{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:25F6FDL3KHXNTWCRSRLRQLZZDR","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":"30f8c7f789c43f451eaeef6b153562cde590d32b0fd4909de5031927f6ff95ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T03:15:55Z","title_canon_sha256":"61fc320e7496eb1eb88d7d54ad80a76140f753600db3f1da6f159960318fcd17"},"schema_version":"1.0","source":{"id":"2502.12486","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12486","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12486v6","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12486","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"25F6FDL3KHXN","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"25F6FDL3KHXNTWCR","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"25F6FDL3","created_at":"2026-07-05T11:10:52Z"}],"graph_snapshots":[{"event_id":"sha256:bcf3022efcbc316b8d04822ede21a7bffcc2373ad48d9be17cf8d024fb6249ca","target":"graph","created_at":"2026-07-05T11:10:52Z","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/2502.12486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business negotiations, which require strategic reasoning-an ability to navigate dynamic environments and align long-term goals amidst uncertainty. Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts. To address these issues, we propose explicit policy optimization (EPO) for strategic reasoning, feat","authors_text":"Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang, Ke Wang, Wentao Ma, Xiaoqian Liu, Yongbin Li, Yuchuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T03:15:55Z","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12486","kind":"arxiv","version":6},"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:e8fd887923dcbac122a95ef99dd8d38257ebb76bcabce57b1b9f318cb0ae6784","target":"record","created_at":"2026-07-05T11:10:52Z","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":"30f8c7f789c43f451eaeef6b153562cde590d32b0fd4909de5031927f6ff95ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T03:15:55Z","title_canon_sha256":"61fc320e7496eb1eb88d7d54ad80a76140f753600db3f1da6f159960318fcd17"},"schema_version":"1.0","source":{"id":"2502.12486","kind":"arxiv","version":6}},"canonical_sha256":"d74be28d7b51eed9d8519457182f391c587adf3e04de16054b2e997cf8580cb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d74be28d7b51eed9d8519457182f391c587adf3e04de16054b2e997cf8580cb2","first_computed_at":"2026-07-05T11:10:52.879350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:52.879350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxUC+MKf/Q7M1U6nSBW5CAm04ojHUev4c43f3utuRrYMt0K9QJq6vdUI3PClhSAKCuHD6xPTtMn17k1VnxsTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:52.879869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12486","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8fd887923dcbac122a95ef99dd8d38257ebb76bcabce57b1b9f318cb0ae6784","sha256:bcf3022efcbc316b8d04822ede21a7bffcc2373ad48d9be17cf8d024fb6249ca"],"state_sha256":"ea096aea85d35ce9495dfa060b153faae998bd50b2dadc4e374c4707e381bad7"}