{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CENLEIBTTTO5FCISHDNADBQJJB","short_pith_number":"pith:CENLEIBT","schema_version":"1.0","canonical_sha256":"111ab220339cddd2891238da018609487d9b3d1c6938a3ed0ac85a197e6eb522","source":{"kind":"arxiv","id":"2606.03657","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongyi Wen, Jinhan Niu, Jinnuo Liu, Yue Peng","submitted_at":"2026-06-02T13:46:04Z","abstract_excerpt":"Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-output contracts, semantics, and executable usage patterns. Existing novel-API benchmarks are typically static, rely on coarse pass/fail metrics, or use synthetic APIs that may not reflect real library evolution. We introduce NovelAPIBench, a fully automated dynamic benchmark that, for any base model and target library, discovers novel APIs, extracts decomposed knowledge bundles, g"},"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":"2606.03657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T13:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"d5e517ba98eeb9116505818c41515e2d8fadf3740a6860c6500c5942129e52b6","abstract_canon_sha256":"cfd0d93b8f49dfd3cffaf55564effbec85b5a6f2b72faac5961101cc4f9cac39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:03.708211Z","signature_b64":"9uc8653Gucn35ZHZWOp0MhIOnHqoKqfTiC2UPzod+r7VjRh/kLYzDcAVScWHINPNrMTpwW5Y1F21RglOQStrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111ab220339cddd2891238da018609487d9b3d1c6938a3ed0ac85a197e6eb522","last_reissued_at":"2026-06-03T01:06:03.707782Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:03.707782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongyi Wen, Jinhan Niu, Jinnuo Liu, Yue Peng","submitted_at":"2026-06-02T13:46:04Z","abstract_excerpt":"Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-output contracts, semantics, and executable usage patterns. Existing novel-API benchmarks are typically static, rely on coarse pass/fail metrics, or use synthetic APIs that may not reflect real library evolution. We introduce NovelAPIBench, a fully automated dynamic benchmark that, for any base model and target library, discovers novel APIs, extracts decomposed knowledge bundles, g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03657","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/2606.03657/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":"2606.03657","created_at":"2026-06-03T01:06:03.707834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03657v1","created_at":"2026-06-03T01:06:03.707834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03657","created_at":"2026-06-03T01:06:03.707834+00:00"},{"alias_kind":"pith_short_12","alias_value":"CENLEIBTTTO5","created_at":"2026-06-03T01:06:03.707834+00:00"},{"alias_kind":"pith_short_16","alias_value":"CENLEIBTTTO5FCIS","created_at":"2026-06-03T01:06:03.707834+00:00"},{"alias_kind":"pith_short_8","alias_value":"CENLEIBT","created_at":"2026-06-03T01:06:03.707834+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/CENLEIBTTTO5FCISHDNADBQJJB","json":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB.json","graph_json":"https://pith.science/api/pith-number/CENLEIBTTTO5FCISHDNADBQJJB/graph.json","events_json":"https://pith.science/api/pith-number/CENLEIBTTTO5FCISHDNADBQJJB/events.json","paper":"https://pith.science/paper/CENLEIBT"},"agent_actions":{"view_html":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB","download_json":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB.json","view_paper":"https://pith.science/paper/CENLEIBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03657&json=true","fetch_graph":"https://pith.science/api/pith-number/CENLEIBTTTO5FCISHDNADBQJJB/graph.json","fetch_events":"https://pith.science/api/pith-number/CENLEIBTTTO5FCISHDNADBQJJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB/action/storage_attestation","attest_author":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB/action/author_attestation","sign_citation":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB/action/citation_signature","submit_replication":"https://pith.science/pith/CENLEIBTTTO5FCISHDNADBQJJB/action/replication_record"}},"created_at":"2026-06-03T01:06:03.707834+00:00","updated_at":"2026-06-03T01:06:03.707834+00:00"}