{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKTB6YS7O5NTL3MIY5DZ2OO2PO","short_pith_number":"pith:OKTB6YS7","schema_version":"1.0","canonical_sha256":"72a61f625f775b35ed88c7479d39da7b9908b90011a7fb02673ff299e9d8c2cc","source":{"kind":"arxiv","id":"2410.04199","version":3},"attestation_state":"computed","paper":{"title":"LongGenBench: Long-context Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peijie Dong, Xiang Liu, Xiaowen Chu, Xuming Hu","submitted_at":"2024-10-05T15:33:25Z","abstract_excerpt":"Current long-context benchmarks primarily focus on retrieval-based tests, requiring Large Language Models (LLMs) to locate specific information within extensive input contexts, such as the needle-in-a-haystack (NIAH) benchmark. Long-context generation refers to the ability of a language model to generate coherent and contextually accurate text that spans across lengthy passages or documents. While recent studies show strong performance on NIAH and other retrieval-based long-context benchmarks, there is a significant lack of benchmarks for evaluating long-context generation capabilities. To bri"},"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":"2410.04199","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T15:33:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09723a7a52d414d959e81c3d3d26393f49acff13bd1cf965be6529f953fdd7bb","abstract_canon_sha256":"7425fd47315e41d41c770107e55f35ca2f1fcf85abd122368c9a38c0e7b329c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:01.910790Z","signature_b64":"d7UMWLdQx0HkdObh7+1SgtqLo3aNrCTFz6Q0cVI3DGDukrDGC7BWeMDMj+WyfSK29QjdkkFIJbUSI4+MqVTrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a61f625f775b35ed88c7479d39da7b9908b90011a7fb02673ff299e9d8c2cc","last_reissued_at":"2026-07-05T09:25:01.910303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:01.910303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongGenBench: Long-context Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peijie Dong, Xiang Liu, Xiaowen Chu, Xuming Hu","submitted_at":"2024-10-05T15:33:25Z","abstract_excerpt":"Current long-context benchmarks primarily focus on retrieval-based tests, requiring Large Language Models (LLMs) to locate specific information within extensive input contexts, such as the needle-in-a-haystack (NIAH) benchmark. Long-context generation refers to the ability of a language model to generate coherent and contextually accurate text that spans across lengthy passages or documents. While recent studies show strong performance on NIAH and other retrieval-based long-context benchmarks, there is a significant lack of benchmarks for evaluating long-context generation capabilities. To bri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04199","kind":"arxiv","version":3},"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/2410.04199/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":"2410.04199","created_at":"2026-07-05T09:25:01.910374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04199v3","created_at":"2026-07-05T09:25:01.910374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04199","created_at":"2026-07-05T09:25:01.910374+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKTB6YS7O5NT","created_at":"2026-07-05T09:25:01.910374+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKTB6YS7O5NTL3MI","created_at":"2026-07-05T09:25:01.910374+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKTB6YS7","created_at":"2026-07-05T09:25:01.910374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17613","citing_title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26837","citing_title":"Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10039","citing_title":"Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO","json":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO.json","graph_json":"https://pith.science/api/pith-number/OKTB6YS7O5NTL3MIY5DZ2OO2PO/graph.json","events_json":"https://pith.science/api/pith-number/OKTB6YS7O5NTL3MIY5DZ2OO2PO/events.json","paper":"https://pith.science/paper/OKTB6YS7"},"agent_actions":{"view_html":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO","download_json":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO.json","view_paper":"https://pith.science/paper/OKTB6YS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04199&json=true","fetch_graph":"https://pith.science/api/pith-number/OKTB6YS7O5NTL3MIY5DZ2OO2PO/graph.json","fetch_events":"https://pith.science/api/pith-number/OKTB6YS7O5NTL3MIY5DZ2OO2PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO/action/storage_attestation","attest_author":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO/action/author_attestation","sign_citation":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO/action/citation_signature","submit_replication":"https://pith.science/pith/OKTB6YS7O5NTL3MIY5DZ2OO2PO/action/replication_record"}},"created_at":"2026-07-05T09:25:01.910374+00:00","updated_at":"2026-07-05T09:25:01.910374+00:00"}