{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RW5YQGKUWBZFIFYDF4PEJYEKEY","short_pith_number":"pith:RW5YQGKU","canonical_record":{"source":{"id":"2502.11033","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T08:05:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"1b979ebae98587d078f381cb3d0b83a725c66faaf2d18abf53498f8f275259ac","abstract_canon_sha256":"7e7e40d85a192524005035692c32907f7c1fa8d6ab03347d9fe3d32e241a0fd0"},"schema_version":"1.0"},"canonical_sha256":"8dbb881954b0725417032f1e44e08a263238144a3f3ca167f1962c33f3ab6844","source":{"kind":"arxiv","id":"2502.11033","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11033","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11033v3","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11033","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_12","alias_value":"RW5YQGKUWBZF","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_16","alias_value":"RW5YQGKUWBZFIFYD","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_8","alias_value":"RW5YQGKU","created_at":"2026-07-05T11:32:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RW5YQGKUWBZFIFYDF4PEJYEKEY","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11033","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T08:05:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"1b979ebae98587d078f381cb3d0b83a725c66faaf2d18abf53498f8f275259ac","abstract_canon_sha256":"7e7e40d85a192524005035692c32907f7c1fa8d6ab03347d9fe3d32e241a0fd0"},"schema_version":"1.0"},"canonical_sha256":"8dbb881954b0725417032f1e44e08a263238144a3f3ca167f1962c33f3ab6844","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:24.736326Z","signature_b64":"qmyA5vaqBvRzhquLGv8YmaEPz4jZn3wg/P0CzLq9NV9scq/ocTVVbSv5mv+W5DNFKO0f3dMCeOi8a3r2LuEcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dbb881954b0725417032f1e44e08a263238144a3f3ca167f1962c33f3ab6844","last_reissued_at":"2026-07-05T11:32:24.735834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:24.735834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11033","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":"2026-07-05T11:32:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEAhmeQ/AJK41uVKIU/90TNvss5seHjXN5nSKpzN6dlZ1QgWqrqy01z7VTrM3wvSJ8UXH9C+pdb/J8wCZsztAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:37:04.237991Z"},"content_sha256":"59a68e53a194540d6cb57229d74e5b9328cf98497ef0f4ac325a46690f6406b3","schema_version":"1.0","event_id":"sha256:59a68e53a194540d6cb57229d74e5b9328cf98497ef0f4ac325a46690f6406b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RW5YQGKUWBZFIFYDF4PEJYEKEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tomer Koren, Uri Sherman, Yishay Mansour","submitted_at":"2025-02-16T08:05:46Z","abstract_excerpt":"Modern policy optimization methods roughly follow the policy mirror descent (PMD) algorithmic template, for which there are by now numerous theoretical convergence results. However, most of these either target tabular environments, or can be applied effectively only when the class of policies being optimized over satisfies strong closure conditions, which is typically not the case when working with parametric policy classes in large-scale environments. In this work, we develop a theoretical framework for PMD for general policy classes where we replace the closure conditions with a strictly wea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11033","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/2502.11033/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":"2026-07-05T11:32:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAVm4l/+7hyWLn2YWxDrrWrBnBcZ8KvDNUJfZshZUVp3oIgAB19hUaDYcqGOkxlhIHIp2EVu6KrxUmXC4qVCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:37:04.238517Z"},"content_sha256":"0e0a876fc396d254bdab7f1e3668b0b95940135595106e74091b425c0c11c6cd","schema_version":"1.0","event_id":"sha256:0e0a876fc396d254bdab7f1e3668b0b95940135595106e74091b425c0c11c6cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/bundle.json","state_url":"https://pith.science/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/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":"2026-08-11T10:37:04Z","links":{"resolver":"https://pith.science/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY","bundle":"https://pith.science/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/bundle.json","state":"https://pith.science/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RW5YQGKUWBZFIFYDF4PEJYEKEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RW5YQGKUWBZFIFYDF4PEJYEKEY","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":"7e7e40d85a192524005035692c32907f7c1fa8d6ab03347d9fe3d32e241a0fd0","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T08:05:46Z","title_canon_sha256":"1b979ebae98587d078f381cb3d0b83a725c66faaf2d18abf53498f8f275259ac"},"schema_version":"1.0","source":{"id":"2502.11033","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11033","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11033v3","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11033","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_12","alias_value":"RW5YQGKUWBZF","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_16","alias_value":"RW5YQGKUWBZFIFYD","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_8","alias_value":"RW5YQGKU","created_at":"2026-07-05T11:32:24Z"}],"graph_snapshots":[{"event_id":"sha256:0e0a876fc396d254bdab7f1e3668b0b95940135595106e74091b425c0c11c6cd","target":"graph","created_at":"2026-07-05T11:32:24Z","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/2502.11033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern policy optimization methods roughly follow the policy mirror descent (PMD) algorithmic template, for which there are by now numerous theoretical convergence results. However, most of these either target tabular environments, or can be applied effectively only when the class of policies being optimized over satisfies strong closure conditions, which is typically not the case when working with parametric policy classes in large-scale environments. In this work, we develop a theoretical framework for PMD for general policy classes where we replace the closure conditions with a strictly wea","authors_text":"Tomer Koren, Uri Sherman, Yishay Mansour","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T08:05:46Z","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11033","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":"sha256:59a68e53a194540d6cb57229d74e5b9328cf98497ef0f4ac325a46690f6406b3","target":"record","created_at":"2026-07-05T11:32:24Z","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":"7e7e40d85a192524005035692c32907f7c1fa8d6ab03347d9fe3d32e241a0fd0","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T08:05:46Z","title_canon_sha256":"1b979ebae98587d078f381cb3d0b83a725c66faaf2d18abf53498f8f275259ac"},"schema_version":"1.0","source":{"id":"2502.11033","kind":"arxiv","version":3}},"canonical_sha256":"8dbb881954b0725417032f1e44e08a263238144a3f3ca167f1962c33f3ab6844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dbb881954b0725417032f1e44e08a263238144a3f3ca167f1962c33f3ab6844","first_computed_at":"2026-07-05T11:32:24.735834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:24.735834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmyA5vaqBvRzhquLGv8YmaEPz4jZn3wg/P0CzLq9NV9scq/ocTVVbSv5mv+W5DNFKO0f3dMCeOi8a3r2LuEcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:24.736326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11033","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59a68e53a194540d6cb57229d74e5b9328cf98497ef0f4ac325a46690f6406b3","sha256:0e0a876fc396d254bdab7f1e3668b0b95940135595106e74091b425c0c11c6cd"],"state_sha256":"6103a049492b6116565eba438e4323c8de1c42b9070cd99cd0c070f505594f35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHovNSV+RmldaWXRLnvU4F9OfWdrDrOoj25A6KQQ4NwK2Gn2K1fxjhj26D51A4Tbt0dSR6do7lLk0elwcu6/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:37:04.243767Z","bundle_sha256":"14c9c09e0171faae2e652da323e1df9fb875ef5c6b51a5f0c9bcc976aa5a2229"}}