{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XUZOIXR364FB7JEXZSSLCGBLCO","short_pith_number":"pith:XUZOIXR3","canonical_record":{"source":{"id":"2206.00833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:13:29Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c574fd0c68215237dba6074ea680685500af0a9b4c1a16783cd4556648ef7108","abstract_canon_sha256":"8d5d68c7a72d026b7713855568319103c4a2ed1b16fb423faaf0b7b60c06c041"},"schema_version":"1.0"},"canonical_sha256":"bd32e45e3bf70a1fa497cca4b1182b13ba790a3b01a10b1f457a7f090fe1b1b2","source":{"kind":"arxiv","id":"2206.00833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00833","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00833v1","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00833","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"XUZOIXR364FB","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"XUZOIXR364FB7JEX","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"XUZOIXR3","created_at":"2026-07-05T04:28:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XUZOIXR364FB7JEXZSSLCGBLCO","target":"record","payload":{"canonical_record":{"source":{"id":"2206.00833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:13:29Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c574fd0c68215237dba6074ea680685500af0a9b4c1a16783cd4556648ef7108","abstract_canon_sha256":"8d5d68c7a72d026b7713855568319103c4a2ed1b16fb423faaf0b7b60c06c041"},"schema_version":"1.0"},"canonical_sha256":"bd32e45e3bf70a1fa497cca4b1182b13ba790a3b01a10b1f457a7f090fe1b1b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:34.202480Z","signature_b64":"CFxZXbp1FA+u+rzGvGtnzid/EOPwZP1VcAh/uro/uMxJjbXyEz1CoqqeDNzaU2AcQcUhdJ7oympxjiIgBh9ACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd32e45e3bf70a1fa497cca4b1182b13ba790a3b01a10b1f457a7f090fe1b1b2","last_reissued_at":"2026-07-05T04:28:34.201993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:34.201993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.00833","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":"2026-07-05T04:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuLTpv2eqEMtKLN18Isn7inytdLv11vaIaLlmFsvSjNzRnv3dwXFvU96+xPhRbClq69qE3lrlt1JBOm7JYSVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:34:52.675744Z"},"content_sha256":"71295fa1b29b6a4eddd4b0fbf8a95929574fc24990665d06601e0c4a4085253d","schema_version":"1.0","event_id":"sha256:71295fa1b29b6a4eddd4b0fbf8a95929574fc24990665d06601e0c4a4085253d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XUZOIXR364FB7JEXZSSLCGBLCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Niao He, R. Srikant, Semih Cayci","submitted_at":"2022-06-02T02:13:29Z","abstract_excerpt":"Natural actor-critic (NAC) and its variants, equipped with the representation power of neural networks, have demonstrated impressive empirical success in solving Markov decision problems with large state spaces. In this paper, we present a finite-time analysis of NAC with neural network approximation, and identify the roles of neural networks, regularization and optimization techniques (e.g., gradient clipping and averaging) to achieve provably good performance in terms of sample complexity, iteration complexity and overparametrization bounds for the actor and the critic. In particular, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00833","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/2206.00833/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":"2026-07-05T04:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iG0p8JxqW6FO0zpbQ1DB0cQ0P58kkjsvPfF6+QyaQCLVmUrhfu8OsLEOL8Zjkbpf9C34v9hfbDXdAtYgxRIFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:34:52.676249Z"},"content_sha256":"9978cb0219bf5974365e54b1501b73227e50442950d6993dfcf0663401b6a07e","schema_version":"1.0","event_id":"sha256:9978cb0219bf5974365e54b1501b73227e50442950d6993dfcf0663401b6a07e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUZOIXR364FB7JEXZSSLCGBLCO/bundle.json","state_url":"https://pith.science/pith/XUZOIXR364FB7JEXZSSLCGBLCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUZOIXR364FB7JEXZSSLCGBLCO/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":"2026-08-11T15:34:52Z","links":{"resolver":"https://pith.science/pith/XUZOIXR364FB7JEXZSSLCGBLCO","bundle":"https://pith.science/pith/XUZOIXR364FB7JEXZSSLCGBLCO/bundle.json","state":"https://pith.science/pith/XUZOIXR364FB7JEXZSSLCGBLCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUZOIXR364FB7JEXZSSLCGBLCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XUZOIXR364FB7JEXZSSLCGBLCO","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":"8d5d68c7a72d026b7713855568319103c4a2ed1b16fb423faaf0b7b60c06c041","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:13:29Z","title_canon_sha256":"c574fd0c68215237dba6074ea680685500af0a9b4c1a16783cd4556648ef7108"},"schema_version":"1.0","source":{"id":"2206.00833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00833","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00833v1","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00833","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"XUZOIXR364FB","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"XUZOIXR364FB7JEX","created_at":"2026-07-05T04:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"XUZOIXR3","created_at":"2026-07-05T04:28:34Z"}],"graph_snapshots":[{"event_id":"sha256:9978cb0219bf5974365e54b1501b73227e50442950d6993dfcf0663401b6a07e","target":"graph","created_at":"2026-07-05T04:28:34Z","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/2206.00833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural actor-critic (NAC) and its variants, equipped with the representation power of neural networks, have demonstrated impressive empirical success in solving Markov decision problems with large state spaces. In this paper, we present a finite-time analysis of NAC with neural network approximation, and identify the roles of neural networks, regularization and optimization techniques (e.g., gradient clipping and averaging) to achieve provably good performance in terms of sample complexity, iteration complexity and overparametrization bounds for the actor and the critic. In particular, we pro","authors_text":"Niao He, R. Srikant, Semih Cayci","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:13:29Z","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00833","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":"sha256:71295fa1b29b6a4eddd4b0fbf8a95929574fc24990665d06601e0c4a4085253d","target":"record","created_at":"2026-07-05T04:28:34Z","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":"8d5d68c7a72d026b7713855568319103c4a2ed1b16fb423faaf0b7b60c06c041","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:13:29Z","title_canon_sha256":"c574fd0c68215237dba6074ea680685500af0a9b4c1a16783cd4556648ef7108"},"schema_version":"1.0","source":{"id":"2206.00833","kind":"arxiv","version":1}},"canonical_sha256":"bd32e45e3bf70a1fa497cca4b1182b13ba790a3b01a10b1f457a7f090fe1b1b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd32e45e3bf70a1fa497cca4b1182b13ba790a3b01a10b1f457a7f090fe1b1b2","first_computed_at":"2026-07-05T04:28:34.201993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:34.201993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CFxZXbp1FA+u+rzGvGtnzid/EOPwZP1VcAh/uro/uMxJjbXyEz1CoqqeDNzaU2AcQcUhdJ7oympxjiIgBh9ACw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:34.202480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71295fa1b29b6a4eddd4b0fbf8a95929574fc24990665d06601e0c4a4085253d","sha256:9978cb0219bf5974365e54b1501b73227e50442950d6993dfcf0663401b6a07e"],"state_sha256":"f92856877b9909436e8f34121e675bfa6fe3356c0f0dac6e417eed6a055b1dcc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSIO1xYuplxQ+13S1v+pNiASv01OXfG6zDktASZ6iLaJqo4OTaiykWxjhMLjB+qeFDP/gr3YwJv+NNC3DRgICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:34:52.680804Z","bundle_sha256":"db4ac01a9de4c7036aab96edef5e406d2cdea7df3c7ff55f1c7e077d683c1047"}}