Paper Citation Record · LEDGER

3D Primitives are a Spatial Language for VLMs

As of 13 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2605.12586.

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

pith.paper-citation-record.v1
2605.12586 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-14T21:32:52.151978Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

16 of 16 outbound references displayed

verified exact11
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 29923a26-1915-402c-9687-486c095ff4dd · outbound

This paper cites The spatial blindspot of vision-language models.arXiv preprint arXiv:2601.09954.

3D Primitives are a Spatial Language for VLMs The spatial blindspot of vision-language models.arXiv preprint arXiv:2601.09954

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:32:58.971089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 88bb82c5-b168-4f3c-851e-13051a645db3 · outbound

This paper cites Program Synthesis with Large Language Models.

3D Primitives are a Spatial Language for VLMs Program Synthesis with Large Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:59.011813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ddaba844-5d0e-4118-92c3-703ae95b5d4e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

3D Primitives are a Spatial Language for VLMs Evaluating Large Language Models Trained on Code

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:58.984612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6ce0409e-659a-400d-a9b0-c2e9eeda9b7e · outbound

This paper cites Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas.

3D Primitives are a Spatial Language for VLMs Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:32:58.976091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6e819d70-b53c-4a08-a7e8-fd370f09b088 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

3D Primitives are a Spatial Language for VLMs SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:58.966580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3919e01c-597e-449d-8440-06452b2dcc1b · outbound

This paper cites Linear mechanisms for spa- tiotemporal reasoning in vision language models.arXiv preprint arXiv:2601.12626.

3D Primitives are a Spatial Language for VLMs Linear mechanisms for spa- tiotemporal reasoning in vision language models.arXiv preprint arXiv:2601.12626

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:32:58.989163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8251b0b6-aeef-4f99-8a9e-9ef63a733bc7 · outbound

This paper cites Llava-st: A multimodal large language model for fine-grained spatial-temporal understanding.

3D Primitives are a Spatial Language for VLMs Llava-st: A multimodal large language model for fine-grained spatial-temporal understanding

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:32:58.980495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d3bef577-88ac-470e-aec5-a1f658d10457 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

3D Primitives are a Spatial Language for VLMs MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:58.993340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5718c137-5411-46f9-aa94-662b9553a17e · outbound

This paper cites Beyond semantics: Rediscovering spatial awareness in vision-language models.

3D Primitives are a Spatial Language for VLMs Beyond semantics: Rediscovering spatial awareness in vision-language models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:32:59.007937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 85ec4c39-6a78-462e-ba08-a55bebc4d37c · outbound

This paper cites Design2code: Benchmarking multimodal code generation for automated front-end engineering.

3D Primitives are a Spatial Language for VLMs Design2code: Benchmarking multimodal code generation for automated front-end engineering

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T21:33:00.156018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b26cd689-e332-4ab7-b3b7-eb13164ff188 · outbound

This paper cites SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition.

3D Primitives are a Spatial Language for VLMs SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:58.996935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 22ac36c4-05e4-483a-a7f6-901f8403ec98 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

3D Primitives are a Spatial Language for VLMs Instruction-Following Evaluation for Large Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:32:58.961463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 420c7853-ffb1-46d8-bd5a-dca623eecb9d · outbound

This paper cites scene_id.

3D Primitives are a Spatial Language for VLMs scene_id

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T21:33:00.159014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 53b51ad9-1b5b-46ad-a946-946cf8570ae0 · outbound

This paper cites best_cc /worst_cc use each model’s primitive-best / primitive-worst scene-code language from Table 1.∆best-direct = best_cc−direct(pp).

3D Primitives are a Spatial Language for VLMs best_cc /worst_cc use each model’s primitive-best / primitive-worst scene-code language from Table 1.∆best-direct = best_cc−direct(pp)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T21:33:00.145737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 05425b58-f0fc-4d3f-b2ce-6a9a31f3ae01 · outbound

This paper cites single-view S3-FT lifts SpatialBabel-QA by ∼+7% averaged across modes on Qwen3-VL-8B.

3D Primitives are a Spatial Language for VLMs single-view S3-FT lifts SpatialBabel-QA by ∼+7% averaged across modes on Qwen3-VL-8B

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T21:33:00.149167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3e247290-6e19-4148-894d-e046f4108f84 · outbound

This paper cites Pass rates: Qwen3-VL-8B 82%, Qwen2.5-VL-7B 84%.

3D Primitives are a Spatial Language for VLMs Pass rates: Qwen3-VL-8B 82%, Qwen2.5-VL-7B 84%

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T21:33:00.152345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.