{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6TXOE3XLHM6RCFWK2SWXF75V64","short_pith_number":"pith:6TXOE3XL","schema_version":"1.0","canonical_sha256":"f4eee26eeb3b3d1116cad4ad72ffb5f724b186f9ccfee83c601eeabd899eba76","source":{"kind":"arxiv","id":"2505.23026","version":2},"attestation_state":"computed","paper":{"title":"Context-Robust Knowledge Editing for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gyubin Choi, Haewon Park, Minjun Kim, Yohan Jo","submitted_at":"2025-05-29T03:11:53Z","abstract_excerpt":"Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In real-world applications, however, preceding contexts often trigger the retrieval of the original knowledge and undermine the intended edit. To address this issue, we develop CHED -- a benchmark designed to evaluate the context robustness of KE methods. Evaluations on CHED show that they often fail when preceding contexts are present. To mitigate this shortcoming, we"},"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":"2505.23026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T03:11:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c96f6541031924a771a95fb4d43f261ca1fc39f020ed52dcd7efc0b21b749e46","abstract_canon_sha256":"a1be5f5f368651a8b937334432ae3008bd2517ab6b864baa7f98fabac139a8c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.661150Z","signature_b64":"VlcgX4cZLdbGc73Pf0q+1Nv0FkkhHKGUWTdsSKU9zMsASjQnkhWrq9I/ekkZMCSGeJCnW7BhFlaTL4GnqgG2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4eee26eeb3b3d1116cad4ad72ffb5f724b186f9ccfee83c601eeabd899eba76","last_reissued_at":"2026-07-05T11:13:27.660693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.660693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Robust Knowledge Editing for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gyubin Choi, Haewon Park, Minjun Kim, Yohan Jo","submitted_at":"2025-05-29T03:11:53Z","abstract_excerpt":"Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In real-world applications, however, preceding contexts often trigger the retrieval of the original knowledge and undermine the intended edit. To address this issue, we develop CHED -- a benchmark designed to evaluate the context robustness of KE methods. Evaluations on CHED show that they often fail when preceding contexts are present. To mitigate this shortcoming, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23026","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/2505.23026/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":"2505.23026","created_at":"2026-07-05T11:13:27.660751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23026v2","created_at":"2026-07-05T11:13:27.660751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23026","created_at":"2026-07-05T11:13:27.660751+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TXOE3XLHM6R","created_at":"2026-07-05T11:13:27.660751+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TXOE3XLHM6RCFWK","created_at":"2026-07-05T11:13:27.660751+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TXOE3XL","created_at":"2026-07-05T11:13:27.660751+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/6TXOE3XLHM6RCFWK2SWXF75V64","json":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64.json","graph_json":"https://pith.science/api/pith-number/6TXOE3XLHM6RCFWK2SWXF75V64/graph.json","events_json":"https://pith.science/api/pith-number/6TXOE3XLHM6RCFWK2SWXF75V64/events.json","paper":"https://pith.science/paper/6TXOE3XL"},"agent_actions":{"view_html":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64","download_json":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64.json","view_paper":"https://pith.science/paper/6TXOE3XL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23026&json=true","fetch_graph":"https://pith.science/api/pith-number/6TXOE3XLHM6RCFWK2SWXF75V64/graph.json","fetch_events":"https://pith.science/api/pith-number/6TXOE3XLHM6RCFWK2SWXF75V64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64/action/storage_attestation","attest_author":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64/action/author_attestation","sign_citation":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64/action/citation_signature","submit_replication":"https://pith.science/pith/6TXOE3XLHM6RCFWK2SWXF75V64/action/replication_record"}},"created_at":"2026-07-05T11:13:27.660751+00:00","updated_at":"2026-07-05T11:13:27.660751+00:00"}