{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJBIMEI5YABHOW2SGCOXL3SNGQ","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":"d9a6d7d17e3040f87db689ae7f6f23b7ab9e6728a276d22c543915c4266007a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T22:06:25Z","title_canon_sha256":"33e7092ea5564dde55374db94fb758991e1a2714ff9114ae5960a148de85b09a"},"schema_version":"1.0","source":{"id":"2502.07985","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07985","created_at":"2026-07-05T10:45:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07985v2","created_at":"2026-07-05T10:45:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07985","created_at":"2026-07-05T10:45:17Z"},{"alias_kind":"pith_short_12","alias_value":"SJBIMEI5YABH","created_at":"2026-07-05T10:45:17Z"},{"alias_kind":"pith_short_16","alias_value":"SJBIMEI5YABHOW2S","created_at":"2026-07-05T10:45:17Z"},{"alias_kind":"pith_short_8","alias_value":"SJBIMEI5","created_at":"2026-07-05T10:45:17Z"}],"graph_snapshots":[{"event_id":"sha256:b23157299e2b5b85a06433a756ab94da955a165d9b1e3c22fd86efbb520fbdc3","target":"graph","created_at":"2026-07-05T10:45:17Z","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/2502.07985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique mechanism that iteratively updates safety prompts-termed specifications-to drive the critique and revision process adaptively. This test-time optimization not only improves performance against adversarial jailbreak requests but also in diverse general safety-related tasks, such as avoiding moral harm or pursuing honest responses. Our empirical evaluations ac","authors_text":"V\\'ictor Gallego","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T22:06:25Z","title":"MetaSC: Test-Time Safety Specification Optimization for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07985","kind":"arxiv","version":2},"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:a6e8bccf3a06d8100365b832ffc6f5bf1d883af4145f342b99dbb2920b69b9c2","target":"record","created_at":"2026-07-05T10:45:17Z","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":"d9a6d7d17e3040f87db689ae7f6f23b7ab9e6728a276d22c543915c4266007a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T22:06:25Z","title_canon_sha256":"33e7092ea5564dde55374db94fb758991e1a2714ff9114ae5960a148de85b09a"},"schema_version":"1.0","source":{"id":"2502.07985","kind":"arxiv","version":2}},"canonical_sha256":"924286111dc002775b52309d75ee4d34168df56cd4090a9229ce8ca20661ab87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"924286111dc002775b52309d75ee4d34168df56cd4090a9229ce8ca20661ab87","first_computed_at":"2026-07-05T10:45:17.167145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:17.167145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9olHIFj61uHbuzCsZ3/Wx1swMmSXpQABtvPvbOPOUK0Ae5SX1P8qm8c8eKn8wXE3DX/GKKBif+i6g5TA7+nqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:17.167712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07985","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6e8bccf3a06d8100365b832ffc6f5bf1d883af4145f342b99dbb2920b69b9c2","sha256:b23157299e2b5b85a06433a756ab94da955a165d9b1e3c22fd86efbb520fbdc3"],"state_sha256":"45d50ff26a34d2dcf917162c0c9caff83fe5ade6dd8a3dcaabe0a6157fec7b2e"}