,0.000029305036,0.00025105398,0.000001111747],"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":[0.00013398408,0.00015902397,0.000047438145,0.0037553473,0.0005869326,0.00006405176,0.0020323894,0.053376652,0.24468519,0.03290505,0.00032173976,0.66193223],"study_design_scores_gemma":[0.00032077823,0.00030702873,0.00002881035,0.00096566614,0.00019641209,0.0003930893,0.000026356025,0.3341736,0.6329135,0.02278579,0.007240783,0.0006482271],"about_ca_topic_score_codex":0.00002686399,"about_ca_topic_score_gemma":0.000004501741,"teacher_disagreement_score":0.66128397,"about_ca_system_score_codex":0.000042947893,"about_ca_system_score_gemma":0.000052706426,"threshold_uncertainty_score":0.7187659},"labels":[],"label_agreement":null},{"id":"W4404060176","doi":"10.1145/3702976","title":"Non-Linear Software Documentation with Interactive Code Examples","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"McGill University","funders":"","keywords":"Computer science; Documentation; Software engineering; Software; Programming language","score_opus":0.06900117343039758,"score_gpt":0.34881224904692565,"score_spread":0.27981107561652807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404060176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02255229,0.00034883805,0.97402215,0.00021743304,0.0008903892,0.00020652244,0.000017126527,0.0017426371,0.0000025922277],"genre_scores_gemma":[0.10709799,0.00009933847,0.8923108,0.00005681967,0.00005249206,0.00013361637,0.000006993253,0.00005413776,0.00018781012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834675,0.00009815994,0.00022227308,0.0006628768,0.00025555372,0.0004143871],"domain_scores_gemma":[0.9912968,0.007799846,0.000024897448,0.0006368508,0.00008214267,0.00015942528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060638395,0.00028478255,0.00028651865,0.00055119785,0.000117759104,0.00017087207,0.000502257,0.00013725707,0.000030120924],"category_scores_gemma":[0.0011693106,0.00025372682,0.00007243857,0.0006558929,0.000055542943,0.0006073185,0.000037210953,0.00064082,0.00003448943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018152336,0.00015602322,0.0014071212,0.0009689186,0.0009449259,0.00040267134,0.007983703,0.40135404,0.0031099103,0.0017180901,0.00023998017,0.5815331],"study_design_scores_gemma":[0.0069161416,0.0075587267,0.053696983,0.0044060037,0.0007505729,0.005691848,0.0008834882,0.69633365,0.13690399,0.0074533997,0.072464444,0.006940758],"about_ca_topic_score_codex":0.000049914182,"about_ca_topic_score_gemma":0.0000075803896,"teacher_disagreement_score":0.57459235,"about_ca_system_score_codex":0.00010274496,"about_ca_system_score_gemma":0.000075080075,"threshold_uncertainty_score":0.9999915},"labels":[],"label_agreement":null},{"id":"W4404373849","doi":"10.1145/3702985","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms—RCR Report","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"BNP Paribas Cardif","keywords":"Computer science; Categorical variable; Artificial intelligence; Software engineering; Machine learning; Programming language; Data mining","score_opus":0.10919899534806334,"score_gpt":0.34966833276716797,"score_spread":0.24046933741910465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404373849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084969925,0.00055745867,0.9971245,0.00033353624,0.00024978226,0.0001134023,0.000019875106,0.0007417748,0.000009993619],"genre_scores_gemma":[0.19632281,0.00011855621,0.8032177,0.0000147222445,0.000018429186,0.000034250752,0.00016847468,0.000012550043,0.00009250091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988801,0.00011301072,0.00028612933,0.00045895853,0.00008284274,0.00017898099],"domain_scores_gemma":[0.9974139,0.0018295202,0.000042703665,0.0006469266,0.000021966993,0.000045012897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013151463,0.000117787924,0.00021985176,0.00026576928,0.000056192,0.000035986974,0.000428891,0.00013254421,0.0000024106241],"category_scores_gemma":[0.0016075625,0.00010756443,0.000039491784,0.00033054344,0.000015613934,0.00019914149,0.000036679376,0.0004293141,4.967367e-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":[0.00004217134,0.00011895179,0.0004663901,0.00085585075,0.00011753615,0.00004929236,0.0011454328,0.64542603,0.00050220615,0.006406961,0.00011310841,0.3447561],"study_design_scores_gemma":[0.00016878643,0.00006536105,0.00030989834,0.000029467808,0.000018681721,0.00018572401,0.0000139706635,0.9932702,0.00018790831,0.00028293798,0.005359815,0.00010723438],"about_ca_topic_score_codex":0.00007725381,"about_ca_topic_score_gemma":0.0000057494144,"teacher_disagreement_score":0.3478442,"about_ca_system_score_codex":0.000019138199,"about_ca_system_score_gemma":0.000041129606,"threshold_uncertainty_score":0.43863502},"labels":[],"label_agreement":null},{"id":"W4404570261","doi":"10.1145/3743133","title":"Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development","year":2025,"lang":"en","type":"preprint","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Law, AI, and Intellectual Property","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 Victoria","funders":"National Science Foundation","keywords":"Generative grammar; Coding (social sciences); Copyright law; Computer science; Artificial intelligence; Intellectual property; Sociology; Social science","score_opus":0.09700942967423726,"score_gpt":0.33212191879071784,"score_spread":0.23511248911648058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404570261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003527846,0.0023822936,0.9909032,0.0008202772,0.0014066725,0.0004138638,0.000055805387,0.00048154633,0.000008481568],"genre_scores_gemma":[0.0041479943,0.0007516038,0.99348974,0.00066664524,0.00012226675,0.00012575314,0.000018916895,0.000034312146,0.0006427713],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976558,0.00025928678,0.00038142657,0.0011660898,0.00015464827,0.00038272672],"domain_scores_gemma":[0.9951346,0.0037813568,0.00007733957,0.00063602603,0.00024720115,0.00012348944],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005387892,0.00049346744,0.0006792553,0.00036251554,0.0004344654,0.00020695238,0.00051326206,0.0004615378,0.000015790441],"category_scores_gemma":[0.0016747263,0.00043535998,0.00010917148,0.00016389725,0.00010801834,0.00016188265,0.00014585807,0.00081346533,0.0000026523114],"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":[0.00026440568,0.0002443443,0.000050151182,0.000611309,0.0016998838,0.000015939735,0.10999463,0.054476608,0.0009796484,0.0022308198,0.0013508539,0.8280814],"study_design_scores_gemma":[0.005493726,0.0023371086,0.0021256984,0.0067769065,0.001061526,0.00016791746,0.004052189,0.22200817,0.40786588,0.039365303,0.29972404,0.009021548],"about_ca_topic_score_codex":0.000093029725,"about_ca_topic_score_gemma":0.00002081989,"teacher_disagreement_score":0.81905985,"about_ca_system_score_codex":0.00015926924,"about_ca_system_score_gemma":0.00026746988,"threshold_uncertainty_score":0.9998098},"labels":[],"label_agreement":null},{"id":"W4404635154","doi":"10.1145/3705309","title":"Detecting Refactoring Commits in Machine Learning Python Projects: A Machine Learning-Based Approach","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Code refactoring; Computer science; Maintainability; Python (programming language); Software engineering; Java; Programming language; Software; Software development; Artificial intelligence; Machine learning","score_opus":0.09068230133371412,"score_gpt":0.3197279064261304,"score_spread":0.22904560509241628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404635154","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021680465,0.0021487817,0.97224826,0.00012244859,0.00063818623,0.00024342799,0.00000475976,0.002908154,0.0000055099736],"genre_scores_gemma":[0.46449292,0.0000793092,0.53510576,0.000016370961,0.00003785971,0.0001019849,0.0000056430376,0.00006641117,0.0000937147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972098,0.00056449557,0.00037257257,0.0008599495,0.0003054464,0.00068775134],"domain_scores_gemma":[0.98934895,0.009818781,0.00003935858,0.0005766914,0.000048625527,0.00016756564],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024308532,0.00038315722,0.00044771523,0.001273687,0.000205043,0.00017863784,0.0006182449,0.00025244142,0.000007998499],"category_scores_gemma":[0.00635265,0.00038718714,0.000116974516,0.001444637,0.000039680832,0.00028897694,0.00006458018,0.002570606,0.0000075642356],"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":[0.000029628305,0.00005900138,0.0040841447,0.0005845258,0.000073105824,0.000089638386,0.0015626623,0.83466,0.0009795774,0.000104531406,0.0000014991906,0.15777169],"study_design_scores_gemma":[0.00053949904,0.0003471283,0.001509479,0.00027992897,0.000021132924,0.0001718362,0.000043630764,0.98844147,0.004006806,0.000045921006,0.004108745,0.0004843985],"about_ca_topic_score_codex":0.00021177605,"about_ca_topic_score_gemma":0.000018715169,"teacher_disagreement_score":0.44281247,"about_ca_system_score_codex":0.00018863851,"about_ca_system_score_gemma":0.000089061214,"threshold_uncertainty_score":0.999858},"labels":[],"label_agreement":null},{"id":"W4405396136","doi":"10.1145/3708519","title":"Automatic Programming: Large Language Models and Beyond","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"Concordia University","funders":"Bộ Giáo dục và Ðào tạo; Ministry of Education, India","keywords":"Computer science; Programmer; Coding (social sciences); Software engineering; Popularity; Software deployment; Programming language; Key (lock); Computer security","score_opus":0.05968806315916537,"score_gpt":0.33576718525188126,"score_spread":0.2760791220927159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405396136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027590817,0.0029688717,0.96622956,0.00025403692,0.0005501731,0.00015438658,0.0000086195105,0.0022403828,0.000003135869],"genre_scores_gemma":[0.22132224,0.000103006736,0.77828723,0.000045892626,0.000030052177,0.00007716765,0.0000017495332,0.000032194082,0.00010046438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865437,0.00009682794,0.00017287592,0.0004794045,0.00017008882,0.00042645464],"domain_scores_gemma":[0.99490535,0.004374128,0.000011434826,0.0005233339,0.000024966337,0.00016079904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090325467,0.00020223716,0.00023437077,0.00042104497,0.000092840935,0.00016178156,0.00034522245,0.00013816246,0.000011578878],"category_scores_gemma":[0.00094079186,0.00019387116,0.000056640012,0.0004518053,0.00003455041,0.00031177612,0.00004563455,0.0004551593,0.000008275628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036918693,0.000042772164,0.000038178514,0.00049310003,0.00012731359,0.00011284808,0.0044188867,0.010989652,0.00038114827,0.008164412,0.000041812156,0.97518617],"study_design_scores_gemma":[0.00048465698,0.00030442263,0.0007480253,0.00019010899,0.0000571826,0.000612391,0.0001617903,0.98640394,0.0017895546,0.0030127068,0.0056473506,0.0005878749],"about_ca_topic_score_codex":0.00001013449,"about_ca_topic_score_gemma":0.0000016326293,"teacher_disagreement_score":0.9754143,"about_ca_system_score_codex":0.000034521476,"about_ca_system_score_gemma":0.00003769451,"threshold_uncertainty_score":0.79058367},"labels":[],"label_agreement":null},{"id":"W4405444248","doi":"10.1145/3708473","title":"Leveraging Data Characteristics for Bug Localization in Deep Learning Programs","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Deep learning; Artificial intelligence; Software engineering; Data science; Machine learning","score_opus":0.13358464562709096,"score_gpt":0.344974517411349,"score_spread":0.21138987178425803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405444248","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015010833,0.00032902582,0.99653953,0.00035657934,0.0005388591,0.0001316402,0.0000068007885,0.0005949118,0.0000015954192],"genre_scores_gemma":[0.20884371,0.00016019093,0.790615,0.000045178796,0.00003918189,0.000056643494,0.00016852433,0.000019945888,0.000051588024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894506,0.00013951438,0.00019070198,0.00046075825,0.00006982564,0.00019411494],"domain_scores_gemma":[0.997949,0.0014338208,0.00002627827,0.0005209596,0.000024041374,0.000045921686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010413924,0.0001174923,0.00015437376,0.00023619195,0.000092930975,0.00012432631,0.00040385197,0.000087091365,0.0000022880315],"category_scores_gemma":[0.001192179,0.00011970554,0.000023470693,0.00031037902,0.000014949035,0.00027037243,0.00002908226,0.00033543666,0.0000030341691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006235698,0.000017984928,0.00040636124,0.00015032031,0.000016918295,0.0000036384733,0.00065452565,0.030301142,0.00008313989,0.0011649269,0.000005060024,0.9671897],"study_design_scores_gemma":[0.00013120858,0.00007110063,0.0013420578,0.00008102266,0.000015692991,0.000026596093,0.000030340187,0.96701145,0.00005035923,0.00032664518,0.030777667,0.00013585284],"about_ca_topic_score_codex":0.000021287968,"about_ca_topic_score_gemma":0.0000053365325,"teacher_disagreement_score":0.9670539,"about_ca_system_score_codex":0.000025912517,"about_ca_system_score_gemma":0.000022957583,"threshold_uncertainty_score":0.48814502},"labels":[],"label_agreement":null},{"id":"W4405570253","doi":"10.1145/3708523","title":"The Impact of Generative AI on Creativity in Software Development: A Research Agenda","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Computer science; Generative grammar; Creativity; Software development; Software engineering; Software; Engineering ethics; Artificial intelligence; Psychology; Programming language; Engineering","score_opus":0.29514797537011833,"score_gpt":0.5079426103073964,"score_spread":0.21279463493727807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405570253","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":[0.3881361,0.0004381281,0.609758,0.00046321366,0.00083515176,0.00018587829,0.000026463482,0.00011392515,0.000043144606],"genre_scores_gemma":[0.9386538,0.00015720227,0.05947427,0.00008452751,0.000039537816,0.00021549879,0.0000035289997,0.000031213713,0.0013404153],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99811655,0.0008064845,0.00022217975,0.0003710292,0.00014873265,0.00033502653],"domain_scores_gemma":[0.98670596,0.01278089,0.000021203989,0.0003673395,0.000055867793,0.00006876636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020830627,0.00014953333,0.0002020873,0.00048278744,0.00021142559,0.000037561687,0.0001996744,0.00011425546,0.000108093904],"category_scores_gemma":[0.002459954,0.00010905489,0.00007355976,0.0007166672,0.00018068605,0.000058334288,0.000010068117,0.00071358774,0.00001689311],"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":[0.000484186,0.00079004775,0.0038534577,0.000121456025,0.00034712494,0.00006434032,0.04575137,0.027795862,0.0055028414,0.0037862721,0.0018162498,0.9096868],"study_design_scores_gemma":[0.0032699574,0.006679026,0.7604595,0.0012913272,0.0001298122,0.000688223,0.0065798885,0.00545906,0.10042652,0.0072062532,0.10556187,0.0022485994],"about_ca_topic_score_codex":0.00017767824,"about_ca_topic_score_gemma":0.000044734454,"teacher_disagreement_score":0.9074382,"about_ca_system_score_codex":0.00010921617,"about_ca_system_score_gemma":0.00017787902,"threshold_uncertainty_score":0.44471294},"labels":[],"label_agreement":null},{"id":"W4405891407","doi":"10.1145/3709357","title":"Software Fairness Debt: Building a Research Agenda for Addressing Bias in AI Systems","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Open Source Software Innovations","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","funders":"","keywords":"Technical debt; Computer science; Transparency (behavior); Software; Software development; Fairness measure; Software