{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PZZ5T4O2FWF4Z4C2SIKYUGDHN5","short_pith_number":"pith:PZZ5T4O2","canonical_record":{"source":{"id":"2401.08326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T12:45:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6820e22d543cbe69100022108cd777e9b7a241f559c9a1a577353a6edd9987e3","abstract_canon_sha256":"3c732d785d19abd84b5e7bcdaf45ac2548e5da0b5897979642089a689a590a98"},"schema_version":"1.0"},"canonical_sha256":"7e73d9f1da2d8bccf05a92158a18676f7d73dac8e60918cf85cbed0eda91fafc","source":{"kind":"arxiv","id":"2401.08326","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08326","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08326v3","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08326","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"PZZ5T4O2FWF4","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"PZZ5T4O2FWF4Z4C2","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"PZZ5T4O2","created_at":"2026-07-05T09:09:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PZZ5T4O2FWF4Z4C2SIKYUGDHN5","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T12:45:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6820e22d543cbe69100022108cd777e9b7a241f559c9a1a577353a6edd9987e3","abstract_canon_sha256":"3c732d785d19abd84b5e7bcdaf45ac2548e5da0b5897979642089a689a590a98"},"schema_version":"1.0"},"canonical_sha256":"7e73d9f1da2d8bccf05a92158a18676f7d73dac8e60918cf85cbed0eda91fafc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:55.605532Z","signature_b64":"ykB+DfmsPpN2evhPEn9O9xFAYb+cQ+nIKLlZAaRYuRArSn77b0bcJD0ZYPFOrwt65BCStgaKUH23/l7AHfBuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e73d9f1da2d8bccf05a92158a18676f7d73dac8e60918cf85cbed0eda91fafc","last_reissued_at":"2026-07-05T09:09:55.605027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:55.605027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08326","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOyHU7Dbj6z5KY+jLMd4ZbsutuLghLp6W9r6qqvg7mM5Q6ld7OGn8M2qOFqAKxDQs/unMf3npGPjzez2tx4tAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:03:35.760484Z"},"content_sha256":"efe18a27ccfafe9dbb1376d36a814583726b134272d86d51aea2890d3fba6233","schema_version":"1.0","event_id":"sha256:efe18a27ccfafe9dbb1376d36a814583726b134272d86d51aea2890d3fba6233"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PZZ5T4O2FWF4Z4C2SIKYUGDHN5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Guanyu Li, Junjie Ye, Qi Zhang, Sixian Li, Songyang Gao, Tao Gui, Xiaoran Fan, Xuanjing Huang, Yilong Wu","submitted_at":"2024-01-16T12:45:15Z","abstract_excerpt":"Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08326","kind":"arxiv","version":3},"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/2401.08326/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":"2026-07-05T09:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnXAx7v4Xx9afc11tgO5nTj3teVpqzxxYNu2T+exJUjJZUuyPwfnvRi1ajYe8y9yjtaKtFPdSWHprD1eDPw2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:03:35.760872Z"},"content_sha256":"ee97668480e8b8ab3ddf6993ee4fc7f35c9243444821c978a359d9e310c7f8df","schema_version":"1.0","event_id":"sha256:ee97668480e8b8ab3ddf6993ee4fc7f35c9243444821c978a359d9e310c7f8df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/bundle.json","state_url":"https://pith.science/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/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":"2026-08-04T11:03:35Z","links":{"resolver":"https://pith.science/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5","bundle":"https://pith.science/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/bundle.json","state":"https://pith.science/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZZ5T4O2FWF4Z4C2SIKYUGDHN5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZZ5T4O2FWF4Z4C2SIKYUGDHN5","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":"3c732d785d19abd84b5e7bcdaf45ac2548e5da0b5897979642089a689a590a98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T12:45:15Z","title_canon_sha256":"6820e22d543cbe69100022108cd777e9b7a241f559c9a1a577353a6edd9987e3"},"schema_version":"1.0","source":{"id":"2401.08326","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08326","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08326v3","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08326","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"PZZ5T4O2FWF4","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"PZZ5T4O2FWF4Z4C2","created_at":"2026-07-05T09:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"PZZ5T4O2","created_at":"2026-07-05T09:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:ee97668480e8b8ab3ddf6993ee4fc7f35c9243444821c978a359d9e310c7f8df","target":"graph","created_at":"2026-07-05T09:09:55Z","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/2401.08326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and ","authors_text":"Caishuang Huang, Guanyu Li, Junjie Ye, Qi Zhang, Sixian Li, Songyang Gao, Tao Gui, Xiaoran Fan, Xuanjing Huang, Yilong Wu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T12:45:15Z","title":"RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08326","kind":"arxiv","version":3},"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:efe18a27ccfafe9dbb1376d36a814583726b134272d86d51aea2890d3fba6233","target":"record","created_at":"2026-07-05T09:09:55Z","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":"3c732d785d19abd84b5e7bcdaf45ac2548e5da0b5897979642089a689a590a98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T12:45:15Z","title_canon_sha256":"6820e22d543cbe69100022108cd777e9b7a241f559c9a1a577353a6edd9987e3"},"schema_version":"1.0","source":{"id":"2401.08326","kind":"arxiv","version":3}},"canonical_sha256":"7e73d9f1da2d8bccf05a92158a18676f7d73dac8e60918cf85cbed0eda91fafc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e73d9f1da2d8bccf05a92158a18676f7d73dac8e60918cf85cbed0eda91fafc","first_computed_at":"2026-07-05T09:09:55.605027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:55.605027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ykB+DfmsPpN2evhPEn9O9xFAYb+cQ+nIKLlZAaRYuRArSn77b0bcJD0ZYPFOrwt65BCStgaKUH23/l7AHfBuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:55.605532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08326","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efe18a27ccfafe9dbb1376d36a814583726b134272d86d51aea2890d3fba6233","sha256:ee97668480e8b8ab3ddf6993ee4fc7f35c9243444821c978a359d9e310c7f8df"],"state_sha256":"2dcf200a89aba7d079d6b9acaeb85901103899e2e2140f7cd79f72adbaba27ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3ZZ4xTFG3ERmJ17nx6g1Qm2bZ4DT49Ei/WZx4vmkjOnufLuAWAJ31ZowIErdvjG4/Hy4xzGKF7PxTvenWjJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:03:35.763780Z","bundle_sha256":"4d25ca0cfbe1d9c1c995cf015f4bab0efc8036c4b98d22de8189d16c724ba023"}}