{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TCMVQURWR75MBB4N4YNU3GDYWW","short_pith_number":"pith:TCMVQURW","canonical_record":{"source":{"id":"2607.11626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-13T14:45:07Z","cross_cats_sorted":[],"title_canon_sha256":"cf7bc9bbe3e5ae0226cea5f2c4dc9e6a9af6c5197cfc8dd655bbefe43a512df4","abstract_canon_sha256":"ff18176a15ad341aa70395e7bf2bc22a6537b705ad7ca27cb4dfa391307c7a97"},"schema_version":"1.0"},"canonical_sha256":"98995852368ffac0878de61b4d9878b5a8288139812a8b3432f0d29f614505c9","source":{"kind":"arxiv","id":"2607.11626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11626","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11626v1","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11626","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"TCMVQURWR75M","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"TCMVQURWR75MBB4N","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"TCMVQURW","created_at":"2026-07-14T02:22:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TCMVQURWR75MBB4N4YNU3GDYWW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.11626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-13T14:45:07Z","cross_cats_sorted":[],"title_canon_sha256":"cf7bc9bbe3e5ae0226cea5f2c4dc9e6a9af6c5197cfc8dd655bbefe43a512df4","abstract_canon_sha256":"ff18176a15ad341aa70395e7bf2bc22a6537b705ad7ca27cb4dfa391307c7a97"},"schema_version":"1.0"},"canonical_sha256":"98995852368ffac0878de61b4d9878b5a8288139812a8b3432f0d29f614505c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:15.592994Z","signature_b64":"795Rc//qnKcNjsumY7N/KDtjOXkVHaETDKsfN1N3OBsN4jpXYHZrrrPXbX9NFkZMxgFtSlVHG5nKCBUkLRObCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98995852368ffac0878de61b4d9878b5a8288139812a8b3432f0d29f614505c9","last_reissued_at":"2026-07-14T02:22:15.591859Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:15.591859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.11626","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":"2026-07-14T02:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSIOGnifMAbvL+x85yNeYUZNBDW96eT5sbMCDQE17LVnRI+6QIT67qBDuKiTfed4eX7wg/NADjo+5VYdsF2XCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:22:43.922298Z"},"content_sha256":"49d051397d2dec424615b2ce5ac86c8b10335b605b91d03cf5c62d04d81f88de","schema_version":"1.0","event_id":"sha256:49d051397d2dec424615b2ce5ac86c8b10335b605b91d03cf5c62d04d81f88de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TCMVQURWR75MBB4N4YNU3GDYWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Policy Convergence of Policy Mirror Descent Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ke Wei, Wenye Li","submitted_at":"2026-07-13T14:45:07Z","abstract_excerpt":"We study the policy convergence of unregularized policy mirror descent (PMD) with arbitrary constant step sizes for finite discounted Markov decision processes. We focus on decomposable mirror maps of the form $h(p)=\\sum_a \\psi(p(a))$, where $\\psi$ satisfies standard Legendre-type assumptions. Under these conditions, we prove that the policy sequence generated by PMD converges in the policy domain to a limiting optimal policy, even when the optimal policy set is not a singleton. This result covers a broad class of commonly used mirror maps, including the squared Euclidean mirror map underlying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11626","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/2607.11626/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":"2026-07-14T02:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fcmyVUoLSelD3PQbBT06nECL1z7HdMWWxTKdJg5grqbUYoKLbbvyecna7I5VlD/uLV6Jr54/DYRDlXLa4ICDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:22:43.922835Z"},"content_sha256":"47650e6e4dbec1a2c38bc3ae1426bd0873adb2208cd49e2fe32376665470bff8","schema_version":"1.0","event_id":"sha256:47650e6e4dbec1a2c38bc3ae1426bd0873adb2208cd49e2fe32376665470bff8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCMVQURWR75MBB4N4YNU3GDYWW/bundle.json","state_url":"https://pith.science