It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling | Paper Citation Record

Observation 6f7277ad-1bf1-4fdc-847d-541cbf4ace07 · outbound

This paper cites Aha Moment Revisited: Are.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Aha Moment Revisited: Are

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:13.768197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 50f6d7ac-01ff-4e22-9333-63beee82a290 · outbound

This paper cites Derpanis and Babak Taati and Radek Grzeszczuk , journal =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Derpanis and Babak Taati and Radek Grzeszczuk , journal =

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:13.556514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 962b721b-f52c-41f6-99e4-cb7dbd128cc4 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:13.400117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3c1e7fd0-db2c-41ca-83f2-ff74f62bc037 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:13.275568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8bbd0e32-07e5-47d2-9e65-6ca56a06c363 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling International Conference on Learning Representations (ICLR) , year =

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:13.092790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3be7c2c8-f98e-4ad3-bb59-c57f7fbf7acd · outbound

This paper cites European Conference on Computer Vision (ECCV) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling European Conference on Computer Vision (ECCV) , year =

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:12.942340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a123f559-3e96-498a-acee-f9aac17acd5c · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling International Conference on Learning Representations (ICLR) , year =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:57.961407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 633c4d71-c4a0-4f54-8482-e32d08bbfab2 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Advances in Neural Information Processing Systems (NeurIPS) , year =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:58.070485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0a7759-b850-4adc-a1a5-5d41120cc0b6 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:58.174287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6733530-9fba-40f3-9a6c-bfd88e817c13 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:58.410926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a83c213-fc7e-4c9d-b302-1baa93d9062d · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:12.776497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7d052149-d858-4fad-899d-79badcfad37f · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:12.615862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25ac64a4-07f5-4856-b7c8-e2638e5a997a · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Advances in Neural Information Processing Systems , year =

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:12.443685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8384a106-ca08-4c26-a81b-b6b0844aa1eb · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Advances in Neural Information Processing Systems , year =

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:12.291517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36615905-9a62-4ff9-a7a2-f93a47598845 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:12.086361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4647aa74-bec2-46b3-a261-2329927b4e4e · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:11.925919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 355aba8b-bec2-4a9c-80a1-c69294c8d440 · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Advances in Neural Information Processing Systems , year =

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:11.765190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e0894387-e8ec-44c3-8432-db58db886a55 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:11.561453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7fe441cc-56c6-4e4f-a82e-ad5097cc5fd5 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year=.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year=

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:11.366001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e84a1fef-c8a8-4d41-821f-c7300b0cde7d · outbound

This paper cites Breakthroughs in statistics: Methodology and distribution , pages=.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Breakthroughs in statistics: Methodology and distribution , pages=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:59.626504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7f41d6-d0d9-4bad-b4ac-9d0cb31af6da · outbound

This paper cites Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , year=.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , year=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:11.135021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 66cb5650-7fdf-4430-b510-13695374caa8 · outbound

This paper cites Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:10.974265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c6e33c1-190c-41f2-b090-2f06142eeae1 · outbound

This paper cites Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:10.835683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64fc627b-4545-4ed9-ad61-e1f5b2b79275 · outbound

This paper cites Same Answer, Different Representations: Hidden Instability in.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Same Answer, Different Representations: Hidden Instability in

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:10.707272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25b50eb7-1490-4ba0-ae10-d87e6cbea4e4 · outbound

This paper cites Probing Visual Language Priors in.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Probing Visual Language Priors in

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:10.571972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6ab907ca-c532-40df-a85d-e480a2d8f6b0 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:10.360751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0f937d36-54a4-4d3a-ae02-ddf2e0cd52b3 · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:00.443432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05786b47-d55c-49b9-a500-9b8fddaf56cc · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:10.164749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation df900f55-e3d3-4e38-83e2-9d7069372adc · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling International Conference on Learning Representations (ICLR) , year =

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:09.982794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 743d7916-ea65-42fd-be4f-1894a851e573 · outbound

