Pith. sign in

Paper Citation Record · LEDGER

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models

As of 9 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2607.22646.

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

pith.paper-citation-record.v1
2607.22646 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:12:29.164418Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

53 of 53 outbound references displayed

  • verified exact1
  • verified fuzzy0
  • unresolved51
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7f631c19-d856-43db-a864-e262afe4c9ba · outbound

This paper cites Fine-grained analysis of sentence embeddings using auxiliary prediction tasks.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Fine-grained analysis of sentence embeddings using auxiliary prediction tasks

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:28.991486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:28.991486Z digest=sha256:007579ae943d87267eac8d7fb978b16b5fc32cc34bbb3b877668d7391fb0c005

Observation 7284c72d-5aad-4231-951d-fd0fbcbb0875 · outbound

This paper cites Transformers as implicit state estimators: In-context learning in dynamical systems.Transactions on Machine Learning Research, 2026.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Transformers as implicit state estimators: In-context learning in dynamical systems.Transactions on Machine Learning Research, 2026

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:28.995564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:28.995564Z digest=sha256:08e2d76ea3ef8fa0f0b48bad7c764c0d3b24cdc2550db464c1e606f8fc8954e9

Observation 88c62d28-d4aa-435c-93f8-199b75b9556f · outbound

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

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models What learning algorithm is in-context learning? investigations with linear models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:28.999109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:28.999109Z digest=sha256:1c06b76a47a482cad125319de921c155a7445735189fcb42ff31c55aa40f0824

Observation 055a8db7-e6d6-4642-abc2-b40e32ebbf21 · outbound

This paper cites Understanding intermediate layers using linear classifier probes, 2017.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Understanding intermediate layers using linear classifier probes, 2017

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.002614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.002614Z digest=sha256:a30c9b42c1cd441e31e150b49d5a948388900d45fc5a69164169784d4ad0db7b

Observation 7ce2e015-b49d-4509-9b31-fe5c0caf6246 · outbound

This paper cites Transformers as statisticians: Provable in-context learning with in-context algorithm selection.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Transformers as statisticians: Provable in-context learning with in-context algorithm selection

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.006008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.006008Z digest=sha256:3709c860a4807bc7c22df191965b9123d8d51bb018282f6c9ef2c06b89f4361c

Observation 5d38cc5d-6ee0-474d-b2df-38f0b04d22c4 · outbound

This paper cites A maximization technique occurring in the statistical analysis of probabilistic functions of markov chains.The annals of mathematical statistics, 41(1):164–171, 1970.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models A maximization technique occurring in the statistical analysis of probabilistic functions of markov chains.The annals of mathematical statistics, 41(1):164–171, 1970

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.009564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.009564Z digest=sha256:b8f4b9d566185464d215027af193d85e3e85f70294153b75af0d4b6ce99ccdab

Observation 5bc0ff0e-cdc1-48f9-9298-0873790dd731 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.013186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.013186Z digest=sha256:d3cc9710c1bd1775ffb8b34d77660cfaa0dc189c19b0c52a31ae3f3cbc3d7dd5

Observation fe2fc961-b621-48d0-b238-f6157fe99718 · outbound

This paper cites What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.016164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.016164Z digest=sha256:e794b8bd429a31b9c61e4d825327692b8a45c41094ecdc9a12c1dd8f14879e8f

Observation 14833cae-8e65-4415-b6dd-a84e5c56ddd4 · outbound

This paper cites Cover and Joy A.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Cover and Joy A

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.019627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.019627Z digest=sha256:e5085c234a1e63a4586cd36edaf4627aaa015cebaea25127c9b0fec17a5937df

Observation 2699e194-2daa-4537-8a30-3b2a925b4063 · outbound

This paper cites an unresolved cited work.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.023107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.023107Z digest=sha256:74f5bafaa9c282ecbe841210b1d60b04b2320eed1c0eabe6aa760567d7a7611a

