{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ANZ7I2DE6YE7LAIO3MVSXQXRSP","short_pith_number":"pith:ANZ7I2DE","canonical_record":{"source":{"id":"2006.07554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8090e9420c46794ef529222d0c3a818a11159dc3610dc098de2309c6ff265fe4","abstract_canon_sha256":"44b348b4d54f957d555efb7fe892d9376fc58a68a12f781a9cb74a9c3b6cff4e"},"schema_version":"1.0"},"canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","source":{"kind":"arxiv","id":"2006.07554","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07554","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07554v1","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07554","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"ANZ7I2DE6YE7","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"ANZ7I2DE6YE7LAIO","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"ANZ7I2DE","created_at":"2026-07-05T01:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ANZ7I2DE6YE7LAIO3MVSXQXRSP","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8090e9420c46794ef529222d0c3a818a11159dc3610dc098de2309c6ff265fe4","abstract_canon_sha256":"44b348b4d54f957d555efb7fe892d9376fc58a68a12f781a9cb74a9c3b6cff4e"},"schema_version":"1.0"},"canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:01.255937Z","signature_b64":"kE8+M14HKgfF8FXPStyi+ct02kktjZvyuPANLlhiW2opgdxWyBR10agm4RaBzkfNhvR0b1vnz7svt4DSndclAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","last_reissued_at":"2026-07-05T01:10:01.255474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:01.255474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07554","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"unUPuXYY3mch70M8CTBD5epVZQi8+Al9GUcic1+RpcnSjhsBiUfBCo5pDTjqQDSWz5cg+hTAI9EyR3UAHQQaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:30:16.311447Z"},"content_sha256":"239a628c266f8d6eb3b0764c5de4459cbdf28db4b1fbf3a99f369e93bf247de0","schema_version":"1.0","event_id":"sha256:239a628c266f8d6eb3b0764c5de4459cbdf28db4b1fbf3a99f369e93bf247de0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ANZ7I2DE6YE7LAIO3MVSXQXRSP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Krzysztof Choromanski, Yunhao Tang","submitted_at":"2020-06-13T03:54:26Z","abstract_excerpt":"Off-policy learning algorithms have been known to be sensitive to the choice of hyper-parameters. However, unlike near on-policy algorithms for which hyper-parameters could be optimized via e.g. meta-gradients, similar techniques could not be straightforwardly applied to off-policy learning. In this work, we propose a framework which entails the application of Evolutionary Strategies to online hyper-parameter tuning in off-policy learning. Our formulation draws close connections to meta-gradients and leverages the strengths of black-box optimization with relatively low-dimensional search space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07554","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07554/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++6MduLf7+vzGeyw7jXTRxWi/UOgoKLHxJFqolIEsMEMJjN/WJdmuCNCVTFjrzV2J1s1gsTSt4o1k36pjziqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:30:16.312316Z"},"content_sha256":"d5369b90402e3282fc838116f32139d2b55ad9cbfe92cff8b4f969d9b9609f86","schema_version":"1.0","event_id":"sha256:d5369b90402e3282fc838116f32139d2b55ad9cbfe92cff8b4f969d9b9609f86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/bundle.json","state_url":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T11:30:16Z","links":{"resolver":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP","bundle":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/bundle.json","state":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ANZ7I2DE6YE7LAIO3MVSXQXRSP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"44b348b4d54f957d555efb7fe892d9376fc58a68a12f781a9cb74a9c3b6cff4e","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","title_canon_sha256":"8090e9420c46794ef529222d0c3a818a11159dc3610dc098de2309c6ff265fe4"},"schema_version":"1.0","source":{"id":"2006.07554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07554","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07554v1","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07554","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"ANZ7I2DE6YE7","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"ANZ7I2DE6YE7LAIO","created_at":"2026-07-05T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"ANZ7I2DE","created_at":"2026-07-05T01:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:d5369b90402e3282fc838116f32139d2b55ad9cbfe92cff8b4f969d9b9609f86","target":"graph","created_at":"2026-07-05T01:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.07554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy learning algorithms have been known to be sensitive to the choice of hyper-parameters. However, unlike near on-policy algorithms for which hyper-parameters could be optimized via e.g. meta-gradients, similar techniques could not be straightforwardly applied to off-policy learning. In this work, we propose a framework which entails the application of Evolutionary Strategies to online hyper-parameter tuning in off-policy learning. Our formulation draws close connections to meta-gradients and leverages the strengths of black-box optimization with relatively low-dimensional search space","authors_text":"Krzysztof Choromanski, Yunhao Tang","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07554","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:239a628c266f8d6eb3b0764c5de4459cbdf28db4b1fbf3a99f369e93bf247de0","target":"record","created_at":"2026-07-05T01:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"44b348b4d54f957d555efb7fe892d9376fc58a68a12f781a9cb74a9c3b6cff4e","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","title_canon_sha256":"8090e9420c46794ef529222d0c3a818a11159dc3610dc098de2309c6ff265fe4"},"schema_version":"1.0","source":{"id":"2006.07554","kind":"arxiv","version":1}},"canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","first_computed_at":"2026-07-05T01:10:01.255474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:01.255474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kE8+M14HKgfF8FXPStyi+ct02kktjZvyuPANLlhiW2opgdxWyBR10agm4RaBzkfNhvR0b1vnz7svt4DSndclAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:01.255937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:239a628c266f8d6eb3b0764c5de4459cbdf28db4b1fbf3a99f369e93bf247de0","sha256:d5369b90402e3282fc838116f32139d2b55ad9cbfe92cff8b4f969d9b9609f86"],"state_sha256":"18a63af6d5fe410b7e0b135524bb0f19993c13ed3a3b221ab75808bb83d739bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ayraKYynTJJqMErzkOlYUzzRrWHlH9jlQmGZXeXz35BNA9DOj93Dnxg9iA3sSjGM6QFporO/niQ15ir2bnuiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:30:16.318290Z","bundle_sha256":"fd2377a3ee790d0099dd8925c7791711cbff40ca065c62296000f9f4dc5742e0"}}