Pith. sign in

Paper Citation Record · LEDGER

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness

As of 17 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2504.17068.

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

pith.paper-citation-record.v1
2504.17068 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:53:43.587917Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:32:05.458441Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

  • verified exact2
  • verified fuzzy27
  • unresolved17
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a83f8bc1-d6c1-4517-8edd-ca8146d3847f · outbound

This paper cites Evolutionary-scale prediction of atomic-level protein structure with a language model,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Evolutionary-scale prediction of atomic-level protein structure with a language model,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.319267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:42.980728Z digest=sha256:7adb20fad4b6fa5dfdf8e8ed92a06f21950a42fd7c6024f56f1f6ef0ebc63301

Observation 49d57f65-8b93-4c8d-87e3-4737c59379a5 · outbound

This paper cites Dnabert-2: Efficient foundation model and benchmark for multi-species genome,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Dnabert-2: Efficient foundation model and benchmark for multi-species genome,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.305480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.001465Z digest=sha256:fb142b5c5f6f52c9021776d05fe81cf6dc1a2db928ca7e0fd62b30d4a9e28cd7

Observation 7e2d4e48-4ce2-4e08-8063-11314df2f50d · outbound

This paper cites RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.006967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.006967Z digest=sha256:9bcb3c337347cfff92ec81924ecbfce0706ff1f8f15cb5536163fa420b35ac3f

Observation 2ad7630a-7ef6-4207-94c2-36750e6c87bf · outbound

This paper cites Transfer learning enables predictions in network biology,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Transfer learning enables predictions in network biology,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.244697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.012424Z digest=sha256:84978652577c4e19d3343fe68c86116cab6e13085d3f0632ad905bdfc3bc88f6

Observation f3c4227a-b4cb-4776-927a-a0252481c830 · outbound

This paper cites Multi-megabase scale genome interpretation with genetic language models.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Multi-megabase scale genome interpretation with genetic language models

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-08-16T10:53:43.936638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.018606Z digest=sha256:1264fba7ab52d9c9847ffac10eab7fc27ff31c4b7cc85eef7e47e3703b206f2e

Observation c702b97e-3e3f-4f71-a98b-3e703312fc82 · outbound

This paper cites Progen2: exploring the boundaries of protein language models,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Progen2: exploring the boundaries of protein language models,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.199954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.024378Z digest=sha256:045043f8f284bf77672f6fa8022748d01e308289a56b3ce84671c1f7d3dbffb2

Observation 503b9085-fdd2-40e9-975d-23bab68c2f28 · outbound

This paper cites Sequence modeling and design from molecular to genome scale with evo,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Sequence modeling and design from molecular to genome scale with evo,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.028603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.028603Z digest=sha256:dc7b5a485b1e797dc4bd78b108b7439f8a1c7dfc895249bb2964acfb2d38b92b

Observation 5c537820-ff51-4f5a-ad15-fe7334b54518 · outbound

This paper cites Rna language models predict mutations that improve rna function,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Rna language models predict mutations that improve rna function,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.170131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.055707Z digest=sha256:1bf28872f03633295d7d01ab0f4ff273eff5f38acd385594709a3df7525e214a

Observation 79a8a0f7-2aee-4695-aa2e-58220f20cf1a · outbound

This paper cites Designing proteins with language models,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Designing proteins with language models,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.113724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.135319Z digest=sha256:f0286bffea2e83c68fba91eda5b4950453995109cf52ab5e812c6897481b3854

Observation 49437d78-c7fc-41cf-b9f8-c5c773ab7a20 · outbound

This paper cites Proteingym: large-scale benchmarks for protein fitness prediction and design,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Proteingym: large-scale benchmarks for protein fitness prediction and design,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.095195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.192626Z digest=sha256:5c0d5a36a758f19648c7f066688be5b992d95c633391507d60b681199b04ac02

Observation 170542f8-83c8-4b08-afa2-ef8185e1c8b4 · outbound

This paper cites Benchmarking dna sequence models for causal regulatory variant prediction in human genetics,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Benchmarking dna sequence models for causal regulatory variant prediction in human genetics,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:45.023724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.196846Z digest=sha256:c4861b1b0591cd3b30f818932e3737bfe9493484ace25717e7a56b0a9bdb93f2

