{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QSPPGZ325M6VQACL5RH6IXO73I","short_pith_number":"pith:QSPPGZ32","schema_version":"1.0","canonical_sha256":"849ef3677aeb3d58004bec4fe45ddfda1f5a9452031769bdc1a263c4cc69e853","source":{"kind":"arxiv","id":"2509.20172","version":7},"attestation_state":"computed","paper":{"title":"Benchmarking Web API Integration Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Amir Molzam Sharifloo, Daniel Maninger, Jannis Brugger, Leon Chemnitz, Mira Mezini","submitted_at":"2025-09-24T14:36:44Z","abstract_excerpt":"API integration is a cornerstone of our digital infrastructure, enabling software systems to connect and interact. However, as shown by many studies, writing or generating correct code to invoke APIs, particularly web APIs, is challenging. Although large language models (LLMs) have become popular in software development, their effectiveness in automating the generation of web API integration code remains unexplored. In order to address this, we present WAPIIBench, a dataset and evaluation pipeline designed to assess the ability of LLMs to generate web API invocation code. Our experiments with "},"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":"2509.20172","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-09-24T14:36:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"70d72abe9f8c3cb943d04250911ef72fd8e386f504ce5c6c2f40d59abc48d57e","abstract_canon_sha256":"6a14b99fca6178b8362e69e65c93d8c9b6c3bbd581ed3fcbdeb8b8c82f1b4d99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:10.492146Z","signature_b64":"7unf+dUkZwTA7Nj+0e6NiM3t1T5FkTFeHAQtUkefKJeAGD1dE7oXX7RZkoZRIuaI30UF0KnD/NYaQziXlcoWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"849ef3677aeb3d58004bec4fe45ddfda1f5a9452031769bdc1a263c4cc69e853","last_reissued_at":"2026-07-07T02:17:10.491262Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:10.491262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Web API Integration Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Amir Molzam Sharifloo, Daniel Maninger, Jannis Brugger, Leon Chemnitz, Mira Mezini","submitted_at":"2025-09-24T14:36:44Z","abstract_excerpt":"API integration is a cornerstone of our digital infrastructure, enabling software systems to connect and interact. However, as shown by many studies, writing or generating correct code to invoke APIs, particularly web APIs, is challenging. Although large language models (LLMs) have become popular in software development, their effectiveness in automating the generation of web API integration code remains unexplored. In order to address this, we present WAPIIBench, a dataset and evaluation pipeline designed to assess the ability of LLMs to generate web API invocation code. Our experiments with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20172","kind":"arxiv","version":7},"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/2509.20172/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":"2509.20172","created_at":"2026-07-07T02:17:10.491398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.20172v7","created_at":"2026-07-07T02:17:10.491398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20172","created_at":"2026-07-07T02:17:10.491398+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSPPGZ325M6V","created_at":"2026-07-07T02:17:10.491398+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSPPGZ325M6VQACL","created_at":"2026-07-07T02:17:10.491398+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSPPGZ32","created_at":"2026-07-07T02:17:10.491398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I","json":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I.json","graph_json":"https://pith.science/api/pith-number/QSPPGZ325M6VQACL5RH6IXO73I/graph.json","events_json":"https://pith.science/api/pith-number/QSPPGZ325M6VQACL5RH6IXO73I/events.json","paper":"https://pith.science/paper/QSPPGZ32"},"agent_actions":{"view_html":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I","download_json":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I.json","view_paper":"https://pith.science/paper/QSPPGZ32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.20172&json=true","fetch_graph":"https://pith.science/api/pith-number/QSPPGZ325M6VQACL5RH6IXO73I/graph.json","fetch_events":"https://pith.science/api/pith-number/QSPPGZ325M6VQACL5RH6IXO73I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I/action/storage_attestation","attest_author":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I/action/author_attestation","sign_citation":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I/action/citation_signature","submit_replication":"https://pith.science/pith/QSPPGZ325M6VQACL5RH6IXO73I/action/replication_record"}},"created_at":"2026-07-07T02:17:10.491398+00:00","updated_at":"2026-07-07T02:17:10.491398+00:00"}