{"id":"W4411811241","doi":"10.1007/978-3-031-97141-9_10","title":"Context is the Key for LLM-Based Text Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Key (lock); Context (archaeology); Segmentation; Artificial intelligence; Information retrieval; Data science; Natural language processing; Computer security; History","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":[0.0006018119,0.001024731,0.0009541666,0.001986497,0.001130239,0.003431071,0.001275439,0.001355982,0.01665122],"category_scores_gemma":[0.00378249,0.0006069306,0.0006649997,0.001831764,0.0008604443,0.005076041,0.002465972,0.001954973,0.02226554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005001621,"about_ca_system_score_gemma":0.0008448182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001009564,"about_ca_topic_score_gemma":0.00224004,"domain_scores_codex":[0.9992083,0.0001385514,0.00008001963,0.0002761785,0.000216933,0.00008005612],"domain_scores_gemma":[0.998287,0.0006884462,0.0001453871,0.0003477637,0.0003912587,0.0001399892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003073411,0.00004817289,0.0005353004,0.0005698242,0.0000222433,0.0002184131,0.0002460314,0.001389465,0.1106411,0.010349,0.02525774,0.8504154],"study_design_scores_gemma":[0.00008503216,0.0004541854,0.004367973,0.0006874378,0.000211381,0.001963812,0.001072201,0.1685303,0.3410188,0.1557834,0.3256077,0.0002177709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0170222,0.007859404,0.9147504,0.002224351,0.001537642,0.000242346,0.001962844,0.02948342,0.02491747],"genre_scores_gemma":[0.2665697,0.003358009,0.6960866,0.001422867,0.001514517,0.0002476993,0.004178575,0.004587254,0.02203478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01665122,"threshold_uncertainty_score":0.05570388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515858657317936,"score_gpt":0.2768597194432386,"score_spread":0.2617011328700592,"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."}}