{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":3,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"be78dae0aa91","filters":{"venue":"Automation of Software Test"}},"results":[{"id":"W2170038720","doi":"10.5555/2663608.2663630","title":"A methodology for energy performance testing of smartphone applications","year":2012,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Green IT and Sustainability","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Energy consumption; Process (computing); Embedded system; Battery (electricity); Flow chart; Energy (signal processing); Reliability engineering; Identification (biology); Power (physics); Operating system; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04031257151996493,"gpt":0.2602263216726672,"spread":0.2199137501527023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003156841,0.00006870419,0.0001506011,0.00006594428,0.00003285701,0.000001922474,0.00007416998,0.00005471205,0.00001318739],"category_scores_gemma":[0.0007919186,0.00007148601,0.00003293369,0.0002073509,0.00003936928,0.0001301506,0.0000136842,0.0000297304,0.000002269813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000313251,"about_ca_system_score_gemma":0.00001637046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002028831,"about_ca_topic_score_gemma":0.000002172948,"domain_scores_codex":[0.9994575,0.00001430858,0.0002580491,0.00005943931,0.00006107454,0.00014964],"domain_scores_gemma":[0.9982379,0.001303573,0.00007919118,0.0001588595,0.0001881723,0.00003229261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000609288,0.0001607547,0.5490819,0.00206265,0.00003691148,3.803139e-8,0.0007237419,0.005194894,0.0108507,0.002021687,0.0005888265,0.4292718],"study_design_scores_gemma":[0.0005432472,0.000176154,0.8193558,0.00005602601,0.0000608523,0.00000789247,0.0001375657,0.08045392,0.08909161,0.003045097,0.006774356,0.0002974673],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3227081,0.0001555045,0.6763619,0.00001199351,0.00005576978,0.0001833632,0.00001784047,0.0002986753,0.0002067801],"genre_scores_gemma":[0.78585,0.000002737651,0.2139216,0.000006285307,0.00003479876,0.0001366254,0.00001443112,0.000009867839,0.00002356075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4631419,"threshold_uncertainty_score":0.2915115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070655751","doi":"10.5555/2819261.2819271","title":"Adaptive random testing by static partitioning","year":2015,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Random testing; Computer science; Overhead (engineering); Point (geometry); Algorithm; Test case; Parallel computing; Distributed computing; Theoretical computer science; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04815471699593189,"gpt":0.2663096841822027,"spread":0.2181549671862708,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006571158,0.0001428267,0.0002113369,0.0001130021,0.00009994061,0.00008868914,0.0004260014,0.00005520944,0.000004786984],"category_scores_gemma":[0.01100282,0.0001411397,0.00003614672,0.0005713544,0.00005607488,0.0005828453,0.0001192391,0.00009659076,0.00004547042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006522544,"about_ca_system_score_gemma":0.000131584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008276571,"about_ca_topic_score_gemma":0.000001301773,"domain_scores_codex":[0.9986767,0.00007297983,0.0003835663,0.0002643166,0.0003874543,0.0002150042],"domain_scores_gemma":[0.9958892,0.002790833,0.0003196289,0.0003801144,0.0004993175,0.0001208701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002978658,0.0006950147,0.1723029,0.0001732543,0.00006564439,0.00003301466,0.005092131,0.00397935,0.0007130522,0.003261535,0.484228,0.3294263],"study_design_scores_gemma":[0.002573427,0.001196422,0.01006824,0.0007063831,0.00003430478,0.00008410301,0.00005891475,0.7818929,0.005848248,0.1960849,0.0007038122,0.0007483219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006728416,0.00008558531,0.979495,0.0001827216,0.00009604895,0.0001708046,0.00001499493,0.01283192,0.0003944944],"genre_scores_gemma":[0.4947983,5.633654e-7,0.5050218,0.00009594282,0.00001361853,0.00002496083,0.000008416875,0.000008259076,0.00002815844],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7779135,"threshold_uncertainty_score":0.9973279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155803905","doi":"10.5555/2663608.2663627","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2012,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Graphical user interface testing; Test (biology); Code coverage; Manual testing; Software engineering; Test harness; Programming language; Reliability engineering; Software; Software development; User interface; Engineering; Software construction; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02530140677214751,"gpt":0.2744781825957093,"spread":0.2491767758235618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005097098,0.0002469934,0.0003122175,0.0001802799,0.0002003184,0.0001226153,0.0006689989,0.0001332105,0.0000792377],"category_scores_gemma":[0.01945576,0.0002512479,0.00008757023,0.000593097,0.0000902402,0.0009848125,0.0002547714,0.0001625617,0.000182539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000076181,"about_ca_system_score_gemma":0.00007952058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009794144,"about_ca_topic_score_gemma":0.00001797662,"domain_scores_codex":[0.9981877,0.0000653782,0.0005478497,0.0003702813,0.0004012309,0.0004275854],"domain_scores_gemma":[0.9885282,0.009738054,0.0004309326,0.0008525564,0.0002782403,0.0001720026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001392828,0.0003432801,0.9159905,0.00003911203,0.0000121815,0.000009207142,0.0007060122,0.00000572774,0.0005812125,0.0002140782,0.02220058,0.05989666],"study_design_scores_gemma":[0.0004588318,0.0003843787,0.9590498,0.0005348371,0.00004288073,0.0001672919,0.00002239102,0.01256697,0.01088926,0.01373396,0.001429803,0.0007195591],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3622459,0.0007243641,0.5887453,0.0004505986,0.0008362776,0.0005738725,0.000127334,0.0446465,0.001649868],"genre_scores_gemma":[0.6062533,0.000004959054,0.3933446,0.0001240726,0.000108395,0.00002376831,0.00002847751,0.00001875272,0.00009367598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2440073,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}