{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:25FCK7VRDCBUS4TUJZ6OCCHQUM","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":"e19fe3ba2614c6703175f1dcd0e89570edb12f5ea12475bb049291331bc66cd4","cross_cats_sorted":["cs.CL","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T14:22:40Z","title_canon_sha256":"71cc0182dd17ddea507a19b74481635cdad52bee74023f190ed1b59bf6ad13cb"},"schema_version":"1.0","source":{"id":"2506.00577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00577","created_at":"2026-07-05T11:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00577v1","created_at":"2026-07-05T11:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00577","created_at":"2026-07-05T11:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"25FCK7VRDCBU","created_at":"2026-07-05T11:13:37Z"},{"alias_kind":"pith_short_16","alias_value":"25FCK7VRDCBUS4TU","created_at":"2026-07-05T11:13:37Z"},{"alias_kind":"pith_short_8","alias_value":"25FCK7VR","created_at":"2026-07-05T11:13:37Z"}],"graph_snapshots":[{"event_id":"sha256:3e2641e46f838a1ce2ae9526f40e1699683b9eb267104e6098205a9a76e7d7e6","target":"graph","created_at":"2026-07-05T11:13:37Z","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/2506.00577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real","authors_text":"Dayiheng Liu, Kexin Yang, Linfeng Zhang, Shaobo Wang, Xiangqi Jin, Xingyu Dong, Xingzhang Ren, Yifang Chen, Yue Min, Yufa Zhou","cross_cats":["cs.CL","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T14:22:40Z","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00577","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:ccb4aa4878b387d20ca57c35354ebf26249952b1ce60b05db315a257fd7d561d","target":"record","created_at":"2026-07-05T11:13:37Z","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":"e19fe3ba2614c6703175f1dcd0e89570edb12f5ea12475bb049291331bc66cd4","cross_cats_sorted":["cs.CL","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T14:22:40Z","title_canon_sha256":"71cc0182dd17ddea507a19b74481635cdad52bee74023f190ed1b59bf6ad13cb"},"schema_version":"1.0","source":{"id":"2506.00577","kind":"arxiv","version":1}},"canonical_sha256":"d74a257eb118834972744e7ce108f0a30b70d6b6cdd929b337127a7779b939ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d74a257eb118834972744e7ce108f0a30b70d6b6cdd929b337127a7779b939ad","first_computed_at":"2026-07-05T11:13:37.260087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:37.260087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XjrEimTFvTk2N8cqfzprBtuMhu+YUeXpvTT0MSbctwJDMsXfe27MNWudKwwEkm+eewVUzA0sSg81D5QLeguXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:37.260593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccb4aa4878b387d20ca57c35354ebf26249952b1ce60b05db315a257fd7d561d","sha256:3e2641e46f838a1ce2ae9526f40e1699683b9eb267104e6098205a9a76e7d7e6"],"state_sha256":"c90897ce3bcda92050ad34515fe6ea7144bc0b58c5292a549f7e79f5ec9f7455"}