Observation 7800832d-3a90-40b5-92ec-44bbc5660743 · outbound

This paper cites Transformers learn latent mixture models in-context via mirror descent.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Transformers learn latent mixture models in-context via mirror descent

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.026455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.026455Z digest=sha256:e0595cc916e7515bf607cb37a80f3d6a02340b78fb4a2a0e5abd2a714f752575

Observation 84b70fc3-3759-466a-bc54-e0d3ed650ab5 · outbound

This paper cites Edelman, eran malach, and Surbhi Goel.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Edelman, eran malach, and Surbhi Goel

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.030080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.030080Z digest=sha256:8d2413911d72957d2ee682774c70f3a3dc00e927e33dde4dcfab123d4f1a7abe

Observation 0592f36f-0d82-470e-8f85-35694a46e638 · outbound

This paper cites What one cannot, two can: Two-layer trans- formers provably represent induction heads on any-order markov chains.arXiv preprint arXiv:2508.07208, 2025.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models What one cannot, two can: Two-layer trans- formers provably represent induction heads on any-order markov chains.arXiv preprint arXiv:2508.07208, 2025

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.033528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.033528Z digest=sha256:6044f232c34977d624fc19c5f5cd4ca5f654a4cf5f42f54c59a9b8a08b0ecf43

Observation 30986058-bf2f-475c-a620-0010de4609f6 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread,.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models A mathematical framework for transformer circuits.Transformer Circuits Thread,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.037120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.037120Z digest=sha256:f784eb842006d392aa45ec3f48745edee843978cbef13ff9ca649331444ee230

Observation 92dc0905-5d21-4a50-acd8-a49c6aa66c56 · outbound

This paper cites Bayesian bandwidth estimation and semi-metric selection for a functional partial linear model with unknown error density.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Bayesian bandwidth estimation and semi-metric selection for a functional partial linear model with unknown error density

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.043445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.043445Z digest=sha256:17e3e2529182fa81c82e795a6dce889fa007ae4e23d4aea1e9943562b6ee745c

Observation 30ab98ac-3857-4609-932a-ed6a75d9d89c · outbound

This paper cites What can transformers learn in-context? a case study of simple function classes.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models What can transformers learn in-context? a case study of simple function classes

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.047114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.047114Z digest=sha256:8166d5509e42377e01a3d52df31e84623b3f919e82f1bedb960fc33a7d81119e

Observation 840ff89a-4d57-492d-ad18-4187a763a51f · outbound

This paper cites Causal abstractions of neural networks.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Causal abstractions of neural networks

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.053802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.053802Z digest=sha256:0a26e6844d5d36f8c4ccd2a10a7e83823b8f25efdc3b5bde2cc2d88a56b9516f

Observation 9911533b-558c-4a36-ab06-2a897f62b5ce · outbound

This paper cites Finding alignments between interpretable causal variables and distributed neural representations.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Finding alignments between interpretable causal variables and distributed neural representations

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.056880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.056880Z digest=sha256:80c8683650e65ded57792f8b8140b2959c631fe07aa85c7353da955e9ba3e150

Observation 9ecdc109-0c00-43eb-a79a-a56850c193d4 · outbound

This paper cites Hidden markov models: Pitfalls and opportunities in ecology.Methods in Ecology and Evolution, 14(1):43–56, 2023.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Hidden markov models: Pitfalls and opportunities in ecology.Methods in Ecology and Evolution, 14(1):43–56, 2023

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.060414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.060414Z digest=sha256:0b380872ae8272dc59817a10a235d3cadeeca3a5e755234684bc58c7d8d90ed1

Observation ed003c3e-4a09-4780-9dd9-fc76dc6516a7 · outbound

This paper cites Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.063618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.063618Z digest=sha256:4c6fce5a65413bb1b71b09cdca0ab74dd5de2d19ea8e274f50be58a5af0d0830

Observation aa8d8150-ee5f-4004-8627-cf83b470c4a4 · outbound

This paper cites A spectral algorithm for learning hidden markov models.Journal of Computer and System Sciences, 78(5):1460–1480, 2012.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models A spectral algorithm for learning hidden markov models.Journal of Computer and System Sciences, 78(5):1460–1480, 2012

