{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5YLEX3LMZ3ZXIR37MJ3O7P7VQA","short_pith_number":"pith:5YLEX3LM","schema_version":"1.0","canonical_sha256":"ee164bed6ccef374477f6276efbff580307adef2219b9d259868a3f9a496d3b8","source":{"kind":"arxiv","id":"2110.06612","version":3},"attestation_state":"computed","paper":{"title":"Exploring Dense Retrieval for Dialogue Response Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Heyan Huang, Tian Lan, Xian-Ling Mao, Yan Wang, Yixuan Su","submitted_at":"2021-10-13T10:10:32Z","abstract_excerpt":"Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and response candidates. While remarkably effective, these models also bring in a steep increase in computational cost. Consequently, such models can only be used as a re-rank module in practice. In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using "},"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":"2110.06612","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T10:10:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d23f58c5301c1956c5ff5c8990742b5618ba34ae3962fc3874f75db8b19dc64","abstract_canon_sha256":"434f36f6d40b88f62cbe49f8a9641d92ce8679eac45c77aa26681bbb8d780876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:17.511525Z","signature_b64":"PiZnH5jIHcHogBGMURJE0IVis8JA7tzCgeIXPl+ppERR5BnCFpWtzm2IfTAvsLGybYPobui3Agvw7gU1gDHeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee164bed6ccef374477f6276efbff580307adef2219b9d259868a3f9a496d3b8","last_reissued_at":"2026-07-05T04:17:17.511078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:17.511078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Dense Retrieval for Dialogue Response Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Heyan Huang, Tian Lan, Xian-Ling Mao, Yan Wang, Yixuan Su","submitted_at":"2021-10-13T10:10:32Z","abstract_excerpt":"Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and response candidates. While remarkably effective, these models also bring in a steep increase in computational cost. Consequently, such models can only be used as a re-rank module in practice. In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06612","kind":"arxiv","version":3},"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/2110.06612/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":"2110.06612","created_at":"2026-07-05T04:17:17.511137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06612v3","created_at":"2026-07-05T04:17:17.511137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06612","created_at":"2026-07-05T04:17:17.511137+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YLEX3LMZ3ZX","created_at":"2026-07-05T04:17:17.511137+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YLEX3LMZ3ZXIR37","created_at":"2026-07-05T04:17:17.511137+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YLEX3LM","created_at":"2026-07-05T04:17:17.511137+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/5YLEX3LMZ3ZXIR37MJ3O7P7VQA","json":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA.json","graph_json":"https://pith.science/api/pith-number/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/graph.json","events_json":"https://pith.science/api/pith-number/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/events.json","paper":"https://pith.science/paper/5YLEX3LM"},"agent_actions":{"view_html":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA","download_json":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA.json","view_paper":"https://pith.science/paper/5YLEX3LM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06612&json=true","fetch_graph":"https://pith.science/api/pith-number/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/graph.json","fetch_events":"https://pith.science/api/pith-number/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/action/storage_attestation","attest_author":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/action/author_attestation","sign_citation":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/action/citation_signature","submit_replication":"https://pith.science/pith/5YLEX3LMZ3ZXIR37MJ3O7P7VQA/action/replication_record"}},"created_at":"2026-07-05T04:17:17.511137+00:00","updated_at":"2026-07-05T04:17:17.511137+00:00"}