{"id":"W1557952530","doi":"10.48550/arxiv.1310.1811","title":"End-to-End Text Recognition with Hybrid HMM Maxout Models","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Benchmark (surveying); Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); End-to-end principle; Character (mathematics); Word (group theory); Character recognition; Text recognition; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003112154,0.0005727515,0.0005207307,0.0007715204,0.0001970989,0.0004033351,0.002219503,0.000309465,0.0004062249],"category_scores_gemma":[0.00002499843,0.000613184,0.0002238964,0.0007308719,0.0001473849,0.001402196,0.002020726,0.0008417496,0.00128597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000327007,"about_ca_system_score_gemma":0.0002822361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000421321,"about_ca_topic_score_gemma":0.00005965406,"domain_scores_codex":[0.9967486,0.0002066461,0.0003264408,0.001860216,0.0002446301,0.0006134916],"domain_scores_gemma":[0.9968281,0.0001147814,0.000343209,0.001659656,0.0006181659,0.0004360887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004751681,0.001744982,0.001043499,0.0009778779,0.001376645,0.005102144,0.002449437,0.1062821,0.0008586782,0.3262186,0.02772185,0.525749],"study_design_scores_gemma":[0.0009647273,0.0004321674,0.0002207696,0.0006888243,0.0001814119,0.0001075596,0.00009045973,0.4282388,0.01049314,0.5545027,0.001918982,0.002160481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375464,0.00001832882,0.8465027,0.0002637939,0.0002255498,0.0009453113,0.00008266193,0.001144312,0.01327084],"genre_scores_gemma":[0.9551993,0.0001333971,0.04170421,0.0004849685,0.00008398062,0.00002422894,0.00009962838,0.00005117616,0.00221911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8176529,"threshold_uncertainty_score":0.9996319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07374208121636969,"score_gpt":0.1862878112567369,"score_spread":0.1125457300403672,"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."}}