{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7LG7AFXTIJ2F5KKV6XA5TIMI53","short_pith_number":"pith:7LG7AFXT","schema_version":"1.0","canonical_sha256":"facdf016f342745ea955f5c1d9a188eee1196f72b108890751525d266113add4","source":{"kind":"arxiv","id":"2402.14207","version":2},"attestation_state":"computed","paper":{"title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Monica S. Lam, Omar Khattab, Peter Xu, Theodore A. Kanell, Yijia Shao, Yucheng Jiang","submitted_at":"2024-02-22T01:20:17Z","abstract_excerpt":"We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. This underexplored problem poses new challenges at the pre-writing stage, including how to research the topic and prepare an outline prior to writing. We propose STORM, a writing system for the Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. STORM models the pre-writing stage by (1) discovering diverse perspectives in researching the given topic, (2) simulating conversations where writers carrying"},"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":"2402.14207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T01:20:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a09115c1f0528025f2ed26e090b182280c98ef5f8354be0831e2f4e1ef50687","abstract_canon_sha256":"e3d900ea77cd4a29df375381bb34806d00bf11dcee56e2e289e5c4dc862e0d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:10.944509Z","signature_b64":"lredT57f7TQLlTbVyXT/j1yT0eK8Wm+OUI4MpIENNNzLXnBa3HscId3qbqOopWSZOsZ6hPRwGvpkFotXJaWVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"facdf016f342745ea955f5c1d9a188eee1196f72b108890751525d266113add4","last_reissued_at":"2026-07-05T08:05:10.944034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:10.944034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Monica S. Lam, Omar Khattab, Peter Xu, Theodore A. Kanell, Yijia Shao, Yucheng Jiang","submitted_at":"2024-02-22T01:20:17Z","abstract_excerpt":"We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. This underexplored problem poses new challenges at the pre-writing stage, including how to research the topic and prepare an outline prior to writing. We propose STORM, a writing system for the Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. STORM models the pre-writing stage by (1) discovering diverse perspectives in researching the given topic, (2) simulating conversations where writers carrying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14207","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/2402.14207/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":"2402.14207","created_at":"2026-07-05T08:05:10.944092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14207v2","created_at":"2026-07-05T08:05:10.944092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14207","created_at":"2026-07-05T08:05:10.944092+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LG7AFXTIJ2F","created_at":"2026-07-05T08:05:10.944092+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LG7AFXTIJ2F5KKV","created_at":"2026-07-05T08:05:10.944092+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LG7AFXT","created_at":"2026-07-05T08:05:10.944092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26246","citing_title":"Lacuna: A Research Map for Machine Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31478","citing_title":"One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11060","citing_title":"Code Researcher: Deep Research Agent for Large Systems Code and Commit History","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13742","citing_title":"Spatial Balancing: Designing an LLM-Powered Spatial Externalization Interface for Iterative Science Communication Writing","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08104","citing_title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11763","citing_title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08872","citing_title":"Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02988","citing_title":"Self-Optimizing Multi-Agent Systems for Deep Research","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":285,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53","json":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53.json","graph_json":"https://pith.science/api/pith-number/7LG7AFXTIJ2F5KKV6XA5TIMI53/graph.json","events_json":"https://pith.science/api/pith-number/7LG7AFXTIJ2F5KKV6XA5TIMI53/events.json","paper":"https://pith.science/paper/7LG7AFXT"},"agent_actions":{"view_html":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53","download_json":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53.json","view_paper":"https://pith.science/paper/7LG7AFXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14207&json=true","fetch_graph":"https://pith.science/api/pith-number/7LG7AFXTIJ2F5KKV6XA5TIMI53/graph.json","fetch_events":"https://pith.science/api/pith-number/7LG7AFXTIJ2F5KKV6XA5TIMI53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53/action/storage_attestation","attest_author":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53/action/author_attestation","sign_citation":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53/action/citation_signature","submit_replication":"https://pith.science/pith/7LG7AFXTIJ2F5KKV6XA5TIMI53/action/replication_record"}},"created_at":"2026-07-05T08:05:10.944092+00:00","updated_at":"2026-07-05T08:05:10.944092+00:00"}