{"id":"W2963537577","doi":"10.48550/arxiv.1606.04754","title":"A Correlational Encoder Decoder Architecture for Pivot Based Sequence\\n Generation","year":2016,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Sequence (biology); Architecture; Computer science; Soft-decision decoder; Arithmetic; Decoding methods; Computer architecture; Parallel computing; Algorithm; Mathematics; Operating system; Art; Genetics","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":[0.0005499567,0.0007676323,0.000580487,0.0004619806,0.0009210597,0.0003575534,0.002330688,0.000735266,0.0003607013],"category_scores_gemma":[0.0001113251,0.00072598,0.0005354875,0.0005571756,0.0003067213,0.001034411,0.001482868,0.0006905532,0.0001438735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004701119,"about_ca_system_score_gemma":0.001325735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000589312,"about_ca_topic_score_gemma":0.00006266432,"domain_scores_codex":[0.995263,0.0003345034,0.0005572217,0.002736158,0.0003090064,0.0008001241],"domain_scores_gemma":[0.9955804,0.0005812419,0.0007029024,0.00196012,0.0007429484,0.0004324251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002226144,0.0002264053,0.0005290463,0.0001029458,0.0001279578,0.0000951035,0.000199674,0.882693,0.001259711,0.09524679,0.003233448,0.01606331],"study_design_scores_gemma":[0.001853728,0.0001569739,0.0002059488,0.0002819538,0.0001141398,0.00001197695,0.000009618702,0.9284328,0.0003891927,0.05709483,0.01054563,0.0009032071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00749947,0.00009231087,0.9865252,0.0007522916,0.002451909,0.00118778,0.0007743171,0.0001628197,0.0005539362],"genre_scores_gemma":[0.9252867,0.00008857075,0.06864964,0.000524828,0.001002091,0.00001537106,0.0006578306,0.00005446095,0.003720575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9178755,"threshold_uncertainty_score":0.9995191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1357752411613671,"score_gpt":0.2180369733358085,"score_spread":0.08226173217444135,"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."}}