{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T4G5P347MCRLDKUYVACCBW3BOR","short_pith_number":"pith:T4G5P347","schema_version":"1.0","canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","source":{"kind":"arxiv","id":"2607.00004","version":1},"attestation_state":"computed","paper":{"title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Yang Yang, Zhichao Geng","submitted_at":"2026-04-20T05:52:25Z","abstract_excerpt":"While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root cause as the \\textit{Vocabulary Gap}: modern tokenizers utilize raw, case-sensitive vocabularies designed for lossless reconstruction, which map single semantic units to redundant surface forms, wasting model capacity on morphological noise and hindering lexical matching. We formalize this intuition through a theoretical framework, demonstrating that appropriate vocabul"},"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":"2607.00004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ce2c72ae63f4e2253371d1e4d2ef9c3d0092f63415259503d4071e63efb5e574","abstract_canon_sha256":"0d2a4837776dd46ecc8f0a4480de9f50506628417113022e38ade9ebdd64e187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:04.182001Z","signature_b64":"oDPiAo36nhhQIlzXjxSsQ11Se7aGDV7TkSjP06EdML3WtgY6Z5VUxZXN4lm5WxKlftZZsPznYfCoGurPu6mWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","last_reissued_at":"2026-07-02T00:18:04.181197Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:04.181197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Yang Yang, Zhichao Geng","submitted_at":"2026-04-20T05:52:25Z","abstract_excerpt":"While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root cause as the \\textit{Vocabulary Gap}: modern tokenizers utilize raw, case-sensitive vocabularies designed for lossless reconstruction, which map single semantic units to redundant surface forms, wasting model capacity on morphological noise and hindering lexical matching. We formalize this intuition through a theoretical framework, demonstrating that appropriate vocabul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00004","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/2607.00004/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":"2607.00004","created_at":"2026-07-02T00:18:04.181311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00004v1","created_at":"2026-07-02T00:18:04.181311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00004","created_at":"2026-07-02T00:18:04.181311+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4G5P347MCRL","created_at":"2026-07-02T00:18:04.181311+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4G5P347MCRLDKUY","created_at":"2026-07-02T00:18:04.181311+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4G5P347","created_at":"2026-07-02T00:18:04.181311+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/T4G5P347MCRLDKUYVACCBW3BOR","json":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR.json","graph_json":"https://pith.science/api/pith-number/T4G5P347MCRLDKUYVACCBW3BOR/graph.json","events_json":"https://pith.science/api/pith-number/T4G5P347MCRLDKUYVACCBW3BOR/events.json","paper":"https://pith.science/paper/T4G5P347"},"agent_actions":{"view_html":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR","download_json":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR.json","view_paper":"https://pith.science/paper/T4G5P347","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00004&json=true","fetch_graph":"https://pith.science/api/pith-number/T4G5P347MCRLDKUYVACCBW3BOR/graph.json","fetch_events":"https://pith.science/api/pith-number/T4G5P347MCRLDKUYVACCBW3BOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/action/storage_attestation","attest_author":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/action/author_attestation","sign_citation":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/action/citation_signature","submit_replication":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/action/replication_record"}},"created_at":"2026-07-02T00:18:04.181311+00:00","updated_at":"2026-07-02T00:18:04.181311+00:00"}