{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ITNTIQXULJMGH4YQ3QK3RTPMV","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":"0073cc9e700838f864793c0201e55a66f64015a6b8e50d6445b711c55a0acb19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T20:54:37Z","title_canon_sha256":"2e46d37f35c329985b5ae8d7e964242ad87266e85ec025f987cd994bc6d98d7c"},"schema_version":"1.0","source":{"id":"2506.02000","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02000","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02000v2","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02000","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"4ITNTIQXULJM","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"4ITNTIQXULJMGH4Y","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"4ITNTIQX","created_at":"2026-07-05T11:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:30883e1fa16dedae0e76390881405e5de86459b90bb0e0e4cfee3a7e5c0c8f63","target":"graph","created_at":"2026-07-05T11:25:11Z","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/2506.02000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhay Gupta, Kevin Zhu, Michael Lu, Sean O'Brien, Vasu Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T20:54:37Z","title":"NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02000","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":"sha256:9045c1041bf5c4faa5706e4607f325683d680dac6f5c689de32dc1d87a4df7d8","target":"record","created_at":"2026-07-05T11:25:11Z","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":"0073cc9e700838f864793c0201e55a66f64015a6b8e50d6445b711c55a0acb19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T20:54:37Z","title_canon_sha256":"2e46d37f35c329985b5ae8d7e964242ad87266e85ec025f987cd994bc6d98d7c"},"schema_version":"1.0","source":{"id":"2506.02000","kind":"arxiv","version":2}},"canonical_sha256":"e226d9a217a2d2c31f9886e0adc66f6571fa109646c87b4bc936c79be613cc9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e226d9a217a2d2c31f9886e0adc66f6571fa109646c87b4bc936c79be613cc9d","first_computed_at":"2026-07-05T11:25:11.696260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:11.696260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/BFoINq/wjZBgEjKdVSFWp9ngYseg9vh2gJlNuW+TFSi7fE7clljdiRA+qcfHqaJoKGAHo6haBpWUGI+F0jAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:11.696761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02000","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9045c1041bf5c4faa5706e4607f325683d680dac6f5c689de32dc1d87a4df7d8","sha256:30883e1fa16dedae0e76390881405e5de86459b90bb0e0e4cfee3a7e5c0c8f63"],"state_sha256":"12a4b3b29de520794010b132825f89134378b11b22c0257084a88d9627eb3097"}