Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z
Paper Citation Record · LEDGER
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
As of 5 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:2605.01345.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-28T10:38:41.735204Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-02T02:46:28.914422Z
Reference resolution
17 of 17 outbound references displayed
- verified exact2
- verified fuzzy6
- unresolved6
- parse uncertain1
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 4c17fc5e-ebf6-4593-a388-ad9af2a779c7 · outbound
This paper cites BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T01:41:14.927669Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 22de78c7-d998-443e-bf55-9c5167dae9d5 · outbound
This paper cites MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T13:25:32.206292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5eeec845-22e0-4a1f-9d7f-d797d875de92 · outbound
This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T01:41:19.847345Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 05c02d7a-20fd-4739-a8fe-a9b8efd5390b · outbound
This paper cites Pviewed = X j∈Goverlap P(Grid i) where Goverlap denotes the grid cells covered by the current intervention crop to a certain extent (15% of the grid area in our experiments).
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Pviewed = X j∈Goverlap P(Grid i) where Goverlap denotes the grid cells covered by the current intervention crop to a certain extent (15% of the grid area in our experiments)
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.621292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2117b56b-c156-4d57-a900-aa530c342d98 · outbound
This paper cites can the model produce an answer.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design can the model produce an answer
Reference 5
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-14T06:18:38.576650Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b23943e9-d012-4fa2-ad34-2980be9ad310 · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.629391Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0e6a07d7-83b3-41c2-b819-ba587c90e0be · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.633491Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e1a8aaec-8d40-4519-80bb-cef56ac8200f · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.625376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 08c29c37-0e8a-45fa-9002-2dc5b229d41e · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.585234Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6cd236af-1bc1-4bf4-b4ae-032383f2e061 · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.607618Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 36e87788-6de7-4c0f-875e-94853e795644 · outbound
This paper cites Yes” or “No.
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.593528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7fbf30a7-6c07-4724-b121-84799cccfc22 · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 12
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-14T06:18:38.580839Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f575d0a1-c6dd-4ed8-8a4a-053aab297e4e · outbound
This paper cites an unresolved cited work.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T06:18:38.611530Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bb7d46c4-cf82-4ed9-beb9-ad3a3b6a85f0 · outbound
This paper cites If current turn == max turns, you must skip tool usage and provide the most accurate<answer>possible based on existing information.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design If current turn == max turns, you must skip tool usage and provide the most accurate<answer>possible based on existing information
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.616011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eeb1aa86-2646-42aa-8ffa-588db6f834a3 · outbound
This paper cites Crop first, perception (e.g., detection) later.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Crop first, perception (e.g., detection) later
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.597602Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 979ac0c1-2936-4a6f-9036-f065806d9c8a · outbound
This paper cites Problem-Solving Strategy 1.Locate the object of interest first: • If the question provides the approximate location, zoom in that area to locate the object.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Problem-Solving Strategy 1.Locate the object of interest first: • If the question provides the approximate location, zoom in that area to locate the object
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.603389Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5f150131-50cc-4373-9836-94264dfd57e7 · outbound
This paper cites You can verify your judgment with detection, but never treat its results as arguments.
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design You can verify your judgment with detection, but never treat its results as arguments
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:18:38.589550Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation c6aa4e48-e6ca-4eb3-98f6-b7610064ce5b · inbound
ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents cites this paper.
ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
Reference 46
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T02:46:28.916114Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.