{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J3O2BL3EPKFI45ILWN5JOMZNNS","short_pith_number":"pith:J3O2BL3E","schema_version":"1.0","canonical_sha256":"4edda0af647a8a8e750bb37a97332d6cb14f1826a55c428a2d1e3147fd97b717","source":{"kind":"arxiv","id":"2105.10267","version":2},"attestation_state":"computed","paper":{"title":"Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Girayhan Ozbay, Da-shan Shiu, Ferdinando Insalata, Maolin Li, Philipp Ennen, Sepehr Jalali, Yen-Ting Lin, Ye Tian","submitted_at":"2021-05-21T10:37:10Z","abstract_excerpt":"In a dialogue system pipeline, a natural language generation (NLG) unit converts the dialogue direction and content to a corresponding natural language realization. A recent trend for dialogue systems is to first pre-train on large datasets and then fine-tune in a supervised manner using datasets annotated with application-specific features. Though novel behaviours can be learned from custom annotation, the required effort severely bounds the quantity of the training set, and the application-specific nature limits the reuse. In light of the recent success of data-driven approaches, we propose "},"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":"2105.10267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-21T10:37:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7e92070ad1a0db93be34a30320d9fca97be7a77a77fdc4ece62bf23a09b1325f","abstract_canon_sha256":"80a35c7b0613bb382fe6d07950387e20e996d1041beaed67cf98ab00ae5096e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:31.462965Z","signature_b64":"5X9lQDHT5RmnkG7fnsl7vzk06TdFX7zZO5vx2boAMu36h2iF0brPa+P3EEMo1qBdUHTUmUFc9NOegOjnREkBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4edda0af647a8a8e750bb37a97332d6cb14f1826a55c428a2d1e3147fd97b717","last_reissued_at":"2026-07-05T02:42:31.462436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:31.462436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Girayhan Ozbay, Da-shan Shiu, Ferdinando Insalata, Maolin Li, Philipp Ennen, Sepehr Jalali, Yen-Ting Lin, Ye Tian","submitted_at":"2021-05-21T10:37:10Z","abstract_excerpt":"In a dialogue system pipeline, a natural language generation (NLG) unit converts the dialogue direction and content to a corresponding natural language realization. A recent trend for dialogue systems is to first pre-train on large datasets and then fine-tune in a supervised manner using datasets annotated with application-specific features. Though novel behaviours can be learned from custom annotation, the required effort severely bounds the quantity of the training set, and the application-specific nature limits the reuse. In light of the recent success of data-driven approaches, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10267","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.10267/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":"2105.10267","created_at":"2026-07-05T02:42:31.462495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.10267v2","created_at":"2026-07-05T02:42:31.462495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10267","created_at":"2026-07-05T02:42:31.462495+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3O2BL3EPKFI","created_at":"2026-07-05T02:42:31.462495+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3O2BL3EPKFI45IL","created_at":"2026-07-05T02:42:31.462495+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3O2BL3E","created_at":"2026-07-05T02:42:31.462495+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/J3O2BL3EPKFI45ILWN5JOMZNNS","json":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS.json","graph_json":"https://pith.science/api/pith-number/J3O2BL3EPKFI45ILWN5JOMZNNS/graph.json","events_json":"https://pith.science/api/pith-number/J3O2BL3EPKFI45ILWN5JOMZNNS/events.json","paper":"https://pith.science/paper/J3O2BL3E"},"agent_actions":{"view_html":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS","download_json":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS.json","view_paper":"https://pith.science/paper/J3O2BL3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.10267&json=true","fetch_graph":"https://pith.science/api/pith-number/J3O2BL3EPKFI45ILWN5JOMZNNS/graph.json","fetch_events":"https://pith.science/api/pith-number/J3O2BL3EPKFI45ILWN5JOMZNNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS/action/storage_attestation","attest_author":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS/action/author_attestation","sign_citation":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS/action/citation_signature","submit_replication":"https://pith.science/pith/J3O2BL3EPKFI45ILWN5JOMZNNS/action/replication_record"}},"created_at":"2026-07-05T02:42:31.462495+00:00","updated_at":"2026-07-05T02:42:31.462495+00:00"}