Paper Citation Record · LEDGER

FairReason: Balancing Reasoning and Social Bias in MLLMs

As of 16 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2507.23067.

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

pith.paper-citation-record.v1
2507.23067 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T11:09:04.872607Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T01:00:07.465292Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy17
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 7004efc8-db6f-451d-b43c-ca02a40800e1 · outbound

This paper cites Clip the bias: How useful is balancing data in multimodal learning?,.

FairReason: Balancing Reasoning and Social Bias in MLLMs Clip the bias: How useful is balancing data in multimodal learning?,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.781142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 237964b7-ceb0-48d3-8f77-cfca7e834e28 · outbound

This paper cites Qwen2.5-vl technical report, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Qwen2.5-vl technical report, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.710817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13eb984e-0e3f-4597-bc89-ab3baa1224bb · outbound

This paper cites A prompt array keeps the bias away: Debiasing vision-language models with ad- versarial learning.

FairReason: Balancing Reasoning and Social Bias in MLLMs A prompt array keeps the bias away: Debiasing vision-language models with ad- versarial learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.751573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1c221963-1549-4b5a-aed1-45c7752aa847 · outbound

This paper cites Bow- man, Julian Michael, Ethan Perez, and Miles Turpin.

FairReason: Balancing Reasoning and Social Bias in MLLMs Bow- man, Julian Michael, Ethan Perez, and Miles Turpin

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.733747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f143a80b-ae1d-4df1-baaf-f12f7e4d169c · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capa- bility in llms via reinforcement learning, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Deepseek-r1: Incentivizing reasoning capa- bility in llms via reinforcement learning, 2025

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.713413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 86d8da64-0d2b-4cf5-a28f-f639f720a0d0 · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Open r1: A fully open reproduction of deepseek-r1, 2025

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.692245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bbd295ba-d0b2-4a03-b525-d349fde37f01 · outbound

This paper cites Vision-r1: Incentivizing reasoning capability in multimodal large language models, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Vision-r1: Incentivizing reasoning capability in multimodal large language models, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.671579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2ecd0d8e-ce4a-44b6-8f10-29146d58d960 · outbound

This paper cites an unresolved cited work.

FairReason: Balancing Reasoning and Social Bias in MLLMs Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:09:05.651478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 64eefe0e-4b8c-49fe-b5a0-279ab978312f · outbound

This paper cites MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems.

FairReason: Balancing Reasoning and Social Bias in MLLMs MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.748471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f1ec6c-bfd1-401a-8135-44a112512fab · outbound

This paper cites Let's Verify Step by Step.

FairReason: Balancing Reasoning and Social Bias in MLLMs Let's Verify Step by Step

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.754040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faeeffa6-db8f-484c-a075-dbacec772dd4 · outbound

This paper cites Inter-gps: Interpretable geometry problem solving with formal language and sym- bolic reasoning.

FairReason: Balancing Reasoning and Social Bias in MLLMs Inter-gps: Interpretable geometry problem solving with formal language and sym- bolic reasoning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.630118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation deb14924-1a98-4b4b-9c8a-6297cf90cfdb · outbound

This paper cites Metaspatial: Reinforcing 3d spa- tial reasoning in vlms for the metaverse.arXiv preprint arXiv:2503.18470, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Metaspatial: Reinforcing 3d spa- tial reasoning in vlms for the metaverse.arXiv preprint arXiv:2503.18470, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.765397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 748b8416-530d-424f-8833-64bfa8c27f70 · outbound

This paper cites Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?.

FairReason: Balancing Reasoning and Social Bias in MLLMs Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.770822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab1bd19-2540-4f77-a237-3f1ddff06c0a · outbound

This paper cites Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models.

FairReason: Balancing Reasoning and Social Bias in MLLMs Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.776385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92c9a00e-a579-4354-a0a7-145138c403cc · outbound

This paper cites Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action.

FairReason: Balancing Reasoning and Social Bias in MLLMs Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.781541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c99034aa-1b3e-4622-817a-7aa0ed2e364f · outbound

This paper cites Do code llms understand design patterns? In2025 IEEE/ACM Inter- national Workshop on Large Language Models for Code (LLM4Code), pages 209–212.

FairReason: Balancing Reasoning and Social Bias in MLLMs Do code llms understand design patterns? In2025 IEEE/ACM Inter- national Workshop on Large Language Models for Code (LLM4Code), pages 209–212

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.786242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce4b64e-fdec-426c-9f63-90b7148a8f81 · outbound

This paper cites BBQ: A hand-built bias benchmark for question answering.

FairReason: Balancing Reasoning and Social Bias in MLLMs BBQ: A hand-built bias benchmark for question answering

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.597637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aba5c2fd-bd6c-4125-bf70-ca28a397a8c0 · outbound

This paper cites Strengthening multi- modal large language model with bootstrapped preference optimization, 2024.