This paper cites Test-Time Scaling for Small.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Test-Time Scaling for Small

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:09.793928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c82c79ab-b42e-4476-b01f-82b1fa1f5835 · outbound

This paper cites International Conference on Machine Learning (ICML) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling International Conference on Machine Learning (ICML) , year =

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:09.619607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1958ed3f-4d0a-4b03-ba29-855da65eede4 · outbound

This paper cites European Conference on Computer Vision (ECCV) , year =.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling European Conference on Computer Vision (ECCV) , year =

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:09.406990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ff450d9b-d154-4bf5-8ed5-a03f70b1b85b · outbound

This paper cites an unresolved cited work.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T04:18:09.224183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1168f2f0-ceb0-4f8d-8fcd-516ef075da0a · outbound

This paper cites Universal Self-Consistency for Large Language Model Generation.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Universal Self-Consistency for Large Language Model Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.096340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6a2007f-4a8f-4388-8d5e-e61a31c773b8 · outbound

This paper cites Advances in neural information processing systems , year=.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Advances in neural information processing systems , year=

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:09.030177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ef43c73e-53b2-4f75-bad5-fe14bf545ed5 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , year=.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Findings of the Association for Computational Linguistics: ACL 2025 , year=

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:08.764362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 783b6880-a223-4f12-9552-f1860ddc3659 · outbound

This paper cites Deep Think with Confidence.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Deep Think with Confidence

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.331152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dec986e-ba4f-41f6-bee3-45fb62adcb28 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Chain-of-thought prompting elicits reasoning in large language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.409501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211a031f-2c45-4362-8c79-ed84ceb6669e · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Self-consistency improves chain of thought reasoning in language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.510655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87453aad-4d38-4cb6-9d2d-883003e82fd9 · outbound

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

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.599326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce18606e-50d1-4638-a81c-484ed19fc1da · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.701024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1503816-343c-4d2b-ac5c-4af66027f1e7 · outbound

This paper cites Aha moment revisited: Are VLM s truly capable of self verification in inference-time scaling? arXiv preprint arXiv:2506.17417, 2026 a.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Aha moment revisited: Are VLM s truly capable of self verification in inference-time scaling? arXiv preprint arXiv:2506.17417, 2026 a

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.796301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7cbbf94-1d48-4f6d-9d33-a924b9ba9aa5 · outbound

This paper cites Seeing but not believing: Probing the disconnect between visual attention and answer correctness in VLM s.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Seeing but not believing: Probing the disconnect between visual attention and answer correctness in VLM s

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:01.872087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4830dccf-df93-4e0b-a57f-1294e85f8838 · outbound

This paper cites Same answer, different representations: Hidden instability in VLM s.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Same answer, different representations: Hidden instability in VLM s

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.003062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c5fbaca-f5d4-4a6e-8476-77dc31f4d868 · outbound

This paper cites Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.099873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e64695-0683-4172-9d0d-5ff6bf843c6c · outbound

This paper cites Diversity matters: Revisiting test-time compute in vision-language models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Diversity matters: Revisiting test-time compute in vision-language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:08.551883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cca778b5-363e-4c04-96fa-455df855e6ef · outbound

This paper cites Vtool-r1: Vlms learn to think with images via reinforcement learning on multimodal tool use.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Vtool-r1: Vlms learn to think with images via reinforcement learning on multimodal tool use

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:08.333460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a2c27826-25f7-4ef7-a988-846aa444833e · outbound

This paper cites Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.360277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841eba7f-065a-4dfe-a01b-3ac66888a80e · outbound

This paper cites No labels, no problem: Training visual reasoners with multimodal verifiers.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling No labels, no problem: Training visual reasoners with multimodal verifiers

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.363295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17efc1ac-f4ca-4ff9-8cd8-025e0a92c3db · outbound

This paper cites On test-time scaling for vision-language models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling On test-time scaling for vision-language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:08.109824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d3135c25-d4ab-41ae-a761-9f9e30d696d6 · outbound

