{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KVKEX3WIDAN6HDLFJ3JBB44KJN","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":"528242dffc77345dda08be728230200417477574b68a30e59f77ce8c4ce70524","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:32:46Z","title_canon_sha256":"27fe93ae57ede1982c2b752f431846a4ea8d305962bd27daf1c93c87afb52481"},"schema_version":"1.0","source":{"id":"2210.05481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05481","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05481v1","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05481","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"KVKEX3WIDAN6","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"KVKEX3WIDAN6HDLF","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"KVKEX3WI","created_at":"2026-07-05T05:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:eb1e019a4105e43547eeb5158e41ffac405ba5b237c972a3fe30a0679b3e8b3c","target":"graph","created_at":"2026-07-05T05:05:17Z","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/2210.05481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jimmy Lin, Odunayo Ogundepo, Xinyu Zhang","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:32:46Z","title":"Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05481","kind":"arxiv","version":1},"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":"sha256:8036c6192edf5fd5dc73a58f2765e0396095fe79312bdaa2b0293b1dd2652399","target":"record","created_at":"2026-07-05T05:05:17Z","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":"528242dffc77345dda08be728230200417477574b68a30e59f77ce8c4ce70524","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:32:46Z","title_canon_sha256":"27fe93ae57ede1982c2b752f431846a4ea8d305962bd27daf1c93c87afb52481"},"schema_version":"1.0","source":{"id":"2210.05481","kind":"arxiv","version":1}},"canonical_sha256":"55544beec8181be38d654ed210f38a4b4c530530010cd5e449468b4fab003f49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55544beec8181be38d654ed210f38a4b4c530530010cd5e449468b4fab003f49","first_computed_at":"2026-07-05T05:05:17.089802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:17.089802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lHpFaCgo+P93hZ3LgfctKeakD64KqaNulCwrax/p2kZH/edd4twttZ5K5j4HIecNumQWAENHlloqKBvA7YQWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:17.090235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8036c6192edf5fd5dc73a58f2765e0396095fe79312bdaa2b0293b1dd2652399","sha256:eb1e019a4105e43547eeb5158e41ffac405ba5b237c972a3fe30a0679b3e8b3c"],"state_sha256":"5a0dcd48a371f79022489c852bbadba5ea1dfda680f177b6f6c3c7c5e0633cc0"}