Pith. sign in

Paper Citation Record · LEDGER

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

As of 8 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 3 inbound Pith citation observations for arXiv:2506.10378.

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

pith.paper-citation-record.v1
2506.10378 v1

Coverage vector

measured 79 of 79 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:39:09.218815Z

measured 82 of 82 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:58:13.488639Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T13:03:26.399621Z

Reference resolution

79 of 79 outbound references displayed

  • verified exact3
  • verified fuzzy41
  • unresolved35
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5b5eb337-be98-45fc-8e67-20706459c945 · outbound

This paper cites GPT-4 Technical Report.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T04:38:59.287822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:38:59.287822Z digest=sha256:f6f8945c03ec67e0fc7292a6659d9035275eddef7e103b118a83a7f5c9f53594

Observation 2f156c47-68dc-435c-bd82-16a2dde1290e · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T04:38:59.369977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:38:59.369977Z digest=sha256:a1ff3e777d3c4b731a245b45e9ed208e5be29a901aa0c81e79178255ae588ec6

Observation bc2b8b17-0cce-49d4-94c1-d35c8a2e4659 · outbound

This paper cites An integrated theory of the mind.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning An integrated theory of the mind

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:21.826616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:38:59.507531Z digest=sha256:d824742d7b8133fe8d38a5b61e4e4259ae317631e5f36075e8a7fc8f634242ff

Observation 65b8ab84-64af-4b6d-8b25-5c2d766e2cc4 · outbound

This paper cites Invariant Risk Minimization.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Invariant Risk Minimization

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T04:38:59.603495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:38:59.603495Z digest=sha256:d6b17add70a0cb6eade3b8a47775d55064c6e35aafe5f64573ff698279738577

Observation 323f5800-c654-42bf-bf47-a1cd174d365e · outbound

This paper cites A Theory for Emergence of Complex Skills in Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning A Theory for Emergence of Complex Skills in Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T04:38:59.692682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:38:59.692682Z digest=sha256:edd4aeb20244282a856738f6c91f7b62e8bf26ebce1676dcde869bbbd5b854c2

Observation dd022874-2223-4474-b16b-b755d05ea680 · outbound

This paper cites Act: A simple theory of complex cognition.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Act: A simple theory of complex cognition

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:21.603880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:38:59.865157Z digest=sha256:372e153e2fbfc3939a5a482c553c81727ba65db5c645da11f9a137a815064e4a

Observation ca7e7632-217f-4820-802b-4c8cee2d224f · outbound

This paper cites Claude 3.5 sonnet.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Claude 3.5 sonnet

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:00.029614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:00.029614Z digest=sha256:36f1ab47fc25c2c6e284705fd21e9e65be506506fb7d69cd99370b03b1ee9abf

Observation 97128679-f3c6-4143-a62b-96ebb4500eac · outbound

This paper cites Invariant risk minimization games.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Invariant risk minimization games

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:21.362767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.175600Z digest=sha256:0c5d0268a3d79935cc0b1dee50ecd0543b91ce6f100712937bc53723d600707e

Observation 2fd55be9-42e3-4bcf-b189-a167d0608724 · outbound

This paper cites Sample complexity of interventional causal representation learning.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Sample complexity of interventional causal representation learning

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:21.076782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.301780Z digest=sha256:689569284e1a2a9b32c68f3f5d199b148c8f29fb970b3d67ae53bbb79db75bf4

Observation fd4b8802-aceb-47e8-92be-dcf3980c068b · outbound

This paper cites An Empirical Study of Scaling Laws for Transfer.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning An Empirical Study of Scaling Laws for Transfer

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-07T04:39:10.333127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.420894Z digest=sha256:98c9d08f49af86a762058c7ace8e0861cdde174196ef9403e80fb300e567571b

Observation 40d4409f-9bed-4740-8485-c6a929d68c88 · outbound

This paper cites Sparks of artificial general intelligence: Early experiments with gpt-4, 2023.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Sparks of artificial general intelligence: Early experiments with gpt-4, 2023

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:20.780177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.595168Z digest=sha256:e122a09dc31c24cece011e0a4dfaa80687d4a70309d1a3a3baf1a747e2a43b5e

Observation c3209fdd-7f3b-4df6-92c4-d79458060d6e · outbound

This paper cites Functional magnetic resonance imaging evidence for a hierarchical organization of the prefrontal cortex.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Functional magnetic resonance imaging evidence for a hierarchical organization of the prefrontal cortex