This paper cites Papadopoulos.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Papadopoulos

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:07.904688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation eb46a0c9-1ceb-4233-9324-10ed4044e27e · outbound

This paper cites ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.744144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1358b848-5911-4369-b752-95b41c4b52f9 · outbound

This paper cites Limits and gains of test-time scaling in vision-language reasoning.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Limits and gains of test-time scaling in vision-language reasoning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:02.909859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100e795c-0d12-452d-b2fe-f0ce1c4abafa · outbound

This paper cites AVIS: Adaptive Test-Time Scaling for Vision-Language Models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling AVIS: Adaptive Test-Time Scaling for Vision-Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:03.076604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec7c0d7-8e2e-4cad-8b01-af61fe933024 · outbound

This paper cites SPARC : Separating perception and reasoning circuits for test-time scaling of VLM s.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling SPARC : Separating perception and reasoning circuits for test-time scaling of VLM s

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:07.678668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0183d71-f307-49f0-86cf-d1254247c256 · outbound

This paper cites MindJourney : Test-time scaling with world models for spatial reasoning.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling MindJourney : Test-time scaling with world models for spatial reasoning

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:07.460962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation eaf06592-8a1a-4438-8d0a-e0c9ff0df461 · outbound

This paper cites Mitigating object hallucinations in large vision-language models through visual contrastive decoding.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:07.319172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ff29790c-10f7-4a78-ac79-0f2c3353c775 · outbound

This paper cites Contrastive region guidance: Improving grounding in vision-language models without training.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Contrastive region guidance: Improving grounding in vision-language models without training

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:07.097489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d58e17d1-d150-48db-880d-943b58e04929 · outbound

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

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:03.769031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a403220-3e4c-4d9e-9f0e-b92a9aabe885 · outbound

This paper cites Test-time consistency in vision language models.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Test-time consistency in vision language models

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:06.948420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ec4e79e-9ed2-4f5e-ac08-390f51a7baee · outbound

This paper cites Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:04.004784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5d5e34-06f8-494c-9116-bb7db8b06eb5 · outbound

This paper cites Test-Time Scaling for Small VLMs on Multilingual Visual MCQ.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Test-Time Scaling for Small VLMs on Multilingual Visual MCQ

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:04.124039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 174db91d-e3ba-4323-b5a0-3b460cbac60a · outbound

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

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:04.246376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69a1dc4d-2dee-41bc-af5d-e8a9ea12441d · outbound

This paper cites Towards VQA models that can read.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Towards VQA models that can read

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:06.763366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ea6360ba-f60b-4874-aa7e-ee61ef807ea0 · outbound

This paper cites Measuring multimodal mathematical reasoning with math-vision dataset.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Measuring multimodal mathematical reasoning with math-vision dataset

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:06.548230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 20f29101-8930-4d88-8ada-dda708c41a30 · outbound

This paper cites MMMU : A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling MMMU : A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:06.333252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cac84d0e-8d0f-4bc9-b39a-18cc56e5c1ed · outbound

This paper cites Probing visual language priors in VLM s ( ViLP ).

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Probing visual language priors in VLM s ( ViLP )

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:06.121435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cd96d20f-5167-40f9-b590-3a4a86f6bb18 · outbound

This paper cites Qwen2.5-VL Technical Report.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Qwen2.5-VL Technical Report

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:04.779213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d7f5ca-b061-44aa-9b60-92c47a59a3df · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling LLaVA-OneVision: Easy Visual Task Transfer

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T04:18:04.895443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc531c45-beea-4152-9fe2-d8d6aea1dcfa · outbound

This paper cites Scalable best-of-n selection for large language models via self-certainty.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Scalable best-of-n selection for large language models via self-certainty

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:05.943908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8ff0b3e2-24eb-4cda-83e0-94417c38bf16 · outbound

This paper cites Confidence improves self-consistency in llms.

It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling Confidence improves self-consistency in llms

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T04:18:05.769438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers