{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3ODL5KLAKGGNBLNUIAIWZQAASR","short_pith_number":"pith:3ODL5KLA","canonical_record":{"source":{"id":"2410.03568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T16:18:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3094e47dcf0924b36a1cb546b3dd505e72db3352c00bfa9a24727c90e301790f","abstract_canon_sha256":"3a8dc79122daac1b49246a518cc4f8194a9952bda29c18c1f7e37ab3b9423113"},"schema_version":"1.0"},"canonical_sha256":"db86bea960518cd0adb440116cc00094711f82754361335857b7c59a4ea3a1a8","source":{"kind":"arxiv","id":"2410.03568","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03568","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03568v1","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03568","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"3ODL5KLAKGGN","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"3ODL5KLAKGGNBLNU","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"3ODL5KLA","created_at":"2026-07-05T09:16:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3ODL5KLAKGGNBLNUIAIWZQAASR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T16:18:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3094e47dcf0924b36a1cb546b3dd505e72db3352c00bfa9a24727c90e301790f","abstract_canon_sha256":"3a8dc79122daac1b49246a518cc4f8194a9952bda29c18c1f7e37ab3b9423113"},"schema_version":"1.0"},"canonical_sha256":"db86bea960518cd0adb440116cc00094711f82754361335857b7c59a4ea3a1a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:03.078691Z","signature_b64":"ZibIY77GV5ceCVNFA21z3EUrZmThX3T8UgqrPqVLEXkA0Of3/72SS0WVQUD/K/YoCQjZ56YAfnLymdABR4ByAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db86bea960518cd0adb440116cc00094711f82754361335857b7c59a4ea3a1a8","last_reissued_at":"2026-07-05T09:16:03.078251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:03.078251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03568","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":"2026-07-05T09:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jXm40zHJhjWktNGb7OO9/ZrAut8E0MWbRhCmZjSrJHvf5wLs6+Dd1v+bymEu6wKlhW3gTFYuE0BvLMaDQJUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:39:41.873119Z"},"content_sha256":"f7d45e6a1781c981dc5c80f55962e1f98ee769d8d348f54381e7893acd8bc4ec","schema_version":"1.0","event_id":"sha256:f7d45e6a1781c981dc5c80f55962e1f98ee769d8d348f54381e7893acd8bc4ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3ODL5KLAKGGNBLNUIAIWZQAASR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abrar Rahman, Binit Mohanty, Garry Bowlin, Sean McGunigal","submitted_at":"2024-10-04T16:18:29Z","abstract_excerpt":"This paper presents a comprehensive study on the tokenization techniques employed by state-of-the-art large language models (LLMs) and their implications on the cost and availability of services across different languages, especially low resource languages. The analysis considers multiple LLMs, including GPT-4 (using cl100k_base embeddings), GPT-3 (with p50k_base embeddings), and DaVinci (employing r50k_base embeddings), as well as the widely used BERT base tokenizer. The study evaluates the tokenization variability observed across these models and investigates the challenges of linguistic rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03568","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/2410.03568/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":"2026-07-05T09:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/I1jJp9dvaI4ZUwCToaKK7/ZCId9bAaXf1FAZucEudXBCc+yzjQUv22gLHqFkEtDRuVq+tvC4ouEjp1Ql77BBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:39:41.874297Z"},"content_sha256":"b267fe9dbdf61bb5849f935c51bf1dc3a48c22e5da2de04b1f4b128ac2918d75","schema_version":"1.0","event_id":"sha256:b267fe9dbdf61bb5849f935c51bf1dc3a48c22e5da2de04b1f4b128ac2918d75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/bundle.json","state_url":"https://pith.science/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/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":"2026-08-16T01:39:41Z","links":{"resolver":"https://pith.science/pith/3ODL5KLAKGGNBLNUIAIWZQAASR","bundle":"https://pith.science/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/bundle.json","state":"https://pith.science/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ODL5KLAKGGNBLNUIAIWZQAASR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3ODL5KLAKGGNBLNUIAIWZQAASR","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":"3a8dc79122daac1b49246a518cc4f8194a9952bda29c18c1f7e37ab3b9423113","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T16:18:29Z","title_canon_sha256":"3094e47dcf0924b36a1cb546b3dd505e72db3352c00bfa9a24727c90e301790f"},"schema_version":"1.0","source":{"id":"2410.03568","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03568","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03568v1","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03568","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"3ODL5KLAKGGN","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"3ODL5KLAKGGNBLNU","created_at":"2026-07-05T09:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"3ODL5KLA","created_at":"2026-07-05T09:16:03Z"}],"graph_snapshots":[{"event_id":"sha256:b267fe9dbdf61bb5849f935c51bf1dc3a48c22e5da2de04b1f4b128ac2918d75","target":"graph","created_at":"2026-07-05T09:16:03Z","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/2410.03568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comprehensive study on the tokenization techniques employed by state-of-the-art large language models (LLMs) and their implications on the cost and availability of services across different languages, especially low resource languages. The analysis considers multiple LLMs, including GPT-4 (using cl100k_base embeddings), GPT-3 (with p50k_base embeddings), and DaVinci (employing r50k_base embeddings), as well as the widely used BERT base tokenizer. The study evaluates the tokenization variability observed across these models and investigates the challenges of linguistic rep","authors_text":"Abrar Rahman, Binit Mohanty, Garry Bowlin, Sean McGunigal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T16:18:29Z","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03568","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:f7d45e6a1781c981dc5c80f55962e1f98ee769d8d348f54381e7893acd8bc4ec","target":"record","created_at":"2026-07-05T09:16:03Z","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":"3a8dc79122daac1b49246a518cc4f8194a9952bda29c18c1f7e37ab3b9423113","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T16:18:29Z","title_canon_sha256":"3094e47dcf0924b36a1cb546b3dd505e72db3352c00bfa9a24727c90e301790f"},"schema_version":"1.0","source":{"id":"2410.03568","kind":"arxiv","version":1}},"canonical_sha256":"db86bea960518cd0adb440116cc00094711f82754361335857b7c59a4ea3a1a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db86bea960518cd0adb440116cc00094711f82754361335857b7c59a4ea3a1a8","first_computed_at":"2026-07-05T09:16:03.078251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:03.078251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZibIY77GV5ceCVNFA21z3EUrZmThX3T8UgqrPqVLEXkA0Of3/72SS0WVQUD/K/YoCQjZ56YAfnLymdABR4ByAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:03.078691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03568","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7d45e6a1781c981dc5c80f55962e1f98ee769d8d348f54381e7893acd8bc4ec","sha256:b267fe9dbdf61bb5849f935c51bf1dc3a48c22e5da2de04b1f4b128ac2918d75"],"state_sha256":"747c425a29786af40f8a4956f76eadc5126f2dcd5c2535576c3ef7d380d251ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnTgfz7nvPspanbYwE2+LkM4Faurua/oCVMWVRuP6+E4Mvzt1Ud1Bcc1A6+ZTB/11tno+oNEk7HO/z+B3eXQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:39:41.879280Z","bundle_sha256":"2ec9eda42f7df1709a79ec25e47d083fa560a7500bfd7c3c3eb0cae4e1865849"}}