{"id":"W2052918223","doi":"10.1045/march2006-choudhury","title":"Document Recognition for a Million Books","year":2006,"lang":"en","type":"article","venue":"D-Lib Magazine","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; World Wide Web; Information retrieval; Scalability; Process (computing); Digital library; Order (exchange); Database; Linguistics","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":[0.0003930145,0.0007892844,0.000620023,0.002936518,0.0007301989,0.002465823,0.0006924744,0.001063804,0.05507511],"category_scores_gemma":[0.001983046,0.000352726,0.0005419341,0.002987656,0.0002091946,0.002039299,0.0007117942,0.0009743213,0.06368405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006129558,"about_ca_system_score_gemma":0.0006089787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003685303,"about_ca_topic_score_gemma":0.005898812,"domain_scores_codex":[0.999426,0.00002853257,0.00005587738,0.0001491777,0.0002851433,0.00005538526],"domain_scores_gemma":[0.9992536,0.0001235529,0.00005033463,0.0001407388,0.0003826119,0.00004909277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001517368,0.00003336406,0.0004769175,0.000199736,0.0000264255,0.0001383286,0.00005054921,0.00064521,0.01740587,0.002156992,0.1446718,0.8340431],"study_design_scores_gemma":[0.00004758794,0.0001662973,0.005950326,0.0002344318,0.0001104729,0.002164435,0.0003575078,0.0561197,0.07519846,0.006226885,0.8533356,0.00008828447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05548001,0.03967108,0.5258646,0.01012675,0.01197347,0.0006922904,0.03478638,0.08882148,0.232584],"genre_scores_gemma":[0.1305299,0.01087891,0.4113624,0.001651832,0.001274837,0.0002846364,0.03854067,0.002470157,0.4030067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05507511,"threshold_uncertainty_score":0.1842446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01687287626591295,"score_gpt":0.2506368321123671,"score_spread":0.2337639558464542,"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."}}