{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NDMSIYZTCQIV5C36E7A5XH3OEX","short_pith_number":"pith:NDMSIYZT","schema_version":"1.0","canonical_sha256":"68d924633314115e8b7e27c1db9f6e25fab5d578166147ada5afcff4775f86ae","source":{"kind":"arxiv","id":"2108.13454","version":1},"attestation_state":"computed","paper":{"title":"Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chenyan Xiong, HongChien Yu, Jamie Callan","submitted_at":"2021-08-30T18:10:26Z","abstract_excerpt":"Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a challenging task due to the shortness and ambiguity of search queries. This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns t"},"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":"2108.13454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-08-30T18:10:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"729ca1e7eb174d51da10408b8c789a16336811a0a3847289ec79a4a4b6bd5a64","abstract_canon_sha256":"e5a27945fba51ea843c5acb13f72dae6194eca51c906da37f82a120fd9567fff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:14.304966Z","signature_b64":"o9LkVRXGmOMIM3Bofm0XJQiBDJcIIVDWnVmQ8G9IpPyDPNgRuLigiw0NQRt66jP5Qmov8A4geb4PC5RGcS+6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d924633314115e8b7e27c1db9f6e25fab5d578166147ada5afcff4775f86ae","last_reissued_at":"2026-07-05T03:10:14.304584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:14.304584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chenyan Xiong, HongChien Yu, Jamie Callan","submitted_at":"2021-08-30T18:10:26Z","abstract_excerpt":"Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a challenging task due to the shortness and ambiguity of search queries. This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13454","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/2108.13454/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":"2108.13454","created_at":"2026-07-05T03:10:14.304641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.13454v1","created_at":"2026-07-05T03:10:14.304641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13454","created_at":"2026-07-05T03:10:14.304641+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDMSIYZTCQIV","created_at":"2026-07-05T03:10:14.304641+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDMSIYZTCQIV5C36","created_at":"2026-07-05T03:10:14.304641+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDMSIYZT","created_at":"2026-07-05T03:10:14.304641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14826","citing_title":"Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX","json":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX.json","graph_json":"https://pith.science/api/pith-number/NDMSIYZTCQIV5C36E7A5XH3OEX/graph.json","events_json":"https://pith.science/api/pith-number/NDMSIYZTCQIV5C36E7A5XH3OEX/events.json","paper":"https://pith.science/paper/NDMSIYZT"},"agent_actions":{"view_html":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX","download_json":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX.json","view_paper":"https://pith.science/paper/NDMSIYZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.13454&json=true","fetch_graph":"https://pith.science/api/pith-number/NDMSIYZTCQIV5C36E7A5XH3OEX/graph.json","fetch_events":"https://pith.science/api/pith-number/NDMSIYZTCQIV5C36E7A5XH3OEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX/action/storage_attestation","attest_author":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX/action/author_attestation","sign_citation":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX/action/citation_signature","submit_replication":"https://pith.science/pith/NDMSIYZTCQIV5C36E7A5XH3OEX/action/replication_record"}},"created_at":"2026-07-05T03:10:14.304641+00:00","updated_at":"2026-07-05T03:10:14.304641+00:00"}