{"id":"W3170992784","doi":"10.48550/arxiv.2106.09373","title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"Innovationsfonden; Villum Fonden","keywords":"Path (computing); Computer science; Representation (politics); Artificial intelligence; ENCODE; Machine learning; Feature learning; Unsupervised 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008023095,0.0002628784,0.000248524,0.0001973332,0.0001010414,0.00009420255,0.0002395625,0.0001764206,0.00003894153],"category_scores_gemma":[0.00002048469,0.0003039226,0.0001085737,0.0004409666,0.00004427506,0.0002407611,0.0002635617,0.0006865328,0.0000094423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001747915,"about_ca_system_score_gemma":0.00003204263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001288782,"about_ca_topic_score_gemma":0.00005079218,"domain_scores_codex":[0.9989303,0.00007171046,0.0001447634,0.0005499865,0.0000811783,0.0002220957],"domain_scores_gemma":[0.9993169,0.00003658322,0.00007637932,0.0003773547,0.000105795,0.00008702704],"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":[0.00001025159,0.00003021758,0.003662088,0.0001298484,0.0001751477,0.0001303002,0.0003462412,0.9924635,0.00005758834,0.001620792,0.0003576576,0.001016378],"study_design_scores_gemma":[0.000497875,0.0000396886,0.002352862,0.0003319177,0.000167774,0.000003025927,0.003078685,0.991883,0.0003460626,0.0003054815,0.000515948,0.000477617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4388452,0.00003599716,0.5513247,0.000007450367,0.0001923544,0.000235953,0.000004286139,0.003648716,0.005705301],"genre_scores_gemma":[0.99633,0.0008891489,0.002318638,0.00001496426,0.00005284674,0.000004277048,0.0001195474,0.00004272547,0.000227816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5574848,"threshold_uncertainty_score":0.9999413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04621553180203722,"score_gpt":0.1826511330023704,"score_spread":0.1364356012003332,"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."}}