system; Process management; Knowledge management; Risk analysis (engineering); Engineering management; Software engineering; Business; Computer security; Engineering; Telecommunications","score_opus":0.37015791711926477,"score_gpt":0.4458075324305976,"score_spread":0.07564961531133285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405891407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062901876,0.001382477,0.98774993,0.0007256565,0.0021425919,0.000515176,0.000032557105,0.0011577501,0.0000036807526],"genre_scores_gemma":[0.16341494,0.00003575741,0.83567715,0.000094530435,0.00009424966,0.00046910738,0.0000049559735,0.000052095653,0.00015720037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99721426,0.0004932846,0.00048449737,0.0008204916,0.00029721373,0.00069025904],"domain_scores_gemma":[0.98396397,0.014884382,0.000038018232,0.0007636897,0.00023462815,0.00011529908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004476035,0.0002683614,0.0004192819,0.0015529294,0.00033644264,0.00047716976,0.00077584985,0.00027378387,0.0000052712257],"category_scores_gemma":[0.005540028,0.00027494374,0.00010497016,0.002113716,0.00007947536,0.00064834306,0.00006367239,0.0010012352,0.000007937216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005129345,0.00013036632,0.00034911212,0.001962164,0.0002362869,0.00015806356,0.006022846,0.26081216,0.0021160317,0.063447915,0.0005290373,0.66418475],"study_design_scores_gemma":[0.0038123012,0.0015290467,0.0029396622,0.008605859,0.00022442683,0.0019706415,0.0015783841,0.71128166,0.014974053,0.051262647,0.19786574,0.0039556185],"about_ca_topic_score_codex":0.00012457371,"about_ca_topic_score_gemma":0.000015158109,"teacher_disagreement_score":0.6602291,"about_ca_system_score_codex":0.00017937226,"about_ca_system_score_gemma":0.00019192834,"threshold_uncertainty_score":0.99997026},"labels":[],"label_agreement":null},{"id":"W4406153408","doi":"10.1145/3711816","title":"LLM-Powered Static Binary Taint Analysis","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Web Application Security Vulnerabilities","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ant Group","keywords":"Taint checking; Computer science; Firmware; Static analysis; Vulnerability (computing); Binary number; Scalability; State (computer science); Computer security; Software; Computer hardware; Operating system; Programming language","score_opus":0.04508240882382882,"score_gpt":0.3181407358867413,"score_spread":0.2730583270629125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406153408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01800827,0.00020463145,0.9797755,0.0011066225,0.00027984323,0.00011731195,0.000008608459,0.00048606924,0.000013162608],"genre_scores_gemma":[0.2352722,0.000050521132,0.764065,0.00028164135,0.000007079154,0.00008860539,0.000002823305,0.000006826221,0.00022528968],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988005,0.00022371039,0.0002397412,0.00041482656,0.00009743362,0.00022378779],"domain_scores_gemma":[0.9957763,0.0031946627,0.000033823708,0.00085882616,0.00006225066,0.000074115575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006817542,0.0001528002,0.00031153712,0.0007027992,0.00012311582,0.000045695848,0.00046690073,0.000101712176,0.000021602453],"category_scores_gemma":[0.0006839765,0.00015802695,0.00010864359,0.0012460813,0.000050213555,0.00011717241,0.000027797998,0.0002512641,0.0000054393727],"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":[0.000061070634,0.00044723594,0.0007617616,0.0003650429,0.0024149632,0.000017239097,0.00538393,0.5014724,0.0026798078,0.11634258,0.0002577319,0.3697962],"study_design_scores_gemma":[0.0037704331,0.001341,0.05786921,0.00021309202,0.0026786893,0.00010424217,0.0015821952,0.69426984,0.03568679,0.1144211,0.085054986,0.0030084022],"about_ca_topic_score_codex":0.000041116124,"about_ca_topic_score_gemma":0.0000067693836,"teacher_disagreement_score":0.3667878,"about_ca_system_score_codex":0.00004626853,"about_ca_system_score_gemma":0.000047166748,"threshold_uncertainty_score":0.6444152},"labels":[],"label_agreement":null},{"id":"W4406385999","doi":"10.1145/3712196","title":"System Safety Monitoring of Learned Components Using Temporal Metric Forecasting","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Fault Detection and Control Systems","field":"Engineering","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":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs; Science Foundation Ireland","keywords":"Computer science; Metric (unit); Real-time computing; Systems engineering; Engineering; Operations management","score_opus":0.10698489540344563,"score_gpt":0.3098304973908639,"score_spread":0.20284560198741824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406385999","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":[0.207986,0.00057420746,0.78901017,0.0000053802696,0.0017670336,0.00012303442,0.0000087610215,0.0005043693,0.00002108343],"genre_scores_gemma":[0.81148463,0.000033114175,0.18836068,0.000002503714,0.00003634926,0.000018326691,0.0000011756248,0.000027024293,0.00003619135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989153,0.00012557559,0.0004136204,0.00020303481,0.00009995979,0.00024247372],"domain_scores_gemma":[0.9985166,0.0010614306,0.000045656274,0.0002687603,0.000043298714,0.000064230786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054436194,0.00019701013,0.0004519871,0.00060945144,0.00010903465,0.000013728958,0.00013000146,0.00017030648,0.000002707271],"category_scores_gemma":[0.0003159805,0.00021154396,0.000099276556,0.0005724932,0.00002083026,0.000063679814,0.000006899633,0.00028984473,9.5364675e-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":[0.00005756866,0.000013644641,0.0014374815,0.00078960933,0.00027679643,0.000004279143,0.00013092204,0.92710674,0.013925474,0.00006447961,0.0000012201293,0.056191806],"study_design_scores_gemma":[0.0016331197,0.00010419846,0.003660192,0.0009453691,0.00023448326,0.00013537596,0.00080409687,0.96035224,0.030334402,0.000031812597,0.0013090596,0.00045562428],"about_ca_topic_score_codex":0.000095332274,"about_ca_topic_score_gemma":0.0000017873604,"teacher_disagreement_score":0.60349864,"about_ca_system_score_codex":0.00012850747,"about_ca_system_score_gemma":0.000013309975,"threshold_uncertainty_score":0.8626512},"labels":[],"label_agreement":null},{"id":"W4406465537","doi":"10.1145/3711904","title":"Making Software Development More Diverse and Inclusive: Key Themes, Challenges, and Future Directions","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"University-Industry-Government Innovation Models","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Key (lock); Software development; Software engineering; Engineering ethics; Data science; Software; Systems engineering; Engineering; Computer security","score_opus":0.07451218141943525,"score_gpt":0.2934927424907315,"score_spread":0.21898056107129624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406465537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08711565,0.0028193528,0.90458834,0.0035669052,0.0008671324,0.0002701922,0.000011527218,0.00054793275,0.00021295127],"genre_scores_gemma":[0.17243046,0.0037703363,0.81955194,0.002465822,0.0005709465,0.00007351855,0.000026167474,0.00007745151,0.0010333497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990873,0.000026044709,0.00017714,0.00036681208,0.00012267209,0.00022007203],"domain_scores_gemma":[0.9992369,0.00038080695,0.00006604782,0.00021403111,0.00008112464,0.000021085285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030817228,0.00022221911,0.00023848699,0.00049529213,0.00045766006,0.00005310775,0.00013009015,0.00026126023,0.000029005134],"category_scores_gemma":[0.0002604425,0.00023602472,0.000029245111,0.00033024955,0.000056183475,0.00036347887,0.00009813334,0.000435274,0.0000016841572],"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":[0.000070638045,0.00007710916,0.001988951,0.0004938145,0.00029786903,0.00001415125,0.0018805611,0.0012901244,0.0000856297,0.0126104895,0.00011662283,0.98107404],"study_design_scores_gemma":[0.0014953901,0.000028774994,0.05211324,0.00029391842,0.0003177926,0.00003292669,0.005799159,0.0010601635,0.00017969523,0.001859409,0.93608296,0.000736599],"about_ca_topic_score_codex":0.000025337726,"about_ca_topic_score_gemma":0.0000240951,"teacher_disagreement_score":0.98033744,"about_ca_system_score_codex":0.000069422305,"about_ca_system_score_gemma":0.000024725392,"threshold_uncertainty_score":0.9624809},"labels":[],"label_agreement":null},{"id":"W4406494387","doi":"10.1145/3712008","title":"Automation in Model-Driven Engineering: A Look Back, and Ahead","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Agencia Estatal de Investigación; European Commission; Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación; Universidad de Málaga","keywords":"Computer science; Automation; Software engineering; Systems engineering; Engineering","score_opus":0.04854884486490869,"score_gpt":0.2991379539605627,"score_spread":0.250589109095654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406494387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009097735,0.00023127529,0.9885235,0.0002963868,0.0002862698,0.00023831766,0.000005558594,0.0013148894,0.0000061004903],"genre_scores_gemma":[0.053654436,0.00014400549,0.94584966,0.00009861502,0.00001024383,0.00011374879,0.0000020976818,0.000025315907,0.00010186234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856746,0.00008440817,0.00032967812,0.0005462553,0.00011360084,0.00035856586],"domain_scores_gemma":[0.9983034,0.0008572921,0.000035267425,0.00065733027,0.000044292337,0.00010239211],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005142668,0.0002898523,0.00038830677,0.0008122632,0.00005835825,0.000051163872,0.0004319617,0.00025383531,0.0000030167294],"category_scores_gemma":[0.0001835662,0.0003240085,0.000058599922,0.0005280661,0.0000326529,0.0002834369,0.000056822868,0.00046008697,0.0000026023688],"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":[0.000009298966,0.000037515852,0.00016727409,0.0001639447,0.0000399806,0.00000676903,0.00044311397,0.8672751,0.0011496991,0.027670609,0.00002498118,0.10301168],"study_design_scores_gemma":[0.0004166912,0.00007130549,0.0013612293,0.00017674608,0.000017444308,0.000035722747,0.0000028860395,0.99186695,0.0021140387,0.0011782774,0.0024546254,0.00030406506],"about_ca_topic_score_codex":0.000023183644,"about_ca_topic_score_gemma":0.000005513982,"teacher_disagreement_score":0.12459184,"about_ca_system_score_codex":0.0000907678,"about_ca_system_score_gemma":0.000049873383,"threshold_uncertainty_score":0.9999212},"labels":[],"label_agreement":null},{"id":"W4406688098","doi":"10.1145/3714461","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Code generation; Code (set theory); Programming language; Software engineering; Key (lock); Operating system; Set (abstract data type)","score_opus":0.13664566024265196,"score_gpt":0.3367384357981753,"score_spread":0.20009277555552335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406688098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006688978,0.0006837651,0.99059844,0.00018175373,0.00018995805,0.00024936057,0.000011782928,0.001393314,0.0000026342223],"genre_scores_gemma":[0.13316064,0.000028713694,0.86625296,0.00010709706,0.00002162184,0.00036747,0.000004233502,0.000015584448,0.00004169941],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990518,0.000072454204,0.00016306315,0.0003757149,0.00008088214,0.00025606045],"domain_scores_gemma":[0.9983305,0.0010853366,0.00003757602,0.00043588463,0.00006916034,0.00004158061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058472523,0.00016803257,0.00021386138,0.00032923903,0.00016180053,0.00005951637,0.00032461624,0.00009455865,6.6500775e-7],"category_scores_gemma":[0.00044566146,0.000147649,0.000044900724,0.0003087997,0.00001853809,0.00025262087,0.000023739767,0.00023308728,1.3717715e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006056027,0.00010509456,0.000008061021,0.00028320422,0.000108275286,0.000016060787,0.0028258571,0.09963588,0.027379762,0.035914615,0.000025416086,0.83363724],"study_design_scores_gemma":[0.0003931161,0.00023524169,0.000006820832,0.0002079715,0.000048467613,0.000044126555,0.00007206265,0.6039583,0.3909477,0.0032844588,0.00046457595,0.0003371358],"about_ca_topic_score_codex":0.000012029657,"about_ca_topic_score_gemma":0.0000077793275,"teacher_disagreement_score":0.83330005,"about_ca_system_score_codex":0.0000404272,"about_ca_system_score_gemma":0.000029998693,"threshold_uncertainty_score":0.6020952},"labels":[],"label_agreement":null},{"id":"W4406738291","doi":"10.1145/3715006","title":"The Good, the Bad, and the Monstrous: Predicting Highly Change-Prone Source Code Methods at Their Inception","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Source code; Code (set theory); Computer security; Programming language","score_opus":0.0632421140070817,"score_gpt":0.3331406067424445,"score_spread":0.2698984927353628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406738291","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01667074,0.0032611915,0.9733244,0.0047190255,0.0009305585,0.000489233,0.0000074311647,0.00059204083,0.000005346216],"genre_scores_gemma":[0.16708937,0.0016030318,0.829325,0.00040868556,0.00013842639,0.0007309565,0.0000018981019,0.000044805893,0.00065778167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973812,0.0011899533,0.00028862516,0.00047008423,0.00018915792,0.0004809663],"domain_scores_gemma":[0.95777863,0.04092166,0.000059368547,0.0010898337,0.000069912596,0.000080588485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005146215,0.00026279734,0.00030640227,0.00017475346,0.0010872675,0.00014861872,0.0010456891,0.0001608872,0.0000019088989],"category_scores_gemma":[0.0045984453,0.00014345195,0.00009751558,0.0005947174,0.00036111806,0.0001494754,0.0002020014,0.00078427786,0.000001877821],"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":[0.00009818319,0.000019302883,0.0007969157,0.000055768756,0.0002495406,0.0000017286138,0.0042044544,0.01740977,0.00064826803,0.0046965904,0.000047664074,0.97177184],"study_design_scores_gemma":[0.0066749635,0.00069277664,0.069693625,0.0005598663,0.0004755822,0.0008172604,0.0020372265,0.72971505,0.019862516,0.009849443,0.15799391,0.0016277436],"about_ca_topic_score_codex":0.000088806206,"about_ca_topic_score_gemma":0.000025856669,"teacher_disagreement_score":0.9701441,"about_ca_system_score_codex":0.000082767525,"about_ca_system_score_gemma":0.00003575423,"threshold_uncertainty_score":0.8362493},"labels":[],"label_agreement":null},{"id":"W4406866174","doi":"10.1145/3715008","title":"Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Reinforcement learning; Suite; Scalability; Minification; Similarity (geometry); Test (biology); Artificial intelligence; Software engineering; Machine learning; Test case; Programming language; Operating system","score_opus":0.04087899492526334,"score_gpt":0.2917156633049735,"score_spread":0.2508366683797102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406866174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067306927,0.00008041264,0.99257207,0.0003545817,0.00019545786,0.0001362995,0.0000012803806,0.005963729,0.000023099008],"genre_scores_gemma":[0.14192058,0.000047140762,0.8572,0.00024075777,0.000010690467,0.000059343784,0.0000038419157,0.000015537882,0.0005020677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888325,0.00010955156,0.00020404342,0.0003989814,0.000120325014,0.00028385752],"domain_scores_gemma":[0.9949325,0.0043269275,0.00004898452,0.0005229933,0.00009653943,0.00007206542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005198114,0.00019817566,0.00024440142,0.00035499458,0.00024833524,0.000071624796,0.00034780212,0.00013464851,0.0000055326846],"category_scores_gemma":[0.0023257807,0.00018560245,0.000040122326,0.00058144744,0.00004033226,0.00016255939,0.00003194706,0.0003870799,0.0000018496779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004394072,0.00010973517,0.007514234,0.00025126076,0.00012235259,0.000021797327,0.0006588008,0.7208798,0.00019694894,0.0013792531,0.0004772531,0.2683446],"study_design_scores_gemma":[0.0021569063,0.0020988304,0.006890507,0.001140158,0.00022132088,0.00027142288,0.000063285304,0.94634444,0.018546226,0.008020303,0.01277443,0.0014721571],"about_ca_topic_score_codex":0.000040912302,"about_ca_topic_score_gemma":0.0000024060303,"teacher_disagreement_score":0.26687247,"about_ca_system_score_codex":0.000046379708,"about_ca_system_score_gemma":0.000058524838,"threshold_uncertainty_score":0.75686485},"labels":[],"label_agreement":null},{"id":"W4406866661","doi":"10.1145/3715109","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"","keywords":"Benchmarking; Computer