{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BJNI3MWQHXOKL4SDI57LWY5U4P","short_pith_number":"pith:BJNI3MWQ","schema_version":"1.0","canonical_sha256":"0a5a8db2d03ddca5f243477ebb63b4e3f10c30c3e619193b1c0a5e06a0f19338","source":{"kind":"arxiv","id":"2112.05662","version":2},"attestation_state":"computed","paper":{"title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2021-12-10T16:49:49Z","abstract_excerpt":"Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged on out-of-domain zero-shot settings (BEIR benchmark), questioning their actual generalization capabilities compared to bag-of-words approaches. Particularly, we wonder if these shortcomings could (partly) be the consequence of the inability of neural IR models to perform lexical matching off-the-shelf. In this work, we propose a measure of discrepancy betwee"},"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":"2112.05662","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-10T16:49:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7d51387273cc07032825ee37cca0775bba6d59d72bddb02ca4e13c5d40541d2e","abstract_canon_sha256":"5d0713af550f030a942ebe410ddde4a8624f546af8dd8f4b04066612ab08b96f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:06.273893Z","signature_b64":"DIEz6w0An4uQkLzVGlYdZE5wE0Fkl8MWmJi6oJsYb2MBqmWIbFAsjvCtHxWG0Kearkck6qTInJgCL7dYGLrXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a5a8db2d03ddca5f243477ebb63b4e3f10c30c3e619193b1c0a5e06a0f19338","last_reissued_at":"2026-07-05T03:40:06.273459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:06.273459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2021-12-10T16:49:49Z","abstract_excerpt":"Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged on out-of-domain zero-shot settings (BEIR benchmark), questioning their actual generalization capabilities compared to bag-of-words approaches. Particularly, we wonder if these shortcomings could (partly) be the consequence of the inability of neural IR models to perform lexical matching off-the-shelf. In this work, we propose a measure of discrepancy betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05662","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/2112.05662/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":"2112.05662","created_at":"2026-07-05T03:40:06.273517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05662v2","created_at":"2026-07-05T03:40:06.273517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05662","created_at":"2026-07-05T03:40:06.273517+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJNI3MWQHXOK","created_at":"2026-07-05T03:40:06.273517+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJNI3MWQHXOKL4SD","created_at":"2026-07-05T03:40:06.273517+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJNI3MWQ","created_at":"2026-07-05T03:40:06.273517+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/BJNI3MWQHXOKL4SDI57LWY5U4P","json":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P.json","graph_json":"https://pith.science/api/pith-number/BJNI3MWQHXOKL4SDI57LWY5U4P/graph.json","events_json":"https://pith.science/api/pith-number/BJNI3MWQHXOKL4SDI57LWY5U4P/events.json","paper":"https://pith.science/paper/BJNI3MWQ"},"agent_actions":{"view_html":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P","download_json":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P.json","view_paper":"https://pith.science/paper/BJNI3MWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05662&json=true","fetch_graph":"https://pith.science/api/pith-number/BJNI3MWQHXOKL4SDI57LWY5U4P/graph.json","fetch_events":"https://pith.science/api/pith-number/BJNI3MWQHXOKL4SDI57LWY5U4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P/action/storage_attestation","attest_author":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P/action/author_attestation","sign_citation":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P/action/citation_signature","submit_replication":"https://pith.science/pith/BJNI3MWQHXOKL4SDI57LWY5U4P/action/replication_record"}},"created_at":"2026-07-05T03:40:06.273517+00:00","updated_at":"2026-07-05T03:40:06.273517+00:00"}