Pith. sign in

Paper Citation Record · LEDGER

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

As of 17 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 12 inbound Pith citation observations for arXiv:2509.05296.

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

pith.paper-citation-record.v1
2509.05296 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:26:50.790923Z

measured 29 of 29 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 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:33:39.212752Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T07:16:44.844161Z

Reference resolution

17 of 17 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved15
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25591e64-741c-413f-8c5a-bf7a3bb307ac · outbound

This paper cites Photo tourism: exploring photo collections in 3d.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Photo tourism: exploring photo collections in 3d

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.749545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.749545Z digest=sha256:2a6c538efe3fe75d66fcc39baf919c8a645a35dfc1423fffef212cf93cf6102d

Observation 3fd812be-c0db-468b-8127-e05c3250452c · outbound

This paper cites BA-Net: Dense Bundle Adjustment Network.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool BA-Net: Dense Bundle Adjustment Network

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.754806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.754806Z digest=sha256:4159fc183c4c32856a764604f5c7722b434d60aea8ccc28eadc919cbf0e87858

Observation 8c0fc5c6-19ce-4602-923f-a7022226e06b · outbound

This paper cites 3D Reconstruction with Spatial Memory.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool 3D Reconstruction with Spatial Memory

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.766675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.766675Z digest=sha256:5d7275e124eceec49feea1c1d36e70a2558a5ad22bdd37ab888a4f19320a39d3

Observation edd19479-f11f-4ce4-a06d-5480be5427e2 · outbound

This paper cites $\pi^3$: Permutation-Equivariant Visual Geometry Learning.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool $\pi^3$: Permutation-Equivariant Visual Geometry Learning

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.776428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.776428Z digest=sha256:70d7b0f77bc08fa4883329a7dd6eb9ddfc289da94f7f55081196eba0a98e80a8

Observation e7934739-36be-4573-a5a1-8c81dd8bc253 · outbound

This paper cites Streaming 4D Visual Geometry Transformer.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Streaming 4D Visual Geometry Transformer

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.790923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.790923Z digest=sha256:37ab26047d11211544dccaf79d18099f2629b13a5c61f4ecd0bd67e9662e8c7b

Observation f1d611f1-8028-4d18-ba48-6efb64200a2a · outbound

This paper cites an unresolved cited work.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Unresolved cited work

Reference 2004

Resolution
unresolved
raw_fallback, observed 2026-08-15T16:26:51.069786Z

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.

source=pdf_text observed=2026-08-15T16:26:50.728399Z digest=sha256:150ef6324b4d9b70d724cb819f7b7c0b7937c32b32a5dea1bf072fb91b338823

Observation 1c289d2f-541f-4071-af58-049658d14119 · outbound

This paper cites DeepVerse: 4D Autoregressive Video Generation as a World Model.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool DeepVerse: 4D Autoregressive Video Generation as a World Model

Reference 2008

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.717720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.717720Z digest=sha256:664a5fd42220f8ba71e3508895cafe14e714fa2523d4fa0f4504506825e39540

Observation 3d9381d2-066f-4372-9a11-0e7be8932639 · outbound

This paper cites Point3r: Streaming 3d reconstruction with explicit spatial pointer memory.arXiv preprint arXiv:2507.02863,.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Point3r: Streaming 3d reconstruction with explicit spatial pointer memory.arXiv preprint arXiv:2507.02863,

Reference 2011

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.781549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.781549Z digest=sha256:2dbc0717086128953f13a428748132769c67f80358c0c6ebc69af3c2625be25d

Observation dde7c5bd-a274-47ca-ae36-374fb60df4cf · outbound

This paper cites Lie-algebraic averaging for globally consistent motion estimation.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Lie-algebraic averaging for globally consistent motion estimation

Reference 2013

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T16:26:51.085287Z

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.

source=pdf_text observed=2026-08-15T16:26:50.723581Z digest=sha256:0167c8cac94714fe0f5e4e6444281d14c793bdef895ad214aeed9668ec22933c

Observation c0f8085f-50c6-4cd1-95f6-176847c2ad25 · outbound

This paper cites Aether: Geometric-Aware Unified World Modeling.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Aether: Geometric-Aware Unified World Modeling

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.760211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.760211Z digest=sha256:7fa547be43b2c0c14b5f3792968ccb6397130cc94e88d0255be7395340cb7aad

Observation aa1f140f-420a-4bdb-8ebd-27dcad2e0bcc · outbound

This paper cites CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.739500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.739500Z digest=sha256:2046669a08eccba7ca66a65179ed747ba656217329dd41b50a6e0c09b350e36d

Observation 24f75ccc-5124-4b93-859b-7267a491aac8 · outbound

This paper cites Decoupled Weight Decay Regularization.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Decoupled Weight Decay Regularization

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.744274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.744274Z digest=sha256:fce295570ad70eb2467c0af966b2fd13ae515cd0065a234d13b62b272b596467

Observation e26320d6-7dd8-46af-b5f4-58876faff4cd · outbound

This paper cites Continuous 3D Perception Model with Persistent State.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Continuous 3D Perception Model with Persistent State

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.771417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.771417Z digest=sha256:10fa5a221bd85d4a760cbe3abe693e6d612b8941ff9fa4884845bb543d979654

Observation 0ffa7494-45c6-4e99-a955-3b9ea41a6073 · outbound

This paper cites Using multiple hypotheses to improve depth-maps for multi-view stereo.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Using multiple hypotheses to improve depth-maps for multi-view stereo

Reference 2021

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T16:26:51.100556Z

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.

source=pdf_text observed=2026-08-15T16:26:50.712382Z digest=sha256:2d8393ca301a2b1c1d6984e71a0495573cf97e94e6fbf847631feef4e8768d12

Observation fc59d3c8-d6c3-4b8c-8f71-3ad26a56f44d · outbound

This paper cites ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.699098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.699098Z digest=sha256:438dd8eddf89187e1511dc8538eaf738565f051a164d5ebdd84dddca5ca9f755

Observation cb6b9a03-0128-4ba2-9944-fa2bffec0c6d · outbound

This paper cites Megadepth: Learning single-view depth prediction from internet photos.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Megadepth: Learning single-view depth prediction from internet photos

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.733765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.733765Z digest=sha256:cfe9ca24bea67fc88c584c89d56e27d51837396991f7ec1df23a5c2f58abbb0e

Observation 4c9fd0b6-4935-4fcf-9bea-e1093822afa6 · outbound

This paper cites Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass.

