{"id":"W6893735387","doi":"10.5281/zenodo.4065270","title":"Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Fredericton","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Categorization; Segmentation; Robustness (evolution); Newspaper; Embedding; Variety (cybernetics); Identification (biology); Process (computing)","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":[0.0004406548,0.0009540038,0.0004732573,0.002350604,0.0002643795,0.001051439,0.0004853159,0.0006930448,0.002568143],"category_scores_gemma":[0.001449485,0.0002557235,0.0006639678,0.001264964,0.0003153001,0.001394197,0.0006012489,0.0006783608,0.002142685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004360053,"about_ca_system_score_gemma":0.0002681045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003900951,"about_ca_topic_score_gemma":0.006036399,"domain_scores_codex":[0.9997327,0.0000454324,0.00001306941,0.0001228086,0.00004023763,0.00004564128],"domain_scores_gemma":[0.9994555,0.000208158,0.00007251961,0.0001065862,0.0001072638,0.00004992239],"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":[0.001260164,0.0004666625,0.009623763,0.0004213645,0.0002764947,0.000361051,0.0003191708,0.06412594,0.08890673,0.0009406016,0.008653564,0.8246446],"study_design_scores_gemma":[0.00003169598,0.0002704033,0.02341984,0.00005728721,0.0001629047,0.0002857668,0.0002098289,0.9263875,0.04192179,0.002734665,0.004468101,0.00005015236],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7354097,0.002244032,0.2348606,0.0005161062,0.0002920493,0.0002099613,0.004022369,0.008911832,0.01353334],"genre_scores_gemma":[0.9223642,0.0004948832,0.06674235,0.00008588446,0.0001554845,0.00005642945,0.004740114,0.0002859931,0.005074718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003900951,"threshold_uncertainty_score":0.008591354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622555442181189,"score_gpt":0.2630946295209617,"score_spread":0.2368690750991498,"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."}}