science; Competence (human resources); Knowledge management; Business; Psychology; Marketing","score_opus":0.08995787232149585,"score_gpt":0.34867155279438006,"score_spread":0.25871368047288423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406866661","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004324777,0.002834901,0.9917193,0.00062934216,0.00016751455,0.00015842971,0.000004046915,0.00015997741,0.0000016994219],"genre_scores_gemma":[0.18734075,0.00019400714,0.81225467,0.00012725845,0.000008655018,0.00004855698,0.0000024510227,0.0000040464984,0.000019577159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938905,0.00013298093,0.00015501758,0.00017502073,0.0000505914,0.00009733547],"domain_scores_gemma":[0.997439,0.0019761224,0.000048497102,0.00045519983,0.00006424663,0.000016928734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007843094,0.000084225576,0.00013797902,0.00012179457,0.00018896352,0.000031461503,0.0003922682,0.000068800335,8.259618e-7],"category_scores_gemma":[0.00041655338,0.00006811858,0.000028854545,0.00016049443,0.00005409734,0.00008905956,0.00003299369,0.00015841513,4.215692e-8],"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":[0.000019326599,0.000050161725,0.00006484689,0.00025336642,0.00008234118,5.504906e-7,0.0019261666,0.0060926755,0.021958597,0.066866174,0.00008747423,0.9025983],"study_design_scores_gemma":[0.0013711541,0.0007729082,0.0018288326,0.00069860596,0.0002569952,0.00010109218,0.00020681156,0.60392386,0.30343997,0.080107346,0.006527245,0.0007652055],"about_ca_topic_score_codex":0.000021163858,"about_ca_topic_score_gemma":0.00001276496,"teacher_disagreement_score":0.9018331,"about_ca_system_score_codex":0.000015716632,"about_ca_system_score_gemma":0.000016625074,"threshold_uncertainty_score":0.27777952},"labels":[],"label_agreement":null},{"id":"W4406957844","doi":"10.1145/3712002","title":"Quantum Software Engineering: Roadmap and Challenges Ahead","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Quantum Computing Algorithms and Architecture","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":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación; European Commission","keywords":"Computer science; Software engineering; Software requirements; Software; Systems engineering; Software development; Software construction; Programming language; Engineering","score_opus":0.05628912930751191,"score_gpt":0.285834054176502,"score_spread":0.22954492486899009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406957844","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017580694,0.005322182,0.97327214,0.0016098894,0.0011384533,0.00011541739,0.0000051456227,0.00095308153,0.0000029776706],"genre_scores_gemma":[0.04477303,0.001289062,0.9535711,0.00017931305,0.00005534202,0.00003252354,0.000001176205,0.000025411739,0.000073040595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848825,0.00012745477,0.00024626037,0.0006126711,0.000115082636,0.0004102742],"domain_scores_gemma":[0.99627835,0.002855425,0.000036673468,0.0006457125,0.00004399422,0.00013984244],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057111954,0.000302666,0.0003944357,0.00043175646,0.00018042907,0.000063197775,0.0004700702,0.000201615,0.0000025010427],"category_scores_gemma":[0.0010709402,0.00029474436,0.00008181645,0.00033147607,0.000045721947,0.00011007199,0.0000674632,0.0005169221,0.0000022229303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015328083,0.000063064996,0.000082191444,0.00039812067,0.00013970316,0.000023880755,0.001060279,0.1108961,0.00025947927,0.01315779,0.000028963346,0.8738751],"study_design_scores_gemma":[0.0019941882,0.0009010138,0.023507377,0.0007687487,0.0001555312,0.00067537953,0.00013612886,0.8909385,0.003367182,0.009790581,0.06604826,0.0017171218],"about_ca_topic_score_codex":0.000015803986,"about_ca_topic_score_gemma":0.0000023448001,"teacher_disagreement_score":0.872158,"about_ca_system_score_codex":0.000022827608,"about_ca_system_score_gemma":0.000039058395,"threshold_uncertainty_score":0.99995047},"labels":[],"label_agreement":null},{"id":"W4406957873","doi":"10.1145/3715693","title":"Assessing the Robustness of Test Selection Methods for Deep Neural Networks","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","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 Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Artificial neural network; Machine learning; Robustness testing; Biology","score_opus":0.05595642973612091,"score_gpt":0.38734945323747966,"score_spread":0.33139302350135874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406957873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006319021,0.00021891142,0.99687296,0.00038502688,0.0014682432,0.00017944917,5.400059e-7,0.00024025775,0.000002722546],"genre_scores_gemma":[0.07935718,0.000012524797,0.9204059,0.00007018936,0.00005086027,0.000060031274,7.6290405e-7,0.000013454553,0.00002908139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866396,0.00048399455,0.00024736053,0.00030676363,0.00005688325,0.00024103424],"domain_scores_gemma":[0.98123443,0.018181505,0.000079108766,0.00037972155,0.000091919035,0.000033322533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018190044,0.00015560363,0.00027354364,0.00020259354,0.0002827023,0.00006163017,0.00048452654,0.00014316563,0.0000020008592],"category_scores_gemma":[0.004381888,0.00012992784,0.00008879728,0.00060050766,0.00005261452,0.00022328651,0.000030885218,0.00044051686,4.5517087e-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":[0.000004006931,0.000009931523,0.00008260869,0.000026630916,0.00002618341,1.1035062e-7,0.000057730635,0.6243794,0.00015478343,0.00063902495,0.0000012928938,0.37461832],"study_design_scores_gemma":[0.00023535767,0.000065368156,0.0010090579,0.000022519844,0.000057821166,0.000019491128,0.000037401565,0.9967154,0.0009860122,0.00043290225,0.00031088642,0.0001077385],"about_ca_topic_score_codex":0.000009784827,"about_ca_topic_score_gemma":0.0000022331253,"teacher_disagreement_score":0.3745106,"about_ca_system_score_codex":0.000029894378,"about_ca_system_score_gemma":0.000027442902,"threshold_uncertainty_score":0.52983034},"labels":[],"label_agreement":null},{"id":"W4407084737","doi":"10.1145/3715111","title":"Software Engineering by and for Humans in an AI Era","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Innovative Human-Technology Interaction","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 Victoria","funders":"Generalitat Valenciana; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Software engineering; Software; Programming language","score_opus":0.054314640578669325,"score_gpt":0.34711768674939253,"score_spread":0.2928030461707232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407084737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075216055,0.00018282798,0.92271197,0.0004888901,0.0006290166,0.00020560202,0.000011642321,0.0005526866,0.0000012952202],"genre_scores_gemma":[0.14653364,0.000030222636,0.85273576,0.00036268437,0.000016705599,0.00019035672,0.0000063593147,0.000020826721,0.00010343625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881005,0.000072085604,0.00025877665,0.00049329957,0.000057045312,0.000308727],"domain_scores_gemma":[0.9977835,0.0016117296,0.00003461393,0.00044584618,0.00007949937,0.000044806697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005006316,0.00021359065,0.00029090137,0.000719395,0.0001269252,0.00005086676,0.00034676553,0.00024477942,0.0000034627383],"category_scores_gemma":[0.0009805816,0.00024067369,0.000038057162,0.00042375427,0.00004317862,0.00037896974,0.000025057452,0.00056633656,7.126175e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002293669,0.00053885323,0.0058351965,0.0009639224,0.00050945743,0.000033772045,0.0042800475,0.072318435,0.06274889,0.116177805,0.00079436006,0.7355699],"study_design_scores_gemma":[0.015455549,0.0059862714,0.091669045,0.0018829181,0.0004537941,0.0006126155,0.0008806017,0.39547578,0.3230149,0.05485101,0.10333215,0.006385395],"about_ca_topic_score_codex":0.00001787553,"about_ca_topic_score_gemma":0.000018121074,"teacher_disagreement_score":0.7291845,"about_ca_system_score_codex":0.00006613207,"about_ca_system_score_gemma":0.000026668698,"threshold_uncertainty_score":0.9814388},"labels":[],"label_agreement":null},{"id":"W4407241478","doi":"10.1145/3711903","title":"Obfuscated Clone Search in JavaScript based on Reinforcement Subsequence Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Blackberry (Canada); Defence Research and Development Canada; McGill University; Queen's University","funders":"","keywords":"Computer science; JavaScript; Scripting language; Codebase; Code refactoring; Programming language; Reinforcement learning; Artificial intelligence; Automatic summarization; Source code; Code (set theory); Theoretical computer science; Software","score_opus":0.0702671741606317,"score_gpt":0.32818521897802067,"score_spread":0.25791804481738895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407241478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0224061,0.00014789964,0.97552025,0.00047127056,0.00051586994,0.00021470369,0.000001367349,0.00070050865,0.000022025515],"genre_scores_gemma":[0.51997405,0.00007072164,0.4791767,0.00017509647,0.0000116190695,0.00010101739,0.0000031241696,0.000021125017,0.00046655544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796915,0.00032469936,0.00029608095,0.0005772497,0.00027644355,0.00055638835],"domain_scores_gemma":[0.99213946,0.0068591144,0.000022441787,0.0007810843,0.000076216864,0.00012169285],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016827541,0.00024180696,0.00031759928,0.0011865819,0.00013000997,0.000061486906,0.00068818085,0.0001827702,0.000020740932],"category_scores_gemma":[0.004005236,0.0002585573,0.000069435686,0.0013098589,0.00004978149,0.00013653889,0.000040385163,0.0010305186,0.000010487682],"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":[0.000035504097,0.00004080216,0.0012081633,0.00008518911,0.000026432577,0.000024772651,0.00021440566,0.9447994,0.0009412421,0.0009566375,0.000009002591,0.05165843],"study_design_scores_gemma":[0.0021282698,0.0007864424,0.03396239,0.0005130939,0.000023761891,0.00003120531,0.00005860176,0.9359017,0.022340912,0.00032134866,0.0032271666,0.000705112],"about_ca_topic_score_codex":0.00011231788,"about_ca_topic_score_gemma":0.000003977138,"teacher_disagreement_score":0.49756795,"about_ca_system_score_codex":0.00019159804,"about_ca_system_score_gemma":0.00012876805,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W4407580437","doi":"10.1145/3717061","title":"An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Code (set theory); Data science; Information retrieval; Programming language","score_opus":0.20914820288916802,"score_gpt":0.39155547964417226,"score_spread":0.18240727675500423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407580437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063252166,0.005237664,0.9303295,0.0005377175,0.00016347886,0.00010380436,0.0000023593002,0.00037147984,0.0000018025758],"genre_scores_gemma":[0.27577952,0.00076512806,0.72330326,0.00009121055,0.000011091598,0.000013728105,8.5136355e-7,0.000005741418,0.00002946964],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913454,0.00022659102,0.00017027935,0.00027885308,0.00008037564,0.00010935517],"domain_scores_gemma":[0.99880624,0.0006480544,0.0000321108,0.00040047607,0.00006610344,0.000046999223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005517748,0.000112937225,0.00021199722,0.00025832618,0.00007369921,0.000022394339,0.00025410607,0.0000969151,0.0000013473029],"category_scores_gemma":[0.00027031984,0.000104975916,0.000017048944,0.00013505938,0.000033451648,0.00015529853,0.00002089966,0.00017428328,4.7416954e-8],"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":[0.000057111716,0.00036425504,0.0000984836,0.00019477647,0.0001473207,0.000020195126,0.007268498,0.0011386898,0.007002832,0.0055401274,0.000021464646,0.97814626],"study_design_scores_gemma":[0.011167402,0.021051375,0.021552777,0.0012583323,0.0012027142,0.00084554596,0.01237919,0.26124325,0.5974359,0.05855048,0.008918506,0.004394522],"about_ca_topic_score_codex":0.000006335299,"about_ca_topic_score_gemma":0.000007242664,"teacher_disagreement_score":0.9737517,"about_ca_system_score_codex":0.000012420917,"about_ca_system_score_gemma":0.000025849773,"threshold_uncertainty_score":0.42807937},"labels":[],"label_agreement":null},{"id":"W4408028155","doi":"10.1145/3721127","title":"Accountability in Code Review: The Role of Intrinsic Drivers and the Impact of LLMs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Aalborg Universitet","keywords":"Accountability; Computer science; Code (set theory); Political science; Programming language","score_opus":0.06464805720780835,"score_gpt":0.4021598462318052,"score_spread":0.3375117890239968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408028155","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":[0.51439524,0.012075534,0.47019842,0.0019544077,0.00035997928,0.00074531714,0.000022950879,0.00006180844,0.00018638067],"genre_scores_gemma":[0.98413694,0.006812444,0.008934112,0.00006241409,0.000008302038,0.000023516697,2.4188614e-7,0.0000036152164,0.000018392077],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892557,0.00054163206,0.00022634999,0.00011402375,0.00007128604,0.00012113403],"domain_scores_gemma":[0.99288,0.006764786,0.000049111142,0.00022895716,0.00005583085,0.000021326292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002693548,0.00006857627,0.0002563763,0.00006829354,0.00010354478,0.0000048690836,0.00019276798,0.00007359125,0.000019991669],"category_scores_gemma":[0.0040709223,0.00004239556,0.000074585674,0.00033034227,0.0006496846,0.000047776204,0.0000093655535,0.00020032148,2.5390747e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042286573,0.00013028388,0.014257387,0.0003484872,0.00027609084,6.337572e-7,0.034043275,0.03030967,0.00069510384,0.03524908,0.0000548139,0.8842123],"study_design_scores_gemma":[0.0058495007,0.0016747084,0.2888158,0.0072094207,0.002367405,0.00003994591,0.10624944,0.0124014225,0.06622225,0.41563532,0.09107379,0.0024610073],"about_ca_topic_score_codex":0.0075658904,"about_ca_topic_score_gemma":0.001037773,"teacher_disagreement_score":0.8817513,"about_ca_system_score_codex":0.000037165915,"about_ca_system_score_gemma":0.00006697102,"threshold_uncertainty_score":0.9990428},"labels":[],"label_agreement":null},{"id":"W4408054024","doi":"10.1145/3721125","title":"Unraveling Code Clone Dynamics in Deep Learning Frameworks","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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; University of Toronto; Université du Québec à Montréal","funders":"","keywords":"Computer science; Code (set theory); Software engineering; Artificial intelligence; Data science; Programming