{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G6USPTWDWIO3IP2XXJ4JRBX3PR","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":"db1035174401cbedd48baa2a5629a777682faa3d82ec2424bad58445f0cf734b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T17:34:12Z","title_canon_sha256":"8df2018d6948408c6a7ce0752890b5fd1eb1244efa8a5d77e2501485c3e95d9b"},"schema_version":"1.0","source":{"id":"2507.22034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22034","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22034v1","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22034","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"G6USPTWDWIO3","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"G6USPTWDWIO3IP2X","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"G6USPTWD","created_at":"2026-07-05T11:45:11Z"}],"graph_snapshots":[{"event_id":"sha256:e739711f78d98b4ac060523423ed32013db0eda57805c3b1e59b7d5655b07a5a","target":"graph","created_at":"2026-07-05T11:45:11Z","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/2507.22034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague, evolving, or indirectly expressed, remains underexplored. To address this gap, we introduce UserBench, a user-centric benchmark designed to evaluate agents in multi-turn, preference-driven interactions. UserBench features simulated users who start with underspecified goals and reveal preferences incrementally, requiring agents to proactively clarify intent and make ","authors_text":"Akshara Prabhakar, Caiming Xiong, Cheng Qian, Haolin Chen, Heng Ji, Huan Wang, Jianguo Zhang, Shelby Heinecke, Silvio Savarese, Weiran Yao, Zhiwei Liu, Zuxin Liu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T17:34:12Z","title":"UserBench: An Interactive Gym Environment for User-Centric Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22034","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":"sha256:7db904ef4c480e2ad99f212e4af35ec80e6f692e976875691c0593e99cd63d13","target":"record","created_at":"2026-07-05T11:45:11Z","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":"db1035174401cbedd48baa2a5629a777682faa3d82ec2424bad58445f0cf734b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T17:34:12Z","title_canon_sha256":"8df2018d6948408c6a7ce0752890b5fd1eb1244efa8a5d77e2501485c3e95d9b"},"schema_version":"1.0","source":{"id":"2507.22034","kind":"arxiv","version":1}},"canonical_sha256":"37a927cec3b21db43f57ba789886fb7c7bcffa5c0da51696ea213ff47a3061ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37a927cec3b21db43f57ba789886fb7c7bcffa5c0da51696ea213ff47a3061ca","first_computed_at":"2026-07-05T11:45:11.972213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:11.972213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"awkrp7RoFjmOTHXg7+lowxMTvhoKIogjXIhtFlUHhy7ANNcrtGy0SUhF8pu2LWjcV/eO1s4dztLN7rR9fuCzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:11.972682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7db904ef4c480e2ad99f212e4af35ec80e6f692e976875691c0593e99cd63d13","sha256:e739711f78d98b4ac060523423ed32013db0eda57805c3b1e59b7d5655b07a5a"],"state_sha256":"449b886b7176e7e9b4c917b7d37da058bc494f49aae2bc4e846666f3009daed0"}