Paper Citation Record · LEDGER

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

As of 22 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 1 inbound Pith citation observation for arXiv:2605.12374.

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

pith.paper-citation-record.v1
2605.12374 v4

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T22:13:22.015938Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T00:28:16.457842Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T00:28:16.754295Z

Reference resolution

11 of 11 outbound references displayed

verified exact0
verified fuzzy6
unresolved4
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 63aecf26-bfe9-4aa9-acbd-bcd60be42b6e · outbound

This paper cites Extending the same analysis to other pre-norm MLLMs is necessary before claiming cross-backbone universality.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Extending the same analysis to other pre-norm MLLMs is necessary before claiming cross-backbone universality

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.284361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 29b95761-43c7-424a-8cf2-e7cfedf7550d · outbound

This paper cites Retraining prior output-as-input methods on the same 49K curated data would further separate data effects from latent-feedback design effects.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Retraining prior output-as-input methods on the same 49K curated data would further separate data effects from latent-feedback design effects

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.286623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 045a9bed-65cf-4efa-a503-1d5df56d2bf5 · outbound

This paper cites an unresolved cited work.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-07-07T14:43:52.271982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d11169a0-1a62-4fa4-8734-e725d260f1db · outbound

This paper cites Section D adds a component-count sweep, but random-basis, no-mean, and matched-parameter full-head controls remain incomplete.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Section D adds a component-count sweep, but random-basis, no-mean, and matched-parameter full-head controls remain incomplete

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.280573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f4746b9f-0020-44bd-8e5a-575538d49f73 · outbound

This paper cites Stronger parser-latent faithfulness tests are left for future work.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Stronger parser-latent faithfulness tests are left for future work

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.288411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c00c0b22-a9dc-4f4e-ac7b-33e0766405f6 · outbound

This paper cites an unresolved cited work.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-07-07T14:43:52.278753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 37fa57a4-7d0e-468c-867d-8c206d579d16 · outbound

This paper cites How many bricks are missing in the wall?.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models How many bricks are missing in the wall?

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-07-07T14:43:52.268827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 668ce728-7afb-493e-9386-6386dfed5967 · outbound

This paper cites an unresolved cited work.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-07-07T14:43:52.277093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4b55c07f-b144-455a-97a2-7210e267953a · outbound

This paper cites an unresolved cited work.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-07-07T14:43:52.282366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d34fede7-e70d-4c15-ab19-743a3e1ac1a2 · outbound

This paper cites By the angle bisector theorem, the ratio of the segments created by the angle bisector is equal to the ratio of the other two sides.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models By the angle bisector theorem, the ratio of the segments created by the angle bisector is equal to the ratio of the other two sides

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.270539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3ef2c7a2-2080-48f3-a01b-8179bc1b4248 · outbound

This paper cites According to the angle bisector theorem, 𝐷𝐸 𝐴𝐸 = 𝐶 𝐷 𝐴𝐵.

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models According to the angle bisector theorem, 𝐷𝐸 𝐴𝐸 = 𝐶 𝐷 𝐴𝐵

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T14:43:52.273652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation 02be4c2c-655d-4632-b4e9-83dc11a6b19b · inbound

LUT: Latent Utility Training for Visual Reasoning cites this paper.

LUT: Latent Utility Training for Visual Reasoning Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T00:28:16.806836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.