{"id":"W2182677133","doi":"","title":"A Textual Entailment System using Anaphora Resolution.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Novelty; Task (project management); Textual entailment; Computer science; Natural language processing; Set (abstract data type); Test set; Artificial intelligence; Logical consequence; Test (biology); Novelty detection; Resolution (logic); Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003695773,0.00007050618,0.00009317744,0.00007455287,0.0001387369,0.0000281216,0.0003755333,0.00003534637,0.000003820034],"category_scores_gemma":[0.000008660301,0.00005972402,0.0000182232,0.0002354426,0.0001610317,0.0002260104,0.0001452261,0.00005063671,0.000001819128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001966345,"about_ca_system_score_gemma":0.00002896983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004443544,"about_ca_topic_score_gemma":8.842445e-7,"domain_scores_codex":[0.999467,0.00005243874,0.000146832,0.0001589977,0.00008059795,0.00009416431],"domain_scores_gemma":[0.9994276,0.00004120874,0.00009613964,0.0003288101,0.0000746189,0.00003164649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009492965,0.00001743445,0.00002124784,0.00003773045,0.000005758229,4.385826e-7,0.0006573265,5.157979e-7,0.001590663,0.9883158,0.000008564848,0.009334987],"study_design_scores_gemma":[0.00009334424,0.00004715013,0.00005574401,0.00003919649,0.00002127396,0.00004127429,0.002528094,0.0008809005,0.1281063,0.8675424,0.0004805994,0.000163692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004321238,0.002510774,0.9905078,0.00001458286,0.00001040788,0.0001702918,0.000003070266,0.0002192432,0.002242562],"genre_scores_gemma":[0.8193909,0.000009002176,0.1804857,0.00001540353,0.00001505951,0.00004593841,0.000001229754,0.000003239808,0.00003360254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8150696,"threshold_uncertainty_score":0.2435475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174668792673123,"score_gpt":0.2588937167682667,"score_spread":0.2414268375009544,"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."}}