{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EQ6MBZGBOY2G3L66RRSW4L7BGU","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":"e330dfef37c8f01bb5511ef0c0265018b818e6bc24935b34057f791b0ebbef58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-29T05:20:32Z","title_canon_sha256":"71c2f88dab5f28d9273d7a66cd3a43b4e7c0fcae94b1352510c7517fbcbfda34"},"schema_version":"1.0","source":{"id":"2605.30854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30854","created_at":"2026-06-01T01:03:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30854v1","created_at":"2026-06-01T01:03:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30854","created_at":"2026-06-01T01:03:21Z"},{"alias_kind":"pith_short_12","alias_value":"EQ6MBZGBOY2G","created_at":"2026-06-01T01:03:21Z"},{"alias_kind":"pith_short_16","alias_value":"EQ6MBZGBOY2G3L66","created_at":"2026-06-01T01:03:21Z"},{"alias_kind":"pith_short_8","alias_value":"EQ6MBZGB","created_at":"2026-06-01T01:03:21Z"}],"graph_snapshots":[{"event_id":"sha256:8de9d9949df2c84660997a68bfa779d997929450af1d973246037f3c8c67da33","target":"graph","created_at":"2026-06-01T01:03:21Z","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/2605.30854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these agents condition on natural language game-state descriptions and emit actions through free-form generation, strategic failure modes -- exploiting weaker opponents, coordinating on harmful equilibria, and externalizing costs are inseparable from the language interface itself. We propose Safe Equilibrium Policy Optimization (\\sepo{}), a training objective that augments expected payoff with explicit penalties for exploitability, collusion risk, and ext","authors_text":"Amit Dhanda, Karthika Arumugam, Kiran Kumar Manku","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-29T05:20:32Z","title":"Safe Equilibrium Policy Optimization for Strategic Agent Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30854","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":"sha256:98a55e0d8ef3284a8e3ff595e7334aca3301f24acc8d8b6914447abd9a2348a9","target":"record","created_at":"2026-06-01T01:03:21Z","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":"e330dfef37c8f01bb5511ef0c0265018b818e6bc24935b34057f791b0ebbef58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-29T05:20:32Z","title_canon_sha256":"71c2f88dab5f28d9273d7a66cd3a43b4e7c0fcae94b1352510c7517fbcbfda34"},"schema_version":"1.0","source":{"id":"2605.30854","kind":"arxiv","version":1}},"canonical_sha256":"243cc0e4c176346dafde8c656e2fe13532bb14690337a680085b01e880252983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"243cc0e4c176346dafde8c656e2fe13532bb14690337a680085b01e880252983","first_computed_at":"2026-06-01T01:03:21.146043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:21.146043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mWpbrwkD6a+8eouGGz7GUt8wZukrIj7Pl6uvj8tEqGA40ACoOUhIdcTlq0qksmmHcrTyBqiMTQNu/uf98gSKCQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:21.146781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98a55e0d8ef3284a8e3ff595e7334aca3301f24acc8d8b6914447abd9a2348a9","sha256:8de9d9949df2c84660997a68bfa779d997929450af1d973246037f3c8c67da33"],"state_sha256":"1c5576b1f1fc91aa61d1c09749ff66efa206403004a337160f1b6b737759607e"}