{"id":"W4412887694","doi":"10.18653/v1/2025.findings-acl.1170","title":"Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Automatic summarization; Computer science; Information retrieval; Natural language processing","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":[0.006856274,0.001915782,0.001786547,0.005203546,0.001228631,0.002487651,0.00292886,0.002327553,0.006820062],"category_scores_gemma":[0.03542543,0.0005287414,0.001665543,0.003946136,0.0007673593,0.005151591,0.002521628,0.00251493,0.003183832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001399258,"about_ca_system_score_gemma":0.002221457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003760855,"about_ca_topic_score_gemma":0.007706728,"domain_scores_codex":[0.9942505,0.002534177,0.0005279303,0.001426095,0.001062762,0.0001985458],"domain_scores_gemma":[0.9860524,0.008779435,0.0008149323,0.001830414,0.002192439,0.0003303506],"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":[0.001430288,0.0003988971,0.003980532,0.001646596,0.0004956752,0.0002177599,0.001550436,0.03573756,0.02070277,0.01572355,0.04961898,0.868497],"study_design_scores_gemma":[0.0005848781,0.001003228,0.003138874,0.0001924346,0.0003262753,0.0002826402,0.0009242122,0.8558476,0.02312198,0.05982836,0.05455356,0.0001961219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02118102,0.003337676,0.9533262,0.0009293787,0.0003417438,0.000771156,0.00479218,0.01296631,0.002354306],"genre_scores_gemma":[0.1634474,0.0006477172,0.815015,0.0006395578,0.000540438,0.0009580074,0.01455864,0.0007679328,0.003425418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006856274,"threshold_uncertainty_score":0.03625989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249753236133718,"score_gpt":0.3038159674298836,"score_spread":0.2788406438165119,"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."}}