{"id":"W4361795437","doi":"10.2139/ssrn.4394373","title":"Domain-General Vs. Domain-Specific Pre-Trained Models Binary Patch Grouping for Improved WSI Representation","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"William Osler Health System; University of Waterloo; McMaster University","funders":"","keywords":"Domain (mathematical analysis); Representation (politics); Binary number; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Arithmetic; 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":[0.0003407645,0.0006537582,0.0006543039,0.0004695715,0.0001936996,0.0006248236,0.0007470577,0.000677363,0.00555602],"category_scores_gemma":[0.0009391319,0.0002083029,0.0006299402,0.0006164502,0.0002913003,0.0008365175,0.00069743,0.001064056,0.003875282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002166862,"about_ca_system_score_gemma":0.0005942103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004015706,"about_ca_topic_score_gemma":0.006208284,"domain_scores_codex":[0.9998078,0.00003944686,0.000009676822,0.00006468363,0.00003719817,0.0000412515],"domain_scores_gemma":[0.9997178,0.0000512858,0.00001537764,0.0001183034,0.00007202748,0.00002526284],"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":[0.0008370154,0.000195291,0.001187435,0.000153322,0.00009005631,0.0001093989,0.000120352,0.1308572,0.1154202,0.006148988,0.01030038,0.7345804],"study_design_scores_gemma":[0.00002009087,0.000112683,0.001329384,0.00002027304,0.00005543284,0.00009806549,0.00006602713,0.953404,0.03697168,0.002707545,0.005196617,0.00001818787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06325854,0.0005492934,0.9273484,0.000202616,0.0001272304,0.00006796501,0.0005533912,0.003964909,0.003927681],"genre_scores_gemma":[0.6191132,0.000724776,0.3572538,0.0002577093,0.0001186162,0.0001629064,0.004490627,0.0009963299,0.01688205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00555602,"threshold_uncertainty_score":0.01858675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04305255522905972,"score_gpt":0.2867782409578404,"score_spread":0.2437256857287807,"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."}}