{"id":"W4399511717","doi":"10.48550/arxiv.2406.04508","title":"OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Institute for Computing, Information and Cognitive Systems","keywords":"occam; Occam's razor; Computer science; Inference; Artificial intelligence; Image (mathematics); Contextual image classification; Machine learning; Pattern recognition (psychology); Data mining; Mathematics; Statistics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002087023,0.0003292231,0.0002453856,0.0003294627,0.0002315907,0.0002448139,0.0005505438,0.0003140378,0.0001040447],"category_scores_gemma":[0.0004872483,0.000361272,0.0001279342,0.0007035935,0.0002977087,0.000111351,0.0009723181,0.0009627798,0.000367017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003229397,"about_ca_system_score_gemma":0.0002414162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004478453,"about_ca_topic_score_gemma":0.00002298585,"domain_scores_codex":[0.9976442,0.000159704,0.0002482396,0.001503145,0.0001467576,0.0002979949],"domain_scores_gemma":[0.9983772,0.0002706316,0.0002641318,0.0007731106,0.0001160897,0.0001988081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003446512,0.000667442,0.001061553,0.001295812,0.00009108568,0.0005920418,0.001717251,0.04697564,0.07763483,0.8001724,0.001947346,0.06749997],"study_design_scores_gemma":[0.0004166259,0.00004401649,0.006934501,0.0001937035,0.0001261172,0.00002399336,0.0004159249,0.9486718,0.01414578,0.02364497,0.00468723,0.0006953061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590302,0.0000686108,0.02917404,0.001036019,0.001443457,0.001043061,0.0001368308,0.0006829687,0.007384892],"genre_scores_gemma":[0.9965378,0.0004525407,0.00001483841,0.0002077589,0.00007489981,0.00001103813,0.00001862674,0.00003157017,0.002650933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9016962,"threshold_uncertainty_score":0.9998839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1992503980946852,"score_gpt":0.2612327154317885,"score_spread":0.0619823173371033,"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."}}