Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models | Paper Citation Record

Observation a5b37670-bc1b-42e1-9b35-d2fcf54fbf07 · outbound

This paper cites MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.152842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation df4ae625-4042-4327-b252-9c5c2f7e1cd0 · outbound

This paper cites Character-level language modeling with deeper self-attention.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Character-level language modeling with deeper self-attention

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.477886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d39d824f-347c-4ed5-8e2d-21940bc8b05e · outbound

This paper cites Program Synthesis with Large Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Program Synthesis with Large Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:36:29.307355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bed9bb2b-1293-40a8-904e-24184a3745c3 · outbound

This paper cites Relaxed recursive transformers: Effective parameter sharing with layer-wise lo RA.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Relaxed recursive transformers: Effective parameter sharing with layer-wise lo RA

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.446606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4ccde85b-60f6-435b-b7af-0840607b71f9 · outbound

This paper cites Mixture-of-recursions: Learning dynamic recursive depths for adaptive token-level computation.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Mixture-of-recursions: Learning dynamic recursive depths for adaptive token-level computation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.489276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eafd033d-358c-4001-8d82-9f8e21d16ff0 · outbound

This paper cites Pondernet: Learning to ponder.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Pondernet: Learning to ponder

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.318848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4282b008-a885-4b7c-ab7e-b829f150f779 · outbound

This paper cites Large Concept Models: Language Modeling in a Sentence Representation Space.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Large Concept Models: Language Modeling in a Sentence Representation Space

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.938338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17154d6a-e643-4fcb-8200-4c6b80ffbb30 · outbound

This paper cites o ppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael K Kopp, G \.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models o ppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael K Kopp, G \

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.469235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 949ad529-ec5c-48ed-a348-2fbcaac31232 · outbound

This paper cites Conditional Computation in Neural Networks for faster models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Conditional Computation in Neural Networks for faster models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:41:24.655364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0bab88ea-4fe3-4761-9724-65e1cded232b · outbound

This paper cites A neural probabilistic language model.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models A neural probabilistic language model

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.293983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fdae45e8-ae3d-465c-b256-6f2d42879c7d · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Piqa: Reasoning about physical commonsense in natural language

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.307227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a01556e-eff6-4dfc-8640-16dcbe040bbe · outbound

This paper cites Language models are few-shot learners.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Language models are few-shot learners

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.389613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae5aef9f-eea5-4b88-acf7-747a27194c85 · outbound

This paper cites Lee, Deming Chen, and Tri Dao.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Lee, Deming Chen, and Tri Dao

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.396132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2ef76be8-a813-47ca-819b-d8b1dd0aa5bf · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Evaluating Large Language Models Trained on Code

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:36:28.849357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6e6d25bf-49f9-4dfa-9e76-5b7fb45eac1b · outbound

This paper cites Bridging the Gap for Tokenizer-Free Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Bridging the Gap for Tokenizer-Free Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.262266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e9e5463b-26bd-4b2f-872b-01021a4a18c8 · outbound

This paper cites Hierarchical multiscale recurrent neural networks.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Hierarchical multiscale recurrent neural networks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.310954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d9b151f9-1c12-4ae0-9a15-1b3eafd9a618 · outbound

This paper cites B ool Q : Exploring the surprising difficulty of natural yes/no questions.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models B ool Q : Exploring the surprising difficulty of natural yes/no questions

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.392949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b01e1819-f1a9-48f4-9c02-ada5a17b18e3 · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Clark, Dan Garrette, Iulia Turc, and John Wieting

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.507672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3b7a85e4-e7d7-4162-87c2-e766bcdbc3c0 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:36:29.139734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eb5807a7-a5f9-4d7a-a453-3ad7ae5517fa · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T17:54:14.284800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ade6638-ef35-4795-83e4-6b3a6dcee219 · outbound

This paper cites Mo EUT : Mixture-of-experts universal transformers.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Mo EUT : Mixture-of-experts universal transformers

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.458156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3fa4007d-2fa5-402c-a808-8700e9a1430f · outbound

This paper cites Getting the most out of your tokenizer for pre-training and domain adaptation.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Getting the most out of your tokenizer for pre-training and domain adaptation

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.790238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation db0c604f-3d80-454a-89f7-4c87eb1f8c52 · outbound

This paper cites Funnel-transformer: Filtering out sequential redundancy for efficient language processing.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Funnel-transformer: Filtering out sequential redundancy for efficient language processing

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.298623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 104d1fa3-97d4-4013-825f-852973f78e50 · outbound

This paper cites Transformers are SSM s: Generalized models and efficient algorithms through structured state space duality.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Transformers are SSM s: Generalized models and efficient algorithms through structured state space duality

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.442994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9484715a-1b7d-40bb-b06d-e411caf3904a · outbound