language","score_opus":0.03839091002517494,"score_gpt":0.32376943785259454,"score_spread":0.2853785278274196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408054024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02065272,0.00045764726,0.97678673,0.00040155818,0.0007842027,0.00012231039,0.0000019057619,0.00078523887,0.000007692368],"genre_scores_gemma":[0.25190848,0.00018535445,0.7476029,0.0000853956,0.000016232612,0.00004962405,0.0000020667949,0.00002179297,0.00012818944],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983653,0.00021293641,0.00028128715,0.00050956523,0.00015122778,0.0004797028],"domain_scores_gemma":[0.9893694,0.009842495,0.000026624017,0.0006046894,0.000058802558,0.000098001314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011539469,0.00021863177,0.0003312567,0.00084383093,0.00012193608,0.00006389578,0.0006289266,0.00041720434,0.000005887731],"category_scores_gemma":[0.0068240985,0.0002477914,0.0000642229,0.0010566935,0.000038894934,0.00014198896,0.000057253983,0.0019263362,0.0000046241316],"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":[0.000015036096,0.000041585932,0.004959444,0.00010347933,0.00005926768,0.000021603775,0.00044456992,0.69789726,0.00014458233,0.0055541666,0.000003331707,0.2907557],"study_design_scores_gemma":[0.0007849206,0.00015259426,0.021348104,0.00028534004,0.000023215776,0.00004971532,0.00014289803,0.97184557,0.0011896885,0.0026039474,0.0010781654,0.0004958502],"about_ca_topic_score_codex":0.000046011926,"about_ca_topic_score_gemma":0.000031488813,"teacher_disagreement_score":0.29025984,"about_ca_system_score_codex":0.00021771801,"about_ca_system_score_gemma":0.00004790795,"threshold_uncertainty_score":0.99999744},"labels":[],"label_agreement":null},{"id":"W4408473356","doi":"10.1145/3723355","title":"Enhancing Log Sentiments: An Exploratory Study of Sentiments and Emotions with Software Logs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Exploratory research; Data science; Software; World Wide Web; Programming language; Sociology","score_opus":0.03968515645815301,"score_gpt":0.30287675622678417,"score_spread":0.26319159976863116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408473356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4159185,0.00008101779,0.5832563,0.000023097513,0.00030035037,0.0002002466,0.0000036142249,0.00021598466,8.8084226e-7],"genre_scores_gemma":[0.55566514,0.000030883428,0.44413605,0.00004078248,0.000009519555,0.000060233222,0.0000016393475,0.000011742969,0.000044017186],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99839973,0.0002985328,0.00035636983,0.00053528324,0.00015536531,0.00025472292],"domain_scores_gemma":[0.99802005,0.00089221296,0.000075070646,0.0008032475,0.00010932747,0.00010007416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079581933,0.00022526536,0.0003954457,0.00036781735,0.00021315395,0.00003461534,0.00031568526,0.00012406702,0.0000046324367],"category_scores_gemma":[0.00023241293,0.000195284,0.000039634833,0.00046704398,0.00006570579,0.00036618946,0.0000460445,0.0002516779,0.0000015571152],"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":[0.0005966351,0.0076164836,0.16415346,0.00391495,0.0037379982,0.000106174775,0.06387426,0.14079168,0.012014152,0.00082716165,0.000075784184,0.6022913],"study_design_scores_gemma":[0.04338306,0.032045037,0.5773226,0.0063721593,0.0038940702,0.0012738879,0.04852616,0.043348115,0.22428706,0.0074412883,0.0031259828,0.008980587],"about_ca_topic_score_codex":0.000037724487,"about_ca_topic_score_gemma":0.00004066864,"teacher_disagreement_score":0.59331065,"about_ca_system_score_codex":0.000035508998,"about_ca_system_score_gemma":0.000058443275,"threshold_uncertainty_score":0.796345},"labels":[],"label_agreement":null},{"id":"W4408797770","doi":"10.1145/3716822","title":"An empirical study on vulnerability disclosure management of open source software systems","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Information and Cyber Security","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":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Vulnerability (computing); Vulnerability management; Open source; Software; Open source software; Empirical research; Computer security; Vulnerability assessment; Operating system","score_opus":0.07854885103263813,"score_gpt":0.37620784924822176,"score_spread":0.2976589982155836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408797770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063370764,0.00004724297,0.93510836,0.00013297444,0.0005755264,0.00044464262,0.000007745424,0.00028095313,0.00003178946],"genre_scores_gemma":[0.6259707,0.00000872191,0.37363032,0.00012631652,0.0000074549357,0.0001070374,0.000002270043,0.000008108893,0.00013906657],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985019,0.00044573887,0.0003366367,0.00037072267,0.0001524958,0.0001924855],"domain_scores_gemma":[0.9979211,0.0008732085,0.000054239903,0.001010604,0.00006216568,0.00007864483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013355372,0.00016890575,0.00032618077,0.00021109714,0.0001596279,0.0001014287,0.0009994031,0.00009813364,0.000004628365],"category_scores_gemma":[0.00015519065,0.00015284446,0.00005244028,0.00040138594,0.000029173412,0.00029356807,0.00007597117,0.0002803903,0.0000022186623],"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":[0.0002787127,0.0029083067,0.013273977,0.0011010071,0.0009043629,0.000022663558,0.015923936,0.28863844,0.000043458116,0.025032395,0.00020404544,0.65166867],"study_design_scores_gemma":[0.014763909,0.009483884,0.7426924,0.0015315462,0.0009305153,0.00014434198,0.019383712,0.1530489,0.006062537,0.0081702685,0.04005185,0.0037361414],"about_ca_topic_score_codex":0.00005203111,"about_ca_topic_score_gemma":0.0000044089384,"teacher_disagreement_score":0.7294184,"about_ca_system_score_codex":0.000037974496,"about_ca_system_score_gemma":0.00002774572,"threshold_uncertainty_score":0.6232816},"labels":[],"label_agreement":null},{"id":"W4408851891","doi":"10.1145/3725212","title":"Towards On-the-Fly Code Performance Profiling","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"National Key Research and Development Program of China","keywords":"Computer science; Profiling (computer programming); On the fly; Programming language; Software engineering; Operating system","score_opus":0.088324649823905,"score_gpt":0.3216710607829046,"score_spread":0.23334641095899958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408851891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011264966,0.00011360438,0.98125535,0.0012073652,0.00060199766,0.00013628701,0.0000033546087,0.0053654024,0.00005166796],"genre_scores_gemma":[0.14231686,0.000058060352,0.8566374,0.0007073841,0.000017672477,0.00009177348,6.226311e-7,0.000012561227,0.00015763783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891007,0.0001406869,0.00018931463,0.00037090472,0.000113023656,0.00027599162],"domain_scores_gemma":[0.9949314,0.004143266,0.0000330005,0.00078465027,0.000054644945,0.00005302036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009904177,0.00018647283,0.00021380359,0.00025897057,0.00025000735,0.000052258827,0.00065064034,0.00011959337,0.0000037778993],"category_scores_gemma":[0.0022594372,0.00014902072,0.000060245566,0.00044226553,0.000050276798,0.000089264984,0.00003365813,0.00043847252,0.000004301174],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034758876,0.00007684087,0.00057692075,0.00015047927,0.00010103387,0.0000087175995,0.0004445989,0.018930165,0.0003772582,0.020886628,0.0006934613,0.95771915],"study_design_scores_gemma":[0.0020595398,0.0023989633,0.013497296,0.0020010015,0.00023744449,0.0004954943,0.00007003049,0.5028499,0.3312757,0.111971065,0.030533083,0.0026105],"about_ca_topic_score_codex":0.000015467867,"about_ca_topic_score_gemma":5.9558846e-7,"teacher_disagreement_score":0.95510864,"about_ca_system_score_codex":0.000036137055,"about_ca_system_score_gemma":0.000059345588,"threshold_uncertainty_score":0.60768884},"labels":[],"label_agreement":null},{"id":"W4409478867","doi":"10.1145/3729533","title":"Evaluating API-Level Deep Learning Fuzzers: A Comprehensive Benchmarking Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Benchmarking; Deep learning; Artificial intelligence; Software engineering; Machine learning; Data science","score_opus":0.16246850762860587,"score_gpt":0.392204384378163,"score_spread":0.22973587674955714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409478867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031148257,0.00016147103,0.9672189,0.000121200734,0.0002841033,0.0002850941,0.0000011633836,0.00076593895,0.0000138927735],"genre_scores_gemma":[0.27406132,0.00003601756,0.725509,0.00008960723,0.000017599481,0.00016827972,7.750582e-7,0.00000937207,0.00010805516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868834,0.00027032365,0.00024583988,0.00045664347,0.00011045632,0.0002283771],"domain_scores_gemma":[0.99730295,0.0020026097,0.00005521025,0.0004888744,0.000092870345,0.00005747941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006426266,0.0001723561,0.00024476738,0.0003395655,0.0003826034,0.000057752382,0.00036738988,0.00010155621,0.000008515324],"category_scores_gemma":[0.0003853727,0.00018276836,0.00006806474,0.0005683123,0.00002705402,0.00011507507,0.000046025852,0.0004457548,0.0000028518623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009402515,0.00007822061,0.0002105447,0.000029109,0.00008987127,0.0000026159587,0.0008101516,0.06342825,0.001276885,0.0014072852,0.00000461475,0.93265307],"study_design_scores_gemma":[0.003530667,0.0043075182,0.055760343,0.00035720156,0.00046959805,0.0002380605,0.0034106765,0.8894279,0.01605471,0.009477514,0.015011156,0.0019546456],"about_ca_topic_score_codex":0.00003542308,"about_ca_topic_score_gemma":0.0000051926845,"teacher_disagreement_score":0.9306984,"about_ca_system_score_codex":0.0000454295,"about_ca_system_score_gemma":0.000029171253,"threshold_uncertainty_score":0.74530774},"labels":[],"label_agreement":null},{"id":"W4410028485","doi":"10.1145/3733717","title":"Learning-Guided Fuzzing for Testing Stateful SDN Controllers","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Fuzz testing; Stateful firewall; Computer science; Computer security; Programming language; Software","score_opus":0.0684615723814985,"score_gpt":0.3068296410605721,"score_spread":0.2383680686790736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410028485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06767533,0.00047894972,0.92947507,0.00008023477,0.0011720095,0.0002093917,0.000010063038,0.0008594647,0.000039512688],"genre_scores_gemma":[0.36168423,0.00020866843,0.63739413,0.00009495381,0.00007253667,0.00016100965,0.0000049885966,0.000046253477,0.00033321558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999041,0.000070221555,0.00024072255,0.0002454809,0.00005922022,0.0003433042],"domain_scores_gemma":[0.9946263,0.0050253775,0.00001942422,0.00020186281,0.00005416375,0.00007288471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051881577,0.00019744613,0.00031422696,0.00026488173,0.00019599176,0.000023972321,0.00014333932,0.00016166149,0.0000057992147],"category_scores_gemma":[0.0025733542,0.00020650888,0.00007771749,0.0002870784,0.00004122486,0.000065399916,0.00000580405,0.0004063105,0.0000020031052],"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":[0.000027864815,0.000010769001,0.00017861777,0.00022879346,0.000113344046,0.0000023252132,0.00030176717,0.9439369,0.00395457,0.00013255709,0.00007755901,0.051034965],"study_design_scores_gemma":[0.006280847,0.000874212,0.0045734486,0.0007245864,0.00050814677,0.00015016814,0.0010866603,0.85630435,0.048410095,0.002821566,0.07653548,0.0017304468],"about_ca_topic_score_codex":0.000011760224,"about_ca_topic_score_gemma":0.0000042277857,"teacher_disagreement_score":0.2940089,"about_ca_system_score_codex":0.00004140016,"about_ca_system_score_gemma":0.000023839635,"threshold_uncertainty_score":0.8421188},"labels":[],"label_agreement":null},{"id":"W4410089993","doi":"10.1145/3733715","title":"Stress Testing Control Loops in Cyber-Physical Systems—RCR Report","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Embedded Systems Design Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Knut och Alice Wallenbergs Stiftelse","keywords":"Computer science; Cyber-physical system; Stress testing (software); Reliability engineering; Programming language; Operating system","score_opus":0.06220045181420397,"score_gpt":0.3230771558298215,"score_spread":0.2608767040156175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410089993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011000984,0.00023256027,0.9867483,0.00010535527,0.00067825767,0.00027841466,0.000005363597,0.0009122792,0.000038530412],"genre_scores_gemma":[0.45636812,0.000005323623,0.54331243,0.00003513483,0.000026220318,0.000133921,5.845089e-7,0.000011341868,0.00010693613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831086,0.00040497855,0.0003824199,0.00048023215,0.00011984572,0.0003016822],"domain_scores_gemma":[0.9934316,0.0055753468,0.00006904132,0.00077529065,0.00008192273,0.000066766865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012038138,0.00019856275,0.0004543639,0.00043380386,0.00007304074,0.000053416305,0.00045422386,0.00016267673,4.5870905e-7],"category_scores_gemma":[0.002266101,0.00020048946,0.00005731804,0.0006083697,0.00003068817,0.00015091484,0.000019872736,0.00041164435,0.0000014167731],"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":[0.00008198126,0.0006116714,0.012490954,0.0016427205,0.0005833798,0.0015547214,0.0028225947,0.5630506,0.023742408,0.046272628,0.00018182425,0.3469645],"study_design_scores_gemma":[0.0052017104,0.0013170555,0.028162986,0.0042507127,0.00033935677,0.004140327,0.00049527467,0.86799574,0.0666209,0.01473857,0.0037794109,0.002957943],"about_ca_topic_score_codex":0.0001911453,"about_ca_topic_score_gemma":0.0000070022525,"teacher_disagreement_score":0.44536716,"about_ca_system_score_codex":0.00007157063,"about_ca_system_score_gemma":0.00006370175,"threshold_uncertainty_score":0.81757236},"labels":[],"label_agreement":null},{"id":"W4410344404","doi":"10.1145/3735553","title":"Large Language Models for Automated Web-Form-Test Generation: An Empirical Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Software engineering; Web application; Natural language processing; Programming language; World Wide Web; Information retrieval","score_opus":0.10826609347819456,"score_gpt":0.39020246290793753,"score_spread":0.281936369429743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410344404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03186381,0.00010234411,0.95178664,0.00018467382,0.0004041658,0.00031964053,0.00001929288,0.015316723,0.0000027011351],"genre_scores_gemma":[0.3135576,0.000006053249,0.6859276,0.0002336763,0.000027066471,0.0001727869,0.0000059270246,0.000013756957,0.00005550555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987487,0.00016332814,0.00023587319,0.00046732553,0.000092660535,0.00029209486],"domain_scores_gemma":[0.9960326,0.0030528533,0.000032771022,0.0007172469,0.00008163228,0.00008291172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010318039,0.00019289664,0.0002743344,0.00031992584,0.00023362883,0.00007263767,0.00043153824,0.00014466482,0.000001996026],"category_scores_gemma":[0.001588337,0.00018780379,0.000059674618,0.0003762717,0.000017532753,0.00022704597,0.000027882314,0.00021114839,8.3988465e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016257248,0.0053170673,0.009873119,0.00056896947,0.0007884064,0.00011505817,0.036108814,0.29474047,0.004995228,0.0068088043,0.009807663,0.6307138],"study_design_scores_gemma":[0.0006277429,0.0005282648,0.0006150365,0.000023828576,0.000039595867,0.00002562179,0.000059287013,0.99400026,0.000804028,0.0027803609,0.0002818047,0.0002141893],"about_ca_topic_score_codex":0.000018123923,"about_ca_topic_score_gemma":0.000012713529,"teacher_disagreement_score":0.69925976,"about_ca_system_score_codex":0.000034365858,"about_ca_system_score_gemma":0.00006556336,"threshold_uncertainty_score":0.7658416},"labels":[],"label_agreement":null},{"id":"W4410537502","doi":"10.1145/3736407","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Coding (social sciences); Natural language processing; Artificial intelligence; Programming language; Statistics; Mathematics","score_opus":0.0823360169353762,"score_gpt":0.36758500400909394,"score_spread":0.2852489870737177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410537502","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024327938,0.0005158159,0.99514765,0.00026061822,0.00032952442,0.00025224415,0.0002701776,0.0007869856,0.000004216465],"genre_scores_gemma":[0.08475281,0.000027818123,0.91426086,0.0006654977,0.000021545984,0.00012232641,0.00007131341,0.000014353427,0.000063442334],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987627,0.00011185984,0.00019487466,0.0004987453,0.0000925511,0.00033926306],"domain_scores_gemma":[0.9976281,0.001568841,0.000033918743,0.0006042821,0.00005772377,0.00010712234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084985635,0.0001909016,0.00026452847,0.00033421325,0.00018961423,0.00009191851,0.00074088795,0.00014801913,0.0000033193223],"category_scores_gemma":[0.0006868558,0.00018424564,0.000041576444,0.0003415741,0.000017439259,0.0004074826,0.000043822612,0.00024557806,0.0000012761545],"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":[0.00021541926,0.00036859632,0.000026602243,0.0008130405,0.00029395337,0.00002906472,0.014907109,0.023781464,0.05436829,0.15383203,0.0009888462,0.75037557],"study_design_scores_gemma":[0.0027295505,0.002179902,0.00008468506,0.0010115625,0.00029850268,0.00018053845,0.0017527853,0.2052687,0.6252098,0.14440629,0.014528096,0.0023495883],"about_ca_topic_score_codex":0.00005863178,"about_ca_topic_score_gemma":0.000022677694,"teacher_disagreement_score":0.748026,"about_ca_system_score_codex":0.000030934483,"about_ca_system_score_gemma":0.000046500412,"threshold_uncertainty_score":0.7513319},"labels":[],"label_agreement":null},{"id":"W4410610020","doi":"10.1145/3735635","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Mining 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 British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Current (fluid); First-generation programming language; Programming paradigm","score_opus":0.09567141734564485,"score_gpt":0.37935461176167246,"score_spread":0.28368319441602763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410610020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053793757,0.00070560264,0.9974191,0.00021721935,0.00044964816,0.00022220604,0.000058174057,0.00038501242,0.000005062931],"genre_scores_gemma":[0.00926976,0.00010134062,0.9900645,0.000069552036,0.00002407257,0.0003007437,0.000013911707,0.000011004928,0.00014513773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909186,0.000039671195,0.00018667697,0.00037878248,0.000063103485,0.00023989078],"domain_scores_gemma":[0.9981087,0.0011940778,0.000028855007,0.0005637927,0.00004043142,0.00006413417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005100722,0.00013432953,0.0001804355,0.00018322325,0.00011950767,0.000066211265,0.00048652253,0.00006849325,0.0000032395324],"category_scores_gemma":[0.00031245057,0.00013314959,0.00005908346,0.00029440687,0.000026621456,0.00014394519,0.000029334355,0.00019462554,0.0000022493762],"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":[0.0000034175293,0.000036148856,0.0000022826002,0.000057395635,0.000022514336,0.000001067877,0.0012493926,0.0075777103,0.00008792853,0.00846764,0.00003799461,0.9824565],"study_design_scores_gemma":[0.0012852753,0.00061827723,0.00019430641,0.00045481342,0.00026362998,0.00012885951,0.0020457844,0.7949997,0.02517046,0.015374108,0.15803431,0.001430444],"about_ca_topic_score_codex":0.000014633285,"about_ca_topic_score_gemma":0.000003901292,"teacher_disagreement_score":0.98102605,"about_ca_system_score_codex":0.000020880314,"about_ca_system_score_gemma":0.00004066585,"threshold_uncertainty_score":0.5429683},"labels":[],"label_agreement":null},{"id":"W4410644286","doi":"10.1145/3736758","title":"CI/CD Configuration Practices in Open Source Android Apps: An Empirical Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Trent University","funders":"","keywords":"Computer science; Android (operating system); Open source; Empirical research; Open source software; World Wide Web; Operating system; Software","score_opus":0.12759613669649247,"score_gpt":0.42595277183427765,"score_spread":0.2983566351377852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410644286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032891016,0.00006397845,0.96524966,0.00032389883,0.000284426,0.00047458475,0.0000017004458,0.00069202523,0.000018706403],"genre_scores_gemma":[0.27244994,0.00003323245,0.72695506,0.00020421168,0.00001147283,0.00020559787,0.000001152467,0.0000116071315,0.0001277323],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99837047,0.0005106854,0.000276633,0.00054552034,0.00009344691,0.00020323039],"domain_scores_gemma":[0.9971114,0.001990522,0.00009807004,0.0006774901,0.00005799885,0.00006452786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012340843,0.00016581011,0.0002821872,0.00044921777,0.00013098998,0.000120759156,0.0007282258,0.00013126877,0.0000066855596],"category_scores_gemma":[0.0017662486,0.00017224977,0.000027261325,0.00060693163,0.000025774521,0.00073103287,0.00005818999,0.00041232706,0.0000018797099],"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":[0.00017764271,0.00079828344,0.0032851386,0.00006264444,0.00009655252,0.00002976408,0.0034100339,0.04658207,0.002265215,0.000732588,0.000039941497,0.94252014],"study_design_scores_gemma":[0.020685332,0.018774556,0.19277202,0.0009981443,0.00062579056,0.0011872783,0.014370611,0.24233323,0.27925098,0.058000665,0.1643035,0.0066978955],"about_ca_topic_score_codex":0.0001042882,"about_ca_topic_score_gemma":0.00009283685,"teacher_disagreement_score":0.93582225,"about_ca_system_score_codex":0.00005378488,"about_ca_system_score_gemma":0.00005444091,"threshold_uncertainty_score":0.7024142},"labels":[],"label_agreement":null},{"id":"W4410771641","doi":"10.1145/3736405","title":"Improving Code Reviewer Recommendation: Accuracy, Latency, Workload, and Bystanders","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Concordia University","funders":"","keywords":"Computer science; Workload; Code (set theory); Latency (audio); Operating system; Telecommunications; Programming language","score_opus":0.07592995547935187,"score_gpt":0.34187308048692294,"score_spread":0.26594312500757106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410771641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035055561,0.001915928,0.9913905,0.0011834115,0.0011458766,0.00019551239,0.000005608124,0.00065057614,0.000007024596],"genre_scores_gemma":[0.032776617,0.0017483264,0.96479213,0.0002910633,0.00003506319,0.000089403955,0.000002271099,0.000023690873,0.00024141902],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985351,0.00017764219,0.00027686055,0.0005309476,0.0001145004,0.00036494993],"domain_scores_gemma":[0.9904959,0.008611148,0.000041264004,0.00061740883,0.00010990353,0.00012432862],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012170039,0.0002217222,0.00031964047,0.00040046213,0.00017599868,0.000093892006,0.00043543667,0.00016161066,0.000013787364],"category_scores_gemma":[0.00893792,0.00022459,0.000058004516,0.00059457135,0.000047465768,0.00026881575,0.00006728656,0.0005061047,0.0000037253433],"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":[0.000015386144,0.000023591672,0.00081541674,0.00025060505,0.00008359687,0.00000605357,0.00022389469,0.0028172666,0.0002580324,0.0006112173,0.00015954644,0.9947354],"study_design_scores_gemma":[0.015642585,0.002512947,0.10736707,0.006655921,0.0010562037,0.0015562021,0.0008997148,0.36548722,0.036353476,0.019664196,0.43370268,0.009101804],"about_ca_topic_score_codex":0.000035004072,"about_ca_topic_score_gemma":0.000006708311,"teacher_disagreement_score":0.9856336,"about_ca_system_score_codex":0.00006457245,"about_ca_system_score_gemma":0.00006356905,"threshold_uncertainty_score":0.9994102},"labels":[],"label_agreement":null},{"id":"W4411087888","doi":"10.1145/3742894","title":"The Havoc Paradox in Generator-Based Fuzzing","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Computer science; Generator (circuit theory); Programming language; Software; Power (physics)","score_opus":0.0603762164017855,"score_gpt":0.3174931715724063,"score_spread":0.25711695517062083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411087888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036697853,0.0005996084,0.9909579,0.0009103751,0.00056014105,0.0000940335,0.000001046057,0.0032004658,0.0000066316125],"genre_scores_gemma":[0.12888606,0.000052675292,0.87054634,0.0003648936,0.000011209586,0.00008036626,4.0065476e-7,0.000009635844,0.000048431375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890786,0.00020960205,0.00020716552,0.00031831925,0.00007953326,0.00027753704],"domain_scores_gemma":[0.99205565,0.007169219,0.000028140772,0.0006680635,0.000033541877,0.000045362973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010995426,0.00014954415,0.0001871535,0.00028745778,0.00022425625,0.00006950423,0.0005308977,0.00011188429,7.1998096e-7],"category_scores_gemma":[0.002217167,0.00012408358,0.000050672224,0.000512468,0.000044699278,0.000066643515,0.000021415934,0.00033684765,0.0000012123453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024255653,0.000057023037,0.0018348153,0.00005600943,0.00004029771,0.00001836065,0.00024100553,0.044420496,0.00037429566,0.006706925,0.0003516169,0.9458749],"study_design_scores_gemma":[0.003139637,0.0007291164,0.02266729,0.0010390946,0.00011491533,0.0001708871,0.000058474772,0.7438399,0.047454428,0.14404854,0.034788005,0.0019497087],"about_ca_topic_score_codex":0.000044392913,"about_ca_topic_score_gemma":0.000009082593,"teacher_disagreement_score":0.9439252,"about_ca_system_score_codex":0.000041242693,"about_ca_system_score_gemma":0.00006553103,"threshold_uncertainty_score":0.5059982},"labels":[],"label_agreement":null},{"id":"W4411236083","doi":"10.1145/3744644","title":"LLM-Cure: LLM-Based Competitor User Review Analysis for Feature Enhancement","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University; Université du Québec à Montréal","funders":"","keywords":"Computer science; Feature (linguistics); Artificial intelligence","score_opus":0.046042394086885305,"score_gpt":0.3511223933018579,"score_spread":0.3050799992149726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411236083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008232068,0.0038914825,0.9928234,0.0020869249,0.00027502925,0.00031574583,0.000014014098,0.0005079813,0.0000030716938],"genre_scores_gemma":[0.0021936577,0.0013871327,0.9943723,0.0012718361,0.00001741005,0.00029246265,0.000016176924,0.000012451091,0.0004365596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986686,0.00015690272,0.00027811594,0.0005159799,0.00011668456,0.00026368792],"domain_scores_gemma":[0.9966114,0.0022124585,0.000072649585,0.00090844894,0.00012569837,0.000069334266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000729087,0.00022573455,0.00060333114,0.0005590197,0.00013276901,0.000029620585,0.00055181363,0.0001353144,0.000012094041],"category_scores_gemma":[0.00066307717,0.00021407453,0.0003016563,0.0013744934,0.00003071026,0.00011905199,0.000019335268,0.00025083774,0.0000012582498],"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":[0.00012022748,0.00096921425,0.00077038404,0.0039716265,0.0062939217,0.000015079669,0.00026286847,0.15437125,0.008860749,0.025132656,0.0033370536,0.795895],"study_design_scores_gemma":[0.003181192,0.0017853136,0.004920556,0.0030102816,0.009698323,0.000021331984,0.000035356315,0.11391682,0.2884494,0.0067203143,0.5653564,0.0029047488],"about_ca_topic_score_codex":0.0000080860555,"about_ca_topic_score_gemma":0.000008983767,"teacher_disagreement_score":0.7929902,"about_ca_system_score_codex":0.000063029176,"about_ca_system_score_gemma":0.00004334993,"threshold_uncertainty_score":0.87297064},"labels":[],"label_agreement":null},{"id":"W4411488587","doi":"10.1145/3744920","title":"On the Utility of Domain Modeling Assistance with Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"McMaster University; Université de Montréal","funders":"","keywords":"Computer science; Modeling language; Domain (mathematical analysis); Usability; Software engineering; Domain analysis; Abstraction; Domain-specific language; Process (computing); Model-driven architecture; Context (archaeology); Subject-matter expert; Domain model; Software; Domain engineering; Human–computer interaction; Software development; Data science; Artificial intelligence; Domain knowledge; Programming language; Component-based software engineering; Software construction","score_opus":0.06253040734009754,"score_gpt":0.3178245270606738,"score_spread":0.25529411972057625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411488587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07787291,0.0002514223,0.9209518,0.0002891121,0.00016306505,0.000139634,0.000010557197,0.00029759668,0.000023892444],"genre_scores_gemma":[0.5556725,0.000014603708,0.44415933,0.00005841318,0.0000042204383,0.000035976853,4.4456849e-7,0.000009155257,0.000045349105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987816,0.00018430763,0.00018313524,0.00035679867,0.00018873317,0.00030542538],"domain_scores_gemma":[0.99193877,0.006968928,0.000024616927,0.0009484467,0.000064772656,0.00005443805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012573489,0.00016652493,0.0002480614,0.00023958596,0.00011580738,0.00002463405,0.0005984764,0.0000974016,0.000008035432],"category_scores_gemma":[0.001334816,0.00012207421,0.000056729295,0.0005338114,0.000041680985,0.00010557704,0.000030434487,0.00044398507,8.6185486e-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":[0.00011343614,0.00012422558,0.0001292096,0.00018818432,0.000186164,0.000014462308,0.0018808616,0.90541255,0.00045031452,0.06750542,0.000040229297,0.023954961],"study_design_scores_gemma":[0.0005905522,0.00015558425,0.00075923046,0.0001976701,0.000022081134,0.000016131475,0.00016761925,0.98318195,0.0036766522,0.01086326,0.00013648938,0.00023279706],"about_ca_topic_score_codex":0.000021252805,"about_ca_topic_score_gemma":0.0000063658713,"teacher_disagreement_score":0.4777996,"about_ca_system_score_codex":0.00002727774,"about_ca_system_score_gemma":0.0000535537,"threshold_uncertainty_score":0.49780422},"labels":[],"label_agreement":null},{"id":"W4412033360","doi":"10.1145/3747289","title":"Towards Understanding Refactoring Engine Bugs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Software engineering; Programming language; Software","score_opus":0.1393592182729809,"score_gpt":0.35114929550490953,"score_spread":0.21179007723192864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412033360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005847108,0.00037274274,0.99013317,0.0005404297,0.0015622979,0.00013286636,0.000003827141,0.0013760958,0.0000314452],"genre_scores_gemma":[0.25708178,0.00012151705,0.74238384,0.00008011608,0.00003384969,0.000044937548,0.0000010505964,0.00002409841,0.00022879518],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983913,0.00011780174,0.0002491845,0.0005360354,0.00020291177,0.0005027744],"domain_scores_gemma":[0.9935248,0.0053932574,0.00002506186,0.0008571585,0.00005230075,0.0001474263],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092046236,0.00025836893,0.00033122674,0.0007738831,0.00017657698,0.000088305096,0.0007227584,0.00019400539,0.000011714413],"category_scores_gemma":[0.0036067646,0.0002701071,0.00008970408,0.00088314345,0.000041881343,0.00022444138,0.00006540039,0.0006117519,0.000005782042],"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":[0.000083212755,0.00018176193,0.0019416925,0.00078556855,0.00078990497,0.00010621908,0.0021701502,0.1993255,0.006096728,0.0936762,0.00022123722,0.6946218],"study_design_scores_gemma":[0.013857067,0.0031701215,0.09168361,0.0035840548,0.0007317005,0.001313367,0.0013355504,0.29705408,0.36735278,0.11042963,0.099965945,0.009522083],"about_ca_topic_score_codex":0.000029292209,"about_ca_topic_score_gemma":0.0000017959508,"teacher_disagreement_score":0.6850997,"about_ca_system_score_codex":0.0002512697,"about_ca_system_score_gemma":0.000087619024,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W4412070868","doi":"10.1145/3747347","title":"Understanding