{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J2YLW4FJBPVCL276VBKEGL43W3","short_pith_number":"pith:J2YLW4FJ","canonical_record":{"source":{"id":"1909.01388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T18:22:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a5e2a7a6a9a7320ed0f7d7d73f51e5b78a5894e1a5e275a9b29e948237e961c","abstract_canon_sha256":"2c821d451368cad725f92d31ff4719daf5e6498fe9d10aff078dd2c735dd3520"},"schema_version":"1.0"},"canonical_sha256":"4eb0bb70a90bea25ebfea854432f9bb6ca2c9d1be1db3d32aeac24d15823020e","source":{"kind":"arxiv","id":"1909.01388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01388","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01388v1","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01388","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"J2YLW4FJBPVC","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"J2YLW4FJBPVCL276","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"J2YLW4FJ","created_at":"2026-07-05T00:02:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J2YLW4FJBPVCL276VBKEGL43W3","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T18:22:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a5e2a7a6a9a7320ed0f7d7d73f51e5b78a5894e1a5e275a9b29e948237e961c","abstract_canon_sha256":"2c821d451368cad725f92d31ff4719daf5e6498fe9d10aff078dd2c735dd3520"},"schema_version":"1.0"},"canonical_sha256":"4eb0bb70a90bea25ebfea854432f9bb6ca2c9d1be1db3d32aeac24d15823020e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:15.709476Z","signature_b64":"misAwfK9H4xL9U3uZxDFCdXsOlmkI+Is1CGCrwdvAWx4IhIAPX8moFj9qVusSUPLYU1lw47a864lFXeptqg/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb0bb70a90bea25ebfea854432f9bb6ca2c9d1be1db3d32aeac24d15823020e","last_reissued_at":"2026-07-05T00:02:15.708999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:15.708999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01388","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":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXehiUMpQLVW57W0vQ8E/3IA7LHvAhkYpNqrI43X/Gfffn8Y1aKwS0YD6mpD30eG4uKabFCeOuADRXGbEbSqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:57:01.301528Z"},"content_sha256":"6e9a819f0778ecfabf3f0e8552334a66a2be199cca9f2ff710f7b98f8649a2d3","schema_version":"1.0","event_id":"sha256:6e9a819f0778ecfabf3f0e8552334a66a2be199cca9f2ff710f7b98f8649a2d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J2YLW4FJBPVCL276VBKEGL43W3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Build User Simulators to Train RL-based Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kun Qian, Weiyan Shi, Xuewei Wang, Zhou Yu","submitted_at":"2019-09-03T18:22:24Z","abstract_excerpt":"User simulators are essential for training reinforcement learning (RL) based dialog models. The performance of the simulator directly impacts the RL policy. However, building a good user simulator that models real user behaviors is challenging. We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly. We present implementations of six user simulators trained with different dialog planning and generation methods. We then calculate a set of automatic metrics to evaluate the quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01388","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/1909.01388/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":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcZffzdnSapkuPFs9fTMD2Wxd+1iz70v6gS2n3ZhJMFnd1U4meyAmK4k5bkY4epZiSEpBk4dx29vJFAr39iHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:57:01.301910Z"},"content_sha256":"deb5870dc51cec817fabb678731714393ac2a7cfb4843810a7150d9f69a9a8d3","schema_version":"1.0","event_id":"sha256:deb5870dc51cec817fabb678731714393ac2a7cfb4843810a7150d9f69a9a8d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2YLW4FJBPVCL276VBKEGL43W3/bundle.json","state_url":"https://pith.science/pith/J2YLW4FJBPVCL276VBKEGL43W3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2YLW4FJBPVCL276VBKEGL43W3/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":"2026-07-18T10:57:01Z","links":{"resolver":"https://pith.science/pith/J2YLW4FJBPVCL276VBKEGL43W3","bundle":"https://pith.science/pith/J2YLW4FJBPVCL276VBKEGL43W3/bundle.json","state":"https://pith.science/pith/J2YLW4FJBPVCL276VBKEGL43W3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2YLW4FJBPVCL276VBKEGL43W3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J2YLW4FJBPVCL276VBKEGL43W3","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":"2c821d451368cad725f92d31ff4719daf5e6498fe9d10aff078dd2c735dd3520","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T18:22:24Z","title_canon_sha256":"4a5e2a7a6a9a7320ed0f7d7d73f51e5b78a5894e1a5e275a9b29e948237e961c"},"schema_version":"1.0","source":{"id":"1909.01388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01388","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01388v1","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01388","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"J2YLW4FJBPVC","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"J2YLW4FJBPVCL276","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"J2YLW4FJ","created_at":"2026-07-05T00:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:deb5870dc51cec817fabb678731714393ac2a7cfb4843810a7150d9f69a9a8d3","target":"graph","created_at":"2026-07-05T00:02:15Z","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/1909.01388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"User simulators are essential for training reinforcement learning (RL) based dialog models. The performance of the simulator directly impacts the RL policy. However, building a good user simulator that models real user behaviors is challenging. We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly. We present implementations of six user simulators trained with different dialog planning and generation methods. We then calculate a set of automatic metrics to evaluate the quality","authors_text":"Kun Qian, Weiyan Shi, Xuewei Wang, Zhou Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T18:22:24Z","title":"How to Build User Simulators to Train RL-based Dialog Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01388","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":"sha256:6e9a819f0778ecfabf3f0e8552334a66a2be199cca9f2ff710f7b98f8649a2d3","target":"record","created_at":"2026-07-05T00:02:15Z","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":"2c821d451368cad725f92d31ff4719daf5e6498fe9d10aff078dd2c735dd3520","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T18:22:24Z","title_canon_sha256":"4a5e2a7a6a9a7320ed0f7d7d73f51e5b78a5894e1a5e275a9b29e948237e961c"},"schema_version":"1.0","source":{"id":"1909.01388","kind":"arxiv","version":1}},"canonical_sha256":"4eb0bb70a90bea25ebfea854432f9bb6ca2c9d1be1db3d32aeac24d15823020e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb0bb70a90bea25ebfea854432f9bb6ca2c9d1be1db3d32aeac24d15823020e","first_computed_at":"2026-07-05T00:02:15.708999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:15.708999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"misAwfK9H4xL9U3uZxDFCdXsOlmkI+Is1CGCrwdvAWx4IhIAPX8moFj9qVusSUPLYU1lw47a864lFXeptqg/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:15.709476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e9a819f0778ecfabf3f0e8552334a66a2be199cca9f2ff710f7b98f8649a2d3","sha256:deb5870dc51cec817fabb678731714393ac2a7cfb4843810a7150d9f69a9a8d3"],"state_sha256":"52b1da109226df7d180d6d43de3e5b24966061f9ffee9c2c2f7fbcaec2a3bf12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Pp5Wd20EJf/t+8UVbXWzS3zBbqOow2cuce7s1UjPEtLMl5kihGAaU3xI2NHGwQRSXp6ZnM2DX9Ku3cNXoPmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T10:57:01.304071Z","bundle_sha256":"04daee3c31df9decae2789cd72e8eefc247953336f5bcf2df8f1752d285c5fc0"}}