{"id":"W3002510907","doi":"10.48550/arxiv.2009.13579","title":"Novelty Search in Representational Space for Sample Efficient Exploration","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Novelty; Leverage (statistics); Computer science; Sample (material); Space (punctuation); Key (lock); Artificial intelligence; Sample space; Similarity (geometry); Machine learning; Theoretical computer science; Psychology; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00171091,0.0009716311,0.001529599,0.0008513672,0.0005337537,0.001450537,0.001926671,0.001683855,0.002871609],"category_scores_gemma":[0.006989924,0.000613843,0.001099733,0.001018673,0.00163414,0.00352849,0.004110154,0.002482877,0.0007001177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014328,"about_ca_system_score_gemma":0.0009448427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008909234,"about_ca_topic_score_gemma":0.001261504,"domain_scores_codex":[0.998822,0.0004785563,0.00005877026,0.0002151954,0.000320064,0.0001053113],"domain_scores_gemma":[0.9973397,0.001584846,0.000234808,0.0004861926,0.0002128339,0.000141671],"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":[0.00027534,0.0001562673,0.001036522,0.0001967796,0.0000918182,0.0001130737,0.0001938944,0.7637696,0.00518779,0.1175252,0.002809019,0.1086447],"study_design_scores_gemma":[0.00001846244,0.00006049504,0.0000546547,0.000008272403,0.000006985395,0.00002647851,0.000009670312,0.9522865,0.0006221601,0.04636802,0.0005302946,0.000007950797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01257878,0.000179506,0.9855272,0.0001958153,0.00001944994,0.00002764789,0.00004139933,0.0003598948,0.00107041],"genre_scores_gemma":[0.5025733,0.0002602492,0.4921241,0.000274976,0.00009886503,0.0003400854,0.0002984504,0.0003190248,0.003711011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002871609,"threshold_uncertainty_score":0.009606481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1633118041488373,"score_gpt":0.249236281397331,"score_spread":0.08592447724849372,"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."}}