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:20.563436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.740456Z digest=sha256:8e8e2bbf89ce10daa95d9374ad569b1bd783414d19a5d93b566f4dc37f0c9529

Observation 28e5998b-8552-4b06-98a8-47f9b8422bde · outbound

This paper cites an unresolved cited work.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:39:20.264283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:00.833696Z digest=sha256:567da3d11adea1b6e459e61692ddb46cef51dca66dfb32655e7671677ae9407d

Observation de90e3fb-28f1-4a21-98d1-5b775466815d · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:00.939328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:00.939328Z digest=sha256:6c29296f8d0ccb148c8379c8d450aab4b022c91dce226a874b644b073ce96e78

Observation d1bc4a66-c46d-4d88-9e53-8b750f4aa34b · outbound

This paper cites Language models are few-shot learners.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Language models are few-shot learners

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:01.031708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:01.031708Z digest=sha256:8ddc2e4129990628fdae9d3f16b893f89b2307bb6918a235488e11dced29734f

Observation 7649992c-1cff-4468-8717-a0b1067f98db · outbound

This paper cites Doubly robust estimation in missing data and causal inference models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Doubly robust estimation in missing data and causal inference models

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:19.971550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.151962Z digest=sha256:37712a387caf443bfc878330b34c312d06fafa8161b339e7405c7767350a777c

Observation 857afd46-23ef-43f6-9372-24649b25d46b · outbound

This paper cites Learning linear causal representations from interventions under general nonlinear mixing.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Learning linear causal representations from interventions under general nonlinear mixing

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:19.707898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.286884Z digest=sha256:84ad4438e17506fc3ce799aab55e45a21b097e88e75e5acfbec5d39aa91d9a9a

Observation 3bb65a48-2ff1-4618-8223-bc7b379979e2 · outbound

This paper cites Rethink reporting of evaluation results in ai.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Rethink reporting of evaluation results in ai

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:19.444566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.423173Z digest=sha256:da7c7e36a482f8c0ff181439f4d76735d9ec5b15c42541d289b0129be1a21397

Observation 84b957a0-8a8e-41cb-bb57-2f13895a89bc · outbound

This paper cites Human cognitive abilities: A survey of factor-analytic studies.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Human cognitive abilities: A survey of factor-analytic studies

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:19.178680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.519923Z digest=sha256:e2345f2f57a6b2388c207632245aef91c9d9b0698e5bc569551ce052c95ff960

Observation bf2150c2-40a9-474f-b6d2-6d27f54b0205 · outbound

This paper cites Structured matrix completion with applications to genomic data integration.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Structured matrix completion with applications to genomic data integration

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:19.014912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.666052Z digest=sha256:ccc51907849afed3276c5bcd046c6ae987fb21528e4ca93746991861973be3ff

Observation 6620d5e0-d391-495b-981b-11bed8aa9c9d · outbound

This paper cites Scaling instruction-finetuned language models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Scaling instruction-finetuned language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:18.768882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:01.791402Z digest=sha256:11e119d7442f9cac98268b28a5bf29d56e0f36ad539743721dfbe2be8354606e

Observation d8a950a4-6679-4d8a-92ba-1c55ccafa577 · outbound

This paper cites Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:01.927070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:01.927070Z digest=sha256:7fb86e0900fea09d5e1ae70d600ccee293cc21bcae166c1988645e7a47bb1ebc

Observation 1dfe70fd-f5c0-4fc1-aaf1-7425c99c5ad9 · outbound

This paper cites The rising costs of training frontier ai models, 2024.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The rising costs of training frontier ai models, 2024

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:02.067496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:02.067496Z digest=sha256:d02deffe0bc8decd5e33a96e6df9bf12ebc85b0880fb118996432894a2c43e93

Observation 39da5403-40f6-4d78-85f8-53acdaf25241 · outbound

This paper cites Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:02.165360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:02.165360Z digest=sha256:7117ec051a5a1022e003fea46ddbfd849906d178278e62825a773c0279db1eeb

Observation 7e9df1be-6852-46da-ad51-2f837412750e · outbound

This paper cites Dorner, and Moritz Hardt.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Dorner, and Moritz Hardt

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:18.578874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:02.265998Z digest=sha256:1b2f9ba9f1a2c27bc1f1c37ee5c4437eed431e9324e8d18c392f8e3e4312ec2c

Observation 807a6921-792e-43e7-875f-c09fd906eb46 · outbound

This paper cites Identifiability, separability, and uniqueness of linear ica models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Identifiability, separability, and uniqueness of linear ica models

