{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AFQVVIMMD7YO7FOFE7DHXEVIZG","short_pith_number":"pith:AFQVVIMM","schema_version":"1.0","canonical_sha256":"01615aa18c1ff0ef95c527c67b92a8c9b5866338805a683d8ce680af9cad9aaf","source":{"kind":"arxiv","id":"2502.19103","version":2},"attestation_state":"computed","paper":{"title":"LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Rishi Ravikumar, Riza Batista-Navarro, Shanghaoran Quan, Siwei Wu, Tyler Loakman, Xiaoyong Wei, Xingwei Qu, Yizhi Li, Yucheng Li","submitted_at":"2025-02-26T12:46:36Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, yet their ability to generate long-form content remains poorly understood and evaluated. Our analysis reveals that current LLMs struggle with length requirements and information density in long-text generation, with performance deteriorating as text length increases. To quantitively locate such a performance degradation and provide further insights on model development, we present LongEval, a benchmark that evaluates long-text generation through both direct and plan-based generation para"},"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":"2502.19103","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T12:46:36Z","cross_cats_sorted":[],"title_canon_sha256":"7ea6860f9f37f611298fc99bc677c1b76a3b5fd7f04c5695498b13f0ce627bc7","abstract_canon_sha256":"fb2c76fdaad3c7f2c0917e3fe909b2e77c57cf3d48caf1dcd43e5636a51f0c01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:14.743035Z","signature_b64":"sXvC41TGogXYqmTRPszjBZ9CCuvvXhztZ/5oT4J7l3ARGYrst9LmbUOSnwiGxhQjC1TxXpBoaXo4kvoIunkqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01615aa18c1ff0ef95c527c67b92a8c9b5866338805a683d8ce680af9cad9aaf","last_reissued_at":"2026-07-05T10:26:14.742132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:14.742132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Rishi Ravikumar, Riza Batista-Navarro, Shanghaoran Quan, Siwei Wu, Tyler Loakman, Xiaoyong Wei, Xingwei Qu, Yizhi Li, Yucheng Li","submitted_at":"2025-02-26T12:46:36Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, yet their ability to generate long-form content remains poorly understood and evaluated. Our analysis reveals that current LLMs struggle with length requirements and information density in long-text generation, with performance deteriorating as text length increases. To quantitively locate such a performance degradation and provide further insights on model development, we present LongEval, a benchmark that evaluates long-text generation through both direct and plan-based generation para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19103","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/2502.19103/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":"2502.19103","created_at":"2026-07-05T10:26:14.742244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19103v2","created_at":"2026-07-05T10:26:14.742244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19103","created_at":"2026-07-05T10:26:14.742244+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFQVVIMMD7YO","created_at":"2026-07-05T10:26:14.742244+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFQVVIMMD7YO7FOF","created_at":"2026-07-05T10:26:14.742244+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFQVVIMM","created_at":"2026-07-05T10:26:14.742244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.05188","citing_title":"Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG","json":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG.json","graph_json":"https://pith.science/api/pith-number/AFQVVIMMD7YO7FOFE7DHXEVIZG/graph.json","events_json":"https://pith.science/api/pith-number/AFQVVIMMD7YO7FOFE7DHXEVIZG/events.json","paper":"https://pith.science/paper/AFQVVIMM"},"agent_actions":{"view_html":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG","download_json":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG.json","view_paper":"https://pith.science/paper/AFQVVIMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19103&json=true","fetch_graph":"https://pith.science/api/pith-number/AFQVVIMMD7YO7FOFE7DHXEVIZG/graph.json","fetch_events":"https://pith.science/api/pith-number/AFQVVIMMD7YO7FOFE7DHXEVIZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG/action/storage_attestation","attest_author":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG/action/author_attestation","sign_citation":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG/action/citation_signature","submit_replication":"https://pith.science/pith/AFQVVIMMD7YO7FOFE7DHXEVIZG/action/replication_record"}},"created_at":"2026-07-05T10:26:14.742244+00:00","updated_at":"2026-07-05T10:26:14.742244+00:00"}