{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YI2NDVY7AKIQCSEHIVQZUFVEWZ","short_pith_number":"pith:YI2NDVY7","schema_version":"1.0","canonical_sha256":"c234d1d71f029101488745619a16a4b674dc86486f14aab402a5760d64279b2b","source":{"kind":"arxiv","id":"2412.13341","version":2},"attestation_state":"computed","paper":{"title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"David Shriver, Keltin Grimes, Marco Christiani, Marissa Connor","submitted_at":"2024-12-17T21:29:30Z","abstract_excerpt":"Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications such as inserting misinformation or simple trojans that result in adversary-specified behaviors when a trigger word is present. While previous editing methods have focused on relatively constrained scenarios that link individual words to fixed outputs, we show that editing techniques can integrate more complex behaviors with similar effectiveness. We develop Concept-ROT, a mod"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.13341","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:29:30Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"d2d7ca03eb9dc760f89ff0112e1b7809a199bfbedc08db1740881e956076c53f","abstract_canon_sha256":"1d6f6058adf383003f5774f9114750efb375ce6847ec9c0d9620049bf371440a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:11.583260Z","signature_b64":"A2TsVUJWig80ljHFL3Aw6SmJX3pWjpc8oT6InUPchjADnjuovTaQ1ua2wth5igTcYHD6eFVZLF7zbhKxfS+1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c234d1d71f029101488745619a16a4b674dc86486f14aab402a5760d64279b2b","last_reissued_at":"2026-07-05T12:05:11.582727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:11.582727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"David Shriver, Keltin Grimes, Marco Christiani, Marissa Connor","submitted_at":"2024-12-17T21:29:30Z","abstract_excerpt":"Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications such as inserting misinformation or simple trojans that result in adversary-specified behaviors when a trigger word is present. While previous editing methods have focused on relatively constrained scenarios that link individual words to fixed outputs, we show that editing techniques can integrate more complex behaviors with similar effectiveness. We develop Concept-ROT, a mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13341","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/2412.13341/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.13341","created_at":"2026-07-05T12:05:11.582824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13341v2","created_at":"2026-07-05T12:05:11.582824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13341","created_at":"2026-07-05T12:05:11.582824+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI2NDVY7AKIQ","created_at":"2026-07-05T12:05:11.582824+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI2NDVY7AKIQCSEH","created_at":"2026-07-05T12:05:11.582824+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI2NDVY7","created_at":"2026-07-05T12:05:11.582824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ","json":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ.json","graph_json":"https://pith.science/api/pith-number/YI2NDVY7AKIQCSEHIVQZUFVEWZ/graph.json","events_json":"https://pith.science/api/pith-number/YI2NDVY7AKIQCSEHIVQZUFVEWZ/events.json","paper":"https://pith.science/paper/YI2NDVY7"},"agent_actions":{"view_html":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ","download_json":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ.json","view_paper":"https://pith.science/paper/YI2NDVY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13341&json=true","fetch_graph":"https://pith.science/api/pith-number/YI2NDVY7AKIQCSEHIVQZUFVEWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YI2NDVY7AKIQCSEHIVQZUFVEWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ/action/storage_attestation","attest_author":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ/action/author_attestation","sign_citation":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ/action/citation_signature","submit_replication":"https://pith.science/pith/YI2NDVY7AKIQCSEHIVQZUFVEWZ/action/replication_record"}},"created_at":"2026-07-05T12:05:11.582824+00:00","updated_at":"2026-07-05T12:05:11.582824+00:00"}