{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GRCYA7E4C3QECFT2OJKY4MFAHS","short_pith_number":"pith:GRCYA7E4","schema_version":"1.0","canonical_sha256":"3445807c9c16e041167a72558e30a03ca5659948a2c76ee966d01a20ca9010f3","source":{"kind":"arxiv","id":"2004.13969","version":3},"attestation_state":"computed","paper":{"title":"Complementing Lexical Retrieval with Semantic Residual Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Benjamin Van Durme, Jamie Callan, Luyu Gao, Tongfei Chen, Zhen Fan, Zhuyun Dai","submitted_at":"2020-04-29T06:10:02Z","abstract_excerpt":"This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines."},"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":"2004.13969","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-04-29T06:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"ad7aed4ff03570c8605c94d7c8763d81e90e7108c36502d6329fd9aa71ae8c8a","abstract_canon_sha256":"1a3f3cc263ca7c95d28245b5dbd4eaa7bb5e4dac35af543f2f213df484dc1952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:47.944335Z","signature_b64":"4/cdyhWg2JHf/kb4Nu37zkTamP6nh4lqb+FPSE31xjNIW7hTJBZxBqRZ42C7hwCY3Lz+3BpUIU3WvW/TxXQHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3445807c9c16e041167a72558e30a03ca5659948a2c76ee966d01a20ca9010f3","last_reissued_at":"2026-07-05T02:26:47.943780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:47.943780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complementing Lexical Retrieval with Semantic Residual Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Benjamin Van Durme, Jamie Callan, Luyu Gao, Tongfei Chen, Zhen Fan, Zhuyun Dai","submitted_at":"2020-04-29T06:10:02Z","abstract_excerpt":"This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13969","kind":"arxiv","version":3},"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/2004.13969/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":"2004.13969","created_at":"2026-07-05T02:26:47.943850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13969v3","created_at":"2026-07-05T02:26:47.943850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13969","created_at":"2026-07-05T02:26:47.943850+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRCYA7E4C3QE","created_at":"2026-07-05T02:26:47.943850+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRCYA7E4C3QECFT2","created_at":"2026-07-05T02:26:47.943850+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRCYA7E4","created_at":"2026-07-05T02:26:47.943850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18297","citing_title":"Comparative Analysis of Lion and AdamW Optimizers for Cross-Encoder Reranking with MiniLM, GTE, and ModernBERT","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS","json":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS.json","graph_json":"https://pith.science/api/pith-number/GRCYA7E4C3QECFT2OJKY4MFAHS/graph.json","events_json":"https://pith.science/api/pith-number/GRCYA7E4C3QECFT2OJKY4MFAHS/events.json","paper":"https://pith.science/paper/GRCYA7E4"},"agent_actions":{"view_html":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS","download_json":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS.json","view_paper":"https://pith.science/paper/GRCYA7E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13969&json=true","fetch_graph":"https://pith.science/api/pith-number/GRCYA7E4C3QECFT2OJKY4MFAHS/graph.json","fetch_events":"https://pith.science/api/pith-number/GRCYA7E4C3QECFT2OJKY4MFAHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS/action/storage_attestation","attest_author":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS/action/author_attestation","sign_citation":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS/action/citation_signature","submit_replication":"https://pith.science/pith/GRCYA7E4C3QECFT2OJKY4MFAHS/action/replication_record"}},"created_at":"2026-07-05T02:26:47.943850+00:00","updated_at":"2026-07-05T02:26:47.943850+00:00"}