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.067045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.067045Z digest=sha256:aab79d54ce6a4a22cacd575fa518fa7068dd4db24ee6eb5a1b2443bfcefb600a

Observation 1e82f1f7-374f-4878-b5b7-6fa61354883e · outbound

This paper cites On Limitation of Transformer for Learning HMMs.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models On Limitation of Transformer for Learning HMMs

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.069979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.069979Z digest=sha256:b86da21a4bd961592c6ad48a181349760f7fe59e10202e6eedabb649649b75b5

Observation 82c8d3e8-7c03-4d2e-a3d8-ad170fc2e860 · outbound

This paper cites Visualisation and ’diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure (extended abstract).

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Visualisation and ’diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure (extended abstract)

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.073581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.073581Z digest=sha256:b71030874396715d5eef26951329eb133a0edfed98a7b123eea0337502e2d38d

Observation 20b9d749-7878-456b-85a5-1a828ab7cb54 · outbound

This paper cites On the origins of linear representations in large language models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models On the origins of linear representations in large language models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.079899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.079899Z digest=sha256:e88b63f52fbbe14f15e38128135a2cab702b38253511f03813c2dbc8551c3ef3

Observation ee2bbb35-b578-4a5c-a099-9db5718da25c · outbound

This paper cites Emergent world models and latent variable estimation in chess-playing lan- guage models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Emergent world models and latent variable estimation in chess-playing lan- guage models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.083209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.083209Z digest=sha256:357b704cac32af823702ef6fe688b9be8558ce73a3f265f4467e2c289ca71152

Observation 10d19bfe-00ab-49a1-9e9e-020266c472b5 · outbound

This paper cites Li, Zifan Carl Guo, and Jacob Andreas.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Li, Zifan Carl Guo, and Jacob Andreas

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.086439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.086439Z digest=sha256:1d8faec855d733ca12b76cecfefd558fb4357e845dbac24facedc2e644f38c64

Observation 5359fe73-a9cf-4873-849b-835349630588 · outbound

This paper cites Emergent world representations: Exploring a sequence model trained on a synthetic task.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Emergent world representations: Exploring a sequence model trained on a synthetic task

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.089828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.089828Z digest=sha256:c2156b3b4dff953aee6aec672f4fda71ef5175b8a2f34f72bf9c999119263f21

Observation 25ad58cf-d7fb-4093-814e-27611dd4e834 · outbound

This paper cites From kepler to newton: Inductive biases guide learned world models in transformers, 2026.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models From kepler to newton: Inductive biases guide learned world models in transformers, 2026

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.092726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.092726Z digest=sha256:fe6f137fd39bea89f7928877ff108e756c98381da9e90ca08f7052e81873376a

Observation e48d86d0-7df0-4402-815d-bdc3273fb67f · outbound

This paper cites Bridging the Usability Gap: Theoretical and Methodological Advances for Spectral Learning of Hidden Markov Models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Bridging the Usability Gap: Theoretical and Methodological Advances for Spectral Learning of Hidden Markov Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.095855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.095855Z digest=sha256:bc191a99c8666eca3ffef547fe80a379d65b8082fd1776349ef5610fa470ccbe

Observation 88f688be-7f99-4fa3-91d8-9b2c57559910 · outbound

This paper cites Attention with markov: A curious case of single-layer transformers.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Attention with markov: A curious case of single-layer transformers

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.099364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.099364Z digest=sha256:468e87cb6abb08317bff5ba32654d72121ab5786fe2d19969532ee49b352bf7e

Observation f5be4ef8-570d-4d9c-a122-84bfa434aa34 · outbound

This paper cites Uncovering ecological state dynamics with hidden markov models.Ecology letters, 23(12):1878–1903, 2020.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Uncovering ecological state dynamics with hidden markov models.Ecology letters, 23(12):1878–1903, 2020