Open Source Contributor Profiles in Popular Machine Learning Libraries","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Open source; Data science; Artificial intelligence; World Wide Web; Machine learning; Programming language; Software","score_opus":0.13514193957706988,"score_gpt":0.3225430056727442,"score_spread":0.1874010660956743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412070868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031458028,0.0002656582,0.99385995,0.0014294295,0.0004019157,0.00030242364,0.0000075776284,0.000562289,0.000024934188],"genre_scores_gemma":[0.1527194,0.000033258035,0.8461681,0.00026591006,0.000012072604,0.00008895495,0.0000075378352,0.000021018182,0.0006837453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984962,0.00031216437,0.00031823656,0.00044380804,0.000097667114,0.0003319679],"domain_scores_gemma":[0.9968011,0.0025569545,0.00005722317,0.00048485733,0.00003993849,0.000059938146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010695844,0.00019843034,0.00036179472,0.00059657096,0.00029257595,0.00026357587,0.00092407886,0.00015610347,0.000011819531],"category_scores_gemma":[0.0023340643,0.00020894247,0.000044824563,0.001114533,0.00005220625,0.0005289691,0.00014422227,0.0006077259,0.0000026905761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017016815,0.00029387494,0.030156195,0.00031200823,0.00043950233,0.00005896714,0.005660041,0.31190678,0.001191651,0.4666538,0.00021229488,0.18294472],"study_design_scores_gemma":[0.016849684,0.0019638895,0.03194728,0.002771257,0.00039618966,0.0004904387,0.004233154,0.41680598,0.02985497,0.21855216,0.2704826,0.005652408],"about_ca_topic_score_codex":0.00012245367,"about_ca_topic_score_gemma":0.000022045464,"teacher_disagreement_score":0.2702703,"about_ca_system_score_codex":0.00011347663,"about_ca_system_score_gemma":0.00008471634,"threshold_uncertainty_score":0.8520426},"labels":[],"label_agreement":null},{"id":"W4412565297","doi":"10.1145/3749839","title":"Tracing Optimization for Performance Modeling and Regression Detection","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Tracing; Programming language","score_opus":0.04749648754092181,"score_gpt":0.30007565846496576,"score_spread":0.2525791709240439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412565297","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10102803,0.000248995,0.8974561,0.00009847959,0.00068020786,0.00018124511,0.000001149711,0.0003041612,0.0000016414956],"genre_scores_gemma":[0.43398994,0.00013951205,0.56574446,0.000029352943,0.000013061255,0.00005688347,6.1734175e-7,0.000005586646,0.000020557354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991773,0.00006140231,0.00020324088,0.00032636078,0.000056677927,0.00017503159],"domain_scores_gemma":[0.9987339,0.0008195282,0.000030431065,0.00030986193,0.000064067855,0.000042243057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006796232,0.00013224653,0.00019185648,0.00023193323,0.0002641683,0.00003339436,0.0001440187,0.0001447548,7.6011906e-7],"category_scores_gemma":[0.00043518413,0.000116333766,0.00004029972,0.00022834686,0.000017762673,0.0002609594,0.000013126203,0.0001606066,2.3824e-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":[0.000021212918,0.000007722651,0.000060276714,0.00018537886,0.000012999503,1.06649004e-7,0.00016147165,0.6601424,0.00015646803,0.00003882971,6.379916e-7,0.33921245],"study_design_scores_gemma":[0.00034149736,0.00009888493,0.00020457424,0.00013616325,0.000019586485,0.000017671955,0.000021973945,0.9928372,0.005926697,0.00019666682,0.000084428255,0.00011468672],"about_ca_topic_score_codex":0.000007253585,"about_ca_topic_score_gemma":0.0000012368761,"teacher_disagreement_score":0.33909777,"about_ca_system_score_codex":0.00003158414,"about_ca_system_score_gemma":0.000021658281,"threshold_uncertainty_score":0.47439533},"labels":[],"label_agreement":null},{"id":"W4412602677","doi":"10.1145/3749100","title":"<scp>AntiCopyPaster</scp> 3.0: Just-in-Time Clone Refactoring","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Code refactoring; Computer science; clone (Java method); Programming language; Software engineering; Software; Biology","score_opus":0.06483042430187017,"score_gpt":0.328490238395962,"score_spread":0.2636598140940918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412602677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11938611,0.0003833185,0.8780941,0.00014616182,0.00097018573,0.00015963588,0.0000036982715,0.00083908596,0.000017717706],"genre_scores_gemma":[0.1254881,0.00014981495,0.8726858,0.0001232954,0.000045257886,0.00008811223,0.0000018462196,0.000038996244,0.0013787503],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99795514,0.00019338164,0.00033361252,0.0006344862,0.00023745614,0.0006459297],"domain_scores_gemma":[0.9857742,0.013030355,0.0000315909,0.0009531646,0.000059800637,0.00015088645],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011829556,0.00028556638,0.0004361675,0.0010121535,0.00010746394,0.00009671191,0.0009864313,0.00024280489,0.0000067491605],"category_scores_gemma":[0.006484476,0.00030914205,0.00008598815,0.0011095107,0.000043465945,0.00024110178,0.000086165164,0.00074107916,0.00002757245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008184092,0.0007970349,0.03761145,0.0017749947,0.0009519914,0.00045819563,0.00603908,0.4621337,0.038577754,0.007921044,0.0010291979,0.4426237],"study_design_scores_gemma":[0.010909236,0.0019240765,0.4939264,0.002954019,0.00037238616,0.0008330055,0.00047221262,0.18766822,0.20909356,0.0068452475,0.08221122,0.0027904306],"about_ca_topic_score_codex":0.00003284052,"about_ca_topic_score_gemma":0.0000018830752,"teacher_disagreement_score":0.45631495,"about_ca_system_score_codex":0.00011266103,"about_ca_system_score_gemma":0.00007058733,"threshold_uncertainty_score":0.99993604},"labels":[],"label_agreement":null},{"id":"W4412827352","doi":"10.1145/3744340","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Sampling (signal processing)","score_opus":0.15140591138260573,"score_gpt":0.37414789205765875,"score_spread":0.22274198067505302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412827352","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03291576,0.00017722354,0.9661418,0.00006419398,0.0002628689,0.00009893984,0.000015115621,0.0003157514,0.000008298252],"genre_scores_gemma":[0.2164716,0.000011572768,0.78327924,0.000068539994,0.000007960021,0.000015734713,7.632264e-7,0.0000096429685,0.00013494505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990005,0.00008548054,0.00022643154,0.0003460532,0.00007786077,0.00026365876],"domain_scores_gemma":[0.99720407,0.0021026356,0.00005116201,0.0005341039,0.000055100485,0.000052952026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005439415,0.00015019988,0.0002635001,0.00026233593,0.00009780046,0.000014656631,0.00036667736,0.00012553533,0.0000027553879],"category_scores_gemma":[0.0011216593,0.0001581727,0.00005849676,0.00030601435,0.000018336603,0.00014343875,0.000037242105,0.00032490672,6.214561e-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":[0.000010007355,0.000054328215,0.00006551527,0.00010828818,0.000057178353,0.0000027904355,0.0017191701,0.69722533,0.018988831,0.0014234842,5.2303847e-7,0.28034455],"study_design_scores_gemma":[0.00040159153,0.000031731204,0.00034878482,0.00006318833,0.00002333869,0.000008115766,0.00010628258,0.97154516,0.026869953,0.0003805174,0.00007592082,0.0001453897],"about_ca_topic_score_codex":0.00004494567,"about_ca_topic_score_gemma":0.000007977263,"teacher_disagreement_score":0.28019917,"about_ca_system_score_codex":0.000031942167,"about_ca_system_score_gemma":0.00004757191,"threshold_uncertainty_score":0.6450095},"labels":[],"label_agreement":null},{"id":"W4413279387","doi":"10.1145/3760775","title":"VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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 Manitoba","funders":"","keywords":"Computer science; Vulnerability (computing); Computer security","score_opus":0.12021106659626543,"score_gpt":0.33913627368043525,"score_spread":0.21892520708416982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413279387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0635108,0.00012345925,0.93404883,0.00044042876,0.0006732606,0.00019716921,0.0000037525865,0.0009981161,0.00000418713],"genre_scores_gemma":[0.26926768,0.00002254842,0.7302457,0.00010516235,0.000015520067,0.00025088465,0.0000022458441,0.00001866359,0.00007160889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984088,0.00020592875,0.00022442888,0.00056546426,0.00020872727,0.00038668554],"domain_scores_gemma":[0.99204904,0.006833907,0.00002663584,0.00088202016,0.00009035169,0.000118033844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009579399,0.0002332708,0.0002813189,0.0005243623,0.00017201235,0.00006936452,0.00050213793,0.000109860775,0.0000110064175],"category_scores_gemma":[0.0019872969,0.0002216527,0.000060189668,0.0008040666,0.000055646626,0.00028959056,0.000025157506,0.00048134688,0.0000041082185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012759621,0.00014385095,0.0032769714,0.00033890232,0.00018703738,0.000033599445,0.0006369083,0.64769965,0.001554757,0.0020922753,0.00003691308,0.3438715],"study_design_scores_gemma":[0.014993907,0.004009091,0.20725241,0.0018257152,0.0004950448,0.0004145694,0.00051947497,0.33614114,0.40427333,0.0059230663,0.019421464,0.004730781],"about_ca_topic_score_codex":0.000040016632,"about_ca_topic_score_gemma":0.0000053614503,"teacher_disagreement_score":0.40271857,"about_ca_system_score_codex":0.0001117821,"about_ca_system_score_gemma":0.00009640307,"threshold_uncertainty_score":0.9038735},"labels":[],"label_agreement":null},{"id":"W4413333491","doi":"10.1145/3762183","title":"Leveraging Reviewer Experience in Code Review Comment Generation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Waterloo","funders":"","keywords":"Computer science; Code (set theory); Software engineering; Programming language","score_opus":0.17826252847388172,"score_gpt":0.3910005918240723,"score_spread":0.2127380633501906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413333491","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030630925,0.012450685,0.980718,0.002283858,0.0009067735,0.00025968853,0.0000014367539,0.00031338827,0.000003048635],"genre_scores_gemma":[0.027733328,0.01184263,0.95708436,0.0028259563,0.000029974224,0.00033288437,0.0000027376334,0.00001781212,0.00013031796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985025,0.00024257335,0.0003351868,0.0004539522,0.00015624377,0.0003095526],"domain_scores_gemma":[0.9962691,0.002773524,0.000029274617,0.00076824316,0.00008386713,0.000075992655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013861643,0.00018119082,0.0003599304,0.0003638355,0.00008204177,0.000034980047,0.0005331731,0.00008949796,0.000011739346],"category_scores_gemma":[0.006015719,0.00018481519,0.000057801055,0.0007525973,0.00002525011,0.00017023267,0.000042634296,0.00040868836,0.0000042943047],"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":[0.000014330844,0.00016958192,0.0019999149,0.0027379508,0.000111531495,0.000044956647,0.0019666285,0.073249534,0.0017701142,0.0029108766,0.0024011077,0.91262347],"study_design_scores_gemma":[0.0052205776,0.00081704627,0.043808293,0.02325037,0.00024649384,0.00035890983,0.00020776618,0.25542626,0.04854366,0.002009373,0.61606747,0.0040437873],"about_ca_topic_score_codex":0.000028144575,"about_ca_topic_score_gemma":0.00000363162,"teacher_disagreement_score":0.9085797,"about_ca_system_score_codex":0.000105242165,"about_ca_system_score_gemma":0.00005024392,"threshold_uncertainty_score":0.7536544},"labels":[],"label_agreement":null},{"id":"W4413592694","doi":"10.1145/3746060","title":"Cost and Benefit of Tracing Features with Embedded Annotations","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Royal Swedish Academy of Sciences","keywords":"Computer science; Tracing; Software engineering; Programming language","score_opus":0.06218509040712472,"score_gpt":0.32871344618109655,"score_spread":0.2665283557739718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413592694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010944183,0.0006543786,0.987255,0.00018451165,0.00029551564,0.00016103758,0.00000865197,0.0004902701,0.0000064474193],"genre_scores_gemma":[0.04697271,0.00012776545,0.9526155,0.000064449174,0.000007628775,0.000055703415,0.0000012137182,0.000014639755,0.00014038247],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990085,0.00008273214,0.00020821918,0.00036909553,0.000088200126,0.00024326344],"domain_scores_gemma":[0.9934586,0.0058538197,0.000049063354,0.00050094986,0.00007123441,0.00006630419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004607019,0.00020183105,0.00035398567,0.00039695035,0.000110096276,0.000025337768,0.00028941286,0.00012492258,0.000001246381],"category_scores_gemma":[0.0014250083,0.00018512024,0.00003981008,0.00049912924,0.000082749975,0.00019043384,0.000025440626,0.00030636415,1.9793039e-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":[0.000038716655,0.00002786102,0.00010873137,0.00016597612,0.00012153925,0.000005946521,0.0011978257,0.6544495,0.0014162114,0.010472494,0.000005361033,0.3319898],"study_design_scores_gemma":[0.012235233,0.004263716,0.20505358,0.0035684137,0.0012888755,0.0021132338,0.003278425,0.056177095,0.49831122,0.2034481,0.0044512628,0.0058108447],"about_ca_topic_score_codex":0.000010577531,"about_ca_topic_score_gemma":0.0000057260904,"teacher_disagreement_score":0.59827244,"about_ca_system_score_codex":0.000022343598,"about_ca_system_score_gemma":0.00002777737,"threshold_uncertainty_score":0.7548984},"labels":[],"label_agreement":null},{"id":"W4414091836","doi":"10.1145/3766890","title":"FairFLRep: Fairness-Aware Fault Localization and Repair of Deep Neural Networks","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep neural networks; Artificial neural network; Quality (philosophy); Baseline (sea); Fault (geology); Pattern recognition (psychology)","score_opus":0.02717373461444464,"score_gpt":0.29582057895049046,"score_spread":0.2686468443360458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414091836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023451888,0.00036326158,0.99586916,0.00013624033,0.0006920145,0.00009668047,0.0000011664843,0.0004922987,0.00000400273],"genre_scores_gemma":[0.483974,0.000042186948,0.51584005,0.00008148124,0.000015655794,0.000011812393,0.0000015509561,0.000009393769,0.000023852092],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988841,0.00023169508,0.00024142065,0.00036181507,0.000081892686,0.00019907071],"domain_scores_gemma":[0.99759007,0.0018006181,0.000055901248,0.00043477194,0.00006454182,0.000054130458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048645915,0.0001596656,0.0002783388,0.00023777466,0.00013404849,0.00002066229,0.00026539003,0.00016455879,0.0000037291827],"category_scores_gemma":[0.00089236174,0.0001637647,0.0000616811,0.00043565515,0.00006235035,0.0001670045,0.000046506062,0.00032888836,1.8001072e-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":[0.000012808177,0.000010939645,0.00075895886,0.00006982659,0.00003832712,0.0000029413522,0.00020819827,0.84583366,0.000015353004,0.0020369003,0.0000026370774,0.15100943],"study_design_scores_gemma":[0.00028079556,0.00006809851,0.0018418985,0.000032862834,0.000035926543,0.00002081327,0.000049575163,0.9966025,0.00015350635,0.00054522563,0.00023962649,0.00012921012],"about_ca_topic_score_codex":0.0000337214,"about_ca_topic_score_gemma":0.000006674154,"teacher_disagreement_score":0.48162884,"about_ca_system_score_codex":0.000020757116,"about_ca_system_score_gemma":0.000013732196,"threshold_uncertainty_score":0.667813},"labels":[],"label_agreement":null},{"id":"W4414115194","doi":"10.1145/3765735","title":"Applications