Pith. sign in

Paper Citation Record · LEDGER

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

As of 11 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2412.16247.

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

pith.paper-citation-record.v1
2412.16247 v3

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:29:14.996369Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T18:43:02.162879Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T00:05:49.323859Z

Reference resolution

26 of 26 outbound references displayed

  • verified exact2
  • verified fuzzy9
  • unresolved13
  • parse uncertain0
  • malformed identifier2
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 81f0cbcf-d406-4af4-ade0-9d9d4066de38 · outbound

This paper cites As observed, the null space component consistently yields the same probing accuracy as the entire token, while the row space component yields significantly lower accuracy.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models As observed, the null space component consistently yields the same probing accuracy as the entire token, while the row space component yields significantly lower accuracy

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.344422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.982458Z digest=sha256:8fe15b9d79c925122809d4d03b7adf2898fc08bb134742b7d0d3cdd1a20d211f

Observation 2d888db0-5d58-446f-848f-f9af862b7397 · outbound

This paper cites interpretable.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models interpretable

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.297722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.996369Z digest=sha256:8606970631479f7e157fe5b24cd13090962ad44f83d3e67963cebd8421652a33

Observation 39d7b0a3-3ee1-4ab4-b9ca-a465bb906c26 · outbound

This paper cites MAViL: Masked Audio-Video Learners.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models MAViL: Masked Audio-Video Learners

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.911386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.911386Z digest=sha256:426d6eb580956c3f6aeb45df250919f77bd9d22e3c745cef7d49c5d06adba03f

Observation c2c85068-6845-4f40-adb0-1ed45183ced7 · outbound

This paper cites On the Origins of Linear Representations in Large Language Models.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models On the Origins of Linear Representations in Large Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.916489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.916489Z digest=sha256:d5fd937b3c849c3ccb60ecf9e59e4de1a295aace05bb8f012d33afebf4600211

Observation 8685ebf8-14e8-4d29-9708-c9a75c71e584 · outbound

This paper cites Madan, S., Henry, T., Dozier, J., Ho, H., Bhandari, N., Sasaki, T., Durand, F., Pfister, H., and Boix, X.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Madan, S., Henry, T., Dozier, J., Ho, H., Bhandari, N., Sasaki, T., Durand, F., Pfister, H., and Boix, X

Reference 11

Resolution
verified exact
doi, observed 2026-08-11T11:29:15.036100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.921152Z digest=sha256:279e27b45239e74b783bc22836da2827d660a104bbda28b85ac7f565c8327eff

Observation 65a598ac-5ff3-4f63-9cf4-e7cb9fcb3ca9 · outbound

This paper cites k-Sparse Autoencoders.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models k-Sparse Autoencoders

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.928321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.928321Z digest=sha256:b62349c486bb560d2d9eaae66bb025cb8840f36da7f65143569a991fe20a1807

Observation b2735643-cf66-4380-bb81-5cceed11e911 · outbound

This paper cites Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.953313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.953313Z digest=sha256:34ce891b6e8d7d9d918c28f284fa1b79d03944364321e2ca2ed5ad589c672d64

Observation b834b941-a731-48c4-85fe-ec8246217126 · outbound

This paper cites Codebook Features: Sparse and Discrete Interpretability for Neural Networks.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Codebook Features: Sparse and Discrete Interpretability for Neural Networks

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.958065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.958065Z digest=sha256:e2f74e549687b9aed6dd5c288a586574d709ba990b4bf226f687e521abba79bf

Observation e9c18b09-b752-4563-9976-e7787260a708 · outbound

This paper cites D., and Vidal, R.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models D., and Vidal, R

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.410731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.962734Z digest=sha256:073576d2ceb5f5bd4f668c3211524701820f0ba92c47bb52d848cc33cf1ff8c8

Observation b8469a04-fd8a-489b-bb4d-d8af79de99cf · outbound

This paper cites an unresolved cited work.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-11T11:29:15.395615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.967769Z digest=sha256:5100acaf3970a22749dcc319da1676f7825ec6e2f5da73b441ddab304558238d

Observation dafb5cd6-700f-4601-8444-9a3b85f4da44 · outbound

This paper cites Both blocks are connected via an encoder-decoder projection matrix W : Rde×dd with, in our case, de = 1664(ViT-G model from (Zhai et al., 2022)) and dd =.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Both blocks are connected via an encoder-decoder projection matrix W : Rde×dd with, in our case, de = 1664(ViT-G model from (Zhai et al., 2022)) and dd =

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.379738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.972742Z digest=sha256:9bbf3401f2d05cd4bd27a88e37019e8d4b79284f33b9be37a62cd74d7bbc3948

Observation ef94df38-d26d-49fa-a708-84485c5de7c8 · outbound

This paper cites # of non-zeros, and log10 learning rate (second and fourth).

