Paper Citation Record · LEDGER

Prototype Transformer: Towards Language Model Architectures Interpretable by Design

As of 23 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2602.11852.

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

pith.paper-citation-record.v1
2602.11852 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T00:02:46.864302Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-13T17:43:52.716947Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T17:48:03.356591Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy0
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1bfac4d-6b43-4614-85e4-264b835edc9d · outbound

This paper cites GPT-4 Technical Report.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.028573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9e2236-62b9-4057-90da-077a4e4f759e · outbound

This paper cites in the”, “of the.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design in the”, “of the

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.752202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3da37f5-1912-488d-a78c-5bace7c0377c · outbound

This paper cites why does my dog eat poo p?.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design why does my dog eat poo p?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.576286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b5c5f2e-3e6c-48c2-92d8-1952187014cd · outbound

This paper cites Alignment faking in large language models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Alignment faking in large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.405381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adedb359-c754-481d-8284-abb4d84791ec · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.447448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46b28b14-7707-4f1e-a7d1-9d6078015bd1 · outbound

This paper cites an unresolved cited work.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.501260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe80cb7-8e10-468a-9df2-844fa94f8921 · outbound

This paper cites Interpreting Attention Layer Outputs with Sparse Autoencoders.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Interpreting Attention Layer Outputs with Sparse Autoencoders

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.553873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4374789-4366-41cb-9250-59ca772f2aa5 · outbound

This paper cites Decoupled Weight Decay Regularization.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Decoupled Weight Decay Regularization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.712646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b0442a0-0e4a-43bc-b578-13a5d9bbdb8b · outbound

This paper cites Revisiting Small Batch Training for Deep Neural Networks.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Revisiting Small Batch Training for Deep Neural Networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.801595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee98cb1-71ec-4910-927b-fcd4aa72dee5 · outbound

This paper cites Pointer Sentinel Mixture Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Pointer Sentinel Mixture Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.868311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fce6703-a533-4f72-8c27-92c5febd96ee · outbound

This paper cites A practical review of mecha- nistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646,.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design A practical review of mecha- nistic interpretability for transformer-based language models.arXiv preprint arXiv:2407.02646,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.980576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a63bffcf-1e9f-4821-adeb-6a6073a781d3 · outbound

This paper cites Sentence-BERT: Sentence embeddings using Siamese BERT- networks.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Sentence-BERT: Sentence embeddings using Siamese BERT- networks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.106968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc58d4da-ff62-462b-89c8-92d5539d6325 · outbound

This paper cites Neural Machine Translation of Rare Words with Subword Units.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Neural Machine Translation of Rare Words with Subword Units

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.222948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41941a36-071c-442f-a066-8c600b8b94ba · outbound

This paper cites BERT Rediscovers the Classical NLP Pipeline.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design BERT Rediscovers the Classical NLP Pipeline

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.502617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb975022-1a6e-46f5-adac-0c72f8705585 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design LLaMA: Open and Efficient Foundation Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.649779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5148a92f-9c00-473b-864f-105e0c29e300 · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.798192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08ba0b77-c02a-48c3-9a40-3b02ad92be0f · outbound

This paper cites MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.051367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ecbbd32-0886-4350-8b15-0a4a915caa04 · outbound

This paper cites Qwen3 Technical Report.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Qwen3 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.227111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 834de153-2f61-4a87-88ae-1c3586f40b90 · outbound

This paper cites Image classification at supercomputer scale.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Image classification at supercomputer scale

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.310196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bfe7acc-6173-4475-b784-2f6042fd6c09 · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.368866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2572600-d266-46aa-9b73-c18d7d38e2fe · outbound

This paper cites Deconstructing What Makes a Good Optimizer for Language Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Deconstructing What Makes a Good Optimizer for Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.444321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5bea32e-e11e-4c37-b82f-13aa38042664 · outbound

This paper cites to help us produce the prototype interpretability html.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design to help us produce the prototype interpretability html

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.512106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab81462-3c7d-4139-81fe-216efd394dbb · outbound

This paper cites You are analyzing a single prototype (a neuron-like feature) from a neural language model.\n.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design You are analyzing a single prototype (a neuron-like feature) from a neural language model.\n

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.864302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b00eba98-5974-4fa3-a4bd-be6ff0f33e8b · outbound

This paper cites an unresolved cited work.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Unresolved cited work

Reference 512

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.654475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40fa6dbd-3e7a-44e4-9b18-20d62b4e15f5 · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Automatically Interpreting Millions of Features in Large Language Models

Reference 1995

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.908484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ced3996-6364-4a23-a77f-5bc065fea788 · outbound

This paper cites GLU Variants Improve Transformer.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design GLU Variants Improve Transformer

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.387740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 020f9809-d3ca-4704-8415-ab7576d37bca · outbound

This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Jamba: A Hybrid Transformer-Mamba Language Model

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.629564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f2a1fc-a6e3-4916-ab4e-87dbfafc3d56 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.942638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c653af77-502d-40b8-8e35-261f826ecdd2 · outbound

This paper cites Toy Models of Superposition.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Toy Models of Superposition

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.238440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15f46023-078f-4a3e-ae84-15d5872d299b · outbound

This paper cites ReZero is All You Need: Fast Convergence at Large Depth.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design ReZero is All You Need: Fast Convergence at Large Depth

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.101431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75b0f373-ec3b-4ecf-9551-f1139e62d36c · outbound

This paper cites Dissecting Recall of Factual Associations in Auto-Regressive Language Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.289013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c45c933-8f46-44dc-921d-f26437a88557 · outbound

This paper cites The Llama 3 Herd of Models.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design The Llama 3 Herd of Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.342008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a80759-3718-4f16-ad06-a22a23c087d3 · outbound

This paper cites What Does BERT Look At? An Analysis of BERT's Attention.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design What Does BERT Look At? An Analysis of BERT's Attention

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.176347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ee83c8-71d3-4a93-938f-b8bb4da36bfc · outbound

This paper cites A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detection.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detection

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:46.162136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4fda4066-2b23-4177-af82-33dbb4f77ae8 · inbound

Collapse-Free Prototype Readout Layer for Transformer Encoders cites this paper.

Collapse-Free Prototype Readout Layer for Transformer Encoders Prototype Transformer: Towards Language Model Architectures Interpretable by Design

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-02T04:04:28.578289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f31719cd-a815-4e8c-a88d-662a3464dd50 · inbound

Graph Memory Transformer (GMT) cites this paper.

Graph Memory Transformer (GMT) Prototype Transformer: Towards Language Model Architectures Interpretable by Design

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-02T04:04:28.578289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.