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.102287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.102287Z digest=sha256:03d1a2e88c75d4f457ca30e014c9d855fe56b6eb9ecefc4a6418f3c5dd05de24

Observation ebe1c62b-1389-4277-aa33-183c78d3521b · outbound

This paper cites Progress mea- sures for grokking via mechanistic interpretability.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Progress mea- sures for grokking via mechanistic interpretability

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.105585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.105585Z digest=sha256:051badb6d3b5ce743436fbe5319251df5e41a14ca49f169578ce460667ef6ca9

Observation 2d4e3b4d-bb3e-411d-9320-71073cc09012 · outbound

This paper cites Emergent linear representations in world models of self-supervised sequence models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Emergent linear representations in world models of self-supervised sequence models

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.108721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.108721Z digest=sha256:ace0607cd319b18a7c821ac0cc53620509beba8ea8362ccba0cbc4503c2406b5

Observation 0970ac45-e0b3-4e29-a676-1542e7f9d60c · outbound

This paper cites Riechers, Daniel Filan, and Adam Shai.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Riechers, Daniel Filan, and Adam Shai

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.114733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.114733Z digest=sha256:ab4f6b8b3ef686c1de7b56db2dbe1d50e87a7da33b908ace6c7d32285f1baf38

Observation cc597277-58f0-48c2-b499-fe2f95fced62 · outbound

This paper cites Transformers on markov data: Constant depth suffices.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Transformers on markov data: Constant depth suffices

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.117895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.117895Z digest=sha256:758e1210c81ea023fe7ff8cd91d92ccc44bdd9dc248182b5042292147a64545b

Observation 0ec44722-f16e-43b4-813d-4d23a59aa436 · outbound

This paper cites Finite sample identification of partially observed bilinear dynamical systems.arXiv preprint arXiv:2501.07652, 2025.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Finite sample identification of partially observed bilinear dynamical systems.arXiv preprint arXiv:2501.07652, 2025

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.120773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.120773Z digest=sha256:cb4b74cf61f1176e93698ca5dad0f1777a05b36bcf5febd90ead735c1417b66f

Observation 2aed8707-67d8-4129-9ffe-5a006dfb89b1 · outbound

This paper cites an unresolved cited work.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.111939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.111939Z digest=sha256:1335c353781de70754eefa3150d9f3185abffc5002121040d5278fa6cdb7fc52

Observation 19a35616-e9f5-4e7f-beae-5702a56bcc74 · outbound

This paper cites Chang, Ashesh Rambachan, and Sendhil Mullainathan.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Chang, Ashesh Rambachan, and Sendhil Mullainathan

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.126661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.126661Z digest=sha256:75adf76d5f77219fdf036936ef02f2110ed21a8516152dc08d65733edd97405b

Observation 60b03b04-346f-49ce-85f2-3a1766e2527b · outbound

This paper cites Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.129465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.129465Z digest=sha256:086d0815f57a4c320028776e80fa29e6970a6cbad515127f56a7970b192c50bf

Observation 7af41a46-775e-400a-8893-099be0bba0aa · outbound

This paper cites Interpreting the Repeated Token Phenomenon in Large Language Models.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Interpreting the Repeated Token Phenomenon in Large Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.133133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.133133Z digest=sha256:09ae7288da59ad723f0bc78905b1696593c9c6f223a5dde73a15053dcb194a96

Observation ce94cf0b-5000-4cf0-9822-420b1ce793b7 · outbound

This paper cites Riechers, Lucas Teixeira, Alexander Gietelink Oldenziel, and Sarah Marzen.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Riechers, Lucas Teixeira, Alexander Gietelink Oldenziel, and Sarah Marzen

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.123812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.123812Z digest=sha256:27e31285988dbc02f53434c7267cef519fde6e3ac68fea10f44ab0ba23303d34

Observation 2760ea5d-4201-4457-9296-929f52203e48 · outbound

This paper cites A hidden markov model for space-time precipitation.Water Resources Research, 27(8):1917–1923, 1991.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models A hidden markov model for space-time precipitation.Water Resources Research, 27(8):1917–1923, 1991

