{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7YAF6MDBBMEUWWWWUWISIW4JL","short_pith_number":"pith:H7YAF6MD","schema_version":"1.0","canonical_sha256":"3ff002f98308584a5ad6b52c8922dc4ac652f15a5273283c9ab6a82eb5d2a595","source":{"kind":"arxiv","id":"2401.04361","version":1},"attestation_state":"computed","paper":{"title":"Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Liu, Jiaan Wang, Jianfeng Qu, Kexin Wang, Wen Hua, Ximing Li, Zhixu Li","submitted_at":"2024-01-09T05:16:52Z","abstract_excerpt":"Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\\emph{e.g.}, knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also m"},"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":"2401.04361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-09T05:16:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4ddf61739ea60e3282ecd2c0ce7db4134dab502ec431e4b2652271c991cc355","abstract_canon_sha256":"bb28c68cd22d2341006931a0b8e3ea0a3b048ef043974cdae7beed8cb5755256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:42.676121Z","signature_b64":"+yhYw9O8dX1jnE/4zpTwhVgAWvrgUqP4lMCqPsyVgTHI6H69aWN3l+/1ZT1kzEz+iiPxYNzD7dYKb/wwsRu5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff002f98308584a5ad6b52c8922dc4ac652f15a5273283c9ab6a82eb5d2a595","last_reissued_at":"2026-07-05T07:31:42.675521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:42.675521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Liu, Jiaan Wang, Jianfeng Qu, Kexin Wang, Wen Hua, Ximing Li, Zhixu Li","submitted_at":"2024-01-09T05:16:52Z","abstract_excerpt":"Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\\emph{e.g.}, knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04361","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.04361/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":"2401.04361","created_at":"2026-07-05T07:31:42.675621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04361v1","created_at":"2026-07-05T07:31:42.675621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04361","created_at":"2026-07-05T07:31:42.675621+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7YAF6MDBBME","created_at":"2026-07-05T07:31:42.675621+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7YAF6MDBBMEUWWW","created_at":"2026-07-05T07:31:42.675621+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7YAF6MD","created_at":"2026-07-05T07:31:42.675621+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/H7YAF6MDBBMEUWWWWUWISIW4JL","json":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL.json","graph_json":"https://pith.science/api/pith-number/H7YAF6MDBBMEUWWWWUWISIW4JL/graph.json","events_json":"https://pith.science/api/pith-number/H7YAF6MDBBMEUWWWWUWISIW4JL/events.json","paper":"https://pith.science/paper/H7YAF6MD"},"agent_actions":{"view_html":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL","download_json":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL.json","view_paper":"https://pith.science/paper/H7YAF6MD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04361&json=true","fetch_graph":"https://pith.science/api/pith-number/H7YAF6MDBBMEUWWWWUWISIW4JL/graph.json","fetch_events":"https://pith.science/api/pith-number/H7YAF6MDBBMEUWWWWUWISIW4JL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL/action/storage_attestation","attest_author":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL/action/author_attestation","sign_citation":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL/action/citation_signature","submit_replication":"https://pith.science/pith/H7YAF6MDBBMEUWWWWUWISIW4JL/action/replication_record"}},"created_at":"2026-07-05T07:31:42.675621+00:00","updated_at":"2026-07-05T07:31:42.675621+00:00"}