{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P2XFTJ5KDN5Z2BAF4J67FLLEHO","short_pith_number":"pith:P2XFTJ5K","canonical_record":{"source":{"id":"2505.00663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T17:07:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"661baa42e1eb6ea52856990a036b06031c9007b4c7068fdd0167f9357af0c3d8","abstract_canon_sha256":"db68e6b1c90aeeb8e2453ab245a5c6a8da9f4053d930489709da450525dd7eb1"},"schema_version":"1.0"},"canonical_sha256":"7eae59a7aa1b7b9d0405e27df2ad643bb02409916f5325946a5f798651bca724","source":{"kind":"arxiv","id":"2505.00663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00663","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00663v1","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00663","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"P2XFTJ5KDN5Z","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"P2XFTJ5KDN5Z2BAF","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"P2XFTJ5K","created_at":"2026-07-05T10:57:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P2XFTJ5KDN5Z2BAF4J67FLLEHO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T17:07:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"661baa42e1eb6ea52856990a036b06031c9007b4c7068fdd0167f9357af0c3d8","abstract_canon_sha256":"db68e6b1c90aeeb8e2453ab245a5c6a8da9f4053d930489709da450525dd7eb1"},"schema_version":"1.0"},"canonical_sha256":"7eae59a7aa1b7b9d0405e27df2ad643bb02409916f5325946a5f798651bca724","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:23.677811Z","signature_b64":"AY1m6OJWPjTQ143zgcdHFTfEUdcpjV8094hbL/Kowg6xhFrBH+z+boAaYDhN9OSE0GN5Coh5iZ7XSnbyaqPBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eae59a7aa1b7b9d0405e27df2ad643bb02409916f5325946a5f798651bca724","last_reissued_at":"2026-07-05T10:57:23.677331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:23.677331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00663","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":"2026-07-05T10:57:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sX9GOO2E+EFbXYPpZDMlsFXISyNigeNjvji4qfsTQ1UNf52zJTsMuXUkT7xWLNgtCjQVi3wNO6MvonMDlLeZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:40:40.776500Z"},"content_sha256":"0e7c8f4d3e15923936cc3ee40381fa4d60410aac774b97df3834f338f7739258","schema_version":"1.0","event_id":"sha256:0e7c8f4d3e15923936cc3ee40381fa4d60410aac774b97df3834f338f7739258"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P2XFTJ5KDN5Z2BAF4J67FLLEHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wasserstein Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brendan Tracey, David Pfau, Diana Borsa, Hado van Hasselt, Ian Davies, Joao G. M. Araujo","submitted_at":"2025-05-01T17:07:01Z","abstract_excerpt":"We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies projected into a finite-dimensional parameter space (e.g., the weights of a neural network), leading to a simple and completely general closed-form update. The resulting algorithm combines many properties of deterministic and classic policy gradient methods. Like deterministic policy gradients, it exploits knowledge of the gradient of the action-value function with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00663","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/2505.00663/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":"2026-07-05T10:57:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHvjzsWrIEFGaMBPrS7TeGjyaMfQ/lOWEc3/Xlynzzd5XS5W2CNXPauP6x5HRuV85MHz+3ixPworZZK8XsNuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:40:40.777100Z"},"content_sha256":"2269c3c0bf26f9be2ca5fb24acd6babbdc9edf589b34d521f33de0eb130a90e0","schema_version":"1.0","event_id":"sha256:2269c3c0bf26f9be2ca5fb24acd6babbdc9edf589b34d521f33de0eb130a90e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/bundle.json","state_url":"https://pith.science/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/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":"2026-08-06T05:40:40Z","links":{"resolver":"https://pith.science/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO","bundle":"https://pith.science/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/bundle.json","state":"https://pith.science/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2XFTJ5KDN5Z2BAF4J67FLLEHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P2XFTJ5KDN5Z2BAF4J67FLLEHO","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":"db68e6b1c90aeeb8e2453ab245a5c6a8da9f4053d930489709da450525dd7eb1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T17:07:01Z","title_canon_sha256":"661baa42e1eb6ea52856990a036b06031c9007b4c7068fdd0167f9357af0c3d8"},"schema_version":"1.0","source":{"id":"2505.00663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00663","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00663v1","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00663","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"P2XFTJ5KDN5Z","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"P2XFTJ5KDN5Z2BAF","created_at":"2026-07-05T10:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"P2XFTJ5K","created_at":"2026-07-05T10:57:23Z"}],"graph_snapshots":[{"event_id":"sha256:2269c3c0bf26f9be2ca5fb24acd6babbdc9edf589b34d521f33de0eb130a90e0","target":"graph","created_at":"2026-07-05T10:57:23Z","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/2505.00663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies projected into a finite-dimensional parameter space (e.g., the weights of a neural network), leading to a simple and completely general closed-form update. The resulting algorithm combines many properties of deterministic and classic policy gradient methods. Like deterministic policy gradients, it exploits knowledge of the gradient of the action-value function with","authors_text":"Brendan Tracey, David Pfau, Diana Borsa, Hado van Hasselt, Ian Davies, Joao G. M. Araujo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T17:07:01Z","title":"Wasserstein Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00663","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":"sha256:0e7c8f4d3e15923936cc3ee40381fa4d60410aac774b97df3834f338f7739258","target":"record","created_at":"2026-07-05T10:57:23Z","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":"db68e6b1c90aeeb8e2453ab245a5c6a8da9f4053d930489709da450525dd7eb1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T17:07:01Z","title_canon_sha256":"661baa42e1eb6ea52856990a036b06031c9007b4c7068fdd0167f9357af0c3d8"},"schema_version":"1.0","source":{"id":"2505.00663","kind":"arxiv","version":1}},"canonical_sha256":"7eae59a7aa1b7b9d0405e27df2ad643bb02409916f5325946a5f798651bca724","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eae59a7aa1b7b9d0405e27df2ad643bb02409916f5325946a5f798651bca724","first_computed_at":"2026-07-05T10:57:23.677331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:23.677331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AY1m6OJWPjTQ143zgcdHFTfEUdcpjV8094hbL/Kowg6xhFrBH+z+boAaYDhN9OSE0GN5Coh5iZ7XSnbyaqPBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:23.677811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e7c8f4d3e15923936cc3ee40381fa4d60410aac774b97df3834f338f7739258","sha256:2269c3c0bf26f9be2ca5fb24acd6babbdc9edf589b34d521f33de0eb130a90e0"],"state_sha256":"bb417151e7d7ac0ccbaff7e543ff13afd8e3dcf5be209aea08fb580b6a8da905"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CRcvN/36oVBCjD1ky9vBR8/9nhf12rXZzcyNPYb9BkXdrA6V8nk1dHlTyuMpcTwguHlEAKt/0RqhUu/zSxv4CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:40:40.780660Z","bundle_sha256":"cb76d4596af85aea050fa543b42676883d803cf7df48488ada08eb1f262ad64c"}}