{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:INL6MKT7B6Q2UCBRAKMSXPAXG4","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":"a1412da2d5260163d3155952f39eaf7f2c75e3c50d2c4b43a88a5faf5ab0a1da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:36:13Z","title_canon_sha256":"89bbdc489cff7444ae7db40d255bd69188b4010427ca5ebdf3c8d272335920a7"},"schema_version":"1.0","source":{"id":"2505.13328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13328","created_at":"2026-07-05T11:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13328v1","created_at":"2026-07-05T11:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13328","created_at":"2026-07-05T11:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"INL6MKT7B6Q2","created_at":"2026-07-05T11:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"INL6MKT7B6Q2UCBR","created_at":"2026-07-05T11:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"INL6MKT7","created_at":"2026-07-05T11:05:28Z"}],"graph_snapshots":[{"event_id":"sha256:5a8b308c51f4228ea587526f127e49634cd4a623bdd3c85d91a6da33198eb0b8","target":"graph","created_at":"2026-07-05T11:05:28Z","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/2505.13328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose \\texttt{DialogTool}, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) \\textit{tool creation}; 2) \\textit{tool utilization}: tool awareness, tool selection, tool execution;","authors_text":"Hongru Wang, Huan Zhang, Jeff Z. Pan, Jianqiao Lu, Kam-Fai Wong, Nan Hu, Wenyu Huang, Yuanhao Xi, Yufei Wang, Zeming Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:36:13Z","title":"Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13328","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:fc26080f86b32664822e20f0e9a7a084690ea80f9d55c5f19879daf6c79605f0","target":"record","created_at":"2026-07-05T11:05:28Z","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":"a1412da2d5260163d3155952f39eaf7f2c75e3c50d2c4b43a88a5faf5ab0a1da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:36:13Z","title_canon_sha256":"89bbdc489cff7444ae7db40d255bd69188b4010427ca5ebdf3c8d272335920a7"},"schema_version":"1.0","source":{"id":"2505.13328","kind":"arxiv","version":1}},"canonical_sha256":"4357e62a7f0fa1aa083102992bbc173731d133e9f0da9ab0b256a0f55ada4629","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4357e62a7f0fa1aa083102992bbc173731d133e9f0da9ab0b256a0f55ada4629","first_computed_at":"2026-07-05T11:05:28.572920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:28.572920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RL1o4iT5lq6qgj6AFyTPUgNhkJOMsi4P0r8BSkt4VqtUzBot0wXwK/YGTGfxXCzKEfe3xQKnbh5QBY5V55rBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:28.573426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc26080f86b32664822e20f0e9a7a084690ea80f9d55c5f19879daf6c79605f0","sha256:5a8b308c51f4228ea587526f127e49634cd4a623bdd3c85d91a6da33198eb0b8"],"state_sha256":"70eaecaf1c11fca163610bc62381cbe7986f7aa98f26b72b25e9a9d9c588b534"}