{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EHMTTSDRYMEGXSU4YQXFOYABY3","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":"154aedc9a9c07dc47b9ded8eadd0e94e080b31f607cf044b935c552e2c255490","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T05:29:12Z","title_canon_sha256":"fd025a3d31a6ae4c01850ab453610489904885509caaa6e9de4abbcb85fe5b9e"},"schema_version":"1.0","source":{"id":"2605.29379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29379","created_at":"2026-05-29T01:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29379v1","created_at":"2026-05-29T01:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29379","created_at":"2026-05-29T01:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"EHMTTSDRYMEG","created_at":"2026-05-29T01:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"EHMTTSDRYMEGXSU4","created_at":"2026-05-29T01:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"EHMTTSDR","created_at":"2026-05-29T01:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:5f103d5da76e620fc4530e8a57a7b827bd70ed337d141f122699671b0c265475","target":"graph","created_at":"2026-05-29T01:05:36Z","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/2605.29379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class while preserving the English, EU-language, and code compression of OpenAI's o200k_base. We construct it through a two-stage retrofit: (1) a script-prune crop that reduces 200,019 tokens to 131,072 by removing nine out-of-scope writing systems, and (2) a surgical retrofit of 2,372 corpus-dead vocabulary slots determined by linear-programming allocation across nine Brahmic Unicode blocks. The pre-tokenizer, decoder, and inherited merge rules are unc","authors_text":"Rohan Shravan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T05:29:12Z","title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29379","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":"sha256:52f191f54229f700765b7fb9e867700a24f1bafeab424267e4c5053c63f6adca","target":"record","created_at":"2026-05-29T01:05:36Z","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":"154aedc9a9c07dc47b9ded8eadd0e94e080b31f607cf044b935c552e2c255490","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T05:29:12Z","title_canon_sha256":"fd025a3d31a6ae4c01850ab453610489904885509caaa6e9de4abbcb85fe5b9e"},"schema_version":"1.0","source":{"id":"2605.29379","kind":"arxiv","version":1}},"canonical_sha256":"21d939c871c3086bca9cc42e576001c6c7937adf1074727bf91e69892ac36ce5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21d939c871c3086bca9cc42e576001c6c7937adf1074727bf91e69892ac36ce5","first_computed_at":"2026-05-29T01:05:36.138920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:36.138920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"81bGoRPY0qV5Wif5ghWfVG/MFq+4Q0cVXIeetZl++k/vLVsUq6TsZu3xRHGwKe/mErF6ScesiXT+DQ0fWWvvCg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:36.139640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52f191f54229f700765b7fb9e867700a24f1bafeab424267e4c5053c63f6adca","sha256:5f103d5da76e620fc4530e8a57a7b827bd70ed337d141f122699671b0c265475"],"state_sha256":"4420788bfe46736e7c82006d15f86e8b52d839d86d7f821a6b2f424dde36ecb4"}