/pith/TCMVQURWR75MBB4N4YNU3GDYWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCMVQURWR75MBB4N4YNU3GDYWW/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":"2026-08-05T14:22:43Z","links":{"resolver":"https://pith.science/pith/TCMVQURWR75MBB4N4YNU3GDYWW","bundle":"https://pith.science/pith/TCMVQURWR75MBB4N4YNU3GDYWW/bundle.json","state":"https://pith.science/pith/TCMVQURWR75MBB4N4YNU3GDYWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCMVQURWR75MBB4N4YNU3GDYWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TCMVQURWR75MBB4N4YNU3GDYWW","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":"ff18176a15ad341aa70395e7bf2bc22a6537b705ad7ca27cb4dfa391307c7a97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-13T14:45:07Z","title_canon_sha256":"cf7bc9bbe3e5ae0226cea5f2c4dc9e6a9af6c5197cfc8dd655bbefe43a512df4"},"schema_version":"1.0","source":{"id":"2607.11626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11626","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11626v1","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11626","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"TCMVQURWR75M","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"TCMVQURWR75MBB4N","created_at":"2026-07-14T02:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"TCMVQURW","created_at":"2026-07-14T02:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:47650e6e4dbec1a2c38bc3ae1426bd0873adb2208cd49e2fe32376665470bff8","target":"graph","created_at":"2026-07-14T02:22:15Z","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/2607.11626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the policy convergence of unregularized policy mirror descent (PMD) with arbitrary constant step sizes for finite discounted Markov decision processes. We focus on decomposable mirror maps of the form $h(p)=\\sum_a \\psi(p(a))$, where $\\psi$ satisfies standard Legendre-type assumptions. Under these conditions, we prove that the policy sequence generated by PMD converges in the policy domain to a limiting optimal policy, even when the optimal policy set is not a singleton. This result covers a broad class of commonly used mirror maps, including the squared Euclidean mirror map underlying","authors_text":"Ke Wei, Wenye Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-13T14:45:07Z","title":"On the Policy Convergence of Policy Mirror Descent Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11626","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":"sha256:49d051397d2dec424615b2ce5ac86c8b10335b605b91d03cf5c62d04d81f88de","target":"record","created_at":"2026-07-14T02:22:15Z","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":"ff18176a15ad341aa70395e7bf2bc22a6537b705ad7ca27cb4dfa391307c7a97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-13T14:45:07Z","title_canon_sha256":"cf7bc9bbe3e5ae0226cea5f2c4dc9e6a9af6c5197cfc8dd655bbefe43a512df4"},"schema_version":"1.0","source":{"id":"2607.11626","kind":"arxiv","version":1}},"canonical_sha256":"98995852368ffac0878de61b4d9878b5a8288139812a8b3432f0d29f614505c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98995852368ffac0878de61b4d9878b5a8288139812a8b3432f0d29f614505c9","first_computed_at":"2026-07-14T02:22:15.591859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T02:22:15.591859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"795Rc//qnKcNjsumY7N/KDtjOXkVHaETDKsfN1N3OBsN4jpXYHZrrrPXbX9NFkZMxgFtSlVHG5nKCBUkLRObCA==","signature_status":"signed_v1","signed_at":"2026-07-14T02:22:15.592994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d051397d2dec424615b2ce5ac86c8b10335b605b91d03cf5c62d04d81f88de","sha256:47650e6e4dbec1a2c38bc3ae1426bd0873adb2208cd49e2fe32376665470bff8"],"state_sha256":"af7d30ffa58891eb0cfe8d71aec2ecf531000ec73621dc38dd9af99841a8486f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"II+eUW989Tsxk2t37wAL1wORw1p5Vp7EQ7b/Q6q0FCE0SefA0iLbWqMXHrbhNFd9aU5vWwYjOxEPAJF/pAVNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:22:43.926417Z","bundle_sha256":"42396ea378bf8f275c7c75cde513ab858dcb9d8f0e99081d22b5a1e2dc6f6b3e"}}