{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXLHBMIHD4JSBXULQIRO3YIUHJ","short_pith_number":"pith:EXLHBMIH","canonical_record":{"source":{"id":"2606.19336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T17:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"02e6ea577816a1b91a5f2a343005a571f11f067779607decf4765f6d72bfb965","abstract_canon_sha256":"869e377d20f0f50cac038078619f8c2f70b587e8cbd426334b3ba7a9e9ba6194"},"schema_version":"1.0"},"canonical_sha256":"25d670b1071f1320de8b8222ede1143a5c04282c55efd151ccd8d6d307621e78","source":{"kind":"arxiv","id":"2606.19336","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19336","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19336v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19336","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"EXLHBMIHD4JS","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"EXLHBMIHD4JSBXUL","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"EXLHBMIH","created_at":"2026-06-19T16:12:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXLHBMIHD4JSBXULQIRO3YIUHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T17:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"02e6ea577816a1b91a5f2a343005a571f11f067779607decf4765f6d72bfb965","abstract_canon_sha256":"869e377d20f0f50cac038078619f8c2f70b587e8cbd426334b3ba7a9e9ba6194"},"schema_version":"1.0"},"canonical_sha256":"25d670b1071f1320de8b8222ede1143a5c04282c55efd151ccd8d6d307621e78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.518963Z","signature_b64":"8/7eOJgSngBZxMJa8B2Px8PRBcujiymNVkFiFgtZBQKOkwUWDeJ003zx8HXcY5kPL5+eIwdtCrQYmIWtgaOqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d670b1071f1320de8b8222ede1143a5c04282c55efd151ccd8d6d307621e78","last_reissued_at":"2026-06-19T16:12:11.518627Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.518627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19336","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QdsWhOLKiV48QXtPAfrX9FIjrdlP86ejspR0ruHW4VvZSRYC7Gnhq3k3Ac9IM/7WDzWjgI+dFjK/IUDxB47zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:23:10.296611Z"},"content_sha256":"bbd6f9d0f8d06c6c3a80950a23a02e27e1e864b905ebd06542a1bfc0565abbe2","schema_version":"1.0","event_id":"sha256:bbd6f9d0f8d06c6c3a80950a23a02e27e1e864b905ebd06542a1bfc0565abbe2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXLHBMIHD4JSBXULQIRO3YIUHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning User Simulators with Turing Rewards","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Pentland, Cedegao E. Zhang, Linlu Qiu, Pengyuan Li, Roger P. Levy, Yingshan Susan Wang, Yoon Kim, Zexue He","submitted_at":"2026-06-17T17:58:48Z","abstract_excerpt":"Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, research in the social sciences, and more. Existing approaches generally do so by training a large language model (LLM) to match a single ground truth response, either by maximizing the log probability or by using a similarity reward. We instead propose {Turing-RL}: a Turing-Test-based reinforcement learning approach for training user simulator models. {Turing-RL} uses a discriminative Turing reward with an LLM judge to score how indistinguishable a ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19336","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/2606.19336/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbbOF/LEDLICNYov8ruzkQM1V/wDEYOPphlev7qo3Kcnz/crnlBJeD0QEEvwnwTMUhplt6uh9/D2YZHiRI28Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:23:10.296939Z"},"content_sha256":"f10b3eaf602d2560220345831e28e695084cdb2118a35e85c5063fb313cf2758","schema_version":"1.0","event_id":"sha256:f10b3eaf602d2560220345831e28e695084cdb2118a35e85c5063fb313cf2758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/bundle.json","state_url":"https://pith.science/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T16:23:10Z","links":{"resolver":"https://pith.science/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ","bundle":"https://pith.science/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/bundle.json","state":"https://pith.science/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXLHBMIHD4JSBXULQIRO3YIUHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXLHBMIHD4JSBXULQIRO3YIUHJ","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":"869e377d20f0f50cac038078619f8c2f70b587e8cbd426334b3ba7a9e9ba6194","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T17:58:48Z","title_canon_sha256":"02e6ea577816a1b91a5f2a343005a571f11f067779607decf4765f6d72bfb965"},"schema_version":"1.0","source":{"id":"2606.19336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19336","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19336v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19336","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"EXLHBMIHD4JS","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"EXLHBMIHD4JSBXUL","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"EXLHBMIH","created_at":"2026-06-19T16:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:f10b3eaf602d2560220345831e28e695084cdb2118a35e85c5063fb313cf2758","target":"graph","created_at":"2026-06-19T16:12:11Z","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/2606.19336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, research in the social sciences, and more. Existing approaches generally do so by training a large language model (LLM) to match a single ground truth response, either by maximizing the log probability or by using a similarity reward. We instead propose {Turing-RL}: a Turing-Test-based reinforcement learning approach for training user simulator models. {Turing-RL} uses a discriminative Turing reward with an LLM judge to score how indistinguishable a ge","authors_text":"Alex Pentland, Cedegao E. Zhang, Linlu Qiu, Pengyuan Li, Roger P. Levy, Yingshan Susan Wang, Yoon Kim, Zexue He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T17:58:48Z","title":"Learning User Simulators with Turing Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19336","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:bbd6f9d0f8d06c6c3a80950a23a02e27e1e864b905ebd06542a1bfc0565abbe2","target":"record","created_at":"2026-06-19T16:12:11Z","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":"869e377d20f0f50cac038078619f8c2f70b587e8cbd426334b3ba7a9e9ba6194","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T17:58:48Z","title_canon_sha256":"02e6ea577816a1b91a5f2a343005a571f11f067779607decf4765f6d72bfb965"},"schema_version":"1.0","source":{"id":"2606.19336","kind":"arxiv","version":1}},"canonical_sha256":"25d670b1071f1320de8b8222ede1143a5c04282c55efd151ccd8d6d307621e78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25d670b1071f1320de8b8222ede1143a5c04282c55efd151ccd8d6d307621e78","first_computed_at":"2026-06-19T16:12:11.518627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:11.518627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/7eOJgSngBZxMJa8B2Px8PRBcujiymNVkFiFgtZBQKOkwUWDeJ003zx8HXcY5kPL5+eIwdtCrQYmIWtgaOqCw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:11.518963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd6f9d0f8d06c6c3a80950a23a02e27e1e864b905ebd06542a1bfc0565abbe2","sha256:f10b3eaf602d2560220345831e28e695084cdb2118a35e85c5063fb313cf2758"],"state_sha256":"cc964b4bc93eb6e56533794ba7cfeac1eaa9762bdb3f7268cfa72026782d7b85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NDrUeMZswzKk+hLFeJdpBZsat7QPydt3JwA3GIi0hNhJOKs25U0D70fKwZfiHXGZkQhHXvcHm6bivB4POEc8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:23:10.300353Z","bundle_sha256":"ae776b8da18056bd25a33bb7f58a6eaed3ae5ed9cdb0f06081733468a06e30a1"}}