This paper cites Universal transformers.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Universal transformers

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.402438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e0e1c019-e0d4-4742-88b2-d410cf5cdd24 · outbound

This paper cites BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 26

Resolution: verified exact; doi, observed 2026-05-12T04:06:19.682237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b19ad1c0-9ce3-4c20-a8d0-282dd964c99d · outbound

This paper cites A new algorithm for data compression.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models A new algorithm for data compression

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.379818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9138ff7f-3b7f-41bf-8e83-4b0a7ea88ed9 · outbound

This paper cites Improving Language Understanding from Screenshots.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Improving Language Understanding from Screenshots

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.128760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3529846b-e939-45e3-a587-7da592bd7876 · outbound

This paper cites Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-12T15:39:41.804715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8741a2a4-54c7-4e18-a16b-c2529ea277f1 · outbound

This paper cites Lee, and Dimitris Papailiopoulos.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Lee, and Dimitris Papailiopoulos

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.484868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a3ebf462-cd4d-47b4-ad71-f1d60bfd6ba2 · outbound

This paper cites Better & Faster Large Language Models via Multi-token Prediction.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Better & Faster Large Language Models via Multi-token Prediction

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:26:09.884823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 533c8037-8125-47ae-bd69-a95e6ce28393 · outbound

This paper cites MANT a: Efficient gradient-based tokenization for end-to-end robust language modeling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MANT a: Efficient gradient-based tokenization for end-to-end robust language modeling

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.461769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9a10a360-d88d-46e3-b34f-e83cc777fd41 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:36:29.003298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1d1635a5-75c3-4166-8d12-393f709b1fec · outbound

This paper cites Think before you speak: Training language models with pause tokens.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Think before you speak: Training language models with pause tokens

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.376239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 448c6cfa-953e-4975-a68c-a7094cba5aa4 · outbound

This paper cites Generating Sequences With Recurrent Neural Networks.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Generating Sequences With Recurrent Neural Networks

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.887084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a3b8d8a6-1cfa-49c3-8122-20fda793484b · outbound

This paper cites Adaptive Computation Time for Recurrent Neural Networks.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Adaptive Computation Time for Recurrent Neural Networks

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-12T11:53:22.734695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c93042f3-5792-45b5-bacd-e505f59884de · outbound

This paper cites Fast and expressive multi-token prediction with probabilistic circuits.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Fast and expressive multi-token prediction with probabilistic circuits

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.512028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation df9c3301-d60b-4170-9348-944cce3b88c7 · outbound

This paper cites Mamba: Linear-time sequence modeling with selective state spaces.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Mamba: Linear-time sequence modeling with selective state spaces

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.434981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e179736f-a2fd-408d-afde-1ea02f97e1af · outbound

This paper cites OLMES: A Standard for Language Model Evaluations.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models OLMES: A Standard for Language Model Evaluations

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.120033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52d0423a-5349-463c-b03d-a209ee79f5e3 · outbound

This paper cites DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking

Reference 40

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T06:36:29.240841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bd8a292b-ab5b-435c-970d-6f08198a24d0 · outbound

This paper cites General-purpose, long-context autoregressive modeling with perceiver AR.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models General-purpose, long-context autoregressive modeling with perceiver AR

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.428019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0d9e771a-d6fa-4a48-88ec-1e9de7d0b470 · outbound

This paper cites Measuring massive multitask language understanding.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Measuring massive multitask language understanding

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.420285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6fb07288-5514-4f0a-ab1c-cae81b06a61c · outbound

This paper cites Block transformer: Global-to-local language modeling for fast inference.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Block transformer: Global-to-local language modeling for fast inference

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.438923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 763c9027-4771-4aaa-9e7a-596e99e52afd · outbound

This paper cites Deep networks with stochastic depth.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Deep networks with stochastic depth

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.416367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 29771bf6-6e85-4dd7-b0a8-9a157412cf50 · outbound

This paper cites Conceptmoe: Adaptive token-to-concept compression for implicit compute allocation.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Conceptmoe: Adaptive token-to-concept compression for implicit compute allocation

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.009644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c19a60f8-b258-42c8-85ac-9e512f693668 · outbound

This paper cites Character-level language modeling with hierarchical recurrent neural networks.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Character-level language modeling with hierarchical recurrent neural networks

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.281143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c9d4a8af-d64c-413b-9b18-497755608a41 · outbound

This paper cites Dynamic Chunking for End-to-End Hierarchical Sequence Modeling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:28.977825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2fa510aa-69a7-4e8d-bc35-d13d9db76557 · outbound

This paper cites Perceiver IO: A General Architecture for Structured Inputs & Outputs.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Perceiver IO: A General Architecture for Structured Inputs & Outputs

