{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DZCZS6GJO5UHKOSQ5WCVPN3G6N","short_pith_number":"pith:DZCZS6GJ","canonical_record":{"source":{"id":"2505.03710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa","abstract_canon_sha256":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f"},"schema_version":"1.0"},"canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","source":{"kind":"arxiv","id":"2505.03710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03710v1","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"DZCZS6GJO5UH","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"DZCZS6GJO5UHKOSQ","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"DZCZS6GJ","created_at":"2026-07-05T10:59:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DZCZS6GJO5UHKOSQ5WCVPN3G6N","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa","abstract_canon_sha256":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f"},"schema_version":"1.0"},"canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:20.849632Z","signature_b64":"hMoZryj6biCCjRxyhGykruko0MgsBXUBuptXNqs3xGBkLDJ+fVw1dOZ7zwIQDbMrBVXVBGh8lmFHKd5Cf5CkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","last_reissued_at":"2026-07-05T10:59:20.849144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:20.849144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03710","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":"2026-07-05T10:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XkKwLhCKW5RJHYmabzLBHCiQ/7wj+jU2sGLlm4uN/8hR1o3lVDANWc4OcXF2hmb0n9ngqzesWxSS0/tTOtcYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:37.748657Z"},"content_sha256":"91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32","schema_version":"1.0","event_id":"sha256:91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DZCZS6GJO5UHKOSQ5WCVPN3G6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actor-Critics Can Achieve Optimal Sample Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Kevin Tan, Wei Fan, Yuting Wei","submitted_at":"2025-05-06T17:32:39Z","abstract_excerpt":"Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work has successfully learned an $\\epsilon$-optimal policy with a sample complexity of $O(1/\\epsilon^2)$ trajectories with general function approximation when strategic exploration is necessary.\n  We address this open problem by introducing a novel actor-critic algorithm that attains a sample-complexity of $O(dH^5 \\log|\\mathcal{A}|/\\epsilon^2 + d H^4 \\log|\\mathc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03710","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/2505.03710/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":"2026-07-05T10:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skOk7lF80Tp3HWzjgb3/mX/NEafDVjkzdrOZQd8RNAh8rXD9ODL/w1fyySzEKOdkhyT+Yb5Pz3RoaH+vkr/3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:37.749624Z"},"content_sha256":"481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a","schema_version":"1.0","event_id":"sha256:481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/bundle.json","state_url":"https://pith.science/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/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":"2026-08-05T17:18:37Z","links":{"resolver":"https://pith.science/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N","bundle":"https://pith.science/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/bundle.json","state":"https://pith.science/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZCZS6GJO5UHKOSQ5WCVPN3G6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DZCZS6GJO5UHKOSQ5WCVPN3G6N","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":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa"},"schema_version":"1.0","source":{"id":"2505.03710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03710v1","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"DZCZS6GJO5UH","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"DZCZS6GJO5UHKOSQ","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"DZCZS6GJ","created_at":"2026-07-05T10:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a","target":"graph","created_at":"2026-07-05T10:59:20Z","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/2505.03710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work has successfully learned an $\\epsilon$-optimal policy with a sample complexity of $O(1/\\epsilon^2)$ trajectories with general function approximation when strategic exploration is necessary.\n  We address this open problem by introducing a novel actor-critic algorithm that attains a sample-complexity of $O(dH^5 \\log|\\mathcal{A}|/\\epsilon^2 + d H^4 \\log|\\mathc","authors_text":"Kevin Tan, Wei Fan, Yuting Wei","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title":"Actor-Critics Can Achieve Optimal Sample Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03710","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":"sha256:91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32","target":"record","created_at":"2026-07-05T10:59:20Z","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":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa"},"schema_version":"1.0","source":{"id":"2505.03710","kind":"arxiv","version":1}},"canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","first_computed_at":"2026-07-05T10:59:20.849144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:20.849144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMoZryj6biCCjRxyhGykruko0MgsBXUBuptXNqs3xGBkLDJ+fVw1dOZ7zwIQDbMrBVXVBGh8lmFHKd5Cf5CkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:20.849632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32","sha256:481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a"],"state_sha256":"c4e3282206479bc834853f1b509c8a59930db64b1805a9c0ece84ac7b350d4be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqUbbLlwaKWYLFG8rYGcrNJ9UFXF17dMoprS/9TldU/ICpqarJQI2aqjrRCS87tyTAbbPP1w7vyEHK+gTI00AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:18:37.754536Z","bundle_sha256":"eceee5784f412288967e81c5984702595601b4607513a22ff1a7ded1adeeaf41"}}