{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:52EWH7FMUZYBHG7IWZRHFDLM2T","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":"5358a946ab98a68b6a5a4802b95de0c380d32fd5b19fa10e1434e087b80e25fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T15:42:12Z","title_canon_sha256":"3ad32e20b397968ba331d162e9c70d44bd6af9ca391af9fdfe7fe0ba2a3f1536"},"schema_version":"1.0","source":{"id":"2402.15390","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15390","created_at":"2026-07-05T10:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15390v2","created_at":"2026-07-05T10:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15390","created_at":"2026-07-05T10:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"52EWH7FMUZYB","created_at":"2026-07-05T10:48:56Z"},{"alias_kind":"pith_short_16","alias_value":"52EWH7FMUZYBHG7I","created_at":"2026-07-05T10:48:56Z"},{"alias_kind":"pith_short_8","alias_value":"52EWH7FM","created_at":"2026-07-05T10:48:56Z"}],"graph_snapshots":[{"event_id":"sha256:1b8b8f1fd920c4d7282285171ce0051aa35b94679536cad85304164db2489a75","target":"graph","created_at":"2026-07-05T10:48:56Z","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/2402.15390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior interpretability research studying narrow distributions has preliminarily identified self-repair, a phenomena where if components in large language models are ablated, later components will change their behavior to compensate. Our work builds off this past literature, demonstrating that self-repair exists on a variety of models families and sizes when ablating individual attention heads on the full training distribution. We further show that on the full training distribution self-repair is imperfect, as the original direct effect of the head is not fully restored, and noisy, since the de","authors_text":"Cody Rushing, Neel Nanda","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T15:42:12Z","title":"Explorations of Self-Repair in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15390","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":"sha256:9945a21014c7f29d026c5ec03c47cae1e7f519c5e5dff618f42af58adcbe3de0","target":"record","created_at":"2026-07-05T10:48:56Z","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":"5358a946ab98a68b6a5a4802b95de0c380d32fd5b19fa10e1434e087b80e25fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T15:42:12Z","title_canon_sha256":"3ad32e20b397968ba331d162e9c70d44bd6af9ca391af9fdfe7fe0ba2a3f1536"},"schema_version":"1.0","source":{"id":"2402.15390","kind":"arxiv","version":2}},"canonical_sha256":"ee8963fcaca670139be8b662728d6cd4d6807d289dbbb0f1fd14075a99ce7e8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee8963fcaca670139be8b662728d6cd4d6807d289dbbb0f1fd14075a99ce7e8a","first_computed_at":"2026-07-05T10:48:56.925818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:56.925818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Q0LbJ1rEQXogONj4XZeqdHHLaeqjhr2zTtDSSBWN1ICggbsZuVKlpMdKFb08QF/2KHuuM5aNtup2jBI8IwmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:56.926280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15390","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9945a21014c7f29d026c5ec03c47cae1e7f519c5e5dff618f42af58adcbe3de0","sha256:1b8b8f1fd920c4d7282285171ce0051aa35b94679536cad85304164db2489a75"],"state_sha256":"45dab88f4a5611f871bd37d27af7c3bddca41b1efc92c3ed9580589e545f93e9"}