Paper Citation Record · LEDGER

From Language Models over Tokens to Language Models over Characters

As of 21 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 6 inbound Pith citation observations for arXiv:2412.03719.

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

pith.paper-citation-record.v1
2412.03719 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T22:18:15.414687Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:29:53.362352Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-19T09:53:02.085184Z

Reference resolution

33 of 33 outbound references displayed

verified exact2
verified fuzzy8
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6fca5c5f-1604-4f17-8a64-15a9b2b1de59 · outbound

This paper cites write newline.

From Language Models over Tokens to Language Models over Characters write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.322841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e02109a3-4de1-43ea-8a02-7cb4b779c669 · outbound

This paper cites Floyd, Vaughan R.

From Language Models over Tokens to Language Models over Characters Floyd, Vaughan R

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.326982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb6ece95-7814-45fb-97ec-e7900cfd98c1 · outbound

This paper cites You should evaluate your language model on marginal likelihood over tokenisations.

From Language Models over Tokens to Language Models over Characters You should evaluate your language model on marginal likelihood over tokenisations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.329920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a9c31e-eaeb-4e09-b91f-9297b865cfd3 · outbound

This paper cites Should you marginalize over possible tokenizations? In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2023.

From Language Models over Tokens to Language Models over Characters Should you marginalize over possible tokenizations? In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2023

Reference 4

Resolution: verified exact; doi, observed 2026-08-11T22:18:15.472701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ede86109-bfc4-4a8c-904c-99d79cf3503a · outbound

This paper cites Formal Aspects of Language Modeling.

From Language Models over Tokens to Language Models over Characters Formal Aspects of Language Modeling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.336243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16040ac6-da22-48ab-b786-90752bf45547 · outbound

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

From Language Models over Tokens to Language Models over Characters BERT : Pre-training of deep bidirectional transformers for language understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.339340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd49539b-aa3a-40c4-860c-f196c3cccc8a · outbound

This paper cites The Llama 3 Herd of Models.

From Language Models over Tokens to Language Models over Characters The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.343052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b52fcac5-c9f8-4e8d-9f13-91c3ab178c26 · outbound

This paper cites A new algorithm for data compression.

From Language Models over Tokens to Language Models over Characters A new algorithm for data compression

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.346099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a6e600-7216-4a37-a91a-44db12175190 · outbound

This paper cites The Foundations of Tokenization: Statistical and Computational Concerns.

From Language Models over Tokens to Language Models over Characters The Foundations of Tokenization: Statistical and Computational Concerns

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.348564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb91da1-d97f-421b-bfe1-48894ab0765a · outbound

This paper cites Grammar-constrained decoding for structured NLP tasks without finetuning.

From Language Models over Tokens to Language Models over Characters Grammar-constrained decoding for structured NLP tasks without finetuning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.887700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 532835b6-6b64-45b0-8933-c0fdaa510a98 · outbound

This paper cites On the proper treatment of tokenization in psycholinguistics.

From Language Models over Tokens to Language Models over Characters On the proper treatment of tokenization in psycholinguistics

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.880059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 79224c68-6cfb-43b3-a464-c8c2c8715f8f · outbound

This paper cites Implementing functional languages with fast equality, sets and maps: An exercise in hash consing.

From Language Models over Tokens to Language Models over Characters Implementing functional languages with fast equality, sets and maps: An exercise in hash consing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.872569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 614a0048-2260-43f4-a84c-480a5ba4a030 · outbound

This paper cites A probabilistic E arley parser as a psycholinguistic model.

From Language Models over Tokens to Language Models over Characters A probabilistic E arley parser as a psycholinguistic model

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.864682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f4e3ae24-f231-4264-bb04-87c1d38b490f · outbound

This paper cites Automata-based constraints for language model decoding.

From Language Models over Tokens to Language Models over Characters Automata-based constraints for language model decoding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.362751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc5fdc5f-ce0c-489b-9516-bb3e2d78defc · outbound

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

From Language Models over Tokens to Language Models over Characters Subword regularization: Improving neural network translation models with multiple subword candidates

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.365214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e4efcc-58b9-4337-bb83-1d1b5357e0e4 · outbound

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

From Language Models over Tokens to Language Models over Characters S entence P iece: A simple and language independent subword tokenizer and detokenizer for neural text processing

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.367862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ea0589-ae25-4320-927f-cccc670a4d3c · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

From Language Models over Tokens to Language Models over Characters Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.370538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41bc8f03-3b8b-42af-9899-d18645613118 · outbound

This paper cites Expectation-based syntactic comprehension.

From Language Models over Tokens to Language Models over Characters Expectation-based syntactic comprehension

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.373407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e5a7829-20a5-4eed-a283-c66fff355bd2 · outbound

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

From Language Models over Tokens to Language Models over Characters The art of prompt design: Prompt boundaries and token healing

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.375939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82418dee-1f4c-4465-a8a6-9199d035ec98 · outbound

This paper cites Guidance.

