{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:37HAHZHBZ6XRAED5V3ZJPQYEHH","short_pith_number":"pith:37HAHZHB","canonical_record":{"source":{"id":"2409.11501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:05:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ce968f22a2102e1cc236f949466534e4505023d2ea348deb0e66ad505ff61ae","abstract_canon_sha256":"111b200f7b5eaba21c5f3be7359c4cd3bbbd161b1b13162fd507ca03daa398bc"},"schema_version":"1.0"},"canonical_sha256":"dfce03e4e1cfaf10107daef297c30439fc0aa6ac3df1b7d79c5b6f824b075c14","source":{"kind":"arxiv","id":"2409.11501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11501","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11501v1","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11501","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"37HAHZHBZ6XR","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"37HAHZHBZ6XRAED5","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"37HAHZHB","created_at":"2026-07-05T10:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:37HAHZHBZ6XRAED5V3ZJPQYEHH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:05:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ce968f22a2102e1cc236f949466534e4505023d2ea348deb0e66ad505ff61ae","abstract_canon_sha256":"111b200f7b5eaba21c5f3be7359c4cd3bbbd161b1b13162fd507ca03daa398bc"},"schema_version":"1.0"},"canonical_sha256":"dfce03e4e1cfaf10107daef297c30439fc0aa6ac3df1b7d79c5b6f824b075c14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:27.665837Z","signature_b64":"ntaT4rqwJ0FAJORt3awaFEgu4UhqqN6SCE97UdU4h8p3giQTv79nS4ReX2zny094MgaAc2XOphhbXTEX39oEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfce03e4e1cfaf10107daef297c30439fc0aa6ac3df1b7d79c5b6f824b075c14","last_reissued_at":"2026-07-05T10:03:27.665407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:27.665407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11501","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":"2026-07-05T10:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnIgQs4FYK6t1UfQUCkSZ8DU4p8n/goCBzKbOmZy4TDj8s6xWql3aQeISi1e3R3PJVu2dLxPFGZhUSofqjf8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:38:22.163409Z"},"content_sha256":"f69d99021ce69b158d3ce633f91c28288f398d9337f94bcc4a791731b741ae1d","schema_version":"1.0","event_id":"sha256:f69d99021ce69b158d3ce633f91c28288f398d9337f94bcc4a791731b741ae1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:37HAHZHBZ6XRAED5V3ZJPQYEHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Egalitarian Language Representation in Language Models: It All Begins with Tokenizers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kengatharaiyer Sarveswaran, Menan Velayuthan","submitted_at":"2024-09-17T19:05:37Z","abstract_excerpt":"Tokenizers act as a bridge between human language and the latent space of language models, influencing how language is represented in these models. Due to the immense popularity of English-Centric Large Language Models (LLMs), efforts are being made to adapt them for other languages. However, we demonstrate that, from a tokenization standpoint, not all tokenizers offer fair representation for complex script languages such as Tamil, Sinhala, and Hindi, primarily due to the choice of pre-tokenization methods. We go further to show that pre-tokenization plays a more critical role than the tokeniz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11501","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/2409.11501/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":"2026-07-05T10:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7QDbWHImWELgMUQ29wU85FvBPT3bqaEnTj9n+Y9lsgnlNEFxJ9TywLOfX/I5A4T0lKsYVFDf0MoYQKHqPzB0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:38:22.163926Z"},"content_sha256":"2c2fce60f99880252aab8b316b74a62abec25e1a57354d81b768d6464f308c09","schema_version":"1.0","event_id":"sha256:2c2fce60f99880252aab8b316b74a62abec25e1a57354d81b768d6464f308c09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/bundle.json","state_url":"https://pith.science/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/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":"2026-08-19T22:38:22Z","links":{"resolver":"https://pith.science/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH","bundle":"https://pith.science/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/bundle.json","state":"https://pith.science/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37HAHZHBZ6XRAED5V3ZJPQYEHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37HAHZHBZ6XRAED5V3ZJPQYEHH","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":"111b200f7b5eaba21c5f3be7359c4cd3bbbd161b1b13162fd507ca03daa398bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:05:37Z","title_canon_sha256":"6ce968f22a2102e1cc236f949466534e4505023d2ea348deb0e66ad505ff61ae"},"schema_version":"1.0","source":{"id":"2409.11501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11501","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11501v1","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11501","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"37HAHZHBZ6XR","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"37HAHZHBZ6XRAED5","created_at":"2026-07-05T10:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"37HAHZHB","created_at":"2026-07-05T10:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:2c2fce60f99880252aab8b316b74a62abec25e1a57354d81b768d6464f308c09","target":"graph","created_at":"2026-07-05T10:03:27Z","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/2409.11501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenizers act as a bridge between human language and the latent space of language models, influencing how language is represented in these models. Due to the immense popularity of English-Centric Large Language Models (LLMs), efforts are being made to adapt them for other languages. However, we demonstrate that, from a tokenization standpoint, not all tokenizers offer fair representation for complex script languages such as Tamil, Sinhala, and Hindi, primarily due to the choice of pre-tokenization methods. We go further to show that pre-tokenization plays a more critical role than the tokeniz","authors_text":"Kengatharaiyer Sarveswaran, Menan Velayuthan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:05:37Z","title":"Egalitarian Language Representation in Language Models: It All Begins with Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11501","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:f69d99021ce69b158d3ce633f91c28288f398d9337f94bcc4a791731b741ae1d","target":"record","created_at":"2026-07-05T10:03:27Z","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":"111b200f7b5eaba21c5f3be7359c4cd3bbbd161b1b13162fd507ca03daa398bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:05:37Z","title_canon_sha256":"6ce968f22a2102e1cc236f949466534e4505023d2ea348deb0e66ad505ff61ae"},"schema_version":"1.0","source":{"id":"2409.11501","kind":"arxiv","version":1}},"canonical_sha256":"dfce03e4e1cfaf10107daef297c30439fc0aa6ac3df1b7d79c5b6f824b075c14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfce03e4e1cfaf10107daef297c30439fc0aa6ac3df1b7d79c5b6f824b075c14","first_computed_at":"2026-07-05T10:03:27.665407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:27.665407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ntaT4rqwJ0FAJORt3awaFEgu4UhqqN6SCE97UdU4h8p3giQTv79nS4ReX2zny094MgaAc2XOphhbXTEX39oEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:27.665837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f69d99021ce69b158d3ce633f91c28288f398d9337f94bcc4a791731b741ae1d","sha256:2c2fce60f99880252aab8b316b74a62abec25e1a57354d81b768d6464f308c09"],"state_sha256":"dd0b4fe3eb85fd1eb363caecaf16b32fb3f4d6ef1eecb146a623c48321ecc641"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pC7znqAkgUHs/Zd1I2qZV1eAlRuCurY2KWsrLOYrRe9CpRQb8C9EwQM5/9ugCjP7s99QlALqFic6VDOjvGo5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:38:22.167695Z","bundle_sha256":"3285b5589bb9c5aac208af2c1ec892f9dc6118803db2268a9a6221f4273bff04"}}