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:18.327581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:02.359901Z digest=sha256:8bd02e99585702fffa3df70cabc64bd27a5159d642a514848c7db7e316a1a284

Observation 2c12e803-a29a-4dde-af3c-70755a429496 · outbound

This paper cites Principal stratification in causal inference.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Principal stratification in causal inference

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:18.071636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:02.506121Z digest=sha256:e5c8dcb09318dff5e3ab5c4a2e927f29a2e678deb0dc393114eff42a009db8a9

Observation c20bbc66-5403-4642-90ff-540b56ac89df · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:02.608864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:02.608864Z digest=sha256:60596d68d8c5082c637e3876d766e8eb97ae56f28e35d09061a6cc8f7fb70b54

Observation 849a6744-74d9-45f2-998d-3f792d00d034 · outbound

This paper cites The Llama 3 Herd of Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The Llama 3 Herd of Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:02.765458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:02.765458Z digest=sha256:3edaa73360ab964ee9dc26c5876e7e6958d99e3b88b9dc4b3167e403b815bc6f

Observation 7d32ca32-d261-4266-856b-6b8ccba45fc0 · outbound

This paper cites A Closer Look at the Limitations of Instruction Tuning.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning A Closer Look at the Limitations of Instruction Tuning

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:02.897278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:02.897278Z digest=sha256:1c928f6d101b604ec88e164d71e94b8de0a57183447e1a3b537c598dec1d69df

Observation 82985dc9-bd92-446b-8882-303e50b9e7c8 · outbound

This paper cites Time Travel in LLMs: Tracing Data Contamination in Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Time Travel in LLMs: Tracing Data Contamination in Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.018166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.018166Z digest=sha256:ff16ca0f101663feb16bafac601447cd9ecb67f37b753bb604fe610b1cc051cb

Observation 33ff0e5e-6777-48b0-b73c-b62777dc885f · outbound

This paper cites The False Promise of Imitating Proprietary LLMs.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The False Promise of Imitating Proprietary LLMs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.121696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.121696Z digest=sha256:e59a5f8546e30e6131d013f955b87d6ae1fc1ee488658e9e066f308f5ed1441d

Observation 9e9bbc31-52ce-4479-b1f1-b5fc9942309e · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.260732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.260732Z digest=sha256:3edb24c9dfabc35efe0b26907b25de0571a648d767f8cd2616728fad9497178a

Observation 93854879-eefc-408e-8f1c-b23c9976534a · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Measuring Massive Multitask Language Understanding

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.396804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.396804Z digest=sha256:f885071f89d2520eb4f904a9462669727a87c19f70f19c413c2a9777de4cf739

Observation 5a909a64-fc2e-4849-a803-da729610dba1 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Training Compute-Optimal Large Language Models

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.523942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.523942Z digest=sha256:1db8e85ab9711a63adb4d6d73501d29af851e03607f1e630f51263b4aada43fb

Observation 72fe85d4-2dc7-4e8a-ab90-6ec234298961 · outbound

This paper cites A sober look at progress in language model reasoning: Pitfalls and paths to reproducibility.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning A sober look at progress in language model reasoning: Pitfalls and paths to reproducibility

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.687198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.687198Z digest=sha256:40fe23d3a66d202c15c51d073ede3502868a4646bc34097c8733e9aa71b14b9f

Observation 886fbafc-d79a-45da-80cf-f7b5384439e1 · outbound

This paper cites Does RLHF Scale? Exploring the Impacts From Data, Model, and Method.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Does RLHF Scale? Exploring the Impacts From Data, Model, and Method

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:03.757222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:03.757222Z digest=sha256:b47e593bbc6e0c72b4d9dbc2e0a90e7c32bd7e4830da844a7f9536a3fc3b7cef

Observation cba8e590-0fb3-4069-bd68-0bbe6e8f6aa6 · outbound

This paper cites a rinen, Jarmo Hurri, Patrik O Hoyer, Aapo Hyv \.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning a rinen, Jarmo Hurri, Patrik O Hoyer, Aapo Hyv \

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:17.772086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:03.893871Z digest=sha256:67e70816fe29aa925f2303917d2449f7b780637ee2ac383bcf55f2277f55ed05

Observation 13fb752e-d767-4945-a0d1-4a2f5b3702ff · outbound

This paper cites Causal discovery from heterogeneous/nonstationary data.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Causal discovery from heterogeneous/nonstationary data

