{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VH25IYYEVCHBKFZAJRTPT7E56V","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":"f376636ce2a213b97d91ef5ba58587f85762004a3e079fa969bbaf346395ce7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:03:06Z","title_canon_sha256":"d9b0bd498d3fcdddbbde02790d5497c66b002d2ce7eeb3caa068ea37fd4f3c81"},"schema_version":"1.0","source":{"id":"2505.03155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03155","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03155v1","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03155","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"VH25IYYEVCHB","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"VH25IYYEVCHBKFZA","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"VH25IYYE","created_at":"2026-07-05T10:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:a770fbc884567011f3317bf92c20b22d63e0a7caa72bd7d1ff56cc7147ed47f5","target":"graph","created_at":"2026-07-05T10:59:10Z","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/2505.03155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the approximation error in modeling problem-dependent quantities is a key notion for characterizing the global convergence of PG methods. We focus on Softmax PG with linear function approximation (referred to as $\\texttt{Lin-SPG}$) and demonstrate that the approximation error is irrelevant to the algorithm's global convergence even for the stochastic bandit setti","authors_text":"Alekh Agarwal, Bo Dai, Csaba Szepesvari, Dale Schuurmans, Jincheng Mei, Matin Aghaei, Max Qiushi Lin, Michael Lu, Sharan Vaswani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:03:06Z","title":"Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03155","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:dfc7d01b5d536d407fad653f0dbdb3c9e535c260f558239fdb80b317a4b986c0","target":"record","created_at":"2026-07-05T10:59:10Z","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":"f376636ce2a213b97d91ef5ba58587f85762004a3e079fa969bbaf346395ce7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:03:06Z","title_canon_sha256":"d9b0bd498d3fcdddbbde02790d5497c66b002d2ce7eeb3caa068ea37fd4f3c81"},"schema_version":"1.0","source":{"id":"2505.03155","kind":"arxiv","version":1}},"canonical_sha256":"a9f5d46304a88e1517204c66f9fc9df55c5da4e826e6d39c6cd386623139a55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9f5d46304a88e1517204c66f9fc9df55c5da4e826e6d39c6cd386623139a55d","first_computed_at":"2026-07-05T10:59:10.955473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:10.955473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vBquJGSKwb1BK6MuFBR2FreOaVyC34HOGAIXEI3s6ooB00tfC/ocPHvqdXR3Xu3xVANjcstZZErM82tvyuKYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:10.955954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfc7d01b5d536d407fad653f0dbdb3c9e535c260f558239fdb80b317a4b986c0","sha256:a770fbc884567011f3317bf92c20b22d63e0a7caa72bd7d1ff56cc7147ed47f5"],"state_sha256":"e51a2827820bdd51239f32577354ed940922f4e1c74ba92ea10de3e0a793f46a"}