{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PPFRUR3YKO2ZRSS262TGN5K7SG","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":"777d790cd6494a80964b8bfd0cb1e12487b214cca7352dd42eef904051423fec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-22T11:53:48Z","title_canon_sha256":"99a4fbae933c9f9535da37e922b77d8a5eaae116f859e533c1e7a06847100661"},"schema_version":"1.0","source":{"id":"2407.15902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15902","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15902v2","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15902","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_12","alias_value":"PPFRUR3YKO2Z","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_16","alias_value":"PPFRUR3YKO2ZRSS2","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_8","alias_value":"PPFRUR3Y","created_at":"2026-07-05T08:51:18Z"}],"graph_snapshots":[{"event_id":"sha256:dee59354858735ac40765d9b752d946452d1cbae7dffff6fa30e1372025d498c","target":"graph","created_at":"2026-07-05T08:51:18Z","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/2407.15902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over the past decade, adversarial training has emerged as one of the few reliable methods for enhancing model robustness against adversarial attacks [Szegedy et al., 2014, Madry et al., 2018, Xhonneux et al., 2024], while many alternative approaches have failed to withstand rigorous subsequent evaluations. Recently, an alternative defense mechanism, namely \"circuit breakers\" [Zou et al., 2024], has shown promising results for aligning LLMs. In this report, we show that the robustness claims of \"Improving Alignment and Robustness with Circuit Breakers\" against unconstraint continuous attacks in","authors_text":"Leo Schwinn, Simon Geisler","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-22T11:53:48Z","title":"Revisiting the Robust Alignment of Circuit Breakers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15902","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":"sha256:079a752db4085cf6f2c1a407187bb82fab8505a125def98a3cfbe365c54e6280","target":"record","created_at":"2026-07-05T08:51:18Z","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":"777d790cd6494a80964b8bfd0cb1e12487b214cca7352dd42eef904051423fec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-22T11:53:48Z","title_canon_sha256":"99a4fbae933c9f9535da37e922b77d8a5eaae116f859e533c1e7a06847100661"},"schema_version":"1.0","source":{"id":"2407.15902","kind":"arxiv","version":2}},"canonical_sha256":"7bcb1a477853b598ca5af6a666f55f91a48a0c24ad4f10b6f34f241cd313f9b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bcb1a477853b598ca5af6a666f55f91a48a0c24ad4f10b6f34f241cd313f9b9","first_computed_at":"2026-07-05T08:51:18.861936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:18.861936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r/FQVNdhK/2xonVxeHmaT1mhl/6Y2iCy/hhGDXDufmW17MGwC3maTap9Jv52WFo4kFMw8MVnzwbhAfOmc5fiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:18.862409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:079a752db4085cf6f2c1a407187bb82fab8505a125def98a3cfbe365c54e6280","sha256:dee59354858735ac40765d9b752d946452d1cbae7dffff6fa30e1372025d498c"],"state_sha256":"637040c0e7a6dc0efd29113b87c7873e9b298a7e343ada7b40c246d4ecadeb08"}