{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E246QXTCD74MBDFUQIYAIN5CGT","short_pith_number":"pith:E246QXTC","canonical_record":{"source":{"id":"2411.12042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:27:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c0f515bd9cf83b558c5b023166e2b209594d6a8b9c242c2aa8008e1d5ea22489","abstract_canon_sha256":"474ab19d9573630e505861fed161b017df65764da3ee30bdcb0938051faa522b"},"schema_version":"1.0"},"canonical_sha256":"26b9e85e621ff8c08cb482300437a234c0166906d9a2514b72d9e5788950c546","source":{"kind":"arxiv","id":"2411.12042","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12042","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12042v2","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12042","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"E246QXTCD74M","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"E246QXTCD74MBDFU","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"E246QXTC","created_at":"2026-07-05T11:12:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E246QXTCD74MBDFUQIYAIN5CGT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:27:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c0f515bd9cf83b558c5b023166e2b209594d6a8b9c242c2aa8008e1d5ea22489","abstract_canon_sha256":"474ab19d9573630e505861fed161b017df65764da3ee30bdcb0938051faa522b"},"schema_version":"1.0"},"canonical_sha256":"26b9e85e621ff8c08cb482300437a234c0166906d9a2514b72d9e5788950c546","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:22.349868Z","signature_b64":"/FsTj9Ao20i+0vvDfU88dSI4LuPlI2v+8Odmgi2eXLyWDtn58RB7HxKeD9BVwbH3+WRTfHUHaSp35vypWUbVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b9e85e621ff8c08cb482300437a234c0166906d9a2514b72d9e5788950c546","last_reissued_at":"2026-07-05T11:12:22.349286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:22.349286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12042","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xf4HC2P9hnXqmSHPTnXMlct3poz2iVPstyDVXFXTeXDm32/PnHthexlBy0rOeq4Yi99H5nUbUnitZpWS/E7lAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:09:52.779695Z"},"content_sha256":"d88c63716054994180b5c5401e1f45869c78136288541d839402230076c5069d","schema_version":"1.0","event_id":"sha256:d88c63716054994180b5c5401e1f45869c78136288541d839402230076c5069d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E246QXTCD74MBDFUQIYAIN5CGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Convergence of Softmax Policy Mirror Ascent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Issam Laradji, Nicolas Le Roux, Reza Asad, Reza Babanezhad, Sharan Vaswani","submitted_at":"2024-11-18T20:27:13Z","abstract_excerpt":"Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that corresponds to mirror ascent in the dual space of logits. We refine this algorithm, removing its need for a normalization across actions and analyze the resulting method (referred to as SPMA). For tabular MDPs, we prove that SPMA with a constant step-size matches the linear convergence of NPG and achieves a faster convergence than constant step-size (accelerated) softmax policy gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12042","kind":"arxiv","version":2},"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/2411.12042/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":"2026-07-05T11:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6zkY6UhbjrL6pu/lMK54UyCxHgS67H12NzzoTJLthPmT6grJLNQ2XZYNjIsc3npbYnt9bxIcSYK+XskWZ7+XCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:09:52.780080Z"},"content_sha256":"35c389239c60e0f4cf2d07d175a3aa9f46cf4a7e8bdf77c0ebde76cc44aa9762","schema_version":"1.0","event_id":"sha256:35c389239c60e0f4cf2d07d175a3aa9f46cf4a7e8bdf77c0ebde76cc44aa9762"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E246QXTCD74MBDFUQIYAIN5CGT/bundle.json","state_url":"https://pith.science/pith/E246QXTCD74MBDFUQIYAIN5CGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E246QXTCD74MBDFUQIYAIN5CGT/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":"2026-08-19T20:09:52Z","links":{"resolver":"https://pith.science/pith/E246QXTCD74MBDFUQIYAIN5CGT","bundle":"https://pith.science/pith/E246QXTCD74MBDFUQIYAIN5CGT/bundle.json","state":"https://pith.science/pith/E246QXTCD74MBDFUQIYAIN5CGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E246QXTCD74MBDFUQIYAIN5CGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E246QXTCD74MBDFUQIYAIN5CGT","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":"474ab19d9573630e505861fed161b017df65764da3ee30bdcb0938051faa522b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:27:13Z","title_canon_sha256":"c0f515bd9cf83b558c5b023166e2b209594d6a8b9c242c2aa8008e1d5ea22489"},"schema_version":"1.0","source":{"id":"2411.12042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12042","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12042v2","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12042","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"E246QXTCD74M","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"E246QXTCD74MBDFU","created_at":"2026-07-05T11:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"E246QXTC","created_at":"2026-07-05T11:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:35c389239c60e0f4cf2d07d175a3aa9f46cf4a7e8bdf77c0ebde76cc44aa9762","target":"graph","created_at":"2026-07-05T11:12:22Z","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/2411.12042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that corresponds to mirror ascent in the dual space of logits. We refine this algorithm, removing its need for a normalization across actions and analyze the resulting method (referred to as SPMA). For tabular MDPs, we prove that SPMA with a constant step-size matches the linear convergence of NPG and achieves a faster convergence than constant step-size (accelerated) softmax policy gradient","authors_text":"Issam Laradji, Nicolas Le Roux, Reza Asad, Reza Babanezhad, Sharan Vaswani","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:27:13Z","title":"Fast Convergence of Softmax Policy Mirror Ascent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12042","kind":"arxiv","version":2},"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:d88c63716054994180b5c5401e1f45869c78136288541d839402230076c5069d","target":"record","created_at":"2026-07-05T11:12:22Z","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":"474ab19d9573630e505861fed161b017df65764da3ee30bdcb0938051faa522b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:27:13Z","title_canon_sha256":"c0f515bd9cf83b558c5b023166e2b209594d6a8b9c242c2aa8008e1d5ea22489"},"schema_version":"1.0","source":{"id":"2411.12042","kind":"arxiv","version":2}},"canonical_sha256":"26b9e85e621ff8c08cb482300437a234c0166906d9a2514b72d9e5788950c546","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b9e85e621ff8c08cb482300437a234c0166906d9a2514b72d9e5788950c546","first_computed_at":"2026-07-05T11:12:22.349286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:22.349286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FsTj9Ao20i+0vvDfU88dSI4LuPlI2v+8Odmgi2eXLyWDtn58RB7HxKeD9BVwbH3+WRTfHUHaSp35vypWUbVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:22.349868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d88c63716054994180b5c5401e1f45869c78136288541d839402230076c5069d","sha256:35c389239c60e0f4cf2d07d175a3aa9f46cf4a7e8bdf77c0ebde76cc44aa9762"],"state_sha256":"6b308111320fb2f4761a796bd5bdd53b522f064f3c1eb7dabac8fec56eab0976"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6jL5VVaBJLCDRTLAJ5i0rCAt4up+drHjluM/3PjAtn0m6fo+U6cuoUzfc4i+RtpHYJUxzy08Wx08JbBYMeqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:09:52.783001Z","bundle_sha256":"c47292b5089f9c41851fb842a79dc64b885dff43ef355e84289e5c18fc91215f"}}