{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LJQ4GLHRZN5TDAK5GTOIW43XOG","short_pith_number":"pith:LJQ4GLHR","schema_version":"1.0","canonical_sha256":"5a61c32cf1cb7b31815d34dc8b737771b9e2046202b18bfe15a98a7a80f9f4f8","source":{"kind":"arxiv","id":"2402.09615","version":6},"attestation_state":"computed","paper":{"title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adriana Meza Soria, Rameswar Panda, Wei Sun, Yikang Shen, Zhen Guo","submitted_at":"2024-02-14T23:09:15Z","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"},"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":"2402.09615","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T23:09:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c267ad02e709f1dd1862e4bfbbc5d6d4c3fd350be5781a20b024149ba221e0a9","abstract_canon_sha256":"e2914462245d012702908fbfa180fecf1df7934553cacffd4cda5fde8f029c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:02.478784Z","signature_b64":"zii/V7mTyNpbRkSrkXNuNQcnO0kQIWO4/q6tJGQeYi6AVJxOZ17WHlLem/g9S/9epQF9f69YTGzc9Ccn7OndBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a61c32cf1cb7b31815d34dc8b737771b9e2046202b18bfe15a98a7a80f9f4f8","last_reissued_at":"2026-07-05T10:14:02.478277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:02.478277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adriana Meza Soria, Rameswar Panda, Wei Sun, Yikang Shen, Zhen Guo","submitted_at":"2024-02-14T23:09:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09615","kind":"arxiv","version":6},"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/2402.09615/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":"2402.09615","created_at":"2026-07-05T10:14:02.478343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09615v6","created_at":"2026-07-05T10:14:02.478343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09615","created_at":"2026-07-05T10:14:02.478343+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJQ4GLHRZN5T","created_at":"2026-07-05T10:14:02.478343+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJQ4GLHRZN5TDAK5","created_at":"2026-07-05T10:14:02.478343+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJQ4GLHR","created_at":"2026-07-05T10:14:02.478343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27763","citing_title":"Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG","json":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG.json","graph_json":"https://pith.science/api/pith-number/LJQ4GLHRZN5TDAK5GTOIW43XOG/graph.json","events_json":"https://pith.science/api/pith-number/LJQ4GLHRZN5TDAK5GTOIW43XOG/events.json","paper":"https://pith.science/paper/LJQ4GLHR"},"agent_actions":{"view_html":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG","download_json":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG.json","view_paper":"https://pith.science/paper/LJQ4GLHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09615&json=true","fetch_graph":"https://pith.science/api/pith-number/LJQ4GLHRZN5TDAK5GTOIW43XOG/graph.json","fetch_events":"https://pith.science/api/pith-number/LJQ4GLHRZN5TDAK5GTOIW43XOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG/action/storage_attestation","attest_author":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG/action/author_attestation","sign_citation":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG/action/citation_signature","submit_replication":"https://pith.science/pith/LJQ4GLHRZN5TDAK5GTOIW43XOG/action/replication_record"}},"created_at":"2026-07-05T10:14:02.478343+00:00","updated_at":"2026-07-05T10:14:02.478343+00:00"}