{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HT4L5CF2RXGKZJ5V275S3B26ID","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":"21a3fd2105f892ad71593d5fce318ca63f022c90f7c5d644e830b292a503fa88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-23T22:13:14Z","title_canon_sha256":"937ce726892f083bd9013aefa1ddfb1278bbb94d89d7242eea43ad75cf3ee50c"},"schema_version":"1.0","source":{"id":"2512.20806","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.20806","created_at":"2026-06-02T02:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2512.20806v3","created_at":"2026-06-02T02:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.20806","created_at":"2026-06-02T02:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"HT4L5CF2RXGK","created_at":"2026-06-02T02:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"HT4L5CF2RXGKZJ5V","created_at":"2026-06-02T02:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"HT4L5CF2","created_at":"2026-06-02T02:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:e4d71d630dc80a4754b9700091d0b16d490f947d7ebc097123fe9709f6f550f8","target":"graph","created_at":"2026-06-02T02:04:12Z","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/2512.20806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwis","authors_text":"Anselm Paulus, Arman Zharmagambetov, Brandon Amos, Ilia Kulikov, Ivan Evtimov, Kamalika Chaudhuri, R\\'emi Munos","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-23T22:13:14Z","title":"Safety Alignment of LMs via Non-cooperative Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.20806","kind":"arxiv","version":3},"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":"sha256:4299075d0b50f5b29714ce91f66b21bad3c2a690c712ae897be4d3a86bd55c8d","target":"record","created_at":"2026-06-02T02:04:12Z","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":"21a3fd2105f892ad71593d5fce318ca63f022c90f7c5d644e830b292a503fa88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-23T22:13:14Z","title_canon_sha256":"937ce726892f083bd9013aefa1ddfb1278bbb94d89d7242eea43ad75cf3ee50c"},"schema_version":"1.0","source":{"id":"2512.20806","kind":"arxiv","version":3}},"canonical_sha256":"3cf8be88ba8dccaca7b5d7fb2d875e40c14dde51753bdf4e2f008febe1ca32f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf8be88ba8dccaca7b5d7fb2d875e40c14dde51753bdf4e2f008febe1ca32f0","first_computed_at":"2026-06-02T02:04:12.669805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:12.669805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qgFhGHlzH7lkJu/4OHLq+A0GWk4jIQDeaIzcdL00zsfKABLtKaYxgLiiCrVgxiPjewH9oiGgGQborCprOxIhBg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:12.670311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.20806","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4299075d0b50f5b29714ce91f66b21bad3c2a690c712ae897be4d3a86bd55c8d","sha256:e4d71d630dc80a4754b9700091d0b16d490f947d7ebc097123fe9709f6f550f8"],"state_sha256":"f3e507d87f99cf3125e715fbf706ae2029e3eb69614872cbdc36f9583e9578e6"}