Paper Citation Record · LEDGER

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images

As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2607.21672.

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

pith.paper-citation-record.v1
2607.21672 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T08:35:43.632942Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

14 of 14 outbound references displayed

verified exact0
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a6061faa-77c9-49a8-99ef-8c60e80593b8 · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:41.706392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de1d7fba-23a8-4471-8cb9-b49677e9a0b0 · outbound

This paper cites Prompt Cache: Modular Attention Reuse for Low-Latency Inference.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Prompt Cache: Modular Attention Reuse for Low-Latency Inference

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:41.852997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6811246-9061-4a4c-aa18-4c1f80076eb0 · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.055729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 493cb634-2ece-4ed7-b632-39ab34f88e07 · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.191767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8533fd70-5f9f-438a-9e3e-d0b5c98c0480 · outbound

This paper cites OCR-free Document Understanding Transformer.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images OCR-free Document Understanding Transformer

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.265776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab67878-b9e3-4eed-a113-05c852b32d5c · outbound

This paper cites Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.464663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 001ff132-0ef9-4c56-9d72-a048ff4c5743 · outbound

This paper cites Text Rendering Strategies for Pixel Language Models.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Text Rendering Strategies for Pixel Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.587883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d612f2a-4bfd-4cfb-a03b-d5c98c5ad993 · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.763305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e45b288-482f-4c22-afb0-73dedb16f7c9 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Code Llama: Open Foundation Models for Code

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:42.923397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8255edb0-8a6d-4225-a18d-cf2733fbd65f · outbound

This paper cites Language Modelling with Pixels.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Language Modelling with Pixels

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:43.157716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a44ddb6-6c7b-4063-b585-ecbe16140621 · outbound

This paper cites CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:43.324219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e053c1-78b9-42a6-a693-e971f03030ae · outbound

This paper cites DeepSeek-OCR: Contexts Optical Compression.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images DeepSeek-OCR: Contexts Optical Compression

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:43.419829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8197c15-cb8d-4b06-b73c-4a06e12f8e4e · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:43.508165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 005b82df-01f1-4ccc-b384-4633d94391d3 · outbound

This paper cites an unresolved cited work.

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:43.632942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.