{"id":"W4403443673","doi":"10.48550/arxiv.2410.08821","title":"DeepNote: Note-Centric Deep Retrieval-Augmented Generation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cognitive psychology; Computer science; Labrador Retriever; Psychology; Information retrieval; Computer vision; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000307983,0.000349642,0.0002979917,0.000453012,0.000153988,0.0003945418,0.001657821,0.0004067916,0.00004367822],"category_scores_gemma":[0.00005415199,0.0004124455,0.0002291169,0.001049752,0.00004262627,0.0003373548,0.003458971,0.0008584344,0.0003663701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006159921,"about_ca_system_score_gemma":0.0003107963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009134745,"about_ca_topic_score_gemma":0.00004339457,"domain_scores_codex":[0.9973723,0.0001409821,0.0002866555,0.00159861,0.0001836256,0.000417886],"domain_scores_gemma":[0.9978833,0.00005901433,0.0001841915,0.001511145,0.0001786808,0.0001836989],"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":[0.0000188382,0.00007512548,0.0001126978,0.0001480458,0.00009947953,0.0007104189,0.0003904926,0.8362013,0.0003871989,0.1553946,0.000369992,0.006091833],"study_design_scores_gemma":[0.0002744966,0.00002160643,0.00003550868,0.00007894052,0.00008148266,0.000005612775,0.00001229593,0.9600077,0.0006938615,0.03800514,0.0003894902,0.0003938624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1505365,0.0003978838,0.844736,0.0002080148,0.002282205,0.0003283353,0.000005158676,0.0004760422,0.001029921],"genre_scores_gemma":[0.9900567,0.0002216104,0.007638994,0.0001559442,0.0003538923,7.835216e-7,0.00002542871,0.00002644586,0.001520199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8395202,"threshold_uncertainty_score":0.9998327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07465491100708617,"score_gpt":0.1970579504967366,"score_spread":0.1224030394896504,"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."}}