{"id":"W4308614207","doi":"10.48550/arxiv.2211.03229","title":"Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Argumentative; Computer science; Exploit; Representation (politics); Legal document; Artificial intelligence; Ranking (information retrieval); Graph; Domain (mathematical analysis); Information retrieval; Legal case; Data mining; Machine learning; Theoretical computer science; Mathematics; Law; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001371242,0.001502224,0.001213241,0.01023683,0.0009281597,0.002136718,0.001169929,0.00106237,0.001788009],"category_scores_gemma":[0.009144234,0.0003953115,0.000982467,0.00576483,0.0004304085,0.003074881,0.001000418,0.001559163,0.002353993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008799969,"about_ca_system_score_gemma":0.001803067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008610707,"about_ca_topic_score_gemma":0.02181046,"domain_scores_codex":[0.9987379,0.0002820643,0.0001541894,0.0003825659,0.0003337241,0.0001096537],"domain_scores_gemma":[0.9953235,0.001982674,0.0005773279,0.0006125775,0.001352859,0.0001510208],"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":[0.0003891558,0.0004302902,0.008107199,0.0008922897,0.0003243921,0.0003255989,0.0008006484,0.0237517,0.02473676,0.005841822,0.04990868,0.8844914],"study_design_scores_gemma":[0.0002503277,0.0007621095,0.01917589,0.0002817744,0.0007679316,0.0006678749,0.001451633,0.8305472,0.03784656,0.04945483,0.0586419,0.0001518757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1994666,0.008171006,0.7455675,0.001707767,0.0006855926,0.001094644,0.0170423,0.01743009,0.008834488],"genre_scores_gemma":[0.3704547,0.002213938,0.5478353,0.0003139705,0.0007839361,0.0005314054,0.06901111,0.0007704755,0.008085083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01023683,"threshold_uncertainty_score":0.01712114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010511661901489,"score_gpt":0.2823362853334743,"score_spread":0.1812851191433254,"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."}}