{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LDWH65QDO3W7AJWERV23QME4BR","short_pith_number":"pith:LDWH65QD","schema_version":"1.0","canonical_sha256":"58ec7f760376edf026c48d75b8309c0c51b04a2e87ed0aca930b52ae9b498654","source":{"kind":"arxiv","id":"2305.13225","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Leyang Cui, Tao Fang, Wei Bi, Xinting Huang, Yue Zhang","submitted_at":"2023-05-22T16:56:44Z","abstract_excerpt":"Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent studies demonstrate that open-sourced smaller foundational models, such as 7B-size LLaMA, can also display remarkable proficiency in tackling diverse tasks when fine-tuned using instruction-driven data. In this work, we investigate a practical problem setting where the primary focus is on one or a few particular tasks rather than general-purpose instruction following, and explore whether LLMs can be beneficial and furt"},"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":"2305.13225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:56:44Z","cross_cats_sorted":[],"title_canon_sha256":"65ff48be1d647ed3f79f938bcff4a7e2995f3d64d346daeeeb6b6043474e3d2a","abstract_canon_sha256":"f219e6787772331e54c8e32c32a6fd3bedcb21d4ee52e7c201065180dba2f145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:40.197695Z","signature_b64":"ZzgzUzveT1C9sKgXpO/L6dILMcSHtSOzxns0Wjdfxssv+oTyQkLaECcMoOGLQ7HDSz3sY3N6p0jDqjoLNmYdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ec7f760376edf026c48d75b8309c0c51b04a2e87ed0aca930b52ae9b498654","last_reissued_at":"2026-07-05T06:58:40.197139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:40.197139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Leyang Cui, Tao Fang, Wei Bi, Xinting Huang, Yue Zhang","submitted_at":"2023-05-22T16:56:44Z","abstract_excerpt":"Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent studies demonstrate that open-sourced smaller foundational models, such as 7B-size LLaMA, can also display remarkable proficiency in tackling diverse tasks when fine-tuned using instruction-driven data. In this work, we investigate a practical problem setting where the primary focus is on one or a few particular tasks rather than general-purpose instruction following, and explore whether LLMs can be beneficial and furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13225","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/2305.13225/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":"2305.13225","created_at":"2026-07-05T06:58:40.197199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13225v2","created_at":"2026-07-05T06:58:40.197199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13225","created_at":"2026-07-05T06:58:40.197199+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDWH65QDO3W7","created_at":"2026-07-05T06:58:40.197199+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDWH65QDO3W7AJWE","created_at":"2026-07-05T06:58:40.197199+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDWH65QD","created_at":"2026-07-05T06:58:40.197199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.08532","citing_title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR","json":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR.json","graph_json":"https://pith.science/api/pith-number/LDWH65QDO3W7AJWERV23QME4BR/graph.json","events_json":"https://pith.science/api/pith-number/LDWH65QDO3W7AJWERV23QME4BR/events.json","paper":"https://pith.science/paper/LDWH65QD"},"agent_actions":{"view_html":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR","download_json":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR.json","view_paper":"https://pith.science/paper/LDWH65QD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13225&json=true","fetch_graph":"https://pith.science/api/pith-number/LDWH65QDO3W7AJWERV23QME4BR/graph.json","fetch_events":"https://pith.science/api/pith-number/LDWH65QDO3W7AJWERV23QME4BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR/action/storage_attestation","attest_author":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR/action/author_attestation","sign_citation":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR/action/citation_signature","submit_replication":"https://pith.science/pith/LDWH65QDO3W7AJWERV23QME4BR/action/replication_record"}},"created_at":"2026-07-05T06:58:40.197199+00:00","updated_at":"2026-07-05T06:58:40.197199+00:00"}