{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0193952,0.00017357903,0.9764009,0.00009832773,0.0000338147,0.00008587354,0.000028455557,0.0011577493,0.0026261895],"genre_scores_gemma":[0.5412027,0.000191325,0.45482045,0.00017341142,0.000047288384,0.00025217788,0.0001850986,0.00043230978,0.0026951486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977362,0.0007534665,0.00011692604,0.00038232945,0.0007868087,0.00022428946],"domain_scores_gemma":[0.99504447,0.0023570335,0.0004141031,0.0010796341,0.0009631102,0.00014166567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013495989,0.0009823682,0.0007886994,0.0014029959,0.00060699054,0.0008880469,0.0018912606,0.00068087154,0.002397967],"category_scores_gemma":[0.007875104,0.0004589129,0.0006944378,0.0008766513,0.0010240508,0.0018591391,0.0015069944,0.00079273246,0.00079095055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005163273,0.00019278667,0.0044901706,0.00026086997,0.00009542358,0.000440102,0.00030915,0.36796066,0.04428661,0.04686249,0.003991455,0.53059393],"study_design_scores_gemma":[0.000060497816,0.00020524295,0.00087651995,0.000033172266,0.000044544904,0.00059082045,0.000055869856,0.94583225,0.019907774,0.027937995,0.004413676,0.00004159437],"about_ca_topic_score_codex":0.0016428658,"about_ca_topic_score_gemma":0.001677903,"teacher_disagreement_score":0.002397967,"about_ca_system_score_codex":0.00073226506,"about_ca_system_score_gemma":0.0009944007,"threshold_uncertainty_score":0.008021951},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025766984,0.00013262352,0.92302275,0.0001907889,0.000076033146,0.0005865486,0.00050796074,0.046796456,0.0029199556],"genre_scores_gemma":[0.24504372,0.00022473939,0.7371125,0.00026915397,0.00004010126,0.0007310818,0.002462655,0.009218436,0.004897537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99354047,0.0022279497,0.00050132355,0.0008453803,0.0024907133,0.00039424517],"domain_scores_gemma":[0.96109253,0.022258673,0.0027992786,0.00969157,0.003441748,0.00071620086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051119053,0.0015448056,0.0007074265,0.0030244945,0.00057062646,0.0027162677,0.003488221,0.0015112924,0.007121533],"category_scores_gemma":[0.041796792,0.001196742,0.0010177328,0.0010794033,0.001755952,0.003698844,0.0025485682,0.0021548818,0.0018321648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089886534,0.00089550193,0.015185007,0.0011335373,0.0002523043,0.0035729702,0.004249083,0.0440286,0.0778772,0.027242182,0.02639132,0.7982734],"study_design_scores_gemma":[0.00052403595,0.0012714561,0.01161928,0.0006538949,0.00016218187,0.004763575,0.0009358537,0.52614653,0.3172794,0.043202948,0.09299826,0.00044259918],"about_ca_topic_score_codex":0.0015799693,"about_ca_topic_score_gemma":0.0026749822,"teacher_disagreement_score":0.007121533,"about_ca_system_score_codex":0.0005798513,"about_ca_system_score_gemma":0.00093896285,"threshold_uncertainty_score":0.02703464},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060621323,0.00010730726,0.99025667,0.000085093474,0.000021638214,0.0005556939,0.00014857431,0.0017593951,0.0010035076],"genre_scores_gemma":[0.07981185,0.00014905744,0.9174393,0.000084850704,0.00002445367,0.0012184582,0.00041775955,0.0001712195,0.0006830933],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9861434,0.0048852325,0.0017193364,0.0017514131,0.004865593,0.0006351276],"domain_scores_gemma":[0.9783322,0.011224144,0.0024906304,0.0031045212,0.004508429,0.00034000538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062103556,0.00198423,0.0009005415,0.0034979144,0.00067531166,0.001977775,0.0023301255,0.0012179456,0.00225014],"category_scores_gemma":[0.029089598,0.0007439205,0.0018644168,0.001512772,0.0014895365,0.0016715173,0.0017408635,0.0016573005,0.0009081851],"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":[0.00034273966,0.001122866,0.012268497,0.0020252096,0.00034104486,0.0018158164,0.0012100111,0.19133835,0.10540431,0.10642346,0.005628134,0.57207954],"study_design_scores_gemma":[0.00016964828,0.0013337224,0.0034582166,0.0005379878,0.00020839211,0.0018521836,0.00033261863,0.7966437,0.106208764,0.058593083,0.030495403,0.00016628577],"about_ca_topic_score_codex":0.0020957184,"about_ca_topic_score_gemma":0.0015281389,"teacher_disagreement_score":0.0062103556,"about_ca_system_score_codex":0.0011803657,"about_ca_system_score_gemma":0.002676569,"threshold_uncertainty_score":0.032843888},"labels":[],"label_agreement":null}]}