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models # of non-zeros, and log10 learning rate (second and fourth)

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.328814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.987118Z digest=sha256:bd5bdac4b329c24df33974840ac50c1ba490f3efc71a09c9a4dfe75dc5c50e00

Observation 7759843a-3cee-421e-8d67-6aaac497e8ae · outbound

This paper cites Ablations In this section we present ablations on type of token, model size, sparsity and learning rate.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Ablations In this section we present ablations on type of token, model size, sparsity and learning rate

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.313071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.991697Z digest=sha256:7d42984e7f1cd5aa6db25ce51be1712ae89e75b137626e22b021126b93cfde3e

Observation cd799213-4d29-4cee-b33f-671da985df48 · outbound

This paper cites register.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models register

Reference 512

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.361519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.977365Z digest=sha256:5c4285b5c7245a0bcc3be86e1ed1ad7d48a7e439d88705f78dbd7cabb9d8b51d

Observation 60df42d6-abd6-4de0-9796-b052dab6b994 · outbound

This paper cites Linguistic regularities in continuous space word representations.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Linguistic regularities in continuous space word representations

Reference 1993

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.426266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.933607Z digest=sha256:d781732498877b475c116dd2b479b6c4fdc90a537d6525f070b2401912923bfa

Observation 7a28f4b4-19c4-43fa-8cc0-1319c5a15829 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 1997

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.943324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.943324Z digest=sha256:5f42788b1cafcc8ec8c68b05dbaf85fa523936eb60ea8c7a5d19f31edfeaf747

Observation 9edb8b5f-9959-4710-a3a7-30ce853eaba4 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Scaling and evaluating sparse autoencoders

Reference 1998

Resolution
malformed identifier
no resolver link, observed 2026-08-11T11:29:14.901067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.901067Z digest=sha256:9b4b2542d9324c6ea6e95fdb9bc4fc7e3ada82c81eeec9c1715d2b4c9ba88c2d

Observation 13b5d422-c246-4173-86bb-292b8db9cc34 · outbound

This paper cites MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations

Reference 2006

Resolution
verified exact
local_arxiv, observed 2026-08-11T11:29:15.282343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.869745Z digest=sha256:d3fd24ad8064e7d955df2a6c814c82cb8e0780bf950b725c7f634506df8faae0

Observation f353655c-e3c7-4930-833a-33793bfa0ea6 · outbound

This paper cites Emergent Linear Representations in World Models of Self-Supervised Sequence Models.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.938467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.938467Z digest=sha256:d10b2c77fbd795133871b207eee2018c48878b398b534aac3de9869726619f99

Observation 3a11f74c-e789-45b4-b24f-5d7c0d1659cb · outbound

This paper cites Vision Transformers Need Registers.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Vision Transformers Need Registers

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.880583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.880583Z digest=sha256:b42e2e21d2dc691cb2c0764dd5c43e723596db2400a46cc1565fc56335f49c2a

Observation 8768e7cb-cea6-4857-9bd4-ec815af0a779 · outbound

This paper cites Toy Models of Superposition.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Toy Models of Superposition

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.885636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.885636Z digest=sha256:1e67a7a941a0fe43ba026a6fe3776bdce4c2310b57036acf954dee55503ebfae

Observation d4135e80-c3a3-4dea-9e0c-7d6e652feb6f · outbound

This paper cites The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.906345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.906345Z digest=sha256:733021a9dd6cc20156aa02156dd71df60f17e04f196bc881e4fb406a2277ddc9

Observation f22c1272-38a3-455a-9aec-924a314f0cec · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.948541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.948541Z digest=sha256:0f17e04492f215bbeb4bafd50bebcad3f2032796e7768b9489bbeeced613ecc8

Observation ba6cee27-5674-4620-aefe-ee86224683a3 · outbound

This paper cites M., Kraus, O., Victors, M., Arumugam, L., Vuggu- mudi, K., Urbanik, J., Hansen, K., Celik, S., Cernek, N., Jagannathan, G., et al.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models M., Kraus, O., Victors, M., Arumugam, L., Vuggu- mudi, K., Urbanik, J., Hansen, K., Celik, S., Cernek, N., Jagannathan, G., et al

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T11:29:15.441518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-11T11:29:14.891088Z digest=sha256:d358154f1283424f5561c2d2661cc07d9eae585cb8f7e51a0ac896e4b2f3c07d

Observation 1052c760-23d3-4661-b152-2d00b615b01d · outbound

This paper cites A Primer on the Inner Workings of Transformer-based Language Models.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models A Primer on the Inner Workings of Transformer-based Language Models

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.896147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.896147Z digest=sha256:cc6e3f45e57d2599e030c13a52ba5eae8460ff6b76c30fa4fa5f09efabeb148f

Observation 82c49952-b78d-465d-954c-475dd65ada54 · outbound

This paper cites an unresolved cited work.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Unresolved cited work

Reference 2024

Resolution
malformed identifier
no resolver link, observed 2026-08-11T11:29:14.875674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.875674Z digest=sha256:51f3d897b1f86b63a63de9dc81d930fa1a7483433a99a191311e81eba1e3668d

Pith citing papers

Observation 681631c6-b373-4395-859a-9eb18dcf66bb · inbound

Learned Dictionaries with Total Variation and Non-Negativity for Single-Cell Microscopy: Convergence Theory and Deterministic Multi-Channel Cell Feature Unification cites this paper.

Learned Dictionaries with Total Variation and Non-Negativity for Single-Cell Microscopy: Convergence Theory and Deterministic Multi-Channel Cell Feature Unification Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-11T00:05:49.326100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-10T18:43:02.162879Z digest=sha256:5e041d6189cdeaec060e4e7f48c7350630624f787a352b64e933b61e6201ed58