{"id":"W2409591106","doi":"10.18653/v1/d16-1147","title":"Key-Value Memory Networks for Directly Reading Documents","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Schema (genetic algorithms); Key (lock); Reading (process); Information retrieval; Construct (python library); Benchmark (surveying); Domain (mathematical analysis); Value (mathematics); Artificial intelligence; Machine learning; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0006500924,0.0002921442,0.0003516772,0.0001078163,0.0001120585,0.0003253198,0.00191369,0.0002932823,0.00002750594],"category_scores_gemma":[0.00005826414,0.0002278242,0.0001946137,0.00006448053,0.00002027154,0.000276315,0.002453159,0.00028376,0.00002774249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001527993,"about_ca_system_score_gemma":0.0001168758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000854611,"about_ca_topic_score_gemma":0.000005139224,"domain_scores_codex":[0.9977325,0.00006533079,0.0004065995,0.001012752,0.0002814712,0.0005013007],"domain_scores_gemma":[0.9978659,0.000216529,0.0001938507,0.001496286,0.00009794462,0.0001295141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001629666,0.00005239158,0.000175134,0.0002271874,0.000212587,0.00001596075,0.0008117564,0.06482147,0.0001915451,0.4836241,0.01739088,0.4324607],"study_design_scores_gemma":[0.0002922742,0.00001561243,0.00001938605,0.0002751823,0.00001440004,0.00000341206,0.00000414969,0.9060957,0.000687772,0.08659164,0.005585547,0.0004149176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004370364,0.0002162527,0.9497071,0.00103931,0.003987727,0.0005990456,0.000002869428,0.000460147,0.04355055],"genre_scores_gemma":[0.2121148,0.0001137995,0.7548978,0.001254016,0.002022696,0.0003961307,0.00001247723,0.0000647597,0.02912352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8412742,"threshold_uncertainty_score":0.92904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02520738783624055,"score_gpt":0.2830949033013971,"score_spread":0.2578875154651566,"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."}}