Observation a7cc7553-b4f3-448a-8fa0-d06f290c1137 · outbound

This paper cites Genome modeling and design across all domains of life with evo 2,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Genome modeling and design across all domains of life with evo 2,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.996491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.201413Z digest=sha256:b5ba363fecd6dbdd6645827e523cd92cbf039285a92f77789568ed4d3feb44c0

Observation 2f9fee4f-66cf-4c21-8a91-109f3e7eac74 · outbound

This paper cites Protein language models are biased by unequal sequence sampling across the tree of life,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Protein language models are biased by unequal sequence sampling across the tree of life,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.981651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.205627Z digest=sha256:07349f46970e606a05bd9d82ee41f26eca3c9d7a737f757e54ddc774ad1f6046

Observation d5f7a1c8-afa6-4246-8360-3acd3a22a7ea · outbound

This paper cites Removing bias in sequence models of protein fitness,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Removing bias in sequence models of protein fitness,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.209582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.209582Z digest=sha256:c919e8f147c3420932c55b379d127e081e391bd707d98ca2259e752251505d6a

Observation e2f586d3-fb62-40f5-8672-ff87fcbb9674 · outbound

This paper cites Protein language model fitness is a matter of preference,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Protein language model fitness is a matter of preference,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.900360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.213571Z digest=sha256:06546cb715a5a165bcaa628931d219b64a68775b3c6f54a61168335c84d122ca

Observation 96209bd8-360d-4cd0-82f3-8088a5e86823 · outbound

This paper cites Masked Language Model Scoring.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Masked Language Model Scoring

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.217723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.217723Z digest=sha256:153ef04aaf216b926317c896b3f99498654106836a21fdb03610ab7fe0027f14

Observation 25c14cb3-aff0-4cbb-acfd-8df2b8d889f0 · outbound

This paper cites Cd-search: protein domain annotations on the fly,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Cd-search: protein domain annotations on the fly,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.885301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.221864Z digest=sha256:901693cbbd1dbd93e16fe70d7b394af8c20b00ba7ec14e2d53f357e6e05ff750

Observation 7f95dc1b-5417-4602-ad37-7698edbf962b · outbound

This paper cites Cdd/sparcle: the conserved domain database in 2020,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Cdd/sparcle: the conserved domain database in 2020,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.835077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.225240Z digest=sha256:6062a1b8ec8f17c3d842cfd3f9e836c8830463043e2e823bb2a78e4768041c71

Observation 2246efb3-35a5-4ef6-8071-0c9e336213ca · outbound

This paper cites Pseudo-perplexity in one fell swoop for protein fitness estimation,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Pseudo-perplexity in one fell swoop for protein fitness estimation,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.228963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.228963Z digest=sha256:925ea9639a2ca454a7f2c8acc69d784f356012c0c2cf7f65d0ea73928118982c

Observation d78742a6-2dc1-48e5-9e8d-bc1d67309910 · outbound

This paper cites The mechanistic basis of data dependence and abrupt learning in an in-context classification task.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness The mechanistic basis of data dependence and abrupt learning in an in-context classification task

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.232684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.232684Z digest=sha256:6e92d1649fcb88aed331fb746cfaa5ea66488af89dd0d8ffa9b143ea0a08d2ec

Observation f8533fbc-94b6-4e95-aa6b-7cc3a8c45a19 · outbound

This paper cites Data distributional properties drive emergent in-context learning in transformers,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Data distributional properties drive emergent in-context learning in transformers,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.769103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.237119Z digest=sha256:a5827674135f1a9cdc6e00edd5da023de33b6c56100bcdb7d0a5d27017c2b8ba

Observation 1c238229-1dd6-474e-aa8e-11ece2dcf3b3 · outbound

This paper cites The transient nature of emergent in-context learning in transformers,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness The transient nature of emergent in-context learning in transformers,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.745053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.240508Z digest=sha256:3223cc83f3d8c9002a730f23494fa4bbb02444405c7f7cc266a3e5e23f6428f4

Observation 06c3435c-03f8-4a9d-85ae-30832db2ead1 · outbound

This paper cites A mathematical framework for transformer circuits,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness A mathematical framework for transformer circuits,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.681802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.244141Z digest=sha256:b8567aa13c5d989a1cb287781af4e175febb0403dd0c0f4c57d2b0ddf41b0cd8

