{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G5LNURYMUTSJLCT42LK2YSHMRL","short_pith_number":"pith:G5LNURYM","canonical_record":{"source":{"id":"2605.18591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:05:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8609f955bf034d783bf43388efce1cb54c0f3f133f395f78592a54bd2d0f3f1","abstract_canon_sha256":"ccf09465aecf98d63ac0f168ed1cdd8b3c68e3201bad8b14ee1a6c72c4672920"},"schema_version":"1.0"},"canonical_sha256":"3756da470ca4e4958a7cd2d5ac48ec8ad5766d3e63d8be51776c74811b4043a8","source":{"kind":"arxiv","id":"2605.18591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18591","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18591v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18591","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"G5LNURYMUTSJ","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"G5LNURYMUTSJLCT4","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"G5LNURYM","created_at":"2026-05-20T00:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G5LNURYMUTSJLCT42LK2YSHMRL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:05:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8609f955bf034d783bf43388efce1cb54c0f3f133f395f78592a54bd2d0f3f1","abstract_canon_sha256":"ccf09465aecf98d63ac0f168ed1cdd8b3c68e3201bad8b14ee1a6c72c4672920"},"schema_version":"1.0"},"canonical_sha256":"3756da470ca4e4958a7cd2d5ac48ec8ad5766d3e63d8be51776c74811b4043a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:09.700182Z","signature_b64":"yOY5KzyhF/aUgp2nYiW36vfYOIyd+rW5wUjMA+Uw8TimqTIzQq0XomWDvzFhvqgWCPct6JY8BgoBukNxNwkXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3756da470ca4e4958a7cd2d5ac48ec8ad5766d3e63d8be51776c74811b4043a8","last_reissued_at":"2026-05-20T00:06:09.699406Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:09.699406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18591","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":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NkYaeyvG5Q5mI0hPxiOdSg2/esCLX2UrZso15KzT3S4iD4w9tF8yLm16LTDOBXv/XgHadhvphzNlnj81GnI9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:17:04.689529Z"},"content_sha256":"42de69d61be6adb37303adf58a4107951c1c93dad2745bf12c38eea1a5d78116","schema_version":"1.0","event_id":"sha256:42de69d61be6adb37303adf58a4107951c1c93dad2745bf12c38eea1a5d78116"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G5LNURYMUTSJLCT42LK2YSHMRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingfei Sun","submitted_at":"2026-05-18T16:05:36Z","abstract_excerpt":"Natural policy gradients improve optimization by accounting for the geometry of distribution space, but their practical use is limited by the cost of estimating and inverting the Fisher matrix. We present Randomized Advantage Transformation (RAT), a method for estimating Tikhonov-regularized natural policy gradients via direct backpropagation. By applying the Woodbury formula, we reformulate the regularized natural policy gradients as vanilla policy gradients with a transformed advantage. RAT computes this transformation efficiently via randomized block Kaczmarz iterations on on-policy mini-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18591","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/2605.18591/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.283683Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"257b17f7e19d59ae71d567bee74968b3d8e6a609305317a5ecac614d1ce021fe"},"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":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"daTufgLdQbdWiKWj6ZP0lyfwB8w8LoUlm5nOI3PI0U/5e/v/0OjUkzC3fP7dySu48r9GzMn0SSgZ+oN545o+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:17:04.689923Z"},"content_sha256":"157b087b9b93eefb9665a8a161d1692a2e18ec07c3d5a2eafd4149e8883b1a65","schema_version":"1.0","event_id":"sha256:157b087b9b93eefb9665a8a161d1692a2e18ec07c3d5a2eafd4149e8883b1a65"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:G5LNURYMUTSJLCT42LK2YSHMRL","target":"integrity","payload":{"note":"Identifier '10.5555/3545946.3598613' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Mingfei Sun and Sam Devlin and Jacob Beck and Katja Hofmann and Shimon Whiteson , editor =. Trust Region Bounds for Decentralized. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems,. 2023 , url =. ","arxiv_id":"2605.18591","detector":"doi_compliance","evidence":{"doi":"10.5555/3545946.3598613","arxiv_id":null,"ref_index":2,"raw_excerpt":"Mingfei Sun and Sam Devlin and Jacob Beck and Katja Hofmann and Shimon Whiteson , editor =. Trust Region Bounds for Decentralized. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems,. 