{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GPE4URLWR3LOWXAO3GSG2ZXEY","short_pith_number":"pith:7GPE4URL","schema_version":"1.0","canonical_sha256":"f99e4e522bb476b75ae076cd236b37261291a41301170034fd61c75987490f92","source":{"kind":"arxiv","id":"2401.14640","version":2},"attestation_state":"computed","paper":{"title":"Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guilin Qi, Hongru Wang, Jeff Z. Pan, Jiaoyan Chen, Nan Hu, Sheng Bi, Tongtong Wu, Yike Wu, Yongrui Chen","submitted_at":"2024-01-26T04:11:07Z","abstract_excerpt":"Attributed Question Answering (AQA) has attracted wide attention, but there are still several limitations in evaluating the attributions, including lacking fine-grained attribution categories, relying on manual annotations, and failing to compare attributions with only subtle differences. To bridge these gaps, we introduce Complex Attributed Question Answering (CAQA), a large-scale benchmark containing comprehensive attribution categories, automatically generated using Knowledge Graphs (KGs), and complex attribution scenarios. We have conducted extensive experiments to verify the effectiveness"},"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":"2401.14640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T04:11:07Z","cross_cats_sorted":[],"title_canon_sha256":"3a05d8d1012d3a1e272120e551d23d2205890a051777043cde6ae5f930f2ed80","abstract_canon_sha256":"5ad3fa644345cef1cea14525bdc7b20ebbc78442cd6e9b6b88a3c2efcce70850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:47.388776Z","signature_b64":"XNncN3/RoTauLzTXqHg7N1x44ZgwrKi7mXiOYs5BlGUGIKid35Rwor+OaIvWRmHTkTFqHwLXGyfuibxW6legAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f99e4e522bb476b75ae076cd236b37261291a41301170034fd61c75987490f92","last_reissued_at":"2026-07-05T11:29:47.388308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:47.388308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guilin Qi, Hongru Wang, Jeff Z. Pan, Jiaoyan Chen, Nan Hu, Sheng Bi, Tongtong Wu, Yike Wu, Yongrui Chen","submitted_at":"2024-01-26T04:11:07Z","abstract_excerpt":"Attributed Question Answering (AQA) has attracted wide attention, but there are still several limitations in evaluating the attributions, including lacking fine-grained attribution categories, relying on manual annotations, and failing to compare attributions with only subtle differences. To bridge these gaps, we introduce Complex Attributed Question Answering (CAQA), a large-scale benchmark containing comprehensive attribution categories, automatically generated using Knowledge Graphs (KGs), and complex attribution scenarios. We have conducted extensive experiments to verify the effectiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14640","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/2401.14640/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":"2401.14640","created_at":"2026-07-05T11:29:47.388380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14640v2","created_at":"2026-07-05T11:29:47.388380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14640","created_at":"2026-07-05T11:29:47.388380+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GPE4URLWR3L","created_at":"2026-07-05T11:29:47.388380+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GPE4URLWR3LOWXA","created_at":"2026-07-05T11:29:47.388380+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GPE4URL","created_at":"2026-07-05T11:29:47.388380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12767","citing_title":"Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY","json":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY.json","graph_json":"https://pith.science/api/pith-number/7GPE4URLWR3LOWXAO3GSG2ZXEY/graph.json","events_json":"https://pith.science/api/pith-number/7GPE4URLWR3LOWXAO3GSG2ZXEY/events.json","paper":"https://pith.science/paper/7GPE4URL"},"agent_actions":{"view_html":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY","download_json":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY.json","view_paper":"https://pith.science/paper/7GPE4URL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14640&json=true","fetch_graph":"https://pith.science/api/pith-number/7GPE4URLWR3LOWXAO3GSG2ZXEY/graph.json","fetch_events":"https://pith.science/api/pith-number/7GPE4URLWR3LOWXAO3GSG2ZXEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY/action/storage_attestation","attest_author":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY/action/author_attestation","sign_citation":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY/action/citation_signature","submit_replication":"https://pith.science/pith/7GPE4URLWR3LOWXAO3GSG2ZXEY/action/replication_record"}},"created_at":"2026-07-05T11:29:47.388380+00:00","updated_at":"2026-07-05T11:29:47.388380+00:00"}