{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PJQATKXZHL3B5FMC6KKHJX2CXU","short_pith_number":"pith:PJQATKXZ","canonical_record":{"source":{"id":"2009.10326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:39:31Z","cross_cats_sorted":[],"title_canon_sha256":"b396ad373a4101569e48341bd6371f6c60f0d0c837d90962a7585bfa16334624","abstract_canon_sha256":"0c15ea82b81729d60f82905b5dbf1491d9a59a555264c4e6d71a00759757713c"},"schema_version":"1.0"},"canonical_sha256":"7a6009aaf93af61e9582f29474df42bd3c6ebcc629ab10062c8a5f84d47e7592","source":{"kind":"arxiv","id":"2009.10326","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10326","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10326v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10326","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"PJQATKXZHL3B","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"PJQATKXZHL3B5FMC","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"PJQATKXZ","created_at":"2026-07-05T01:37:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PJQATKXZHL3B5FMC6KKHJX2CXU","target":"record","payload":{"canonical_record":{"source":{"id":"2009.10326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:39:31Z","cross_cats_sorted":[],"title_canon_sha256":"b396ad373a4101569e48341bd6371f6c60f0d0c837d90962a7585bfa16334624","abstract_canon_sha256":"0c15ea82b81729d60f82905b5dbf1491d9a59a555264c4e6d71a00759757713c"},"schema_version":"1.0"},"canonical_sha256":"7a6009aaf93af61e9582f29474df42bd3c6ebcc629ab10062c8a5f84d47e7592","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:18.340735Z","signature_b64":"PlPYURQ9U2YvPwpmIlBFRpW5350dsNsHJb7rpClV1xKMap7ngUMItbevM8cHj5fVc3pB6AR9lu2H1xtEkgKDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a6009aaf93af61e9582f29474df42bd3c6ebcc629ab10062c8a5f84d47e7592","last_reissued_at":"2026-07-05T01:37:18.340275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:18.340275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.10326","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":"bGEnM9A0AWviMC2wpqE55ZH1oaFw64GGQ33hNfDkWSIpMMw+1Lb3GBR61Jr+ZXX2mXcHhtnquuVtX3skWD/bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:51:11.471010Z"},"content_sha256":"744e381828b150c09a28b0801ce29e1371dee71ac7aca6509e4a3ba8284f6ecc","schema_version":"1.0","event_id":"sha256:744e381828b150c09a28b0801ce29e1371dee71ac7aca6509e4a3ba8284f6ecc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PJQATKXZHL3B5FMC6KKHJX2CXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Xiaoyuan Liu, Zhi Chen","submitted_at":"2020-09-22T05:39:31Z","abstract_excerpt":"The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue belief state tracking (summarising conversation history) and dialogue decision-making (deciding how to reply to the user). In this work, we only focus on devising a policy that chooses which dialogue action to respond to the user. The sequential system decision-making process can be abstracted into a partially observable Markov decision process (POMDP). Under"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10326","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/2009.10326/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":"6fRMxcJKK6W7KthJqy9gRcJV0O+GtONbekM+KFeNrjC9/c9QMDexGlQCazjs4u9/VvsBHFSaD8DGzC/s3mn9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:51:11.471401Z"},"content_sha256":"b80a0868b3d814d3db1566a296740a318561824e1c5420334a9dac370e93144a","schema_version":"1.0","event_id":"sha256:b80a0868b3d814d3db1566a296740a318561824e1c5420334a9dac370e93144a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/bundle.json","state_url":"https://pith.science/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/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":"2026-07-06T08:51:11Z","links":{"resolver":"https://pith.science/pith/PJQATKXZHL3B5FMC6KKHJX2CXU","bundle":"https://pith.science/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/bundle.json","state":"https://pith.science/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJQATKXZHL3B5FMC6KKHJX2CXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PJQATKXZHL3B5FMC6KKHJX2CXU","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":"0c15ea82b81729d60f82905b5dbf1491d9a59a555264c4e6d71a00759757713c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:39:31Z","title_canon_sha256":"b396ad373a4101569e48341bd6371f6c60f0d0c837d90962a7585bfa16334624"},"schema_version":"1.0","source":{"id":"2009.10326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10326","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10326v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10326","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"PJQATKXZHL3B","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"PJQATKXZHL3B5FMC","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"PJQATKXZ","created_at":"2026-07-05T01:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:b80a0868b3d814d3db1566a296740a318561824e1c5420334a9dac370e93144a","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/2009.10326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue belief state tracking (summarising conversation history) and dialogue decision-making (deciding how to reply to the user). In this work, we only focus on devising a policy that chooses which dialogue action to respond to the user. The sequential system decision-making process can be abstracted into a partially observable Markov decision process (POMDP). Under","authors_text":"Kai Yu, Lu Chen, Xiaoyuan Liu, Zhi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:39:31Z","title":"Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10326","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":"sha256:744e381828b150c09a28b0801ce29e1371dee71ac7aca6509e4a3ba8284f6ecc","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":"0c15ea82b81729d60f82905b5dbf1491d9a59a555264c4e6d71a00759757713c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T05:39:31Z","title_canon_sha256":"b396ad373a4101569e48341bd6371f6c60f0d0c837d90962a7585bfa16334624"},"schema_version":"1.0","source":{"id":"2009.10326","kind":"arxiv","version":1}},"canonical_sha256":"7a6009aaf93af61e9582f29474df42bd3c6ebcc629ab10062c8a5f84d47e7592","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a6009aaf93af61e9582f29474df42bd3c6ebcc629ab10062c8a5f84d47e7592","first_computed_at":"2026-07-05T01:37:18.340275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:18.340275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PlPYURQ9U2YvPwpmIlBFRpW5350dsNsHJb7rpClV1xKMap7ngUMItbevM8cHj5fVc3pB6AR9lu2H1xtEkgKDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:18.340735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:744e381828b150c09a28b0801ce29e1371dee71ac7aca6509e4a3ba8284f6ecc","sha256:b80a0868b3d814d3db1566a296740a318561824e1c5420334a9dac370e93144a"],"state_sha256":"fcd07dc48cb7cac201f8994e417e94836faa06f527bc9a6696235386e28095db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svQJ6wMrIFNyTCAzROS4ooO1QEqCFFGcL8BR8bbgp/XYi59PhfGY4m02t1H+dYJLS+XiLV0sTBgs1u/Ys79CDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:51:11.473961Z","bundle_sha256":"53145c9e656edb2ede1860818d1762295e5ec03b49b37229958c41db97ecaa37"}}