{"id":"W3187633063","doi":"10.24963/ijcai.2021/452","title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","year":2021,"lang":"en","type":"article","venue":"","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; HEC Montréal","funders":"Innovationsfonden; Villum Fonden","keywords":"Computer science; Path (computing); Artificial intelligence; Machine learning; Representation (politics); ENCODE; Unsupervised learning; Feature learning; Ranking (information retrieval)","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":[0.00003615973,0.00007160638,0.00006978772,0.00004002284,0.00004494618,0.00003888998,0.00003497145,0.00002416855,0.00008413199],"category_scores_gemma":[0.00001778342,0.0000636765,0.00002062898,0.0002187395,0.000008585705,0.0001361817,0.00001757412,0.0001069343,0.00001193094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002219701,"about_ca_system_score_gemma":0.000005726295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001638347,"about_ca_topic_score_gemma":0.00001719773,"domain_scores_codex":[0.999575,0.0000167349,0.00008686913,0.0001232275,0.00009579035,0.0001023618],"domain_scores_gemma":[0.9998036,0.0000178495,0.0000100397,0.00009505486,0.00004264094,0.00003082314],"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":[0.00002263913,0.0001984095,0.03151844,0.0002855879,0.0004928947,0.0001600257,0.003277029,0.6617352,0.01687624,0.02576502,0.04410255,0.215566],"study_design_scores_gemma":[0.001156345,0.00009806014,0.01484151,0.0001487823,0.00006193609,0.0000244251,0.008897857,0.9094942,0.03553701,0.0002408844,0.0289543,0.00054466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08190427,0.00004199541,0.8324363,0.00006280797,0.00009064325,0.0001090735,6.855726e-7,0.007136649,0.07821758],"genre_scores_gemma":[0.9763923,0.0001398199,0.02301703,0.00004244134,0.00002810938,0.00002043119,0.00002041129,0.00001529216,0.0003241075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8944881,"threshold_uncertainty_score":0.2596653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0124466022333569,"score_gpt":0.2313686672399588,"score_spread":0.2189220650066019,"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."}}