{"id":"W7104389014","doi":"10.18653/v1/2025.newsum-main.10","title":"Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scalability; Scale (ratio); Key (lock); Context (archaeology); Process (computing); Feature (linguistics)","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":[0.002811634,0.001912604,0.001452868,0.001328182,0.0008587721,0.002576536,0.00422783,0.001551665,0.01095098],"category_scores_gemma":[0.007625626,0.000947322,0.001700319,0.001116521,0.0009670988,0.002845853,0.003009588,0.002317325,0.003191338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001579363,"about_ca_system_score_gemma":0.002901248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01241778,"about_ca_topic_score_gemma":0.0159695,"domain_scores_codex":[0.9984908,0.0004644544,0.0001031696,0.0003127554,0.0004672529,0.0001614955],"domain_scores_gemma":[0.9975231,0.00100588,0.0001994716,0.0004950831,0.0005187216,0.000257764],"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":[0.0008931526,0.0002740138,0.002261602,0.0004805178,0.0002985865,0.00073477,0.0003308009,0.6277912,0.01042394,0.0441482,0.04629899,0.2660644],"study_design_scores_gemma":[0.00004417415,0.00003034939,0.0000876492,0.000008251799,0.00001485041,0.00003441205,0.00001778765,0.9828415,0.001092084,0.01185774,0.003957821,0.00001344856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002433351,0.0002451406,0.9798563,0.0001859254,0.00007846709,0.0001425905,0.0003455965,0.01497289,0.001739761],"genre_scores_gemma":[0.1802033,0.0002514037,0.8103097,0.0002195482,0.0001208077,0.000755418,0.001907259,0.002215242,0.004017208],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01241778,"threshold_uncertainty_score":0.03663468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02569015319742484,"score_gpt":0.3419693545959577,"score_spread":0.3162792013985328,"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."}}