Paper Citation Record · LEDGER

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

As of 18 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2501.02669.

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

pith.paper-citation-record.v1
2501.02669 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T22:13:01.238326Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:32:43.191067Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T08:53:16.341543Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy14
unresolved16
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d9b929af-00a5-4a12-a07f-ffbbe87e0c48 · outbound

This paper cites shape type), the model first needs to correctly enumerate the attribute values (e.g.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? shape type), the model first needs to correctly enumerate the attribute values (e.g

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.945341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4738033a-e60a-4a35-956d-6ed14f3af148 · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:04.316329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 091f7cb5-6e71-487f-9f52-4ced86728735 · outbound

This paper cites backtracking.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? backtracking

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:04.185468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8e50b250-444e-4e1c-bf56-e893c2fd84f8 · outbound

This paper cites • To reason about the query: the model needs to correctly enumerate the attribute values for each image in the query similarly.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? • To reason about the query: the model needs to correctly enumerate the attribute values for each image in the query similarly

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.583444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6c348bf4-4c2b-4212-a0e3-77dd9ac44850 · outbound

This paper cites Singh, A., Natarajan, V ., Shah, M., Jiang, Y ., Chen, X., Batra, D., Parikh, D., and Rohrbach, M.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Singh, A., Natarajan, V ., Shah, M., Jiang, Y ., Chen, X., Batra, D., Parikh, D., and Rohrbach, M

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:04.534759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c049058d-af3d-4975-a6dd-142ba2e4f579 · outbound

This paper cites Sun, Z., Yu, L., Shen, Y ., Liu, W., Yang, Y ., Welleck, S., and Gan, C.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Sun, Z., Yu, L., Shen, Y ., Liu, W., Yang, Y ., Welleck, S., and Gan, C

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:04.485464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b1f6d2a1-d1f7-456c-823d-73939131dfb8 · outbound

This paper cites Are Large-Language Models Graph Algorithmic Reasoners?.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Are Large-Language Models Graph Algorithmic Reasoners?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.399401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3404e2f-cd44-4751-b728-0c2a890cb8ae · outbound

This paper cites MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.424752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 978db19d-91f2-44da-93e8-ee725fb2899f · outbound

This paper cites single-hop.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? single-hop

Reference 10

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T22:13:04.444754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08ac75a3-4241-45ca-a8be-d40be35b0bad · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:03.794769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 06843895-1faa-4f65-bca3-c48f112ca72d · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:03.679614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1eb820e9-c6d1-4b40-9924-28cc28c105b4 · outbound

This paper cites (line type , XOR), the model needs to identify the correct values of the attribute domain d for each option image and the correct relationr.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? (line type , XOR), the model needs to identify the correct values of the attribute domain d for each option image and the correct relationr

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.474745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b419063-6839-4715-8156-031645c3f018 · outbound

This paper cites 46 Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Table 14.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? 46 Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Table 14

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.364749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7ae0808f-cb8f-4690-a4f4-9fc0568f3f2c · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:03.263094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff329e0e-2a4a-4a88-bc39-a405a7262fdb · outbound

This paper cites Answer: 95 November December Figure 32.ASIMPLEexample fromTable Readout.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Answer: 95 November December Figure 32.ASIMPLEexample fromTable Readout

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.182008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6309a005-e4a2-45e2-aa3e-7b52bb1c3aaa · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:03.094820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68bb3852-c4eb-48c8-ad6d-d2dfe5c2ff34 · outbound

This paper cites Answer: 233 Figure 33.AHARDexample fromTable Readout.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Answer: 233 Figure 33.AHARDexample fromTable Readout

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:03.025587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 353eb138-7832-49d5-9b38-081d30de6fb4 · outbound

This paper cites The grid is filled up with objects, which you will be asked to recognize and collect, and obstacles, which you should avoid.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? The grid is filled up with objects, which you will be asked to recognize and collect, and obstacles, which you should avoid

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:02.904748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bb8675ab-8c9c-4b48-91ce-fa88e39e2ca1 · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:02.788039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f517d880-22c6-4f55-8aad-13066805e3a0 · outbound

This paper cites The grid is filled up with objects, which you will be asked to recognize and collect, and obstacles, which you should avoid.

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:02.663678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 93957649-5c7b-4775-8d6c-c13322deba03 · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:02.569937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 244b66e0-b917-4c17-9f2c-6a9a29e89968 · outbound

This paper cites 51 Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? The image shows a a puzzle in a 3 by 3 grid followed by 4 options.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? 51 Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? The image shows a a puzzle in a 3 by 3 grid followed by 4 options

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:02.435490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b3021570-a7b2-4bce-8e26-1ffd20f0dd7f · outbound

This paper cites … position: Image 1: (1, 0), (0, 2) Image 2: (0, 2), (1, 1) Image 3: (0, 2) This suggests the AND relation.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? … position: Image 1: (1, 0), (0, 2) Image 2: (0, 2), (1, 1) Image 3: (0, 2) This suggests the AND relation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:02.378205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff24848f-4171-4f07-85ec-70295e6d4e8f · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:02.234271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c6d5e29a-2eca-46f5-a933-a7fba6130d87 · outbound

This paper cites color: Image 1: 189, 135 Image 2: 189 Image 3: 189 This suggests the AND relation.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? color: Image 1: 189, 135 Image 2: 189 Image 3: 189 This suggests the AND relation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T22:13:02.124845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4fd0a3a0-7f46-41c1-b50e-e97941bb5a47 · outbound

This paper cites an unresolved cited work.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:13:02.015722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bde4c299-e96c-446b-bf43-ee2ffed36c6d · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.234747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8a3da1c-c5fe-4d93-8c2b-3099b57c98ba · outbound

This paper cites Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Reference 576

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.216677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc9d72c-a524-41a7-89f5-4345f31dbb77 · outbound

This paper cites Convert,.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? Convert,

Reference 2015

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T22:13:04.074754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9a97e119-ad7e-4962-bab7-09c74feee0eb · outbound

This paper cites doi: 10.18653/v1/2023.acl-short.43.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? doi: 10.18653/v1/2023.acl-short.43

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.299514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a01c31-c3bc-444b-8b05-59224c67ef9c · outbound

This paper cites On Pre-training of Multimodal Language Models Customized for Chart Understanding.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? On Pre-training of Multimodal Language Models Customized for Chart Understanding

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.264753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db99015a-11da-4001-9936-ae37af6886cb · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-10T22:13:00.271469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1102cc23-3b0f-46de-8988-d3a531a0f46d · inbound

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models cites this paper.

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-05T16:32:43.191067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f397b56-197c-44e0-9ad9-cc6c9852c6d3 · inbound

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models cites this paper.

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:53:16.343122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.