Pith. sign in

Paper Citation Record · LEDGER

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content

As of 14 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2607.16117.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.16117 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:22:42.436125Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

58 of 58 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved54
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4afdfa54-f88a-46e0-9a15-bcbed05c5422 · outbound

This paper cites Alabi, Yanke Mao, Haonan Gao, and En-Shiun Annie Lee.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Alabi, Yanke Mao, Haonan Gao, and En-Shiun Annie Lee

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:36.763206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:36.763206Z digest=sha256:6cc64625feb1c0477894a4eccd33a3bcd17aa53cfca18fdfd673c5c090ac6ed6

Observation 7ebeb8e9-7f88-4a7f-b891-d2444363f441 · outbound

This paper cites Do all languages cost the same? tokenization in the era of commercial language models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Do all languages cost the same? tokenization in the era of commercial language models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:36.812325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:36.812325Z digest=sha256:aac5d201e18bd3b1b92d372cc2534e77a07fd8c7e95f0a0280de1e31e990a558

Observation 690b540f-d575-476a-8e7d-c6a90a6cc88c · outbound

This paper cites Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:36.902178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:36.902178Z digest=sha256:21e5de8c3e5e0ea72768e53901bcbe7826dd80508a6a7a3fcb89a37e414e2a86

Observation 89d56c74-8406-4bfb-a1c7-5fb00e869092 · outbound

This paper cites MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:36.983051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:36.983051Z digest=sha256:d549e439afd30e1a5c10c87fe271a9e2af075032ec406da55ec413cd432e59e2

Observation d9a50f12-f94e-496d-a3b0-c902f0c676c2 · outbound

This paper cites Longformer: The Long-Document Transformer.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Longformer: The Long-Document Transformer

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.066132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.066132Z digest=sha256:e35cbb108dee983a4297617f6b41d3fe120dbdfbcbf1ccb6df1ea3e5507a87b4

Observation 1db98461-7eb8-4595-bc6f-c35a2a4aa943 · outbound

This paper cites A massively parallel corpus: the bible in 100 languages.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content A massively parallel corpus: the bible in 100 languages

Reference 6

Resolution
verified exact
doi, observed 2026-08-01T21:23:49.821748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-01T21:22:37.209113Z digest=sha256:25c91299aa84fc81f8fd6adaee4151a67dfbc8ab9eb9dd692ce752d977fb29fc

Observation 56cfdd58-8a93-49ce-9d91-b3cb70c42225 · outbound

This paper cites Clark, Dan Garrette, Iulia Turc, and John Wieting.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Clark, Dan Garrette, Iulia Turc, and John Wieting

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.281928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.281928Z digest=sha256:68a3d27fb553577d158dd7d9c85bf0e51339508ec9a3246955c9aac9a732199f

Observation 1c1471e1-2942-487b-a3f8-870c9090db12 · outbound

This paper cites BERT : Pre-training of deep bidirectional transformers for language understanding.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content BERT : Pre-training of deep bidirectional transformers for language understanding

Reference 8

Resolution
malformed identifier
no resolver link, observed 2026-08-01T21:22:37.384422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.384422Z digest=sha256:f83e55a7c834dd80afe4f2c26fb662996e2d18afe9cb1a6550ca31bb7fcb26fd

Observation f84267cb-b37d-44e6-a32e-f03f760090f7 · outbound

This paper cites Multiscale byte language models -- a hierarchical architecture for causal million-length sequence modeling.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Multiscale byte language models -- a hierarchical architecture for causal million-length sequence modeling

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.479630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.479630Z digest=sha256:ff2e80406652025394149ad7992f0206e57d14632bd17dbe25711fa4eff3468f

Observation af455e76-ba7b-4c17-a00b-03e5f6650175 · outbound

This paper cites O mer Veysel C a g atan, Akash Kundu, Martin Bernstorff, Shitao Xiao, Akshita Sukhlecha, Bhavish Pahwa, Rafa Po \'s wiata, Kranthi Kiran GV, Shawon Ashraf, Daniel Auras, Bj \.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content O mer Veysel C a g atan, Akash Kundu, Martin Bernstorff, Shitao Xiao, Akshita Sukhlecha, Bhavish Pahwa, Rafa Po \'s wiata, Kranthi Kiran GV, Shawon Ashraf, Daniel Auras, Bj \

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.572373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.572373Z digest=sha256:c86eca3d321964c037e814e75eb445103077d70013d8dbd8af2f2a4b2948a0fc

