{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ITNTIQXULJMGH4YQ3QK3RTPMV","short_pith_number":"pith:4ITNTIQX","schema_version":"1.0","canonical_sha256":"e226d9a217a2d2c31f9886e0adc66f6571fa109646c87b4bc936c79be613cc9d","source":{"kind":"arxiv","id":"2506.02000","version":2},"attestation_state":"computed","paper":{"title":"NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhay Gupta, Kevin Zhu, Michael Lu, Sean O'Brien, Vasu Sharma","submitted_at":"2025-05-20T20:54:37Z","abstract_excerpt":"Current large language models (LLMs) struggle to answer questions that span tens of thousands of tokens, especially when multi-hop reasoning is involved. While prior benchmarks explore long-context comprehension or multi-hop reasoning in isolation, none jointly vary context length and reasoning depth in natural narrative settings. We introduce NovelHopQA, the first benchmark to evaluate 1-4 hop QA over 64k-128k-token excerpts from 83 full-length public-domain novels. A keyword-guided pipeline builds hop-separated chains grounded in coherent storylines. We evaluate seven state-of-the-art models"},"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":"2506.02000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T20:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"2e46d37f35c329985b5ae8d7e964242ad87266e85ec025f987cd994bc6d98d7c","abstract_canon_sha256":"0073cc9e700838f864793c0201e55a66f64015a6b8e50d6445b711c55a0acb19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:11.696761Z","signature_b64":"V/BFoINq/wjZBgEjKdVSFWp9ngYseg9vh2gJlNuW+TFSi7fE7clljdiRA+qcfHqaJoKGAHo6haBpWUGI+F0jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e226d9a217a2d2c31f9886e0adc66f6571fa109646c87b4bc936c79be613cc9d","last_reissued_at":"2026-07-05T11:25:11.696260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:11.696260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhay Gupta, Kevin Zhu, Michael Lu, Sean O'Brien, Vasu Sharma","submitted_at":"2025-05-20T20:54:37Z","abstract_excerpt":"Current large language models (LLMs) struggle to answer questions that span tens of thousands of tokens, especially when multi-hop reasoning is involved. While prior benchmarks explore long-context comprehension or multi-hop reasoning in isolation, none jointly vary context length and reasoning depth in natural narrative settings. We introduce NovelHopQA, the first benchmark to evaluate 1-4 hop QA over 64k-128k-token excerpts from 83 full-length public-domain novels. A keyword-guided pipeline builds hop-separated chains grounded in coherent storylines. We evaluate seven state-of-the-art models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02000","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/2506.02000/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":"2506.02000","created_at":"2026-07-05T11:25:11.696323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02000v2","created_at":"2026-07-05T11:25:11.696323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02000","created_at":"2026-07-05T11:25:11.696323+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ITNTIQXULJM","created_at":"2026-07-05T11:25:11.696323+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ITNTIQXULJMGH4Y","created_at":"2026-07-05T11:25:11.696323+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ITNTIQX","created_at":"2026-07-05T11:25:11.696323+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/4ITNTIQXULJMGH4YQ3QK3RTPMV","json":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV.json","graph_json":"https://pith.science/api/pith-number/4ITNTIQXULJMGH4YQ3QK3RTPMV/graph.json","events_json":"https://pith.science/api/pith-number/4ITNTIQXULJMGH4YQ3QK3RTPMV/events.json","paper":"https://pith.science/paper/4ITNTIQX"},"agent_actions":{"view_html":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV","download_json":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV.json","view_paper":"https://pith.science/paper/4ITNTIQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02000&json=true","fetch_graph":"https://pith.science/api/pith-number/4ITNTIQXULJMGH4YQ3QK3RTPMV/graph.json","fetch_events":"https://pith.science/api/pith-number/4ITNTIQXULJMGH4YQ3QK3RTPMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV/action/storage_attestation","attest_author":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV/action/author_attestation","sign_citation":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV/action/citation_signature","submit_replication":"https://pith.science/pith/4ITNTIQXULJMGH4YQ3QK3RTPMV/action/replication_record"}},"created_at":"2026-07-05T11:25:11.696323+00:00","updated_at":"2026-07-05T11:25:11.696323+00:00"}