From Language Models over Tokens to Language Models over Characters Guidance

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.848315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f3b821c7-86ee-405b-aef1-1d9be74b7128 · outbound

This paper cites Recurrent neural network based language model.

From Language Models over Tokens to Language Models over Characters Recurrent neural network based language model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.381029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66fecbe2-db4a-434a-99de-96b111677111 · outbound

This paper cites Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities.

From Language Models over Tokens to Language Models over Characters Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.383587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e2e1554-dc84-41fc-8626-7bf304b77e5f · outbound

This paper cites Muckley, and Karen Ullrich.

From Language Models over Tokens to Language Models over Characters Muckley, and Karen Ullrich

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.840807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e9a13951-c116-49df-bff4-626a7bec7c0a · outbound

This paper cites How to Compute the Probability of a Word.

From Language Models over Tokens to Language Models over Characters How to Compute the Probability of a Word

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.388908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05fe6c9-8060-4772-b91c-baf953df0ccf · outbound

This paper cites Synchromesh: Reliable code generation from pre-trained language models.

From Language Models over Tokens to Language Models over Characters Synchromesh: Reliable code generation from pre-trained language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.832838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e68da3e7-3dc7-411b-be9d-abe3782ccb45 · outbound

This paper cites Language models are unsupervised multitask learners.

From Language Models over Tokens to Language Models over Characters Language models are unsupervised multitask learners

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:18:15.825127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e2fb611c-b487-42d3-ac72-814aac061e4c · outbound

This paper cites PICARD: parsing incrementally for constrained auto-regressive decoding from language models.

From Language Models over Tokens to Language Models over Characters PICARD: parsing incrementally for constrained auto-regressive decoding from language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.396908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28c1f7b-8396-4b66-a640-ca8099d93a55 · outbound

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

From Language Models over Tokens to Language Models over Characters Neural machine translation of rare words with subword units

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.400329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db14f669-d2aa-4848-8b75-dc61461e8262 · outbound

This paper cites an unresolved cited work.

From Language Models over Tokens to Language Models over Characters Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.403029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f05709-d0f2-4ac5-8830-297cb30c079a · outbound

This paper cites From feedforward to recurrent LSTM neural networks for language modeling.

From Language Models over Tokens to Language Models over Characters From feedforward to recurrent LSTM neural networks for language modeling

Reference 30

Resolution: verified exact; raw_fallback, observed 2026-08-11T22:18:15.667863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 06527b45-076a-4c6e-918f-87e912ccbb07 · outbound

This paper cites Attention Is All You Need.

From Language Models over Tokens to Language Models over Characters Attention Is All You Need

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.408041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad58d31-0587-4c36-812d-1b7baf47fe0c · outbound

This paper cites Efficient Guided Generation for Large Language Models.

From Language Models over Tokens to Language Models over Characters Efficient Guided Generation for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.410786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff67263d-0c97-43b2-a07b-ea17c506e86a · outbound

This paper cites \ T ransformers: S tate-of-the-art natural language processing.

From Language Models over Tokens to Language Models over Characters \ T ransformers: S tate-of-the-art natural language processing

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T22:18:15.414687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9b1df227-a42b-4f5f-8268-758708d528c7 · inbound

The Impact of Token Granularity on the Predictive Power of Language Model Surprisal cites this paper.

The Impact of Token Granularity on the Predictive Power of Language Model Surprisal From Language Models over Tokens to Language Models over Characters

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T14:30:05.141552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0982b19-e0bb-4e0d-a9b6-360f351b2ac9 · inbound

Causal Estimation of Tokenisation Bias cites this paper.

Causal Estimation of Tokenisation Bias From Language Models over Tokens to Language Models over Characters

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:44.643052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a9b1b6e-9900-4adc-8969-3bc3476d0ede · inbound

The Harmonic Structure of Information Contours cites this paper.

The Harmonic Structure of Information Contours From Language Models over Tokens to Language Models over Characters

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T10:58:47.836882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adfa4472-f90c-49e5-bb8f-8cac585f3a33 · inbound

Sampling from Your Language Model One Byte at a Time cites this paper.

Sampling from Your Language Model One Byte at a Time From Language Models over Tokens to Language Models over Characters

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-19T09:53:02.086678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ee9e9032-942b-4e24-827d-bf609c272e1d · inbound

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior cites this paper.

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior From Language Models over Tokens to Language Models over Characters

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:53.362352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44689339-ce74-4f75-92d6-f565fc68fcc1 · inbound

Language Models are not Equally Robust to Non-Canonical Tokenization across Languages cites this paper.

Language Models are not Equally Robust to Non-Canonical Tokenization across Languages From Language Models over Tokens to Language Models over Characters

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-30T19:48:50.891887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.