{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCBCZ3Z73LSE6D3O7FSIPRSZ3T","short_pith_number":"pith:YCBCZ3Z7","schema_version":"1.0","canonical_sha256":"c0822cef3fdae44f0f6ef96487c659dcf1546b321d811b7fe1828b11cd5fe762","source":{"kind":"arxiv","id":"2504.05732","version":2},"attestation_state":"computed","paper":{"title":"LLM$\\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo An, Chaoqun He, Haoyu Wang, Maosong Sun, Shuo Wang, Xiaorong Wang, Yujia Fu, Zhili Li, Zhiyuan Liu, Zhu Zhang, Zirui Ren","submitted_at":"2025-04-08T07:03:48Z","abstract_excerpt":"Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM$\\times$MapReduce-V2, a novel test-time scaling strategy designe"},"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":"2504.05732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T07:03:48Z","cross_cats_sorted":[],"title_canon_sha256":"09492f62ee755ed67062251eb94d718ffecd7780513252e4c89f3e61dd02d768","abstract_canon_sha256":"9e2033393c503f6dcc63094df4776088ce1c7669a3f860697fa4049b17aef91a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:16.769324Z","signature_b64":"IGBumpa3e/8vK/YOoOBkXhaXC+TZEGKa4erieFcEIBF+OGE+av5SwBKIrrJXNi1db1ihtHh3ZrVgI+8lmnlOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0822cef3fdae44f0f6ef96487c659dcf1546b321d811b7fe1828b11cd5fe762","last_reissued_at":"2026-07-05T10:49:16.768812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:16.768812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM$\\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo An, Chaoqun He, Haoyu Wang, Maosong Sun, Shuo Wang, Xiaorong Wang, Yujia Fu, Zhili Li, Zhiyuan Liu, Zhu Zhang, Zirui Ren","submitted_at":"2025-04-08T07:03:48Z","abstract_excerpt":"Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM$\\times$MapReduce-V2, a novel test-time scaling strategy designe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05732","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/2504.05732/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":"2504.05732","created_at":"2026-07-05T10:49:16.768873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05732v2","created_at":"2026-07-05T10:49:16.768873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05732","created_at":"2026-07-05T10:49:16.768873+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCBCZ3Z73LSE","created_at":"2026-07-05T10:49:16.768873+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCBCZ3Z73LSE6D3O","created_at":"2026-07-05T10:49:16.768873+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCBCZ3Z7","created_at":"2026-07-05T10:49:16.768873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29522","citing_title":"DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T","json":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T.json","graph_json":"https://pith.science/api/pith-number/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/graph.json","events_json":"https://pith.science/api/pith-number/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/events.json","paper":"https://pith.science/paper/YCBCZ3Z7"},"agent_actions":{"view_html":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T","download_json":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T.json","view_paper":"https://pith.science/paper/YCBCZ3Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05732&json=true","fetch_graph":"https://pith.science/api/pith-number/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/action/storage_attestation","attest_author":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/action/author_attestation","sign_citation":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/action/citation_signature","submit_replication":"https://pith.science/pith/YCBCZ3Z73LSE6D3O7FSIPRSZ3T/action/replication_record"}},"created_at":"2026-07-05T10:49:16.768873+00:00","updated_at":"2026-07-05T10:49:16.768873+00:00"}