{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01695139,0.0003889216,0.0007213091,0.004256514,0.005533787,0.01197904,0.002681165,0.004377055,0.005082173],"category_scores_gemma":[0.04346655,0.0007906586,0.001066344,0.01386645,0.005680906,0.01989711,0.008771506,0.003017423,0.001281861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003778028,"about_ca_system_score_gemma":0.002777464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02909924,"about_ca_topic_score_gemma":0.02399805,"domain_scores_codex":[0.9862489,0.005855802,0.001611382,0.002161281,0.003310755,0.0008118377],"domain_scores_gemma":[0.958781,0.02349154,0.001292116,0.01095804,0.004476201,0.001001133],"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":[0.0009596592,0.0005787218,0.02564336,0.0008065327,0.0001578203,0.01065812,0.03728218,0.01244611,0.005948505,0.7430713,0.03803319,0.1244145],"study_design_scores_gemma":[0.0003251028,0.0001582647,0.02552249,0.0009144992,0.000169526,0.006519088,0.03023067,0.04678189,0.01798855,0.1769612,0.6941639,0.000264833],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.595886,0.002229734,0.1295101,0.02188759,0.0004292216,0.001379504,0.01474733,0.001662748,0.2322678],"genre_scores_gemma":[0.8050153,0.001121809,0.1493493,0.002407999,0.0002014811,0.0009484243,0.02040987,0.0009032399,0.01964262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.988021,"threshold_uncertainty_score":0.08964854,"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."}}