{"id":"W2010792847","doi":"10.1109/icdar.2013.105","title":"A Probabilistic Model for Reconstruction of Torn Forensic Documents","year":2013,"lang":"en","type":"article","venue":"","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Probabilistic logic; Computer science; Set (abstract data type); Process (computing); Subject (documents); Data mining; Artificial intelligence; Order (exchange); Information retrieval; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.00008443971,0.00006735437,0.00009816168,0.00005975891,0.0000598142,0.00007980246,0.0001743423,0.00003656284,0.00001441513],"category_scores_gemma":[0.00003877634,0.00005471374,0.00004374938,0.0001013244,0.0000543708,0.0007708329,0.00003354655,0.00003155574,0.00001060103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001981892,"about_ca_system_score_gemma":0.00007763984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002666814,"about_ca_topic_score_gemma":0.000003721641,"domain_scores_codex":[0.9993901,0.000008489139,0.0001936282,0.0001915031,0.00008217201,0.0001341406],"domain_scores_gemma":[0.9994323,0.00002634646,0.00009344419,0.0001832678,0.0002313632,0.00003324727],"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":[0.000003463266,0.00002522594,0.000135697,0.00009771226,0.000008505027,3.601925e-8,0.0002295081,0.0007186353,0.001720812,0.0180637,0.0009783823,0.9780183],"study_design_scores_gemma":[0.0001749238,0.00002721448,0.0000349413,0.00001472284,0.000003555186,0.0000216035,0.00001826461,0.8277476,0.004309934,0.1675769,0.000009441208,0.00006083553],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05546697,0.00001464818,0.9414718,0.0001685216,0.000324423,0.000280441,5.406452e-7,0.0000805182,0.002192151],"genre_scores_gemma":[0.5490291,8.454045e-7,0.4498144,0.00002651621,0.00001642448,0.00005267242,5.719778e-7,0.000002998046,0.001056497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9779575,"threshold_uncertainty_score":0.2231162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0151041566781653,"score_gpt":0.2344864607945041,"score_spread":0.2193823041163388,"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."}}