{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TSUDGEEJJW65XEXFJ7VDBPXTCI","short_pith_number":"pith:TSUDGEEJ","schema_version":"1.0","canonical_sha256":"9ca83310894dbddb92e54fea30bef3121dd6543bf4255a54749517cb3361c495","source":{"kind":"arxiv","id":"2504.14856","version":1},"attestation_state":"computed","paper":{"title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Delai Qiu, Jiajun Shen, Jun Zhao, Kang Liu, Shengping Liu, Tong Zhou, Yubo Chen","submitted_at":"2025-04-21T04:50:16Z","abstract_excerpt":"While hallucinations of large language models could been alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers remains questionable. In this work, we introduce Context-Prior Augmented Citation Generation task, requiring models to generate citations considering both external and internal knowledge while providing trustworthy references, with 5 evaluation metrics focusing on 3 aspects: answer helpfulness, citation faithfulness, and trustworthiness. We introduce RAEL, t"},"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":"2504.14856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T04:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"0eec2ed682179f15674ffa130a384682c141edc6ad8afd356af87b1b4324507c","abstract_canon_sha256":"9fd2fa069225f9e3e60ab4f559d27aeca3aa39dc0d3f08096cde61aedf02db7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:51.781785Z","signature_b64":"AC8H/9J+dxiSbJ1la5VtDyaKlnNY/i8UIkz7dLi//MjdIf5npdHEb+J/tWfZ1R4emq0IbXEyuycRHcOPOHsLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ca83310894dbddb92e54fea30bef3121dd6543bf4255a54749517cb3361c495","last_reissued_at":"2026-07-05T10:51:51.781269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:51.781269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Delai Qiu, Jiajun Shen, Jun Zhao, Kang Liu, Shengping Liu, Tong Zhou, Yubo Chen","submitted_at":"2025-04-21T04:50:16Z","abstract_excerpt":"While hallucinations of large language models could been alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers remains questionable. In this work, we introduce Context-Prior Augmented Citation Generation task, requiring models to generate citations considering both external and internal knowledge while providing trustworthy references, with 5 evaluation metrics focusing on 3 aspects: answer helpfulness, citation faithfulness, and trustworthiness. We introduce RAEL, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14856","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/2504.14856/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":"2504.14856","created_at":"2026-07-05T10:51:51.781340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14856v1","created_at":"2026-07-05T10:51:51.781340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14856","created_at":"2026-07-05T10:51:51.781340+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSUDGEEJJW65","created_at":"2026-07-05T10:51:51.781340+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSUDGEEJJW65XEXF","created_at":"2026-07-05T10:51:51.781340+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSUDGEEJ","created_at":"2026-07-05T10:51:51.781340+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/TSUDGEEJJW65XEXFJ7VDBPXTCI","json":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI.json","graph_json":"https://pith.science/api/pith-number/TSUDGEEJJW65XEXFJ7VDBPXTCI/graph.json","events_json":"https://pith.science/api/pith-number/TSUDGEEJJW65XEXFJ7VDBPXTCI/events.json","paper":"https://pith.science/paper/TSUDGEEJ"},"agent_actions":{"view_html":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI","download_json":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI.json","view_paper":"https://pith.science/paper/TSUDGEEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14856&json=true","fetch_graph":"https://pith.science/api/pith-number/TSUDGEEJJW65XEXFJ7VDBPXTCI/graph.json","fetch_events":"https://pith.science/api/pith-number/TSUDGEEJJW65XEXFJ7VDBPXTCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI/action/storage_attestation","attest_author":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI/action/author_attestation","sign_citation":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI/action/citation_signature","submit_replication":"https://pith.science/pith/TSUDGEEJJW65XEXFJ7VDBPXTCI/action/replication_record"}},"created_at":"2026-07-05T10:51:51.781340+00:00","updated_at":"2026-07-05T10:51:51.781340+00:00"}