{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BJNI3MWQHXOKL4SDI57LWY5U4P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5d0713af550f030a942ebe410ddde4a8624f546af8dd8f4b04066612ab08b96f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-10T16:49:49Z","title_canon_sha256":"7d51387273cc07032825ee37cca0775bba6d59d72bddb02ca4e13c5d40541d2e"},"schema_version":"1.0","source":{"id":"2112.05662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05662","created_at":"2026-07-05T03:40:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05662v2","created_at":"2026-07-05T03:40:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05662","created_at":"2026-07-05T03:40:06Z"},{"alias_kind":"pith_short_12","alias_value":"BJNI3MWQHXOK","created_at":"2026-07-05T03:40:06Z"},{"alias_kind":"pith_short_16","alias_value":"BJNI3MWQHXOKL4SD","created_at":"2026-07-05T03:40:06Z"},{"alias_kind":"pith_short_8","alias_value":"BJNI3MWQ","created_at":"2026-07-05T03:40:06Z"}],"graph_snapshots":[{"event_id":"sha256:a3d1756b83d0156bcd2ce7c04cbca052edc4c99210fdbd2fa4569f59873c909c","target":"graph","created_at":"2026-07-05T03:40:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.05662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Piwowarski, St\\'ephane Clinchant, Thibault Formal","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-10T16:49:49Z","title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05662","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4047e1b06d8bfc008642f8786eafe0f6d64577a4824d91c396f7f027a5998b23","target":"record","created_at":"2026-07-05T03:40:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5d0713af550f030a942ebe410ddde4a8624f546af8dd8f4b04066612ab08b96f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-10T16:49:49Z","title_canon_sha256":"7d51387273cc07032825ee37cca0775bba6d59d72bddb02ca4e13c5d40541d2e"},"schema_version":"1.0","source":{"id":"2112.05662","kind":"arxiv","version":2}},"canonical_sha256":"0a5a8db2d03ddca5f243477ebb63b4e3f10c30c3e619193b1c0a5e06a0f19338","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a5a8db2d03ddca5f243477ebb63b4e3f10c30c3e619193b1c0a5e06a0f19338","first_computed_at":"2026-07-05T03:40:06.273459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:06.273459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DIEz6w0An4uQkLzVGlYdZE5wE0Fkl8MWmJi6oJsYb2MBqmWIbFAsjvCtHxWG0Kearkck6qTInJgCL7dYGLrXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:06.273893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4047e1b06d8bfc008642f8786eafe0f6d64577a4824d91c396f7f027a5998b23","sha256:a3d1756b83d0156bcd2ce7c04cbca052edc4c99210fdbd2fa4569f59873c909c"],"state_sha256":"c719efe1cb0786e702ef4ed6a9bd86667f03a4ed3c4f69e8c7d17fb9dcfe7d5c"}