{"id":"W2574762171","doi":"10.63317/3yjtmzi2qxqk","title":"WikiCoref: An English Coreference-annotated Corpus of Wikipedia Articles","year":2016,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Coreference; Computer science; Annotation; Natural language processing; Information retrieval; Artificial intelligence; Resource (disambiguation); Resolution (logic); Scheme (mathematics); World Wide Web","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":[0.0002164745,0.0001336846,0.0001721081,0.0001150024,0.00003854437,0.00006940281,0.001058953,0.0000642572,0.00005896381],"category_scores_gemma":[0.0001922167,0.0000771012,0.00003593721,0.0003889134,0.0001161954,0.001087021,0.0002153691,0.00007603878,0.00001486938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000245078,"about_ca_system_score_gemma":0.00006362273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005193785,"about_ca_topic_score_gemma":0.00002560228,"domain_scores_codex":[0.9988102,0.00005346986,0.0002651211,0.0003408102,0.000274814,0.0002555989],"domain_scores_gemma":[0.9985956,0.0001101307,0.000133085,0.0006343977,0.0004135784,0.0001132416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002753247,0.0001495629,0.005022315,0.00001859783,0.00001377335,0.00001919834,0.001631719,4.466937e-7,0.1802844,0.288798,0.001391535,0.522643],"study_design_scores_gemma":[0.0005435796,0.0004213457,0.002330143,0.0001017785,0.000008575543,0.0000130656,0.00005046334,0.002152613,0.8839726,0.1092345,0.0007786709,0.0003926815],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4565344,0.0003290182,0.5388879,0.0003304784,0.0002733835,0.0001521374,0.000006959295,0.001895101,0.001590665],"genre_scores_gemma":[0.7707008,0.00001276876,0.2288746,0.0001145637,0.00004003613,0.000005754615,0.000001081707,0.000007361894,0.0002431188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7036882,"threshold_uncertainty_score":0.3144096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01968518263512315,"score_gpt":0.2557407684198562,"score_spread":0.236055585784733,"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."}}