and Challenges of Fairness APIs in Machine Learning Software","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; York University; University of Calgary","funders":"","keywords":"Troubleshooting; Software; Ask price; Software development; Software peer review; Face (sociological concept)","score_opus":0.10476442243813705,"score_gpt":0.3753859940296217,"score_spread":0.27062157159148464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414115194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010658373,0.005217862,0.9802245,0.0033339774,0.00014386015,0.00017297023,0.0000083114355,0.00013554622,0.00010461806],"genre_scores_gemma":[0.7010233,0.02558702,0.27280334,0.00011838988,0.00003681952,0.00009381617,0.0000023327327,0.00001842906,0.00031654348],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911195,0.00028012562,0.00015887957,0.00018512706,0.00008117958,0.00018273228],"domain_scores_gemma":[0.9959613,0.0037437382,0.00003344756,0.0001302071,0.000069742746,0.000061526465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012833118,0.00009321814,0.00023509325,0.00023390268,0.00023315722,0.000015525591,0.00011873461,0.00021474621,0.0000074307627],"category_scores_gemma":[0.0031728589,0.000101965765,0.000034627898,0.00025257905,0.00016028713,0.00008098104,0.000009829106,0.0003947859,3.3092536e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003252111,0.0000987823,0.0034311365,0.00046803235,0.000099473255,0.0000020330951,0.020084811,0.004688,0.00018389859,0.08156883,0.0000028569427,0.8893396],"study_design_scores_gemma":[0.0074394243,0.0014676596,0.11909485,0.0022671723,0.00081801036,0.00003221728,0.06961321,0.0022423754,0.0057697985,0.38890386,0.39889157,0.0034598536],"about_ca_topic_score_codex":0.0009061895,"about_ca_topic_score_gemma":0.00091227115,"teacher_disagreement_score":0.88587976,"about_ca_system_score_codex":0.000027034972,"about_ca_system_score_gemma":0.000060234004,"threshold_uncertainty_score":0.4158043},"labels":[],"label_agreement":null},{"id":"W4414153585","doi":"10.1145/3767167","title":"The Havoc Paradox in Generator-Based Fuzzing—RCR Report","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Artifact (error); Scripting language; Exploit; Affect (linguistics)","score_opus":0.04416990580043428,"score_gpt":0.3086626128790792,"score_spread":0.2644927070786449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414153585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040703886,0.0005121166,0.9920315,0.0025751216,0.00048592302,0.00010837883,0.0000022556792,0.00020127375,0.0000130291155],"genre_scores_gemma":[0.04340915,0.000093534836,0.95578825,0.00021560218,0.000021478714,0.00017226252,0.0000018762266,0.000006977837,0.00029085364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990843,0.00011195709,0.00022383372,0.00030488113,0.00007113532,0.00020391385],"domain_scores_gemma":[0.9970869,0.002153463,0.0000297123,0.0006497352,0.000035888435,0.00004430578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073730253,0.00011087331,0.00013936496,0.00016094465,0.00026006522,0.00003689207,0.00037584174,0.00008422513,0.000001511616],"category_scores_gemma":[0.00043642538,0.0000937772,0.000047728576,0.0004789313,0.000043108677,0.000067830224,0.0000145343065,0.0002471501,0.0000018585621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026645814,0.00021718687,0.0012207205,0.000060205264,0.00010761761,0.0000797916,0.00028906,0.35347426,0.0017404151,0.0832514,0.00041602858,0.55911666],"study_design_scores_gemma":[0.0024526995,0.00029342293,0.058016468,0.00021192548,0.00009652975,0.00053609477,0.00014318242,0.6139586,0.016849462,0.039128106,0.26707453,0.001238972],"about_ca_topic_score_codex":0.000026770313,"about_ca_topic_score_gemma":0.000013155032,"teacher_disagreement_score":0.5578777,"about_ca_system_score_codex":0.00003599487,"about_ca_system_score_gemma":0.000083338986,"threshold_uncertainty_score":0.3824123},"labels":[],"label_agreement":null},{"id":"W4414913062","doi":"10.1145/3770084","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"","keywords":"Code generation; Second-generation programming language; Leverage (statistics); Syntax; Python (programming language); Code (set theory); Domain-specific language; Semantics (computer science); Fourth-generation programming language","score_opus":0.07723071174492212,"score_gpt":0.325472582362461,"score_spread":0.24824187061753888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414913062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010257936,0.00037414164,0.9874273,0.00022275964,0.00025680067,0.00037864092,0.00003475313,0.0010465758,0.0000010855828],"genre_scores_gemma":[0.023309663,0.00003772743,0.9761013,0.00017168521,0.000031392672,0.00024627036,0.00002116781,0.000026936254,0.000053857322],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867094,0.00019663252,0.00022019721,0.0005263264,0.000099143435,0.0002867437],"domain_scores_gemma":[0.99674326,0.0024896336,0.000037838443,0.00058945274,0.00006209009,0.00007773652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010723486,0.00023270852,0.00029121863,0.00037811795,0.0001548948,0.00007543144,0.00031329537,0.00017650833,0.0000010524726],"category_scores_gemma":[0.00017469522,0.00024063782,0.00006212498,0.0002957449,0.000039304632,0.00007715813,0.000018484732,0.0002477557,4.5676387e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006131144,0.00011527098,0.00011631436,0.00017389873,0.000077567,0.000005879566,0.00038643612,0.101236455,0.0029376682,0.017297326,0.00023004127,0.87736183],"study_design_scores_gemma":[0.0042112125,0.0021930605,0.009121181,0.0008026996,0.000113939066,0.00005189213,0.000041122737,0.37490335,0.099513814,0.0013996683,0.50551945,0.0021285852],"about_ca_topic_score_codex":0.000015559306,"about_ca_topic_score_gemma":0.000013962504,"teacher_disagreement_score":0.87523323,"about_ca_system_score_codex":0.00005034988,"about_ca_system_score_gemma":0.000029505876,"threshold_uncertainty_score":0.98129255},"labels":[],"label_agreement":null},{"id":"W4414993542","doi":"10.1145/3771283","title":"LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Ottawa","funders":"","keywords":"Anomaly detection; Inference; Anomaly (physics); Artificial neural network; Key (lock); Software; Cache; Ensemble learning","score_opus":0.07009888762071217,"score_gpt":0.3147679512299077,"score_spread":0.24466906360919552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414993542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033970915,0.00022360585,0.9622433,0.00036830833,0.0022809375,0.00019076899,0.000012206171,0.0006852269,0.000024710194],"genre_scores_gemma":[0.5689851,0.000075352706,0.4304818,0.00019420421,0.000034859524,0.000048612917,0.0000040067716,0.000013653057,0.00016240474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983242,0.00020520683,0.00029683576,0.0006941214,0.0001465505,0.00033304648],"domain_scores_gemma":[0.9962499,0.0019098994,0.000047426474,0.0016477543,0.00006122164,0.0000837839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00130527,0.00021682128,0.00031142271,0.00037097765,0.00024202316,0.00004970702,0.0007777464,0.0001995407,0.000006480035],"category_scores_gemma":[0.0008511941,0.00019477485,0.0000642382,0.0005846657,0.000045746987,0.00017707385,0.000062359475,0.00035765336,0.000014847109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008071496,0.00026810548,0.0002903202,0.00027223327,0.00015965973,0.00000965587,0.0003974254,0.29803315,0.001077382,0.0013170665,0.00010163162,0.6979927],"study_design_scores_gemma":[0.0041510123,0.002448569,0.027641596,0.00083400164,0.00036325722,0.0003692668,0.00022555415,0.7087365,0.120997384,0.002166173,0.12980117,0.0022655537],"about_ca_topic_score_codex":0.00007459145,"about_ca_topic_score_gemma":0.000012815299,"teacher_disagreement_score":0.6957271,"about_ca_system_score_codex":0.000073968244,"about_ca_system_score_gemma":0.0000633108,"threshold_uncertainty_score":0.79426885},"labels":[],"label_agreement":null},{"id":"W4415312861","doi":"10.1145/3771929","title":"Continuously Learning Bug Locations","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"Polytechnique Montréal","funders":"","keywords":"Software bug; Software regression; Software; Code (set theory); Deep learning; Forgetting; Source code; Mean reciprocal rank","score_opus":0.04947276161402145,"score_gpt":0.3231860867865974,"score_spread":0.27371332517257596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415312861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009920311,0.0003992738,0.9868856,0.0005749574,0.0007568836,0.00012485113,0.0000016604856,0.0013178596,0.00001856648],"genre_scores_gemma":[0.20650057,0.00009656909,0.7921096,0.000115975185,0.00002307594,0.000086332795,0.0000015873972,0.000019376588,0.0010469143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986951,0.0001685073,0.00020793173,0.00043055305,0.00013238641,0.0003655283],"domain_scores_gemma":[0.9915089,0.007619965,0.000023507668,0.0006583335,0.000085698506,0.00010358329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007663402,0.0001837872,0.00025242657,0.00055578206,0.00019614134,0.000069494694,0.00059323816,0.00014721099,0.00001085379],"category_scores_gemma":[0.005517759,0.00019818019,0.00006773136,0.0006876444,0.000045077275,0.00015102379,0.000042137297,0.0006335224,0.000015291731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026990085,0.0001222343,0.0055269497,0.00023639489,0.00030911918,0.000029397375,0.0009997223,0.3675894,0.0020086325,0.01336822,0.00028544138,0.6094975],"study_design_scores_gemma":[0.008429484,0.0023990197,0.2658579,0.0015291253,0.00047940214,0.0009639293,0.0006338134,0.31387228,0.081320316,0.017301012,0.30191615,0.0052975793],"about_ca_topic_score_codex":0.000027629698,"about_ca_topic_score_gemma":0.0000020964517,"teacher_disagreement_score":0.6041999,"about_ca_system_score_codex":0.000054662774,"about_ca_system_score_gemma":0.000069911046,"threshold_uncertainty_score":0.8081554},"labels":[],"label_agreement":null},{"id":"W4415330783","doi":"10.1145/3744902","title":"Do Current Language Models Support Code Intelligence for R Programming Language? RCR Report","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Analysis with R","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 British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Parsing; Code (set theory); Natural language; Matching (statistics); Replicate; Source code; Compiler","score_opus":0.09264298462753738,"score_gpt":0.38361259729604125,"score_spread":0.29096961266850385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415330783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009406991,0.00083186,0.9965807,0.00018428163,0.0007395331,0.00023361758,0.0000288499,0.00045380986,0.0000066412563],"genre_scores_gemma":[0.025879856,0.00008362344,0.97344375,0.000075695,0.000027072387,0.00017460457,0.00002425148,0.000015221212,0.00027590373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985716,0.00008985456,0.00034093976,0.0005557034,0.0001192713,0.0003226722],"domain_scores_gemma":[0.99733615,0.0014737806,0.00006217947,0.0009685029,0.0000720297,0.00008738291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011686719,0.00018823,0.00031646676,0.00036215878,0.000105837935,0.00007781742,0.0006198695,0.00009641344,0.0000063473144],"category_scores_gemma":[0.0010886177,0.00018341845,0.000117115196,0.00046525183,0.000033149074,0.00023337033,0.000041832922,0.0002642402,0.0000024719914],"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":[0.000010576654,0.00005044321,0.000022913206,0.000117836506,0.00009663852,0.000032453932,0.0014415575,0.030164601,0.0001515515,0.0030591774,0.000058602673,0.9647936],"study_design_scores_gemma":[0.002741447,0.0012474566,0.00066383433,0.0010406583,0.0015867449,0.0018319541,0.0034855832,0.6795304,0.06964248,0.020659136,0.21385872,0.0037116143],"about_ca_topic_score_codex":0.000027862203,"about_ca_topic_score_gemma":0.000014714809,"teacher_disagreement_score":0.96108204,"about_ca_system_score_codex":0.000037852897,"about_ca_system_score_gemma":0.00006896164,"threshold_uncertainty_score":0.7479587},"labels":[],"label_agreement":null},{"id":"W4415589112","doi":"10.1145/3773034","title":"Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Neural Networks and Applications","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":"Alberta Medical Association","funders":"","keywords":"Shields; Overhead (engineering); Reduction (mathematics); Software; Control (management); Reliability (semiconductor); Safety standards; Runtime system","score_opus":0.0516818758031873,"score_gpt":0.3185185259233981,"score_spread":0.2668366501202108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415589112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03431465,0.00031184047,0.963209,0.0014703202,0.00019523366,0.0002577362,0.0000031824816,0.00023516521,0.0000029012438],"genre_scores_gemma":[0.2730232,0.000034677483,0.7264389,0.00019289472,0.000019303217,0.00018979292,6.198102e-7,0.000007824611,0.000092811424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931264,0.000037667414,0.00013780185,0.00026092344,0.000040662366,0.00021030863],"domain_scores_gemma":[0.9970838,0.0025285159,0.00002392828,0.00027903123,0.000027233471,0.000057484365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023012023,0.00012000986,0.00017731453,0.00013457575,0.00020001913,0.000057808193,0.00021302438,0.00007131074,0.000001061354],"category_scores_gemma":[0.00027534144,0.0001095713,0.0000478175,0.00022081242,0.00003850189,0.000046298395,0.00001960278,0.0001368545,3.3456993e-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":[0.00001592652,0.00006262936,0.00004815214,0.00019853392,0.00007853546,0.0000017574589,0.00075653143,0.14955764,0.001906628,0.028353669,0.0000422547,0.8189778],"study_design_scores_gemma":[0.00075573917,0.00031769034,0.003033543,0.00018581325,0.0001517624,0.00010361688,0.00015977923,0.97276074,0.00992786,0.0055617867,0.0065030875,0.00053855556],"about_ca_topic_score_codex":0.000008994184,"about_ca_topic_score_gemma":0.0000012851322,"teacher_disagreement_score":0.82320315,"about_ca_system_score_codex":0.000010342572,"about_ca_system_score_gemma":0.0000134467755,"threshold_uncertainty_score":0.4468188},"labels":[],"label_agreement":null},{"id":"W4415622293","doi":"10.1145/3773285","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Topic Modeling","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; Huawei Technologies (Canada)","funders":"","keywords":"Benchmarking; Benchmark (surveying); Task (project management); Code (set theory); Program comprehension; Code generation; Source