{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KVKEX3WIDAN6HDLFJ3JBB44KJN","short_pith_number":"pith:KVKEX3WI","schema_version":"1.0","canonical_sha256":"55544beec8181be38d654ed210f38a4b4c530530010cd5e449468b4fab003f49","source":{"kind":"arxiv","id":"2210.05481","version":1},"attestation_state":"computed","paper":{"title":"Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Odunayo Ogundepo, Xinyu Zhang","submitted_at":"2022-10-11T14:32:46Z","abstract_excerpt":"Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique properties, the design of the tokenization algorithm is usually language-specific and requires at least some lingustic knowledge. However, only a handful of the 7000+ languages on the planet benefit from specialized, custom-built tokenization algorithms, while the other languages are stuck with a \"default\" whitespace tokenizer, which cannot capture the intricacie"},"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":"2210.05481","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:32:46Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"27fe93ae57ede1982c2b752f431846a4ea8d305962bd27daf1c93c87afb52481","abstract_canon_sha256":"528242dffc77345dda08be728230200417477574b68a30e59f77ce8c4ce70524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:17.090235Z","signature_b64":"lHpFaCgo+P93hZ3LgfctKeakD64KqaNulCwrax/p2kZH/edd4twttZ5K5j4HIecNumQWAENHlloqKBvA7YQWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55544beec8181be38d654ed210f38a4b4c530530010cd5e449468b4fab003f49","last_reissued_at":"2026-07-05T05:05:17.089802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:17.089802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Odunayo Ogundepo, Xinyu Zhang","submitted_at":"2022-10-11T14:32:46Z","abstract_excerpt":"Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique properties, the design of the tokenization algorithm is usually language-specific and requires at least some lingustic knowledge. However, only a handful of the 7000+ languages on the planet benefit from specialized, custom-built tokenization algorithms, while the other languages are stuck with a \"default\" whitespace tokenizer, which cannot capture the intricacie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05481","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/2210.05481/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":"2210.05481","created_at":"2026-07-05T05:05:17.089853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05481v1","created_at":"2026-07-05T05:05:17.089853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05481","created_at":"2026-07-05T05:05:17.089853+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVKEX3WIDAN6","created_at":"2026-07-05T05:05:17.089853+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVKEX3WIDAN6HDLF","created_at":"2026-07-05T05:05:17.089853+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVKEX3WI","created_at":"2026-07-05T05:05:17.089853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12240","citing_title":"Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN","json":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN.json","graph_json":"https://pith.science/api/pith-number/KVKEX3WIDAN6HDLFJ3JBB44KJN/graph.json","events_json":"https://pith.science/api/pith-number/KVKEX3WIDAN6HDLFJ3JBB44KJN/events.json","paper":"https://pith.science/paper/KVKEX3WI"},"agent_actions":{"view_html":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN","download_json":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN.json","view_paper":"https://pith.science/paper/KVKEX3WI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05481&json=true","fetch_graph":"https://pith.science/api/pith-number/KVKEX3WIDAN6HDLFJ3JBB44KJN/graph.json","fetch_events":"https://pith.science/api/pith-number/KVKEX3WIDAN6HDLFJ3JBB44KJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN/action/storage_attestation","attest_author":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN/action/author_attestation","sign_citation":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN/action/citation_signature","submit_replication":"https://pith.science/pith/KVKEX3WIDAN6HDLFJ3JBB44KJN/action/replication_record"}},"created_at":"2026-07-05T05:05:17.089853+00:00","updated_at":"2026-07-05T05:05:17.089853+00:00"}