{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:25LINL6LOXBRFLW5JRWIAMAVDX","short_pith_number":"pith:25LINL6L","schema_version":"1.0","canonical_sha256":"d75686afcb75c312aedd4c6c8030151df0f5bc9d43587fd678451380198dd63c","source":{"kind":"arxiv","id":"2606.11079","version":1},"attestation_state":"computed","paper":{"title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ryan Shea, Yunan Lu, Yusen Zhang, Zhou Yu","submitted_at":"2026-06-09T16:39:32Z","abstract_excerpt":"Evaluation remains a critical bottleneck for interactive agent development. Existing evaluation methods often rely on static benchmarks, which fail to capture the dynamic, multi-step nature of agentic behavior and struggle to expose meaningful failure modes. While user-simulation-based evaluation offers a promising alternative, existing simulation frameworks suffer from two major limitations. First, they provide limited mechanisms for evaluating the quality and comprehensiveness of simulated interactions, making it difficult to assess whether a simulator sufficiently explores an agent's capabi"},"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":"2606.11079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T16:39:32Z","cross_cats_sorted":[],"title_canon_sha256":"54cc92bbceba1bccbf0c6b5262dd0c63e374ab5bfc4d27989aebabb8717cd9c8","abstract_canon_sha256":"3886f78d77a3d4b52228b02c1cbcdc4a75c50e7ba5434757f6896e9c5814de22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:08.953625Z","signature_b64":"fcQAcYETs9U3xAquwW6z5UNLKhgaSE4wFAtmKu39L5eTgpCLu1btn/1osXxdPy2h7WZENUEgknRhR9UgCGo5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75686afcb75c312aedd4c6c8030151df0f5bc9d43587fd678451380198dd63c","last_reissued_at":"2026-06-10T01:11:08.952716Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:08.952716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ryan Shea, Yunan Lu, Yusen Zhang, Zhou Yu","submitted_at":"2026-06-09T16:39:32Z","abstract_excerpt":"Evaluation remains a critical bottleneck for interactive agent development. Existing evaluation methods often rely on static benchmarks, which fail to capture the dynamic, multi-step nature of agentic behavior and struggle to expose meaningful failure modes. While user-simulation-based evaluation offers a promising alternative, existing simulation frameworks suffer from two major limitations. First, they provide limited mechanisms for evaluating the quality and comprehensiveness of simulated interactions, making it difficult to assess whether a simulator sufficiently explores an agent's capabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11079","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/2606.11079/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":"2606.11079","created_at":"2026-06-10T01:11:08.952882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11079v1","created_at":"2026-06-10T01:11:08.952882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11079","created_at":"2026-06-10T01:11:08.952882+00:00"},{"alias_kind":"pith_short_12","alias_value":"25LINL6LOXBR","created_at":"2026-06-10T01:11:08.952882+00:00"},{"alias_kind":"pith_short_16","alias_value":"25LINL6LOXBRFLW5","created_at":"2026-06-10T01:11:08.952882+00:00"},{"alias_kind":"pith_short_8","alias_value":"25LINL6L","created_at":"2026-06-10T01:11:08.952882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX","json":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX.json","graph_json":"https://pith.science/api/pith-number/25LINL6LOXBRFLW5JRWIAMAVDX/graph.json","events_json":"https://pith.science/api/pith-number/25LINL6LOXBRFLW5JRWIAMAVDX/events.json","paper":"https://pith.science/paper/25LINL6L"},"agent_actions":{"view_html":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX","download_json":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX.json","view_paper":"https://pith.science/paper/25LINL6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11079&json=true","fetch_graph":"https://pith.science/api/pith-number/25LINL6LOXBRFLW5JRWIAMAVDX/graph.json","fetch_events":"https://pith.science/api/pith-number/25LINL6LOXBRFLW5JRWIAMAVDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX/action/storage_attestation","attest_author":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX/action/author_attestation","sign_citation":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX/action/citation_signature","submit_replication":"https://pith.science/pith/25LINL6LOXBRFLW5JRWIAMAVDX/action/replication_record"}},"created_at":"2026-06-10T01:11:08.952882+00:00","updated_at":"2026-06-10T01:11:08.952882+00:00"}