{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFT2KGQ5FHVKT6O732X4RHOSS6","short_pith_number":"pith:LFT2KGQ5","schema_version":"1.0","canonical_sha256":"5967a51a1d29eaa9f9dfdeafc89dd297b4ed3a984e203c25dd214e88d934dd62","source":{"kind":"arxiv","id":"2411.14790","version":4},"attestation_state":"computed","paper":{"title":"KBAlign: Efficient Self Adaptation on Specific Knowledge Bases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Ruobing Wang, Shi Yu, Shuo Wang, Xu Han, Yukun Yan, Yuxuan Chen, Zhenghao Liu, Zheni Zeng, Zhiyuan Liu","submitted_at":"2024-11-22T08:21:03Z","abstract_excerpt":"Although retrieval-augmented generation (RAG) remains essential for knowledge-based question answering (KBQA), current paradigms face critical challenges under specific domains. Existing methods struggle with targeted adaptation on small-scale KBs: vanilla unsupervised training exhibits poor effectiveness, while fine-tuning incurs prohibitive costs of external signals. We present KBAlign, a self-supervised framework that enhances RAG systems through efficient model adaptation. Our key insight is to leverage the model's intrinsic capabilities for knowledge alignment through two innovative mecha"},"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":"2411.14790","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T08:21:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4db9fc82c91fc1087ce7f8a37c09bfad58aae499ac0acf31f635146213d69fdb","abstract_canon_sha256":"f1397dba48f26345b563df44eb46f9502d0045085580653085782aaa8425cfae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:18.614020Z","signature_b64":"BI+GsJy/kA4eX0zfhSrcRtF3S45YSw6l+ynMrH3Lknt09ZktYuCgmyNsLbhWQlapvZjvCKtKlWORlCnLfQYbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5967a51a1d29eaa9f9dfdeafc89dd297b4ed3a984e203c25dd214e88d934dd62","last_reissued_at":"2026-07-05T11:03:18.613584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:18.613584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KBAlign: Efficient Self Adaptation on Specific Knowledge Bases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Ruobing Wang, Shi Yu, Shuo Wang, Xu Han, Yukun Yan, Yuxuan Chen, Zhenghao Liu, Zheni Zeng, Zhiyuan Liu","submitted_at":"2024-11-22T08:21:03Z","abstract_excerpt":"Although retrieval-augmented generation (RAG) remains essential for knowledge-based question answering (KBQA), current paradigms face critical challenges under specific domains. Existing methods struggle with targeted adaptation on small-scale KBs: vanilla unsupervised training exhibits poor effectiveness, while fine-tuning incurs prohibitive costs of external signals. We present KBAlign, a self-supervised framework that enhances RAG systems through efficient model adaptation. Our key insight is to leverage the model's intrinsic capabilities for knowledge alignment through two innovative mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14790","kind":"arxiv","version":4},"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/2411.14790/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":"2411.14790","created_at":"2026-07-05T11:03:18.613638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14790v4","created_at":"2026-07-05T11:03:18.613638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14790","created_at":"2026-07-05T11:03:18.613638+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFT2KGQ5FHVK","created_at":"2026-07-05T11:03:18.613638+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFT2KGQ5FHVKT6O7","created_at":"2026-07-05T11:03:18.613638+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFT2KGQ5","created_at":"2026-07-05T11:03:18.613638+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/LFT2KGQ5FHVKT6O732X4RHOSS6","json":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6.json","graph_json":"https://pith.science/api/pith-number/LFT2KGQ5FHVKT6O732X4RHOSS6/graph.json","events_json":"https://pith.science/api/pith-number/LFT2KGQ5FHVKT6O732X4RHOSS6/events.json","paper":"https://pith.science/paper/LFT2KGQ5"},"agent_actions":{"view_html":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6","download_json":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6.json","view_paper":"https://pith.science/paper/LFT2KGQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14790&json=true","fetch_graph":"https://pith.science/api/pith-number/LFT2KGQ5FHVKT6O732X4RHOSS6/graph.json","fetch_events":"https://pith.science/api/pith-number/LFT2KGQ5FHVKT6O732X4RHOSS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6/action/storage_attestation","attest_author":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6/action/author_attestation","sign_citation":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6/action/citation_signature","submit_replication":"https://pith.science/pith/LFT2KGQ5FHVKT6O732X4RHOSS6/action/replication_record"}},"created_at":"2026-07-05T11:03:18.613638+00:00","updated_at":"2026-07-05T11:03:18.613638+00:00"}