{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7Q53ZEFRRCHS7GCTTVQVVJBVA","short_pith_number":"pith:C7Q53ZEF","schema_version":"1.0","canonical_sha256":"17e1dde4858c44797cc29ceb0ad521a835f81966b86b0e8f7d61ef56d19f7a04","source":{"kind":"arxiv","id":"2402.16767","version":1},"attestation_state":"computed","paper":{"title":"CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Changjiang Zhou, Jiafeng Guo, Jiangui Chen, Maarten de Rijke, Ruqing Zhang, Xueqi Cheng, Yixing Fan","submitted_at":"2024-02-26T17:35:44Z","abstract_excerpt":"Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most existing research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, i"},"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":"2402.16767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-26T17:35:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d7b626aeccd31fe8cc430aec9608e2e69a1244dbe7f14c78503bd38239ad2d7c","abstract_canon_sha256":"93eaecd6e04e9541062c8224e854c052e039969e7ae2cc0b3d1a92092712dc5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:26.046307Z","signature_b64":"FI3liEWvWI/WzotJ6a4+eWFM0VWLy2F1zYD4/p88KT1PRvxDVgK+Xf8NX1cCzbj4OTBAX5NBto6i+ckQuGCfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e1dde4858c44797cc29ceb0ad521a835f81966b86b0e8f7d61ef56d19f7a04","last_reissued_at":"2026-07-05T07:49:26.045955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:26.045955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Changjiang Zhou, Jiafeng Guo, Jiangui Chen, Maarten de Rijke, Ruqing Zhang, Xueqi Cheng, Yixing Fan","submitted_at":"2024-02-26T17:35:44Z","abstract_excerpt":"Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most existing research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16767","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/2402.16767/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":"2402.16767","created_at":"2026-07-05T07:49:26.046012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16767v1","created_at":"2026-07-05T07:49:26.046012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16767","created_at":"2026-07-05T07:49:26.046012+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7Q53ZEFRRCH","created_at":"2026-07-05T07:49:26.046012+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7Q53ZEFRRCHS7GC","created_at":"2026-07-05T07:49:26.046012+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7Q53ZEF","created_at":"2026-07-05T07:49:26.046012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23388","citing_title":"A Parametric Memory Head for Continual Generative Retrieval","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA","json":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA.json","graph_json":"https://pith.science/api/pith-number/C7Q53ZEFRRCHS7GCTTVQVVJBVA/graph.json","events_json":"https://pith.science/api/pith-number/C7Q53ZEFRRCHS7GCTTVQVVJBVA/events.json","paper":"https://pith.science/paper/C7Q53ZEF"},"agent_actions":{"view_html":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA","download_json":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA.json","view_paper":"https://pith.science/paper/C7Q53ZEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16767&json=true","fetch_graph":"https://pith.science/api/pith-number/C7Q53ZEFRRCHS7GCTTVQVVJBVA/graph.json","fetch_events":"https://pith.science/api/pith-number/C7Q53ZEFRRCHS7GCTTVQVVJBVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA/action/storage_attestation","attest_author":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA/action/author_attestation","sign_citation":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA/action/citation_signature","submit_replication":"https://pith.science/pith/C7Q53ZEFRRCHS7GCTTVQVVJBVA/action/replication_record"}},"created_at":"2026-07-05T07:49:26.046012+00:00","updated_at":"2026-07-05T07:49:26.046012+00:00"}