{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LDQLBZG65KWMECVIPXHC43Y7A4","short_pith_number":"pith:LDQLBZG6","schema_version":"1.0","canonical_sha256":"58e0b0e4deeaacc20aa87dce2e6f1f0728678c22cee807ea1cd42deaef47b928","source":{"kind":"arxiv","id":"2311.10775","version":1},"attestation_state":"computed","paper":{"title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nicholas Farn, Richard Shin","submitted_at":"2023-11-15T23:50:31Z","abstract_excerpt":"Large language models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Many recent works seek to augment LLM-based assistants with external tools so they can access private or up-to-date information and carry out actions on behalf of users. To better measure the performance of these assistants, this paper introduces ToolTalk, a benchmark consisting of complex user intents requiring multi-step tool usage specified through dialogue. ToolTalk contains 28 tools grouped into 7 plugins, and includes a complete simulated"},"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":"2311.10775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:50:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9cc7161cd8448360c55d5f71e35cbd506ce823b899785674fddfdf56c41cf55f","abstract_canon_sha256":"f513c5b6a39c65f567c08d1bbfc0da58d786495eebd3a90bcab75dcf108cd98f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:22.152917Z","signature_b64":"EEGLKrEhGV7tNelnW2jwy2Xq/9gZuxxvxRWtSIGYjr+rYCLQ2K3r3yEMuCTgtDPnTcpWKBd13ZWdxFR/8Z0DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58e0b0e4deeaacc20aa87dce2e6f1f0728678c22cee807ea1cd42deaef47b928","last_reissued_at":"2026-07-05T07:14:22.152419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:22.152419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nicholas Farn, Richard Shin","submitted_at":"2023-11-15T23:50:31Z","abstract_excerpt":"Large language models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Many recent works seek to augment LLM-based assistants with external tools so they can access private or up-to-date information and carry out actions on behalf of users. To better measure the performance of these assistants, this paper introduces ToolTalk, a benchmark consisting of complex user intents requiring multi-step tool usage specified through dialogue. ToolTalk contains 28 tools grouped into 7 plugins, and includes a complete simulated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10775","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/2311.10775/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":"2311.10775","created_at":"2026-07-05T07:14:22.152484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10775v1","created_at":"2026-07-05T07:14:22.152484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10775","created_at":"2026-07-05T07:14:22.152484+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDQLBZG65KWM","created_at":"2026-07-05T07:14:22.152484+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDQLBZG65KWMECVI","created_at":"2026-07-05T07:14:22.152484+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDQLBZG6","created_at":"2026-07-05T07:14:22.152484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27141","citing_title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16909","citing_title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4","json":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4.json","graph_json":"https://pith.science/api/pith-number/LDQLBZG65KWMECVIPXHC43Y7A4/graph.json","events_json":"https://pith.science/api/pith-number/LDQLBZG65KWMECVIPXHC43Y7A4/events.json","paper":"https://pith.science/paper/LDQLBZG6"},"agent_actions":{"view_html":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4","download_json":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4.json","view_paper":"https://pith.science/paper/LDQLBZG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10775&json=true","fetch_graph":"https://pith.science/api/pith-number/LDQLBZG65KWMECVIPXHC43Y7A4/graph.json","fetch_events":"https://pith.science/api/pith-number/LDQLBZG65KWMECVIPXHC43Y7A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4/action/storage_attestation","attest_author":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4/action/author_attestation","sign_citation":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4/action/citation_signature","submit_replication":"https://pith.science/pith/LDQLBZG65KWMECVIPXHC43Y7A4/action/replication_record"}},"created_at":"2026-07-05T07:14:22.152484+00:00","updated_at":"2026-07-05T07:14:22.152484+00:00"}