2023 , url =. doi:10.5555/3545946.3598613 , timestamp =","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":2,"audited_at":"2026-05-20T12:52:19.118923Z","event_type":"pith.integrity.v1","detected_doi":"10.5555/3545946.3598613","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"8b3462b738d33b2a9a4ec1e5852b4cc19dbd1d59378505b9f2ca8c067b0f285e","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":5144,"payload_sha256":"cfaa9ffe2a07e5acf5d60ce8810edfebba6de061f9df903fd40381c8a127cedf","signature_b64":"zZcTh4RC+zOi8zDQGBQCChYOK/gNeR3iUWaLQ8272J1VozRifSAXL4FXnO4keC5piY8G+Z5+7C9mii8ugOQNCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T12:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CgqpPDe3xLfElVhs9oqWTKa+iQ9AFNecKdW7ETtn1WIfEsMX2lGqZmnDFouPT2ktb77jQ7rM2XYLaVRWZQxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:17:04.690807Z"},"content_sha256":"bc0fba5bc2e23cb9a9ed6eef716f3238637a079207c62a87959968dacd501b6a","schema_version":"1.0","event_id":"sha256:bc0fba5bc2e23cb9a9ed6eef716f3238637a079207c62a87959968dacd501b6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5LNURYMUTSJLCT42LK2YSHMRL/bundle.json","state_url":"https://pith.science/pith/G5LNURYMUTSJLCT42LK2YSHMRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5LNURYMUTSJLCT42LK2YSHMRL/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":"2026-05-21T19:17:04Z","links":{"resolver":"https://pith.science/pith/G5LNURYMUTSJLCT42LK2YSHMRL","bundle":"https://pith.science/pith/G5LNURYMUTSJLCT42LK2YSHMRL/bundle.json","state":"https://pith.science/pith/G5LNURYMUTSJLCT42LK2YSHMRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5LNURYMUTSJLCT42LK2YSHMRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G5LNURYMUTSJLCT42LK2YSHMRL","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ccf09465aecf98d63ac0f168ed1cdd8b3c68e3201bad8b14ee1a6c72c4672920","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:05:36Z","title_canon_sha256":"f8609f955bf034d783bf43388efce1cb54c0f3f133f395f78592a54bd2d0f3f1"},"schema_version":"1.0","source":{"id":"2605.18591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18591","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18591v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18591","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"G5LNURYMUTSJ","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"G5LNURYMUTSJLCT4","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"G5LNURYM","created_at":"2026-05-20T00:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:157b087b9b93eefb9665a8a161d1692a2e18ec07c3d5a2eafd4149e8883b1a65","target":"graph","created_at":"2026-05-20T00:06:09Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.283683Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18591/integrity.json","findings":[],"snapshot_sha256":"257b17f7e19d59ae71d567bee74968b3d8e6a609305317a5ecac614d1ce021fe","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural policy gradients improve optimization by accounting for the geometry of distribution space, but their practical use is limited by the cost of estimating and inverting the Fisher matrix. We present Randomized Advantage Transformation (RAT), a method for estimating Tikhonov-regularized natural policy gradients via direct backpropagation. By applying the Woodbury formula, we reformulate the regularized natural policy gradients as vanilla policy gradients with a transformed advantage. RAT computes this transformation efficiently via randomized block Kaczmarz iterations on on-policy mini-ba","authors_text":"Mingfei Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:05:36Z","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18591","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":"sha256:42de69d61be6adb37303adf58a4107951c1c93dad2745bf12c38eea1a5d78116","target":"record","created_at":"2026-05-20T00:06:09Z","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":"ccf09465aecf98d63ac0f168ed1cdd8b3c68e3201bad8b14ee1a6c72c4672920","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:05:36Z","title_canon_sha256":"f8609f955bf034d783bf43388efce1cb54c0f3f133f395f78592a54bd2d0f3f1"},"schema_version":"1.0","source":{"id":"2605.18591","kind":"arxiv","version":1}},"canonical_sha256":"3756da470ca4e4958a7cd2d5ac48ec8ad5766d3e63d8be51776c74811b4043a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3756da470ca4e4958a7cd2d5ac48ec8ad5766d3e63d8be51776c74811b4043a8","first_computed_at":"2026-05-20T00:06:09.699406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:09.699406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOY5KzyhF/aUgp2nYiW36vfYOIyd+rW5wUjMA+Uw8TimqTIzQq0XomWDvzFhvqgWCPct6JY8BgoBukNxNwkXCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:09.700182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42de69d61be6adb37303adf58a4107951c1c93dad2745bf12c38eea1a5d78116","sha256:157b087b9b93eefb9665a8a161d1692a2e18ec07c3d5a2eafd4149e8883b1a65","sha256:bc0fba5bc2e23cb9a9ed6eef716f3238637a079207c62a87959968dacd501b6a"],"state_sha256":"66404ef8dc6853db5af835afa8724cfa797cf7781fb8baf3b609daf44146e384"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udn5q1EzIqzeeIXh7hhZAePOuIoYfEselnHaulL0kB7XH1q8qbjbOfz5UYY6Wxv7/JxxQ6yZgSQBnptzArsOAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T19:17:04.692936Z","bundle_sha256":"e3777ae2b9b64e607554c81941e73aae743d4ed5ba63d89754e9fc5e9229510f"}}