{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FODA646QYWP5PGFW6RUT5K6IQU","short_pith_number":"pith:FODA646Q","canonical_record":{"source":{"id":"2403.04746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T18:50:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"129fccc1e9fdcedde15ce27c482fa1d71014581733b36839478afa8b0086b125","abstract_canon_sha256":"ac03c6a1bf88a67fa8ec206a54d036c1e7574437c731154e7655f3877a2d1829"},"schema_version":"1.0"},"canonical_sha256":"2b860f73d0c59fd798b6f4693eabc885338bc61b8a3f401c44e6e098decad2a4","source":{"kind":"arxiv","id":"2403.04746","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04746","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04746v1","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04746","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_12","alias_value":"FODA646QYWP5","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_16","alias_value":"FODA646QYWP5PGFW","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_8","alias_value":"FODA646Q","created_at":"2026-07-05T07:53:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FODA646QYWP5PGFW6RUT5K6IQU","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T18:50:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"129fccc1e9fdcedde15ce27c482fa1d71014581733b36839478afa8b0086b125","abstract_canon_sha256":"ac03c6a1bf88a67fa8ec206a54d036c1e7574437c731154e7655f3877a2d1829"},"schema_version":"1.0"},"canonical_sha256":"2b860f73d0c59fd798b6f4693eabc885338bc61b8a3f401c44e6e098decad2a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:27.365232Z","signature_b64":"pF+WdBWuqaJy3JEPJC+VO5qOQ+oUdUPKSxDQcTdgLY1ihZ/dQJd5x024qtdmvPE46U/fAl9taf7N1Y64WkqiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b860f73d0c59fd798b6f4693eabc885338bc61b8a3f401c44e6e098decad2a4","last_reissued_at":"2026-07-05T07:53:27.364744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:27.364744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04746","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":"2026-07-05T07:53:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFUvaKtr5kBQVoI/w5mTqfOkMPc7FDH5NLpJDxEiv3kluhdLjnTkEiL6JfyppaXSHQZ0LL5KQw2mYBNPdW8oDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:07:17.031054Z"},"content_sha256":"12ff77730161de32cf6ba359059bac1cf638c3525e961f3ed57131d0a8f3391a","schema_version":"1.0","event_id":"sha256:12ff77730161de32cf6ba359059bac1cf638c3525e961f3ed57131d0a8f3391a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FODA646QYWP5PGFW6RUT5K6IQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Boshi Wang, Hao Fang, Jason Eisner, Yu Su","submitted_at":"2024-03-07T18:50:51Z","abstract_excerpt":"Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs primarily focuses on the broad coverage of tools and the flexibility of adding new tools. However, a critical aspect that has surprisingly been understudied is simply how accurately an LLM uses tools for which it has been trained. We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04746","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/2403.04746/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":"2026-07-05T07:53:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wuYdzlOULXoupQfEY58/MUXnTtgE07KZnE1GOobaU0q5Ot5WhZbRbQRG2cJAsF9Cf7JIy1s0JLDEMse5cJ/9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:07:17.032488Z"},"content_sha256":"db1aa06b649c5493d3088999432d3db5f1c2b955ff5947f8f48b9ccf99de179d","schema_version":"1.0","event_id":"sha256:db1aa06b649c5493d3088999432d3db5f1c2b955ff5947f8f48b9ccf99de179d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FODA646QYWP5PGFW6RUT5K6IQU/bundle.json","state_url":"https://pith.science/pith/FODA646QYWP5PGFW6RUT5K6IQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FODA646QYWP5PGFW6RUT5K6IQU/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":"2026-08-10T11:07:17Z","links":{"resolver":"https://pith.science/pith/FODA646QYWP5PGFW6RUT5K6IQU","bundle":"https://pith.science/pith/FODA646QYWP5PGFW6RUT5K6IQU/bundle.json","state":"https://pith.science/pith/FODA646QYWP5PGFW6RUT5K6IQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FODA646QYWP5PGFW6RUT5K6IQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FODA646QYWP5PGFW6RUT5K6IQU","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":"ac03c6a1bf88a67fa8ec206a54d036c1e7574437c731154e7655f3877a2d1829","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T18:50:51Z","title_canon_sha256":"129fccc1e9fdcedde15ce27c482fa1d71014581733b36839478afa8b0086b125"},"schema_version":"1.0","source":{"id":"2403.04746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04746","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04746v1","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04746","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_12","alias_value":"FODA646QYWP5","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_16","alias_value":"FODA646QYWP5PGFW","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_8","alias_value":"FODA646Q","created_at":"2026-07-05T07:53:27Z"}],"graph_snapshots":[{"event_id":"sha256:db1aa06b649c5493d3088999432d3db5f1c2b955ff5947f8f48b9ccf99de179d","target":"graph","created_at":"2026-07-05T07:53:27Z","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/2403.04746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs primarily focuses on the broad coverage of tools and the flexibility of adding new tools. However, a critical aspect that has surprisingly been understudied is simply how accurately an LLM uses tools for which it has been trained. We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in pr","authors_text":"Benjamin Van Durme, Boshi Wang, Hao Fang, Jason Eisner, Yu Su","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T18:50:51Z","title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04746","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":"sha256:12ff77730161de32cf6ba359059bac1cf638c3525e961f3ed57131d0a8f3391a","target":"record","created_at":"2026-07-05T07:53:27Z","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":"ac03c6a1bf88a67fa8ec206a54d036c1e7574437c731154e7655f3877a2d1829","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T18:50:51Z","title_canon_sha256":"129fccc1e9fdcedde15ce27c482fa1d71014581733b36839478afa8b0086b125"},"schema_version":"1.0","source":{"id":"2403.04746","kind":"arxiv","version":1}},"canonical_sha256":"2b860f73d0c59fd798b6f4693eabc885338bc61b8a3f401c44e6e098decad2a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b860f73d0c59fd798b6f4693eabc885338bc61b8a3f401c44e6e098decad2a4","first_computed_at":"2026-07-05T07:53:27.364744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:27.364744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pF+WdBWuqaJy3JEPJC+VO5qOQ+oUdUPKSxDQcTdgLY1ihZ/dQJd5x024qtdmvPE46U/fAl9taf7N1Y64WkqiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:27.365232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12ff77730161de32cf6ba359059bac1cf638c3525e961f3ed57131d0a8f3391a","sha256:db1aa06b649c5493d3088999432d3db5f1c2b955ff5947f8f48b9ccf99de179d"],"state_sha256":"d2e0cbae72f40dab07a504e0ded062b2780de852184070b0db2837904d0ce177"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcpT6onrX7imiAmbhN5MF0619SEYjnRLsYznDYKf7IXW0ttCJquWeRjDeevvK7Pagop9HUYCoUt5VUaJanNqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:07:17.043897Z","bundle_sha256":"2c616f54a50d7a4281cec13db807ff0166fdb66a11af9b712e6c23517960a492"}}