{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003290722,0.0001767549,0.0002061925,0.0002200329,0.0001141532,0.0001200875,0.0008947323,0.0001187097,0.00001254055],"category_scores_gemma":[0.0001773871,0.0002119568,0.0001243709,0.0005828306,0.00003828299,0.0001875067,0.001040894,0.0004906416,0.00002906089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001412301,"about_ca_system_score_gemma":0.0002096879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005916206,"about_ca_topic_score_gemma":0.00003154084,"domain_scores_codex":[0.9983217,0.000139118,0.0001588424,0.0009972616,0.0001288264,0.0002543257],"domain_scores_gemma":[0.9987639,0.0003430963,0.0001170162,0.0005349152,0.0001288198,0.0001122403],"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":[0.00002244749,0.00005576642,0.001333046,0.00004400394,0.0000123445,0.00002719495,0.0006178538,0.8138245,0.00002046529,0.1833676,0.0001207544,0.0005540297],"study_design_scores_gemma":[0.0005022947,0.0000407709,0.001591186,0.00003060175,0.000007211093,6.44557e-7,0.0001040133,0.9696038,0.00009907484,0.02747018,0.0003411871,0.0002090409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05666317,0.000009784152,0.9403349,0.001809694,0.0003224576,0.0003845802,0.0000333181,0.00013176,0.0003103184],"genre_scores_gemma":[0.9658308,0.00001234753,0.03349908,0.00006859891,0.0001200483,0.000003770477,0.00009361884,0.0000119851,0.0003597378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9091676,"threshold_uncertainty_score":0.8643346,"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."}}