{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6NMUSXDMPIE4USQMFJYY242UQF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aab5d3ff0a7a755e529b89dd1b3fca4f61f91faef8bb5ba6460e2ead8d49d364","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T20:30:45Z","title_canon_sha256":"fad5a255672debb9fb1ed7cdea65b2761adf4769ca46af242e3019014f6d2f3a"},"schema_version":"1.0","source":{"id":"2402.14116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14116","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14116v2","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14116","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"6NMUSXDMPIE4","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"6NMUSXDMPIE4USQM","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"6NMUSXDM","created_at":"2026-07-05T08:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:0d4740d3b0d4aaf6ff11cc8289e28350d5df128e5261a0e1dedd988c87970023","target":"graph","created_at":"2026-07-05T08:28:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.14116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One type of question that is commonly found in day-to-day scenarios is ``fan-out'' questions, complex multi-hop, multi-document reasoning questions that require finding information about a large number of entities. However, there exist few resources to evaluate this type of question-answering capability among large language models. To evaluate complex reasoning in LLMs more fully, we present FanOutQA, a high-quality dataset of fan-out question-answer pairs and human-annotated decompositions with English Wikipedia as the knowledge base. We formulate three benchmark settings across our dataset a","authors_text":"Alyssa Hwang, Andrew Zhu, Chris Callison-Burch, Liam Dugan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T20:30:45Z","title":"FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14116","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:505b74bf9d5f39f2c039940da0cc971345f3625a86eed2dc04dfd9890a1a25e9","target":"record","created_at":"2026-07-05T08:28:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aab5d3ff0a7a755e529b89dd1b3fca4f61f91faef8bb5ba6460e2ead8d49d364","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T20:30:45Z","title_canon_sha256":"fad5a255672debb9fb1ed7cdea65b2761adf4769ca46af242e3019014f6d2f3a"},"schema_version":"1.0","source":{"id":"2402.14116","kind":"arxiv","version":2}},"canonical_sha256":"f359495c6c7a09ca4a0c2a718d7354814707c2af102f33ebb95be1dc6be18a97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f359495c6c7a09ca4a0c2a718d7354814707c2af102f33ebb95be1dc6be18a97","first_computed_at":"2026-07-05T08:28:27.158125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:27.158125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fovZlCvMIiJWPg9Xxyl7SjPXlVhsEY3+Mtjz8zsn3jfNhLePLPo77KaEuoQCBdie/GYiyF/aGyPqsT041+39CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:27.158582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:505b74bf9d5f39f2c039940da0cc971345f3625a86eed2dc04dfd9890a1a25e9","sha256:0d4740d3b0d4aaf6ff11cc8289e28350d5df128e5261a0e1dedd988c87970023"],"state_sha256":"946785a63779753fa0eec1ca3d6d0af743908c12b8da0275d052f566ae159e49"}