{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KTLBF45XEYS32MGDEIE2RPPLY4","short_pith_number":"pith:KTLBF45X","schema_version":"1.0","canonical_sha256":"54d612f3b72625bd30c32209a8bdebc703294758a2d9e81bfc6b60f5d8ad52ff","source":{"kind":"arxiv","id":"2203.08372","version":1},"attestation_state":"computed","paper":{"title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Ming Gong, Nan Duan, Shunyu Zhang, Yaobo Liang","submitted_at":"2022-03-16T03:36:38Z","abstract_excerpt":"Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to al"},"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":"2203.08372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T03:36:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"27e4e3d678b83f0bd2265ae25d27d956fefa577e9615995a505e0b178dea5968","abstract_canon_sha256":"d6cca5c5b2315995115bb6a684c6ef2e69fcab32dd29ff288119c63eecff40fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:43.991113Z","signature_b64":"8R3tLN7R5yruSHaK+yRAyOy+jijvTHdb5FPE/5fN/u8mW72URbkABV5mNFeZnXem0Gr0BOphrJCimOscI21tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d612f3b72625bd30c32209a8bdebc703294758a2d9e81bfc6b60f5d8ad52ff","last_reissued_at":"2026-07-05T04:05:43.990718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:43.990718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Ming Gong, Nan Duan, Shunyu Zhang, Yaobo Liang","submitted_at":"2022-03-16T03:36:38Z","abstract_excerpt":"Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08372","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/2203.08372/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":"2203.08372","created_at":"2026-07-05T04:05:43.990783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08372v1","created_at":"2026-07-05T04:05:43.990783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08372","created_at":"2026-07-05T04:05:43.990783+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTLBF45XEYS3","created_at":"2026-07-05T04:05:43.990783+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTLBF45XEYS32MGD","created_at":"2026-07-05T04:05:43.990783+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTLBF45X","created_at":"2026-07-05T04:05:43.990783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4","json":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4.json","graph_json":"https://pith.science/api/pith-number/KTLBF45XEYS32MGDEIE2RPPLY4/graph.json","events_json":"https://pith.science/api/pith-number/KTLBF45XEYS32MGDEIE2RPPLY4/events.json","paper":"https://pith.science/paper/KTLBF45X"},"agent_actions":{"view_html":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4","download_json":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4.json","view_paper":"https://pith.science/paper/KTLBF45X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08372&json=true","fetch_graph":"https://pith.science/api/pith-number/KTLBF45XEYS32MGDEIE2RPPLY4/graph.json","fetch_events":"https://pith.science/api/pith-number/KTLBF45XEYS32MGDEIE2RPPLY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4/action/storage_attestation","attest_author":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4/action/author_attestation","sign_citation":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4/action/citation_signature","submit_replication":"https://pith.science/pith/KTLBF45XEYS32MGDEIE2RPPLY4/action/replication_record"}},"created_at":"2026-07-05T04:05:43.990783+00:00","updated_at":"2026-07-05T04:05:43.990783+00:00"}