{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PHVX77AQHA22HPA2X76MT4NEAV","short_pith_number":"pith:PHVX77AQ","schema_version":"1.0","canonical_sha256":"79eb7ffc103835a3bc1abffcc9f1a40550ad5f0d1fcc24b320139a7be261722d","source":{"kind":"arxiv","id":"2009.10270","version":1},"attestation_state":"computed","paper":{"title":"Embedding-based Zero-shot Retrieval through Query Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bing Xiang, Cicero Nogueira dos Santos, Davis Liang, Peng Xu, Ramesh Nallapati, Siamak Shakeri, Zhiheng Huang","submitted_at":"2020-09-22T01:54:27Z","abstract_excerpt":"Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train,"},"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":"2009.10270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-09-22T01:54:27Z","cross_cats_sorted":[],"title_canon_sha256":"2ff051b70c29d81328e5c953aa6e40dae69e839791501e0406740be36e48abad","abstract_canon_sha256":"8a3c8fd04cab3783d0806140d3155b8905981092293e7421eab81ed3aa64fee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:17.810264Z","signature_b64":"4rZX4LIIu4P1uebg7M6MMBPzxtZ3Rq1HP3RpYg0EGXYYwzGvrWESBXJBejtPJNKSxe8xsBpOo2OecHOTCDPWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79eb7ffc103835a3bc1abffcc9f1a40550ad5f0d1fcc24b320139a7be261722d","last_reissued_at":"2026-07-05T01:37:17.809695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:17.809695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding-based Zero-shot Retrieval through Query Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bing Xiang, Cicero Nogueira dos Santos, Davis Liang, Peng Xu, Ramesh Nallapati, Siamak Shakeri, Zhiheng Huang","submitted_at":"2020-09-22T01:54:27Z","abstract_excerpt":"Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10270","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/2009.10270/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":"2009.10270","created_at":"2026-07-05T01:37:17.809756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10270v1","created_at":"2026-07-05T01:37:17.809756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10270","created_at":"2026-07-05T01:37:17.809756+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHVX77AQHA22","created_at":"2026-07-05T01:37:17.809756+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHVX77AQHA22HPA2","created_at":"2026-07-05T01:37:17.809756+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHVX77AQ","created_at":"2026-07-05T01:37:17.809756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV","json":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV.json","graph_json":"https://pith.science/api/pith-number/PHVX77AQHA22HPA2X76MT4NEAV/graph.json","events_json":"https://pith.science/api/pith-number/PHVX77AQHA22HPA2X76MT4NEAV/events.json","paper":"https://pith.science/paper/PHVX77AQ"},"agent_actions":{"view_html":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV","download_json":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV.json","view_paper":"https://pith.science/paper/PHVX77AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10270&json=true","fetch_graph":"https://pith.science/api/pith-number/PHVX77AQHA22HPA2X76MT4NEAV/graph.json","fetch_events":"https://pith.science/api/pith-number/PHVX77AQHA22HPA2X76MT4NEAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV/action/storage_attestation","attest_author":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV/action/author_attestation","sign_citation":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV/action/citation_signature","submit_replication":"https://pith.science/pith/PHVX77AQHA22HPA2X76MT4NEAV/action/replication_record"}},"created_at":"2026-07-05T01:37:17.809756+00:00","updated_at":"2026-07-05T01:37:17.809756+00:00"}