{"id":"W4391767348","doi":"","title":"Do (colored) backgrounds matter? An experiment on artificially augmented ground truth for handwritten text recognition applied to historical manuscripts","year":2024,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Colored; Ground truth; Computer science; Artificial intelligence; Natural language processing; Speech recognition; Pattern recognition (psychology); Sociology","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":[0.001389134,0.0009205012,0.0007105902,0.0004546246,0.0005006722,0.001584429,0.000879075,0.001268744,0.004616184],"category_scores_gemma":[0.009745892,0.0004094088,0.0006215894,0.0004416692,0.0006124323,0.001170866,0.0008603196,0.0009760393,0.002002493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002674731,"about_ca_system_score_gemma":0.0004177172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003424204,"about_ca_topic_score_gemma":0.002767001,"domain_scores_codex":[0.9989781,0.0002995138,0.00008446693,0.0003737417,0.0001748951,0.00008930662],"domain_scores_gemma":[0.9941323,0.003662866,0.0002637789,0.001056986,0.0006363953,0.000247559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01126638,0.001952611,0.006116255,0.002285074,0.0004290924,0.001890764,0.001553359,0.05318023,0.465436,0.001666824,0.008240335,0.4459829],"study_design_scores_gemma":[0.0005612283,0.004106555,0.03838956,0.0003277295,0.0007936227,0.001894885,0.001525737,0.5395163,0.3909898,0.002738866,0.01896877,0.0001869563],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9340249,0.0008642753,0.05608478,0.0002060275,0.0005436943,0.0002041631,0.001151025,0.002828695,0.004092465],"genre_scores_gemma":[0.9337699,0.0003467075,0.05777456,0.0001413832,0.00006550696,0.00008196308,0.002759283,0.0004210032,0.004639787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004616184,"threshold_uncertainty_score":0.01544261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03406623719093441,"score_gpt":0.2590868283488217,"score_spread":0.2250205911578873,"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."}}