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-15T16:26:50.785821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:26:50.785821Z digest=sha256:e3c7ad10df26412134cb4a59c01da0c9cef6319a31267bad94c85c1d1d98a340

Pith citing papers

Observation ec5bbb20-52f9-4bc9-b729-bc03aa5e9cd4 · inbound

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction cites this paper.

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-03T06:33:39.212752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T06:33:39.212752Z digest=sha256:bb8263acc1a7ae2c3133fec755de59f15ba5261444cf43acf5ee8fe53a94ff24

Observation c3cfdaed-ed39-41d2-80f2-dae5e3710ea0 · inbound

FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry cites this paper.

FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-15T14:46:08.263997Z

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.

source=pdf_text observed=2026-05-15T14:41:38.781110Z digest=sha256:e840ff393a6205fe1cd3fbfae47940566ecae954ffa655d53e72c81e2b636b73

Observation d6aa9b5d-d39e-4bed-b981-2c3dddcb8778 · inbound

2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction cites this paper.

2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-13T21:45:59.210064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T21:45:59.210064Z digest=sha256:7accc364b54aa739a0ac172bd110323ecffa507abc6b23412a6b56929a69d3e2

Observation b56770ab-fadf-4ba1-b38d-5bf584d2b0da · inbound

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective cites this paper.

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 104

Resolution
verified exact
arxiv_id, observed 2026-05-10T13:20:26.313310Z

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.

source=pdf_text observed=2026-05-10T13:13:42.052386Z digest=sha256:af426f7100ba6333ff7b2f114ae5c470dbe69e5942f7976db7fd97bc24c610cc

Observation e67de1b4-c2fa-47d7-ba00-df493979cf3f · inbound

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval cites this paper.

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 60

Resolution
verified exact
arxiv_id, observed 2026-05-12T06:06:27.216060Z

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.

source=pdf_text observed=2026-05-12T04:34:27.255728Z digest=sha256:fa7e47e1bda2e29eaeb03b404a24be64c42cb8d56b0b178c940f44fabf8fb755

Observation e4083b65-1485-4d8b-86a0-2712aee31849 · inbound

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer cites this paper.

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 67

Resolution
verified exact
arxiv_id, observed 2026-05-15T14:00:03.366493Z

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.

source=pdf_text observed=2026-05-15T13:56:17.912350Z digest=sha256:54f7672e26101203d6b886bd8ccd5d53989dfbaead30c9652bab807ff1f44e0c

Observation c54d867d-0eec-44f4-b529-a1354b7c74c0 · inbound

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction cites this paper.

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-19T20:17:45.652379Z

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.

source=pdf_text observed=2026-05-19T20:13:39.983216Z digest=sha256:c31e11ea57a934c00019ed45318f4c5921eb21a7561b9fd455a37d7d266939e4

Observation 01c784c1-5a43-4247-933f-a154091937ec · inbound

Geo-Align: Video Generation Alignment via Metric Geometry Reward cites this paper.

Geo-Align: Video Generation Alignment via Metric Geometry Reward WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 36

Resolution
verified exact
arxiv_id, observed 2026-05-25T04:16:35.969661Z

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.

source=pdf_text observed=2026-05-25T04:15:58.667672Z digest=sha256:309f9f70c5fa230b70f8378d14c4da444422f989ea804efecfd43737d282f419

Observation b878f9e0-26a6-48c7-8d7b-f8dadc244b80 · inbound

SpatialBench: Is Your Spatial Foundation Model an All-Round Player? cites this paper.

SpatialBench: Is Your Spatial Foundation Model an All-Round Player? WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 55

Resolution
verified exact
arxiv_id, observed 2026-06-29T17:53:47.249878Z

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.

source=pdf_text observed=2026-06-29T17:49:58.532910Z digest=sha256:d9eefb5b2772f4a1a520065efe6a0753abc42eae36b0963ad60080aef22ba2cd

Observation 204d9663-2424-41e4-8462-f98ed73d8bf2 · inbound

Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping cites this paper.

Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-07-02T07:16:44.846658Z

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.

source=pdf_text observed=2026-06-28T07:02:35.276984Z digest=sha256:27726300f59a71bec26a74c8a4ea84bc54857df5bc303fb1781d891a353ed76e

Observation e9d1e0f8-b51a-4046-81c5-75350aa7aa25 · inbound

Glob3R: Global Structure-from-Motion with 3D Foundation Models cites this paper.

Glob3R: Global Structure-from-Motion with 3D Foundation Models WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-13T01:21:15.228734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T01:21:15.228734Z digest=sha256:80b5a5d4518a530deb17ff72c46e16adb3b43ae0b3da41b38184b4c6f17a073c

Observation d2f8b45b-8f2f-4032-9e8b-823ae91c54e0 · inbound

IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer cites this paper.

IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T13:07:07.231951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T13:07:07.231951Z digest=sha256:36443b76a7a4f0f3d44c07d1d8bb1151f0c91ed966ae5bd20ca6d306978ed4b1