{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GF5YPPOM7OIHEPLYKZEVECWPCN","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":"20684c93756440535244abb8eea32822eda7960b379f88b415afbd1ef8a8ef6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T21:06:28Z","title_canon_sha256":"ec084409245a495f196f7aa5bc25a1da69b8cd4d0657840dc257bd43d9435db4"},"schema_version":"1.0","source":{"id":"2504.02130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02130","created_at":"2026-07-05T10:43:51Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02130v1","created_at":"2026-07-05T10:43:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02130","created_at":"2026-07-05T10:43:51Z"},{"alias_kind":"pith_short_12","alias_value":"GF5YPPOM7OIH","created_at":"2026-07-05T10:43:51Z"},{"alias_kind":"pith_short_16","alias_value":"GF5YPPOM7OIHEPLY","created_at":"2026-07-05T10:43:51Z"},{"alias_kind":"pith_short_8","alias_value":"GF5YPPOM","created_at":"2026-07-05T10:43:51Z"}],"graph_snapshots":[{"event_id":"sha256:d9b22eb78dbf43374d9e7f89ff0fe4ed2bdf9564365afa874e8df2b44fac1117","target":"graph","created_at":"2026-07-05T10:43:51Z","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/2504.02130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the policy update and the representation. textcolor{blue}{First}, we establish a few key observations that frame the study: \\textbf{(i)} Global convergence can be achieved under linear function approximation without policy or reward realizability, both for the standard Softmax PG and natural policy gradient (NPG). \\textbf{(ii)} Approximation error is not a key quantity for characterizing global convergence in either algorit","authors_text":"Alekh Agarwal, Bo Dai, Csaba Szepesvari, Dale Schuurmans, Jincheng Mei, Mohammad Ghavamzadeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T21:06:28Z","title":"Ordering-based Conditions for Global Convergence of Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02130","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":"sha256:574bc1dda1897114603e4fb9b955f5bc9951bc94deea00393f802771ea48b9bf","target":"record","created_at":"2026-07-05T10:43:51Z","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":"20684c93756440535244abb8eea32822eda7960b379f88b415afbd1ef8a8ef6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T21:06:28Z","title_canon_sha256":"ec084409245a495f196f7aa5bc25a1da69b8cd4d0657840dc257bd43d9435db4"},"schema_version":"1.0","source":{"id":"2504.02130","kind":"arxiv","version":1}},"canonical_sha256":"317b87bdccfb90723d785649520acf13497964e150edba6328fef1cccf278c88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"317b87bdccfb90723d785649520acf13497964e150edba6328fef1cccf278c88","first_computed_at":"2026-07-05T10:43:51.021351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:51.021351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bFDM3+QNdPX3xPnviH7BAVKaUrtVCrWX8t9qOjbey9xnR1x+O11xM9K69h5csETiaC7jvvfmpDfEXhEaDsy/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:51.021814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:574bc1dda1897114603e4fb9b955f5bc9951bc94deea00393f802771ea48b9bf","sha256:d9b22eb78dbf43374d9e7f89ff0fe4ed2bdf9564365afa874e8df2b44fac1117"],"state_sha256":"8215d56edcbef0f8eb7be2177ec6401eadac308f5e71f4c69bbe5e8df558b33c"}