{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LJQ4GLHRZN5TDAK5GTOIW43XOG","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":"e2914462245d012702908fbfa180fecf1df7934553cacffd4cda5fde8f029c69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T23:09:15Z","title_canon_sha256":"c267ad02e709f1dd1862e4bfbbc5d6d4c3fd350be5781a20b024149ba221e0a9"},"schema_version":"1.0","source":{"id":"2402.09615","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09615","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09615v6","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09615","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_12","alias_value":"LJQ4GLHRZN5T","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_16","alias_value":"LJQ4GLHRZN5TDAK5","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_8","alias_value":"LJQ4GLHR","created_at":"2026-07-05T10:14:02Z"}],"graph_snapshots":[{"event_id":"sha256:97ce4ac27b70be0d943dba201f9020ef5b519c26190401199f636a6e23409985","target":"graph","created_at":"2026-07-05T10:14:02Z","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/2402.09615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce API Pack, a massive multi-programming language dataset containing over one million instruction-API calls for improving the API call generation capabilities of large language models. Our evaluation highlights three key findings: First, fine-tuning on API Pack enables open-source models to outperform GPT-3.5 and GPT-4 in generating code for entirely new API calls. We show this by fine-tuning CodeLlama-13B on 20,000 Python instances from API Pack. Second, fine-tuning on a large dataset in one language, combined with smaller datasets from others, improves API generation accuracy acros","authors_text":"Adriana Meza Soria, Rameswar Panda, Wei Sun, Yikang Shen, Zhen Guo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T23:09:15Z","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09615","kind":"arxiv","version":6},"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":"sha256:73608d80cb60e8e3dde77a68a4563ee39c8944c87e2edc74af2d975b004bd78d","target":"record","created_at":"2026-07-05T10:14:02Z","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":"e2914462245d012702908fbfa180fecf1df7934553cacffd4cda5fde8f029c69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T23:09:15Z","title_canon_sha256":"c267ad02e709f1dd1862e4bfbbc5d6d4c3fd350be5781a20b024149ba221e0a9"},"schema_version":"1.0","source":{"id":"2402.09615","kind":"arxiv","version":6}},"canonical_sha256":"5a61c32cf1cb7b31815d34dc8b737771b9e2046202b18bfe15a98a7a80f9f4f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a61c32cf1cb7b31815d34dc8b737771b9e2046202b18bfe15a98a7a80f9f4f8","first_computed_at":"2026-07-05T10:14:02.478277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:02.478277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zii/V7mTyNpbRkSrkXNuNQcnO0kQIWO4/q6tJGQeYi6AVJxOZ17WHlLem/g9S/9epQF9f69YTGzc9Ccn7OndBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:02.478784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09615","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73608d80cb60e8e3dde77a68a4563ee39c8944c87e2edc74af2d975b004bd78d","sha256:97ce4ac27b70be0d943dba201f9020ef5b519c26190401199f636a6e23409985"],"state_sha256":"8986846202430aaec86e2d57e7e0831e043041dab44c71799cccbcf24c9221bc"}