{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UKVRXD7Y7JFWIQRQ3AVMGI63AO","short_pith_number":"pith:UKVRXD7Y","canonical_record":{"source":{"id":"2406.19228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:52:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac23566f48ff35db7bc1cf05d56a82f8052d603f155122125b4d865a78ee37e9","abstract_canon_sha256":"8231a414600652f2e478ae7aca8a18d68a6ec380ac867b64335a6d1d454a536f"},"schema_version":"1.0"},"canonical_sha256":"a2ab1b8ff8fa4b644230d82ac323db03a5451ab6f73864e3c805b214a92b0f3f","source":{"kind":"arxiv","id":"2406.19228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19228","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19228v1","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19228","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"UKVRXD7Y7JFW","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"UKVRXD7Y7JFWIQRQ","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"UKVRXD7Y","created_at":"2026-07-05T08:37:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UKVRXD7Y7JFWIQRQ3AVMGI63AO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:52:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac23566f48ff35db7bc1cf05d56a82f8052d603f155122125b4d865a78ee37e9","abstract_canon_sha256":"8231a414600652f2e478ae7aca8a18d68a6ec380ac867b64335a6d1d454a536f"},"schema_version":"1.0"},"canonical_sha256":"a2ab1b8ff8fa4b644230d82ac323db03a5451ab6f73864e3c805b214a92b0f3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:32.099602Z","signature_b64":"Aj4k7+T0GZG/J2YhInC2Cn9ACQ7EsvraJetgJoAAg0lDd0eAlupyqAYlP6AIg+2xkN0QNbllvERZQgVOtB3bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ab1b8ff8fa4b644230d82ac323db03a5451ab6f73864e3c805b214a92b0f3f","last_reissued_at":"2026-07-05T08:37:32.099147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:32.099147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19228","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":"2026-07-05T08:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3RVJ3xeez7F2aWJqLd9vol7rYv95O15YNXcXUj659UshKDz8XYaN7Le3jgsb7XjYIOUM6zhn+20VSx5g18eCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:21:22.199746Z"},"content_sha256":"1e0965513e8910f9acb68b4027eb2629a3b3f0cc377260579d94ab26a7b3b2b7","schema_version":"1.0","event_id":"sha256:1e0965513e8910f9acb68b4027eb2629a3b3f0cc377260579d94ab26a7b3b2b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UKVRXD7Y7JFWIQRQ3AVMGI63AO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tools Fail: Detecting Silent Errors in Faulty Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jimin Sun, So Yeon Min, Yingshan Chang, Yonatan Bisk","submitted_at":"2024-06-27T14:52:34Z","abstract_excerpt":"Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots. However, most ontologies and surveys of tool-use have assumed the core challenge for LLMs is choosing the tool. Instead, we introduce a framework for tools more broadly which guides us to explore a model's ability to detect \"silent\" tool errors, and reflect on how to plan. This more directly aligns with the increasingly popular use of models as tools. We provide an initial approach to failure recovery with promising results both on a controlle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19228","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/2406.19228/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":"2026-07-05T08:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2p78lSSgQNqUMZkh/xyP6bkn04HzADsSFzq0CpcPq02VoaI1dsZKpaF51AlzpNh6rMT+bYWRdPSH386VbEGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:21:22.200235Z"},"content_sha256":"2fd08b9d61f4d045cfda5b5ede206bf54035fa8112dc643196c40f1780024757","schema_version":"1.0","event_id":"sha256:2fd08b9d61f4d045cfda5b5ede206bf54035fa8112dc643196c40f1780024757"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/bundle.json","state_url":"https://pith.science/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/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":"2026-08-22T00:21:22Z","links":{"resolver":"https://pith.science/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO","bundle":"https://pith.science/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/bundle.json","state":"https://pith.science/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKVRXD7Y7JFWIQRQ3AVMGI63AO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UKVRXD7Y7JFWIQRQ3AVMGI63AO","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":"8231a414600652f2e478ae7aca8a18d68a6ec380ac867b64335a6d1d454a536f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:52:34Z","title_canon_sha256":"ac23566f48ff35db7bc1cf05d56a82f8052d603f155122125b4d865a78ee37e9"},"schema_version":"1.0","source":{"id":"2406.19228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19228","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19228v1","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19228","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"UKVRXD7Y7JFW","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"UKVRXD7Y7JFWIQRQ","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"UKVRXD7Y","created_at":"2026-07-05T08:37:32Z"}],"graph_snapshots":[{"event_id":"sha256:2fd08b9d61f4d045cfda5b5ede206bf54035fa8112dc643196c40f1780024757","target":"graph","created_at":"2026-07-05T08:37:32Z","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/2406.19228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots. However, most ontologies and surveys of tool-use have assumed the core challenge for LLMs is choosing the tool. Instead, we introduce a framework for tools more broadly which guides us to explore a model's ability to detect \"silent\" tool errors, and reflect on how to plan. This more directly aligns with the increasingly popular use of models as tools. We provide an initial approach to failure recovery with promising results both on a controlle","authors_text":"Jimin Sun, So Yeon Min, Yingshan Chang, Yonatan Bisk","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:52:34Z","title":"Tools Fail: Detecting Silent Errors in Faulty Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19228","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":"sha256:1e0965513e8910f9acb68b4027eb2629a3b3f0cc377260579d94ab26a7b3b2b7","target":"record","created_at":"2026-07-05T08:37:32Z","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":"8231a414600652f2e478ae7aca8a18d68a6ec380ac867b64335a6d1d454a536f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:52:34Z","title_canon_sha256":"ac23566f48ff35db7bc1cf05d56a82f8052d603f155122125b4d865a78ee37e9"},"schema_version":"1.0","source":{"id":"2406.19228","kind":"arxiv","version":1}},"canonical_sha256":"a2ab1b8ff8fa4b644230d82ac323db03a5451ab6f73864e3c805b214a92b0f3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2ab1b8ff8fa4b644230d82ac323db03a5451ab6f73864e3c805b214a92b0f3f","first_computed_at":"2026-07-05T08:37:32.099147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:32.099147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aj4k7+T0GZG/J2YhInC2Cn9ACQ7EsvraJetgJoAAg0lDd0eAlupyqAYlP6AIg+2xkN0QNbllvERZQgVOtB3bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:32.099602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e0965513e8910f9acb68b4027eb2629a3b3f0cc377260579d94ab26a7b3b2b7","sha256:2fd08b9d61f4d045cfda5b5ede206bf54035fa8112dc643196c40f1780024757"],"state_sha256":"0764692f5fbfa75cf5c8f3916f1cbab5b98bdf86a7a3c22af893ae7e30f24fc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9JVznpRC0jUXcx3/TrFGrN/pYOYjsimphDtGISlA3oKyOPDdH58Hxm0AEQXETea8w02hdGk9J9G38carBCBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:21:22.204041Z","bundle_sha256":"523bae2640f53f275cbaa97e567c826592b09f3eb986e0b3ee4597da5ae7b30a"}}