{"id":"W65944014","doi":"10.1609/icwsm.v3i1.13980","title":"Regression-Based Summarization of Email Conversations","year":2009,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Artificial intelligence; Regression; Binary classification; Natural language processing; Machine learning; Random forest; Regression analysis; Recall; Support vector machine; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001457809,0.00006749632,0.0001055224,0.00007393879,0.00006842403,0.00004720673,0.0005781961,0.0000484168,0.00001373445],"category_scores_gemma":[0.0002264895,0.00004976837,0.00004114831,0.0001000219,0.00006583212,0.0001700307,0.00006480145,0.00008172185,7.219485e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002117279,"about_ca_system_score_gemma":0.0000937376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004674904,"about_ca_topic_score_gemma":0.000003266025,"domain_scores_codex":[0.9992026,0.000005406932,0.0001879837,0.0001432006,0.0003893237,0.00007148607],"domain_scores_gemma":[0.9991948,0.00007365106,0.0002152381,0.00005153301,0.0004423557,0.00002244366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001475406,0.00004857507,0.002402759,0.0000122891,0.000008843707,8.531447e-8,0.002432426,0.000006878901,0.01625255,0.9618138,0.0002756233,0.0167314],"study_design_scores_gemma":[0.002156771,0.0001893589,0.05064485,0.0007681844,0.00003752276,0.000002751606,0.001616921,0.5636114,0.08254855,0.2969462,0.001017705,0.0004598285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399076,0.00001556881,0.005765001,0.03869128,0.0007462705,0.0001674829,0.00001446299,0.0000506543,0.01464164],"genre_scores_gemma":[0.9976459,0.00001068585,0.001885843,0.000311235,0.00007046022,0.000002722426,0.000001782363,0.000001908725,0.00006943633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6648676,"threshold_uncertainty_score":0.2029495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03218593799524793,"score_gpt":0.2552067750714423,"score_spread":0.2230208370761944,"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."}}