{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LDQLBZG65KWMECVIPXHC43Y7A4","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":"f513c5b6a39c65f567c08d1bbfc0da58d786495eebd3a90bcab75dcf108cd98f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:50:31Z","title_canon_sha256":"9cc7161cd8448360c55d5f71e35cbd506ce823b899785674fddfdf56c41cf55f"},"schema_version":"1.0","source":{"id":"2311.10775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10775","created_at":"2026-07-05T07:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10775v1","created_at":"2026-07-05T07:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10775","created_at":"2026-07-05T07:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"LDQLBZG65KWM","created_at":"2026-07-05T07:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"LDQLBZG65KWMECVI","created_at":"2026-07-05T07:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"LDQLBZG6","created_at":"2026-07-05T07:14:22Z"}],"graph_snapshots":[{"event_id":"sha256:365acedcf6ffb9cbc5d5535f4a671d4adf671ccd69893a04ec79c416710b4788","target":"graph","created_at":"2026-07-05T07:14:22Z","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/2311.10775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Nicholas Farn, Richard Shin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:50:31Z","title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10775","kind":"arxiv","version":1},"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":"sha256:61f73603e0c49e07feb3d411cafd02b993ec2b6945c98345593fe4ed50215623","target":"record","created_at":"2026-07-05T07:14:22Z","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":"f513c5b6a39c65f567c08d1bbfc0da58d786495eebd3a90bcab75dcf108cd98f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:50:31Z","title_canon_sha256":"9cc7161cd8448360c55d5f71e35cbd506ce823b899785674fddfdf56c41cf55f"},"schema_version":"1.0","source":{"id":"2311.10775","kind":"arxiv","version":1}},"canonical_sha256":"58e0b0e4deeaacc20aa87dce2e6f1f0728678c22cee807ea1cd42deaef47b928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58e0b0e4deeaacc20aa87dce2e6f1f0728678c22cee807ea1cd42deaef47b928","first_computed_at":"2026-07-05T07:14:22.152419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:22.152419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EEGLKrEhGV7tNelnW2jwy2Xq/9gZuxxvxRWtSIGYjr+rYCLQ2K3r3yEMuCTgtDPnTcpWKBd13ZWdxFR/8Z0DDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:22.152917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.10775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61f73603e0c49e07feb3d411cafd02b993ec2b6945c98345593fe4ed50215623","sha256:365acedcf6ffb9cbc5d5535f4a671d4adf671ccd69893a04ec79c416710b4788"],"state_sha256":"1890127b9574e11c16e40b0cbb8ccd7ecccf24e20a529d264335459201b1a74d"}