{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VULK7EW754RUBI54D2P3XH727U","short_pith_number":"pith:VULK7EW7","schema_version":"1.0","canonical_sha256":"ad16af92dfef2340a3bc1e9fbb9ffafd327a3022544a1606237dd07ed3b17555","source":{"kind":"arxiv","id":"2503.04723","version":2},"attestation_state":"computed","paper":{"title":"Shifting Long-Context LLMs Research from Input to Output","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Juanzi Li, Ming Shan Hee, Roy Ka-Wei Lee, Shangqing Tu, Yuhao Wu, Yushi Bai, Zhiqing Hu","submitted_at":"2025-03-06T18:59:37Z","abstract_excerpt":"Recent advancements in long-context Large Language Models (LLMs) have primarily concentrated on processing extended input contexts, resulting in significant strides in long-context comprehension. However, the equally critical aspect of generating long-form outputs has received comparatively less attention. This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation. Tasks such as novel writing, long-term planning, and complex reasoning require models to understand extensive contexts and produce coherent, contextually rich, and logically "},"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":"2503.04723","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T18:59:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94429731713d663e407577e1eac3581e58a10df73721aa9832f56d9ffa1aadd3","abstract_canon_sha256":"e18ffe915fb626d17409ddacd41c9ec1da08cfc3fe1880228d6e5bfa8e550f7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:17.224063Z","signature_b64":"giRTJkj6zf6ORTuMBv3VX2D6Y3gfrdTKwvvvYiHsgGXLGKKdUdSGliwmvMymzv8TUReFPC8wMSOlGVUZQPCAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad16af92dfef2340a3bc1e9fbb9ffafd327a3022544a1606237dd07ed3b17555","last_reissued_at":"2026-07-05T10:26:17.223223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:17.223223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shifting Long-Context LLMs Research from Input to Output","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Juanzi Li, Ming Shan Hee, Roy Ka-Wei Lee, Shangqing Tu, Yuhao Wu, Yushi Bai, Zhiqing Hu","submitted_at":"2025-03-06T18:59:37Z","abstract_excerpt":"Recent advancements in long-context Large Language Models (LLMs) have primarily concentrated on processing extended input contexts, resulting in significant strides in long-context comprehension. However, the equally critical aspect of generating long-form outputs has received comparatively less attention. This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation. Tasks such as novel writing, long-term planning, and complex reasoning require models to understand extensive contexts and produce coherent, contextually rich, and logically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04723","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/2503.04723/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":"2503.04723","created_at":"2026-07-05T10:26:17.223311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04723v2","created_at":"2026-07-05T10:26:17.223311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04723","created_at":"2026-07-05T10:26:17.223311+00:00"},{"alias_kind":"pith_short_12","alias_value":"VULK7EW754RU","created_at":"2026-07-05T10:26:17.223311+00:00"},{"alias_kind":"pith_short_16","alias_value":"VULK7EW754RUBI54","created_at":"2026-07-05T10:26:17.223311+00:00"},{"alias_kind":"pith_short_8","alias_value":"VULK7EW7","created_at":"2026-07-05T10:26:17.223311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.18841","citing_title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U","json":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U.json","graph_json":"https://pith.science/api/pith-number/VULK7EW754RUBI54D2P3XH727U/graph.json","events_json":"https://pith.science/api/pith-number/VULK7EW754RUBI54D2P3XH727U/events.json","paper":"https://pith.science/paper/VULK7EW7"},"agent_actions":{"view_html":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U","download_json":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U.json","view_paper":"https://pith.science/paper/VULK7EW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04723&json=true","fetch_graph":"https://pith.science/api/pith-number/VULK7EW754RUBI54D2P3XH727U/graph.json","fetch_events":"https://pith.science/api/pith-number/VULK7EW754RUBI54D2P3XH727U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U/action/storage_attestation","attest_author":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U/action/author_attestation","sign_citation":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U/action/citation_signature","submit_replication":"https://pith.science/pith/VULK7EW754RUBI54D2P3XH727U/action/replication_record"}},"created_at":"2026-07-05T10:26:17.223311+00:00","updated_at":"2026-07-05T10:26:17.223311+00:00"}