{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6MBDCVDT2SD2AO6HYZYOKWXYC","short_pith_number":"pith:H6MBDCVD","schema_version":"1.0","canonical_sha256":"3f98118aa39ea43d01de3e33872ad7c089684737a0832c3f9ba4d449a2bf5a25","source":{"kind":"arxiv","id":"2412.12151","version":1},"attestation_state":"computed","paper":{"title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Lei Chen, Xiaodan Zhu, Yuanhao Shen","submitted_at":"2024-12-11T06:09:12Z","abstract_excerpt":"The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the models. In this paper, we conduct a study on a family of state-of-the-art LLMs on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfiden"},"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":"2412.12151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-11T06:09:12Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"c5536f3211fab1703e622c5a474568ed8b9f68e0f523b3a429c34c3138991da9","abstract_canon_sha256":"f91e5314c1482b8541bed3392256480f49653b661197bef673c8fe85c2a3e1e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:10.582726Z","signature_b64":"ezu66cZDxVadhnqdJ0K+JKLA49l5CjyWCaOAwuyDe24D6PUbUlS8NVrQ9MeqxT4VwGqvNWJdLjIBt50yIDJ2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f98118aa39ea43d01de3e33872ad7c089684737a0832c3f9ba4d449a2bf5a25","last_reissued_at":"2026-07-05T09:50:10.582304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:10.582304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Lei Chen, Xiaodan Zhu, Yuanhao Shen","submitted_at":"2024-12-11T06:09:12Z","abstract_excerpt":"The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the models. In this paper, we conduct a study on a family of state-of-the-art LLMs on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfiden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12151","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/2412.12151/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":"2412.12151","created_at":"2026-07-05T09:50:10.582371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12151v1","created_at":"2026-07-05T09:50:10.582371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12151","created_at":"2026-07-05T09:50:10.582371+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6MBDCVDT2SD","created_at":"2026-07-05T09:50:10.582371+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6MBDCVDT2SD2AO6","created_at":"2026-07-05T09:50:10.582371+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6MBDCVD","created_at":"2026-07-05T09:50:10.582371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC","json":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC.json","graph_json":"https://pith.science/api/pith-number/H6MBDCVDT2SD2AO6HYZYOKWXYC/graph.json","events_json":"https://pith.science/api/pith-number/H6MBDCVDT2SD2AO6HYZYOKWXYC/events.json","paper":"https://pith.science/paper/H6MBDCVD"},"agent_actions":{"view_html":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC","download_json":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC.json","view_paper":"https://pith.science/paper/H6MBDCVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12151&json=true","fetch_graph":"https://pith.science/api/pith-number/H6MBDCVDT2SD2AO6HYZYOKWXYC/graph.json","fetch_events":"https://pith.science/api/pith-number/H6MBDCVDT2SD2AO6HYZYOKWXYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC/action/storage_attestation","attest_author":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC/action/author_attestation","sign_citation":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC/action/citation_signature","submit_replication":"https://pith.science/pith/H6MBDCVDT2SD2AO6HYZYOKWXYC/action/replication_record"}},"created_at":"2026-07-05T09:50:10.582371+00:00","updated_at":"2026-07-05T09:50:10.582371+00:00"}