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:17.523010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:03.984543Z digest=sha256:2d1c4902f7b90fb59044fd34a19f6ee1d4c275d4f96ef9f13c290e75f81d386d

Observation ed05d5e7-26e2-4a10-a86b-55338cf6d2f2 · outbound

This paper cites Learning linear causal representations from general environments: Identifiability and intrinsic ambiguity.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Learning linear causal representations from general environments: Identifiability and intrinsic ambiguity

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:17.319643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.095786Z digest=sha256:5e25b85c294d9f5c055518a821284650d64429f0178a8cd4fd6269e6730ccbe8

Observation 5e90efc9-8eca-49ef-b053-d41769d333a8 · outbound

This paper cites Mistral 7B.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Mistral 7B

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:04.248793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:04.248793Z digest=sha256:a6de83a32887629b3589f4b590e20ca1f49de5561b9d0234c93047016e855366

Observation 64ff5b48-23e3-49b0-aaef-91c840753910 · outbound

This paper cites The construct of creativity: Structural model for self-reported creativity ratings.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The construct of creativity: Structural model for self-reported creativity ratings

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:17.096415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.353312Z digest=sha256:da6264f1ec35181532e7ded204d8b413d29678daa25d78f17948791cf1184d44

Observation 9bc53b76-d732-483d-a549-ee7364b8092b · outbound

This paper cites Scaling Laws for Neural Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Scaling Laws for Neural Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:04.466095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:04.466095Z digest=sha256:4208c6b27e293bc75d2a609489cd5c3f613d2a6a7db688213277ea63d4498658

Observation 1c4027f5-05b3-45e0-bd1b-e61aa5e720a8 · outbound

This paper cites The architecture of cognitive control in the human prefrontal cortex.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The architecture of cognitive control in the human prefrontal cortex

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:16.815111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.555256Z digest=sha256:cd37651baad65dcc361960efe2935da497c7d6013d6f2ecf1ba97c877a673329

Observation 4312c244-0569-4849-9e3e-5e2b03dc4fc9 · outbound

This paper cites Solving quantitative reasoning problems with language models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Solving quantitative reasoning problems with language models

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:16.615163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.647940Z digest=sha256:c54a87d22aaa73e5ccbf1d6888819a6b0b713fc5900efef69220dc59054450e3

Observation 7c8ef998-8f49-4b69-8240-766ef8ac77ad · outbound

This paper cites Holistic evaluation of language models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Holistic evaluation of language models

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:16.405930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.799167Z digest=sha256:850049e5d16afda6400a0535726811fbb6b9e4a833a0db3e55a8da8cae840a17

Observation 881357b0-9473-403a-a862-0ed62aa483e5 · outbound

This paper cites Not-just-scaling laws: Towards a better understanding of the downstream impact of language model design decisions.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Not-just-scaling laws: Towards a better understanding of the downstream impact of language model design decisions

Reference 47

Resolution
verified exact
raw_fallback, observed 2026-08-07T04:39:09.929296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:04.907319Z digest=sha256:a327fa55dc4654d77dcc13730f9cd38bf17446a7722786204bb5bfc05ce858fd

Observation 92014512-796e-41ce-8bbe-2f557bb3087a · outbound

This paper cites a tsch, Bernhard Sch \.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning a tsch, Bernhard Sch \

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:16.156807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.057279Z digest=sha256:722649dacae04bd444eff781375d96e7864e774a7530a920b8f7809acab41f6a

Observation ea42288d-69a3-4cf0-9cd3-d8799c45b5c5 · outbound

This paper cites an unresolved cited work.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:39:15.966129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.192921Z digest=sha256:8cb5d8af2680b6f3f082592021d632a9dc78bc5cf2eb91c3b6b1363246fe5947

Observation 97c7bca5-0022-4283-920a-2f2dfbe117bf · outbound

This paper cites an unresolved cited work.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:39:15.646961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.265187Z digest=sha256:eaf81a708fea3be5459d93029ec0bc373cfdbcfcabe51e50bc9d6f8759a76b00

Observation 01771925-1151-4807-8901-d210432db236 · outbound

This paper cites Training language models to follow instructions with human feedback.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Training language models to follow instructions with human feedback

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:05.358578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:05.358578Z digest=sha256:638efbb1ce9809111e6734bed56f4cd96ad9d6cd5c2fb49e081b6fc2068b5285

