Paper Citation Record · LEDGER

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs

As of 6 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2604.12896.

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

pith.paper-citation-record.v1
2604.12896 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T15:29:25.650175Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

39 of 39 outbound references displayed

verified exact15
verified fuzzy22
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4d716c47-5f46-4c19-8567-f92b4aecbce5 · outbound

This paper cites Per- ception tokens enhance visual reasoning in multimodal lan- guage models.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Per- ception tokens enhance visual reasoning in multimodal lan- guage models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.685588Z

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 303a81e6-0a18-414c-a1da-9dcd0f3f3662 · outbound

This paper cites PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:02.000635Z

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 af90f8ee-3e68-4ed5-813e-664d3890c303 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T10:26:01.983777Z

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 bdb2de89-3591-442e-b628-56222da10caf · outbound

This paper cites MMFactory: A Universal Solution Search Engine for Vision-Language Tasks.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs MMFactory: A Universal Solution Search Engine for Vision-Language Tasks

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.993879Z

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 e2acb4af-17dc-4eab-ab7c-239ce84866ee · outbound

This paper cites GRIT: Teaching MLLMs to Think with Images.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs GRIT: Teaching MLLMs to Think with Images

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:44:46.816923Z

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 0c876103-aa47-44f8-b5d4-3bc3c96474ea · outbound

This paper cites Hidden in plain sight: Vlms overlook their visual repre- sentations.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Hidden in plain sight: Vlms overlook their visual repre- sentations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.688708Z

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 23821e26-51d2-4539-a125-a4e668480c5e · outbound

This paper cites Llmdet: Learning strong open-vocabulary object detectors under the supervision of large language models.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Llmdet: Learning strong open-vocabulary object detectors under the supervision of large language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.691861Z

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 61f3ea5c-202e-48f5-ae94-beaef5b02923 · outbound

This paper cites Blink: Multimodal large language mod- els can see but not perceive.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Blink: Multimodal large language mod- els can see but not perceive

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.695215Z

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 248ff6d7-2c0b-40f5-9547-a92a613a5b9b · outbound

This paper cites Visual program- ming: Compositional visual reasoning without training.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Visual program- ming: Compositional visual reasoning without training

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.698186Z

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 df35a4e1-385a-4265-af30-5d1c0a6d1b66 · outbound

This paper cites Vi- sual sketchpad: Sketching as a visual chain of thought for multimodal language models.Advances in Neural Informa- tion Processing Systems, 37:139348–139379.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Vi- sual sketchpad: Sketching as a visual chain of thought for multimodal language models.Advances in Neural Informa- tion Processing Systems, 37:139348–139379

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.682501Z

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 bf45f232-5d31-45fd-abcb-9c0ea52bc4ee · outbound

This paper cites Zebra-cot: A dataset for interleaved vision language reasoning.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Zebra-cot: A dataset for interleaved vision language reasoning

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:02.008662Z

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 fb98abb0-49e8-4d7d-a333-73c31baa0d74 · outbound

This paper cites Llava-plus: Learning to use tools for creating multimodal agents.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Llava-plus: Learning to use tools for creating multimodal agents

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.679110Z

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 df645dfa-8df4-4b18-811b-69b3acbd51a2 · outbound

This paper cites Grounding dino: Marrying dino with grounded pre-training for open-set object detection.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Grounding dino: Marrying dino with grounded pre-training for open-set object detection

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.655114Z

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 767e7b78-2c8d-4e9e-a64c-ca61b4e04aa5 · outbound

This paper cites Latte: Learning to think with vision specialists.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Latte: Learning to think with vision specialists

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.670107Z

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 dcca2f04-7181-4814-8539-f2377c8e7737 · outbound

This paper cites Gpt-5 system card.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Gpt-5 system card

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.629081Z

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 60abb331-28db-486e-a432-73f4ec20ddb8 · outbound

This paper cites Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Systems, 36:42748–42761.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Systems, 36:42748–42761

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.631871Z

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 ef04fe77-52e5-47ce-b185-40b53d1cc8d0 · outbound

This paper cites Grounded Reinforcement Learning for Visual Reasoning.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Grounded Reinforcement Learning for Visual Reasoning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.973499Z

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 ad68073c-d313-45b0-b4ff-760dc9255775 · outbound

This paper cites Loftr: Detector-free local feature matching with transformers.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Loftr: Detector-free local feature matching with transformers

