{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SR4IMHDJL44ITN2O3YYWIHY7ES","short_pith_number":"pith:SR4IMHDJ","schema_version":"1.0","canonical_sha256":"9478861c695f3889b74ede31641f1f24ac20f0d2a590374f8cf335f86dcec2ba","source":{"kind":"arxiv","id":"2004.08114","version":1},"attestation_state":"computed","paper":{"title":"Show Us the Way: Learning to Manage Dialog from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Gabriel Gordon-Hall, Gerasimos Lampouras, Ignacio Iacobacci, Philip John Gorinski","submitted_at":"2020-04-17T08:41:54Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.08114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T08:41:54Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"65fe10cd77039027c1d8c8fa00c9d4f50017663aa5b20edc59fe36b8e3ccef8d","abstract_canon_sha256":"f502ec182940c41aa5a63df9539621e89594f3ccec57236495c8649d9bcc15a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:50.207264Z","signature_b64":"vfiTj2WToIbX1IkBikke9YCY+mTIiqp2VJ66EYW1aHM7/X35CuYn+hOAqFeaaeZDvUvhtEXfXIIprByVJmjhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9478861c695f3889b74ede31641f1f24ac20f0d2a590374f8cf335f86dcec2ba","last_reissued_at":"2026-07-05T00:55:50.206870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:50.206870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Show Us the Way: Learning to Manage Dialog from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Gabriel Gordon-Hall, Gerasimos Lampouras, Ignacio Iacobacci, Philip John Gorinski","submitted_at":"2020-04-17T08:41:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08114","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.08114/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.08114","created_at":"2026-07-05T00:55:50.206925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.08114v1","created_at":"2026-07-05T00:55:50.206925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08114","created_at":"2026-07-05T00:55:50.206925+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR4IMHDJL44I","created_at":"2026-07-05T00:55:50.206925+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR4IMHDJL44ITN2O","created_at":"2026-07-05T00:55:50.206925+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR4IMHDJ","created_at":"2026-07-05T00:55:50.206925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES","json":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES.json","graph_json":"https://pith.science/api/pith-number/SR4IMHDJL44ITN2O3YYWIHY7ES/graph.json","events_json":"https://pith.science/api/pith-number/SR4IMHDJL44ITN2O3YYWIHY7ES/events.json","paper":"https://pith.science/paper/SR4IMHDJ"},"agent_actions":{"view_html":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES","download_json":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES.json","view_paper":"https://pith.science/paper/SR4IMHDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.08114&json=true","fetch_graph":"https://pith.science/api/pith-number/SR4IMHDJL44ITN2O3YYWIHY7ES/graph.json","fetch_events":"https://pith.science/api/pith-number/SR4IMHDJL44ITN2O3YYWIHY7ES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES/action/storage_attestation","attest_author":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES/action/author_attestation","sign_citation":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES/action/citation_signature","submit_replication":"https://pith.science/pith/SR4IMHDJL44ITN2O3YYWIHY7ES/action/replication_record"}},"created_at":"2026-07-05T00:55:50.206925+00:00","updated_at":"2026-07-05T00:55:50.206925+00:00"}