Observation 9b48849d-5b01-4662-8309-4b87b91a1977 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content GLM-5: from Vibe Coding to Agentic Engineering

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.680542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.680542Z digest=sha256:141ee4f0676168263e321258215b2f2a07ec94a019da1714f99bebcd75b7343a

Observation 3c9eeacf-439a-4216-9443-06f56ccc44ce · outbound

This paper cites The Llama 3 Herd of Models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content The Llama 3 Herd of Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.776856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.776856Z digest=sha256:956b5eeb23980b1a5f48d6f323a2e95da3bf64b3f626ee81f3ae3fd38251b5c3

Observation 57a89f98-0c42-4bb8-affa-5c4801d5e21e · outbound

This paper cites Bitext mining using distilled sentence representations for low-resource languages.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Bitext mining using distilled sentence representations for low-resource languages

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.864150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.864150Z digest=sha256:390876d8692e69e71ec2f135f2676cb5d4d4af37603aed81ffc2f4302c0da890

Observation 66cc1f93-437d-4249-a7c2-cc3e3cfc178e · outbound

This paper cites HTML Bible Index -- Ukrainian.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content HTML Bible Index -- Ukrainian

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:37.939070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:37.939070Z digest=sha256:5b9710d2a4904bfb6df3890bb2ee2635668d0940ca7efb24062af71c96e430c8

Observation 4e885ffe-ebd8-4dfa-812c-11fbb4ae657e · outbound

This paper cites Perceiver: General perception with iterative attention.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Perceiver: General perception with iterative attention

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.019718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.019718Z digest=sha256:d97a6b1e893ae5f189cd3ed48643d4feec4d67172192883a5d7190c7e246ac5a

Observation 51b4d924-55d4-48cf-a363-b90deaada197 · outbound

This paper cites Ticls: Tightly coupled language text spotter.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Ticls: Tightly coupled language text spotter

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.087203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.087203Z digest=sha256:7261d16aba6ea8c1ba78ffe93be4068ea5eb30854dbed2aabdf2b8a9f2d32e56

Observation 91cc27fb-f243-4255-b5ae-5eb7e8441060 · outbound

This paper cites Lotz, Ingo Ziegler, Phillip Rust, and Desmond Elliott.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Lotz, Ingo Ziegler, Phillip Rust, and Desmond Elliott

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.175841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.175841Z digest=sha256:4d86d8695a403d4234f6a222fb20779b143b052160d8591000f50fe8bbca4a1b

Observation 471917f3-ca0e-4399-8062-c12b98fd00ba · outbound

This paper cites Supervised contrastive learning.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Supervised contrastive learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.269022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.269022Z digest=sha256:344047234be4fb765fc94e72081b63e2977655dd30d961e01abca79e1cdc694f

Observation b4e2f324-9862-4c83-bdeb-5478d9520292 · outbound

This paper cites Ocr-free document understanding transformer.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Ocr-free document understanding transformer

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.363007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.363007Z digest=sha256:d756f9aed27d72a2c41509d0e9abd27f4f29dde7f445dfe4f2409d78a8a3d712

Observation ab8c803d-d344-4aa5-a89c-107a7c3ec915 · outbound

This paper cites Adam: A method for stochastic optimization.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Adam: A method for stochastic optimization

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.463697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.463697Z digest=sha256:0426c67b0f537b6799bfd9a3306de36f829f20732f8967e516a8c6b90f805506

Observation c89ecd3e-30f7-4298-baeb-c123b5584fa9 · outbound

This paper cites E uroparl: A parallel corpus for statistical machine translation.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content E uroparl: A parallel corpus for statistical machine translation

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.628112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.628112Z digest=sha256:e89c6c75694e744c48417ebf4a7fb9d596c14ad6ed024d3d50b9632bd524620d

Observation b48456d1-f3bd-4221-b18a-c26cb4e44827 · outbound

This paper cites Subword regularization: Improving neural network translation models with multiple subword candidates.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Subword regularization: Improving neural network translation models with multiple subword candidates

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.779807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.779807Z digest=sha256:c13fc6419130ceffa0d3d585925d77c9c677d69a7758fbc984824956e45292b4

Observation 7ba85ef0-8e0b-4cd5-bbe4-627f9a986fef · outbound

This paper cites S entence P iece: A simple and language independent subword tokenizer and detokenizer for neural text processing.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content S entence P iece: A simple and language independent subword tokenizer and detokenizer for neural text processing

