{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:57XR3W3TN74OOMQUZULBWMQYFF","short_pith_number":"pith:57XR3W3T","canonical_record":{"source":{"id":"2004.03809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a725279ac1a65111ddf52c65c7ee198846a0be4fa53e2c55af5156076707513","abstract_canon_sha256":"2b8a6fd2b8973f09404ab9ffaf22d2fa52671b470436e2f5940d2cd147f3873a"},"schema_version":"1.0"},"canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","source":{"kind":"arxiv","id":"2004.03809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03809","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03809v2","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03809","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_12","alias_value":"57XR3W3TN74O","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_16","alias_value":"57XR3W3TN74OOMQU","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_8","alias_value":"57XR3W3T","created_at":"2026-07-05T00:57:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:57XR3W3TN74OOMQUZULBWMQYFF","target":"record","payload":{"canonical_record":{"source":{"id":"2004.03809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a725279ac1a65111ddf52c65c7ee198846a0be4fa53e2c55af5156076707513","abstract_canon_sha256":"2b8a6fd2b8973f09404ab9ffaf22d2fa52671b470436e2f5940d2cd147f3873a"},"schema_version":"1.0"},"canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:35.595616Z","signature_b64":"2v3ahne0nEjBNhBxNqKD6JqHI93yWJjU5P4L/DD8nc4XajtH1UXRmCAg5nXOdXLaNt9qYYHVduik/qBqu98gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","last_reissued_at":"2026-07-05T00:57:35.595231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:35.595231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.03809","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:57:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eYpKr9xessX6NvOHdP7UN/jT3i17qu/WX1rbadRfjd5oRjFCT5ld+7fVTKLUbFIL27bVgND71T3hofTWYoz+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:11:03.999816Z"},"content_sha256":"e3c99ebd868db7d30ae05bc0c294f5044fc686e73264dafa60f5de19d823eee2","schema_version":"1.0","event_id":"sha256:e3c99ebd868db7d30ae05bc0c294f5044fc686e73264dafa60f5de19d823eee2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:57XR3W3TN74OOMQUZULBWMQYFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Minlie Huang, Runze Liang, Ryuichi Takanobu","submitted_at":"2020-04-08T04:51:40Z","abstract_excerpt":"Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03809","kind":"arxiv","version":2},"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/2004.03809/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":"2026-07-05T00:57:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMq1AITqE+XmAj0Smqr2sH3FOHLcz3TNJTyAz2hFcESjWavUdupiM5y9s3gFi7s4uqjZAAwUNdFbqjWPZtlAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:11:04.000319Z"},"content_sha256":"6c14a058f0de876253d1abc4d9bbd59fb413d891dc498aeb2224c5c5f1772f09","schema_version":"1.0","event_id":"sha256:6c14a058f0de876253d1abc4d9bbd59fb413d891dc498aeb2224c5c5f1772f09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/bundle.json","state_url":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57XR3W3TN74OOMQUZULBWMQYFF/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":"2026-08-16T20:11:04Z","links":{"resolver":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF","bundle":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/bundle.json","state":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57XR3W3TN74OOMQUZULBWMQYFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:57XR3W3TN74OOMQUZULBWMQYFF","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":"2b8a6fd2b8973f09404ab9ffaf22d2fa52671b470436e2f5940d2cd147f3873a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","title_canon_sha256":"4a725279ac1a65111ddf52c65c7ee198846a0be4fa53e2c55af5156076707513"},"schema_version":"1.0","source":{"id":"2004.03809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03809","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03809v2","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03809","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_12","alias_value":"57XR3W3TN74O","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_16","alias_value":"57XR3W3TN74OOMQU","created_at":"2026-07-05T00:57:35Z"},{"alias_kind":"pith_short_8","alias_value":"57XR3W3T","created_at":"2026-07-05T00:57:35Z"}],"graph_snapshots":[{"event_id":"sha256:6c14a058f0de876253d1abc4d9bbd59fb413d891dc498aeb2224c5c5f1772f09","target":"graph","created_at":"2026-07-05T00:57:35Z","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/2004.03809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning,","authors_text":"Minlie Huang, Runze Liang, Ryuichi Takanobu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03809","kind":"arxiv","version":2},"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:e3c99ebd868db7d30ae05bc0c294f5044fc686e73264dafa60f5de19d823eee2","target":"record","created_at":"2026-07-05T00:57:35Z","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":"2b8a6fd2b8973f09404ab9ffaf22d2fa52671b470436e2f5940d2cd147f3873a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","title_canon_sha256":"4a725279ac1a65111ddf52c65c7ee198846a0be4fa53e2c55af5156076707513"},"schema_version":"1.0","source":{"id":"2004.03809","kind":"arxiv","version":2}},"canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","first_computed_at":"2026-07-05T00:57:35.595231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:35.595231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2v3ahne0nEjBNhBxNqKD6JqHI93yWJjU5P4L/DD8nc4XajtH1UXRmCAg5nXOdXLaNt9qYYHVduik/qBqu98gCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:35.595616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3c99ebd868db7d30ae05bc0c294f5044fc686e73264dafa60f5de19d823eee2","sha256:6c14a058f0de876253d1abc4d9bbd59fb413d891dc498aeb2224c5c5f1772f09"],"state_sha256":"8e9866b1b8b968b048e756abbf812b6d6e6b8b0631b3a95082d0e07f899f2296"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuGq3Y321kfuf+xlk+xLuH0cv5UdKg4pROedUaJBiGSRpbBtAGUsFqQ5YFSjpczB/WoxxVeS1FzDVtZnIZo2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:11:04.003857Z","bundle_sha256":"2679a02d246af352a6b56cd0b483a5909204bcbcbeeeee2b9ab8e45f207f2890"}}