{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X7LXZ742O2XTSLSG4YBS4JH573","short_pith_number":"pith:X7LXZ742","schema_version":"1.0","canonical_sha256":"bfd77cff9a76af392e46e6032e24fdfef4e56728ffd118c229e7d9693b1f2ea5","source":{"kind":"arxiv","id":"2412.11418","version":2},"attestation_state":"computed","paper":{"title":"ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liyu Zhang, Tianqing Fang, Weiqi Wang, Yangqiu Song","submitted_at":"2024-12-16T03:34:40Z","abstract_excerpt":"Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model. However, editing commonsense knowledge still faces difficulties, including limited knowledge coverage in existing resources, the infeasibility of annotating labels for an overabundance of commonsense knowledge, and the strict knowledge formats of current editing methods. In this paper, we address these challenges by presenting ConceptEdit, a framework that "},"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":"2412.11418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T03:34:40Z","cross_cats_sorted":[],"title_canon_sha256":"a6e7c559ddb2d2c4b94b24dbb5247bfae1dfa6a36087e4f0faad98ee880e3997","abstract_canon_sha256":"d9e75fed1de5e3d1d3e29dd2665699f0345668e645310282441b02db5a6cda62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:21.211553Z","signature_b64":"EvtuaXooaYkbz0qV2n53yQrH+iWaBsS5WjjTU2yAtj/DU9x/ihv1q1nhlY04b09tz+8wsjQjs5dPaCDKyckXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfd77cff9a76af392e46e6032e24fdfef4e56728ffd118c229e7d9693b1f2ea5","last_reissued_at":"2026-07-05T11:11:21.211054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:21.211054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liyu Zhang, Tianqing Fang, Weiqi Wang, Yangqiu Song","submitted_at":"2024-12-16T03:34:40Z","abstract_excerpt":"Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model. However, editing commonsense knowledge still faces difficulties, including limited knowledge coverage in existing resources, the infeasibility of annotating labels for an overabundance of commonsense knowledge, and the strict knowledge formats of current editing methods. In this paper, we address these challenges by presenting ConceptEdit, a framework that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11418","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/2412.11418/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":"2412.11418","created_at":"2026-07-05T11:11:21.211110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11418v2","created_at":"2026-07-05T11:11:21.211110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11418","created_at":"2026-07-05T11:11:21.211110+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7LXZ742O2XT","created_at":"2026-07-05T11:11:21.211110+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7LXZ742O2XTSLSG","created_at":"2026-07-05T11:11:21.211110+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7LXZ742","created_at":"2026-07-05T11:11:21.211110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07995","citing_title":"Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573","json":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573.json","graph_json":"https://pith.science/api/pith-number/X7LXZ742O2XTSLSG4YBS4JH573/graph.json","events_json":"https://pith.science/api/pith-number/X7LXZ742O2XTSLSG4YBS4JH573/events.json","paper":"https://pith.science/paper/X7LXZ742"},"agent_actions":{"view_html":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573","download_json":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573.json","view_paper":"https://pith.science/paper/X7LXZ742","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11418&json=true","fetch_graph":"https://pith.science/api/pith-number/X7LXZ742O2XTSLSG4YBS4JH573/graph.json","fetch_events":"https://pith.science/api/pith-number/X7LXZ742O2XTSLSG4YBS4JH573/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573/action/storage_attestation","attest_author":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573/action/author_attestation","sign_citation":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573/action/citation_signature","submit_replication":"https://pith.science/pith/X7LXZ742O2XTSLSG4YBS4JH573/action/replication_record"}},"created_at":"2026-07-05T11:11:21.211110+00:00","updated_at":"2026-07-05T11:11:21.211110+00:00"}