{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YGXYM4JTVBOSKF45WJ4PFYOGVV","short_pith_number":"pith:YGXYM4JT","schema_version":"1.0","canonical_sha256":"c1af867133a85d25179db278f2e1c6ad6fd93f538102744cfc03834314ad1cd2","source":{"kind":"arxiv","id":"2106.06169","version":2},"attestation_state":"computed","paper":{"title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoyu Song, Kaiyan Zhang, Ting Liu, Wei-Nan Zhang, Yan Wang","submitted_at":"2021-06-11T05:02:05Z","abstract_excerpt":"Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue models. In this work, we show how the challenges can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understandi"},"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":"2106.06169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-11T05:02:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40dcf59057b5fb9e046a88f54feb7c85403e1a23642e0fe42f17a308cb46710f","abstract_canon_sha256":"96ffef3cf2c85ecbaf71bcc5b9ede551e8d7c0a9a24a5dc26bdd347c035555c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:01.684746Z","signature_b64":"AN888aulzPJWEC0bp5CUu0SfwNlrO5n9o4eaJdtj4+VSxweMoFytbk9vy51UivfKZ3cNS2wt4EaSxHXJqV59AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1af867133a85d25179db278f2e1c6ad6fd93f538102744cfc03834314ad1cd2","last_reissued_at":"2026-07-05T02:49:01.684340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:01.684340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoyu Song, Kaiyan Zhang, Ting Liu, Wei-Nan Zhang, Yan Wang","submitted_at":"2021-06-11T05:02:05Z","abstract_excerpt":"Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue models. In this work, we show how the challenges can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understandi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06169","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/2106.06169/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":"2106.06169","created_at":"2026-07-05T02:49:01.684395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06169v2","created_at":"2026-07-05T02:49:01.684395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06169","created_at":"2026-07-05T02:49:01.684395+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGXYM4JTVBOS","created_at":"2026-07-05T02:49:01.684395+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGXYM4JTVBOSKF45","created_at":"2026-07-05T02:49:01.684395+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGXYM4JT","created_at":"2026-07-05T02:49:01.684395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13157","citing_title":"Role-Playing Evaluation for Large Language Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV","json":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV.json","graph_json":"https://pith.science/api/pith-number/YGXYM4JTVBOSKF45WJ4PFYOGVV/graph.json","events_json":"https://pith.science/api/pith-number/YGXYM4JTVBOSKF45WJ4PFYOGVV/events.json","paper":"https://pith.science/paper/YGXYM4JT"},"agent_actions":{"view_html":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV","download_json":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV.json","view_paper":"https://pith.science/paper/YGXYM4JT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06169&json=true","fetch_graph":"https://pith.science/api/pith-number/YGXYM4JTVBOSKF45WJ4PFYOGVV/graph.json","fetch_events":"https://pith.science/api/pith-number/YGXYM4JTVBOSKF45WJ4PFYOGVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV/action/storage_attestation","attest_author":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV/action/author_attestation","sign_citation":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV/action/citation_signature","submit_replication":"https://pith.science/pith/YGXYM4JTVBOSKF45WJ4PFYOGVV/action/replication_record"}},"created_at":"2026-07-05T02:49:01.684395+00:00","updated_at":"2026-07-05T02:49:01.684395+00:00"}