{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008352967,0.0007968572,0.000760015,0.0002642262,0.0005449179,0.001461798,0.004238715,0.0005962649,0.000003083146],"category_scores_gemma":[0.0002851486,0.0007591541,0.000355454,0.001226288,0.0005936016,0.001123581,0.001576248,0.0004652906,0.000005091004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009886031,"about_ca_system_score_gemma":0.000969956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000248874,"about_ca_topic_score_gemma":0.0006607719,"domain_scores_codex":[0.9941465,0.00005406012,0.0007615133,0.002747626,0.001104521,0.00118575],"domain_scores_gemma":[0.996924,0.000420835,0.0003622371,0.001760002,0.0003215917,0.0002113248],"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":[0.00003657658,0.00007417702,0.001968644,0.0001326265,0.00003765946,0.00001537099,0.0003558181,0.28764,0.00002358072,0.04900708,0.00003341092,0.6606751],"study_design_scores_gemma":[0.0009878497,0.00009141247,0.0005890247,0.0002090513,0.00001527355,0.00001672642,7.395536e-7,0.941978,0.00006401395,0.05473836,0.0005500366,0.0007594727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001234006,0.0002419313,0.990328,0.0003323501,0.00229851,0.001284721,0.0001668598,0.0002625285,0.004961663],"genre_scores_gemma":[0.1670758,0.00001498149,0.8309589,0.0009600198,0.0003903038,0.0000634378,0.00006056406,0.00001973498,0.0004563001],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6599156,"threshold_uncertainty_score":0.9995748,"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."}}