{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003526167,0.00008775129,0.0001336227,0.0001446299,0.0006519782,0.0003797596,0.0004094415,0.0000483547,0.0002995026],"category_scores_gemma":[0.0003916049,0.00009644205,0.00004061543,0.0003605353,0.00005907181,0.0002833556,0.0005972502,0.0001108432,0.00006184452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000121473,"about_ca_system_score_gemma":0.000006736485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195704,"about_ca_topic_score_gemma":5.533626e-7,"domain_scores_codex":[0.9988863,0.0001750621,0.000201673,0.0003197182,0.000235077,0.0001821717],"domain_scores_gemma":[0.9990348,0.00005875873,0.00009327073,0.0002019067,0.0005211056,0.00009015985],"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":[0.00003681297,0.0002325573,0.0000116001,0.0001688567,0.00004930711,0.00001496269,0.002388564,0.000005487118,0.1131138,0.02181413,0.09111768,0.7710462],"study_design_scores_gemma":[0.002563833,0.001717329,0.001785091,0.0001772372,0.00005497238,0.0006342597,0.001712406,0.00549247,0.1932401,0.003712101,0.7882605,0.0006497565],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02926734,0.0003311299,0.9467757,0.002410815,0.0001707175,0.0007890753,0.00007632246,0.001293907,0.01888493],"genre_scores_gemma":[0.9613228,0.0001272776,0.03612392,0.0002756366,0.00007883873,2.334744e-7,0.0005609043,0.0004244965,0.001085844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9320555,"threshold_uncertainty_score":0.5014555,"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."}}