{"id":"W4407693761","doi":"10.1109/ccat64370.2024.00021","title":"Reordering of Double Pass Merging Chunking to Improve Retrieval Augmented Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Magnetic properties of thin films","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Chunking (psychology); Computer science; Artificial intelligence","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":[0.001884859,0.001276213,0.001193344,0.001164264,0.0007605557,0.001304107,0.001830719,0.00102757,0.00408642],"category_scores_gemma":[0.007380162,0.0005064216,0.0008917345,0.001027378,0.0006551738,0.002806654,0.002127469,0.001150749,0.001810602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006105449,"about_ca_system_score_gemma":0.001501989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003701136,"about_ca_topic_score_gemma":0.005237878,"domain_scores_codex":[0.9985386,0.0003980457,0.000210163,0.0003611725,0.0003328024,0.0001591798],"domain_scores_gemma":[0.9954894,0.001903421,0.0002782275,0.001148663,0.001041067,0.0001390892],"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":[0.001432516,0.0003613668,0.005398373,0.0005983531,0.0002473143,0.000859298,0.001491119,0.06017128,0.1365768,0.006369488,0.01245572,0.7740383],"study_design_scores_gemma":[0.0001663337,0.0006790693,0.003195768,0.00005043617,0.0002225282,0.0006720443,0.0005215619,0.7388059,0.225011,0.01008239,0.02048805,0.0001049436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1506582,0.001289131,0.8286388,0.0003518993,0.0003048317,0.0005592804,0.000698659,0.01429372,0.003205478],"genre_scores_gemma":[0.4091977,0.0002124266,0.5825765,0.0002159774,0.00009076559,0.0002930715,0.002179387,0.001315622,0.003918511],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00408642,"threshold_uncertainty_score":0.01367038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01605453147786917,"score_gpt":0.2516312370355729,"score_spread":0.2355767055577038,"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."}}