{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZFSDS2XNZPAODRSC6CDZJ7IPVG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"48416aa0a4c90168c08ac249b8984e454a3eedf3cd8b674204ed9d561ec5202a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-15T14:48:42Z","title_canon_sha256":"d80ec9a30babf940120c80c73fec9aa61249da00972f67a03006a0bc3e688850"},"schema_version":"1.0","source":{"id":"2408.08343","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08343","created_at":"2026-07-05T08:57:58Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08343v2","created_at":"2026-07-05T08:57:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08343","created_at":"2026-07-05T08:57:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZFSDS2XNZPAO","created_at":"2026-07-05T08:57:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZFSDS2XNZPAODRSC","created_at":"2026-07-05T08:57:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZFSDS2XN","created_at":"2026-07-05T08:57:58Z"}],"graph_snapshots":[{"event_id":"sha256:7db6630980e5358c03f1a05b598e89021b3c04ec88766b065c944d343fd977a5","target":"graph","created_at":"2026-07-05T08:57:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.08343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daoyuan Wu, Shuai Wang, Zhendong Su, Zongjie Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-15T14:48:42Z","title":"API-guided Dataset Synthesis to Finetune Large Code Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08343","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a24bbb83dd30297e2aef7ec409684aea4d75cc96ab1765721ca3ed46f28745bf","target":"record","created_at":"2026-07-05T08:57:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"48416aa0a4c90168c08ac249b8984e454a3eedf3cd8b674204ed9d561ec5202a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-15T14:48:42Z","title_canon_sha256":"d80ec9a30babf940120c80c73fec9aa61249da00972f67a03006a0bc3e688850"},"schema_version":"1.0","source":{"id":"2408.08343","kind":"arxiv","version":2}},"canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","first_computed_at":"2026-07-05T08:57:58.715622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:58.715622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"etsuCjRxDMu1rUNz4QhxDXEaUqA4pnH2gsoYrS+cslQSEjw4qlYHyXuSoj+Rk6Cu+hrgFe2O04FANGfjmxZgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:58.716150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08343","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a24bbb83dd30297e2aef7ec409684aea4d75cc96ab1765721ca3ed46f28745bf","sha256:7db6630980e5358c03f1a05b598e89021b3c04ec88766b065c944d343fd977a5"],"state_sha256":"7355d992890ebdd835b7ec6d67ed5dc0e8c5d4c3d0aa13d3d8c5cc39b5caa997"}