{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2350095,0.001626117,0.002088587,0.004109967,0.001757402,0.004784114,0.003384388,0.002053539,0.005284426],"category_scores_gemma":[0.4282179,0.0005908301,0.003164666,0.003909114,0.004278907,0.004842339,0.003316605,0.003470405,0.001390114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00232965,"about_ca_system_score_gemma":0.003693557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00228608,"about_ca_topic_score_gemma":0.001163722,"domain_scores_codex":[0.749607,0.1694276,0.01806683,0.01512782,0.04391992,0.003850861],"domain_scores_gemma":[0.2772965,0.6003953,0.03703619,0.04300911,0.04097126,0.001291605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01175718,0.002818525,0.333393,0.003717264,0.004029436,0.0007661065,0.009707236,0.0673712,0.01929679,0.08495578,0.007608681,0.4545788],"study_design_scores_gemma":[0.001362302,0.02085898,0.1779198,0.0007613381,0.001613011,0.000701509,0.00689415,0.6438579,0.07019541,0.05946562,0.01584048,0.000529601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.168243,0.0002360479,0.8152863,0.0005432258,0.0001855898,0.003006576,0.0008129379,0.001130089,0.01055626],"genre_scores_gemma":[0.7632855,0.0001056081,0.2307953,0.0001785418,0.0001004513,0.003930926,0.0007103516,0.0001579482,0.0007353612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2350095,"threshold_uncertainty_score":0.9433694,"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."}}