{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SC7PRGHTQCMJM5Z3OWIRTQAQRW","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":"ed99fdf8492dba15be4589548d35000caff20b6d7d394740afc8927da08fafb9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T17:32:32Z","title_canon_sha256":"87c6d9c5cc7d9f76c2244c23d686ac09aef2acd7ae9fc08a5b7731f710436ab6"},"schema_version":"1.0","source":{"id":"2403.12766","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12766","created_at":"2026-07-05T10:52:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12766v3","created_at":"2026-07-05T10:52:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12766","created_at":"2026-07-05T10:52:54Z"},{"alias_kind":"pith_short_12","alias_value":"SC7PRGHTQCMJ","created_at":"2026-07-05T10:52:54Z"},{"alias_kind":"pith_short_16","alias_value":"SC7PRGHTQCMJM5Z3","created_at":"2026-07-05T10:52:54Z"},{"alias_kind":"pith_short_8","alias_value":"SC7PRGHT","created_at":"2026-07-05T10:52:54Z"}],"graph_snapshots":[{"event_id":"sha256:2d632b3513c73d70c711a782bc4b5f8d2f62f345d67bfc87dc4f981cc1f30ecf","target":"graph","created_at":"2026-07-05T10:52:54Z","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/2403.12766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have pushed the boundaries of natural language processing, especially in long-context understanding. However, the evaluation of these models' long-context abilities remains a challenge due to the limitations of current benchmarks. To address this gap, we introduce NovelQA, a benchmark tailored for evaluating LLMs with complex, extended narratives. Constructed from English novels, NovelQA offers a unique blend of complexity, length, and narrative coherence, making it an ideal tool for assessing deep textual understanding in LLMs. This paper de","authors_text":"Boqi Pan, Cheng Deng, Cunxiang Wang, Guangsheng Bao, Qian Wang, Qipeng Guo, Ruoxi Ning, Tonghui Wu, Xiangkun Hu, Yue Zhang, Zheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T17:32:32Z","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12766","kind":"arxiv","version":3},"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":"sha256:4e480df98780e9669860187cf039ba288d3ba7e55f10e8289800ec0b94a13da3","target":"record","created_at":"2026-07-05T10:52:54Z","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":"ed99fdf8492dba15be4589548d35000caff20b6d7d394740afc8927da08fafb9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T17:32:32Z","title_canon_sha256":"87c6d9c5cc7d9f76c2244c23d686ac09aef2acd7ae9fc08a5b7731f710436ab6"},"schema_version":"1.0","source":{"id":"2403.12766","kind":"arxiv","version":3}},"canonical_sha256":"90bef898f3809896773b759119c0108db0c6a2efc123c56d3f244dc95bf73c18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90bef898f3809896773b759119c0108db0c6a2efc123c56d3f244dc95bf73c18","first_computed_at":"2026-07-05T10:52:54.190444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:54.190444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQfgQNxNChXUAzbXuaSqpXj8Wr3tod1Dl48M06F0jaNd49/Hf7xA8+DVFWoF3UwwD3b0xgd7g1lPIn0ZdCdQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:54.190943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12766","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e480df98780e9669860187cf039ba288d3ba7e55f10e8289800ec0b94a13da3","sha256:2d632b3513c73d70c711a782bc4b5f8d2f62f345d67bfc87dc4f981cc1f30ecf"],"state_sha256":"d70b0db97dc0b7e9d834625d740dfb45fbd956e5a3c8c7c4a95be7b0b13fd9ee"}