{"id":"W4313037550","doi":"10.23919/eusipco55093.2022.9909661","title":"Contrastive Learning for Time Series on Dynamic Graphs","year":2022,"lang":"en","type":"article","venue":"2022 30th European Signal Processing Conference (EUSIPCO)","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Series (stratigraphy); Graph; Artificial intelligence; Time series; Piecewise; Multivariate statistics; Anomaly detection; Machine learning; Pattern recognition (psychology); Theoretical computer science; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001157815,0.0003612083,0.0004143369,0.0002586675,0.002142365,0.000716433,0.001342201,0.00003091525,0.0007093715],"category_scores_gemma":[0.00009147331,0.000358706,0.0002043165,0.0008641648,0.0001403882,0.0007049176,0.0007617659,0.0006414087,0.00008783703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009877564,"about_ca_system_score_gemma":0.0002368438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006639207,"about_ca_topic_score_gemma":0.000002753897,"domain_scores_codex":[0.9968531,0.0004988955,0.0004881424,0.0009209815,0.0006062183,0.0006327008],"domain_scores_gemma":[0.998587,0.0001629284,0.0004699144,0.0003348673,0.0002983512,0.0001469905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004366596,0.0003135632,0.0002329436,0.0001439523,0.0002069821,0.0002143579,0.006063363,0.02875427,0.02178242,0.0302758,0.001569557,0.9100062],"study_design_scores_gemma":[0.0007998691,0.001794585,0.0006430844,0.0001114905,0.00006660083,0.00006646752,0.001183522,0.9618042,0.0002860656,0.002920411,0.02948036,0.0008433448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02710268,0.0007685657,0.9176411,0.001491102,0.0004109401,0.0009039657,0.00007497795,0.001223373,0.0503833],"genre_scores_gemma":[0.9878439,0.000009184961,0.00373181,0.0003448106,0.00006972881,0.00005818814,0.00006730756,0.00006058401,0.007814428],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9607413,"threshold_uncertainty_score":0.9998865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01455236412292159,"score_gpt":0.2247749059684716,"score_spread":0.2102225418455499,"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."}}