{"id":"W4402670593","doi":"10.18653/v1/2024.repl4nlp-1.14","title":"QAVSA: Question Answering using Vector Symbolic Algebras","year":2024,"lang":"en","type":"article","venue":"","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Question answering; Computer science; Vector (molecular biology); Information retrieval; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001992953,0.001224654,0.001417327,0.002912403,0.001263123,0.005201965,0.003321677,0.001629536,0.03809746],"category_scores_gemma":[0.01081596,0.001006266,0.003156637,0.002624653,0.001655435,0.01088611,0.005748251,0.002810861,0.01176009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001437922,"about_ca_system_score_gemma":0.002438492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007541161,"about_ca_topic_score_gemma":0.00809481,"domain_scores_codex":[0.997183,0.0008732769,0.0002726023,0.000538009,0.0009201577,0.0002129997],"domain_scores_gemma":[0.9970176,0.001572298,0.0001204157,0.0006900815,0.0004614129,0.0001381958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007985308,0.0003343489,0.001491196,0.001368413,0.0002525419,0.0002552249,0.0008454541,0.01845209,0.007617803,0.447113,0.110211,0.4112603],"study_design_scores_gemma":[0.0001773866,0.00008924425,0.0004438276,0.0002157883,0.0001187365,0.0001792971,0.0003197225,0.2511,0.009800605,0.6307182,0.1067452,0.00009200395],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006208024,0.000744736,0.8994569,0.000920612,0.0003585537,0.0004708791,0.008594177,0.06989992,0.0133461],"genre_scores_gemma":[0.2537002,0.001645521,0.6834775,0.001101766,0.0003964187,0.00105281,0.03497466,0.007295514,0.01635555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03809746,"threshold_uncertainty_score":0.1274487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02093743097716264,"score_gpt":0.2782669546037996,"score_spread":0.2573295236266369,"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."}}