{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YULXUPPR5IGQHPJRK3MDGDSFVJ","short_pith_number":"pith:YULXUPPR","schema_version":"1.0","canonical_sha256":"c5177a3df1ea0d03bd3156d8330e45aa42ef005c418dd19fa164994f00080224","source":{"kind":"arxiv","id":"2009.09427","version":2},"attestation_state":"computed","paper":{"title":"Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianzhi Shao, Minlie Huang, Rongsheng Zhang, Xiaoxi Mao, Yadong Xi, Yinhe Zheng","submitted_at":"2020-09-20T13:06:38Z","abstract_excerpt":"Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data dilemma, we propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. Specifically, a data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data. A ranking module is employed to filter out low-quality dialogues. Further, "},"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":"2009.09427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-20T13:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"60713e20d4bab34b63ac6d7ba7960e8566f7e09327637e1046d2d0e66f60906f","abstract_canon_sha256":"3ad06be48c5341201a857c0d331dbec754370248a22e29130b5c32a5978c2a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:33.528611Z","signature_b64":"3M0VPsKKUhZdp+dZNECjfZy8hdneZNxAfM6MwSb38YiLmiuEV4CztyWO0XgL8aDUClQuapLtt5XjW//+4f6aDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5177a3df1ea0d03bd3156d8330e45aa42ef005c418dd19fa164994f00080224","last_reissued_at":"2026-07-05T01:50:33.527960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:33.527960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianzhi Shao, Minlie Huang, Rongsheng Zhang, Xiaoxi Mao, Yadong Xi, Yinhe Zheng","submitted_at":"2020-09-20T13:06:38Z","abstract_excerpt":"Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data dilemma, we propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. Specifically, a data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data. A ranking module is employed to filter out low-quality dialogues. Further, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09427","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/2009.09427/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":"2009.09427","created_at":"2026-07-05T01:50:33.528038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09427v2","created_at":"2026-07-05T01:50:33.528038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09427","created_at":"2026-07-05T01:50:33.528038+00:00"},{"alias_kind":"pith_short_12","alias_value":"YULXUPPR5IGQ","created_at":"2026-07-05T01:50:33.528038+00:00"},{"alias_kind":"pith_short_16","alias_value":"YULXUPPR5IGQHPJR","created_at":"2026-07-05T01:50:33.528038+00:00"},{"alias_kind":"pith_short_8","alias_value":"YULXUPPR","created_at":"2026-07-05T01:50:33.528038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.17760","citing_title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ","json":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ.json","graph_json":"https://pith.science/api/pith-number/YULXUPPR5IGQHPJRK3MDGDSFVJ/graph.json","events_json":"https://pith.science/api/pith-number/YULXUPPR5IGQHPJRK3MDGDSFVJ/events.json","paper":"https://pith.science/paper/YULXUPPR"},"agent_actions":{"view_html":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ","download_json":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ.json","view_paper":"https://pith.science/paper/YULXUPPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09427&json=true","fetch_graph":"https://pith.science/api/pith-number/YULXUPPR5IGQHPJRK3MDGDSFVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YULXUPPR5IGQHPJRK3MDGDSFVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ/action/storage_attestation","attest_author":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ/action/author_attestation","sign_citation":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ/action/citation_signature","submit_replication":"https://pith.science/pith/YULXUPPR5IGQHPJRK3MDGDSFVJ/action/replication_record"}},"created_at":"2026-07-05T01:50:33.528038+00:00","updated_at":"2026-07-05T01:50:33.528038+00:00"}