{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K6JOCPLJV3TK57N4J6V5QK4V4S","short_pith_number":"pith:K6JOCPLJ","canonical_record":{"source":{"id":"2406.03678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T01:46:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5347413958a157628d28b1bbf16b07d4cf685f59da2234b75aa4b67430312afe","abstract_canon_sha256":"7fdb71408e674878179d2d16d6d3e65e3cf8c150c6ebbac97b9c9f06863e21a1"},"schema_version":"1.0"},"canonical_sha256":"5792e13d69aee6aefdbc4fabd82b95e4ba608c76fdfb4cbad9461ee3d8860c2a","source":{"kind":"arxiv","id":"2406.03678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03678","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03678v1","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03678","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"K6JOCPLJV3TK","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"K6JOCPLJV3TK57N4","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"K6JOCPLJ","created_at":"2026-07-05T08:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K6JOCPLJV3TK57N4J6V5QK4V4S","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T01:46:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5347413958a157628d28b1bbf16b07d4cf685f59da2234b75aa4b67430312afe","abstract_canon_sha256":"7fdb71408e674878179d2d16d6d3e65e3cf8c150c6ebbac97b9c9f06863e21a1"},"schema_version":"1.0"},"canonical_sha256":"5792e13d69aee6aefdbc4fabd82b95e4ba608c76fdfb4cbad9461ee3d8860c2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:14.381631Z","signature_b64":"fQP7aXYyIq/96M3ErwCZ3nZ9ag/7yWFgSp2NcIwKI6QFkbk0QOUrcWo+NI7oassAwaF1262th5naigXSD9tZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5792e13d69aee6aefdbc4fabd82b95e4ba608c76fdfb4cbad9461ee3d8860c2a","last_reissued_at":"2026-07-05T08:28:14.381194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:14.381194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03678","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":"2026-07-05T08:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M37KdSBWc0fkHQrem3VR/jcnAtEhzdaQNhogPmpN4BASOimM4yIdzMO4S5KTkNWNqcow5ITSA2bs7f9OFXa/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:12:44.357670Z"},"content_sha256":"2fb427b11b41cf3edc39c2465953813eb480ba8da35222ab7bb2bfcfd79f4ff6","schema_version":"1.0","event_id":"sha256:2fb427b11b41cf3edc39c2465953813eb480ba8da35222ab7bb2bfcfd79f4ff6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K6JOCPLJV3TK57N4J6V5QK4V4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reflective Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junliang Xing, Renye Yan, Yaozhong Gan, Zhe Wu","submitted_at":"2024-06-06T01:46:49Z","abstract_excerpt":"On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy Optimization (RPO), a novel on-policy extension that amalgamates past and future state-action information for policy optimization. This approach empowers the agent for introspection, allowing modifications to its actions within the current state. Theoretical analysis confirms that policy performance is monotonically improved and contracts the solution space, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03678","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/2406.03678/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":"2026-07-05T08:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tfhyIyLdKzNe7qbSVm3Kg+Oa5BTw6jwPWxPEY5h/+JvdE0/H1nwbQl8WCUJQKWKoNKx595zvyQW5fU7nQtTsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:12:44.358190Z"},"content_sha256":"a5107f4d357312fb5dcc35f6339efe6639c76874d86929018c7e7f93536adb73","schema_version":"1.0","event_id":"sha256:a5107f4d357312fb5dcc35f6339efe6639c76874d86929018c7e7f93536adb73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/bundle.json","state_url":"https://pith.science/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/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":"2026-08-11T16:12:44Z","links":{"resolver":"https://pith.science/pith/K6JOCPLJV3TK57N4J6V5QK4V4S","bundle":"https://pith.science/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/bundle.json","state":"https://pith.science/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6JOCPLJV3TK57N4J6V5QK4V4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K6JOCPLJV3TK57N4J6V5QK4V4S","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":"7fdb71408e674878179d2d16d6d3e65e3cf8c150c6ebbac97b9c9f06863e21a1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T01:46:49Z","title_canon_sha256":"5347413958a157628d28b1bbf16b07d4cf685f59da2234b75aa4b67430312afe"},"schema_version":"1.0","source":{"id":"2406.03678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03678","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03678v1","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03678","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"K6JOCPLJV3TK","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"K6JOCPLJV3TK57N4","created_at":"2026-07-05T08:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"K6JOCPLJ","created_at":"2026-07-05T08:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:a5107f4d357312fb5dcc35f6339efe6639c76874d86929018c7e7f93536adb73","target":"graph","created_at":"2026-07-05T08:28:14Z","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/2406.03678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy Optimization (RPO), a novel on-policy extension that amalgamates past and future state-action information for policy optimization. This approach empowers the agent for introspection, allowing modifications to its actions within the current state. Theoretical analysis confirms that policy performance is monotonically improved and contracts the solution space, ","authors_text":"Junliang Xing, Renye Yan, Yaozhong Gan, Zhe Wu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T01:46:49Z","title":"Reflective Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03678","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":"sha256:2fb427b11b41cf3edc39c2465953813eb480ba8da35222ab7bb2bfcfd79f4ff6","target":"record","created_at":"2026-07-05T08:28:14Z","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":"7fdb71408e674878179d2d16d6d3e65e3cf8c150c6ebbac97b9c9f06863e21a1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T01:46:49Z","title_canon_sha256":"5347413958a157628d28b1bbf16b07d4cf685f59da2234b75aa4b67430312afe"},"schema_version":"1.0","source":{"id":"2406.03678","kind":"arxiv","version":1}},"canonical_sha256":"5792e13d69aee6aefdbc4fabd82b95e4ba608c76fdfb4cbad9461ee3d8860c2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5792e13d69aee6aefdbc4fabd82b95e4ba608c76fdfb4cbad9461ee3d8860c2a","first_computed_at":"2026-07-05T08:28:14.381194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:14.381194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQP7aXYyIq/96M3ErwCZ3nZ9ag/7yWFgSp2NcIwKI6QFkbk0QOUrcWo+NI7oassAwaF1262th5naigXSD9tZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:14.381631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fb427b11b41cf3edc39c2465953813eb480ba8da35222ab7bb2bfcfd79f4ff6","sha256:a5107f4d357312fb5dcc35f6339efe6639c76874d86929018c7e7f93536adb73"],"state_sha256":"10b2dcd1eaa4241e87c2717b3bc88d33535a5618b1d2c4a95e2a58b12a18f733"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6z9noQ99zldw3ZgmCsHeB8Wbn1Os7u5OVd+jw8ZrJvO66uZuQK9FVKmEAM0BDZkswesBi7WvoqHTYIcg+V9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:12:44.363001Z","bundle_sha256":"e1fa7934faac6fffac3f6eb11d5ec1c810752b774ea82183fdc0724a4c1a648b"}}