{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5E3VCU3P2CENEMMXNXN7RVIS64","short_pith_number":"pith:5E3VCU3P","schema_version":"1.0","canonical_sha256":"e93751536fd088d231976ddbf8d512f730014f232f44a8b47a83baa762b5d20e","source":{"kind":"arxiv","id":"2501.05255","version":2},"attestation_state":"computed","paper":{"title":"CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Andrey Boytsov, Anne Goujon, Cedric Lothritz, Jacques Klein, Saad Ezzini, Tegawend\\'e F. Bissyand\\'e, Ulrick Ble, Xunzhu Tang, Yewei Song","submitted_at":"2025-01-09T14:12:43Z","abstract_excerpt":"API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is particularly challenging in scenarios requiring multi-step interactions with complex parameterization and nested API dependencies. Addressing these challenges, this work contributes to the evaluation and assessment of AI-based software development through three key advancements: (1) the introduction of a novel dataset specifically designed for benchmarking API function selection, parameter generation, and nested API "},"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":"2501.05255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-09T14:12:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0c3084b28547b2ad14a7b036fbff0866d37c2c7b08c7f3a6376e8b6205706886","abstract_canon_sha256":"6ac0e5d1bdee93de1f0a19c4bc3f33912cf5cf631d758c260c0158ce2a0b89ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:14.857769Z","signature_b64":"OXG0Bepoiuitn7y8EMMwPU0tD5Dow1Rz3cPd0YfS8oum7tzuPVwwVbqstksWD4aLj1x61hFr7/Ut/1CUkCL2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e93751536fd088d231976ddbf8d512f730014f232f44a8b47a83baa762b5d20e","last_reissued_at":"2026-07-05T10:53:14.857214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:14.857214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Andrey Boytsov, Anne Goujon, Cedric Lothritz, Jacques Klein, Saad Ezzini, Tegawend\\'e F. Bissyand\\'e, Ulrick Ble, Xunzhu Tang, Yewei Song","submitted_at":"2025-01-09T14:12:43Z","abstract_excerpt":"API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is particularly challenging in scenarios requiring multi-step interactions with complex parameterization and nested API dependencies. Addressing these challenges, this work contributes to the evaluation and assessment of AI-based software development through three key advancements: (1) the introduction of a novel dataset specifically designed for benchmarking API function selection, parameter generation, and nested API "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05255","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/2501.05255/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":"2501.05255","created_at":"2026-07-05T10:53:14.857278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05255v2","created_at":"2026-07-05T10:53:14.857278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05255","created_at":"2026-07-05T10:53:14.857278+00:00"},{"alias_kind":"pith_short_12","alias_value":"5E3VCU3P2CEN","created_at":"2026-07-05T10:53:14.857278+00:00"},{"alias_kind":"pith_short_16","alias_value":"5E3VCU3P2CENEMMX","created_at":"2026-07-05T10:53:14.857278+00:00"},{"alias_kind":"pith_short_8","alias_value":"5E3VCU3P","created_at":"2026-07-05T10:53:14.857278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09395","citing_title":"Empirical Study for Structured Output Control in LLMs for Software Engineering","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64","json":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64.json","graph_json":"https://pith.science/api/pith-number/5E3VCU3P2CENEMMXNXN7RVIS64/graph.json","events_json":"https://pith.science/api/pith-number/5E3VCU3P2CENEMMXNXN7RVIS64/events.json","paper":"https://pith.science/paper/5E3VCU3P"},"agent_actions":{"view_html":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64","download_json":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64.json","view_paper":"https://pith.science/paper/5E3VCU3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05255&json=true","fetch_graph":"https://pith.science/api/pith-number/5E3VCU3P2CENEMMXNXN7RVIS64/graph.json","fetch_events":"https://pith.science/api/pith-number/5E3VCU3P2CENEMMXNXN7RVIS64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64/action/storage_attestation","attest_author":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64/action/author_attestation","sign_citation":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64/action/citation_signature","submit_replication":"https://pith.science/pith/5E3VCU3P2CENEMMXNXN7RVIS64/action/replication_record"}},"created_at":"2026-07-05T10:53:14.857278+00:00","updated_at":"2026-07-05T10:53:14.857278+00:00"}