{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZFSDS2XNZPAODRSC6CDZJ7IPVG","short_pith_number":"pith:ZFSDS2XN","schema_version":"1.0","canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","source":{"kind":"arxiv","id":"2408.08343","version":2},"attestation_state":"computed","paper":{"title":"API-guided Dataset Synthesis to Finetune Large Code Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Shuai Wang, Zhendong Su, Zongjie Li","submitted_at":"2024-08-15T14:48:42Z","abstract_excerpt":"Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a vital role in aligning these models with specific requirements and enhancing their performance in particular domains. However, synthesizing high-quality SFT datasets poses a significant challenge due to the uneven quality of datasets and the scarcity of domain-specific datasets.\n  Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataSco"},"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":"2408.08343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-15T14:48:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d80ec9a30babf940120c80c73fec9aa61249da00972f67a03006a0bc3e688850","abstract_canon_sha256":"48416aa0a4c90168c08ac249b8984e454a3eedf3cd8b674204ed9d561ec5202a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:58.716150Z","signature_b64":"etsuCjRxDMu1rUNz4QhxDXEaUqA4pnH2gsoYrS+cslQSEjw4qlYHyXuSoj+Rk6Cu+hrgFe2O04FANGfjmxZgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","last_reissued_at":"2026-07-05T08:57:58.715622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:58.715622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"API-guided Dataset Synthesis to Finetune Large Code Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Shuai Wang, Zhendong Su, Zongjie Li","submitted_at":"2024-08-15T14:48:42Z","abstract_excerpt":"Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a vital role in aligning these models with specific requirements and enhancing their performance in particular domains. However, synthesizing high-quality SFT datasets poses a significant challenge due to the uneven quality of datasets and the scarcity of domain-specific datasets.\n  Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataSco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08343","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/2408.08343/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":"2408.08343","created_at":"2026-07-05T08:57:58.715677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08343v2","created_at":"2026-07-05T08:57:58.715677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08343","created_at":"2026-07-05T08:57:58.715677+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFSDS2XNZPAO","created_at":"2026-07-05T08:57:58.715677+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFSDS2XNZPAODRSC","created_at":"2026-07-05T08:57:58.715677+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFSDS2XN","created_at":"2026-07-05T08:57:58.715677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19262","citing_title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG","json":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG.json","graph_json":"https://pith.science/api/pith-number/ZFSDS2XNZPAODRSC6CDZJ7IPVG/graph.json","events_json":"https://pith.science/api/pith-number/ZFSDS2XNZPAODRSC6CDZJ7IPVG/events.json","paper":"https://pith.science/paper/ZFSDS2XN"},"agent_actions":{"view_html":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG","download_json":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG.json","view_paper":"https://pith.science/paper/ZFSDS2XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08343&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFSDS2XNZPAODRSC6CDZJ7IPVG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFSDS2XNZPAODRSC6CDZJ7IPVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/action/storage_attestation","attest_author":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/action/author_attestation","sign_citation":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/action/citation_signature","submit_replication":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/action/replication_record"}},"created_at":"2026-07-05T08:57:58.715677+00:00","updated_at":"2026-07-05T08:57:58.715677+00:00"}