{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5QT65DSZW6BJWJAZBGMSSCS3LV","short_pith_number":"pith:5QT65DSZ","canonical_record":{"source":{"id":"1811.07550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"d3eabf88b347b503a7a54d1dd0e5b7c46b25e17e58a1d40f755ab4a3b03020de","abstract_canon_sha256":"331fcb10d30bbbeb866cf1e007add43a767c14462c31214f63daae3a7ab275ad"},"schema_version":"1.0"},"canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","source":{"kind":"arxiv","id":"1811.07550","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07550","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07550v1","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07550","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"pith_short_12","alias_value":"5QT65DSZW6BJ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5QT65DSZW6BJWJAZ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5QT65DSZ","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5QT65DSZW6BJWJAZBGMSSCS3LV","target":"record","payload":{"canonical_record":{"source":{"id":"1811.07550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"d3eabf88b347b503a7a54d1dd0e5b7c46b25e17e58a1d40f755ab4a3b03020de","abstract_canon_sha256":"331fcb10d30bbbeb866cf1e007add43a767c14462c31214f63daae3a7ab275ad"},"schema_version":"1.0"},"canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:24.126212Z","signature_b64":"5DBGZBx2bfzbTdFpYmoKMn7IwBCBDhl016+Qkth1gVOpEHGDC2Yu+4NYxx1Menhsd2mMiNliq69jkFMb/VzvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","last_reissued_at":"2026-05-18T00:00:24.125736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:24.125736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.07550","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":"2026-05-18T00:00:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77he9+6xQd7bcKy3t0MD3LClI5n38YfzJGilJv0dX9Bwy5i/B0mtD13cVb0KHjTGd4MriyxbOY+Nt4p92oMyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:54:23.516270Z"},"content_sha256":"c0acc6827e8bd38d1d976790fa4ad5e26c98995996dea0b6b380b7a1960f822e","schema_version":"1.0","event_id":"sha256:c0acc6827e8bd38d1d976790fa4ad5e26c98995996dea0b6b380b7a1960f822e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5QT65DSZW6BJWJAZBGMSSCS3LV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive 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":"Jianfeng Gao, Jingjing Liu, Xiujun Li, Yiming Yang, Yuexin Wu","submitted_at":"2018-11-19T08:23:34Z","abstract_excerpt":"Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07550","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":""},"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":"2026-05-18T00:00:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U2gr3tvUYK0ur3d8YnNyQ8KfOoqN8/4xaXC6BQJqcxlReL0xO/4Xusn8xdDvIiJ3dqwGxwZjISFqrG4KoitnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:54:23.516661Z"},"content_sha256":"f05720e67617d5a0229abc14e0c4d82cb929768ed97d7eab0412832952835c55","schema_version":"1.0","event_id":"sha256:f05720e67617d5a0229abc14e0c4d82cb929768ed97d7eab0412832952835c55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/bundle.json","state_url":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/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":"2026-06-11T12:54:23Z","links":{"resolver":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV","bundle":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/bundle.json","state":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5QT65DSZW6BJWJAZBGMSSCS3LV","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":"331fcb10d30bbbeb866cf1e007add43a767c14462c31214f63daae3a7ab275ad","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","title_canon_sha256":"d3eabf88b347b503a7a54d1dd0e5b7c46b25e17e58a1d40f755ab4a3b03020de"},"schema_version":"1.0","source":{"id":"1811.07550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07550","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07550v1","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07550","created_at":"2026-05-18T00:00:24Z"},{"alias_kind":"pith_short_12","alias_value":"5QT65DSZW6BJ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5QT65DSZW6BJWJAZ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5QT65DSZ","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:f05720e67617d5a0229abc14e0c4d82cb929768ed97d7eab0412832952835c55","target":"graph","created_at":"2026-05-18T00:00:24Z","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 task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically ","authors_text":"Jianfeng Gao, Jingjing Liu, Xiujun Li, Yiming Yang, Yuexin Wu","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07550","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:c0acc6827e8bd38d1d976790fa4ad5e26c98995996dea0b6b380b7a1960f822e","target":"record","created_at":"2026-05-18T00:00:24Z","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":"331fcb10d30bbbeb866cf1e007add43a767c14462c31214f63daae3a7ab275ad","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","title_canon_sha256":"d3eabf88b347b503a7a54d1dd0e5b7c46b25e17e58a1d40f755ab4a3b03020de"},"schema_version":"1.0","source":{"id":"1811.07550","kind":"arxiv","version":1}},"canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","first_computed_at":"2026-05-18T00:00:24.125736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:24.125736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5DBGZBx2bfzbTdFpYmoKMn7IwBCBDhl016+Qkth1gVOpEHGDC2Yu+4NYxx1Menhsd2mMiNliq69jkFMb/VzvDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:24.126212Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0acc6827e8bd38d1d976790fa4ad5e26c98995996dea0b6b380b7a1960f822e","sha256:f05720e67617d5a0229abc14e0c4d82cb929768ed97d7eab0412832952835c55"],"state_sha256":"035bd3b4bfd92484fa9dd270290bab91ac7abee0d884e6963e46e5707fdad4b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+RBaKP9BtIqlx/oB9cPHi32/tJwMqDCSFvX6camCJXIfE2vHllmPqgyILHhvmGQtB/oYDrMxk0hRISzOLYaAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:54:23.518856Z","bundle_sha256":"111dfcf7b7efc37aea45cd361fb693ce40e767ea995f20bcf708f42f836054f9"}}