{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLMV6KFTDAMNG65LB7WIG7YHTX","short_pith_number":"pith:CLMV6KFT","schema_version":"1.0","canonical_sha256":"12d95f28b31818d37bab0fec837f079de9469ec48fb8ce1dc492e2afefaeeef3","source":{"kind":"arxiv","id":"2403.06551","version":1},"attestation_state":"computed","paper":{"title":"ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Wang, Jian Luan, Peng Li, Wei Liu, Yang Liu, Yuanhang Zheng","submitted_at":"2024-03-11T09:52:32Z","abstract_excerpt":"Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous studies have proposed retrieving suitable tools for the LLM based on the user query. However, previously proposed methods do not consider the differences between seen and unseen tools, nor do they take the hierarchy of the tool library into account, which may lead to suboptimal performance for tool retrieval. Therefore, to address the aforementioned issues, we "},"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":"2403.06551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-11T09:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"0376d354e90b82ea39e0a847ccb5c1b8c70b94d55c63d7943bc789cd763c649c","abstract_canon_sha256":"8cfb205cffc438df608c1134a7a0239aa48784b9cf1a4f8b43957127980bbacc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:46.115415Z","signature_b64":"XCPr+XibWy/mEC7cpS+tvAm5sAfka4tORUCPOCDXJuIZYHB9crSguvAVYYPdu3PYDOCCAK9sw8cQ7dwDE6kVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d95f28b31818d37bab0fec837f079de9469ec48fb8ce1dc492e2afefaeeef3","last_reissued_at":"2026-07-05T08:29:46.114972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:46.114972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Wang, Jian Luan, Peng Li, Wei Liu, Yang Liu, Yuanhang Zheng","submitted_at":"2024-03-11T09:52:32Z","abstract_excerpt":"Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous studies have proposed retrieving suitable tools for the LLM based on the user query. However, previously proposed methods do not consider the differences between seen and unseen tools, nor do they take the hierarchy of the tool library into account, which may lead to suboptimal performance for tool retrieval. Therefore, to address the aforementioned issues, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06551","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/2403.06551/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":"2403.06551","created_at":"2026-07-05T08:29:46.115033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06551v1","created_at":"2026-07-05T08:29:46.115033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06551","created_at":"2026-07-05T08:29:46.115033+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLMV6KFTDAMN","created_at":"2026-07-05T08:29:46.115033+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLMV6KFTDAMNG65L","created_at":"2026-07-05T08:29:46.115033+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLMV6KFT","created_at":"2026-07-05T08:29:46.115033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.19793","citing_title":"Prompt Injection Attack to Tool Selection in LLM Agents","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13787","citing_title":"ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX","json":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX.json","graph_json":"https://pith.science/api/pith-number/CLMV6KFTDAMNG65LB7WIG7YHTX/graph.json","events_json":"https://pith.science/api/pith-number/CLMV6KFTDAMNG65LB7WIG7YHTX/events.json","paper":"https://pith.science/paper/CLMV6KFT"},"agent_actions":{"view_html":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX","download_json":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX.json","view_paper":"https://pith.science/paper/CLMV6KFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06551&json=true","fetch_graph":"https://pith.science/api/pith-number/CLMV6KFTDAMNG65LB7WIG7YHTX/graph.json","fetch_events":"https://pith.science/api/pith-number/CLMV6KFTDAMNG65LB7WIG7YHTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX/action/storage_attestation","attest_author":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX/action/author_attestation","sign_citation":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX/action/citation_signature","submit_replication":"https://pith.science/pith/CLMV6KFTDAMNG65LB7WIG7YHTX/action/replication_record"}},"created_at":"2026-07-05T08:29:46.115033+00:00","updated_at":"2026-07-05T08:29:46.115033+00:00"}