{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PNUYYMIK4M55GWW6A7DFNCTEXN","short_pith_number":"pith:PNUYYMIK","schema_version":"1.0","canonical_sha256":"7b698c310ae33bd35ade07c6568a64bb55604d55815a2d726207f84859648869","source":{"kind":"arxiv","id":"2410.04045","version":1},"attestation_state":"computed","paper":{"title":"Neuron-Level Sequential Editing for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"An Zhang, Houcheng Jiang, Junfeng Fang, Ruipeng Wang, Tao Liang, Tianyu Zhang, Xiang Wang","submitted_at":"2024-10-05T05:52:22Z","abstract_excerpt":"This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to adjust the model outputs without the need for costly retraining. Existing model editing methods, especially those that alter model parameters, typically focus on single-round editing and often face significant challenges in sequential model editing-most notably issues of model forgetting and failure. To address these challenges, we introduce a new model editing m"},"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":"2410.04045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T05:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"d9b85070cc5edca6622912ba2e3d48fa97661db22751a4431b2d8bec44c6a012","abstract_canon_sha256":"1a3c3a3ef719bed85f554fda9f3ca899eacb2090d502f52a4dbddd6e579eac06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:28.325190Z","signature_b64":"oQR0xbCJEr7yh7cw9VF7qMEUVnE35NUkjDKhgLWGfHoai0wbKyNfL51HnUgF6bHC6rXvDTqMwPHRoRBsRFhpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b698c310ae33bd35ade07c6568a64bb55604d55815a2d726207f84859648869","last_reissued_at":"2026-07-05T09:16:28.324615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:28.324615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuron-Level Sequential Editing for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"An Zhang, Houcheng Jiang, Junfeng Fang, Ruipeng Wang, Tao Liang, Tianyu Zhang, Xiang Wang","submitted_at":"2024-10-05T05:52:22Z","abstract_excerpt":"This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to adjust the model outputs without the need for costly retraining. Existing model editing methods, especially those that alter model parameters, typically focus on single-round editing and often face significant challenges in sequential model editing-most notably issues of model forgetting and failure. To address these challenges, we introduce a new model editing m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04045","kind":"arxiv","version":1},"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/2410.04045/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":"2410.04045","created_at":"2026-07-05T09:16:28.324679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04045v1","created_at":"2026-07-05T09:16:28.324679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04045","created_at":"2026-07-05T09:16:28.324679+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNUYYMIK4M55","created_at":"2026-07-05T09:16:28.324679+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNUYYMIK4M55GWW6","created_at":"2026-07-05T09:16:28.324679+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNUYYMIK","created_at":"2026-07-05T09:16:28.324679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15053","citing_title":"TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN","json":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN.json","graph_json":"https://pith.science/api/pith-number/PNUYYMIK4M55GWW6A7DFNCTEXN/graph.json","events_json":"https://pith.science/api/pith-number/PNUYYMIK4M55GWW6A7DFNCTEXN/events.json","paper":"https://pith.science/paper/PNUYYMIK"},"agent_actions":{"view_html":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN","download_json":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN.json","view_paper":"https://pith.science/paper/PNUYYMIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04045&json=true","fetch_graph":"https://pith.science/api/pith-number/PNUYYMIK4M55GWW6A7DFNCTEXN/graph.json","fetch_events":"https://pith.science/api/pith-number/PNUYYMIK4M55GWW6A7DFNCTEXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN/action/storage_attestation","attest_author":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN/action/author_attestation","sign_citation":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN/action/citation_signature","submit_replication":"https://pith.science/pith/PNUYYMIK4M55GWW6A7DFNCTEXN/action/replication_record"}},"created_at":"2026-07-05T09:16:28.324679+00:00","updated_at":"2026-07-05T09:16:28.324679+00:00"}