{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EHMTTSDRYMEGXSU4YQXFOYABY3","short_pith_number":"pith:EHMTTSDR","canonical_record":{"source":{"id":"2605.29379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T05:29:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd025a3d31a6ae4c01850ab453610489904885509caaa6e9de4abbcb85fe5b9e","abstract_canon_sha256":"154aedc9a9c07dc47b9ded8eadd0e94e080b31f607cf044b935c552e2c255490"},"schema_version":"1.0"},"canonical_sha256":"21d939c871c3086bca9cc42e576001c6c7937adf1074727bf91e69892ac36ce5","source":{"kind":"arxiv","id":"2605.29379","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EHMTTSDRYMEGXSU4YQXFOYABY3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T05:29:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd025a3d31a6ae4c01850ab453610489904885509caaa6e9de4abbcb85fe5b9e","abstract_canon_sha256":"154aedc9a9c07dc47b9ded8eadd0e94e080b31f607cf044b935c552e2c255490"},"schema_version":"1.0"},"canonical_sha256":"21d939c871c3086bca9cc42e576001c6c7937adf1074727bf91e69892ac36ce5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:36.139640Z","signature_b64":"81bGoRPY0qV5Wif5ghWfVG/MFq+4Q0cVXIeetZl++k/vLVsUq6TsZu3xRHGwKe/mErF6ScesiXT+DQ0fWWvvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21d939c871c3086bca9cc42e576001c6c7937adf1074727bf91e69892ac36ce5","last_reissued_at":"2026-05-29T01:05:36.138920Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:36.138920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29379","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5oBLmGwWL3gNKIuqPAp7UMaIW34r0sBj6l7KxRygPby/nWY9JgPFU69KUoXzObnGHUOBVgtnt043Gt8v2UMcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:32:17.600591Z"},"content_sha256":"52f191f54229f700765b7fb9e867700a24f1bafeab424267e4c5053c63f6adca","schema_version":"1.0","event_id":"sha256:52f191f54229f700765b7fb9e867700a24f1bafeab424267e4c5053c63f6adca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EHMTTSDRYMEGXSU4YQXFOYABY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Rohan Shravan","submitted_at":"2026-05-28T05:29:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29379","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/2605.29379/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2y1HLWkq3e3sJJ0vCraANU9UuFdveAMqmol4oZ5afu9rpk9o+dXPpLTHxQLBoleu6KJchyQdjYl/m1itnqxgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:32:17.601350Z"},"content_sha256":"5f103d5da76e620fc4530e8a57a7b827bd70ed337d141f122699671b0c265475","schema_version":"1.0","event_id":"sha256:5f103d5da76e620fc4530e8a57a7b827bd70ed337d141f122699671b0c265475"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/bundle.json","state_url":"https://pith.science/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T22:32:17Z","links":{"resolver":"https://pith.science/pith/EHMTTSDRYMEGXSU4YQXFOYABY3","bundle":"https://pith.science/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/bundle.json","state":"https://pith.science/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHMTTSDRYMEGXSU4YQXFOYABY3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2aQOtpORdFg58HlM20zBAms2UWAhD16nI542JsTqXVeCbwV39ES39mSpjZy0/YEWfYLOj3BrS6yH2E9LXZE7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T22:32:17.608515Z","bundle_sha256":"e897a45392f017a7dd915d8717850074876ab38194571612bd8bbe1c1871b0ee"}}