{"id":"W4362419701","doi":"10.31237/osf.io/gz5rw","title":"Extended Abstract: CNN-based Patch Benchmarking","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Benchmark (surveying); Benchmarking; ENCODE; Task (project management); Variety (cybernetics); Image (mathematics); Object (grammar); Matching (statistics); Computer vision; Subroutine; Pattern recognition (psychology); Similarity (geometry); Range (aeronautics); Function (biology); 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":[],"consensus_categories":[],"category_scores_codex":[0.001590963,0.001341177,0.001229162,0.001080276,0.0004287223,0.001398275,0.003882034,0.001571334,0.01918952],"category_scores_gemma":[0.006087676,0.0004442694,0.0006782545,0.001478981,0.0005095719,0.002276655,0.001882085,0.001172477,0.005751419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001026653,"about_ca_system_score_gemma":0.0006547282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007291922,"about_ca_topic_score_gemma":0.007338076,"domain_scores_codex":[0.9986681,0.0002099621,0.00006940871,0.0004617249,0.0003926283,0.0001982133],"domain_scores_gemma":[0.9979533,0.0002682482,0.00009410184,0.0009477132,0.0006190847,0.0001174776],"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":[0.001360653,0.0006031084,0.009842846,0.0007498482,0.0005266177,0.0004558666,0.00007272798,0.305228,0.02433925,0.01267538,0.1397928,0.5043528],"study_design_scores_gemma":[0.00006778143,0.0001677552,0.002824357,0.00003086454,0.00004112948,0.0001929073,0.00002794246,0.9615715,0.01551978,0.008277918,0.01125621,0.00002191026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.332259,0.006462201,0.4991425,0.001824546,0.003338037,0.0007492647,0.01994955,0.05869042,0.07758451],"genre_scores_gemma":[0.7816808,0.0005335656,0.1585497,0.0006172247,0.0002773924,0.0003467845,0.03629302,0.002925045,0.01877651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01918952,"threshold_uncertainty_score":0.06419528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05589014290483632,"score_gpt":0.3102263510594575,"score_spread":0.2543362081546211,"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."}}