{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GKM36CFKE3WUMH5WG4VYTUS4F6","short_pith_number":"pith:GKM36CFK","schema_version":"1.0","canonical_sha256":"3299bf08aa26ed461fb6372b89d25c2fa9ad7c7f04e8f9600ff864fbe3b9a6c6","source":{"kind":"arxiv","id":"1508.03386","version":1},"attestation_state":"computed","paper":{"title":"Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"David Vandyke, Dongho Kim, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","submitted_at":"2015-08-13T23:44:03Z","abstract_excerpt":"To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the dialogue's success by observing whether this presented task was achieved or not. Our aim however is to be able to learn from real users acting under their own volition, in which case it is non-trivial to rate the success as any prior knowledge of the task is simply unavailable. User feedback may be utilised but has been found to be inconsistent. Hence, here we pre"},"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":"1508.03386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-13T23:44:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dbc50ca39f41c18f19c30c2ab56ebe7ef925119e58dd943ca6510c6f172ba794","abstract_canon_sha256":"8c909ca222114a378c49555def2222ea663c30db69af20a58f1c33857b5a56f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:17.953893Z","signature_b64":"v3i3ltLk7ViAe6i2+/o8FVwfFvG/76wbNaxnYyoChd4FPAt/MuUgLRBrExnEi81LP1ZMwJ3DyX++YoliTeqwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3299bf08aa26ed461fb6372b89d25c2fa9ad7c7f04e8f9600ff864fbe3b9a6c6","last_reissued_at":"2026-05-18T01:35:17.953153Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:17.953153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"David Vandyke, Dongho Kim, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","submitted_at":"2015-08-13T23:44:03Z","abstract_excerpt":"To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the dialogue's success by observing whether this presented task was achieved or not. Our aim however is to be able to learn from real users acting under their own volition, in which case it is non-trivial to rate the success as any prior knowledge of the task is simply unavailable. User feedback may be utilised but has been found to be inconsistent. Hence, here we pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03386","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1508.03386","created_at":"2026-05-18T01:35:17.953275+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.03386v1","created_at":"2026-05-18T01:35:17.953275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03386","created_at":"2026-05-18T01:35:17.953275+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKM36CFKE3WU","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKM36CFKE3WUMH5W","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKM36CFK","created_at":"2026-05-18T12:29:22.688609+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/GKM36CFKE3WUMH5WG4VYTUS4F6","json":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6.json","graph_json":"https://pith.science/api/pith-number/GKM36CFKE3WUMH5WG4VYTUS4F6/graph.json","events_json":"https://pith.science/api/pith-number/GKM36CFKE3WUMH5WG4VYTUS4F6/events.json","paper":"https://pith.science/paper/GKM36CFK"},"agent_actions":{"view_html":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6","download_json":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6.json","view_paper":"https://pith.science/paper/GKM36CFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.03386&json=true","fetch_graph":"https://pith.science/api/pith-number/GKM36CFKE3WUMH5WG4VYTUS4F6/graph.json","fetch_events":"https://pith.science/api/pith-number/GKM36CFKE3WUMH5WG4VYTUS4F6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6/action/storage_attestation","attest_author":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6/action/author_attestation","sign_citation":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6/action/citation_signature","submit_replication":"https://pith.science/pith/GKM36CFKE3WUMH5WG4VYTUS4F6/action/replication_record"}},"created_at":"2026-05-18T01:35:17.953275+00:00","updated_at":"2026-05-18T01:35:17.953275+00:00"}