Observation 101cc215-76a4-4175-b185-a127293098a9 · outbound

This paper cites In-context Learning and Induction Heads.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness In-context Learning and Induction Heads

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.247875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.247875Z digest=sha256:d1dde5d0a74367410b37146059937569d697ce3d8ae89c620630d3a465fafac9

Observation b358f9ca-293d-404c-bf56-0b5153c03dd5 · outbound

This paper cites Language models are few-shot learners,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Language models are few-shot learners,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.295312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.295312Z digest=sha256:cbfdf99af62f0851e072f79cb0a335f5e26cbcb54f1d83a39312efd927224f37

Observation 49d14125-9806-4202-83ef-439814f38468 · outbound

This paper cites What learning algorithm is in-context learning? Investigations with linear models.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness What learning algorithm is in-context learning? Investigations with linear models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.355517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.355517Z digest=sha256:6bce9d4d83a0097928907fcd9ca74f33373b7061746e50088d2785365d1c4348

Observation 3012d045-e4ca-4321-8edf-221f54e4c3dc · outbound

This paper cites Transformers learn in-context by gradient descent,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Transformers learn in-context by gradient descent,

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.658870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.360424Z digest=sha256:9c5f095b87cabefb89483097dac5aaa301d33f37597344c432697ba449446a32

Observation ba1a77f6-63aa-4437-afa2-e27200cdcb01 · outbound

This paper cites Competition Dynamics Shape Algorithmic Phases of In-Context Learning.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Competition Dynamics Shape Algorithmic Phases of In-Context Learning

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.364085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.364085Z digest=sha256:927e5f7c082dc3c4f4406db81d10c3c1c7fcccb6e8f84f7be336c260d965a09a

Observation dd35be21-d905-4087-a373-47113d9098d0 · outbound

This paper cites Attention is all you need,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Attention is all you need,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.368691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.368691Z digest=sha256:ce9406ee2853d75caea8c206b74f5c483ea6a4243d5befaa421dffe4c25beebc

Observation 2202be62-e10b-4936-b8f6-f77765b59675 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.373076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.373076Z digest=sha256:c2e15d938ff33dee4b1ad80f12c699c178bfe104edf31ad33013148341e693bc

Observation 92a6359c-c1af-4f7a-a7bd-7e4d039fa545 · outbound

This paper cites Language models are unsupervised multitask learners,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Language models are unsupervised multitask learners,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.537987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.377269Z digest=sha256:e481c3bfb3e399e4798ec760c282e89527661daed2ebb693eea3369d4e7edc03

Observation 0b535fe9-c0c0-4520-a6e6-69c9ff40db97 · outbound

This paper cites Convolutions are competitive with transformers for protein sequence pretraining,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Convolutions are competitive with transformers for protein sequence pretraining,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.380545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.380545Z digest=sha256:a91bfe1867ae72f5b19b2ed7ffa22010b4fa3543f5a6a078b550f2340debedcb

Observation 8a851906-9e35-48df-ad51-e8abbb2bf090 · outbound

This paper cites Long-context protein language model,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Long-context protein language model,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.511605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.384611Z digest=sha256:58e4e2be13c47172bcb1c17c3fd9f3ab460d91c63c308b471c5a58de65ec3dc9

Observation a51fb5f1-63cb-48f7-861b-9d725b4c5541 · outbound

This paper cites Larger language models do in-context learning differently.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Larger language models do in-context learning differently

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.389602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.389602Z digest=sha256:27c3aa5de015608dd31719ffe75ae8bfbdb639ecab461983362e0d791f6b4244

Observation bae34c45-c0cf-4c11-82f6-4460a06912d5 · outbound

This paper cites Amino acid metabolism conflicts with protein diversity,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Amino acid metabolism conflicts with protein diversity,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.394219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.413524Z digest=sha256:ef53bc87bb49b4478aacc78fc8514c76ba2b6a4a725dfb2a54a2808001e31054

Observation 6d299b79-69ca-424d-af94-fb4230f6a1d7 · outbound

This paper cites Lost in the middle: How language models use long contexts,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Lost in the middle: How language models use long contexts,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.481338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.481338Z digest=sha256:ac21be420853d3983ae8dfe88484c72d9889b94edd3c7f3bf7e3dbdb41dcde4e

