{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KMLEVUUGVVSNN4Z6WFBDJ7LFDH","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":"720fbfedf6b0c89ff295e8949ab3efa55f1b1541b386a30a5845d9e81f2456b1","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T17:37:16Z","title_canon_sha256":"e787c5daecac2c69c51923a34f7d6ffd67b914d6da7188b4088e9b819585fd51"},"schema_version":"1.0","source":{"id":"2503.01763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01763","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01763v2","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01763","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"KMLEVUUGVVSN","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"KMLEVUUGVVSNN4Z6","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"KMLEVUUG","created_at":"2026-07-05T11:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:ec8db7a05acbb7b2f04bf82243f2a98bc679ef805bd8d6392a912ac93e98525d","target":"graph","created_at":"2026-07-05T11:09:45Z","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/2503.01763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to select useful tools from large toolsets is a critical initial step. However, the performance of IR models in tool retrieval tasks remains underexplored and unclear. Most tool-use benchmarks simplify this step by manually pre-annotating a small set of relevant tools for each task, which is far from the real-world scenarios. In this paper, we propose ToolRet, a","authors_text":"Dawei Yin, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Yuhan Wang, Zhaochun Ren, Zhengliang Shi","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T17:37:16Z","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01763","kind":"arxiv","version":2},"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":"sha256:05ba56de319d6195e314623c7fc4d2e58965c488bad63b049e306666923d4cf0","target":"record","created_at":"2026-07-05T11:09:45Z","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":"720fbfedf6b0c89ff295e8949ab3efa55f1b1541b386a30a5845d9e81f2456b1","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T17:37:16Z","title_canon_sha256":"e787c5daecac2c69c51923a34f7d6ffd67b914d6da7188b4088e9b819585fd51"},"schema_version":"1.0","source":{"id":"2503.01763","kind":"arxiv","version":2}},"canonical_sha256":"53164ad286ad64d6f33eb14234fd6519c104d0fe42e60e4fecd1dd4b9807afc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53164ad286ad64d6f33eb14234fd6519c104d0fe42e60e4fecd1dd4b9807afc9","first_computed_at":"2026-07-05T11:09:45.766865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:45.766865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"foRmAZ+n5THEJWXYUJNip/oKMEFdjmGoUEa9uutPQ2pvLwwm3k413QykCo3OyHcbXQXMQyWpaULw4Oh5ftY4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:45.767364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05ba56de319d6195e314623c7fc4d2e58965c488bad63b049e306666923d4cf0","sha256:ec8db7a05acbb7b2f04bf82243f2a98bc679ef805bd8d6392a912ac93e98525d"],"state_sha256":"c40f80e679ab7cfa1320adaf90817296ac465e5b9a04b94d6b98a66f8b50a8f5"}