{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJPN47LKQ5ZDL2S5HRFSROCPAM","short_pith_number":"pith:BJPN47LK","schema_version":"1.0","canonical_sha256":"0a5ede7d6a877235ea5d3c4b28b84f032ac5fa54ed94ab26a50d00d8e16462bf","source":{"kind":"arxiv","id":"2402.15491","version":2},"attestation_state":"computed","paper":{"title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Asim Munawar, Ibrahim Abdelaziz, Kinjal Basu, Luis A. Lastras, Maxwell Crouse, Pavan Kapanipathi, Sadhana Kumaravel, Soham Dan, Subhajit Chaudhury, Vinod Muthusamy","submitted_at":"2024-02-23T18:30:49Z","abstract_excerpt":"There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire sufficient quantities of train and test data that involve calls to tools / APIs. Two lines of research have emerged as the predominant strategies for addressing this challenge. The first has focused on synthetic data generation techniques, while the second has involved curating task-adjacent datasets which can be transformed into API / Tool-based tasks. In this paper"},"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":"2402.15491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T18:30:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7215bd5e340fbe35708fa843761d9ee461cd7fd7568b9e71790e0ff043a6983","abstract_canon_sha256":"57254a50104b0d8f131d695051770a428d6323a2a2e723d93ef0e5759c382ae4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:53.412723Z","signature_b64":"AWs/JYgVoA8jn9rXedKDMTvGvObEPlCPOhOJaKxq/Vvgru8m0xmFP+QOhZOxiESR6ASt/aiwSfL3K2cuFkCdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a5ede7d6a877235ea5d3c4b28b84f032ac5fa54ed94ab26a50d00d8e16462bf","last_reissued_at":"2026-07-05T08:20:53.412225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:53.412225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Asim Munawar, Ibrahim Abdelaziz, Kinjal Basu, Luis A. Lastras, Maxwell Crouse, Pavan Kapanipathi, Sadhana Kumaravel, Soham Dan, Subhajit Chaudhury, Vinod Muthusamy","submitted_at":"2024-02-23T18:30:49Z","abstract_excerpt":"There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire sufficient quantities of train and test data that involve calls to tools / APIs. Two lines of research have emerged as the predominant strategies for addressing this challenge. The first has focused on synthetic data generation techniques, while the second has involved curating task-adjacent datasets which can be transformed into API / Tool-based tasks. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15491","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/2402.15491/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":"2402.15491","created_at":"2026-07-05T08:20:53.412282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15491v2","created_at":"2026-07-05T08:20:53.412282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15491","created_at":"2026-07-05T08:20:53.412282+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJPN47LKQ5ZD","created_at":"2026-07-05T08:20:53.412282+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJPN47LKQ5ZDL2S5","created_at":"2026-07-05T08:20:53.412282+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJPN47LK","created_at":"2026-07-05T08:20:53.412282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03444","citing_title":"An Auditable Agent Platform For Automated Molecular Optimisation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM","json":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM.json","graph_json":"https://pith.science/api/pith-number/BJPN47LKQ5ZDL2S5HRFSROCPAM/graph.json","events_json":"https://pith.science/api/pith-number/BJPN47LKQ5ZDL2S5HRFSROCPAM/events.json","paper":"https://pith.science/paper/BJPN47LK"},"agent_actions":{"view_html":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM","download_json":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM.json","view_paper":"https://pith.science/paper/BJPN47LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15491&json=true","fetch_graph":"https://pith.science/api/pith-number/BJPN47LKQ5ZDL2S5HRFSROCPAM/graph.json","fetch_events":"https://pith.science/api/pith-number/BJPN47LKQ5ZDL2S5HRFSROCPAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM/action/storage_attestation","attest_author":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM/action/author_attestation","sign_citation":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM/action/citation_signature","submit_replication":"https://pith.science/pith/BJPN47LKQ5ZDL2S5HRFSROCPAM/action/replication_record"}},"created_at":"2026-07-05T08:20:53.412282+00:00","updated_at":"2026-07-05T08:20:53.412282+00:00"}