{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KNNMMJA3QS2RAP3GTSEGSIVCEA","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":"91f42372fb8ea5bb2d93a6b7d3078b91431edb99fcd1b257e7d61365c2b11b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:35:31Z","title_canon_sha256":"ec2827f55f599e738f876d9e31f5d40498e77d532e08df66f41bd5c644f2c011"},"schema_version":"1.0","source":{"id":"2306.09200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09200","created_at":"2026-07-05T07:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09200v2","created_at":"2026-07-05T07:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09200","created_at":"2026-07-05T07:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"KNNMMJA3QS2R","created_at":"2026-07-05T07:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"KNNMMJA3QS2RAP3G","created_at":"2026-07-05T07:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"KNNMMJA3","created_at":"2026-07-05T07:26:55Z"}],"graph_snapshots":[{"event_id":"sha256:d8ff366f8eb4be4bf8d27bde8046ad6f933800638762ed3aa06792e76c6df658","target":"graph","created_at":"2026-07-05T07:26:55Z","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/2306.09200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the invaluable thought process or strategic considerations. Despite this, the majority of preceding research focuses on only one source: they either use historical replay exclusively to directly learn policy or value functions, or engaged in language model training utilizing mere language corpus. In this paper, we argue that a powerful autonomous agent s","authors_text":"David Mguni, Hongrui Tang, Jun Wang, Kun Shao, Mengyue Yang, Xidong Feng, Yali Du, Yicheng Luo, Ziyan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:35:31Z","title":"ChessGPT: Bridging Policy Learning and Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09200","kind":"arxiv","version":2},"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:ecdc23e76226557a2467ee446a7b4b30768d5d7f65cbf7d164a88103528faa8b","target":"record","created_at":"2026-07-05T07:26:55Z","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":"91f42372fb8ea5bb2d93a6b7d3078b91431edb99fcd1b257e7d61365c2b11b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:35:31Z","title_canon_sha256":"ec2827f55f599e738f876d9e31f5d40498e77d532e08df66f41bd5c644f2c011"},"schema_version":"1.0","source":{"id":"2306.09200","kind":"arxiv","version":2}},"canonical_sha256":"535ac6241b84b5103f669c886922a22010256a67634861b52fee5094137e4103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"535ac6241b84b5103f669c886922a22010256a67634861b52fee5094137e4103","first_computed_at":"2026-07-05T07:26:55.478846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:55.478846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5i5uBgyk58RORUJNNm5BvO/CyzjFMCGCG7/k3JNGCbaFm2tIHrdJzahgXaotH9yB6GGXeqCTz+FTE5reQUgWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:55.479397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecdc23e76226557a2467ee446a7b4b30768d5d7f65cbf7d164a88103528faa8b","sha256:d8ff366f8eb4be4bf8d27bde8046ad6f933800638762ed3aa06792e76c6df658"],"state_sha256":"05a8539e41864ab8e4040d73f9768c954c91c7bc89bb2b5284d658647f92680c"}