{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XZC2EOQOXDJHIKRPXTTYLD2KWJ","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":"b18e3ac671847f37037b39a4ef265a7acb01773feffa09876522ece01fab7f1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T21:01:14Z","title_canon_sha256":"62669ffd2298721c0b3cb2f33d5a3124978d86ca049f275065bda57dd95e9e8f"},"schema_version":"1.0","source":{"id":"2607.23362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23362","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23362v1","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23362","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"XZC2EOQOXDJH","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"XZC2EOQOXDJHIKRP","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"XZC2EOQO","created_at":"2026-07-28T01:22:49Z"}],"graph_snapshots":[{"event_id":"sha256:da3381263e49d44a9135deacb603ddaaef63bcd5f2b37f66db4439d13049079c","target":"graph","created_at":"2026-07-28T01:22:49Z","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/2607.23362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that subword vocabularies can be trained to optimize compression for a specific inference rule rather than relying on greedy heuristics such as Byte Pair Encoding (BPE). We extend this approach to greedy left-to-right longest-match decoding, the fast and widely used inference rule underlying WordPiece. We introduce Joint Optimization for Greedy Longest-Match Tokenization (JOLT), which formulates vocabulary learning as an integer program over vocabulary-selection and segmentation-choice variables. Greedy-consistency constraints ensure that each optimized segmentation exact","authors_text":"Adam Wiemerslage, Adhiraj Singh, Craig W. Schmidt, Deepanshu Mody, Ghina Al Shdaifat, Hamza Alshamy, Varshini Reddy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T21:01:14Z","title":"Joint Optimization for Greedy Longest-match Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23362","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":"sha256:235c1329e4d4842fc98ee4faa524f6ba17ebc27a1681126e558eb6888c95fdde","target":"record","created_at":"2026-07-28T01:22:49Z","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":"b18e3ac671847f37037b39a4ef265a7acb01773feffa09876522ece01fab7f1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T21:01:14Z","title_canon_sha256":"62669ffd2298721c0b3cb2f33d5a3124978d86ca049f275065bda57dd95e9e8f"},"schema_version":"1.0","source":{"id":"2607.23362","kind":"arxiv","version":1}},"canonical_sha256":"be45a23a0eb8d2742a2fbce7858f4ab25866e531e4bdb7f9f8a2cf57ec63e035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be45a23a0eb8d2742a2fbce7858f4ab25866e531e4bdb7f9f8a2cf57ec63e035","first_computed_at":"2026-07-28T01:22:49.234190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:49.234190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bH7h5XOmVNPjYGG6Ym9Lk9wyCkMSMXtBIx2SfICwe+fh7w1wPqTlPLfMZyfr7idfKEMV1e/6EvJwgWv4F+2DCA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:49.234975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:235c1329e4d4842fc98ee4faa524f6ba17ebc27a1681126e558eb6888c95fdde","sha256:da3381263e49d44a9135deacb603ddaaef63bcd5f2b37f66db4439d13049079c"],"state_sha256":"785f6f7ad055e2169b73c527f04951bf2ed0c05ee9b19b13cd12e7f17b13c5b4"}