{"id":"W3169661950","doi":"10.48550/arxiv.2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal\\n Neighborhood Coding","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Coding (social sciences); Series (stratigraphy); Representation (politics); Computer science; Feature learning; Unsupervised learning; Artificial intelligence; Time series; Predictive coding; Theoretical computer science; Pattern recognition (psychology); Natural language processing; Machine learning; Mathematics; Statistics","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005822006,0.000776695,0.001119548,0.0003950946,0.001334246,0.001239449,0.001486386,0.0003922572,0.0004373844],"category_scores_gemma":[0.0001674266,0.0008705923,0.0007163062,0.002361361,0.0002746499,0.002441719,0.001785698,0.0008496249,0.00004993571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002726476,"about_ca_system_score_gemma":0.0005597762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002980395,"about_ca_topic_score_gemma":0.0001127551,"domain_scores_codex":[0.9950237,0.0004198904,0.000655747,0.002767146,0.0002570424,0.0008764536],"domain_scores_gemma":[0.9956693,0.0003431264,0.001071518,0.001473098,0.001100534,0.0003423959],"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":[0.0005447883,0.0001875966,0.0250074,0.0003512129,0.00108074,0.0005672553,0.002588935,0.9434999,0.0006286571,0.02115584,0.00004783483,0.004339862],"study_design_scores_gemma":[0.001319173,0.0005319578,0.00102292,0.000523762,0.0006373236,0.00003495112,0.003926367,0.9884554,0.0006821593,0.001253702,0.0005098344,0.001102455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1703524,0.0000998883,0.8257821,0.0002016672,0.0002760475,0.0006884833,0.00001331733,0.0002308539,0.002355214],"genre_scores_gemma":[0.9770998,0.0002387013,0.009940021,0.00004026504,0.0001922557,0.000004853418,0.0002662636,0.00006993757,0.01214784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8158421,"threshold_uncertainty_score":0.9999659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05763475466629842,"score_gpt":0.1854699109872249,"score_spread":0.1278351563209265,"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."}}