{"id":"W4416033588","doi":"10.18653/v1/2025.newsum-main.4","title":"Beyond Paraphrasing: Analyzing Summarization Abstractiveness and Reasoning","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Automatic summarization; Feature (linguistics); Key (lock); Term (time); Context (archaeology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008921248,0.0006334314,0.0006058935,0.004676897,0.0007517228,0.004196393,0.001120014,0.001119599,0.00369172],"category_scores_gemma":[0.09356151,0.0003200889,0.0007571955,0.00413158,0.001064998,0.007988357,0.001511337,0.001480462,0.0008990394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117241,"about_ca_system_score_gemma":0.0006947145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00357002,"about_ca_topic_score_gemma":0.003097729,"domain_scores_codex":[0.9939446,0.003468076,0.0005560142,0.0007600648,0.001097453,0.0001737671],"domain_scores_gemma":[0.9019024,0.07234467,0.01018621,0.008138025,0.006697325,0.0007313491],"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":[0.001603486,0.0005765396,0.1140833,0.004892353,0.0009997905,0.001082912,0.05729916,0.05855497,0.04951565,0.08155952,0.01724574,0.6125866],"study_design_scores_gemma":[0.0001880951,0.000979519,0.1046057,0.0009913507,0.0008998598,0.001248932,0.01591015,0.6167969,0.03587856,0.1557343,0.06642015,0.0003464788],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4996249,0.004038291,0.4638594,0.001913157,0.0001127805,0.0009267625,0.004657886,0.004041812,0.02082491],"genre_scores_gemma":[0.9061788,0.0006559412,0.08673936,0.0001747633,0.00005459026,0.0001745709,0.003919746,0.0002786921,0.00182351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008921248,"threshold_uncertainty_score":0.04718065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01349526445810739,"score_gpt":0.269114633124226,"score_spread":0.2556193686661186,"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."}}