FairReason: Balancing Reasoning and Social Bias in MLLMs Strengthening multi- modal large language model with bootstrapped preference optimization, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.578304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 456d9335-e59e-41d9-994e-91e907429cf7 · outbound

This paper cites Sciscigpt: Advancing human- ai collaboration in the science of science.arXiv preprint arXiv:2504.05559, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Sciscigpt: Advancing human- ai collaboration in the science of science.arXiv preprint arXiv:2504.05559, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.800286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 628aee97-0de9-493b-856c-9432c3878e01 · outbound

This paper cites Math- llava: Bootstrapping mathematical reasoning for multimodal large language models, 2024.

FairReason: Balancing Reasoning and Social Bias in MLLMs Math- llava: Bootstrapping mathematical reasoning for multimodal large language models, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.558330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6bc74ccc-78a2-4bfe-936d-243a7ced6938 · outbound

This paper cites Qwen3 technical report, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Qwen3 technical report, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.810669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee327d2b-a324-45f8-afa2-bb06c787a588 · outbound

This paper cites Llamav-o1: Rethinking step-by- step visual reasoning in llms, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Llamav-o1: Rethinking step-by- step visual reasoning in llms, 2025

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.518730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation de2cf14c-784b-4d7b-ab7e-39b1406b50a5 · outbound

This paper cites an unresolved cited work.

FairReason: Balancing Reasoning and Social Bias in MLLMs Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:09:05.499995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cfd2d042-5356-4b00-8688-ea679611ee49 · outbound

This paper cites VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model.

FairReason: Balancing Reasoning and Social Bias in MLLMs VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.824554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad60f27-15ce-41b4-828b-d665bf2a7be1 · outbound

This paper cites an unresolved cited work.

FairReason: Balancing Reasoning and Social Bias in MLLMs Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:09:05.480283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7db72356-a416-44a1-af8d-15321ef60698 · outbound

This paper cites Does reasoning introduce bias? a study of social bias evaluation and mitigation in llm reason- ing, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Does reasoning introduce bias? a study of social bias evaluation and mitigation in llm reason- ing, 2025

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.462119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6ddc9a1-a7a2-4271-a1d8-a95169bf74e3 · outbound

This paper cites Llava-cot: Let vision language models reason step- by-step, 2024.

FairReason: Balancing Reasoning and Social Bias in MLLMs Llava-cot: Let vision language models reason step- by-step, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.442547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 69b874d1-6887-461a-a692-5606b4c2fa66 · outbound

This paper cites Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In European Conference on Computer Vision, pages 169–186.

FairReason: Balancing Reasoning and Social Bias in MLLMs Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In European Conference on Computer Vision, pages 169–186

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.842979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbc6850-267b-4c73-a241-f80c6236bc48 · outbound

This paper cites MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models.

FairReason: Balancing Reasoning and Social Bias in MLLMs MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T11:09:04.847931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2762fdfb-5cc2-486a-b659-e4949867980f · outbound

This paper cites VLStereoSet: A study of stereotypical bias in pre-trained vision-language models.

FairReason: Balancing Reasoning and Social Bias in MLLMs VLStereoSet: A study of stereotypical bias in pre-trained vision-language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.409998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c69935c5-9286-4a26-aa76-7407a17f8ba5 · outbound

This paper cites Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models, 2025.

FairReason: Balancing Reasoning and Social Bias in MLLMs Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models, 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.391360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d289c445-d819-4e6e-a6fb-ab23b0962474 · outbound

This paper cites For SFT and model distillation, we utilize theLLaMA-Factoryframework with hyperparameter configurations listed in Table 1.

FairReason: Balancing Reasoning and Social Bias in MLLMs For SFT and model distillation, we utilize theLLaMA-Factoryframework with hyperparameter configurations listed in Table 1

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.371781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dc58bfde-cd0b-4fc3-b1e8-018fc98ee399 · outbound

This paper cites an unresolved cited work.

FairReason: Balancing Reasoning and Social Bias in MLLMs Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:09:05.352965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4022a2b7-4a13-4b5b-b649-97b38ebc6a71 · outbound

This paper cites 1 Table 3.

FairReason: Balancing Reasoning and Social Bias in MLLMs 1 Table 3

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:09:05.333940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 445bcf17-5e65-4a3c-90a6-8cbe5df08f33 · inbound

MagicSim: A Unified Infrastructure for Executable Embodied Interaction cites this paper.

MagicSim: A Unified Infrastructure for Executable Embodied Interaction FairReason: Balancing Reasoning and Social Bias in MLLMs

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:58:58.072373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 911c7159-76b4-4415-a026-7d4beff48639 · inbound

MagicSim: A Unified Infrastructure for Executable Embodied Interaction cites this paper.

MagicSim: A Unified Infrastructure for Executable Embodied Interaction FairReason: Balancing Reasoning and Social Bias in MLLMs

Reference 95

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T01:00:19.778235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.