{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMJREJO23HXLAHMTE5RRPYGUVI","short_pith_number":"pith:WMJREJO2","schema_version":"1.0","canonical_sha256":"b3131225dad9eeb01d93276317e0d4aa1ce2aa2b624c77c4bd7c0c3f4fbed0b7","source":{"kind":"arxiv","id":"2503.11346","version":1},"attestation_state":"computed","paper":{"title":"AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"(2) Poisson Lab, Fengyu Li (1), Huawei), Hui Zu (1), Jia Zhou (1), Jingwen Zhao (2), Junhao Zhu (1), Lu Chen (1), Yanfei Zhang (1), Yilin Li (1), Yunjun Gao (1) ((1) Zhejiang University","submitted_at":"2025-03-14T12:23:45Z","abstract_excerpt":"Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmente"},"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":"2503.11346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T12:23:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7e204adb07dbed9e0f48ae6594fcca0f4692a3a1a3c242f545ecdf07a2a9961","abstract_canon_sha256":"246a4750dce1a12998ed871f3ed2890b59887557c3a057f2460f820e6da83099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:29.349076Z","signature_b64":"ZEmNXLU7Gl3NZSpPXaUBRxHb15Er5IUaOxQys3hkula+O1irlUgTVMUryHb2iJij7rDVwXCCh9bMwTBxcIiQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3131225dad9eeb01d93276317e0d4aa1ce2aa2b624c77c4bd7c0c3f4fbed0b7","last_reissued_at":"2026-07-05T10:31:29.348129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:29.348129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"(2) Poisson Lab, Fengyu Li (1), Huawei), Hui Zu (1), Jia Zhou (1), Jingwen Zhao (2), Junhao Zhu (1), Lu Chen (1), Yanfei Zhang (1), Yilin Li (1), Yunjun Gao (1) ((1) Zhejiang University","submitted_at":"2025-03-14T12:23:45Z","abstract_excerpt":"Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmente"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11346","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/2503.11346/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":"2503.11346","created_at":"2026-07-05T10:31:29.348242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11346v1","created_at":"2026-07-05T10:31:29.348242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11346","created_at":"2026-07-05T10:31:29.348242+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMJREJO23HXL","created_at":"2026-07-05T10:31:29.348242+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMJREJO23HXLAHMT","created_at":"2026-07-05T10:31:29.348242+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMJREJO2","created_at":"2026-07-05T10:31:29.348242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00648","citing_title":"DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI","json":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI.json","graph_json":"https://pith.science/api/pith-number/WMJREJO23HXLAHMTE5RRPYGUVI/graph.json","events_json":"https://pith.science/api/pith-number/WMJREJO23HXLAHMTE5RRPYGUVI/events.json","paper":"https://pith.science/paper/WMJREJO2"},"agent_actions":{"view_html":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI","download_json":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI.json","view_paper":"https://pith.science/paper/WMJREJO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11346&json=true","fetch_graph":"https://pith.science/api/pith-number/WMJREJO23HXLAHMTE5RRPYGUVI/graph.json","fetch_events":"https://pith.science/api/pith-number/WMJREJO23HXLAHMTE5RRPYGUVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI/action/storage_attestation","attest_author":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI/action/author_attestation","sign_citation":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI/action/citation_signature","submit_replication":"https://pith.science/pith/WMJREJO23HXLAHMTE5RRPYGUVI/action/replication_record"}},"created_at":"2026-07-05T10:31:29.348242+00:00","updated_at":"2026-07-05T10:31:29.348242+00:00"}