Paper Citation Record · LEDGER

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA

As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.16189.

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

pith.paper-citation-record.v1
2607.16189 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:09:45.965576Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0bb08b37-1d7a-4026-bb59-b6966e225fc1 · outbound

This paper cites Qwen3-VL Technical Report.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Qwen3-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:41.763169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd76cc4-84a5-4b04-a048-2c579d8112cf · outbound

This paper cites Revisiting the “video” in video-language understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Revisiting the “video” in video-language understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:41.875217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbaa2b13-bfd2-4873-bcee-8ca162105cd8 · outbound

This paper cites VideoMiner: Iteratively grounding key frames of hour-long videos via tree-based group relative policy optimization.arXiv preprint arXiv:2510.06040, 2025.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA VideoMiner: Iteratively grounding key frames of hour-long videos via tree-based group relative policy optimization.arXiv preprint arXiv:2510.06040, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:41.954161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e9ccef5-c63d-42d8-94b8-88ec37652e5b · outbound

This paper cites CG-Bench: Clue-grounded question answering benchmark for long video understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA CG-Bench: Clue-grounded question answering benchmark for long video understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.030375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44046130-c663-4c9c-98a3-c56a08721efa · outbound

This paper cites ShareGPT4Video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems (NeurIPS), 2024.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA ShareGPT4Video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems (NeurIPS), 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.195155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e31af0a0-7e39-488b-9e68-b986d5e74fa7 · outbound

This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.330014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43099faf-9860-4b49-99d3-a85d55c1c44f · outbound

This paper cites VideoZoomer: Reinforcement-learned temporal focusing for long video reasoning.arXiv preprint arXiv:2512.22315, 2025.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA VideoZoomer: Reinforcement-learned temporal focusing for long video reasoning.arXiv preprint arXiv:2512.22315, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.446315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6c9e309-563c-4c60-8957-33fe452cd3ca · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.508311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5e3cd1-0857-4f95-9390-550c22a657e4 · outbound

This paper cites an unresolved cited work.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.622277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6babdc4c-0950-4397-8730-7ec9fca0dbaf · outbound

This paper cites ReVisionLLM: Recursive vision-language model for temporal grounding in hour-long videos.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA ReVisionLLM: Recursive vision-language model for temporal grounding in hour-long videos

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.728739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df930178-2b3a-43b9-a0b3-2c4480914b84 · outbound

This paper cites Long movie clip classification with state-space video models.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Long movie clip classification with state-space video models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:42.910965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40fca317-5763-4c9f-bd62-79b95b4e733d · outbound

This paper cites Efficient movie scene detection using state-space transformers.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Efficient movie scene detection using state-space transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.043540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44921443-2857-4240-83d4-3e84c564af26 · outbound

This paper cites Video ReCap: Recursive captioning of hour-long videos.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Video ReCap: Recursive captioning of hour-long videos

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.128553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3fb1495-cc4e-4279-873e-002b7ba41fa5 · outbound

This paper cites BIMBA: Selective-scan compression for long-range video question answering.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA BIMBA: Selective-scan compression for long-range video question answering

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.287488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a9c70b5-7d51-4f0b-a03b-b8e2fc64a5bd · outbound

This paper cites an unresolved cited work.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.382041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d96c88b-f6e2-46a0-8165-73e347507928 · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.463242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca4c39a9-0a3f-4708-8551-7ace2a98966f · outbound

This paper cites LLaMA-VID: An image is worth 2 tokens in large language models.European Conference on Computer Vision (ECCV), 2024.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LLaMA-VID: An image is worth 2 tokens in large language models.European Conference on Computer Vision (ECCV), 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.571420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe511cd-bbb2-40ce-8e78-b68d1ce62936 · outbound

This paper cites TimeSearch-R: Adaptive temporal search for long-form video understanding via self-verification reinforcement learning.arXiv preprint arXiv:2511.05489, 2025.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA TimeSearch-R: Adaptive temporal search for long-form video understanding via self-verification reinforcement learning.arXiv preprint arXiv:2511.05489, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.682875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c09683-d885-4508-b4c4-a0212dd8815e · outbound

This paper cites an unresolved cited work.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.802551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e4b502-7a54-4aea-8e2c-6dcf227a67f6 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Learning transferable visual models from natural language supervision

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:43.929348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f14f7b0-4d50-4382-8e79-5db2ade9af63 · outbound

