{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4Q6L4WDODFG4H6IFEBTRSYANVS","short_pith_number":"pith:4Q6L4WDO","schema_version":"1.0","canonical_sha256":"e43cbe586e194dc3f905206719600dac93a8b6df7fe93192d09dca286e3aba8b","source":{"kind":"arxiv","id":"2002.07510","version":2},"attestation_state":"computed","paper":{"title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byeongchang Kim, Gunhee Kim, Jaewoo Ahn","submitted_at":"2020-02-18T11:59:59Z","abstract_excerpt":"Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response inf"},"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":"2002.07510","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-18T11:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"f38e094e3d05e00a979d05fba087c0c2b8daffe499e10e937154984d65d643aa","abstract_canon_sha256":"c72287e4e2855a6b1a61277ad6fdc3b0ae3874cea58b76c36a12e55bfb877d78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:33.833073Z","signature_b64":"EIxj/s+LQE9ONPssP/1rbJsMF5JrPYL8OZEi8p5wDewniq9EBF67X3dbtkaGjH99UpHlcUwBqO2SjUOdh+SzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43cbe586e194dc3f905206719600dac93a8b6df7fe93192d09dca286e3aba8b","last_reissued_at":"2026-07-05T01:10:33.832650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:33.832650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byeongchang Kim, Gunhee Kim, Jaewoo Ahn","submitted_at":"2020-02-18T11:59:59Z","abstract_excerpt":"Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07510","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/2002.07510/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":"2002.07510","created_at":"2026-07-05T01:10:33.832708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07510v2","created_at":"2026-07-05T01:10:33.832708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07510","created_at":"2026-07-05T01:10:33.832708+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q6L4WDODFG4","created_at":"2026-07-05T01:10:33.832708+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q6L4WDODFG4H6IF","created_at":"2026-07-05T01:10:33.832708+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q6L4WDO","created_at":"2026-07-05T01:10:33.832708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10877","citing_title":"Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS","json":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS.json","graph_json":"https://pith.science/api/pith-number/4Q6L4WDODFG4H6IFEBTRSYANVS/graph.json","events_json":"https://pith.science/api/pith-number/4Q6L4WDODFG4H6IFEBTRSYANVS/events.json","paper":"https://pith.science/paper/4Q6L4WDO"},"agent_actions":{"view_html":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS","download_json":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS.json","view_paper":"https://pith.science/paper/4Q6L4WDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07510&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q6L4WDODFG4H6IFEBTRSYANVS/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q6L4WDODFG4H6IFEBTRSYANVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS/action/storage_attestation","attest_author":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS/action/author_attestation","sign_citation":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS/action/citation_signature","submit_replication":"https://pith.science/pith/4Q6L4WDODFG4H6IFEBTRSYANVS/action/replication_record"}},"created_at":"2026-07-05T01:10:33.832708+00:00","updated_at":"2026-07-05T01:10:33.832708+00:00"}