{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BWGMSZ74OK733FD7O64H6VLL6G","short_pith_number":"pith:BWGMSZ74","schema_version":"1.0","canonical_sha256":"0d8cc967fc72bfbd947f77b87f556bf1b0fdacc6b3c151750ef4d450df64b241","source":{"kind":"arxiv","id":"2310.04945","version":1},"attestation_state":"computed","paper":{"title":"Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Zheng, Da Tang, Ke Sun, Liang Zhao, Xun Zhou, Yingtong Bu, Yukun Ma, Zheng Zhang","submitted_at":"2023-10-07T23:29:00Z","abstract_excerpt":"This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The methodology has three main components: 1) Carefully blending in-domain and general-purpose data during fine-tuning to achieve an optimal balance between general and specialized capabilities; 2) Designing a comprehensive evaluation framework with 45 questions tailored to assess performance on functionally relevant dimensions like reliability, consistency, and business "},"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":"2310.04945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-07T23:29:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4171dd97e57c772803f7e4eef6e287541f60fb2022e346c17bc160fc62a73124","abstract_canon_sha256":"9172893f2555d820b487c9871a92a9cc084156b3573c81eb89ab74981d618bfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:24.796228Z","signature_b64":"gnZ9/x7ErmzwsGKv8m6vWtmHLCzVVLfh/tcyRWterkMfbab3teAys9dj8oe5UUZxXOKcE1k5aiLCIYQHtnRQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d8cc967fc72bfbd947f77b87f556bf1b0fdacc6b3c151750ef4d450df64b241","last_reissued_at":"2026-07-05T06:58:24.795755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:24.795755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Zheng, Da Tang, Ke Sun, Liang Zhao, Xun Zhou, Yingtong Bu, Yukun Ma, Zheng Zhang","submitted_at":"2023-10-07T23:29:00Z","abstract_excerpt":"This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The methodology has three main components: 1) Carefully blending in-domain and general-purpose data during fine-tuning to achieve an optimal balance between general and specialized capabilities; 2) Designing a comprehensive evaluation framework with 45 questions tailored to assess performance on functionally relevant dimensions like reliability, consistency, and business "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04945","kind":"arxiv","version":1},"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/2310.04945/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":"2310.04945","created_at":"2026-07-05T06:58:24.795814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04945v1","created_at":"2026-07-05T06:58:24.795814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04945","created_at":"2026-07-05T06:58:24.795814+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWGMSZ74OK73","created_at":"2026-07-05T06:58:24.795814+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWGMSZ74OK733FD7","created_at":"2026-07-05T06:58:24.795814+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWGMSZ74","created_at":"2026-07-05T06:58:24.795814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.07177","citing_title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G","json":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G.json","graph_json":"https://pith.science/api/pith-number/BWGMSZ74OK733FD7O64H6VLL6G/graph.json","events_json":"https://pith.science/api/pith-number/BWGMSZ74OK733FD7O64H6VLL6G/events.json","paper":"https://pith.science/paper/BWGMSZ74"},"agent_actions":{"view_html":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G","download_json":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G.json","view_paper":"https://pith.science/paper/BWGMSZ74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04945&json=true","fetch_graph":"https://pith.science/api/pith-number/BWGMSZ74OK733FD7O64H6VLL6G/graph.json","fetch_events":"https://pith.science/api/pith-number/BWGMSZ74OK733FD7O64H6VLL6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G/action/storage_attestation","attest_author":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G/action/author_attestation","sign_citation":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G/action/citation_signature","submit_replication":"https://pith.science/pith/BWGMSZ74OK733FD7O64H6VLL6G/action/replication_record"}},"created_at":"2026-07-05T06:58:24.795814+00:00","updated_at":"2026-07-05T06:58:24.795814+00:00"}