Paper Citation Record · LEDGER

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph

As of 18 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 2 inbound Pith citation observations for arXiv:2505.03173.

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

pith.paper-citation-record.v1
2505.03173 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:01:14.798928Z

measured 35 of 35 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T14:53:56.693464Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T15:28:33.980713Z

Reference resolution

33 of 33 outbound references displayed

verified exact1
verified fuzzy23
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dd674685-4fb2-4151-9ace-18582f4983fa · outbound

This paper cites GPT-4 Technical Report.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.708843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0c62299-891b-4494-b823-7904943be452 · outbound

This paper cites An image is worth 16x16 words: Trans- formers for image recognition at scale.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.061281Z

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.

Observation c8811903-3d78-4809-98d6-23b0db109b08 · outbound

This paper cites Assistgpt: A general multi-modal assistant that can plan, execute, inspect, and learn,.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Assistgpt: A general multi-modal assistant that can plan, execute, inspect, and learn,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.053643Z

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.

Observation fcb1de7c-c632-4199-8614-e6fac6925367 · outbound

This paper cites Ma-lmm: Memory-augmented large multimodal model for long-term video understand- ing.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Ma-lmm: Memory-augmented large multimodal model for long-term video understand- ing

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.045796Z

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.

Observation a18529be-24f9-42ea-ba7e-91f92a28d9d3 · outbound

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

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Video recap: Recursive captioning of hour-long videos,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.037885Z

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.

Observation 5021188d-ee2d-49a0-8938-43d3f977888a · outbound

This paper cites Videorag: Retrieval- augmented generation over video corpus,.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Videorag: Retrieval- augmented generation over video corpus,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.030146Z

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.

Observation 27a4157c-9b7a-497b-b809-96b8663b1a76 · outbound

This paper cites Egoschema: a diagnos- tic benchmark for very long-form video language under- standing.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Egoschema: a diagnos- tic benchmark for very long-form video language under- standing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.005982Z

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.

Observation 0768b8ad-b363-4f7a-be89-a2fa77856ff3 · outbound

This paper cites Verbs in action: Improving verb understanding in video- language models,.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Verbs in action: Improving verb understanding in video- language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.998256Z

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.

Observation d65c5189-8114-4652-9ab9-9b54a5a3328a · outbound

This paper cites Learning to compress prompts with gist tokens.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Learning to compress prompts with gist tokens

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.990276Z

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.

Observation 8161181f-2bb3-4950-b669-e0351003646b · outbound

This paper cites A simple recipe for contrastively pre-training video-first encoders beyond 16 frames.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph A simple recipe for contrastively pre-training video-first encoders beyond 16 frames

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.982231Z

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.

Observation 03ee98dd-2565-4305-9f96-bf84ea34ef64 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Learning Transferable Visual Models From Natural Language Supervision

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.751068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3599a215-5317-44ef-b9b7-3d0ce8bc8f25 · outbound

This paper cites SAM 2: Segment Anything in Images and Videos.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph SAM 2: Segment Anything in Images and Videos

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.754256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf75a49d-0623-40bf-91e3-fe5ad7a0b0ea · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.974075Z

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.

Observation be8a1184-f330-438a-a3c1-c83e71f1ebe7 · outbound

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

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.762350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b73d6246-93f3-4368-88c4-970bc6c5cfa7 · outbound

This paper cites MovieChat+: Question-aware Sparse Memory for Long Video Question Answering.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph MovieChat+: Question-aware Sparse Memory for Long Video Question Answering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.765351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 437d1270-31e3-4984-8e90-bd84155314d3 · outbound

This paper cites Vipergpt: Visual inference via python execu- tion for reasoning.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Vipergpt: Visual inference via python execu- tion for reasoning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.957763Z

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.

Observation a5b72c30-35c9-4022-8741-26c3e5a64d9c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.770918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88415a62-705a-428f-a11b-fe8a0863cb71 · outbound

This paper cites Ada- coder: Adaptive prompt compression for programmatic vi- sual question answering.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Ada- coder: Adaptive prompt compression for programmatic vi- sual question answering

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.949613Z

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.

