{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XAVHY5GV2YGZO57GDPVZ3Z4GGC","short_pith_number":"pith:XAVHY5GV","schema_version":"1.0","canonical_sha256":"b82a7c74d5d60d9777e61beb9de786309f87dfad205dbde487ef5bbcb197b2a9","source":{"kind":"arxiv","id":"2503.06868","version":1},"attestation_state":"computed","paper":{"title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fanshuang Kong, Junhao Zhang, Richong Zhang, Yanhan Ye, Yaowei Zheng, Ziyang Miao","submitted_at":"2025-03-10T02:44:36Z","abstract_excerpt":"Existing long-text generation methods primarily concentrate on producing lengthy texts from short inputs, neglecting the long-input and long-output tasks. Such tasks have numerous practical applications while lacking available benchmarks. Moreover, as the input grows in length, existing methods inevitably encounter the \"lost-in-the-middle\" phenomenon. In this paper, we first introduce a Long Input and Output Benchmark (LongInOutBench), including a synthetic dataset and a comprehensive evaluation framework, addressing the challenge of the missing benchmark. We then develop the Retrieval-Augment"},"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":"2503.06868","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T02:44:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90634e9ac52b7d9e2eb4117c2e1303aec0da255571775127cf23c4983dbc293d","abstract_canon_sha256":"6dc7e51a15d49d923de3cded25c60fc2daf303c85eece5b04004bbe35866d7d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:44.713946Z","signature_b64":"oJLUk7yoQkZjeHLqVeQnkYRxXR3DNxoY5WlgvFbE2dWc5W6B0Q3vagHp1C48oeJ0qS5lpaunjD1o6Br3i4B6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82a7c74d5d60d9777e61beb9de786309f87dfad205dbde487ef5bbcb197b2a9","last_reissued_at":"2026-07-05T10:27:44.713102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:44.713102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fanshuang Kong, Junhao Zhang, Richong Zhang, Yanhan Ye, Yaowei Zheng, Ziyang Miao","submitted_at":"2025-03-10T02:44:36Z","abstract_excerpt":"Existing long-text generation methods primarily concentrate on producing lengthy texts from short inputs, neglecting the long-input and long-output tasks. Such tasks have numerous practical applications while lacking available benchmarks. Moreover, as the input grows in length, existing methods inevitably encounter the \"lost-in-the-middle\" phenomenon. In this paper, we first introduce a Long Input and Output Benchmark (LongInOutBench), including a synthetic dataset and a comprehensive evaluation framework, addressing the challenge of the missing benchmark. We then develop the Retrieval-Augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06868","kind":"arxiv","version":1},"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/2503.06868/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":"2503.06868","created_at":"2026-07-05T10:27:44.713207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06868v1","created_at":"2026-07-05T10:27:44.713207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06868","created_at":"2026-07-05T10:27:44.713207+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAVHY5GV2YGZ","created_at":"2026-07-05T10:27:44.713207+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAVHY5GV2YGZO57G","created_at":"2026-07-05T10:27:44.713207+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAVHY5GV","created_at":"2026-07-05T10:27:44.713207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.01219","citing_title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC","json":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC.json","graph_json":"https://pith.science/api/pith-number/XAVHY5GV2YGZO57GDPVZ3Z4GGC/graph.json","events_json":"https://pith.science/api/pith-number/XAVHY5GV2YGZO57GDPVZ3Z4GGC/events.json","paper":"https://pith.science/paper/XAVHY5GV"},"agent_actions":{"view_html":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC","download_json":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC.json","view_paper":"https://pith.science/paper/XAVHY5GV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06868&json=true","fetch_graph":"https://pith.science/api/pith-number/XAVHY5GV2YGZO57GDPVZ3Z4GGC/graph.json","fetch_events":"https://pith.science/api/pith-number/XAVHY5GV2YGZO57GDPVZ3Z4GGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC/action/storage_attestation","attest_author":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC/action/author_attestation","sign_citation":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC/action/citation_signature","submit_replication":"https://pith.science/pith/XAVHY5GV2YGZO57GDPVZ3Z4GGC/action/replication_record"}},"created_at":"2026-07-05T10:27:44.713207+00:00","updated_at":"2026-07-05T10:27:44.713207+00:00"}