{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C64P3BJPUXBNCGCLOCUJOW4YTE","short_pith_number":"pith:C64P3BJP","canonical_record":{"source":{"id":"2410.12949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:35:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b58d963d4120eb8def750f28457c98846b8d7c49906d467fc64070acad268d96","abstract_canon_sha256":"b228380560dbe52dd888a4f141e74e41060c8940075811d7f0021d1e3e781e55"},"schema_version":"1.0"},"canonical_sha256":"17b8fd852fa5c2d1184b70a8975b98990ce7851c2932ff9a46980e2ed608f1e9","source":{"kind":"arxiv","id":"2410.12949","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12949","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12949v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12949","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"C64P3BJPUXBN","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"C64P3BJPUXBNCGCL","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"C64P3BJP","created_at":"2026-07-05T09:44:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C64P3BJPUXBNCGCLOCUJOW4YTE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:35:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b58d963d4120eb8def750f28457c98846b8d7c49906d467fc64070acad268d96","abstract_canon_sha256":"b228380560dbe52dd888a4f141e74e41060c8940075811d7f0021d1e3e781e55"},"schema_version":"1.0"},"canonical_sha256":"17b8fd852fa5c2d1184b70a8975b98990ce7851c2932ff9a46980e2ed608f1e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:36.300965Z","signature_b64":"pKM/eW1pn2fe96pkfW5uEB46cyAtUNDxfp9MW7jmvozl4KP62uIIQPvkkgiMcLDhwfpx5OF942eu4VdB2rYJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17b8fd852fa5c2d1184b70a8975b98990ce7851c2932ff9a46980e2ed608f1e9","last_reissued_at":"2026-07-05T09:44:36.300467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:36.300467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12949","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pCU4rCfaoBFkjuBCPMRQHHCFB5CGCHD/42exNunh/LsEt/mdMlBB43Th/kzNuHyg0N856naoRz4+ch7aXLmQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:51:22.207947Z"},"content_sha256":"f215f8fb727437908f0ed79149e693f9445770bef6b35d8afcb268c6af919f3c","schema_version":"1.0","event_id":"sha256:f215f8fb727437908f0ed79149e693f9445770bef6b35d8afcb268c6af919f3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C64P3BJPUXBNCGCLOCUJOW4YTE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite, Phillip Guo","submitted_at":"2024-10-16T18:35:02Z","abstract_excerpt":"Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic interpretability -- which, in part, aims to identify model components (circuits) associated to specific interpretable mechanisms that make up a model capability -- can improve the precision and effectiveness of editing and unlearning. We find a stark difference in unlearning and edit robustness when training components localized by different methods. We highlight an i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12949","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.12949/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kvS68hg9uLduqAInb8iFdlZaUwH8DQDUEg8uKlRiRyyS+nFxm3M7VoSVAMa+Tg2R0o/TxVAtXZ7krQa6idOrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:51:22.208445Z"},"content_sha256":"4ade2b3f446f4762e3f08ec4548a54cb80b71f9e14fbefcc27854e5ff30a0f06","schema_version":"1.0","event_id":"sha256:4ade2b3f446f4762e3f08ec4548a54cb80b71f9e14fbefcc27854e5ff30a0f06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/bundle.json","state_url":"https://pith.science/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T07:51:22Z","links":{"resolver":"https://pith.science/pith/C64P3BJPUXBNCGCLOCUJOW4YTE","bundle":"https://pith.science/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/bundle.json","state":"https://pith.science/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C64P3BJPUXBNCGCLOCUJOW4YTE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C64P3BJPUXBNCGCLOCUJOW4YTE","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":"b228380560dbe52dd888a4f141e74e41060c8940075811d7f0021d1e3e781e55","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:35:02Z","title_canon_sha256":"b58d963d4120eb8def750f28457c98846b8d7c49906d467fc64070acad268d96"},"schema_version":"1.0","source":{"id":"2410.12949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12949","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12949v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12949","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"C64P3BJPUXBN","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"C64P3BJPUXBNCGCL","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"C64P3BJP","created_at":"2026-07-05T09:44:36Z"}],"graph_snapshots":[{"event_id":"sha256:4ade2b3f446f4762e3f08ec4548a54cb80b71f9e14fbefcc27854e5ff30a0f06","target":"graph","created_at":"2026-07-05T09:44:36Z","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/2410.12949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic interpretability -- which, in part, aims to identify model components (circuits) associated to specific interpretable mechanisms that make up a model capability -- can improve the precision and effectiveness of editing and unlearning. We find a stark difference in unlearning and edit robustness when training components localized by different methods. We highlight an i","authors_text":"Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite, Phillip Guo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:35:02Z","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12949","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:f215f8fb727437908f0ed79149e693f9445770bef6b35d8afcb268c6af919f3c","target":"record","created_at":"2026-07-05T09:44:36Z","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":"b228380560dbe52dd888a4f141e74e41060c8940075811d7f0021d1e3e781e55","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:35:02Z","title_canon_sha256":"b58d963d4120eb8def750f28457c98846b8d7c49906d467fc64070acad268d96"},"schema_version":"1.0","source":{"id":"2410.12949","kind":"arxiv","version":2}},"canonical_sha256":"17b8fd852fa5c2d1184b70a8975b98990ce7851c2932ff9a46980e2ed608f1e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17b8fd852fa5c2d1184b70a8975b98990ce7851c2932ff9a46980e2ed608f1e9","first_computed_at":"2026-07-05T09:44:36.300467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:36.300467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKM/eW1pn2fe96pkfW5uEB46cyAtUNDxfp9MW7jmvozl4KP62uIIQPvkkgiMcLDhwfpx5OF942eu4VdB2rYJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:36.300965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f215f8fb727437908f0ed79149e693f9445770bef6b35d8afcb268c6af919f3c","sha256:4ade2b3f446f4762e3f08ec4548a54cb80b71f9e14fbefcc27854e5ff30a0f06"],"state_sha256":"a0e36ab98156ce35f9cb0d34a4cb9481933da0b0d9ea7bc96cf259db5b450bdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysFdi+LTofuPtPaYz1zJG9FYR7HSWUtb3pxy2Ex1lWP4AcBvHesGEOGTEGd7U+PCrCe3pXQK2Af8TrgqG1KwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:51:22.212730Z","bundle_sha256":"f68f9424771156ec7f7e6d8b76adb196d302e1f53bd185fb41e7aef764944cea"}}