{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TFWDP3CO62MYKUKHPC2I4PNLVG","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":"adc7ae33206a7278c3484d6a37ba75a3a2d1e031b7fd2abf880cb3d72ebfb556","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-18T13:04:55Z","title_canon_sha256":"3f425204a9f85aa343dab1a4414b9095d4914e3b47713779811ad4a70a270a8b"},"schema_version":"1.0","source":{"id":"2503.14227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14227","created_at":"2026-07-05T10:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14227v1","created_at":"2026-07-05T10:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14227","created_at":"2026-07-05T10:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"TFWDP3CO62MY","created_at":"2026-07-05T10:33:58Z"},{"alias_kind":"pith_short_16","alias_value":"TFWDP3CO62MYKUKH","created_at":"2026-07-05T10:33:58Z"},{"alias_kind":"pith_short_8","alias_value":"TFWDP3CO","created_at":"2026-07-05T10:33:58Z"}],"graph_snapshots":[{"event_id":"sha256:1e90eced3919c897e35182c2eff88cb5622f1fad5b15aa942dfdcefb6dd43e9e","target":"graph","created_at":"2026-07-05T10:33:58Z","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/2503.14227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of tools has extended the capabilities of language models (LMs) beyond vanilla text generation to versatile scenarios. However, tool-augmented language models (TaLMs) often assume 'perfect' information access and tool availability, which may not hold in the real world. To systematically study TaLMs' imperfections, we introduce the FAIL-TALMS benchmark, featuring two major failures: under-specified user queries and non-available tools. FAIL-TALMS contains 1,749 examples using 906 tools across 21 categories, including single- and multi-tool usage. We evaluate top-performing propr","authors_text":"Eduardo Trevi\\~no, Graham Neubig, Hugo Contant, James Ngai, Zora Zhiruo Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-18T13:04:55Z","title":"Benchmarking Failures in Tool-Augmented Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14227","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":"sha256:1c4026d808c5bccf0aa8fae416555e957582327e81a95115554152bbd43868a2","target":"record","created_at":"2026-07-05T10:33:58Z","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":"adc7ae33206a7278c3484d6a37ba75a3a2d1e031b7fd2abf880cb3d72ebfb556","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-18T13:04:55Z","title_canon_sha256":"3f425204a9f85aa343dab1a4414b9095d4914e3b47713779811ad4a70a270a8b"},"schema_version":"1.0","source":{"id":"2503.14227","kind":"arxiv","version":1}},"canonical_sha256":"996c37ec4ef69985514778b48e3daba9b0f42ce50c89e2bb588ae9e9b2c6821b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"996c37ec4ef69985514778b48e3daba9b0f42ce50c89e2bb588ae9e9b2c6821b","first_computed_at":"2026-07-05T10:33:58.281293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:58.281293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Be6KnWx6y6Fm3vgW6WXD7Jsk8mELgrATYyeOoeXJgKrtsZkhU85L0or0qmuSRnnNv2tYyhDcSaEe/Gy5nLZgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:58.281937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c4026d808c5bccf0aa8fae416555e957582327e81a95115554152bbd43868a2","sha256:1e90eced3919c897e35182c2eff88cb5622f1fad5b15aa942dfdcefb6dd43e9e"],"state_sha256":"d03da9c786055cd5c09cbce792155dfeaf4ca80ebb961dc07132b1c37b5a9a51"}