Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-11T20:06:55.102341Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2607.04319.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-11T20:06:55.102341Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-13T05:35:58.568346Z
A source-named dated measurement, never combined with another source.
Source: cited_works
14 of 14 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 516e9a00-9c20-423f-8dd8-5933890f4509 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Eliciting Latent Predictions from Transformers with the Tuned Lens
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a9e657b-287b-495e-bb2d-5aa7d759a9fc · outbound
Legible-by-Construction: Attention and End-to-End Transformers Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f34fa1d5-9cfc-493a-9470-dc84295675c7 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Softmax linear units
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87555c08-0e83-4cf0-ae23-cde7b5a07b5a · outbound
Legible-by-Construction: Attention and End-to-End Transformers Interpreting Attention Layer Outputs with Sparse Autoencoders
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 84580820-33dc-40a2-ad25-b70c95739731 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f74dd00b-be05-40a4-a6eb-8f82b200bfd7 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Bilinear MLPs enable weight-based mechanistic interpretability
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f5079130-d1f2-4118-a6e1-627332b5c157 · outbound
Legible-by-Construction: Attention and End-to-End Transformers TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4ea3e01-b25e-48db-861b-8dc620cab92f · outbound
Legible-by-Construction: Attention and End-to-End Transformers Theory, Analysis, and Best Practices for Sigmoid Self-Attention
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b637bd4-608e-461f-bb52-d782258aba24 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d09f6241-3780-4338-a501-091044b78a5e · outbound
Legible-by-Construction: Attention and End-to-End Transformers GLU Variants Improve Transformer
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af1c2717-da20-41c7-bb73-973bb2715865 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Dense SAE latents are features, not bugs.arXiv preprint arXiv:2506.15679,
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de236efa-f568-4a98-b507-9504b95eb3c0 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Codebook Features: Sparse and Discrete Interpretability for Neural Networks
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d0b6656a-3ac3-4dda-8d62-651e1933e341 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Analyzing Differentiable Fuzzy Logic Operators
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d4aabf59-6730-40f8-95d8-3a644025f4e2 · outbound
Legible-by-Construction: Attention and End-to-End Transformers Small-scale proxies for large-scale Transformer training instabilities
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3efa7add-bed7-471a-a6e2-890af8586706 · inbound
Training, Reading, and Editing Legible Transformers Legible-by-Construction: Attention and End-to-End Transformers
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.