{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003695444,0.0008816877,0.001198661,0.004193358,0.001312755,0.001439776,0.001690658,0.001799029,0.001931505],"category_scores_gemma":[0.01069567,0.0004013245,0.001180675,0.002652092,0.0006982111,0.003016654,0.002867757,0.00129448,0.001692809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006155581,"about_ca_system_score_gemma":0.001071506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004000789,"about_ca_topic_score_gemma":0.005170553,"domain_scores_codex":[0.9969406,0.001019585,0.000214553,0.0009635311,0.0005708183,0.0002910175],"domain_scores_gemma":[0.9955205,0.002351253,0.0002360563,0.0008556412,0.0009082067,0.0001283651],"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":[0.0004965232,0.0005080686,0.00999184,0.0001816938,0.0001934718,0.0002126275,0.0006531144,0.02540177,0.03469329,0.001871232,0.005531227,0.9202651],"study_design_scores_gemma":[0.00007133996,0.0005169964,0.01511656,0.00003268303,0.0001498072,0.0007532634,0.0005589795,0.9098098,0.05630014,0.008897886,0.007725619,0.00006701264],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3006458,0.001043377,0.6891085,0.0002504558,0.0001354157,0.0002266232,0.0003046786,0.004594643,0.003690544],"genre_scores_gemma":[0.6990564,0.0002406703,0.2930109,0.0002429806,0.0001267951,0.0001966542,0.002185487,0.0003176343,0.004622424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004193358,"threshold_uncertainty_score":0.01954359,"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."}}