{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XORNQB7WYJAW5G6T5HH2HB62BN","short_pith_number":"pith:XORNQB7W","canonical_record":{"source":{"id":"1801.06176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9","abstract_canon_sha256":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423"},"schema_version":"1.0"},"canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","source":{"kind":"arxiv","id":"1801.06176","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06176v3","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"XORNQB7WYJAW","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XORNQB7WYJAW5G6T","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XORNQB7W","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XORNQB7WYJAW5G6T5HH2HB62BN","target":"record","payload":{"canonical_record":{"source":{"id":"1801.06176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9","abstract_canon_sha256":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423"},"schema_version":"1.0"},"canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:06.139762Z","signature_b64":"d+m3Myf+9Xfjw5NyjK7B4f7wAraLtdas/2tHhKN9Se2k6JmDdW7+c39iJ+iRo/xnvjdi5mkWkq0m2GZDMUs1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","last_reissued_at":"2026-05-18T00:15:06.139055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:06.139055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.06176","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZzhEv1U4H/yll1MvLr/WHUPkKr1UVfEcqPnB6cMQOnYhI3ZbwBMe6OqDhO336BeIAeKvLizq3oCxL0tXpkZ/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:45:10.607786Z"},"content_sha256":"8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12","schema_version":"1.0","event_id":"sha256:8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XORNQB7WYJAW5G6T5HH2HB62BN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su, Xiujun Li","submitted_at":"2018-01-18T18:57:33Z","abstract_excerpt":"Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06176","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QIuSOfg6aylGVePzxPL4kj1bsE8LpP5V/le373Fq5VCookdXFrZ5a98G6DPuLZoQBWrA/f8GUbNCmXqQRg2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:45:10.608246Z"},"content_sha256":"a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df","schema_version":"1.0","event_id":"sha256:a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XORNQB7WYJAW5G6T5HH2HB62BN/bundle.json","state_url":"https://pith.science/pith/XORNQB7WYJAW5G6T5HH2HB62BN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XORNQB7WYJAW5G6T5HH2HB62BN/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":"2026-08-09T03:45:10Z","links":{"resolver":"https://pith.science/pith/XORNQB7WYJAW5G6T5HH2HB62BN","bundle":"https://pith.science/pith/XORNQB7WYJAW5G6T5HH2HB62BN/bundle.json","state":"https://pith.science/pith/XORNQB7WYJAW5G6T5HH2HB62BN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XORNQB7WYJAW5G6T5HH2HB62BN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XORNQB7WYJAW5G6T5HH2HB62BN","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":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9"},"schema_version":"1.0","source":{"id":"1801.06176","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06176v3","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"XORNQB7WYJAW","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XORNQB7WYJAW5G6T","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XORNQB7W","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df","target":"graph","created_at":"2026-05-18T00:15:06Z","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"},"paper":{"abstract_excerpt":"Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the wor","authors_text":"Baolin Peng, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su, Xiujun Li","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06176","kind":"arxiv","version":3},"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":"sha256:8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12","target":"record","created_at":"2026-05-18T00:15:06Z","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":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9"},"schema_version":"1.0","source":{"id":"1801.06176","kind":"arxiv","version":3}},"canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","first_computed_at":"2026-05-18T00:15:06.139055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:06.139055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d+m3Myf+9Xfjw5NyjK7B4f7wAraLtdas/2tHhKN9Se2k6JmDdW7+c39iJ+iRo/xnvjdi5mkWkq0m2GZDMUs1CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:06.139762Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.06176","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12","sha256:a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df"],"state_sha256":"259653c6a43cb1405dda36ff7e5cd7666bfa5322c09ffbdbb0c79cb1bd64d75c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HjqHLGzBKzSnf79FRDwedogK0Q5nBtIwuEYMZG1W4M8ZvsUni4QgQp4L/niMSg/A9I6eedkhevbayUvZypOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:45:10.611698Z","bundle_sha256":"abfda50c0f52d4d4bc7414c8f6b57c5779c822a4238386e45dc78e4d1e50aa67"}}