{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PVJK624CQS3RINZAJPN4A67HDG","short_pith_number":"pith:PVJK624C","canonical_record":{"source":{"id":"1711.11023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T18:51:14Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"d5e9ef26000d81082d77a1d67e8b7b6804218d96952f5e1851b023602ba051dc","abstract_canon_sha256":"ba392c07c4a34f06387f3a753ad70207651b6d8c3116eea13786c1899f2a12bb"},"schema_version":"1.0"},"canonical_sha256":"7d52af6b8284b71437204bdbc07be7198fc303a163f7ba41ac739e728ed8494b","source":{"kind":"arxiv","id":"1711.11023","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11023","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11023v2","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11023","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"PVJK624CQS3R","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PVJK624CQS3RINZA","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PVJK624C","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PVJK624CQS3RINZAJPN4A67HDG","target":"record","payload":{"canonical_record":{"source":{"id":"1711.11023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T18:51:14Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"d5e9ef26000d81082d77a1d67e8b7b6804218d96952f5e1851b023602ba051dc","abstract_canon_sha256":"ba392c07c4a34f06387f3a753ad70207651b6d8c3116eea13786c1899f2a12bb"},"schema_version":"1.0"},"canonical_sha256":"7d52af6b8284b71437204bdbc07be7198fc303a163f7ba41ac739e728ed8494b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:08.553253Z","signature_b64":"P9rYwkCZx8u9cAr9Y83MEcve0iKEw1ttEvOM/Su/rXYlv24AqpcaopAakhhj0pCbsg+sXSELV8kRDndWrP41Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d52af6b8284b71437204bdbc07be7198fc303a163f7ba41ac739e728ed8494b","last_reissued_at":"2026-05-18T00:19:08.552538Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:08.552538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.11023","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":"2026-05-18T00:19:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7Va5kpI5VzNNiAOlz+uDxM6J2BHfDaGCOfVZBXw+KZTdOrSmXtJ0NLWpVOgqTh5/yY75vDC9ETB5660A9Q5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T07:57:06.495290Z"},"content_sha256":"9572a74d02bb08c429a4d9f595ef253c9898616b42371d43e69c0e4b4122dc14","schema_version":"1.0","event_id":"sha256:9572a74d02bb08c429a4d9f595ef253c9898616b42371d43e69c0e4b4122dc14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PVJK624CQS3RINZAJPN4A67HDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"stat.ML","authors_text":"I\\~nigo Casanueva, Lina Rojas-Barahona, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","submitted_at":"2017-11-29T18:51:14Z","abstract_excerpt":"Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been investigated over recent years. However, the lack of a common benchmarking framework makes it difficult to perform a fair comparison between different models and their capability to generalise to different environments. Therefore, this paper proposes a set of challenging simulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11023","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":""},"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":"2026-05-18T00:19:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMUGeSbPKEhFmLdhQbracBqewhh0eZYyvZl55YiF+dX8aouU84zmJMLSHUAnASXzHEDDCXsh5ODkfytt2jk1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T07:57:06.495962Z"},"content_sha256":"5fa407c3890b7a20932c099e5f441a70c23fd623c9644f3335cea05d5b5a171f","schema_version":"1.0","event_id":"sha256:5fa407c3890b7a20932c099e5f441a70c23fd623c9644f3335cea05d5b5a171f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVJK624CQS3RINZAJPN4A67HDG/bundle.json","state_url":"https://pith.science/pith/PVJK624CQS3RINZAJPN4A67HDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVJK624CQS3RINZAJPN4A67HDG/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":"2026-06-09T07:57:06Z","links":{"resolver":"https://pith.science/pith/PVJK624CQS3RINZAJPN4A67HDG","bundle":"https://pith.science/pith/PVJK624CQS3RINZAJPN4A67HDG/bundle.json","state":"https://pith.science/pith/PVJK624CQS3RINZAJPN4A67HDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVJK624CQS3RINZAJPN4A67HDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PVJK624CQS3RINZAJPN4A67HDG","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":"ba392c07c4a34f06387f3a753ad70207651b6d8c3116eea13786c1899f2a12bb","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T18:51:14Z","title_canon_sha256":"d5e9ef26000d81082d77a1d67e8b7b6804218d96952f5e1851b023602ba051dc"},"schema_version":"1.0","source":{"id":"1711.11023","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11023","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11023v2","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11023","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"PVJK624CQS3R","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PVJK624CQS3RINZA","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PVJK624C","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:5fa407c3890b7a20932c099e5f441a70c23fd623c9644f3335cea05d5b5a171f","target":"graph","created_at":"2026-05-18T00:19:08Z","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":"Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been investigated over recent years. However, the lack of a common benchmarking framework makes it difficult to perform a fair comparison between different models and their capability to generalise to different environments. Therefore, this paper proposes a set of challenging simulat","authors_text":"I\\~nigo Casanueva, Lina Rojas-Barahona, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T18:51:14Z","title":"A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11023","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":"sha256:9572a74d02bb08c429a4d9f595ef253c9898616b42371d43e69c0e4b4122dc14","target":"record","created_at":"2026-05-18T00:19:08Z","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":"ba392c07c4a34f06387f3a753ad70207651b6d8c3116eea13786c1899f2a12bb","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T18:51:14Z","title_canon_sha256":"d5e9ef26000d81082d77a1d67e8b7b6804218d96952f5e1851b023602ba051dc"},"schema_version":"1.0","source":{"id":"1711.11023","kind":"arxiv","version":2}},"canonical_sha256":"7d52af6b8284b71437204bdbc07be7198fc303a163f7ba41ac739e728ed8494b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d52af6b8284b71437204bdbc07be7198fc303a163f7ba41ac739e728ed8494b","first_computed_at":"2026-05-18T00:19:08.552538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:08.552538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P9rYwkCZx8u9cAr9Y83MEcve0iKEw1ttEvOM/Su/rXYlv24AqpcaopAakhhj0pCbsg+sXSELV8kRDndWrP41Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:08.553253Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.11023","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9572a74d02bb08c429a4d9f595ef253c9898616b42371d43e69c0e4b4122dc14","sha256:5fa407c3890b7a20932c099e5f441a70c23fd623c9644f3335cea05d5b5a171f"],"state_sha256":"cb037519b2ab74abc0140a1c1dc9060370475998bea4b6a8e1ae49eac4cc8a27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VB2BlpsWneSIlMJTlmTj90kh4kKk82Bem+emdlkR+Qd4PSW8rhpOy+sqJ5h1qPbUuZIFSUqI9rYWFVcirRjnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T07:57:06.500251Z","bundle_sha256":"a3aa71ca3b936fd707f070cbd2eb361f593fb0bc729bee62f923b099a18c25b8"}}