{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2BL7IKBMD6VB4ZMOYFNMSQ76WX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d465eb609ed18b194cce88ae32beebc83a53338350e4ba600de1485a51eddb4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-30T15:21:51Z","title_canon_sha256":"dc6ecb1226e302d75c8352ec4fb6f4c6cc08f7f379b3c3603c18baedbe489f45"},"schema_version":"1.0","source":{"id":"2505.10570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10570","created_at":"2026-07-05T11:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10570v1","created_at":"2026-07-05T11:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10570","created_at":"2026-07-05T11:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"2BL7IKBMD6VB","created_at":"2026-07-05T11:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"2BL7IKBMD6VB4ZMO","created_at":"2026-07-05T11:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"2BL7IKBM","created_at":"2026-07-05T11:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:5a403bba3e6608d4f8f0bc8dd1c075bc407dc3f1ba1b23eb127e71b673d7ebad","target":"graph","created_at":"2026-07-05T11:04:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.10570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ibrahim Abdelaziz, Kinjal Basu, Kiran Kate, Mayank Agarwal, Subhajit Chaudhury, Tejaswini Pedapati, Vijil Chenthamarakshan, Yara Rizk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-30T15:21:51Z","title":"LongFuncEval: Measuring the effectiveness of long context models for function calling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10570","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fac721b8312b4d8199d06e0a96909fe01a45ab83e671a7f9bed8c0982873fb69","target":"record","created_at":"2026-07-05T11:04:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d465eb609ed18b194cce88ae32beebc83a53338350e4ba600de1485a51eddb4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-30T15:21:51Z","title_canon_sha256":"dc6ecb1226e302d75c8352ec4fb6f4c6cc08f7f379b3c3603c18baedbe489f45"},"schema_version":"1.0","source":{"id":"2505.10570","kind":"arxiv","version":1}},"canonical_sha256":"d057f4282c1faa1e658ec15ac943feb5f4abedc5556d886f79c0fafca21d4c89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d057f4282c1faa1e658ec15ac943feb5f4abedc5556d886f79c0fafca21d4c89","first_computed_at":"2026-07-05T11:04:01.768444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:01.768444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Lw5uj12Y9Co4mOoKn3ygTK2654F0nb56gafrUYs5rRyIsZc0ftP6Lnahr4RKn3X7uAln2+1/dbhFJMvCC3BDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:01.768913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fac721b8312b4d8199d06e0a96909fe01a45ab83e671a7f9bed8c0982873fb69","sha256:5a403bba3e6608d4f8f0bc8dd1c075bc407dc3f1ba1b23eb127e71b673d7ebad"],"state_sha256":"2d2245893544f6eaac3038395cf5efa946f6f326336f7664298a9a7a34676369"}