{"id":"W158988288","doi":"","title":"Enhancing Cross Document Coreference of Web Documents with Context Similarity and Very Large Scale Text Categorization","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Coreference; Computer science; Categorization; Context (archaeology); Task (project management); Information retrieval; Similarity (geometry); Benchmark (surveying); Set (abstract data type); Natural language processing; Feature (linguistics); Artificial intelligence; Scale (ratio); Resolution (logic)","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":[0.0002801527,0.0001481585,0.0001770433,0.0001067115,0.0001525276,0.0002780765,0.0005535983,0.0001065288,0.00009162541],"category_scores_gemma":[0.00004339599,0.0001123898,0.00002225599,0.0002961692,0.0001825541,0.001114221,0.0003105161,0.0001848369,0.00001600886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002200214,"about_ca_system_score_gemma":0.0000862552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006234519,"about_ca_topic_score_gemma":0.0007983167,"domain_scores_codex":[0.9987659,0.00002060741,0.000284565,0.0003961378,0.0002865593,0.00024619],"domain_scores_gemma":[0.9989415,0.00006510572,0.0001800809,0.0005770948,0.0001685282,0.0000676916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004081712,0.0002470932,0.1829202,0.00007493095,0.00003563249,0.000002973538,0.001290275,0.000005373603,0.1173221,0.6677957,0.0003582426,0.02990673],"study_design_scores_gemma":[0.002453376,0.0003766421,0.1047621,0.00005184595,0.00001784325,0.0000153346,0.0009148141,0.00540635,0.8593482,0.01889898,0.007161937,0.0005925844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7698662,0.00002705948,0.2271915,0.0004967243,0.0001686389,0.0002029599,0.000003702662,0.0002652755,0.001777951],"genre_scores_gemma":[0.9865613,0.00003482748,0.01244185,0.0001065296,0.000009429657,0.00002162206,0.000005124402,0.000006007548,0.0008133366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7420261,"threshold_uncertainty_score":0.4583124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009312888888777668,"score_gpt":0.2551020906265004,"score_spread":0.2457892017377227,"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."}}