{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2554L6RKOWSA75DJ2BVPKJBODL","short_pith_number":"pith:2554L6RK","schema_version":"1.0","canonical_sha256":"d77bc5fa2a75a40ff469d06af5242e1ae2707ec9a66ca640db415251e5bf080d","source":{"kind":"arxiv","id":"2306.07206","version":1},"attestation_state":"computed","paper":{"title":"RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyundong J. Cho, Jonathan May, Marjorie Freedman, Shuai Liu, Xuezhe Ma","submitted_at":"2023-06-12T16:10:21Z","abstract_excerpt":"Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge. In this work, we propose a new retrieval-enhanced approach for personalized response generation. Specifically, we design a hierarchical transformer retriever trained on dialogue domain data to perform personalized retrieval and a context-aware prefix encoder that fuses the retrieved information to the decoder more effectively. Extensive experiments on a real-world dataset demonstrate the effectiveness of our model at generating more fluent and personalized responses. We"},"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":"2306.07206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T16:10:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c31d59ebcecd7e68d46716d1dffc9e42908dd3f471d2aa419bd50ff1bf08184a","abstract_canon_sha256":"9601fa5498ba4df46fb697546a37488af5bf10d6ab1008282ff487c1acdcf64f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:48.887530Z","signature_b64":"EjEFXhIGdSjK2DZouswgGPW1vE4Px35BJXq7ceFKupw4gDzT40G58Q1qPBXfFKMDRiKsB5wX1ryak+uRp09ICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d77bc5fa2a75a40ff469d06af5242e1ae2707ec9a66ca640db415251e5bf080d","last_reissued_at":"2026-07-05T06:19:48.887055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:48.887055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyundong J. Cho, Jonathan May, Marjorie Freedman, Shuai Liu, Xuezhe Ma","submitted_at":"2023-06-12T16:10:21Z","abstract_excerpt":"Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge. In this work, we propose a new retrieval-enhanced approach for personalized response generation. Specifically, we design a hierarchical transformer retriever trained on dialogue domain data to perform personalized retrieval and a context-aware prefix encoder that fuses the retrieved information to the decoder more effectively. Extensive experiments on a real-world dataset demonstrate the effectiveness of our model at generating more fluent and personalized responses. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07206","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/2306.07206/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":"2306.07206","created_at":"2026-07-05T06:19:48.887113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07206v1","created_at":"2026-07-05T06:19:48.887113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07206","created_at":"2026-07-05T06:19:48.887113+00:00"},{"alias_kind":"pith_short_12","alias_value":"2554L6RKOWSA","created_at":"2026-07-05T06:19:48.887113+00:00"},{"alias_kind":"pith_short_16","alias_value":"2554L6RKOWSA75DJ","created_at":"2026-07-05T06:19:48.887113+00:00"},{"alias_kind":"pith_short_8","alias_value":"2554L6RK","created_at":"2026-07-05T06:19:48.887113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL","json":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL.json","graph_json":"https://pith.science/api/pith-number/2554L6RKOWSA75DJ2BVPKJBODL/graph.json","events_json":"https://pith.science/api/pith-number/2554L6RKOWSA75DJ2BVPKJBODL/events.json","paper":"https://pith.science/paper/2554L6RK"},"agent_actions":{"view_html":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL","download_json":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL.json","view_paper":"https://pith.science/paper/2554L6RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07206&json=true","fetch_graph":"https://pith.science/api/pith-number/2554L6RKOWSA75DJ2BVPKJBODL/graph.json","fetch_events":"https://pith.science/api/pith-number/2554L6RKOWSA75DJ2BVPKJBODL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL/action/storage_attestation","attest_author":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL/action/author_attestation","sign_citation":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL/action/citation_signature","submit_replication":"https://pith.science/pith/2554L6RKOWSA75DJ2BVPKJBODL/action/replication_record"}},"created_at":"2026-07-05T06:19:48.887113+00:00","updated_at":"2026-07-05T06:19:48.887113+00:00"}