{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TV5X63E6MLJPYSZ5ALMCNNNJOJ","short_pith_number":"pith:TV5X63E6","schema_version":"1.0","canonical_sha256":"9d7b7f6c9e62d2fc4b3d02d826b5a9724410c6629823e9910ffad9856b5256b2","source":{"kind":"arxiv","id":"2412.04141","version":3},"attestation_state":"computed","paper":{"title":"Reducing Tool Hallucination via Reliability Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Da Ma, Hongshen Xu, Kai Yu, Lei Pan, Lu Chen, Ruisheng Cao, Su Zhu, Zichen Zhu, Zihan Wang","submitted_at":"2024-12-05T13:10:54Z","abstract_excerpt":"Large Language Models (LLMs) have expanded their capabilities beyond language generation to interact with external tools, enabling automation and real-world applications. However, tool hallucinations, where models either select inappropriate tools or misuse them, pose significant challenges, leading to erroneous task execution, increased computational costs, and reduced system reliability. To systematically address this issue, we define and categorize tool hallucinations into two main types, tool selection hallucination and tool usage hallucination. To evaluate and mitigate these issues, we in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.04141","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T13:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"20ab0943878946428050abfd5e28c3ee4efeadc03c30a727bda31d3b6515a3e6","abstract_canon_sha256":"5c9fad47cd0b297b698b7b4a606b839477782b03c7c444e016d33554470be626"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:37.807165Z","signature_b64":"23ouG1RdVo6QnLUYDFrweZFjpns/8cxXjGTV9lKWmOSfSfK5B7pZUBYhlvj15H0Egi2miabxnNFvV1bS7nnWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d7b7f6c9e62d2fc4b3d02d826b5a9724410c6629823e9910ffad9856b5256b2","last_reissued_at":"2026-07-05T11:11:37.806685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:37.806685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing Tool Hallucination via Reliability Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Da Ma, Hongshen Xu, Kai Yu, Lei Pan, Lu Chen, Ruisheng Cao, Su Zhu, Zichen Zhu, Zihan Wang","submitted_at":"2024-12-05T13:10:54Z","abstract_excerpt":"Large Language Models (LLMs) have expanded their capabilities beyond language generation to interact with external tools, enabling automation and real-world applications. However, tool hallucinations, where models either select inappropriate tools or misuse them, pose significant challenges, leading to erroneous task execution, increased computational costs, and reduced system reliability. To systematically address this issue, we define and categorize tool hallucinations into two main types, tool selection hallucination and tool usage hallucination. To evaluate and mitigate these issues, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04141","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/2412.04141/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.04141","created_at":"2026-07-05T11:11:37.806742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04141v3","created_at":"2026-07-05T11:11:37.806742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04141","created_at":"2026-07-05T11:11:37.806742+00:00"},{"alias_kind":"pith_short_12","alias_value":"TV5X63E6MLJP","created_at":"2026-07-05T11:11:37.806742+00:00"},{"alias_kind":"pith_short_16","alias_value":"TV5X63E6MLJPYSZ5","created_at":"2026-07-05T11:11:37.806742+00:00"},{"alias_kind":"pith_short_8","alias_value":"TV5X63E6","created_at":"2026-07-05T11:11:37.806742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27209","citing_title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22977","citing_title":"The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ","json":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ.json","graph_json":"https://pith.science/api/pith-number/TV5X63E6MLJPYSZ5ALMCNNNJOJ/graph.json","events_json":"https://pith.science/api/pith-number/TV5X63E6MLJPYSZ5ALMCNNNJOJ/events.json","paper":"https://pith.science/paper/TV5X63E6"},"agent_actions":{"view_html":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ","download_json":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ.json","view_paper":"https://pith.science/paper/TV5X63E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04141&json=true","fetch_graph":"https://pith.science/api/pith-number/TV5X63E6MLJPYSZ5ALMCNNNJOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TV5X63E6MLJPYSZ5ALMCNNNJOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ/action/storage_attestation","attest_author":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ/action/author_attestation","sign_citation":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ/action/citation_signature","submit_replication":"https://pith.science/pith/TV5X63E6MLJPYSZ5ALMCNNNJOJ/action/replication_record"}},"created_at":"2026-07-05T11:11:37.806742+00:00","updated_at":"2026-07-05T11:11:37.806742+00:00"}