{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZFSDS2XNZPAODRSC6CDZJ7IPVG","short_pith_number":"pith:ZFSDS2XN","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"},"canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","source":{"kind":"arxiv","id":"2408.08343","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZFSDS2XNZPAODRSC6CDZJ7IPVG","target":"record","payload":{"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"},"canonical_sha256":"c964396aedcbc0e1c642f08794fd0fa9a5572610032e84eebdf140498ca8329b","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"},"source_kind":"arxiv","source_id":"2408.08343","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0+rNkQJaruw934SVgZyj5VE5jPFoV2LoZjm6UBWFeZqdK/0soPkZUXBy5wXwNY2JZhJPbGGoPj5qFx8N/QlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:31:00.617093Z"},"content_sha256":"a24bbb83dd30297e2aef7ec409684aea4d75cc96ab1765721ca3ed46f28745bf","schema_version":"1.0","event_id":"sha256:a24bbb83dd30297e2aef7ec409684aea4d75cc96ab1765721ca3ed46f28745bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZFSDS2XNZPAODRSC6CDZJ7IPVG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHicaJ5iMw+UHIUz4v+SqxF6ekSq0ETxiOQMc8zHFOvlwiMBem0+ImsBYvBzi1xGwAltOJyVUed/dfZv63cVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:31:00.618001Z"},"content_sha256":"7db6630980e5358c03f1a05b598e89021b3c04ec88766b065c944d343fd977a5","schema_version":"1.0","event_id":"sha256:7db6630980e5358c03f1a05b598e89021b3c04ec88766b065c944d343fd977a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/bundle.json","state_url":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:31:00Z","links":{"resolver":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG","bundle":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/bundle.json","state":"https://pith.science/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFSDS2XNZPAODRSC6CDZJ7IPVG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7K3t5vuVz8YJgyUBRPLRR2WgqX0vT/qoCVnD6xOW87L3UlUQb441jG4xe4Px1dQ2/BmwbS5DH4dgaB+feChCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:31:00.626942Z","bundle_sha256":"a3ec12a0a990754696cfbdf8ed3b07da9ee0106850d1ec577373c2bb813f33fb"}}