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.914733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.914733Z digest=sha256:cd3d175c3665f51e5654cefbdc7968db5f69c0887ff7cd0770f4f5a6869d6512

Observation 493f913f-00d2-4540-b3bc-2b1c2c5420a3 · outbound

This paper cites P ix2 S truct: Screenshot parsing as pretraining for visual language understanding.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content P ix2 S truct: Screenshot parsing as pretraining for visual language understanding

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:38.983778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:38.983778Z digest=sha256:f56be8d754f17dbaaa9afb478accbbe8cfb41fdda99f55dcfc591c299d769208

Observation dedbb092-5bd6-4977-9bf3-ec1232f7e99f · outbound

This paper cites Trocr: transformer-based optical character recognition with pre-trained models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Trocr: transformer-based optical character recognition with pre-trained models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:39.135595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:39.135595Z digest=sha256:d77567962a6a4cabb262412017093c089ab564082cb0ea607d7b96c5ddc4f407

Observation de52aea0-b594-4c14-b241-c165b657feee · outbound

This paper cites Tokenization impacts multilingual language modeling: Assessing vocabulary allocation and overlap across languages.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Tokenization impacts multilingual language modeling: Assessing vocabulary allocation and overlap across languages

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:39.275565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:39.275565Z digest=sha256:daf3be493dfb24c17bd28f639b1d1c0180fbbe2b146b5332877a8e4d59f0e291

Observation ac2178cf-71ee-42c3-82be-3dd35c4887e3 · outbound

This paper cites Character-aware models improve visual text rendering.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Character-aware models improve visual text rendering

Reference 27

Resolution
verified exact
doi, observed 2026-08-01T21:23:49.478668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-01T21:22:39.449884Z digest=sha256:f8663592dfc36a9280a9af65e2da38e5cbdb2cee2bbfafb91808e6f2b7b9faa3

Observation 1de230ae-c90c-4808-848b-05ba9dfb49e1 · outbound

This paper cites Glyph-byt5: A customized text encoder for accurate visual text rendering.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Glyph-byt5: A customized text encoder for accurate visual text rendering

Reference 28

Resolution
verified exact
doi, observed 2026-08-01T21:23:49.345965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-01T21:22:39.605288Z digest=sha256:90b7aaf523799d8eeb40a828eaf4a279915dcd577ca966ade3bdcd6843acf055

Observation cae33c4a-309e-4b18-8237-aa5ce9036c2f · outbound

This paper cites Decoupled weight decay regularization.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Decoupled weight decay regularization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:39.790370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:39.790370Z digest=sha256:2576e06b2a49c2b4fc5178455b3d1b7d8c17b6a1541b1cf984c996ebcc2fa6b8

Observation 7152fbb3-9129-4a9b-971d-25084ce08c86 · outbound

This paper cites Beyond fertility: STRR as a metric for multilingual tokenization evaluation.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Beyond fertility: STRR as a metric for multilingual tokenization evaluation

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:39.929199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:39.929199Z digest=sha256:bc141ebe6ead544737ce56d55723bd782492718ed996c4cd05174bf044bf0cba

Observation 4fac4be3-b216-46be-81f3-7fa56dff9d7a · outbound

This paper cites Hierarchical autoregressive transformers: Combining byte- and word-level processing for robust, adaptable language models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Hierarchical autoregressive transformers: Combining byte- and word-level processing for robust, adaptable language models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.053631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.053631Z digest=sha256:8d9346041549afa6b2b7148c5c28cd8aa085ba068a139d4695ccd991834182ea

Observation 664c8bad-32ff-47e9-ab49-1e76f9ff9703 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.189860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.189860Z digest=sha256:d7779ee1584a06fd2eb36fff0fc1aef10f7029148efeaf59a0467c18e263753c

Observation aefc44b6-41f4-4a9f-b909-64291cf33feb · outbound

This paper cites Byte latent transformer: Patches scale better than tokens.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Byte latent transformer: Patches scale better than tokens

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.322457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.322457Z digest=sha256:d5db700a2ba132898001778a9e9ac0d67e2df92371c5ee5e227f89eae044d2ef

Observation 46aa5a51-013f-4128-b092-16f4a6a767c0 · outbound

This paper cites Language model tokenizers introduce unfairness between languages.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Language model tokenizers introduce unfairness between languages