Observation 7488f1a5-dbe9-43d4-99f5-b28335ffd11a · outbound

This paper cites ViLA: Efficient Video-Language Alignment for Video Question Answering.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph ViLA: Efficient Video-Language Alignment for Video Question Answering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.776345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d416d066-b936-416a-be9e-7c95e9de30f6 · outbound

This paper cites Multi-object event graph representation learning for Video Question Answering.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Multi-object event graph representation learning for Video Question Answering

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:01:14.832565Z

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.

Observation ff6182f9-1f46-4c46-a885-50cc455b62bc · outbound

This paper cites Lin, and Shan Yang.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Lin, and Shan Yang

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.940973Z

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.

Observation a304a8b1-b8f2-4402-b061-e1be1a3df203 · outbound

This paper cites Next-qa: Next phase of question- answering to explaining temporal actions.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Next-qa: Next phase of question- answering to explaining temporal actions

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.931986Z

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.

Observation 66fa0fe5-85ee-4cbd-a34b-6af5a826998b · outbound

This paper cites Panoptic video scene graph generation.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Panoptic video scene graph generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.923372Z

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.

Observation 59da04ba-dce6-43e0-bb27-f2689270641f · outbound

This paper cites Hitea: Hierarchical temporal-aware video-language pre-training.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Hitea: Hierarchical temporal-aware video-language pre-training

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.915141Z

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.

Observation cf82f1df-f90a-417e-820c-0252b135159b · outbound

This paper cites Self-chained image-language model for video localization and question answering,.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Self-chained image-language model for video localization and question answering,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.906482Z

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.

Observation a46a9c46-72b0-4d6f-a180-cf40ee98ea68 · outbound

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

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph A simple llm framework for long-range video question-answering,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.897960Z

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.

Observation c4a9a83e-32cb-450f-9419-6bacb76822ad · outbound

This paper cites Scene Graph Generation: A Comprehensive Survey.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Scene Graph Generation: A Comprehensive Survey

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.798928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 601ee9d7-c920-4086-bbd6-fa27ee0eed10 · outbound

This paper cites Blip-2: bootstrapping language-image pre- training with frozen image encoders and large language models.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Blip-2: bootstrapping language-image pre- training with frozen image encoders and large language models

Reference 2011

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.014129Z

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.

Observation 2d8918c0-6144-4c31-8156-6cac6447526c · outbound

This paper cites Annotating ob- jects and relations in user-generated videos.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Annotating ob- jects and relations in user-generated videos

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:14.965752Z

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.

Observation ec729ce4-c5cc-4b2d-ae53-ea614241bbc9 · outbound

This paper cites The Llama 3 Herd of Models.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph The Llama 3 Herd of Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T00:01:14.720668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f17f6d06-23d4-4578-a86f-5c7997e98c73 · outbound

This paper cites H ´enaff.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph H ´enaff

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.076794Z

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.

Observation 9e38ea69-44dd-4392-bf0b-ca863ef50213 · outbound

This paper cites Video scene graph generation from single-frame weak su- pervision.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Video scene graph generation from single-frame weak su- pervision

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.069196Z

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.

Observation f9b52198-9885-4c3c-9785-495002c2ed05 · outbound

This paper cites Thinking, Fast and Slow.

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph Thinking, Fast and Slow

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:01:15.022345Z

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.

Pith citing papers

Observation a2985342-f94f-4a93-8025-16aeb2d2fd8d · inbound

Rethinking RAG in Long Videos: What to Retrieve and How to Use It? cites this paper.

Rethinking RAG in Long Videos: What to Retrieve and How to Use It? RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-03T15:28:33.982204Z

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.

Observation ef80f3f6-6590-4486-9016-d493673eabde · inbound

Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data cites this paper.

Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-14T14:53:56.693464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.