{"id":"W6949232142","doi":"10.5281/zenodo.14854239","title":"Artifact for \"Toward a Better Understanding of Probabilistic Delta Debugging\"","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artifact (error); Probabilistic logic; Pattern recognition (psychology); Delta; Statistical model","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003888238,0.0002638456,0.0003545977,0.0004183524,0.0006515658,0.0003546808,0.001124477,0.0002455859,0.05370964],"category_scores_gemma":[0.0008770117,0.0002640538,0.0001483806,0.0003468388,0.0002413404,0.00005587788,0.0008740987,0.0004059515,0.000815661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002819868,"about_ca_system_score_gemma":0.00002593691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003696245,"about_ca_topic_score_gemma":0.000001623423,"domain_scores_codex":[0.9979945,0.000102504,0.0003442457,0.0005769393,0.0004615851,0.0005201745],"domain_scores_gemma":[0.9986478,0.00008324325,0.0002098497,0.000592668,0.0003140189,0.0001524036],"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":[0.00007968619,0.0001479683,0.000001785225,0.002991269,0.0002641632,0.000008565096,0.0002283206,0.000007171734,0.004077442,0.005274499,0.9680091,0.01891002],"study_design_scores_gemma":[0.0006332399,0.00008751437,0.000002314731,0.0006470388,0.00006540579,0.00001067092,0.0002196881,0.0002332489,0.001680479,0.001534751,0.9946182,0.0002674353],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00008980989,0.0002051253,0.01024983,0.0006831351,0.00008117957,0.0006391424,0.0019505,0.001000019,0.9851013],"genre_scores_gemma":[0.1769574,0.0003095292,0.001761572,0.0002080335,0.001305771,0.000001231843,0.01298515,0.02076664,0.7857046],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1993966,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0664641324435924,"score_gpt":0.2685592242257994,"score_spread":0.202095091782207,"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."}}