{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V4AU7NUPW5ZVIZAR6NNRKG2WLN","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":"2042bcad5ab29f2e5233549751c8150614cb628e70321c4daf308e5cf9c5d82a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T18:47:33Z","title_canon_sha256":"26f74f5f266edc3d20a9ceae087cba90b6c09cab4d72a59d1c332d9cda8e05bc"},"schema_version":"1.0","source":{"id":"2506.17789","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17789","created_at":"2026-06-23T01:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17789v3","created_at":"2026-06-23T01:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17789","created_at":"2026-06-23T01:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"V4AU7NUPW5ZV","created_at":"2026-06-23T01:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"V4AU7NUPW5ZVIZAR","created_at":"2026-06-23T01:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"V4AU7NUP","created_at":"2026-06-23T01:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:a1bfd82153ab2b7d631edc1216f19dd72596f26fcfc857c2c59039290d4a4d0d","target":"graph","created_at":"2026-06-23T01:11:56Z","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/2506.17789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization plays a pivotal role in NLP and is fundamental to training language models. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those in the Indian subcontinent. In this work, we present a comprehensive empirical study of multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families. We systematically evaluate the effects of (i) widely used subword algorithms: BPE and Unigram LM, (ii) script and orthography-aware normaliz","authors_text":"Ganesh Ramakrishnan, Maharaj Brahma, Maunendra Sankar Desarkar, Nagasai Saketh Naidu, N J Karthika, Rajat Verma, Rohit Saluja","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T18:47:33Z","title":"Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17789","kind":"arxiv","version":3},"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":"sha256:57599dc73ce0f5c5e8d28b6dbeee86e1b30f55bd315182fbfe9cc14063db2374","target":"record","created_at":"2026-06-23T01:11:56Z","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":"2042bcad5ab29f2e5233549751c8150614cb628e70321c4daf308e5cf9c5d82a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T18:47:33Z","title_canon_sha256":"26f74f5f266edc3d20a9ceae087cba90b6c09cab4d72a59d1c332d9cda8e05bc"},"schema_version":"1.0","source":{"id":"2506.17789","kind":"arxiv","version":3}},"canonical_sha256":"af014fb68fb773546411f35b151b565b623a01e0f95cd7c852b061072da67921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af014fb68fb773546411f35b151b565b623a01e0f95cd7c852b061072da67921","first_computed_at":"2026-06-23T01:11:56.026025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:11:56.026025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OrUQLAi1i+3jLGXEpR++f6itHDEFqBCGCsiJNd/5eOA3sITaPlJ6Us+EhGuUh/ShMm7g7zUBy76MPhceDJa4BQ==","signature_status":"signed_v1","signed_at":"2026-06-23T01:11:56.026699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17789","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57599dc73ce0f5c5e8d28b6dbeee86e1b30f55bd315182fbfe9cc14063db2374","sha256:a1bfd82153ab2b7d631edc1216f19dd72596f26fcfc857c2c59039290d4a4d0d"],"state_sha256":"602a9e3a67c9f67ea6242854844f7813ee41d9414380c7d5e397497144f37e38"}