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.485573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.485573Z digest=sha256:f701cecb819557d513a980449c7248f71d61a4aaf4e9c13b5956ec9e4433d5aa

Observation 1990d8bf-9dc6-4202-9278-839befd4f4fe · outbound

This paper cites Language Models are Unsupervised Multitask Learners , 2019.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Language Models are Unsupervised Multitask Learners , 2019

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.573849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.573849Z digest=sha256:06882afbc0cb919a8e20edfd78f54ef7bb15837389389fdb1a90a0856c730830

Observation 6e76818f-677f-4f88-aa77-f5dbdd3cfe6b · outbound

This paper cites Learning transferable visual models from natural language supervision.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Learning transferable visual models from natural language supervision

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.652257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.652257Z digest=sha256:7461c68fe5f45c014974acd4f0d018b0a1c898ba3896bad1587028be7f7701c7

Observation 4122f4c8-1c4b-47c0-93ea-8717ca75631b · outbound

This paper cites When every token counts: Optimal segmentation for low-resource language models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content When every token counts: Optimal segmentation for low-resource language models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.764452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.764452Z digest=sha256:23d1b736af5d7343a0d6b67f16c2d1845e445a4ef6e62e6e2f63ad5d78409754

Observation fbd82c04-164b-4c27-a563-ae7bf0763a07 · outbound

This paper cites Making monolingual sentence embeddings multilingual using knowledge distillation.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Making monolingual sentence embeddings multilingual using knowledge distillation

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.866372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.866372Z digest=sha256:d7cb29adc2d4a3c425b8564e3cb27e7059e673c85b28580c1f1e95407b8a0ac3

Observation 708f2e87-c438-477a-a744-7abc754436c6 · outbound

This paper cites How good is your tokenizer? on the monolingual performance of multilingual language models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content How good is your tokenizer? on the monolingual performance of multilingual language models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:40.965157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:40.965157Z digest=sha256:df14a0550357f09ade11d11beb95e4bc9ec991f1271ae84c5aea8ee95ee6daed

Observation e93f06ce-3a4d-43f8-893d-0a810a01ee8b · outbound

This paper cites Lotz, Emanuele Bugliarello, Elizabeth Salesky, Miryam de Lhoneux, and Desmond Elliott.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Lotz, Emanuele Bugliarello, Elizabeth Salesky, Miryam de Lhoneux, and Desmond Elliott

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.052936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.052936Z digest=sha256:2fe78f0d8af6785612bfbf4e41b6599cd4603846748c6301fd1aa001f6cc4bdf

Observation e818e859-dcd0-4289-8205-6ec2795292d9 · outbound

This paper cites Robust open-vocabulary translation from visual text representations.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Robust open-vocabulary translation from visual text representations

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.122188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.122188Z digest=sha256:531bfc50b3fd244c933d7839e08cdf8255c8ebdf51f9611f2cdd5c458a5984f0

Observation 1365610e-2bd3-485b-a54e-c061e205b892 · outbound

This paper cites Neural machine translation of rare words with subword units.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Neural machine translation of rare words with subword units

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.193745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.193745Z digest=sha256:b948616480331a5a7d2e3b347fc313772fe233f6a9390cb61e439a81c6e446d5

Observation 3e0a7752-7c68-436e-908b-176d6a0ff37c · outbound

This paper cites Dropout: A simple way to prevent neural networks from overfitting.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Dropout: A simple way to prevent neural networks from overfitting

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.268227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.268227Z digest=sha256:e0cdb0bb459d66655f7afed3ebe29f73db6a901545f16e270060bb40e1da5483

Observation c9fffd0b-2f2a-4b62-9e69-cd84c0bacdff · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Roformer: Enhanced transformer with rotary position embedding

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.340888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.340888Z digest=sha256:517e642ca06614932974e99d936d02cfab551f6d1ce582641993ddd8d03aa85d

Observation acfe7422-013c-4cc1-9c27-d9272676e2dc · outbound

This paper cites Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, and Donald Metzler.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, and Donald Metzler

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.408834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.408834Z digest=sha256:8fd063e617399da42a2b082e1ae91652955f6d8fda0b4b9d6db8ae1133644cd9

Observation 29f73f0c-4deb-4a60-9613-bf83de9ab48c · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Representation Learning with Contrastive Predictive Coding

