{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SR4IMHDJL44ITN2O3YYWIHY7ES","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":"f502ec182940c41aa5a63df9539621e89594f3ccec57236495c8649d9bcc15a7","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T08:41:54Z","title_canon_sha256":"65fe10cd77039027c1d8c8fa00c9d4f50017663aa5b20edc59fe36b8e3ccef8d"},"schema_version":"1.0","source":{"id":"2004.08114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08114","created_at":"2026-07-05T00:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08114v1","created_at":"2026-07-05T00:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08114","created_at":"2026-07-05T00:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"SR4IMHDJL44I","created_at":"2026-07-05T00:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"SR4IMHDJL44ITN2O","created_at":"2026-07-05T00:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"SR4IMHDJ","created_at":"2026-07-05T00:55:50Z"}],"graph_snapshots":[{"event_id":"sha256:2482a294bc049e753ea2d9aaed26d70fdc47e7d22730c5d7f93cbe6575985aff","target":"graph","created_at":"2026-07-05T00:55:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.08114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present our submission to the End-to-End Multi-Domain Dialog Challenge Track of the Eighth Dialog System Technology Challenge. Our proposed dialog system adopts a pipeline architecture, with distinct components for Natural Language Understanding, Dialog State Tracking, Dialog Management and Natural Language Generation. At the core of our system is a reinforcement learning algorithm which uses Deep Q-learning from Demonstrations to learn a dialog policy with the help of expert examples. We find that demonstrations are essential to training an accurate dialog policy where both state and actio","authors_text":"Gabriel Gordon-Hall, Gerasimos Lampouras, Ignacio Iacobacci, Philip John Gorinski","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T08:41:54Z","title":"Show Us the Way: Learning to Manage Dialog from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08114","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:ad3d1573086b3afd67e3a7280dcb0ffa57ef60d2d11722c8de80c3eb1a84b014","target":"record","created_at":"2026-07-05T00:55:50Z","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":"f502ec182940c41aa5a63df9539621e89594f3ccec57236495c8649d9bcc15a7","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T08:41:54Z","title_canon_sha256":"65fe10cd77039027c1d8c8fa00c9d4f50017663aa5b20edc59fe36b8e3ccef8d"},"schema_version":"1.0","source":{"id":"2004.08114","kind":"arxiv","version":1}},"canonical_sha256":"9478861c695f3889b74ede31641f1f24ac20f0d2a590374f8cf335f86dcec2ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9478861c695f3889b74ede31641f1f24ac20f0d2a590374f8cf335f86dcec2ba","first_computed_at":"2026-07-05T00:55:50.206870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:50.206870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vfiTj2WToIbX1IkBikke9YCY+mTIiqp2VJ66EYW1aHM7/X35CuYn+hOAqFeaaeZDvUvhtEXfXIIprByVJmjhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:50.207264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.08114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad3d1573086b3afd67e3a7280dcb0ffa57ef60d2d11722c8de80c3eb1a84b014","sha256:2482a294bc049e753ea2d9aaed26d70fdc47e7d22730c5d7f93cbe6575985aff"],"state_sha256":"32510560554718f033f752a71f65f57fde6cf17bf2704c557d14429941aff014"}