code","score_opus":0.11296114902424609,"score_gpt":0.36077962888675685,"score_spread":0.24781847986251077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415622293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02806752,0.0002606299,0.9706544,0.00016173757,0.0005139278,0.00012790864,0.000021293785,0.00018869294,0.0000038531716],"genre_scores_gemma":[0.3106455,0.000015320942,0.6891541,0.000066506174,0.000019037767,0.00003147983,0.0000039979545,0.0000063122225,0.000057783946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992033,0.00008683718,0.00019824383,0.00027113038,0.00006374789,0.00017670817],"domain_scores_gemma":[0.9984936,0.0009817585,0.000036896905,0.00040066376,0.000054373017,0.000032673146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005616354,0.00010571101,0.00020485529,0.00016746455,0.000089905436,0.000027583943,0.00023131033,0.00010536764,0.0000012836671],"category_scores_gemma":[0.00039903703,0.00010520366,0.00005975364,0.00015165495,0.000009635419,0.00017315245,0.000015041981,0.00012975997,1.4591703e-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":[0.000009298812,0.00006796757,0.000019166326,0.00018209637,0.00008224546,0.0000014802932,0.0015717418,0.73125494,0.03386635,0.02664385,0.00002992857,0.20627095],"study_design_scores_gemma":[0.00043701215,0.00003490243,0.00010998106,0.00003874813,0.00003217266,0.0000055807145,0.00006471713,0.9756721,0.021787316,0.0013733302,0.0003288623,0.00011527335],"about_ca_topic_score_codex":0.000012673805,"about_ca_topic_score_gemma":0.0000067543156,"teacher_disagreement_score":0.28257796,"about_ca_system_score_codex":0.000022047878,"about_ca_system_score_gemma":0.0000328237,"threshold_uncertainty_score":0.42900807},"labels":[],"label_agreement":null},{"id":"W4416229447","doi":"10.1145/3776739","title":"An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Face","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Documentation; License; Software; Face (sociological concept); Artificial neural network; Facial recognition system; Work (physics); Convolutional neural network","score_opus":0.06670334465444491,"score_gpt":0.3676025793805503,"score_spread":0.30089923472610536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416229447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040190294,0.0006088026,0.9581064,0.00074923324,0.000086069565,0.00006919633,0.000030672163,0.0001573082,0.000002031748],"genre_scores_gemma":[0.40368673,0.00048518303,0.59562004,0.0001433599,0.000006179949,0.0000059774457,0.00003028356,0.000009320796,0.000012922626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986666,0.00034446886,0.00021901677,0.00047676827,0.00010428423,0.00018889719],"domain_scores_gemma":[0.9970806,0.0023444728,0.00006289155,0.00039537853,0.00004093375,0.00007568564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084514957,0.00017588513,0.0003737473,0.00070792285,0.0001902966,0.00004361941,0.0002124476,0.00010504186,0.0000026564271],"category_scores_gemma":[0.00079980586,0.0001801925,0.00003655773,0.00045666008,0.000052309002,0.00024946858,0.000041143776,0.00040585385,1.3007472e-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":[0.000020575086,0.000019290348,0.00076854374,0.000042314325,0.0001924665,0.0000017839542,0.0017492323,0.8959204,0.00026176745,0.0007622337,0.0000018500059,0.100259565],"study_design_scores_gemma":[0.00030577584,0.00011791443,0.0052341456,0.000035765515,0.00023416369,0.000007943265,0.00018678395,0.9930756,0.00024664783,0.0002608703,0.00014475701,0.0001496475],"about_ca_topic_score_codex":0.000048290374,"about_ca_topic_score_gemma":0.000018136776,"teacher_disagreement_score":0.36349642,"about_ca_system_score_codex":0.000020307856,"about_ca_system_score_gemma":0.000017621236,"threshold_uncertainty_score":0.7348037},"labels":[],"label_agreement":null},{"id":"W4416767288","doi":"10.1145/3778031","title":"Understanding and Estimating the Execution Time of Quantum Circuits","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Quantum Computing Algorithms and Architecture","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":"Quantum computer; Quantum circuit; Quantum; Quantum algorithm; Qubit; Quantum information; Provisioning; Benchmark (surveying); Quantum network","score_opus":0.08260533931163938,"score_gpt":0.2945200368030502,"score_spread":0.21191469749141084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416767288","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020542618,0.00019670023,0.9781075,0.0005032309,0.00041908823,0.00006675733,0.0000017620325,0.00015775865,0.000004571682],"genre_scores_gemma":[0.34832773,0.000013903221,0.65155476,0.00006140706,0.000013179733,0.0000045277184,2.860904e-7,0.000005028523,0.000019190898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929786,0.0001247247,0.00015086637,0.00021381161,0.00006348124,0.00014928605],"domain_scores_gemma":[0.99700403,0.0026263506,0.000037455786,0.00028318944,0.000018976347,0.000029973653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061805104,0.00010372145,0.00017042691,0.00016011781,0.00018915022,0.00002768699,0.00022650592,0.00006421675,0.0000010114849],"category_scores_gemma":[0.00044032646,0.00008172932,0.000034336765,0.00027240627,0.000056660858,0.00005057524,0.000025705338,0.0002182064,3.2555337e-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":[0.000007681291,0.000030248722,0.00005816505,0.00017191691,0.00011733169,0.0000037118054,0.002380411,0.6005945,0.0024438605,0.035763174,0.000023873195,0.3584051],"study_design_scores_gemma":[0.0001584486,0.00006602894,0.0006273415,0.00010177332,0.00002050364,0.000044966666,0.00003810888,0.9859431,0.0008863896,0.011963837,0.0000615834,0.000087961955],"about_ca_topic_score_codex":0.000009581755,"about_ca_topic_score_gemma":3.2893612e-7,"teacher_disagreement_score":0.38534853,"about_ca_system_score_codex":0.000017360997,"about_ca_system_score_gemma":0.000020908954,"threshold_uncertainty_score":0.33328247},"labels":[],"label_agreement":null},{"id":"W4417339614","doi":"10.1145/3785001","title":"An Empirical Study of Self-Admitted Technical Debt in Machine Learning Software","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Technical debt; Context (archaeology); Empirical research; Code smell; Pipeline (software); Source code; Code (set theory)","score_opus":0.05521184893937985,"score_gpt":0.3650327064973448,"score_spread":0.30982085755796496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417339614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3209113,0.00014339674,0.67752224,0.00005966793,0.00019817035,0.000205637,0.0000017782884,0.0009569511,8.840943e-7],"genre_scores_gemma":[0.49376744,0.00002491866,0.50607586,0.000024482808,0.000007179229,0.00006487988,0.0000012697535,0.000017530765,0.000016428268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9977202,0.00055255595,0.00042857663,0.00063497486,0.00024105652,0.00042266533],"domain_scores_gemma":[0.9910572,0.007754007,0.000041314408,0.000924773,0.00008616643,0.000136547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014023018,0.00025861093,0.00049997866,0.0010877454,0.00010100397,0.00003434456,0.0008859845,0.00024229383,0.0000066819634],"category_scores_gemma":[0.004974175,0.00026584178,0.00006609586,0.0014421677,0.00003556886,0.0001825781,0.00007025864,0.0010710671,0.0000017231871],"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":[0.00014210147,0.002524345,0.41106555,0.00033834187,0.00028205846,0.00011385232,0.0040638912,0.42048377,0.0021746508,0.00028494527,0.000015430169,0.15851107],"study_design_scores_gemma":[0.0047896183,0.004398636,0.8521167,0.00027047587,0.00013309745,0.00018194052,0.00035507538,0.1296982,0.0051166257,0.00079560187,0.0009970212,0.0011470132],"about_ca_topic_score_codex":0.000101121725,"about_ca_topic_score_gemma":0.000043123207,"teacher_disagreement_score":0.44105116,"about_ca_system_score_codex":0.00009447359,"about_ca_system_score_gemma":0.00008820893,"threshold_uncertainty_score":0.9999794},"labels":[],"label_agreement":null},{"id":"W4417436230","doi":"10.1145/3785363","title":"Galápagos: Automated N-Version Programming with LLMs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Correctness; Redundancy (engineering); Software; Symbolic execution; Program analysis; Automatic programming; Software quality; Programming paradigm; Software testing","score_opus":0.04061881690512797,"score_gpt":0.3080365130385907,"score_spread":0.2674176961334627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417436230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003194809,0.00013278502,0.97065353,0.00029284606,0.0002955776,0.00013349271,0.000001596274,0.025284525,0.000010808771],"genre_scores_gemma":[0.06623493,0.000020825359,0.9333974,0.00016522198,0.0000078355715,0.00005978187,0.0000015333815,0.0000141553055,0.00009831004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893105,0.0001146751,0.00016211288,0.00040288205,0.000106063395,0.0002832052],"domain_scores_gemma":[0.9971249,0.0020955002,0.00003525863,0.00060525775,0.00006642104,0.00007265815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005209685,0.00018892493,0.00023534975,0.0003707302,0.00017894141,0.00006139717,0.00040864872,0.00013333945,0.000002277636],"category_scores_gemma":[0.0008958234,0.00016619886,0.00004473586,0.0006051086,0.0000458134,0.00013410911,0.00002711689,0.00028050283,0.0000027935348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006333141,0.00012491064,0.0009925452,0.00019737554,0.00016256051,0.000060159087,0.00060057704,0.015658647,0.00033229322,0.0017039017,0.00092691026,0.97917676],"study_design_scores_gemma":[0.0068789846,0.005039911,0.015817638,0.0039138175,0.00064572296,0.002460371,0.00019165706,0.8121606,0.051725823,0.0275713,0.069231145,0.0043630395],"about_ca_topic_score_codex":0.000041995703,"about_ca_topic_score_gemma":0.0000016264552,"teacher_disagreement_score":0.97481376,"about_ca_system_score_codex":0.00003768907,"about_ca_system_score_gemma":0.00005054304,"threshold_uncertainty_score":0.67773926},"labels":[],"label_agreement":null},{"id":"W7116688751","doi":"10.1145/3785472","title":"A Multi-Agent RAG Framework for Regulatory Compliance Checking of Software Requirements","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Requirements engineering; Software requirements; Requirements analysis; Software requirements specification; Requirements elicitation; Compliance (psychology); Non-functional requirement; Requirements management; Functional requirement","score_opus":0.19879113178629848,"score_gpt":0.38080256214929037,"score_spread":0.1820114303629919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116688751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006672026,0.00045912122,0.99069786,0.00010925885,0.0014582474,0.0003406367,0.000012616094,0.00024946674,7.6528914e-7],"genre_scores_gemma":[0.096185125,0.000041375373,0.9034105,0.00010199892,0.000021146605,0.00010244488,0.0000022882411,0.000013632288,0.00012150757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987595,0.00011983132,0.00036182173,0.00040128562,0.00011256011,0.0002450171],"domain_scores_gemma":[0.99717635,0.001921444,0.00011152676,0.00063539343,0.00009502204,0.000060255556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007320465,0.0001743437,0.00034216527,0.00024239958,0.0001419052,0.000020950267,0.000390703,0.00017641556,0.0000037124887],"category_scores_gemma":[0.0012674233,0.00018137763,0.00011026315,0.00027345566,0.000030143578,0.00012876384,0.000024047233,0.00018087274,0.0000011547761],"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":[0.00019766798,0.0006467225,0.0041484293,0.0042302636,0.0010300551,0.00000815828,0.0049371887,0.11877424,0.034778286,0.03428585,0.00017546651,0.7967877],"study_design_scores_gemma":[0.012865693,0.001459536,0.20017044,0.008949819,0.00068609486,0.00009889066,0.00053915166,0.49982366,0.22659382,0.025147587,0.020247795,0.0034175052],"about_ca_topic_score_codex":0.000016527589,"about_ca_topic_score_gemma":0.0000024892631,"teacher_disagreement_score":0.7933702,"about_ca_system_score_codex":0.000053106967,"about_ca_system_score_gemma":0.00003802081,"threshold_uncertainty_score":0.73963654},"labels":[],"label_agreement":null},{"id":"W7117477189","doi":"10.1145/3786771","title":"Assessing and Advancing Benchmarks for Evaluating Large Language Models in Software Engineering Tasks","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","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":"University of Ottawa","funders":"","keywords":"Popularity; Software quality assurance; Model-driven architecture; Software development; Coding (social sciences); Quality (philosophy); Software; Benchmark (surveying); Social software engineering","score_opus":0.07511031672640531,"score_gpt":0.3920066529526886,"score_spread":0.3168963362262833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117477189","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08182426,0.0012476104,0.9153393,0.00013583072,0.0005430578,0.00034067826,0.0000115670655,0.0005555677,0.0000021415985],"genre_scores_gemma":[0.21127747,0.000054838532,0.78830296,0.00007044262,0.000023022978,0.0001955321,0.000006266637,0.000033795775,0.000035688772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978436,0.00014467287,0.0003763087,0.0006984881,0.00019038073,0.0007465046],"domain_scores_gemma":[0.9854408,0.013671784,0.000043044896,0.0006220002,0.000083998886,0.00013840925],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025144198,0.00031639225,0.00045933778,0.0008716071,0.00017197487,0.00015516981,0.00046888518,0.00023641651,0.0000054193015],"category_scores_gemma":[0.01137996,0.00035534552,0.00008105001,0.00064154365,0.000024236846,0.00054502964,0.00008839968,0.0006496983,4.8203145e-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":[0.000027347205,0.00006594922,0.0013225045,0.0007732847,0.000105804735,0.000023033623,0.0018441794,0.75343764,0.0024609182,0.002097492,0.000020764337,0.23782106],"study_design_scores_gemma":[0.0020283437,0.00021430815,0.009188664,0.00074154034,0.00005829238,0.000069690344,0.00032582646,0.9809336,0.0037000917,0.0013777817,0.0006276167,0.00073421607],"about_ca_topic_score_codex":0.00003445131,"about_ca_topic_score_gemma":0.00000923111,"teacher_disagreement_score":0.23708685,"about_ca_system_score_codex":0.0001344542,"about_ca_system_score_gemma":0.0000881683,"threshold_uncertainty_score":0.99988985},"labels":[],"label_agreement":null},{"id":"W7128191878","doi":"10.1145/3745764","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Key Research and Development Program of China","keywords":"Robustness (evolution); Natural language; Coding (social sciences); Code (set theory); Natural language generation","score_opus":0.056644086971520985,"score_gpt":0.31641526681795956,"score_spread":0.2597711798464386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128191878","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017287692,0.00033793505,0.9799492,0.00094565505,0.0011818551,0.0001216403,0.0000042881675,0.00016751906,0.0000042519005],"genre_scores_gemma":[0.3331617,0.000007505887,0.66649264,0.00015288273,0.000016993441,0.000025826563,3.461287e-7,0.000004609355,0.00013747241],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925315,0.00012502713,0.00016698772,0.00022572961,0.000077218756,0.00015189643],"domain_scores_gemma":[0.99714,0.0022073728,0.000023034081,0.00055280165,0.00004264775,0.000034129756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005143621,0.000097600554,0.00016830281,0.0001741854,0.000112446214,0.0000210919,0.00047493124,0.000056974986,0.0000023244754],"category_scores_gemma":[0.00084840244,0.00007744001,0.000043043805,0.00035484319,0.00001558891,0.00006858545,0.00003322722,0.00021577526,5.473391e-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":[0.0000090129915,0.000031133604,0.000043792403,0.00004911114,0.000098019984,0.0000016263036,0.003937786,0.77922386,0.001739888,0.007589368,0.000032569675,0.20724382],"study_design_scores_gemma":[0.00079306297,0.00013066482,0.004298685,0.0001662844,0.0001239487,0.000046986766,0.00081298023,0.9805472,0.009059025,0.00079093844,0.0027830768,0.00044716895],"about_ca_topic_score_codex":0.000029414003,"about_ca_topic_score_gemma":0.000012321166,"teacher_disagreement_score":0.31587404,"about_ca_system_score_codex":0.0000217407,"about_ca_system_score_gemma":0.000029964376,"threshold_uncertainty_score":0.3157912},"labels":[],"label_agreement":null}]}