{"id":"W2133726639","doi":"10.1613/jair.2622","title":"Identification of Pleonastic It Using the Web","year":2009,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Pronoun; Identification (biology); Set (abstract data type); Simple (philosophy); Natural language; Syntactic structure","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":[0.009097558,0.00006665616,0.0001475316,0.0003560387,0.0002660265,0.0001982052,0.001257346,0.00005772898,0.00002924221],"category_scores_gemma":[0.001454783,0.00004606878,0.0001017013,0.001320991,0.0001658187,0.0004196715,0.00008398985,0.0005717639,0.00002816832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007904531,"about_ca_system_score_gemma":0.0004254645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006623141,"about_ca_topic_score_gemma":0.000003467473,"domain_scores_codex":[0.9971362,0.0004810101,0.00089789,0.0001336453,0.001064599,0.0002866297],"domain_scores_gemma":[0.9971476,0.0005750979,0.0004061556,0.0003180089,0.001459819,0.00009328481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008305708,0.0001891502,0.0000749887,0.00001527987,0.00002075715,0.00002261399,0.003028556,0.00659901,0.4778546,0.3060594,0.0002774987,0.205775],"study_design_scores_gemma":[0.00001985919,0.0002762018,0.0001727137,0.00007339523,0.000006602005,0.00006296452,0.001599865,0.4661837,0.4190722,0.1121678,0.0002901662,0.00007445157],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09420965,0.0002179795,0.89706,0.007996618,0.0003185872,0.0001021188,8.693824e-7,0.000006623259,0.00008759165],"genre_scores_gemma":[0.9961169,0.0000756367,0.003532647,0.0000544803,0.0001832663,4.360471e-7,1.163545e-7,0.000002735408,0.00003382496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9019072,"threshold_uncertainty_score":0.315305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.332724037939916,"score_gpt":0.4899785421297413,"score_spread":0.1572545041898253,"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."}}