{"id":"W4416126051","doi":"10.1007/978-981-95-3061-8_1","title":"Global Discovery: A Global Graph-RAG Approach for Query-Focused Multimodal Summarization Across Multiple PDF Papers","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Automatic summarization; Focus (optics); Field (mathematics); Process (computing); Natural language generation; Comprehension","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":[0.002334195,0.002174626,0.002470033,0.007687197,0.001627738,0.003539351,0.003472786,0.002103117,0.01449999],"category_scores_gemma":[0.006235518,0.001009001,0.001836348,0.008481462,0.0008385354,0.004933042,0.004071442,0.001919206,0.007122892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008539517,"about_ca_system_score_gemma":0.001721802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005820944,"about_ca_topic_score_gemma":0.0117723,"domain_scores_codex":[0.9980178,0.0004752479,0.0001156502,0.0006502526,0.0005879352,0.0001531163],"domain_scores_gemma":[0.9971603,0.001079442,0.0001999015,0.0007715928,0.0006450829,0.0001436401],"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":[0.0007286742,0.0002834411,0.001091886,0.0007940728,0.0003891183,0.0003572086,0.0005310407,0.02779962,0.02192836,0.01417326,0.07642177,0.8555015],"study_design_scores_gemma":[0.000139042,0.0004453134,0.002216791,0.0001319262,0.0005515936,0.0004938953,0.0008787217,0.8230491,0.02185508,0.07120478,0.07886135,0.0001723074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007244493,0.002004285,0.9629364,0.0005199484,0.0002974902,0.0003399308,0.003385512,0.01872667,0.00454523],"genre_scores_gemma":[0.1154461,0.00174432,0.8418875,0.0004804612,0.0006124423,0.0004629564,0.01500283,0.003194207,0.02116911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01449999,"threshold_uncertainty_score":0.04850733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01436133181771301,"score_gpt":0.2554453064310938,"score_spread":0.2410839746133808,"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."}}