{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DHFWS5CXQYAEGZWGZMNPE2J2R3","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":"f2359e9a587b2a53769b5eb306b64495be999cec481cb2fc55fed07378fcaf7e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-13T01:16:13Z","title_canon_sha256":"9014c3c057641df09df01b2a0929bd36dfc465a5ea972149b9abf6332759e8cd"},"schema_version":"1.0","source":{"id":"2601.08118","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.08118","created_at":"2026-05-20T00:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2601.08118v3","created_at":"2026-05-20T00:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08118","created_at":"2026-05-20T00:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"DHFWS5CXQYAE","created_at":"2026-05-20T00:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"DHFWS5CXQYAEGZWG","created_at":"2026-05-20T00:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"DHFWS5CX","created_at":"2026-05-20T00:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:2c03e0b24263ee30db6a1330d6a4b8854a3b013ceca9e5b44354a869a7b05650","target":"graph","created_at":"2026-05-20T00:04:21Z","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/2601.08118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as human simulators, both for evaluating conversational systems and for generating fine-tuning data. However, naive \"act-as-a-user\" prompting often yields verbose, unrealistic utterances, motivating principled evaluation of *user proxy agents*. We present **MirrorBench**, a reproducible and extensible benchmarking framework that evaluates user proxies solely on their ability to produce human-like user utterances across diverse conversational regimes, explicitly decoupled from downstream task success. **MirrorBench** combines three lexical-dive","authors_text":"Anil Babu Ankisettipalli, Ashutosh Hathidara, Julien Yu, Sebastian Schreiber, Vaishali Senthil","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-13T01:16:13Z","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08118","kind":"arxiv","version":3},"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":"sha256:60e53587315f9ce676208e49828e54969d5d443eba4c4d1b88e49201b7730427","target":"record","created_at":"2026-05-20T00:04:21Z","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":"f2359e9a587b2a53769b5eb306b64495be999cec481cb2fc55fed07378fcaf7e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-13T01:16:13Z","title_canon_sha256":"9014c3c057641df09df01b2a0929bd36dfc465a5ea972149b9abf6332759e8cd"},"schema_version":"1.0","source":{"id":"2601.08118","kind":"arxiv","version":3}},"canonical_sha256":"19cb69745786004366c6cb1af2693a8ef378ab11e3cdf3b415b4a6e271c6c3c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19cb69745786004366c6cb1af2693a8ef378ab11e3cdf3b415b4a6e271c6c3c1","first_computed_at":"2026-05-20T00:04:21.345567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:21.345567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e7SFqp6aiHtbuEhFTwkZE8XgBFz5pkumgNx1WcERwCQJQLSslAzMkeE+ck2MRdJQ2nfij/z6LaqZR4h61821Cw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:21.346452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.08118","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60e53587315f9ce676208e49828e54969d5d443eba4c4d1b88e49201b7730427","sha256:2c03e0b24263ee30db6a1330d6a4b8854a3b013ceca9e5b44354a869a7b05650"],"state_sha256":"c5fedb9e4ac599f70ae29afc27b4e38840fea4eefd8ec3ae7fb84617e757134c"}