{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_35b91ec6e9f20f747e934c3831082fa2e998a046eac62aa83acb067b94a6d385","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_35b91ec6e9f20f747e934c3831082fa2e998a046eac62aa83acb067b94a6d385","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"06e4cb9f9f98e15ae977dacdaa88ad27e04b77efb2f77c3c02ae8ea113822f8d","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"06e4cb9f9f98e15ae977dacdaa88ad27e04b77efb2f77c3c02ae8ea113822f8d","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"06e4cb9f9f98e15ae977dacdaa88ad27e04b77efb2f77c3c02ae8ea113822f8d","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2601.08118v3 Announce Type: replace \nAbstract: 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-diversity metrics (**MATTR**, **Yule's~$K$**, and **HD-D**) with three LLM-judge-based metrics (**GTEval**, **Pairwise Indistinguishability**, and **Rubric-and-Reason**), and contextualizes judge scores using Human-Human and Proxy-Proxy calibration controls. Across four public datasets, **MirrorBench** yields variance-aware comparisons and reveals s","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","url":"https://arxiv.org/abs/2601.08118","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.08118v3 Announce Type: replace \nAbstract: 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-diversity metrics (**MATTR**, **Yule's~$K$**, and **HD-D**) with three LLM-judge-based metrics (**GTEval**, **Pairwise Indistinguishability**, and **Rubric-and-Reason**), and contextualizes judge scores using Human-Human and Proxy-Proxy calibration controls. Across four public datasets, **MirrorBench** yields variance-aware comparisons and reveals s","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.08118"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:b78bebc7643fd9444509a9f7e815ff2c730bca13c4f545fc2b63969c71f4655f0a0cf886dae390d11c68a4fae3ee000d761c8ce38f307b896fd1a1c71f1e1904","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.08118"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"c8826690af6465bc00692694034409d21eb0abdc4373cc1f9852ca16c347e26f","leaf_index":142948,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"81460f18856b06d89a0dc31ecaa9407130ce03524a6ed6bfac5cc89ab6caa122","side":"right"},{"sibling":"86982857600c8decca6dc6f332b116f27f0d7c1d6534ed1eb1a39de1730c230c","side":"right"},{"sibling":"c4f4d58f4f6ca81333890f8c528f39ee1427b321135fd4a66301272c4b99cb36","side":"left"},{"sibling":"9380adb8bf2cefb0584b48d014dc045d19a86b275e7967d23bb7854a07dfb8da","side":"right"},{"sibling":"5d66455999949b75b76491bd5509b46200de9adfb92742abfe69399eb6beb4c4","side":"right"},{"sibling":"3f9a5345017ea65e5d058e222a647991f120e8ad55377a6ea03ee8db431d977d","side":"left"},{"sibling":"18920e627055779d158c7c223ef853d7d69b12953cbd8e0326b3401e85b3e0a0","side":"left"},{"sibling":"1d2edc28d27d4c312510482f7321ca401bdfe21a8e83916a1ba677f0ea4fcd2b","side":"right"},{"sibling":"78a19962a2f444f055541381645626e3d4e1c8c7c2811bf54eeb89100f89f5b2","side":"right"},{"sibling":"db97141c585f6a1e6bebe92b3ea300ea0f38a2321ca286d85850b11b2dd162a6","side":"left"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_35b91ec6e9f20f747e934c3831082fa2e998a046eac62aa83acb067b94a6d385"}}