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:47:14.368858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 32ec8fda-688a-48da-a1da-2688492f6782 · outbound

This paper cites Perceiver: General perception with iterative attention.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Perceiver: General perception with iterative attention

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.383706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 303385c4-0d43-4ac6-b8f8-3d9d6249d87c · outbound

This paper cites `` low-resource '' text classification: A parameter-free classification method with compressors.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models `` low-resource '' text classification: A parameter-free classification method with compressors

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.343094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b180b5a6-dc70-4904-b5e7-e5b1062322d6 · outbound

This paper cites MrT5: Dynamic Token Merging for Efficient Byte-level Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.928013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation abffccac-c31b-4d9e-902c-40b6ea87487d · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Subword regularization: Improving neural network translation models with multiple subword candidates

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.353721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3d2df5aa-93d6-40e6-b645-f69dba7fb476 · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models S entence P iece: A simple and language independent subword tokenizer and detokenizer for neural text processing

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.285555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e563b4f-ee86-416c-bfb6-345a22a3786a · outbound

This paper cites Mamba-3: Improved sequence modeling using state space principles.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Mamba-3: Improved sequence modeling using state space principles

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.399400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7861d0da-8c14-4247-a758-834f7c2ff845 · outbound

This paper cites Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.075646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f26fe72-8ceb-49ad-9377-9faedc558799 · outbound

This paper cites Training LLMs over Neurally Compressed Text.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Training LLMs over Neurally Compressed Text

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:28.952129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1d5eba93-1f43-4c78-9e57-d6d325bc3670 · outbound

This paper cites DataComp-LM: In search of the next generation of training sets for language models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models DataComp-LM: In search of the next generation of training sets for language models

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:58:17.761776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9699f24d-0927-420a-a535-75180591fe3d · outbound

This paper cites MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:28.968337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b91d14af-756d-4463-bb37-1c242002f7aa · outbound

This paper cites Smith, and Yejin Choi.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Smith, and Yejin Choi

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.277059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 29744b20-b3d1-42b1-ae19-f3cb4d3bef1f · outbound

This paper cites Decoupled weight decay regularization.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Decoupled weight decay regularization

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.350401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b20de449-b3d5-4d72-8919-2c90cc6c6d94 · outbound

This paper cites Text rendering strategies for pixel language models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Text rendering strategies for pixel language models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.405883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d928f038-711e-4ed1-b0cd-7249749f9f33 · outbound

This paper cites Starcoder 2 and the stack v2: The next generation.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Starcoder 2 and the stack v2: The next generation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.500264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4ecb3e0d-da08-4a44-86df-edf53afc970e · outbound

This paper cites The art of prompt design: Prompt boundaries and token healing.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models The art of prompt design: Prompt boundaries and token healing

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.503996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 319fe42b-e335-4e72-b036-6550ee642834 · outbound

This paper cites Guidance.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Guidance

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.496641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 323195a1-9d0d-4ac9-9322-5e67180d5615 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.328161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b6b19845-325a-49f3-846d-2831fa844e7b · outbound

This paper cites Minixhofer, T.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Minixhofer, T

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.206351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f2e5a378-ef06-4093-8ff7-0a407bcee020 · outbound

This paper cites Hierarchical transformers are more efficient language models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Hierarchical transformers are more efficient language models

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.450872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6c428cfe-862d-4929-a668-421fed0f9a22 · outbound

This paper cites Efficient transformers with dynamic token pooling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Efficient transformers with dynamic token pooling

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.315000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e2b73c34-d868-473f-b1c9-35637e98a049 · outbound

This paper cites Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.879364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2a0d88a2-9ad4-4115-af90-bdca6c3c9326 · outbound

This paper cites GPT-4 Technical Report.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models GPT-4 Technical Report

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:36:28.914004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cd7fb21d-0d92-40c9-b092-663f8dacf775 · outbound

This paper cites FLEXITOKENS: Flexible Tokenization for Evolving Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models FLEXITOKENS: Flexible Tokenization for Evolving Language Models

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-14T02:56:13.953344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 53a577bf-b816-4a10-ad63-442b74c0309b · outbound

This paper cites Byte Latent Transformer: Patches Scale Better Than Tokens.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Byte Latent Transformer: Patches Scale Better Than Tokens

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.184901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 626da5f5-2f83-4268-93c0-77ac5a6a2eaa · outbound

This paper cites Openwebmath: An open dataset of high-quality mathematical web text.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Openwebmath: An open dataset of high-quality mathematical web text

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.323155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5d331cc4-1b11-4e5f-be0f-46429cf8d53c · outbound

This paper cites Dynamic large concept models: Latent reasoning in an adaptive semantic space.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Dynamic large concept models: Latent reasoning in an adaptive semantic space

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:28.796718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ea47df25-b79d-4ca1-9240-1bf4cbffcfb2 · outbound

This paper cites Learning to Generate Reviews and Discovering Sentiment.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Learning to Generate Reviews and Discovering Sentiment

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.039412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 73f206ef-6d41-4de0-adb0-ac5abc801272 · outbound

This paper cites an unresolved cited work.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-05-12T16:46:42.412942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04407f9a-01d5-44cf-9868-0dd310ee8d78 · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:02.305925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a776c116-46c5-412f-a994-dc32c9c80966 · outbound

This paper cites Solidgoldmagikarp (plus, prompt generation).