Observation ca8c5e2f-7154-4333-bee1-42dc5277916d · outbound

This paper cites Hairpin rna: a secondary structure of primary importance,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Hairpin rna: a secondary structure of primary importance,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.367243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.500446Z digest=sha256:fe25a61b84266783bd63d9ede8d280a450bec4d8a25a0a1eb75bf555d68dbb7d

Observation a9f3617a-5a01-4b57-8ce2-59081736c9fe · outbound

This paper cites Protein codes promote selective subcellular compartmentalization,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Protein codes promote selective subcellular compartmentalization,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.268114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.505404Z digest=sha256:087f6f2b781f0103c2799e026113fa480fecd882ffc60cdf918c120ed5503574

Observation 044e5c10-f726-4858-b5f7-ac880a9307dd · outbound

This paper cites Netgo 3.0: protein language model improves large-scale functional annotations,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Netgo 3.0: protein language model improves large-scale functional annotations,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.237678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.511447Z digest=sha256:0af56d43cde45f4b32a802053da3ed0d71e3163d1023ef04f8eff8c3495600c1

Observation 6a02b6b9-7006-4a16-bb66-46f361ba3d3b · outbound

This paper cites Protein repeats: structures, functions, and evolution,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Protein repeats: structures, functions, and evolution,

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.222460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.516681Z digest=sha256:b894d84edb3f4613a65b5ee16586554a2fae26c92d19d5dadf1b35b550926dd6

Observation f436f8ab-0113-427e-8c14-e7956115154a · outbound

This paper cites Parallel Structures in Pre-training Data Yield In-Context Learning.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Parallel Structures in Pre-training Data Yield In-Context Learning

Reference 41

Resolution
verified exact
local_arxiv, observed 2026-08-16T10:53:43.767456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.520782Z digest=sha256:f9ff1ab20fe7856e676ed91355354891087aaaf52512a836cf7f5589ed554b77

Observation c5ac879b-e5da-43bb-89b1-12e6e02d58f8 · outbound

This paper cites A practical review of mechanistic interpretability for transformer-based language models,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness A practical review of mechanistic interpretability for transformer-based language models,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.525178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.525178Z digest=sha256:9280a90d77116592ba9b6fd6e53158e36f1278aafa1fde8ee1388e79f312f6d0

Observation 28d44e32-c24d-4899-a8c7-35eaef233baa · outbound

This paper cites Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-16T10:53:43.530364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:53:43.530364Z digest=sha256:fc4be700a95a872c0a92878b6d22bc4f1b58bda576e03aae0d5b15f99ab2af3b

Observation 6edde657-040d-4060-923c-27a8ef683afa · outbound

This paper cites Can models learn skill composition from examples?,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Can models learn skill composition from examples?,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.129629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.576803Z digest=sha256:c7a01c64f4d3db69f8159f31dd1133cdcb833542fb48e8c669061bffbcdf52f4

Observation a034056b-a65a-4d1b-a146-08d3b5185be8 · outbound

This paper cites Uniprot: a hub for protein information,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Uniprot: a hub for protein information,

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.107550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.582063Z digest=sha256:c71a2245d0103fc472bdc48240f0bf8fa1f0604039cc684eec0aa9f4e8e12698

Observation eef770fa-7367-484f-b374-6e1bb44cd924 · outbound

This paper cites Mmseqs2 enables sensitive protein sequence searching for the analysis of massive data sets,.

In-Context Learning can distort the relationship between sequence likelihoods and biological fitness Mmseqs2 enables sensitive protein sequence searching for the analysis of massive data sets,

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:53:44.026723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-16T10:53:43.587917Z digest=sha256:76bda8a4c38bddf67322650f811f3f76db16a2add8e835b5d72120ae0808fad2

Pith citing papers

Observation d5176445-c058-4dca-9223-10415180d8c3 · inbound

Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models cites this paper.

Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models In-Context Learning can distort the relationship between sequence likelihoods and biological fitness

Reference 2022

Resolution
malformed identifier
no resolver link, observed 2026-08-02T20:32:05.458441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T20:32:05.458441Z digest=sha256:610d95b4dc49115fdfa1007ad269a20bb35f464815821ce8e574c3f9d07b65e0