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.139406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.139406Z digest=sha256:5d3b7ab39390ab4de7c042931c1590338aa79b1ffad6f36f3c611da55b202f04

Observation 3f951cf7-62b1-4548-8fd0-1878838111a6 · outbound

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

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.136135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.136135Z digest=sha256:9b137f4594c4688ce78af627d7cee5d24675eb6b8d6141a3f9153259694a4f36

Observation b7c012dc-495e-43fc-a351-836784248fe1 · outbound

This paper cites an unresolved cited work.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.143448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.143448Z digest=sha256:dbde7f021deb12387139aefe76aec1bc3a1df5a4ffba1dd50b83b158c01c3153

Observation a8356188-0210-4c27-896a-1e68775b1861 · outbound

This paper cites , t−1: • Set eb′ k =f tri(o1:t, ebk, ok).

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models , t−1: • Set eb′ k =f tri(o1:t, ebk, ok)

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.146396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.146396Z digest=sha256:7593133f95e56c6b317394e5ae2309cb1d7b9f952cf046c9c65ad7927e26d00a

Observation 8011ce58-e325-4411-aa32-3e539ab4463a · outbound

This paper cites • Setc o =f bi(o1:t, ebo t+1).

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models • Setc o =f bi(o1:t, ebo t+1)

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.149575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.149575Z digest=sha256:09df3cdad7679fc791b5cae91cee79562031dca2d88eff7ca6830544f7e125ae

Observation ba06a9fb-d3d5-4c5d-9706-7cd5b280fe61 · outbound

This paper cites Normalize overo∈ O.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Normalize overo∈ O

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.152223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.152223Z digest=sha256:6d719e3a5bdce8bf3017dff91c4946f4d871dda730117fda91ed7d062b8f544c

Observation 7e289956-e5c3-4f70-8cdf-2d38e2257d3c · outbound

This paper cites We need at least (32, 128), and increasing beyond (64,256) does not lead to better performance.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models We need at least (32, 128), and increasing beyond (64,256) does not lead to better performance

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.155542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.155542Z digest=sha256:6bc868c6e6516e8dc79e746b464a78e5c52dc97f728eac2db19cd23124141281

Observation bbe10af3-d4a6-45c8-b982-6d62737561be · outbound

This paper cites Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.164418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.164418Z digest=sha256:0f767301e59ddd926338d536ac38fdcada6224017ce9e9e468fdc26883ed1928

Observation 9b5da672-25d9-4760-a1c1-8666c6a76e4b · outbound

This paper cites URL https://doi.org/10.24963/ijcai.2018/796.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models URL https://doi.org/10.24963/ijcai.2018/796

Reference 2018

Resolution
verified exact
doi, observed 2026-08-02T10:13:54.040576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-02T10:12:29.076883Z digest=sha256:aa104a02996a669d1ed7746e6693a09291a171af7ad17933d853f58518ce5282

Observation 7270d7da-52f5-46b0-8700-400d3a22ec16 · outbound

This paper cites an unresolved cited work.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Unresolved cited work

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.040580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.040580Z digest=sha256:1536edf78cd45693c0a90921e1c530ea76fe70e690a78a861a3cb10c9830f237

Observation ece68604-b140-463d-93f1-364d4b9cd282 · outbound

This paper cites an unresolved cited work.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Unresolved cited work

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-02T10:12:29.050520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.050520Z digest=sha256:709a817ee4eedc397c986c5e29efea78a7d0ca8b94fd92bfa155b039b8690fa1

Observation 2ce97ef0-bd26-4f97-b437-bb68ea134657 · outbound

This paper cites AAAA.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models AAAA

Reference 4096

Resolution
malformed identifier
no resolver link, observed 2026-08-02T10:12:29.159501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T10:12:29.159501Z digest=sha256:4a225da01f980e5accbb03410e4b87a0b86d0375fa5ba662412cb196aef6ec77

Pith citing papers

No inbound Pith citation observations are available.