{"id":"W2947823345","doi":"10.4230/oasics.ldk.2019.22","title":"Opening Digitized Newspapers Corpora: Europeana’s Full-Text Data Interoperability Case","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canarie","funders":"","keywords":"Newspaper; Interoperability; Metadata; Computer science; Cultural heritage; World Wide Web; Digitization; Digital library; Publishing; Political science; Linguistics; Media studies; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009620041,0.000600421,0.0007203755,0.0002054032,0.0007918919,0.00401604,0.001760108,0.0001243143,0.003135072],"category_scores_gemma":[0.0001592276,0.0004979403,0.0002948956,0.00007982057,0.0004467322,0.007004118,0.001416923,0.0006475874,0.001715219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283983,"about_ca_system_score_gemma":0.00009011966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000190636,"about_ca_topic_score_gemma":0.001175797,"domain_scores_codex":[0.9964556,0.00007400843,0.001510615,0.0005455043,0.000499476,0.0009148309],"domain_scores_gemma":[0.9966444,0.0002036483,0.0005223705,0.001915965,0.0004147816,0.0002988795],"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":[0.002981714,0.002138838,0.008795489,0.004554111,0.00202798,0.0009558171,0.3148434,0.0001217416,0.00008281859,0.455164,0.1404549,0.06787924],"study_design_scores_gemma":[0.003540965,0.0005574117,0.00006325813,0.0002500358,0.00008608243,0.0005435674,0.04526268,0.003654403,0.00001463198,0.0005398303,0.9445453,0.000941799],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6909631,0.00004804362,0.0001085185,0.0001595425,0.001895425,0.001370383,0.003450752,0.0002710926,0.3017331],"genre_scores_gemma":[0.9733545,0.00001396058,0.0004058341,0.001576093,0.000461737,0.00004017207,0.003012534,0.0001098491,0.02102531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8040905,"threshold_uncertainty_score":0.9997472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08152154047678656,"score_gpt":0.2635114314603703,"score_spread":0.1819898909835838,"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."}}