{"id":"W2140217726","doi":"10.1007/s10032-005-0147-6","title":"Retrieving poorly degraded OCR documents","year":2005,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université de Montréal; Concordia University","funders":"","keywords":"Computer science; Information retrieval; Precision and recall; Query expansion; Relevance (law); Software; Vector space model; Optical character recognition; Artificial intelligence; Pattern recognition (psychology); Selection (genetic algorithm); Error detection and correction; Document retrieval; Data mining; Natural language processing; Image (mathematics); Algorithm","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000601451,0.0002126049,0.000273966,0.001020964,0.0002205644,0.001167988,0.0007086835,0.0000715174,0.0004352556],"category_scores_gemma":[0.0001138506,0.0001735172,0.0003173701,0.0007236225,0.00003925742,0.0021613,0.0001622794,0.0003471916,0.0000930623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002100702,"about_ca_system_score_gemma":0.00003341382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001278751,"about_ca_topic_score_gemma":0.000006687064,"domain_scores_codex":[0.9977096,0.0001004095,0.0005994131,0.000394975,0.0009401027,0.0002554686],"domain_scores_gemma":[0.9985753,0.0001046637,0.000421614,0.0002071429,0.0004931237,0.0001981703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006926824,0.0001521324,0.002164913,0.000002371499,0.001288109,0.00009033875,0.000153925,0.00004407565,0.000520501,0.002167451,0.001293104,0.9920538],"study_design_scores_gemma":[0.00901345,0.002205273,0.04328684,0.0009954526,0.002316491,0.001597432,0.0003199102,0.01823979,0.2697621,0.3018901,0.346726,0.003647167],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08441254,0.0005547092,0.9027068,0.008389378,0.0006252944,0.0001615058,0.00001133361,0.0001777759,0.002960652],"genre_scores_gemma":[0.9435344,0.003321337,0.04855217,0.002600612,0.0006041347,0.000008228227,0.0000339642,0.00001287357,0.001332215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884067,"threshold_uncertainty_score":0.9998689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01535983961365943,"score_gpt":0.3048018974636144,"score_spread":0.2894420578499549,"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."}}