{"id":"W1990659078","doi":"10.1115/ipc2006-10325","title":"ILI Performance Verification and Assessment Using Statistical Hypothesis Testing","year":2006,"lang":"en","type":"article","venue":"Volume 2: Integrity Management; Poster Session; Student Paper Competition","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petroleum Technology Alliance Canada; Desjardins","funders":"","keywords":"Computer science; Statistical hypothesis testing; Certainty; Field (mathematics); Excavation; Data mining; Reliability engineering; Test (biology); Statistics; Engineering; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0002163638,0.0002729319,0.0002200866,0.0001528496,0.0002828818,0.0002189289,0.0001708904,0.000085023,0.0001056266],"category_scores_gemma":[0.00001276867,0.0002597401,0.00003513609,0.0001940434,0.00006115648,0.0004938653,0.0001441511,0.0003587622,0.00002279748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002823554,"about_ca_system_score_gemma":0.00001123837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009398774,"about_ca_topic_score_gemma":0.00001681061,"domain_scores_codex":[0.9984457,0.00005618802,0.0004048844,0.0003490527,0.0003830529,0.0003611516],"domain_scores_gemma":[0.9994338,0.00006909353,0.00007351343,0.0002650365,0.00009785406,0.0000606998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006810008,0.0004924533,0.7242256,0.002185072,0.0003480684,0.000102994,0.0006335085,0.01435755,0.06882644,0.01539918,0.002076535,0.1712845],"study_design_scores_gemma":[0.0004381252,0.00005284939,0.9610093,0.0003950058,0.00008292993,0.00001583697,0.0004527793,0.03373083,0.0003638338,0.0003873997,0.002724792,0.0003462741],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.948367,0.00005957083,0.02868772,0.0000651272,0.0007538121,0.0004109488,0.00002075031,0.0002975574,0.02133749],"genre_scores_gemma":[0.9517325,0.00006644027,0.04759783,0.00006350774,0.0002308516,0.00004305257,0.00004054299,0.00003794771,0.0001872935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2367837,"threshold_uncertainty_score":0.9999855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01801491956329122,"score_gpt":0.2533146600942416,"score_spread":0.2352997405309504,"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."}}