{"id":"W4394973187","doi":"10.48550/arxiv.2404.11793","title":"Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Automatic summarization; Argument (complex analysis); Key (lock); Metric (unit); Point (geometry); Computer science; Process management; Business; Mathematics; Operations management; Information retrieval; Engineering; Computer security; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001616014,0.000316177,0.0003926312,0.001376084,0.0001440081,0.0003901341,0.0005742472,0.0002028087,0.00001116805],"category_scores_gemma":[0.0001571779,0.0003866136,0.00008342266,0.00186624,0.00003785211,0.001100092,0.001550487,0.0005019035,0.000006982663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001325619,"about_ca_system_score_gemma":0.000269501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001424928,"about_ca_topic_score_gemma":0.0003290925,"domain_scores_codex":[0.9971927,0.0003913437,0.0004095439,0.00149303,0.0002444319,0.000268914],"domain_scores_gemma":[0.998355,0.00009593967,0.0002935094,0.0008825843,0.0002756403,0.00009734297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007392601,0.0001305112,0.002183281,0.000397342,0.0001147852,0.0001913591,0.001844617,0.8737238,0.005950432,0.08238405,0.00001042284,0.03306201],"study_design_scores_gemma":[0.00022397,0.00003818669,0.001334036,0.0002637359,0.000138462,0.00000371361,0.00005928797,0.9127424,0.003195958,0.08164502,0.000005084954,0.0003501873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4214156,0.0001588328,0.5774963,0.00003747103,0.0001857673,0.0003981777,0.000001594727,0.0002276524,0.00007853249],"genre_scores_gemma":[0.9732869,0.0002159409,0.02621495,0.00002843826,0.0001135525,0.000009202225,0.00005660761,0.00002174625,0.00005270004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5518712,"threshold_uncertainty_score":0.9998586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0549172077928813,"score_gpt":0.2416762866461128,"score_spread":0.1867590788532315,"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."}}