This paper cites Understanding long videos in one multimodal language model pass.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Understanding long videos in one multimodal language model pass

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.052763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdeeffc3-46f4-4f02-b7e9-6321d1ef67df · outbound

This paper cites an unresolved cited work.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.148009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a55875-f353-4b32-9ba8-3b1c1b284223 · outbound

This paper cites xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.272531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 751eb134-49f0-4ee9-953f-35fff8f7cfeb · outbound

This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.385817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5d2c529-0028-4e4a-b1de-c4ff5247ef5c · outbound

This paper cites MovieChat: From dense token to sparse memory for long video understanding.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA MovieChat: From dense token to sparse memory for long video understanding.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.512577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4955792f-f0e2-48f5-b1f6-b3a1c10e2f66 · outbound

This paper cites Adaptive keyframe sampling for long video understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Adaptive keyframe sampling for long video understanding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.636461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a7e6fa5-5466-454f-8284-109e92a63dce · outbound

This paper cites Alvarez, Lei Zhang, and Zhiding Yu.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Alvarez, Lei Zhang, and Zhiding Yu

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.742647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06acb4e-218a-443d-ad58-723e803b012f · outbound

This paper cites LVBench: An Extreme Long Video Understanding Benchmark.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LVBench: An Extreme Long Video Understanding Benchmark

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.860609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 659a6dfb-9521-4811-ab31-a4ca266faee6 · outbound

This paper cites AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:44.952695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4169a6b-2f5d-4b69-910a-9db16aedc76f · outbound

This paper cites Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.070624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca71d312-04bf-4640-9f7a-976d50d0a3c2 · outbound

This paper cites VideoTree: Adaptive tree-based video representation for LLM reasoning on long videos.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA VideoTree: Adaptive tree-based video representation for LLM reasoning on long videos

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.141034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2160f28-107f-4777-aa54-4fcf8fa980b3 · outbound

This paper cites Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.205921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47ada167-aec7-4386-aa2c-5396ba2e10b0 · outbound

This paper cites LongVideoBench: A benchmark for long- context interleaved video-language understanding.Advances in Neural Information Processing Systems (NeurIPS), 2024.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LongVideoBench: A benchmark for long- context interleaved video-language understanding.Advances in Neural Information Processing Systems (NeurIPS), 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.254499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffb45fa-d594-474d-aa85-e13fd2a50c35 · outbound

This paper cites LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.294808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b1174a-3beb-4864-aa68-2cf561590e83 · outbound

This paper cites Generative Frame Sampler for Long Video Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Generative Frame Sampler for Long Video Understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.384742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb651f5-d098-4d35-8655-7cfa911c0247 · outbound

This paper cites T*: Re-thinking Temporal Search for Long-Form Video Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA T*: Re-thinking Temporal Search for Long-Form Video Understanding

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.454954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c761285d-106e-48eb-a426-a80e90c012f3 · outbound

This paper cites MomentSeeker: A benchmark for long-video moment retrieval.arXiv preprint arXiv:2502.12558, 2025.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA MomentSeeker: A benchmark for long-video moment retrieval.arXiv preprint arXiv:2502.12558, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.511098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d04a5fb-0e4a-4430-bed8-93c0705a9293 · outbound

This paper cites Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.593997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80010330-3aa0-499f-8133-04338642dd97 · outbound

This paper cites A simple LLM framework for long-range video question-answering.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA A simple LLM framework for long-range video question-answering

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.641212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8524ad-ed63-4605-8c9d-a10dec30233e · outbound

This paper cites SiLVR: A Simple Language-based Video Reasoning Framework.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA SiLVR: A Simple Language-based Video Reasoning Framework

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.691759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a0e3e4e-fe69-4804-b274-743ef21e3497 · outbound

This paper cites Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.802892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57e3b34-6e00-4cb7-8c0b-ecef8bc297ba · outbound

This paper cites Long Context Transfer from Language to Vision.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Long Context Transfer from Language to Vision

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.855573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efea4c79-7408-4801-a2dd-e4c8152affec · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA MLVU: Benchmarking Multi-task Long Video Understanding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.916527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3752c4c4-f498-4b2e-8689-473e325b665f · outbound

This paper cites User: Current Segment [t s-te]:.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA User: Current Segment [t s-te]:

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-08-01T21:09:45.965576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.