{"id":"W7066382463","doi":"","title":"Information Retrieval with Dense and Sparse Representations","year":2024,"lang":"en","type":"dissertation","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Query expansion; Relevance (law); Question answering; Pipeline (software); Language model; Matching (statistics); Bottleneck; Representation (politics); Sentence","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":[0.002208291,0.0006900155,0.001190749,0.001935219,0.0005017842,0.002372354,0.001311209,0.001181046,0.00307301],"category_scores_gemma":[0.01063474,0.0005021651,0.001276369,0.002385873,0.001149741,0.006961336,0.002554933,0.002122568,0.001889842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044154,"about_ca_system_score_gemma":0.0009468501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00200311,"about_ca_topic_score_gemma":0.002389431,"domain_scores_codex":[0.9982015,0.0007252051,0.0001351179,0.0003904355,0.0004209359,0.0001269584],"domain_scores_gemma":[0.9960205,0.002185609,0.0001924574,0.001067702,0.0004447867,0.00008892731],"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":[0.000280378,0.0002778602,0.00117756,0.0008862438,0.0001636084,0.0002354052,0.0007309953,0.1130361,0.02249778,0.2088244,0.02452991,0.6273599],"study_design_scores_gemma":[0.00005169841,0.0001184809,0.0004537239,0.00005610472,0.00005016242,0.0001737437,0.0001450991,0.7620156,0.005766232,0.2180589,0.01306801,0.00004220016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01257171,0.001485224,0.9810326,0.001023014,0.00007632292,0.0001225132,0.0003885961,0.0008374678,0.002462606],"genre_scores_gemma":[0.2887363,0.003527956,0.694398,0.0008403029,0.0005657482,0.0004330457,0.002859029,0.0002448333,0.008394822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00307301,"threshold_uncertainty_score":0.0116787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01176057460793488,"score_gpt":0.2525750935037714,"score_spread":0.2408145188958365,"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."}}