{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A3HSD7RNO7OUBYY6QP6SW65AD3","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":"366d38082e892af7655de8fb2cef95d54279bdebaa44ab54ffff52af2c011a2f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T17:59:56Z","title_canon_sha256":"a6c484aac5b78ec4773ed021373eee170c199e2966d0a7338ebc647fb0ac9535"},"schema_version":"1.0","source":{"id":"2605.22821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22821","created_at":"2026-05-22T02:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22821v1","created_at":"2026-05-22T02:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22821","created_at":"2026-05-22T02:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"A3HSD7RNO7OU","created_at":"2026-05-22T02:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"A3HSD7RNO7OUBYY6","created_at":"2026-05-22T02:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"A3HSD7RN","created_at":"2026-05-22T02:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:0944a1d69e03f802ef14b3b593a7d21fb1c8d0c3abdf99dee0667e292f1ae6cf","target":"graph","created_at":"2026-05-22T02:04:56Z","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/2605.22821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make locally optimal decisions without considering the resulting vocabulary as a whole. We instead formulate tokeniser construction as a linear program and solve it using convex optimisation tools, yielding a new algorithm we call ConvexTok. We find ConvexTok consistently improves intrinsic tokenisation metrics and the bits-per-byte (BpB) achieved by language models; it also improves downstream task performance, but less consistently. Furthermore, ","authors_text":"Craig W. Schmidt, Dennis Komm, Jan Tempus, Philip Whittington, Tiago Pimentel","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T17:59:56Z","title":"Tokenisation via Convex Relaxations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22821","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":"sha256:64666e92ce7c3a691a94d8d59c157caaade1478398288ed4d15ba633dfbaab2d","target":"record","created_at":"2026-05-22T02:04:56Z","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":"366d38082e892af7655de8fb2cef95d54279bdebaa44ab54ffff52af2c011a2f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T17:59:56Z","title_canon_sha256":"a6c484aac5b78ec4773ed021373eee170c199e2966d0a7338ebc647fb0ac9535"},"schema_version":"1.0","source":{"id":"2605.22821","kind":"arxiv","version":1}},"canonical_sha256":"06cf21fe2d77dd40e31e83fd2b7ba01ed1152b4f0db83df720fbcd2c2914631f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06cf21fe2d77dd40e31e83fd2b7ba01ed1152b4f0db83df720fbcd2c2914631f","first_computed_at":"2026-05-22T02:04:56.345304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:56.345304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1QT1X0+nTB7rfscnochacOMM8dzkWo8QB4Xa6csj5GhouNzvQNB5M/xVs+/nYeO23deN+uGHABgFS4KAQ8/yAg==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:56.345741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64666e92ce7c3a691a94d8d59c157caaade1478398288ed4d15ba633dfbaab2d","sha256:0944a1d69e03f802ef14b3b593a7d21fb1c8d0c3abdf99dee0667e292f1ae6cf"],"state_sha256":"473f4ee0f93cbbda403442c0792791bfcbf14add2515ba443b81bace18b8ed14"}