{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OKH7ZXWQK7AW5C7V2T7BJ6WAYD","short_pith_number":"pith:OKH7ZXWQ","canonical_record":{"source":{"id":"1608.05081","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"4acf1f50a38b1c3a44c21c477c44e7cdd1363c4be16e8dbace5c71619f5e5b5b","abstract_canon_sha256":"d22b71b8bba6d3395edf5627e5ceb74c56b0d34c20ccde7bc27bd01a296bc510"},"schema_version":"1.0"},"canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","source":{"kind":"arxiv","id":"1608.05081","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05081","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05081v4","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05081","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"pith_short_12","alias_value":"OKH7ZXWQK7AW","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OKH7ZXWQK7AW5C7V","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OKH7ZXWQ","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OKH7ZXWQK7AW5C7V2T7BJ6WAYD","target":"record","payload":{"canonical_record":{"source":{"id":"1608.05081","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"4acf1f50a38b1c3a44c21c477c44e7cdd1363c4be16e8dbace5c71619f5e5b5b","abstract_canon_sha256":"d22b71b8bba6d3395edf5627e5ceb74c56b0d34c20ccde7bc27bd01a296bc510"},"schema_version":"1.0"},"canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:31.439181Z","signature_b64":"01olYdvMFmEpm5+LDzFYSVVSnazi/YVRFAvkWHE8a7bOUpyaX9UrgmDHfNjgaTRCLZovSZrv3YmuAbT7U2SkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","last_reissued_at":"2026-05-18T00:29:31.438558Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:31.438558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.05081","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOgyaRUW4eRXRYz8r5l0h4HdgtlmNTLVQjll7nBmOuTgS6DmcEnJNOt5uaf4Tqu+Qa7czs3gyjsPd9aW08JMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T12:33:34.469931Z"},"content_sha256":"02260ee03a06a26f61d8abdd8f56495425d2831faecf40d9fd1a15d1c50f55ea","schema_version":"1.0","event_id":"sha256:02260ee03a06a26f61d8abdd8f56495425d2831faecf40d9fd1a15d1c50f55ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OKH7ZXWQK7AW5C7V2T7BJ6WAYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faisal Ahmed, Jianfeng Gao, Li Deng, Lihong Li, Xiujun Li, Zachary C. Lipton","submitted_at":"2016-08-17T20:00:04Z","abstract_excerpt":"We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05081","kind":"arxiv","version":4},"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":"2026-05-18T00:29:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49q2TpNgHGZeaU+ouoUMdHZdny3Xaopc5E1n7EyyVCLHEeCIuWFKN9tcXrBVJ9UAnhOPgMFm1MeSDj5G3yKeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T12:33:34.470275Z"},"content_sha256":"6b1a89a19e48135344477065ea7acbe43737335c4a807446a02995fd6e99acd6","schema_version":"1.0","event_id":"sha256:6b1a89a19e48135344477065ea7acbe43737335c4a807446a02995fd6e99acd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/bundle.json","state_url":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/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":"2026-07-02T12:33:34Z","links":{"resolver":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD","bundle":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/bundle.json","state":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OKH7ZXWQK7AW5C7V2T7BJ6WAYD","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":"d22b71b8bba6d3395edf5627e5ceb74c56b0d34c20ccde7bc27bd01a296bc510","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","title_canon_sha256":"4acf1f50a38b1c3a44c21c477c44e7cdd1363c4be16e8dbace5c71619f5e5b5b"},"schema_version":"1.0","source":{"id":"1608.05081","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05081","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05081v4","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05081","created_at":"2026-05-18T00:29:31Z"},{"alias_kind":"pith_short_12","alias_value":"OKH7ZXWQK7AW","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OKH7ZXWQK7AW5C7V","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OKH7ZXWQ","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:6b1a89a19e48135344477065ea7acbe43737335c4a807446a02995fd6e99acd6","target":"graph","created_at":"2026-05-18T00:29:31Z","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":"We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.","authors_text":"Faisal Ahmed, Jianfeng Gao, Li Deng, Lihong Li, Xiujun Li, Zachary C. Lipton","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05081","kind":"arxiv","version":4},"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":"sha256:02260ee03a06a26f61d8abdd8f56495425d2831faecf40d9fd1a15d1c50f55ea","target":"record","created_at":"2026-05-18T00:29:31Z","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":"d22b71b8bba6d3395edf5627e5ceb74c56b0d34c20ccde7bc27bd01a296bc510","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","title_canon_sha256":"4acf1f50a38b1c3a44c21c477c44e7cdd1363c4be16e8dbace5c71619f5e5b5b"},"schema_version":"1.0","source":{"id":"1608.05081","kind":"arxiv","version":4}},"canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","first_computed_at":"2026-05-18T00:29:31.438558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:31.438558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"01olYdvMFmEpm5+LDzFYSVVSnazi/YVRFAvkWHE8a7bOUpyaX9UrgmDHfNjgaTRCLZovSZrv3YmuAbT7U2SkDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:31.439181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.05081","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02260ee03a06a26f61d8abdd8f56495425d2831faecf40d9fd1a15d1c50f55ea","sha256:6b1a89a19e48135344477065ea7acbe43737335c4a807446a02995fd6e99acd6"],"state_sha256":"557344df36a90c0a856a049201c344651c9ca2302907c84b7fcf4e6a1fce60a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wBLcdPcdMS6rlpK960l/Mj1nj9pUD2GipitcYJAordQo5a38FNi8DKefUR34q1airiKtL9KJEy6OOYGhw97bAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T12:33:34.472188Z","bundle_sha256":"71bde77da0fad239057405fc9eb56e0b20f165bc83f3aeca4b4cce38cbe5f36e"}}