{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BATOEOY5MKM22YZQ3DEGRXTAXU","short_pith_number":"pith:BATOEOY5","canonical_record":{"source":{"id":"2506.06376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:58:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f609c574f7c6646f5582a8a6c12295c9022b9f5b4c9381d390ba15839dcb24e","abstract_canon_sha256":"ebfe202dd4488eb191b18cfcb40841155b86c5ece342a922510dd477991df6f5"},"schema_version":"1.0"},"canonical_sha256":"0826e23b1d6299ad6330d8c868de60bd012e285a2c41eb70a3b1f314ced13deb","source":{"kind":"arxiv","id":"2506.06376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06376","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06376v1","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06376","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"BATOEOY5MKM2","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"BATOEOY5MKM22YZQ","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"BATOEOY5","created_at":"2026-07-05T11:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BATOEOY5MKM22YZQ3DEGRXTAXU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:58:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f609c574f7c6646f5582a8a6c12295c9022b9f5b4c9381d390ba15839dcb24e","abstract_canon_sha256":"ebfe202dd4488eb191b18cfcb40841155b86c5ece342a922510dd477991df6f5"},"schema_version":"1.0"},"canonical_sha256":"0826e23b1d6299ad6330d8c868de60bd012e285a2c41eb70a3b1f314ced13deb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:49.175544Z","signature_b64":"eiX7506W2aMnn0ZWe+/KszQSrk9W2KwjoTKZ1/EEvpSAekwYGS36M/oU5eAaKTaMSTQTV+nKwBwoF38MjQ7xAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0826e23b1d6299ad6330d8c868de60bd012e285a2c41eb70a3b1f314ced13deb","last_reissued_at":"2026-07-05T11:17:49.175064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:49.175064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06376","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":"2026-07-05T11:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6uolu2VAuaKssHGviDTsK5mIIt4NTFDP740EvZ2IlrB4HQiGN904SD5mqnCC2GwtwqWLVNVG3dOGnH8gJ3gCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:40:19.834411Z"},"content_sha256":"c0903c6141838d4e125a0e07efde03af94b37bd4b767aeade9d1cd4054c13a6b","schema_version":"1.0","event_id":"sha256:c0903c6141838d4e125a0e07efde03af94b37bd4b767aeade9d1cd4054c13a6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BATOEOY5MKM22YZQ3DEGRXTAXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongjie Zhang, Heng Dong, Kefei Duan","submitted_at":"2025-06-04T14:58:27Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level objectives. Existing methods either rely on short-term auto-regressive action generation or face limitations in accurately simulating rollouts and assessing outcomes, leading to sub-optimal decisions. This paper introduces a novel LLM-based Actor-Critic framework, termed LAC, that effectively improves LLM policies with long-term action evaluations in a principled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06376","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/2506.06376/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":"2026-07-05T11:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4ER7M/bsyrkltP6SnCXnFOn9M32kjG4Ro2oS8AJW2BQpbD1bzFn9T+ABUiW+g21f617yq/8SQrZ+row9ILnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:40:19.835002Z"},"content_sha256":"64bb1313326db2302eeb86a09c31ab75157a04c5ed6958618aba5a40e679dd91","schema_version":"1.0","event_id":"sha256:64bb1313326db2302eeb86a09c31ab75157a04c5ed6958618aba5a40e679dd91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/bundle.json","state_url":"https://pith.science/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/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":"2026-08-09T21:40:19Z","links":{"resolver":"https://pith.science/pith/BATOEOY5MKM22YZQ3DEGRXTAXU","bundle":"https://pith.science/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/bundle.json","state":"https://pith.science/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BATOEOY5MKM22YZQ3DEGRXTAXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BATOEOY5MKM22YZQ3DEGRXTAXU","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":"ebfe202dd4488eb191b18cfcb40841155b86c5ece342a922510dd477991df6f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:58:27Z","title_canon_sha256":"7f609c574f7c6646f5582a8a6c12295c9022b9f5b4c9381d390ba15839dcb24e"},"schema_version":"1.0","source":{"id":"2506.06376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06376","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06376v1","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06376","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"BATOEOY5MKM2","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"BATOEOY5MKM22YZQ","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"BATOEOY5","created_at":"2026-07-05T11:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:64bb1313326db2302eeb86a09c31ab75157a04c5ed6958618aba5a40e679dd91","target":"graph","created_at":"2026-07-05T11:17:49Z","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/2506.06376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level objectives. Existing methods either rely on short-term auto-regressive action generation or face limitations in accurately simulating rollouts and assessing outcomes, leading to sub-optimal decisions. This paper introduces a novel LLM-based Actor-Critic framework, termed LAC, that effectively improves LLM policies with long-term action evaluations in a principled","authors_text":"Chongjie Zhang, Heng Dong, Kefei Duan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:58:27Z","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06376","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:c0903c6141838d4e125a0e07efde03af94b37bd4b767aeade9d1cd4054c13a6b","target":"record","created_at":"2026-07-05T11:17:49Z","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":"ebfe202dd4488eb191b18cfcb40841155b86c5ece342a922510dd477991df6f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:58:27Z","title_canon_sha256":"7f609c574f7c6646f5582a8a6c12295c9022b9f5b4c9381d390ba15839dcb24e"},"schema_version":"1.0","source":{"id":"2506.06376","kind":"arxiv","version":1}},"canonical_sha256":"0826e23b1d6299ad6330d8c868de60bd012e285a2c41eb70a3b1f314ced13deb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0826e23b1d6299ad6330d8c868de60bd012e285a2c41eb70a3b1f314ced13deb","first_computed_at":"2026-07-05T11:17:49.175064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:49.175064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eiX7506W2aMnn0ZWe+/KszQSrk9W2KwjoTKZ1/EEvpSAekwYGS36M/oU5eAaKTaMSTQTV+nKwBwoF38MjQ7xAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:49.175544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0903c6141838d4e125a0e07efde03af94b37bd4b767aeade9d1cd4054c13a6b","sha256:64bb1313326db2302eeb86a09c31ab75157a04c5ed6958618aba5a40e679dd91"],"state_sha256":"caa39b6ec5bbdb121fb3334212a00f088e40e7e82f8c37f454d87e249179e6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V2w3fTy2p8BMaFphW75r4XcmUAafUjsCiqmR9xqR50clLJ/etQwMRx3rCGEhG3LS6pkVaIJvW3cvlcrlzKT2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:40:19.839311Z","bundle_sha256":"1a4e435f6810d049b91bbf473bdcecbb441679a084d750412dad09f8196fb352"}}