{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2BL7IKBMD6VB4ZMOYFNMSQ76WX","short_pith_number":"pith:2BL7IKBM","schema_version":"1.0","canonical_sha256":"d057f4282c1faa1e658ec15ac943feb5f4abedc5556d886f79c0fafca21d4c89","source":{"kind":"arxiv","id":"2505.10570","version":1},"attestation_state":"computed","paper":{"title":"LongFuncEval: Measuring the effectiveness of long context models for function calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ibrahim Abdelaziz, Kinjal Basu, Kiran Kate, Mayank Agarwal, Subhajit Chaudhury, Tejaswini Pedapati, Vijil Chenthamarakshan, Yara Rizk","submitted_at":"2025-04-30T15:21:51Z","abstract_excerpt":"Multiple recent studies have documented large language models' (LLMs) performance on calling external tools/functions. Others focused on LLMs' abilities to handle longer context lengths. At the intersection of these areas lies another interesting problem: LLMs' abilities to accurately perform function calls in long context settings. Particularly, when calling tools, LLMs are encumbered by three predominant challenges: (1) a large catalog of tools, (2) long responses from the tool APIs, and (3) long multi-turn conversations. These challenges are particularly relevant to enterprise applications "},"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":"2505.10570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-30T15:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"dc6ecb1226e302d75c8352ec4fb6f4c6cc08f7f379b3c3603c18baedbe489f45","abstract_canon_sha256":"d465eb609ed18b194cce88ae32beebc83a53338350e4ba600de1485a51eddb4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:01.768913Z","signature_b64":"8Lw5uj12Y9Co4mOoKn3ygTK2654F0nb56gafrUYs5rRyIsZc0ftP6Lnahr4RKn3X7uAln2+1/dbhFJMvCC3BDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d057f4282c1faa1e658ec15ac943feb5f4abedc5556d886f79c0fafca21d4c89","last_reissued_at":"2026-07-05T11:04:01.768444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:01.768444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongFuncEval: Measuring the effectiveness of long context models for function calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ibrahim Abdelaziz, Kinjal Basu, Kiran Kate, Mayank Agarwal, Subhajit Chaudhury, Tejaswini Pedapati, Vijil Chenthamarakshan, Yara Rizk","submitted_at":"2025-04-30T15:21:51Z","abstract_excerpt":"Multiple recent studies have documented large language models' (LLMs) performance on calling external tools/functions. Others focused on LLMs' abilities to handle longer context lengths. At the intersection of these areas lies another interesting problem: LLMs' abilities to accurately perform function calls in long context settings. Particularly, when calling tools, LLMs are encumbered by three predominant challenges: (1) a large catalog of tools, (2) long responses from the tool APIs, and (3) long multi-turn conversations. These challenges are particularly relevant to enterprise applications "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10570","kind":"arxiv","version":1},"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/2505.10570/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":"2505.10570","created_at":"2026-07-05T11:04:01.768502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10570v1","created_at":"2026-07-05T11:04:01.768502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10570","created_at":"2026-07-05T11:04:01.768502+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BL7IKBMD6VB","created_at":"2026-07-05T11:04:01.768502+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BL7IKBMD6VB4ZMO","created_at":"2026-07-05T11:04:01.768502+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BL7IKBM","created_at":"2026-07-05T11:04:01.768502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25139","citing_title":"Buildrix: An Open Platform for Sharing and Benchmarking Agentic AI Skills in Building Engineering","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17519","citing_title":"Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30317","citing_title":"MCP Server Architecture Patterns for LLM-Integrated Applications","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24660","citing_title":"How Many Tools Should an LLM Agent See? A Chance-Corrected Answer","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10015","citing_title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX","json":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX.json","graph_json":"https://pith.science/api/pith-number/2BL7IKBMD6VB4ZMOYFNMSQ76WX/graph.json","events_json":"https://pith.science/api/pith-number/2BL7IKBMD6VB4ZMOYFNMSQ76WX/events.json","paper":"https://pith.science/paper/2BL7IKBM"},"agent_actions":{"view_html":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX","download_json":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX.json","view_paper":"https://pith.science/paper/2BL7IKBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10570&json=true","fetch_graph":"https://pith.science/api/pith-number/2BL7IKBMD6VB4ZMOYFNMSQ76WX/graph.json","fetch_events":"https://pith.science/api/pith-number/2BL7IKBMD6VB4ZMOYFNMSQ76WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX/action/storage_attestation","attest_author":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX/action/author_attestation","sign_citation":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX/action/citation_signature","submit_replication":"https://pith.science/pith/2BL7IKBMD6VB4ZMOYFNMSQ76WX/action/replication_record"}},"created_at":"2026-07-05T11:04:01.768502+00:00","updated_at":"2026-07-05T11:04:01.768502+00:00"}