{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4BFUT2CPZRIIQ4LONGZCVMGMIA","short_pith_number":"pith:4BFUT2CP","canonical_record":{"source":{"id":"1711.11486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T16:09:02Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"67f57ba990a6c24ba7e63d67a41a2f0add3b56d3f5ec4ad813633032bc8d8c60","abstract_canon_sha256":"bf55e9ce9106d31aed78ba5c0667d5e248233fc4329f1d01938979a6b5c2c474"},"schema_version":"1.0"},"canonical_sha256":"e04b49e84fcc5088716e69b22ab0cc4026d0561d48dae7acd2a88fdc02c35eda","source":{"kind":"arxiv","id":"1711.11486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11486","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11486v1","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11486","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"4BFUT2CPZRII","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4BFUT2CPZRIIQ4LO","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4BFUT2CP","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4BFUT2CPZRIIQ4LONGZCVMGMIA","target":"record","payload":{"canonical_record":{"source":{"id":"1711.11486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T16:09:02Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"67f57ba990a6c24ba7e63d67a41a2f0add3b56d3f5ec4ad813633032bc8d8c60","abstract_canon_sha256":"bf55e9ce9106d31aed78ba5c0667d5e248233fc4329f1d01938979a6b5c2c474"},"schema_version":"1.0"},"canonical_sha256":"e04b49e84fcc5088716e69b22ab0cc4026d0561d48dae7acd2a88fdc02c35eda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.704352Z","signature_b64":"On2K1mXlNXew3MlzN2NEhatLFhRB+hiemsvsC+Rsyf0ppI2IWariXrWgsD9bWLGMMhGYcbjxOj4KiBUuHwknCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04b49e84fcc5088716e69b22ab0cc4026d0561d48dae7acd2a88fdc02c35eda","last_reissued_at":"2026-05-18T00:29:07.703647Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.703647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.11486","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":"2026-05-18T00:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZ56WONXeZ5nj856L2frqUiRIVFQNP9rElEypKtK1rC6a9jTXN+canowAzX3L69R8+1HvUIu59ojTcysmHRrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:05:23.010807Z"},"content_sha256":"57046d8b99e8e984536eb459562aba5ef415960985c665bfec5fa6854e9f86f7","schema_version":"1.0","event_id":"sha256:57046d8b99e8e984536eb459562aba5ef415960985c665bfec5fa6854e9f86f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4BFUT2CPZRIIQ4LONGZCVMGMIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Christopher Tegho, Milica Ga\\v{s}i\\'c, Pawe{\\l} Budzianowski","submitted_at":"2017-11-30T16:09:02Z","abstract_excerpt":"In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning methods are very promising but rely on epsilon-greedy exploration, thus subjecting the user to a random choice of action during learning. Alternative approaches such as Gaussian Process SARSA (GPSARSA) estimate uncertainties and are sample efficient, leading to better user experience, but on the expense of a greater computational complexity. This paper examine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11486","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":"2026-05-18T00:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJ5dNscqCcXHIBV8Vojm96JVKhPTouvvqiAHbSOFOlcSBZeGRIPGSzQd3zcFXQ41PU6V+7+ez8EVoLR1zty4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:05:23.011506Z"},"content_sha256":"3413fe61ef60b499e1a64d84f29f550035596bcf0391475f35cee191add52d2a","schema_version":"1.0","event_id":"sha256:3413fe61ef60b499e1a64d84f29f550035596bcf0391475f35cee191add52d2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/bundle.json","state_url":"https://pith.science/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/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":"2026-06-07T21:05:23Z","links":{"resolver":"https://pith.science/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA","bundle":"https://pith.science/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/bundle.json","state":"https://pith.science/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BFUT2CPZRIIQ4LONGZCVMGMIA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4BFUT2CPZRIIQ4LONGZCVMGMIA","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":"bf55e9ce9106d31aed78ba5c0667d5e248233fc4329f1d01938979a6b5c2c474","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T16:09:02Z","title_canon_sha256":"67f57ba990a6c24ba7e63d67a41a2f0add3b56d3f5ec4ad813633032bc8d8c60"},"schema_version":"1.0","source":{"id":"1711.11486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11486","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11486v1","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11486","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"4BFUT2CPZRII","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4BFUT2CPZRIIQ4LO","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4BFUT2CP","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:3413fe61ef60b499e1a64d84f29f550035596bcf0391475f35cee191add52d2a","target":"graph","created_at":"2026-05-18T00:29:07Z","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":"In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning methods are very promising but rely on epsilon-greedy exploration, thus subjecting the user to a random choice of action during learning. Alternative approaches such as Gaussian Process SARSA (GPSARSA) estimate uncertainties and are sample efficient, leading to better user experience, but on the expense of a greater computational complexity. This paper examine","authors_text":"Christopher Tegho, Milica Ga\\v{s}i\\'c, Pawe{\\l} Budzianowski","cross_cats":["cs.CL","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T16:09:02Z","title":"Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11486","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":"sha256:57046d8b99e8e984536eb459562aba5ef415960985c665bfec5fa6854e9f86f7","target":"record","created_at":"2026-05-18T00:29:07Z","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":"bf55e9ce9106d31aed78ba5c0667d5e248233fc4329f1d01938979a6b5c2c474","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T16:09:02Z","title_canon_sha256":"67f57ba990a6c24ba7e63d67a41a2f0add3b56d3f5ec4ad813633032bc8d8c60"},"schema_version":"1.0","source":{"id":"1711.11486","kind":"arxiv","version":1}},"canonical_sha256":"e04b49e84fcc5088716e69b22ab0cc4026d0561d48dae7acd2a88fdc02c35eda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e04b49e84fcc5088716e69b22ab0cc4026d0561d48dae7acd2a88fdc02c35eda","first_computed_at":"2026-05-18T00:29:07.703647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:07.703647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"On2K1mXlNXew3MlzN2NEhatLFhRB+hiemsvsC+Rsyf0ppI2IWariXrWgsD9bWLGMMhGYcbjxOj4KiBUuHwknCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:07.704352Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.11486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57046d8b99e8e984536eb459562aba5ef415960985c665bfec5fa6854e9f86f7","sha256:3413fe61ef60b499e1a64d84f29f550035596bcf0391475f35cee191add52d2a"],"state_sha256":"16dc97e969fa7759aec56968c3a0d94b39f40c736bb08e7edb6160b8ab8beb0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO2eClQYpo+zKYRDrNvmhwUpRgkr+06Or8bpcGBXlBhoASgjgW0RhOnYm1WdiAyirIAEVLlRu101h1MmNmmmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:05:23.014986Z","bundle_sha256":"d5c62f8741598f5fab6510c724f0d0c3e81e059098dfb635f90337765fc420a2"}}