{"id":"W4417511932","doi":"10.36227/techrxiv.176617650.04595470/v1","title":"ADAPTIVE DETECTOR-VERIFIER FRAMEWORK FOR ZERO-SHOT POLYP DETECTION IN OPEN-WORLD SETTINGS","year":2025,"lang":"","type":"preprint","venue":"","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Thresholding; Detector; Testbed; Pattern recognition (psychology); Precision and recall; Construct (python library); Domain (mathematical analysis)","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":[],"consensus_categories":[],"category_scores_codex":[0.004871311,0.001390276,0.001539453,0.0007196705,0.0005640908,0.001622738,0.003899506,0.00309317,0.003045245],"category_scores_gemma":[0.01505306,0.0008869978,0.0006254662,0.0003503823,0.001692061,0.002401801,0.002950141,0.003520873,0.001069645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571322,"about_ca_system_score_gemma":0.00291536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005095833,"about_ca_topic_score_gemma":0.005748431,"domain_scores_codex":[0.9972841,0.0008660133,0.00009156724,0.0008122344,0.0006624246,0.0002836739],"domain_scores_gemma":[0.9947276,0.003145444,0.0004714292,0.0007057455,0.0006621142,0.0002875784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001315159,0.0005901683,0.004143581,0.0003873195,0.0002003327,0.0006567786,0.000334148,0.5390305,0.03202552,0.03198826,0.009779653,0.3795486],"study_design_scores_gemma":[0.00003264077,0.000103868,0.0002009526,0.000008525051,0.00001057887,0.0001066945,0.0000128475,0.9875169,0.005073474,0.006076962,0.0008393251,0.0000172013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01228975,0.0003598735,0.9829347,0.0003390521,0.00004750364,0.0001156937,0.0001049385,0.002974781,0.0008337141],"genre_scores_gemma":[0.5043837,0.0002496443,0.4894598,0.000713975,0.000103923,0.0002803619,0.0005054501,0.0004473953,0.003855766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005095833,"threshold_uncertainty_score":0.02576226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05238447988697193,"score_gpt":0.3442506218970824,"score_spread":0.2918661420101105,"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."}}