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.479804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.479804Z digest=sha256:6b9643776fcf5190b5733fcbff36343557e3d72422052201949f4b0eb3ec1b70

Observation 617299bd-5135-4124-9555-716636fe1476 · outbound

This paper cites Attention is all you need.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Attention is all you need

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.567529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.567529Z digest=sha256:53973a4111a87bf79d547120edc1fdf2995d8aa7a6934176a64ae53c6d778a18

Observation 11952a5d-fd7e-4996-987c-c84521da349f · outbound

This paper cites Error patterns in historical ocr: A comparative analysis of trocr and a vision-language model, 2026.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Error patterns in historical ocr: A comparative analysis of trocr and a vision-language model, 2026

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.668392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.668392Z digest=sha256:a3dc54f19b62b026fc434b2e2fd1d3322d7d567a5a0c04eb5746fc0a57cda3bb

Observation 2b1bc23a-7e06-44ad-ad71-17b0b215c266 · outbound

This paper cites an unresolved cited work.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Unresolved cited work

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.767793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.767793Z digest=sha256:f09a4eea3f27f1111419d133caa9100a812a16fe64caebd440cb018886c77fd2

Observation 0f8bf97d-6fe7-460e-892e-9b1b9dbaa99f · outbound

This paper cites The Holy Bible international: Text and audio bibles.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content The Holy Bible international: Text and audio bibles

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.836533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.836533Z digest=sha256:06e62d077178326508f423c6e2f2c5846ad88329092f62344e4787678d36dfbe

Observation 708009d9-68af-40ca-b455-d605ac09cc3d · outbound

This paper cites On layer normalization in the transformer architecture.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content On layer normalization in the transformer architecture

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.913579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.913579Z digest=sha256:bbeb81c001e762b619bbda45308c0fd3eea71c9aa2d54577a4fdfc74262c89a0

Observation 478fbc81-65c8-4675-8d82-87983efe1de8 · outbound

This paper cites B y T 5: Towards a token-free future with pre-trained byte-to-byte models.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content B y T 5: Towards a token-free future with pre-trained byte-to-byte models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:41.984457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:41.984457Z digest=sha256:da470728c67f9f0bf96743458be897b4c354a2a7ce48ce0fd8936c3015a6463d

Observation 298aecb2-20e4-4f5e-b979-36255ca1d114 · outbound

This paper cites Qwen3 Technical Report.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Qwen3 Technical Report

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.054784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.054784Z digest=sha256:42c7200fb2cc11f76b59229ffc77b8c7e2a282bfb86a3892b83d7f7d24bfc21f

Observation 53396375-1549-4551-9fa7-5bac8d3560ea · outbound

This paper cites Megabyte: Predicting million-byte sequences with multiscale transformers.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Megabyte: Predicting million-byte sequences with multiscale transformers

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.124243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.124243Z digest=sha256:3f127f7219ade680453a08e029adc597b79f366455876dfc0555ff78c3787bc5

Observation 2c442f75-bb28-49ac-a844-8fb21ebba32d · outbound

This paper cites Big bird: Transformers for longer sequences.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Big bird: Transformers for longer sequences

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.199436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.199436Z digest=sha256:ce6f306a33e81f36ebcdfb0ef977b17d1204e5a08f34f5de6174a2698c27b703

Observation 072e5444-8eeb-43ff-90a2-3b30afa727cb · outbound

This paper cites Root mean square layer normalization.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content Root mean square layer normalization

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.285016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.285016Z digest=sha256:fb314aff8769ce631473404ffc5e3bd449bd43f699dc59d9baf159a1659e2dd8

Observation 5b5aa7f9-d62b-4d8d-8579-5c62997a6ba5 · outbound

This paper cites MIRACL : A multilingual retrieval dataset covering 18 diverse languages.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content MIRACL : A multilingual retrieval dataset covering 18 diverse languages

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.357323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.357323Z digest=sha256:fa1d9d76a79ef2d3379efbdab4509fe277422ed4f5b31656026ab280fed16bfb

Observation d1798f42-01cd-43cb-938c-cf700bd193e7 · outbound

This paper cites The U nited N ations parallel corpus v1.0.

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content The U nited N ations parallel corpus v1.0

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-01T21:22:42.436125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T21:22:42.436125Z digest=sha256:1d1ea35822b91ad6a737236e11de7825116a859f90e4c8cf3eca077e004f62d9

Pith citing papers

No inbound Pith citation observations are available.