{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WRV45YDIVZSPYOXPVJ63KCP75Y","short_pith_number":"pith:WRV45YDI","canonical_record":{"source":{"id":"2310.02951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-04T16:41:36Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"eda043d53d44762f0628f945e5316cdabee10368ac3b8e27164e395ce7283daf","abstract_canon_sha256":"b5a0940da4bd4c1d5ef31c82bb2d91631f5135d0e32c2334c199e79fcffda0d6"},"schema_version":"1.0"},"canonical_sha256":"b46bcee068ae64fc3aefaa7db509ffee134ad29e0b35e42bf85273f56537eecf","source":{"kind":"arxiv","id":"2310.02951","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02951","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02951v3","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02951","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"WRV45YDIVZSP","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"WRV45YDIVZSPYOXP","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"WRV45YDI","created_at":"2026-07-05T11:16:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WRV45YDIVZSPYOXPVJ63KCP75Y","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-04T16:41:36Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"eda043d53d44762f0628f945e5316cdabee10368ac3b8e27164e395ce7283daf","abstract_canon_sha256":"b5a0940da4bd4c1d5ef31c82bb2d91631f5135d0e32c2334c199e79fcffda0d6"},"schema_version":"1.0"},"canonical_sha256":"b46bcee068ae64fc3aefaa7db509ffee134ad29e0b35e42bf85273f56537eecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:47.910090Z","signature_b64":"6woujGOmSHXLJNm2rTOOsaICJ7gQoz9g9YGTkaU7WAEkTYpQ9Lb63fredp9kVQzrdnHp2KYSzVM1PHpzv3pXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46bcee068ae64fc3aefaa7db509ffee134ad29e0b35e42bf85273f56537eecf","last_reissued_at":"2026-07-05T11:16:47.909624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:47.909624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02951","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JV3PAn9eBbVtd8j9rza0QbmsyeeJpYvBX00ptYeRpFRlenpflNcy+/HgRPLREYPtzhJzcEKSoFAnRdaRPH81BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:18:31.185402Z"},"content_sha256":"3433e1ab5fd9ab2b9957398188059ee00ebcdaad8518b00637791e6b873f2611","schema_version":"1.0","event_id":"sha256:3433e1ab5fd9ab2b9957398188059ee00ebcdaad8518b00637791e6b873f2611"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WRV45YDIVZSPYOXPVJ63KCP75Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"math.OC","authors_text":"Bekzhan Kerimkulov, David Siska, James-Michael Leahy, Lukasz Szpruch, Yufei Zhang","submitted_at":"2023-10-04T16:41:36Z","abstract_excerpt":"We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent method. We establish the global well-posedness of the gradient flow and demonstrate its exponential convergence to the optimal policy. Moreover, we prove the flow is stable with respect to gradient evaluation, offering insights into the performance of a natural policy gradient flow with log-linear policy parameterisation. To overcome challenges stemming from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02951","kind":"arxiv","version":3},"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/2310.02951/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":"2026-07-05T11:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kOeYRwtKcNsG468l44O+eXzORYaHAFJjdXHGVExwkdyGfi/SeDtpv0rG2MNKXLgRpkFimp6zi5Q9cQ4PxbMJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:18:31.186322Z"},"content_sha256":"c742f376c7fd7eb1f3486f1a3a1bf119384e311e7b275079a53b8aa3c9f89954","schema_version":"1.0","event_id":"sha256:c742f376c7fd7eb1f3486f1a3a1bf119384e311e7b275079a53b8aa3c9f89954"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/bundle.json","state_url":"https://pith.science/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/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":"2026-08-09T09:18:31Z","links":{"resolver":"https://pith.science/pith/WRV45YDIVZSPYOXPVJ63KCP75Y","bundle":"https://pith.science/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/bundle.json","state":"https://pith.science/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRV45YDIVZSPYOXPVJ63KCP75Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WRV45YDIVZSPYOXPVJ63KCP75Y","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":"b5a0940da4bd4c1d5ef31c82bb2d91631f5135d0e32c2334c199e79fcffda0d6","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-04T16:41:36Z","title_canon_sha256":"eda043d53d44762f0628f945e5316cdabee10368ac3b8e27164e395ce7283daf"},"schema_version":"1.0","source":{"id":"2310.02951","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02951","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02951v3","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02951","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"WRV45YDIVZSP","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"WRV45YDIVZSPYOXP","created_at":"2026-07-05T11:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"WRV45YDI","created_at":"2026-07-05T11:16:47Z"}],"graph_snapshots":[{"event_id":"sha256:c742f376c7fd7eb1f3486f1a3a1bf119384e311e7b275079a53b8aa3c9f89954","target":"graph","created_at":"2026-07-05T11:16:47Z","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/2310.02951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent method. We establish the global well-posedness of the gradient flow and demonstrate its exponential convergence to the optimal policy. Moreover, we prove the flow is stable with respect to gradient evaluation, offering insights into the performance of a natural policy gradient flow with log-linear policy parameterisation. To overcome challenges stemming from t","authors_text":"Bekzhan Kerimkulov, David Siska, James-Michael Leahy, Lukasz Szpruch, Yufei Zhang","cross_cats":["cs.LG","math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-04T16:41:36Z","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02951","kind":"arxiv","version":3},"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":"sha256:3433e1ab5fd9ab2b9957398188059ee00ebcdaad8518b00637791e6b873f2611","target":"record","created_at":"2026-07-05T11:16:47Z","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":"b5a0940da4bd4c1d5ef31c82bb2d91631f5135d0e32c2334c199e79fcffda0d6","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-04T16:41:36Z","title_canon_sha256":"eda043d53d44762f0628f945e5316cdabee10368ac3b8e27164e395ce7283daf"},"schema_version":"1.0","source":{"id":"2310.02951","kind":"arxiv","version":3}},"canonical_sha256":"b46bcee068ae64fc3aefaa7db509ffee134ad29e0b35e42bf85273f56537eecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b46bcee068ae64fc3aefaa7db509ffee134ad29e0b35e42bf85273f56537eecf","first_computed_at":"2026-07-05T11:16:47.909624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:47.909624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6woujGOmSHXLJNm2rTOOsaICJ7gQoz9g9YGTkaU7WAEkTYpQ9Lb63fredp9kVQzrdnHp2KYSzVM1PHpzv3pXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:47.910090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02951","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3433e1ab5fd9ab2b9957398188059ee00ebcdaad8518b00637791e6b873f2611","sha256:c742f376c7fd7eb1f3486f1a3a1bf119384e311e7b275079a53b8aa3c9f89954"],"state_sha256":"c08ee7ef655badd64a67409de4d69af5b3b5d31f9f9f29ac03521640e11d6bb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKSxQLzyvV1g98u+MCmcIt/gIyP0NPbuEJWXwnhri3kc/ma2ERHejFnvL0UYMFimn772xzh/xJvcpS5nXMP/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:18:31.193295Z","bundle_sha256":"3386ffc0c1e7e03f9431858f4d9ed5703fa5e2761f75186d33c0a3c0ce11ccd9"}}