{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2KQFQMGSQWMKHS5HKNLEAUMPXP","short_pith_number":"pith:2KQFQMGS","schema_version":"1.0","canonical_sha256":"d2a05830d28598a3cba7535640518fbbde09fd11b74975e105760fa89fa00cb2","source":{"kind":"arxiv","id":"2506.00536","version":1},"attestation_state":"computed","paper":{"title":"Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyue Wang, Qingyao Ai, Weihang Su, Yiqun Liu, Yujia Zhou","submitted_at":"2025-05-31T12:51:12Z","abstract_excerpt":"Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by injecting new knowledge directly into the input context, leaving model parameters unchanged. However, existing ICE approaches do not explicitly separate the newly injected knowledge from the model's original reasoning process. This entanglement often results in conflicts between external updates and internal parametric knowledge, undermining the consistency and"},"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":"2506.00536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T12:51:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df1aba3132c684f759e14c7e971511f331559399f8b02f05337d7dc340aebc1c","abstract_canon_sha256":"3feb21f6993799fb24b8e3f37a852e9f715f560ff7abd519aae193905e09f415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:36.620932Z","signature_b64":"AB0sUJrYMkMKJaGa2YawMr0zOwyf7qdG76co3x3ZqWLEv/SLU3WZuSdwtgcV/lA0RpKhUrL5fY6SEaf9xnKYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a05830d28598a3cba7535640518fbbde09fd11b74975e105760fa89fa00cb2","last_reissued_at":"2026-07-05T11:13:36.620562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:36.620562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyue Wang, Qingyao Ai, Weihang Su, Yiqun Liu, Yujia Zhou","submitted_at":"2025-05-31T12:51:12Z","abstract_excerpt":"Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by injecting new knowledge directly into the input context, leaving model parameters unchanged. However, existing ICE approaches do not explicitly separate the newly injected knowledge from the model's original reasoning process. This entanglement often results in conflicts between external updates and internal parametric knowledge, undermining the consistency and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00536","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/2506.00536/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":"2506.00536","created_at":"2026-07-05T11:13:36.620623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00536v1","created_at":"2026-07-05T11:13:36.620623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00536","created_at":"2026-07-05T11:13:36.620623+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KQFQMGSQWMK","created_at":"2026-07-05T11:13:36.620623+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KQFQMGSQWMKHS5H","created_at":"2026-07-05T11:13:36.620623+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KQFQMGS","created_at":"2026-07-05T11:13:36.620623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22627","citing_title":"Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24894","citing_title":"RWGBench: Evaluating Scholarly Positioning in Related Work Generation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09285","citing_title":"BetaEdit: Null-Space Constrained Sequential Model Editing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02011","citing_title":"Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP","json":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP.json","graph_json":"https://pith.science/api/pith-number/2KQFQMGSQWMKHS5HKNLEAUMPXP/graph.json","events_json":"https://pith.science/api/pith-number/2KQFQMGSQWMKHS5HKNLEAUMPXP/events.json","paper":"https://pith.science/paper/2KQFQMGS"},"agent_actions":{"view_html":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP","download_json":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP.json","view_paper":"https://pith.science/paper/2KQFQMGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00536&json=true","fetch_graph":"https://pith.science/api/pith-number/2KQFQMGSQWMKHS5HKNLEAUMPXP/graph.json","fetch_events":"https://pith.science/api/pith-number/2KQFQMGSQWMKHS5HKNLEAUMPXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP/action/storage_attestation","attest_author":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP/action/author_attestation","sign_citation":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP/action/citation_signature","submit_replication":"https://pith.science/pith/2KQFQMGSQWMKHS5HKNLEAUMPXP/action/replication_record"}},"created_at":"2026-07-05T11:13:36.620623+00:00","updated_at":"2026-07-05T11:13:36.620623+00:00"}