Paper Citation Record · LEDGER

G$^2$TAM: Geometry Grounded Track Anything Model

As of 8 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.03789.

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

pith.paper-citation-record.v1
2607.03789 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T23:56:52.009530Z

measured 18 of 18 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

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a0e79cc5-f833-4f3d-98fe-fe58c9fc55c4 · outbound

This paper cites Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D.

G$^2$TAM: Geometry Grounded Track Anything Model Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb859ce0-9be2-4510-afe3-b46617973ccf · outbound

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

G$^2$TAM: Geometry Grounded Track Anything Model ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01684f2e-885d-4528-b5d0-182573a6ee2e · outbound

This paper cites SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes.

G$^2$TAM: Geometry Grounded Track Anything Model SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593fcb7d-99d2-4276-83f8-2ed8bf40478b · outbound

This paper cites Crafting papers on machine learning.

G$^2$TAM: Geometry Grounded Track Anything Model Crafting papers on machine learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f8defb1-5b75-4237-8d1c-43c81f2000b1 · outbound

This paper cites Semantic-SAM: Segment and Recognize Anything at Any Granularity.

G$^2$TAM: Geometry Grounded Track Anything Model Semantic-SAM: Segment and Recognize Anything at Any Granularity

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad0b777-8d58-4ecf-9391-9c849c917c3d · outbound

This paper cites ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations.

G$^2$TAM: Geometry Grounded Track Anything Model ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab1d252-937b-42ed-8cd4-8684e05b8c26 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

G$^2$TAM: Geometry Grounded Track Anything Model DINOv2: Learning Robust Visual Features without Supervision

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f78e15-5830-44b7-9092-fb2f376a6ba7 · outbound

This paper cites The 2017 DAVIS Challenge on Video Object Segmentation.

G$^2$TAM: Geometry Grounded Track Anything Model The 2017 DAVIS Challenge on Video Object Segmentation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed0f0878-fbc9-4785-8cbb-ceb0fa58f3ed · outbound

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

G$^2$TAM: Geometry Grounded Track Anything Model SAM 2: Segment Anything in Images and Videos

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1068309-5839-4e15-a8fd-e9afc634e3f9 · outbound

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

G$^2$TAM: Geometry Grounded Track Anything Model $\pi^3$: Permutation-Equivariant Visual Geometry Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75455b46-ea1f-4277-91c1-37e3a05e8699 · outbound

This paper cites VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding.

G$^2$TAM: Geometry Grounded Track Anything Model VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f60f7822-4f5f-4953-a487-ded8df6f07c8 · outbound

This paper cites Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos.

G$^2$TAM: Geometry Grounded Track Anything Model Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f933e600-46e6-4317-af23-4d2d5d8dd5c5 · outbound

This paper cites Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation.

G$^2$TAM: Geometry Grounded Track Anything Model Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5df747a-f828-44c5-9865-3d7c4dfcaadf · outbound

This paper cites MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion.

G$^2$TAM: Geometry Grounded Track Anything Model MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13c9f45b-6c4b-4d20-9950-981ed7ff8ed9 · outbound

This paper cites From flatland to space: Teaching vision-language models to per- ceive and reason in 3d.arXiv preprint arXiv:2503.22976, 2025a.

G$^2$TAM: Geometry Grounded Track Anything Model From flatland to space: Teaching vision-language models to per- ceive and reason in 3d.arXiv preprint arXiv:2503.22976, 2025a

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64eb363-7dfc-4c76-934f-fd8a2a3b4655 · outbound

This paper cites an unresolved cited work.

G$^2$TAM: Geometry Grounded Track Anything Model Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e85a35b5-d17e-4736-b174-9ade2e382db5 · outbound

This paper cites To stabilize optimization, the data sampler ensures that each mini-batch contains only one data type.

G$^2$TAM: Geometry Grounded Track Anything Model To stabilize optimization, the data sampler ensures that each mini-batch contains only one data type

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82767fa5-f7b7-44b9-9325-40b453c9951e · outbound

This paper cites the keyboard closer to the window.

G$^2$TAM: Geometry Grounded Track Anything Model the keyboard closer to the window

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T23:56:52.009530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.