Paper Citation Record · LEDGER

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models

As of 18 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2601.22574.

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

pith.paper-citation-record.v1
2601.22574 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:36:26.484082Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T02:31:40.463891Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T07:36:31.820599Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9eef630c-9d12-4349-937f-3ceb8eba3994 · outbound

This paper cites Grounding language with vision: A conditional mutual information calibrated decoding strat- egy for reducing hallucinations in lvlms.arXiv preprint arXiv:2505.19678,.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Grounding language with vision: A conditional mutual information calibrated decoding strat- egy for reducing hallucinations in lvlms.arXiv preprint arXiv:2505.19678,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.276084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c1b3e6-57a4-4dab-94d9-c39b6b685622 · outbound

This paper cites Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.319744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68a30ba-060e-45b2-8058-16df557cbff3 · outbound

This paper cites Mentalmac: Enhancing large language models for detect- ing mental manipulation via multi-task anti-curriculum distillation.arXiv preprint arXiv:2505.15255, 2025b.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Mentalmac: Enhancing large language models for detect- ing mental manipulation via multi-task anti-curriculum distillation.arXiv preprint arXiv:2505.15255, 2025b

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.378480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41f780d3-8f56-4fd1-b112-2ccb19bdf0e7 · outbound

This paper cites VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.474447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd967670-d41d-46f1-b8f7-289c78e505c0 · outbound

This paper cites H., Jo, Y ., and Seo, M.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models H., Jo, Y ., and Seo, M

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.569043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5808543-5658-4a0d-a05f-415c4feb81f9 · outbound

This paper cites Decoupled Weight Decay Regularization.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Decoupled Weight Decay Regularization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.779451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3e0954-924c-4902-80ea-91d18c307674 · outbound

This paper cites Countervid: Counterfactual video generation for mitigat- ing action and temporal hallucinations in video-language models.arXiv preprint arXiv:2601.04778,.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Countervid: Counterfactual video generation for mitigat- ing action and temporal hallucinations in video-language models.arXiv preprint arXiv:2601.04778,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.834881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4de1f7b8-f60c-4ef0-a021-b1bbfe3febcc · outbound

This paper cites Smart- sight: Mitigating hallucination in video-llms without com- promising video understanding via temporal attention collapse.arXiv preprint arXiv:2512.18671,.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Smart- sight: Mitigating hallucination in video-llms without com- promising video understanding via temporal attention collapse.arXiv preprint arXiv:2512.18671,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.911702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d80fcd96-959f-4a72-9985-1e19fcb2a6e0 · outbound

This paper cites VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.055855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4183cc5b-88aa-481a-af8f-b4baa078a506 · outbound

This paper cites an unresolved cited work.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.108846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9498603f-c74d-4438-8ebf-1b6bc3972838 · outbound

This paper cites Kardia-r1: Unleashing llms to reason to- ward understanding and empathy for emotional support via rubric-as-judge reinforcement learning.arXiv preprint arXiv:2512.01282, 2025a.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Kardia-r1: Unleashing llms to reason to- ward understanding and empathy for emotional support via rubric-as-judge reinforcement learning.arXiv preprint arXiv:2512.01282, 2025a

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.211914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5c1c029-6c75-436f-b0b4-16d7c869f433 · outbound

This paper cites Video-llama: An instruction- tuned audio-visual language model for video understand- ing.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Video-llama: An instruction- tuned audio-visual language model for video understand- ing

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.275069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96dd6031-5c4b-4cab-a7c0-83252aa71abb · outbound

This paper cites Eventhallusion: Diagnosing event hallucinations in video llms.arXiv preprint arXiv:2409.16597, 2024a.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Eventhallusion: Diagnosing event hallucinations in video llms.arXiv preprint arXiv:2409.16597, 2024a

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.315860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 237834a3-6d1f-41ef-9563-5d0b483f3496 · outbound

This paper cites j., Gui, L., Fu, D., Feng, J., Liu, Z., and Li, C.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models j., Gui, L., Fu, D., Feng, J., Liu, Z., and Li, C

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.367685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 659eaaf6-511a-473d-9f5c-9b76a50e4198 · outbound

This paper cites Can pruning improve reasoning? revisiting long-cot compression with capability in mind for better reasoning.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Can pruning improve reasoning? revisiting long-cot compression with capability in mind for better reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.425417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e077945-d7b4-47c6-84b1-e83c05dd89c0 · outbound

This paper cites Layernorm Linear GeLU Linear GeLU Linear Tanh Layernorm Linear GeLU Linear GeLU Linear Tanh Figure 6.Overview of the architecture of SSD.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Layernorm Linear GeLU Linear GeLU Linear Tanh Layernorm Linear GeLU Linear GeLU Linear Tanh Figure 6.Overview of the architecture of SSD

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.484082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b21c44-bcda-46b7-982c-d67aab7717c5 · outbound

This paper cites Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.992400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a6763e4-2535-425b-9843-2594ba84dcf7 · outbound

This paper cites Helpd: Mitigating hallucination of lvlms by hierarchical feedback learning with vision-enhanced penalty decoding.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Helpd: Mitigating hallucination of lvlms by hierarchical feedback learning with vision-enhanced penalty decoding

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:26.165448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c897ce-3b31-45da-9dc2-7ccd05ab297e · outbound

This paper cites an unresolved cited work.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Unresolved cited work

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.694297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf08541-6493-4209-b923-2632e50ca56d · outbound

This paper cites Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.124649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f265e5e-95f3-4a29-a098-211c1d0d2a1c · outbound

This paper cites Decoupling contrastive decoding: Robust hallucination mitigation in multimodal large language models.arXiv preprint arXiv:2504.08809,.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Decoupling contrastive decoding: Robust hallucination mitigation in multimodal large language models.arXiv preprint arXiv:2504.08809,

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.182617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c5176a0-b158-44a3-b733-7f69cc794a5b · outbound

This paper cites PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning.

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T06:36:25.228855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a41e6d9f-3019-400d-b960-51b86cea64b0 · inbound

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models cites this paper.

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-08T02:03:50.869564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.