{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMQPCNG4GTDLFP6MB76HBJCMOA","short_pith_number":"pith:QMQPCNG4","schema_version":"1.0","canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","source":{"kind":"arxiv","id":"2304.08138","version":2},"attestation_state":"computed","paper":{"title":"Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","submitted_at":"2023-04-17T10:42:30Z","abstract_excerpt":"Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search engines. The main issue is that the pre-trained language model-based encoders used by DRs are typically trained and fine-tuned using clean, well-curated text data. Misspelled queries are typically not found in the data used for training these models, and thus misspelled queries observed at inference time are out-of-distribution compared to the data used for training and fine-tuning. Previous efforts to address this 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":"2304.08138","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"fddbe6d8ac34ddb5b90dfe0fe50d000993490a08bed2921fc34e78e06effffa8","abstract_canon_sha256":"43e6bb25bc6c3aada807c2e3d706aed5fa96095df244d27d782740cd839707a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:40.435119Z","signature_b64":"ZohXkMwgHSSVE3GZE8/7Uls9cB7MShY5C+WMRaQlEVLHhkOiI4Yb4dj1sG+6yR7eVtKgXW7rClF0tAWqXLdSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","last_reissued_at":"2026-07-05T07:16:40.434590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:40.434590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","submitted_at":"2023-04-17T10:42:30Z","abstract_excerpt":"Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search engines. The main issue is that the pre-trained language model-based encoders used by DRs are typically trained and fine-tuned using clean, well-curated text data. Misspelled queries are typically not found in the data used for training these models, and thus misspelled queries observed at inference time are out-of-distribution compared to the data used for training and fine-tuning. Previous efforts to address this i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08138","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/2304.08138/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":"2304.08138","created_at":"2026-07-05T07:16:40.434659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08138v2","created_at":"2026-07-05T07:16:40.434659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08138","created_at":"2026-07-05T07:16:40.434659+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMQPCNG4GTDL","created_at":"2026-07-05T07:16:40.434659+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMQPCNG4GTDLFP6M","created_at":"2026-07-05T07:16:40.434659+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMQPCNG4","created_at":"2026-07-05T07:16:40.434659+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/QMQPCNG4GTDLFP6MB76HBJCMOA","json":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA.json","graph_json":"https://pith.science/api/pith-number/QMQPCNG4GTDLFP6MB76HBJCMOA/graph.json","events_json":"https://pith.science/api/pith-number/QMQPCNG4GTDLFP6MB76HBJCMOA/events.json","paper":"https://pith.science/paper/QMQPCNG4"},"agent_actions":{"view_html":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA","download_json":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA.json","view_paper":"https://pith.science/paper/QMQPCNG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08138&json=true","fetch_graph":"https://pith.science/api/pith-number/QMQPCNG4GTDLFP6MB76HBJCMOA/graph.json","fetch_events":"https://pith.science/api/pith-number/QMQPCNG4GTDLFP6MB76HBJCMOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/action/storage_attestation","attest_author":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/action/author_attestation","sign_citation":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/action/citation_signature","submit_replication":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/action/replication_record"}},"created_at":"2026-07-05T07:16:40.434659+00:00","updated_at":"2026-07-05T07:16:40.434659+00:00"}