{"id":"W4232285071","doi":"10.1007/978-0-387-39940-9_2509","title":"Document Segmentation","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence","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":[0.000330467,0.001132494,0.0008158537,0.003049271,0.0009491665,0.002884591,0.001210783,0.0008913029,0.08891959],"category_scores_gemma":[0.0009156059,0.0005722138,0.0008204944,0.003597448,0.0004120164,0.002088044,0.00107214,0.0008394612,0.09248455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006255804,"about_ca_system_score_gemma":0.0009676933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001731155,"about_ca_topic_score_gemma":0.002605894,"domain_scores_codex":[0.9996426,0.00001981076,0.00002741165,0.0001575731,0.0001106503,0.00004190107],"domain_scores_gemma":[0.9994343,0.00009329584,0.00002769691,0.0001575101,0.0002396062,0.00004767185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001317928,0.00004947407,0.0002661236,0.0004600186,0.00002203676,0.0001259371,0.000103186,0.0006759322,0.04840949,0.0098334,0.1074624,0.8324602],"study_design_scores_gemma":[0.00002888087,0.0001074909,0.0018542,0.0001714239,0.00008807761,0.001348815,0.0001609587,0.01056603,0.1156952,0.01495772,0.8549691,0.00005210971],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01169507,0.009775627,0.5350114,0.001001996,0.001404025,0.0007906483,0.01430499,0.0468436,0.3791726],"genre_scores_gemma":[0.06264219,0.00635465,0.4969962,0.0007736558,0.0004765133,0.0003445855,0.04019287,0.005862041,0.3863573],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08891959,"threshold_uncertainty_score":0.2974657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01135273343368949,"score_gpt":0.2582528176788796,"score_spread":0.2469000842451901,"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."}}