{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7AL7BSKY76PHOSHMU4WKEA4UM7","short_pith_number":"pith:7AL7BSKY","canonical_record":{"source":{"id":"2411.04913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T17:51:55Z","cross_cats_sorted":["math.OC","math.PR"],"title_canon_sha256":"9c47a11fc1afd88e72575eef3df2f2210357773b692225b0a7066c73d1136efc","abstract_canon_sha256":"c492522fcb8e8988fe7937468aecbec6c623760cc752ac0c5d6183b0a5413fb1"},"schema_version":"1.0"},"canonical_sha256":"f817f0c958ff9e7748eca72ca2039467f50d3f8700b389dbb0e7aeb289078668","source":{"kind":"arxiv","id":"2411.04913","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04913","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04913v1","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04913","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"7AL7BSKY76PH","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"7AL7BSKY76PHOSHM","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"7AL7BSKY","created_at":"2026-07-05T09:32:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7AL7BSKY76PHOSHMU4WKEA4UM7","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T17:51:55Z","cross_cats_sorted":["math.OC","math.PR"],"title_canon_sha256":"9c47a11fc1afd88e72575eef3df2f2210357773b692225b0a7066c73d1136efc","abstract_canon_sha256":"c492522fcb8e8988fe7937468aecbec6c623760cc752ac0c5d6183b0a5413fb1"},"schema_version":"1.0"},"canonical_sha256":"f817f0c958ff9e7748eca72ca2039467f50d3f8700b389dbb0e7aeb289078668","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:36.061600Z","signature_b64":"LL3WsVaOON5Tj9F4P5S35f2zjZBz4odm6dvV55w5oJHCCPEmQOL3gv6flphC41Jp3m+4Yg6z0+S7KrlPmhYFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f817f0c958ff9e7748eca72ca2039467f50d3f8700b389dbb0e7aeb289078668","last_reissued_at":"2026-07-05T09:32:36.061073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:36.061073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04913","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":"2026-07-05T09:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87lkpPS/DXtjeAVnwXe7nQH3+4lBkOKFz6AUPuwoS9tsJ8oynQxuc1Vwo2UhrwWxK5F+o9McNKNJoKl+nu9OBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:42:22.807054Z"},"content_sha256":"48223c0724fcecfd809c40c246b7ab4014cf66e69f086c53d349027605225d1c","schema_version":"1.0","event_id":"sha256:48223c0724fcecfd809c40c246b7ab4014cf66e69f086c53d349027605225d1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7AL7BSKY76PHOSHMU4WKEA4UM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure Matters: Dynamic Policy Gradient","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["math.OC","math.PR"],"primary_cat":"cs.LG","authors_text":"Leif D\\\"oring, Sara Klein, Simon Weissmann, Tamer Ba\\c{s}ar, Xiangyuan Zhang","submitted_at":"2024-11-07T17:51:55Z","abstract_excerpt":"In this work, we study $\\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework directly integrates dynamic programming with (any) policy gradient method, explicitly leveraging the Markovian property of the environment. DynPG dynamically adjusts the problem horizon during training, decomposing the original infinite-horizon MDP into a sequence of contextual bandit problems. By iteratively solving these contextual bandits, DynPG converges to the stationary optimal policy of the infinite-horizon M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04913","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/2411.04913/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":"2026-07-05T09:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMiftINh7P5muC4bgDL7vY0Fhuibc7/ASUlCC8t2U611UcXE8JRII1Guk28o9mQo2WIScW183jxpTFUVz/pYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:42:22.807555Z"},"content_sha256":"5656f8b0ac6392ffaf5d7a07a6d827b1ce6cfae213ac9f4afdb02fc235dafc74","schema_version":"1.0","event_id":"sha256:5656f8b0ac6392ffaf5d7a07a6d827b1ce6cfae213ac9f4afdb02fc235dafc74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/bundle.json","state_url":"https://pith.science/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/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":"2026-08-06T02:42:22Z","links":{"resolver":"https://pith.science/pith/7AL7BSKY76PHOSHMU4WKEA4UM7","bundle":"https://pith.science/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/bundle.json","state":"https://pith.science/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7AL7BSKY76PHOSHMU4WKEA4UM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7AL7BSKY76PHOSHMU4WKEA4UM7","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":"c492522fcb8e8988fe7937468aecbec6c623760cc752ac0c5d6183b0a5413fb1","cross_cats_sorted":["math.OC","math.PR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T17:51:55Z","title_canon_sha256":"9c47a11fc1afd88e72575eef3df2f2210357773b692225b0a7066c73d1136efc"},"schema_version":"1.0","source":{"id":"2411.04913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04913","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04913v1","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04913","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"7AL7BSKY76PH","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"7AL7BSKY76PHOSHM","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"7AL7BSKY","created_at":"2026-07-05T09:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:5656f8b0ac6392ffaf5d7a07a6d827b1ce6cfae213ac9f4afdb02fc235dafc74","target":"graph","created_at":"2026-07-05T09:32:36Z","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/2411.04913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study $\\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework directly integrates dynamic programming with (any) policy gradient method, explicitly leveraging the Markovian property of the environment. DynPG dynamically adjusts the problem horizon during training, decomposing the original infinite-horizon MDP into a sequence of contextual bandit problems. By iteratively solving these contextual bandits, DynPG converges to the stationary optimal policy of the infinite-horizon M","authors_text":"Leif D\\\"oring, Sara Klein, Simon Weissmann, Tamer Ba\\c{s}ar, Xiangyuan Zhang","cross_cats":["math.OC","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T17:51:55Z","title":"Structure Matters: Dynamic Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04913","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":"sha256:48223c0724fcecfd809c40c246b7ab4014cf66e69f086c53d349027605225d1c","target":"record","created_at":"2026-07-05T09:32:36Z","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":"c492522fcb8e8988fe7937468aecbec6c623760cc752ac0c5d6183b0a5413fb1","cross_cats_sorted":["math.OC","math.PR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T17:51:55Z","title_canon_sha256":"9c47a11fc1afd88e72575eef3df2f2210357773b692225b0a7066c73d1136efc"},"schema_version":"1.0","source":{"id":"2411.04913","kind":"arxiv","version":1}},"canonical_sha256":"f817f0c958ff9e7748eca72ca2039467f50d3f8700b389dbb0e7aeb289078668","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f817f0c958ff9e7748eca72ca2039467f50d3f8700b389dbb0e7aeb289078668","first_computed_at":"2026-07-05T09:32:36.061073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:36.061073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LL3WsVaOON5Tj9F4P5S35f2zjZBz4odm6dvV55w5oJHCCPEmQOL3gv6flphC41Jp3m+4Yg6z0+S7KrlPmhYFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:36.061600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48223c0724fcecfd809c40c246b7ab4014cf66e69f086c53d349027605225d1c","sha256:5656f8b0ac6392ffaf5d7a07a6d827b1ce6cfae213ac9f4afdb02fc235dafc74"],"state_sha256":"af67418b02f7853e4e8feb28f55ef849ee3000e38dc625b97157e6c29e9c875f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHxcM4Yx1P0ZK7ve1YqMbnYZi4z347dvyuPdLLu9d0/k4lWkJr5Q/SEw/87hiyOQOvQU5OI+pmB19SPeSEZLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:42:22.810986Z","bundle_sha256":"efdaa79a277f1b954a802089f2b8d724e478ad174d2ac26dfa9642d6a3ef50ae"}}