{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QH7YROHDI2KMERXY4PYAQHNO55","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b6f65e463bca20fe0863be78ebdfc87bf6ea164b79f3dc0b0e861e5c86b2bbd6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T05:22:21Z","title_canon_sha256":"791a64563c30c11b64e7f92290ffdd42e1b9676b2f69028b4f8ab1c60858fdec"},"schema_version":"1.0","source":{"id":"2605.19377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19377","created_at":"2026-05-20T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19377v1","created_at":"2026-05-20T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19377","created_at":"2026-05-20T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"QH7YROHDI2KM","created_at":"2026-05-20T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"QH7YROHDI2KMERXY","created_at":"2026-05-20T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"QH7YROHD","created_at":"2026-05-20T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:f7c934182bca362d1769381f78fc3b6e5ebdf6a98dac3f1cf9fb423f4dc89293","target":"graph","created_at":"2026-05-20T01:05:42Z","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/2605.19377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasingly rely on fine-tuning as a defensive strategy. Yet the theoretical foundations underlying this robustness fine-tuning remain underexplored. We introduce a game-theoretic framework in which the interaction between an evaluator (auditing the model for jailbreaks) and a trainer is formalized as a two-player game.\n  A key feature of our approach is the use of group actions, a mathematical structure that captures symmetries and transformations, to ","authors_text":"Anne-Marie Kermarrec, Jade Garcia-Bourr\\'ee, Paul Wang, Vincent Corruble","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T05:22:21Z","title":"The Evaluation Game: Beyond Static LLM Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19377","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":"sha256:6594a1520351cb6a90b38c424b29964aa76e5d683e63b0a98bde57b442009204","target":"record","created_at":"2026-05-20T01:05:42Z","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":"b6f65e463bca20fe0863be78ebdfc87bf6ea164b79f3dc0b0e861e5c86b2bbd6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T05:22:21Z","title_canon_sha256":"791a64563c30c11b64e7f92290ffdd42e1b9676b2f69028b4f8ab1c60858fdec"},"schema_version":"1.0","source":{"id":"2605.19377","kind":"arxiv","version":1}},"canonical_sha256":"81ff88b8e34694c246f8e3f0081daeef5fe2efa4d845dcff0e40a84d584490f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81ff88b8e34694c246f8e3f0081daeef5fe2efa4d845dcff0e40a84d584490f7","first_computed_at":"2026-05-20T01:05:42.626912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:42.626912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DggC+3UvEiqPx+6IsfbYW8Z8bZj1FiMTEy5JIa9OWH8SYFWLIOZABFXBSLINBq1Shu0IjOHhMoQupl1bzFObCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:42.627597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6594a1520351cb6a90b38c424b29964aa76e5d683e63b0a98bde57b442009204","sha256:f7c934182bca362d1769381f78fc3b6e5ebdf6a98dac3f1cf9fb423f4dc89293","sha256:9aa5ddef07190eee37c0abfd2de94a6d9352469167c7845d3c5911b7c3468653"],"state_sha256":"17f9be9ea0519a4da53fa274a22c9f3571692c8ea6f8ac47ccd8d17ecc483f96"}