Paper Citation Record · LEDGER

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

As of 7 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 1 inbound Pith citation observation for arXiv:2606.14530.

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

pith.paper-citation-record.v1
2606.14530 v3

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T11:29:00.487021Z

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T00:17:20.154713Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-08T00:24:22.511228Z

Reference resolution

10 of 10 outbound references displayed

verified exact0
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 957f63e9-bd32-40ea-9356-7593a0e3d0c4 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:59.373524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311f301d-1cf2-4add-b1bf-1075ff043cc0 · outbound

This paper cites Cor- rectness assessment of code generated by large language models using internal representations,.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Cor- rectness assessment of code generated by large language models using internal representations,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:59.475074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b53e812-2b7a-4a79-ae74-7a1899678245 · outbound

This paper cites On LLMs’ internal repre- sentation of code correctness, 2025.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation On LLMs’ internal repre- sentation of code correctness, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:59.772422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a129b3f-d303-4f21-b4ed-13a80d9b677d · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:59.889002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a39ad1-9f98-4218-8169-07a62f84ec20 · outbound

This paper cites How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T11:29:00.013874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8243db1-8a37-4690-b4d5-86bd2c7b7af9 · outbound

This paper cites Qwen3 Technical Report.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Qwen3 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T11:29:00.163285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee0a0ca2-6aa1-48a3-8331-5f2cfe8d3e7c · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T11:29:00.284133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e54cd2b-a323-4802-93b0-6c7b0eb9b41d · outbound

This paper cites Pedregosa, G.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Pedregosa, G

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T11:29:00.377680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4fa7eaa-f57f-44eb-95fa-d5e6d3b54024 · outbound

This paper cites Cawley and Nicola L.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Cawley and Nicola L

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T11:29:00.487021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3e31360-8b80-4519-ba68-4fc3cb125a7d · outbound

This paper cites Correctness Assessment of Code Generated by Large Language Models Using Internal Representations.

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation Correctness Assessment of Code Generated by Large Language Models Using Internal Representations

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:59.629957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0b3bf7c2-4298-4230-8c3a-4ce7f6f5f726 · inbound

Latent Programming Horizons in Coding Agents cites this paper.

Latent Programming Horizons in Coding Agents Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-13T02:17:38.327208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.