{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YKP5TTTSRAV2YTNY5MWLHCWSRG","short_pith_number":"pith:YKP5TTTS","schema_version":"1.0","canonical_sha256":"c29fd9ce72882bac4db8eb2cb38ad289a5d9f98a0f90f08e66619dd64b4dc384","source":{"kind":"arxiv","id":"2504.00824","version":2},"attestation_state":"computed","paper":{"title":"ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Schneider, Huaye Zeng, Ping Nie, Wenhu Chen, Xiang Yue, Xueguang Ma, Yi Lu, Yubo Wang, Yuxuan Zhang, Zhiheng Lyu","submitted_at":"2025-04-01T14:12:14Z","abstract_excerpt":"Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly improved factual accuracy in general-purpose text generation, their ability to support professional academic writing remains limited. In this work, we introduce ScholarCopilot, a unified framework designed to enhance existing large language models for generating professional academic articles with accurate and contextually relevant citations. ScholarCopilot dynamically determines when to retrieve scholarly reference"},"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":"2504.00824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:12:14Z","cross_cats_sorted":[],"title_canon_sha256":"aa0277de768d9ff7588f9f18103a90bbefb12996b15c59baf9d742c46f5c1a2b","abstract_canon_sha256":"6cb94ae15758c2c2ab81dbf55a2262c905885beeaface6838d1343f56aed7815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:47.378806Z","signature_b64":"1OXpYo8Jbjh2n4hqz8UHIQ/1/eiyjbikqu8OUQ0PqeyHsZJatS0s1QApQYhmieGhGKyWVyMouq3GIjIV/1B/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c29fd9ce72882bac4db8eb2cb38ad289a5d9f98a0f90f08e66619dd64b4dc384","last_reissued_at":"2026-07-05T10:43:47.378172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:47.378172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Schneider, Huaye Zeng, Ping Nie, Wenhu Chen, Xiang Yue, Xueguang Ma, Yi Lu, Yubo Wang, Yuxuan Zhang, Zhiheng Lyu","submitted_at":"2025-04-01T14:12:14Z","abstract_excerpt":"Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly improved factual accuracy in general-purpose text generation, their ability to support professional academic writing remains limited. In this work, we introduce ScholarCopilot, a unified framework designed to enhance existing large language models for generating professional academic articles with accurate and contextually relevant citations. ScholarCopilot dynamically determines when to retrieve scholarly reference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00824","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/2504.00824/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":"2504.00824","created_at":"2026-07-05T10:43:47.378239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00824v2","created_at":"2026-07-05T10:43:47.378239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00824","created_at":"2026-07-05T10:43:47.378239+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKP5TTTSRAV2","created_at":"2026-07-05T10:43:47.378239+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKP5TTTSRAV2YTNY","created_at":"2026-07-05T10:43:47.378239+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKP5TTTS","created_at":"2026-07-05T10:43:47.378239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20622","citing_title":"pAI/MSc: ML Theory Research with Humans on the Loop","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04562","citing_title":"Paper Espresso: From Paper Overload to Research Insight","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG","json":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG.json","graph_json":"https://pith.science/api/pith-number/YKP5TTTSRAV2YTNY5MWLHCWSRG/graph.json","events_json":"https://pith.science/api/pith-number/YKP5TTTSRAV2YTNY5MWLHCWSRG/events.json","paper":"https://pith.science/paper/YKP5TTTS"},"agent_actions":{"view_html":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG","download_json":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG.json","view_paper":"https://pith.science/paper/YKP5TTTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00824&json=true","fetch_graph":"https://pith.science/api/pith-number/YKP5TTTSRAV2YTNY5MWLHCWSRG/graph.json","fetch_events":"https://pith.science/api/pith-number/YKP5TTTSRAV2YTNY5MWLHCWSRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG/action/storage_attestation","attest_author":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG/action/author_attestation","sign_citation":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG/action/citation_signature","submit_replication":"https://pith.science/pith/YKP5TTTSRAV2YTNY5MWLHCWSRG/action/replication_record"}},"created_at":"2026-07-05T10:43:47.378239+00:00","updated_at":"2026-07-05T10:43:47.378239+00:00"}