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Solidgoldmagikarp (plus, prompt generation)

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.454477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e7f05fa1-038f-42ef-82d5-bf77bda3a08f · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Lotz, Emanuele Bugliarello, Elizabeth Salesky, Miryam de Lhoneux, and Desmond Elliott

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.465256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 75c4f69a-aa95-4c86-be27-ff4bfa0b4f73 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Winogrande: An adversarial winograd schema challenge at scale

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.368815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9c91c57b-26cb-46b0-b7b0-7aea5313010c · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Robust open-vocabulary translation from visual text representations

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.357496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1358df84-fcff-433a-8038-2887c466d418 · outbound

This paper cites Japanese and korean voice search.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Japanese and korean voice search

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.339496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0cae3c0e-7e90-4dea-9d85-9c8524f753b2 · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Neural machine translation of rare words with subword units

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.424027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9b5ee4b2-cd9a-4ea0-b7ab-431894f91dc0 · outbound

This paper cites SpaceByte: Towards Deleting Tokenization from Large Language Modeling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models SpaceByte: Towards Deleting Tokenization from Large Language Modeling

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.090174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cb630b05-c1e7-4b16-8bd7-fa16816d1380 · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Blockwise parallel decoding for deep autoregressive models

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.290011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4662c9dc-dd95-470e-bfde-e5aed21e6f98 · outbound

This paper cites Generating text with recurrent neural networks.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Generating text with recurrent neural networks

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.361809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 818ac257-47a3-4845-b669-46133384fa50 · outbound

This paper cites Sparse universal transformer.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Sparse universal transformer

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.431444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3fd762a8-b3b8-45ab-9edf-0c209165ee4d · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, and Donald Metzler

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.365289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b906c358-94d1-46ea-9b78-cf7d5c7a9722 · outbound

This paper cites From Bytes to Ideas: Language Modeling with Autoregressive U-Nets.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

Reference 89

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.198403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eb950473-1012-45be-9eac-ab678a94bd2e · outbound

This paper cites MambaByte: Token-free Selective State Space Model.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MambaByte: Token-free Selective State Space Model

Reference 90

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:36:29.110367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1aed69f3-a39b-4bf3-9295-2f7d1846d93f · outbound

This paper cites Parallel loop transformer for efficient test-time computation scaling.CoRR, abs/2510.24824.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Parallel loop transformer for efficient test-time computation scaling.CoRR, abs/2510.24824

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.026786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f683faf2-3189-4eec-9029-366a612255d5 · outbound

This paper cites Efficient Pretraining Length Scaling.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Efficient Pretraining Length Scaling

Reference 92

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.285778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6c881321-048e-4011-9d33-d52fbfe35ff7 · outbound

This paper cites Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-05-12T15:21:29.028955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fc9d9a3b-a53c-445e-a988-fe3fd882444f · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models B y T 5: Towards a token-free future with pre-trained byte-to-byte models

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.302910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation daccf9ec-9873-4498-94a3-b761c17004b8 · outbound

This paper cites Problematic Tokens: Tokenizer Bias in Large Language Models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Problematic Tokens: Tokenizer Bias in Large Language Models

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:36:29.172693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 77da302a-c137-4766-8f78-592c9548acb2 · outbound

This paper cites Scaling embedding layers in language models.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Scaling embedding layers in language models

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.493134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17cbaf07-d478-487a-9ddb-132efd34862c · outbound

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

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models MEGABYTE : Predicting million-byte sequences with multiscale transformers

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.346658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ddd6ee95-0fdc-4e84-9b82-880d6749e8ac · outbound

This paper cites H ella S wag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models H ella S wag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.335783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7d255cad-4e4f-4144-8e01-2a0a326d65e1 · outbound

This paper cites Ponder LM : Pretraining language models to ponder in continuous space.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Ponder LM : Pretraining language models to ponder in continuous space

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.481482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f24ce0fc-075b-4fac-b0fc-10ba1da542c1 · outbound

This paper cites Linear complexity randomized self-attention mechanism.

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models Linear complexity randomized self-attention mechanism

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T16:46:42.372163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers