{"id":"W4409374936","doi":"10.21203/rs.3.rs-6411861/v1","title":"An Optimized Content Retriever from Web Articles using Large Language Models and FAISS Indexing","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Search engine indexing; Content (measure theory); Computer science; Information retrieval; Labrador Retriever; World Wide Web; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001166543,0.001623198,0.002181283,0.004908192,0.001040898,0.002645652,0.001832781,0.001376413,0.01273905],"category_scores_gemma":[0.004188258,0.0007238914,0.001695225,0.003686203,0.0003649919,0.003248607,0.001520776,0.0009451646,0.01606415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009686527,"about_ca_system_score_gemma":0.001977592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007834755,"about_ca_topic_score_gemma":0.01318407,"domain_scores_codex":[0.9989966,0.0001616732,0.0001110643,0.0002699807,0.0003258183,0.0001348158],"domain_scores_gemma":[0.998156,0.0007557328,0.00008755043,0.0003550269,0.0005337464,0.0001118641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001381721,0.0003617526,0.001437988,0.0004161864,0.0002543987,0.0002764531,0.0001376212,0.008568093,0.06803559,0.004036992,0.05759756,0.8574957],"study_design_scores_gemma":[0.0004219936,0.0004432315,0.00281386,0.00003126223,0.0003517058,0.0006540184,0.0002598413,0.8674105,0.0817982,0.01103534,0.03464159,0.000138464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03973111,0.001916871,0.8032958,0.0005491511,0.0004591917,0.0005345,0.007352306,0.1410763,0.005084854],"genre_scores_gemma":[0.1695635,0.0007778987,0.7854117,0.0003088624,0.0005766632,0.0004489424,0.01987455,0.004758713,0.018279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01273905,"threshold_uncertainty_score":0.04261631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1937052211221907,"score_gpt":0.4134479178797606,"score_spread":0.2197426967575699,"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."}}