{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JAQ2K43OKGG4SIIEB33LPNJWDF","short_pith_number":"pith:JAQ2K43O","canonical_record":{"source":{"id":"2408.09493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"627df2dcfc7d18d539ff9cb2134c285a0b5cdbb27e2f19c083dae4cfe29dd51c","abstract_canon_sha256":"16d135db1589a008a1b0438df02e3cff634f9d9ce66068400f3624af701ed81e"},"schema_version":"1.0"},"canonical_sha256":"4821a5736e518dc921040ef6b7b536197a35299c4090190522fed02def37bd6a","source":{"kind":"arxiv","id":"2408.09493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09493","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09493v2","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09493","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"JAQ2K43OKGG4","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"JAQ2K43OKGG4SIIE","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"JAQ2K43O","created_at":"2026-07-05T09:02:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JAQ2K43OKGG4SIIEB33LPNJWDF","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"627df2dcfc7d18d539ff9cb2134c285a0b5cdbb27e2f19c083dae4cfe29dd51c","abstract_canon_sha256":"16d135db1589a008a1b0438df02e3cff634f9d9ce66068400f3624af701ed81e"},"schema_version":"1.0"},"canonical_sha256":"4821a5736e518dc921040ef6b7b536197a35299c4090190522fed02def37bd6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:24.192311Z","signature_b64":"AMVEqy0Iqjb1ZvN/lB/71tR/UtJ4ZzysyYvMnXtVWZcPyl1fnRG+Y4XKj0LGd3EUy92WaNUyU97zH0TibtUiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4821a5736e518dc921040ef6b7b536197a35299c4090190522fed02def37bd6a","last_reissued_at":"2026-07-05T09:02:24.191871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:24.191871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09493","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnyBdPvBUMC7riGrxkDITSPhnYl7UYmWV/CCcNu7QZyjir6q6ABIEl5KgA/k5sa+a6vbFF6xLb2ObM8yTYisCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:54:34.285643Z"},"content_sha256":"428f9d6e9f34d5513366e3fdfcae60f71a3712d32f78da877adc669f37c786b8","schema_version":"1.0","event_id":"sha256:428f9d6e9f34d5513366e3fdfcae60f71a3712d32f78da877adc669f37c786b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JAQ2K43OKGG4SIIEB33LPNJWDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"So Nakashima, Tetsuya J. Kobayashi","submitted_at":"2024-08-18T14:16:55Z","abstract_excerpt":"Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can significantly be enhanced by exploiting a population of agents in various ways. Zeroth-Order Optimization (ZOO) leverages an agent population to estimate the gradient of the objective function, enabling robust policy refinement even in non-differentiable scenarios. As another application, Genetic Algorithms (GA) boosts the exploration of policy landscapes by mutationa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09493","kind":"arxiv","version":2},"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/2408.09493/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":"2026-07-05T09:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mPNEMtJfjB2uw9BjPWLkpEy9yElv9ynwFGtjauMI76yqLaKkPcrQVOF2ON9Ifphyk4Jg9f1wRRRNO1AwVp4sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:54:34.286159Z"},"content_sha256":"5e612b2b089d2f1d7d3e56dfd4bed85a8662dbb32347704152ec421cba9b4d74","schema_version":"1.0","event_id":"sha256:5e612b2b089d2f1d7d3e56dfd4bed85a8662dbb32347704152ec421cba9b4d74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/bundle.json","state_url":"https://pith.science/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/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":"2026-08-19T08:54:34Z","links":{"resolver":"https://pith.science/pith/JAQ2K43OKGG4SIIEB33LPNJWDF","bundle":"https://pith.science/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/bundle.json","state":"https://pith.science/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAQ2K43OKGG4SIIEB33LPNJWDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JAQ2K43OKGG4SIIEB33LPNJWDF","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":"16d135db1589a008a1b0438df02e3cff634f9d9ce66068400f3624af701ed81e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:16:55Z","title_canon_sha256":"627df2dcfc7d18d539ff9cb2134c285a0b5cdbb27e2f19c083dae4cfe29dd51c"},"schema_version":"1.0","source":{"id":"2408.09493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09493","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09493v2","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09493","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"JAQ2K43OKGG4","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"JAQ2K43OKGG4SIIE","created_at":"2026-07-05T09:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"JAQ2K43O","created_at":"2026-07-05T09:02:24Z"}],"graph_snapshots":[{"event_id":"sha256:5e612b2b089d2f1d7d3e56dfd4bed85a8662dbb32347704152ec421cba9b4d74","target":"graph","created_at":"2026-07-05T09:02:24Z","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/2408.09493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can significantly be enhanced by exploiting a population of agents in various ways. Zeroth-Order Optimization (ZOO) leverages an agent population to estimate the gradient of the objective function, enabling robust policy refinement even in non-differentiable scenarios. As another application, Genetic Algorithms (GA) boosts the exploration of policy landscapes by mutationa","authors_text":"So Nakashima, Tetsuya J. Kobayashi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:16:55Z","title":"Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09493","kind":"arxiv","version":2},"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":"sha256:428f9d6e9f34d5513366e3fdfcae60f71a3712d32f78da877adc669f37c786b8","target":"record","created_at":"2026-07-05T09:02:24Z","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":"16d135db1589a008a1b0438df02e3cff634f9d9ce66068400f3624af701ed81e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:16:55Z","title_canon_sha256":"627df2dcfc7d18d539ff9cb2134c285a0b5cdbb27e2f19c083dae4cfe29dd51c"},"schema_version":"1.0","source":{"id":"2408.09493","kind":"arxiv","version":2}},"canonical_sha256":"4821a5736e518dc921040ef6b7b536197a35299c4090190522fed02def37bd6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4821a5736e518dc921040ef6b7b536197a35299c4090190522fed02def37bd6a","first_computed_at":"2026-07-05T09:02:24.191871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:24.191871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AMVEqy0Iqjb1ZvN/lB/71tR/UtJ4ZzysyYvMnXtVWZcPyl1fnRG+Y4XKj0LGd3EUy92WaNUyU97zH0TibtUiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:24.192311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:428f9d6e9f34d5513366e3fdfcae60f71a3712d32f78da877adc669f37c786b8","sha256:5e612b2b089d2f1d7d3e56dfd4bed85a8662dbb32347704152ec421cba9b4d74"],"state_sha256":"af1aec311704af4e50ba4b65229562fdac430b80217122f249c5516fbb8f0590"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CoHGy7kbDryOEzNwIAmgd6bOiM+7ZjM6jFPSczhxj40Nfrhx07WZS2aTsGFMqrtic8fDvgv5EXlZW+m5eUVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:54:34.291250Z","bundle_sha256":"9cf31ae8d22f7b52f0c38ce273fdcb8ab909e8d658a2865bdd6f568883106dfa"}}