Paper Citation Record · LEDGER

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading

As of 9 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2608.05675.

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

pith.paper-citation-record.v1
2608.05675 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T04:25:12.769616Z

measured 35 of 35 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

35 of 35 outbound references displayed

verified exact5
verified fuzzy14
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 971b53fa-e0a4-4ced-b1f8-cb5b518603c3 · outbound

This paper cites Consistency and uncertainty: Identifying unreliable responses from black- box vision-language models for selective visual question answering.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Consistency and uncertainty: Identifying unreliable responses from black- box vision-language models for selective visual question answering

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.784020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cc51ce31-1a64-48ad-b61c-e8165ea315fd · outbound

This paper cites Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-08T04:25:13.330657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 73ce549a-78a7-4730-8d21-8207fd2e83b3 · outbound

This paper cites Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.541452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd44f61e-f513-429b-8191-9d974e6d9ef7 · outbound

This paper cites When does consensus mean correctness? measuring the agreement–accuracy coupling with semantics-preserving re-rendering, 2026.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading When does consensus mean correctness? measuring the agreement–accuracy coupling with semantics-preserving re-rendering, 2026

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.773517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c015198a-6c34-4120-8719-3315e8f7b1d2 · outbound

This paper cites VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.547977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 324b48c5-fe9a-4e47-8523-173af80dcf8c · outbound

This paper cites MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.551331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a98f18-bbb6-4304-8e56-85abeed5adde · outbound

This paper cites Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-08T04:25:13.279652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 97d8b933-70ac-4a74-818d-8ea5d4d00107 · outbound

This paper cites Minimum Complete MR Subsets under Semantic-Mutation Fault Models: A Support-Set Domination Boundary.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Minimum Complete MR Subsets under Semantic-Mutation Fault Models: A Support-Set Domination Boundary

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-08T04:25:13.239424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 66a2c1ef-12b7-4253-af09-998904e382f7 · outbound

This paper cites Learning more from less: Exploiting counterfactuals for data-efficient chart understanding.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Learning more from less: Exploiting counterfactuals for data-efficient chart understanding

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.762207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 25459cbd-7207-4ae9-86e9-78436ad06543 · outbound

This paper cites What if the tv was off? examining counterfactual reasoning abilities of multi-modal language models.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading What if the tv was off? examining counterfactual reasoning abilities of multi-modal language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.750607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e0b2120f-e9c2-492e-b222-eb0151a43b02 · outbound

This paper cites Pixels versus priors: Controlling knowledge priors in vision-language models through visual counterfacts.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Pixels versus priors: Controlling knowledge priors in vision-language models through visual counterfacts

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.668760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc4babbd-4507-46ec-b34d-27401892eb7a · outbound

This paper cites Unraveling the truth: Do vlms really understand charts? a deep dive into consistency and robustness,.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Unraveling the truth: Do vlms really understand charts? a deep dive into consistency and robustness,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.575602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 21ca5df7-5329-4e2c-a516-5ab910fdb6f3 · outbound

This paper cites Losing the plot: How vlm responses degrade on imperfect charts.arXiv preprint arXiv:2509.18425, 2025.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Losing the plot: How vlm responses degrade on imperfect charts.arXiv preprint arXiv:2509.18425, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.673318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791fe285-59f5-40d7-bf0b-5a0738bcd07d · outbound

This paper cites Chart-rvr: Re- inforcement learning with verifiable rewards for explainable chart reasoning, 2025.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Chart-rvr: Re- inforcement learning with verifiable rewards for explainable chart reasoning, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.690593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d0fe238-aa48-4677-b763-652e34dbbf98 · outbound

This paper cites On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.703555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1fe272f-0362-4cb3-8b22-4185cc153a53 · outbound

This paper cites Metamorphic testing of large language models for natural language processing.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Metamorphic testing of large language models for natural language processing

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.481362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bbdfc398-db25-4a17-8aae-bd43f593b96e · outbound

This paper cites Test Adequacy for Metamorphic Testing: Criteria, Measurement, and Implication.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Test Adequacy for Metamorphic Testing: Criteria, Measurement, and Implication

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-08T04:25:13.037554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d839a4fb-3533-4606-a0ad-d473194fc118 · outbound

This paper cites Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.419245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c156a134-ba06-4c34-8457-f1f578776d30 · outbound

This paper cites Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.719335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 288fa25d-f424-4d9e-8736-7fdd09290a39 · outbound

This paper cites Charthal: A fine- grained framework evaluating hallucination of large vision language models in chart understanding,.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Charthal: A fine- grained framework evaluating hallucination of large vision language models in chart understanding,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.403827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0beb59da-f21e-4b11-acd1-fedaf983a845 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.729933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80dbaa5c-34a5-414f-a2ff-12245f7791a2 · outbound

This paper cites VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.733496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ec0f49-fd64-4c2f-853a-cedc6c43b64c · outbound

This paper cites On the foundations of noise-free selective classification.Journal of Machine Learning Research, 11(5), 2010.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading On the foundations of noise-free selective classification.Journal of Machine Learning Research, 11(5), 2010

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.737324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a5cb1f1-4245-419f-ab48-aa51230bddd9 · outbound

This paper cites On calibration of modern neural networks.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading On calibration of modern neural networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.740674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96e6808-c678-4655-a9c2-6e310b502511 · outbound

This paper cites selective prediction.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading selective prediction

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.383905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 561772f1-a781-49fb-ba9a-a164f08e8086 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.747454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06608525-9f3c-420f-9eab-c390fb9956cf · outbound

This paper cites Chart-coca: Self-improving chart understanding of vision lms via code-driven synthesis and candidate-conditioned answering, 2025.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Chart-coca: Self-improving chart understanding of vision lms via code-driven synthesis and candidate-conditioned answering, 2025

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.375575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eed7e0c9-dea0-4734-a036-057f6814f165 · outbound

This paper cites Qwen2.5-VL Technical Report.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Qwen2.5-VL Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.753983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ca3d88e-1ea3-4011-b591-1e95570a0345 · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101, 2024.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.757329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf2aeedb-1b36-4ff9-a3b8-13112e82a264 · outbound

This paper cites Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.760192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e82498-249a-4472-bca4-68bf66e21834 · outbound

This paper cites Chartqa: A benchmark for question answering about charts with visual and logical reasoning.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Chartqa: A benchmark for question answering about charts with visual and logical reasoning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.360893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f284bd14-6ffe-4f7e-8254-89a565d70b7d · outbound

This paper cites Testing and validating machine learning classifiers by metamorphic testing.Journal of Systems and Software, 84(4):544–558, 2011.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Testing and validating machine learning classifiers by metamorphic testing.Journal of Systems and Software, 84(4):544–558, 2011

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.350741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9f93cdf4-c08d-46b3-9509-6c13dbbcfb58 · outbound

This paper cites how many countries have the same value.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading how many countries have the same value

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:25:13.340967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fd5c90c4-5917-4c83-b8a6-52ef127e9843 · outbound

This paper cites Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T04:25:12.655194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fb2a6f-3443-4c2c-9182-e9b75c64a326 · outbound

This paper cites an unresolved cited work.

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading Unresolved cited work

Reference 2025

Resolution: verified exact; raw_fallback, observed 2026-08-08T04:25:12.945043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.