{"id":"W4393604030","doi":"10.5281/zenodo.7702887","title":"An Empirical Evaluation of Quasi-Static Executable Slices","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Executable; Computer science; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00481562,0.0002037559,0.0002650678,0.0005072323,0.001382809,0.001376561,0.003170915,0.0001441832,0.001123818],"category_scores_gemma":[0.001692609,0.0002128151,0.00006857522,0.001016484,0.0001049703,0.000451201,0.001266952,0.0006184702,0.007149132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001579881,"about_ca_system_score_gemma":0.0000238658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002592626,"about_ca_topic_score_gemma":0.000002534055,"domain_scores_codex":[0.9951936,0.002049605,0.0003874375,0.0006765612,0.001287689,0.0004050889],"domain_scores_gemma":[0.997316,0.00008406972,0.0003252874,0.00124723,0.0008488545,0.0001785758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006018729,0.0001749888,4.293479e-7,0.00009961102,0.00002867116,0.000005111218,0.0008716898,0.0004258209,0.000018139,0.00008600748,0.8164833,0.1818002],"study_design_scores_gemma":[0.0002619953,0.0004631108,0.00009749875,0.00007692497,0.00004729073,0.00002802891,0.0001986513,0.01566147,0.000007721477,0.00008518599,0.9828605,0.0002115903],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001561704,0.0003091625,0.1096268,0.001552984,0.001211855,0.002054256,0.8755855,0.005796356,0.002301421],"genre_scores_gemma":[0.002402973,0.00004600147,0.003136759,0.00007151342,0.0001566724,1.61348e-7,0.9932688,0.0007737414,0.0001433883],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1815886,"threshold_uncertainty_score":0.9999173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1060738739800595,"score_gpt":0.3606133292739469,"score_spread":0.2545394552938874,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}