{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FVP6GIBRY3XJLCMSB6ZBFEV5BL","short_pith_number":"pith:FVP6GIBR","canonical_record":{"source":{"id":"2607.04686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T05:25:21Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"e3d63eb65b479c16e3a2b29acfeb394a4204f39319d97820db22f074c0c463be","abstract_canon_sha256":"860f65879b66a466a7c674dc1cdcac46aae6c13217500c1aec13fb8757e20593"},"schema_version":"1.0"},"canonical_sha256":"2d5fe32031c6ee9589920fb21292bd0af5430bcdde79f8f5dc0a09166b157e52","source":{"kind":"arxiv","id":"2607.04686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04686","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04686v1","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04686","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"FVP6GIBRY3XJ","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"FVP6GIBRY3XJLCMS","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"FVP6GIBR","created_at":"2026-07-07T02:19:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FVP6GIBRY3XJLCMSB6ZBFEV5BL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T05:25:21Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"e3d63eb65b479c16e3a2b29acfeb394a4204f39319d97820db22f074c0c463be","abstract_canon_sha256":"860f65879b66a466a7c674dc1cdcac46aae6c13217500c1aec13fb8757e20593"},"schema_version":"1.0"},"canonical_sha256":"2d5fe32031c6ee9589920fb21292bd0af5430bcdde79f8f5dc0a09166b157e52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:57.835575Z","signature_b64":"b89iikuSJPYop2ZhMvCiUuOgrgLGBua5XehyvWYr1Ojfq0f+5ru5hicE79A4r54ermkaRWL0YYhp+BaX4EwpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d5fe32031c6ee9589920fb21292bd0af5430bcdde79f8f5dc0a09166b157e52","last_reissued_at":"2026-07-07T02:19:57.834805Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:57.834805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04686","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJrZaYDjnlOQwWMdiBfFdQC8OvGbR5ls8lUHAvk1f+qH+Ko5o2YGoNVRXOlRr2JYuuVWNrRt2qdA3M9Rp/olAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:53:21.566689Z"},"content_sha256":"7a2990dc59546d2802fae67dabfe86f9dee0ce1c470025b9348c9fec8a1c42ac","schema_version":"1.0","event_id":"sha256:7a2990dc59546d2802fae67dabfe86f9dee0ce1c470025b9348c9fec8a1c42ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FVP6GIBRY3XJLCMSB6ZBFEV5BL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Harsh Soni","submitted_at":"2026-07-06T05:25:21Z","abstract_excerpt":"Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate. Tool-required tasks return values the model wouldn't guess, forcing it to trust the tool while control tasks attach the same tools but should be answered directly. We label each tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04686","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/2607.04686/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKC8skYm8cPPbHytmk6X8RyWBBiDYNBLaCEG9ddoHW5k02V3W4XsUM/nWzk+9EDk0gvR6vmxba7YtsraOI1kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:53:21.567503Z"},"content_sha256":"e8ea2bb0909a6d8e328a1caa243a768e4a9230beb646ab95e0d9802463bba8bd","schema_version":"1.0","event_id":"sha256:e8ea2bb0909a6d8e328a1caa243a768e4a9230beb646ab95e0d9802463bba8bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/bundle.json","state_url":"https://pith.science/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:53:21Z","links":{"resolver":"https://pith.science/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL","bundle":"https://pith.science/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/bundle.json","state":"https://pith.science/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVP6GIBRY3XJLCMSB6ZBFEV5BL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FVP6GIBRY3XJLCMSB6ZBFEV5BL","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":"860f65879b66a466a7c674dc1cdcac46aae6c13217500c1aec13fb8757e20593","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T05:25:21Z","title_canon_sha256":"e3d63eb65b479c16e3a2b29acfeb394a4204f39319d97820db22f074c0c463be"},"schema_version":"1.0","source":{"id":"2607.04686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04686","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04686v1","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04686","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"FVP6GIBRY3XJ","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"FVP6GIBRY3XJLCMS","created_at":"2026-07-07T02:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"FVP6GIBR","created_at":"2026-07-07T02:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:e8ea2bb0909a6d8e328a1caa243a768e4a9230beb646ab95e0d9802463bba8bd","target":"graph","created_at":"2026-07-07T02:19:57Z","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/2607.04686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate. Tool-required tasks return values the model wouldn't guess, forcing it to trust the tool while control tasks attach the same tools but should be answered directly. We label each tr","authors_text":"Harsh Soni","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T05:25:21Z","title":"ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04686","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":"sha256:7a2990dc59546d2802fae67dabfe86f9dee0ce1c470025b9348c9fec8a1c42ac","target":"record","created_at":"2026-07-07T02:19:57Z","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":"860f65879b66a466a7c674dc1cdcac46aae6c13217500c1aec13fb8757e20593","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T05:25:21Z","title_canon_sha256":"e3d63eb65b479c16e3a2b29acfeb394a4204f39319d97820db22f074c0c463be"},"schema_version":"1.0","source":{"id":"2607.04686","kind":"arxiv","version":1}},"canonical_sha256":"2d5fe32031c6ee9589920fb21292bd0af5430bcdde79f8f5dc0a09166b157e52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d5fe32031c6ee9589920fb21292bd0af5430bcdde79f8f5dc0a09166b157e52","first_computed_at":"2026-07-07T02:19:57.834805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:57.834805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b89iikuSJPYop2ZhMvCiUuOgrgLGBua5XehyvWYr1Ojfq0f+5ru5hicE79A4r54ermkaRWL0YYhp+BaX4EwpBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:57.835575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a2990dc59546d2802fae67dabfe86f9dee0ce1c470025b9348c9fec8a1c42ac","sha256:e8ea2bb0909a6d8e328a1caa243a768e4a9230beb646ab95e0d9802463bba8bd"],"state_sha256":"ed7fa18e4354f79176aa01385657f06591f37247b34b1435e978d3b7006f385f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FR2J6qo/sdSHhxuzuMgBQ93P+IDMoE01V5GUHiKeETJSo5TctNI7fuEVxHAbuP906k8utQi57ApqalwgW/5VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:53:21.578714Z","bundle_sha256":"024fdd1807d83a9801eacec340d456ad2682eb3d5963e086263b9e5a74ddeb03"}}