{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:R2ZTLU2VWTRZWALJZM4SDO7CRY","short_pith_number":"pith:R2ZTLU2V","canonical_record":{"source":{"id":"2009.10321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:08:48Z","cross_cats_sorted":[],"title_canon_sha256":"83318095d6f0f3f2054722aafe943696ce81c0a4c049eea96e26f9f28a3d28c7","abstract_canon_sha256":"a17ceb8a017215b58519334ba1857287cb48f0888d182780d3b09e27a4dccb08"},"schema_version":"1.0"},"canonical_sha256":"8eb335d355b4e39b0169cb3921bbe28e27544a6d8116aa2a672fd2b287818900","source":{"kind":"arxiv","id":"2009.10321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10321","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10321v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10321","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"R2ZTLU2VWTRZ","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"R2ZTLU2VWTRZWALJ","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"R2ZTLU2V","created_at":"2026-07-05T01:37:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:R2ZTLU2VWTRZWALJZM4SDO7CRY","target":"record","payload":{"canonical_record":{"source":{"id":"2009.10321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:08:48Z","cross_cats_sorted":[],"title_canon_sha256":"83318095d6f0f3f2054722aafe943696ce81c0a4c049eea96e26f9f28a3d28c7","abstract_canon_sha256":"a17ceb8a017215b58519334ba1857287cb48f0888d182780d3b09e27a4dccb08"},"schema_version":"1.0"},"canonical_sha256":"8eb335d355b4e39b0169cb3921bbe28e27544a6d8116aa2a672fd2b287818900","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:18.285221Z","signature_b64":"wAkhJMzDAKgF1WgJ6/cbrRBGYrcWxN9Fu379AYAkA/7f3yON8wGwgHqPILGJQYPuJnwAs4OzEVDdgBJwW5oeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb335d355b4e39b0169cb3921bbe28e27544a6d8116aa2a672fd2b287818900","last_reissued_at":"2026-07-05T01:37:18.284740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:18.284740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.10321","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":"2026-07-05T01:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v5ItJZiCk08LV91E6kkXh3IPj/hngDIVnhBHSdFhGkXFZh9mseVV/qZ3uJwa6aGwI/n0lSZMZ6Ula1NZvlJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:31:33.086190Z"},"content_sha256":"9f313ce7af378fffa23d8b57ac8a584ac059058a6c607bbda01e78946ba69355","schema_version":"1.0","event_id":"sha256:9f313ce7af378fffa23d8b57ac8a584ac059058a6c607bbda01e78946ba69355"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:R2ZTLU2VWTRZWALJZM4SDO7CRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for On-line Dialogue State Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Xiang Zhou, Zhi Chen","submitted_at":"2020-09-22T05:08:48Z","abstract_excerpt":"Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep reinforcement learning (DRL) framework for on-line DST optimization is proposed. To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems. In addition, dialogue policy can be further jointly updated. Experiments show that on-line DST optimization can effectively improve the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10321","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/2009.10321/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":"2026-07-05T01:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lv8C1K5TXlqCfORT4/vWwlsfuSvmfhTu5biEIK7/h7Zd5GR8/hwI0/BmPspuahQShrySZ9C9kJyfsOgeZQXuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:31:33.087110Z"},"content_sha256":"f4efa51e490c3591f24df64d1a92dd298586bed2be56914d8af971fe2c889833","schema_version":"1.0","event_id":"sha256:f4efa51e490c3591f24df64d1a92dd298586bed2be56914d8af971fe2c889833"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/bundle.json","state_url":"https://pith.science/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/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":"2026-08-09T14:31:33Z","links":{"resolver":"https://pith.science/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY","bundle":"https://pith.science/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/bundle.json","state":"https://pith.science/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2ZTLU2VWTRZWALJZM4SDO7CRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R2ZTLU2VWTRZWALJZM4SDO7CRY","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":"a17ceb8a017215b58519334ba1857287cb48f0888d182780d3b09e27a4dccb08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:08:48Z","title_canon_sha256":"83318095d6f0f3f2054722aafe943696ce81c0a4c049eea96e26f9f28a3d28c7"},"schema_version":"1.0","source":{"id":"2009.10321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10321","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10321v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10321","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"R2ZTLU2VWTRZ","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"R2ZTLU2VWTRZWALJ","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"R2ZTLU2V","created_at":"2026-07-05T01:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:f4efa51e490c3591f24df64d1a92dd298586bed2be56914d8af971fe2c889833","target":"graph","created_at":"2026-07-05T01:37:18Z","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/2009.10321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep reinforcement learning (DRL) framework for on-line DST optimization is proposed. To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems. In addition, dialogue policy can be further jointly updated. Experiments show that on-line DST optimization can effectively improve the","authors_text":"Kai Yu, Lu Chen, Xiang Zhou, Zhi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:08:48Z","title":"Deep Reinforcement Learning for On-line Dialogue State Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10321","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":"sha256:9f313ce7af378fffa23d8b57ac8a584ac059058a6c607bbda01e78946ba69355","target":"record","created_at":"2026-07-05T01:37:18Z","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":"a17ceb8a017215b58519334ba1857287cb48f0888d182780d3b09e27a4dccb08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:08:48Z","title_canon_sha256":"83318095d6f0f3f2054722aafe943696ce81c0a4c049eea96e26f9f28a3d28c7"},"schema_version":"1.0","source":{"id":"2009.10321","kind":"arxiv","version":1}},"canonical_sha256":"8eb335d355b4e39b0169cb3921bbe28e27544a6d8116aa2a672fd2b287818900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb335d355b4e39b0169cb3921bbe28e27544a6d8116aa2a672fd2b287818900","first_computed_at":"2026-07-05T01:37:18.284740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:18.284740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAkhJMzDAKgF1WgJ6/cbrRBGYrcWxN9Fu379AYAkA/7f3yON8wGwgHqPILGJQYPuJnwAs4OzEVDdgBJwW5oeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:18.285221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f313ce7af378fffa23d8b57ac8a584ac059058a6c607bbda01e78946ba69355","sha256:f4efa51e490c3591f24df64d1a92dd298586bed2be56914d8af971fe2c889833"],"state_sha256":"85eaeec9543d13a23acaf606cb4de9cccd4959f307bd7f1322e47dc3f090b1f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+T17xZsB/bSDN2iVRHdm+kNs5S4XXMshmCQdcS4YEzutaUturGWlf7PWx0kAjzsqJkmOr9WcApuKtElnxbJoDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:31:33.094189Z","bundle_sha256":"28f70c4a8572a4616a333dfef99272879c942f49ee04e66b16b1716817ddc72b"}}