{"meta":{"query_hash":"be78dae0aa91","filters":{"venue":"Automation of Software Test"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"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/be78dae0aa91","api":"https://metacan.xera.ac/api/v1/cohort?venue=Automation+of+Software+Test"},"results":[{"id":"W2070655751","doi":"10.5555/2819261.2819271","title":"Adaptive random testing by static partitioning","year":2015,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Random testing; Computer science; Overhead (engineering); Point (geometry); Algorithm; Test case; Parallel computing; Distributed computing; Theoretical computer science; Mathematics; Machine learning","score_opus":0.048154716995931886,"score_gpt":0.2663096841822027,"score_spread":0.2181549671862708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070655751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006728416,0.00008558531,0.979495,0.00018272159,0.00009604895,0.00017080456,0.000014994932,0.012831916,0.00039449445],"genre_scores_gemma":[0.49479833,5.633654e-7,0.50502175,0.00009594282,0.000013618531,0.000024960833,0.000008416875,0.000008259076,0.000028158442],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867666,0.000072979834,0.00038356625,0.00026431662,0.0003874543,0.00021500417],"domain_scores_gemma":[0.99588925,0.002790833,0.00031962886,0.00038011442,0.0004993175,0.000120870136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00065711583,0.00014282674,0.00021133694,0.00011300206,0.00009994061,0.00008868914,0.00042600144,0.000055209443,0.0000047869844],"category_scores_gemma":[0.011002823,0.00014113967,0.000036146717,0.0005713544,0.00005607488,0.0005828453,0.000119239085,0.00009659076,0.000045470424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029786579,0.00069501466,0.17230287,0.00017325433,0.00006564439,0.000033014658,0.0050921305,0.0039793504,0.0007130522,0.0032615354,0.48422804,0.3294263],"study_design_scores_gemma":[0.002573427,0.0011964224,0.010068237,0.0007063831,0.00003430478,0.00008410301,0.000058914753,0.7818929,0.0058482476,0.19608495,0.0007038122,0.00074832194],"about_ca_topic_score_codex":0.000082765706,"about_ca_topic_score_gemma":0.0000013017727,"teacher_disagreement_score":0.7779135,"about_ca_system_score_codex":0.00006522544,"about_ca_system_score_gemma":0.00013158402,"threshold_uncertainty_score":0.9973279},"labels":[],"label_agreement":null},{"id":"W2155803905","doi":"10.5555/2663608.2663627","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2012,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Graphical user interface testing; Test (biology); Code coverage; Manual testing; Software engineering; Test harness; Programming language; Reliability engineering; Software; Software development; User interface; Engineering; Software construction; Machine learning","score_opus":0.02530140677214751,"score_gpt":0.27447818259570933,"score_spread":0.24917677582356182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155803905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3622459,0.00072436413,0.5887453,0.0004505986,0.0008362776,0.00057387253,0.00012733405,0.044646498,0.001649868],"genre_scores_gemma":[0.60625327,0.0000049590544,0.39334464,0.00012407255,0.000108394954,0.000023768309,0.000028477507,0.000018752724,0.00009367598],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99818766,0.0000653782,0.00054784975,0.00037028134,0.00040123094,0.0004275854],"domain_scores_gemma":[0.9885282,0.009738054,0.00043093256,0.00085255643,0.0002782403,0.00017200263],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005097098,0.00024699335,0.00031221754,0.0001802799,0.0002003184,0.00012261533,0.00066899887,0.00013321053,0.0000792377],"category_scores_gemma":[0.019455763,0.0002512479,0.00008757023,0.000593097,0.0000902402,0.0009848125,0.0002547714,0.00016256173,0.00018253902],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013928279,0.00034328015,0.91599053,0.00003911203,0.0000121814965,0.000009207142,0.00070601224,0.00000572774,0.0005812125,0.0002140782,0.022200579,0.059896663],"study_design_scores_gemma":[0.0004588318,0.0003843787,0.9590498,0.0005348371,0.00004288073,0.00016729195,0.00002239102,0.01256697,0.010889265,0.013733959,0.0014298025,0.00071955915],"about_ca_topic_score_codex":0.0009794144,"about_ca_topic_score_gemma":0.000017976625,"teacher_disagreement_score":0.24400735,"about_ca_system_score_codex":0.000076181,"about_ca_system_score_gemma":0.00007952058,"threshold_uncertainty_score":0.999994},"labels":[],"label_agreement":null},{"id":"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,"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; Energy consumption; Process (computing); Embedded system; Battery (electricity); Flow chart; Energy (signal processing); Reliability engineering; Identification (biology); Power (physics); Operating system; Engineering","score_opus":0.04031257151996493,"score_gpt":0.26022632167266724,"score_spread":0.21991375015270231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170038720","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":[0.32270813,0.00015550455,0.6763619,0.000011993513,0.00005576978,0.00018336317,0.000017840473,0.00029867532,0.00020678008],"genre_scores_gemma":[0.78585005,0.0000027376511,0.21392162,0.0000062853073,0.000034798762,0.00013662539,0.000014431117,0.000009867839,0.000023560751],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994575,0.000014308584,0.0002580491,0.000059439313,0.00006107454,0.00014963996],"domain_scores_gemma":[0.9982379,0.0013035735,0.00007919118,0.00015885946,0.00018817229,0.000032292606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031568413,0.00006870419,0.0001506011,0.00006594428,0.000032857006,0.0000019224735,0.00007416998,0.000054712047,0.000013187392],"category_scores_gemma":[0.0007919186,0.00007148601,0.000032933687,0.00020735091,0.00003936928,0.00013015061,0.000013684202,0.000029730403,0.0000022698127],"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":[0.00000609288,0.00016075475,0.5490819,0.0020626504,0.000036911482,3.803139e-8,0.00072374195,0.005194894,0.010850696,0.002021687,0.0005888265,0.4292718],"study_design_scores_gemma":[0.0005432472,0.00017615399,0.8193558,0.000056026005,0.000060852304,0.00000789247,0.00013756569,0.080453925,0.089091614,0.0030450965,0.006774356,0.00029746734],"about_ca_topic_score_codex":0.000020288306,"about_ca_topic_score_gemma":0.0000021729477,"teacher_disagreement_score":0.46314195,"about_ca_system_score_codex":0.000031325097,"about_ca_system_score_gemma":0.000016370464,"threshold_uncertainty_score":0.29151148},"labels":[],"label_agreement":null}]}