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.647855Z

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 1400c1a6-5de6-47c5-8590-c7a4e54a5dae · outbound

This paper cites Vipergpt: Vi- sual inference via python execution for reasoning.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Vipergpt: Vi- sual inference via python execution for reasoning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.658284Z

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 9519956b-d8d7-4f96-8b4f-8f5bcae686fa · outbound

This paper cites Emergent correspondence from image diffusion.Advances in Neural Information Processing Systems, 36:1363–1389.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Emergent correspondence from image diffusion.Advances in Neural Information Processing Systems, 36:1363–1389

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.667044Z

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 08a21b56-9925-4bf3-a657-0c4a718ce2b4 · outbound

This paper cites Tulip: Contrastive image-text learning with richer vision understanding.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Tulip: Contrastive image-text learning with richer vision understanding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.634567Z

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 75506738-098f-4cc5-9006-a381ef6e2830 · outbound

This paper cites Qwen3 technical report.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Qwen3 technical report

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.637249Z

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 63baa1e1-b5ec-4784-bcf4-0d1ab3d8bb23 · outbound

This paper cites Raft: Recurrent all-pairs field transforms for optical flow.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Raft: Recurrent all-pairs field transforms for optical flow

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.673027Z

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 0cac81a4-60f5-43ca-ada6-a04a7df1ce1a · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.651748Z

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 5a86a0d0-18d2-4bec-9c6e-3b84c97c2383 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-11T10:26:01.950624Z

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 47cbdb7e-ffd7-4a73-95e5-b9f1ac60d283 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.626496Z

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 edd76505-38a9-4b5d-8cb5-af12a9118c6f · outbound

This paper cites Open vision reasoner: Transferring linguistic cognitive behavior for visual reasoning.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Open vision reasoner: Transferring linguistic cognitive behavior for visual reasoning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.944505Z

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 cd8cd4ee-0ba8-46f9-be89-3e322b5230d6 · outbound

This paper cites Depth anything: Unleashing the power of large-scale unlabeled data.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Depth anything: Unleashing the power of large-scale unlabeled data

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.661430Z

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 4c6ad6c9-fdf3-43df-8778-46a1964bd261 · outbound

This paper cites Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.935651Z

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 ad7551bf-0755-407d-bbea-79925e110763 · outbound

This paper cites Introducing Visual Perception Token into Multimodal Large Language Model.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Introducing Visual Perception Token into Multimodal Large Language Model

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.904902Z

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 4a740743-3438-4ae6-9ad0-ab9a1b75d28e · outbound

This paper cites Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:50:01.041344Z

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 65ead13e-0d5c-4b26-bcff-61e6f648efcc · outbound

This paper cites Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-11T10:26:01.917789Z

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 e796cd22-198b-4d2f-bedd-16dcb0c9a8a4 · outbound

This paper cites Thyme: Think Beyond Images.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Thyme: Think Beyond Images

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:33:29.495992Z

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 9d74e71e-3af3-426f-a6cd-fa668f1aaefb · outbound

This paper cites Vipact: Visual-perception enhancement via specialized vlm agent collaboration and tool-use.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Vipact: Visual-perception enhancement via specialized vlm agent collaboration and tool-use

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.958968Z

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 7c0852ea-11b5-4a98-be9c-18e7298cf73c · outbound

This paper cites Reinforced Visual Perception with Tools.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Reinforced Visual Perception with Tools

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:26:01.924607Z

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 827ec209-92dc-4c38-ae08-0b7fdcfc99bd · outbound

This paper cites Mainly, we provide samples of prompts for both frontier and open-source MLLMs.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Mainly, we provide samples of prompts for both frontier and open-source MLLMs

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.640749Z

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 d0ea9244-4b20-4433-b8aa-5651e641f6c2 · outbound

This paper cites left" or.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs left" or

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T23:25:29.644241Z

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 d94cf8ab-521a-4cb9-8777-7e17d42d456e · outbound

This paper cites 5.1 we discussed the quality of visual interpretation of current MLLMs.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs 5.1 we discussed the quality of visual interpretation of current MLLMs

Reference 38

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T23:25:29.676071Z

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 89665866-e434-43de-820b-3ef85228df5b · outbound

This paper cites an unresolved cited work.

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-17T23:25:29.664380Z

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

No inbound Pith citation observations are available.