{"id":"W4403539812","doi":"10.1016/j.eswa.2024.125557","title":"VGTS: Visually Guided Text Spotting for novel categories in historical manuscripts","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Spotting; Computer science; Natural language processing; Artificial intelligence; Information retrieval","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":[0.0003690601,0.0001952256,0.0002482138,0.0003087059,0.0001615548,0.0003870025,0.0005991523,0.00009928198,0.000002956875],"category_scores_gemma":[0.00002759743,0.000166576,0.00005927842,0.0007966405,0.00003309899,0.0004593487,0.00007644675,0.0001295494,0.0000482695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005990335,"about_ca_system_score_gemma":0.0001641927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005047831,"about_ca_topic_score_gemma":0.00004778232,"domain_scores_codex":[0.9982907,0.00002935963,0.0004916086,0.0006244396,0.0002523889,0.0003115456],"domain_scores_gemma":[0.9988979,0.0001885605,0.00008829749,0.0005411538,0.0001858872,0.00009823227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001187335,0.0003650426,0.0001423083,0.0005192234,0.00006211289,0.00002055205,0.003863615,0.00003357799,0.01786268,0.8463309,0.08732682,0.04346128],"study_design_scores_gemma":[0.0004102432,0.000122432,0.00007600847,0.0003849327,0.000008763463,0.0001884114,0.0002969802,0.03487466,0.003967326,0.00321956,0.9559339,0.0005168191],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001288441,0.002201352,0.9909753,0.001639618,0.0002899439,0.001757396,0.000009883372,0.001100137,0.001897582],"genre_scores_gemma":[0.6391744,0.00007527958,0.325319,0.0004115252,0.0007133602,0.03083963,0.00004761353,0.00008516143,0.003334047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.868607,"threshold_uncertainty_score":0.6792771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03840895304255738,"score_gpt":0.301956647548362,"score_spread":0.2635476945058046,"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."}}