{"id":"W2124961859","doi":"10.1109/icpc.2007.6","title":"A Comparative Study of Three Program Exploration Tools","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Computer science; Task (project management); Variety (cybernetics); Software engineering; Software; Plan (archaeology); Human–computer interaction; Code (set theory); Programming language; Artificial intelligence; Systems engineering; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.000438796,0.00005599064,0.0001027106,0.0001018516,0.00002462526,0.00006561769,0.000401167,0.00001683458,0.000005407483],"category_scores_gemma":[0.00009331157,0.00004664573,0.00001491549,0.0005330525,0.00001431294,0.0005189669,0.0001248367,0.00006866198,0.00001946409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996349,"about_ca_system_score_gemma":0.0000197295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000303892,"about_ca_topic_score_gemma":0.0001600236,"domain_scores_codex":[0.9991842,0.00001541763,0.000150237,0.0001583928,0.0003341445,0.0001576393],"domain_scores_gemma":[0.999074,0.0004037,0.00002527458,0.0003254317,0.0001277998,0.00004374101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005726562,0.006310554,0.1440019,0.00004331445,0.0001577756,0.00005906047,0.03975289,0.003792898,0.001983691,0.03285613,0.001145077,0.7698394],"study_design_scores_gemma":[0.001290778,0.004353279,0.9096912,0.00001787575,0.000004996369,0.000004209081,0.002735392,0.06016152,0.01977525,0.001175859,0.0004794753,0.0003102314],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4578962,0.000005185359,0.5410039,0.00001563816,0.00004037903,0.000407798,5.820771e-8,0.0002047985,0.0004260275],"genre_scores_gemma":[0.9407018,1.618965e-7,0.05920137,0.000003278344,0.00001397556,0.00004156132,3.802102e-7,0.000002524889,0.00003495812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7695292,"threshold_uncertainty_score":0.1902158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1536241476508637,"score_gpt":0.3823456594317601,"score_spread":0.2287215117808964,"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."}}