{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001935142,0.0003965509,0.0004794265,0.001636025,0.0001628347,0.0002194555,0.0009733314,0.0007518289,0.000005369815],"category_scores_gemma":[0.0002490235,0.0003649134,0.00008501113,0.001480369,0.0002237456,0.0016361,0.0002693385,0.0008048184,0.00004215013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009940234,"about_ca_system_score_gemma":0.0003982103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006381996,"about_ca_topic_score_gemma":0.0002668595,"domain_scores_codex":[0.9979044,0.00001788559,0.000609942,0.0005746895,0.0005443816,0.0003487253],"domain_scores_gemma":[0.9977916,0.00002602844,0.0004764087,0.00128311,0.0003362694,0.00008651383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003704936,0.0002354234,0.003235567,0.003399226,0.001506566,0.0004744295,0.01832886,0.00203637,0.003739198,0.731523,0.009160424,0.2259905],"study_design_scores_gemma":[0.007173458,0.001948581,0.007811575,0.00892623,0.002137562,0.001365659,0.01160419,0.09556733,0.07823899,0.0930994,0.685215,0.006912053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8116818,0.003501145,0.1467369,0.01221152,0.00490236,0.00195586,0.0001184105,0.002855676,0.01603634],"genre_scores_gemma":[0.8180374,0.0005005218,0.1764589,0.000132283,0.0001070288,0.0001089926,0.0004079624,0.00006552244,0.004181389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6760545,"threshold_uncertainty_score":0.9998803,"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."}}