Paper Citation Record · LEDGER

SAE-V: Interpreting Multimodal Models for Enhanced Alignment

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 7 inbound Pith citation observations for arXiv:2502.17514.

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

pith.paper-citation-record.v1
2502.17514 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 7 of 7 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:10:20.348244Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T17:42:26.146474Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation a2da71b1-6def-4915-b75b-e768b7b39b48 · inbound

Visually Interpretable Subtask Reasoning for Visual Question Answering cites this paper.

Visually Interpretable Subtask Reasoning for Visual Question Answering SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T22:10:20.348244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3718863a-9e81-4eab-bf02-cd2c3667f1ca · inbound

Insights into a radiology-specialised multimodal large language model with sparse autoencoders cites this paper.

Insights into a radiology-specialised multimodal large language model with sparse autoencoders SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:42.634461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 982c4970-6ab6-49b9-b66c-fc711f66c449 · inbound

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models cites this paper.

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:51:15.556604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 54f5a48b-9ede-4177-8784-e63dcae1ba27 · inbound

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models cites this paper.

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:23:37.489944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d1a46366-9a7a-43f8-ab5d-4512702fee2c · inbound

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cites this paper.

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T22:49:10.125441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6c92b56c-319c-4776-8982-92702044c42a · inbound

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models cites this paper.

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:25:23.863287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e5eb263a-5b69-4d2d-a837-c5b65ace4820 · inbound

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition cites this paper.

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T17:42:26.148133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.