Observation f372a1cc-a702-4d7d-930a-873e20d78ab7 · outbound

This paper cites Causal diagrams for empirical research.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Causal diagrams for empirical research

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:15.450728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.492378Z digest=sha256:4e88a3f2910fbedaeda5680ac7bdf1e557b14e086fc615da8c1419c51fde05ca

Observation a2777412-bf94-44ab-a025-aa78374b6908 · outbound

This paper cites On the identifiability of bayesian factor analytic models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning On the identifiability of bayesian factor analytic models

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:15.225195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.639697Z digest=sha256:4c05bb907db73fb165a7c27bc88ff18a44e88a7e5715bc1ce8e1f5cd2e861638

Observation 083c9f47-7b1d-403f-86ab-81f1d9818fe8 · outbound

This paper cites Sloth: scaling laws for llm skills to predict multi-benchmark performance across families.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Sloth: scaling laws for llm skills to predict multi-benchmark performance across families

Reference 54

Resolution
verified exact
raw_fallback, observed 2026-08-07T04:39:09.635730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.766473Z digest=sha256:27c37bf58d10272f2c4f527e364d0be2002912bc3ab248d776e494df1dd0a8d1

Observation 1db11138-c297-4adc-a336-ddc03eb2eccf · outbound

This paper cites Evolm: In search of lost language model training dynamics, 2025.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Evolm: In search of lost language model training dynamics, 2025

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:14.927579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:05.895689Z digest=sha256:78580e204a9b569dfc16704bdacb54a06bad68327ebbbe141c44cf671920f749

Observation ff26cae3-b612-4087-9aec-7b5096df579f · outbound

This paper cites Safetywashing: Do ai safety benchmarks actually measure safety progress? Advances in Neural Information Processing Systems , 37:68559--68594, 2025.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Safetywashing: Do ai safety benchmarks actually measure safety progress? Advances in Neural Information Processing Systems , 37:68559--68594, 2025

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:14.638098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.006821Z digest=sha256:20a07c9267d3f0608370498f192daa6494a8e46c5d173910527b4150d5882a79

Observation a1ca435d-8a21-45ea-ab4b-468a3923f8da · outbound

This paper cites A simpler approach to matrix completion.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning A simpler approach to matrix completion

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:14.398228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.141851Z digest=sha256:de7de3f30567940eb57fa2c11e372f83a15d427cacc6a479d56471bcf3be0a8e

Observation 020ec77d-927a-44b5-bd45-76219c69c749 · outbound

This paper cites Maddison, and Tatsunori Hashimoto.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Maddison, and Tatsunori Hashimoto

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:14.153380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.258579Z digest=sha256:0f9c2584f100aa773d666c3a79bc2dcb3086fcb45ff3741d498a9737ceccc483

Observation 2ce67ae2-8170-467a-9f1a-493f5c3cf32a · outbound

This paper cites The architecture of complexity.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning The architecture of complexity

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:13.814004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.427379Z digest=sha256:eed809fa2d5f3d180a240313b3fbc98eaea0e4cc509d5b43b2977c79a5e7d930

Observation cbcacfde-0564-4ca1-b2d9-e9efccb98d3f · outbound

This paper cites Toward causal representation learning.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Toward causal representation learning

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:13.607870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.577987Z digest=sha256:8cbd933241f699d95a2be468cd671a0a2c9a25af21e3ed9347fa0c3489867e3d

Observation d5ef6c67-2fbf-4fc2-b28c-4f51f55ad966 · outbound

This paper cites Are emergent abilities of large language models a mirage? Advances in Neural Information Processing Systems , 36:55565--55581, 2023.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Are emergent abilities of large language models a mirage? Advances in Neural Information Processing Systems , 36:55565--55581, 2023

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:13.298759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.764599Z digest=sha256:66282361230ef37adfaf7763d34ece688b7a767608ac77236e95b993f7b7bcb3

Observation f1ba9a89-d3de-498a-bbe6-5fc7d8e95d76 · outbound

This paper cites Linear causal disentanglement via interventions.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Linear causal disentanglement via interventions

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:13.047722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:06.874199Z digest=sha256:0251d829a6c93afb6b90f1ab0d4eef79a758be9b46cb9102857b1a6b762ebf47

Observation 438ce11a-8062-4d6d-be7d-3c818cee1042 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:07.048487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:07.048487Z digest=sha256:3a991913d179826632ad47f739b50efa517963ad90ad5466b7bdd0be965dbed8

Observation 4892c736-dcf1-442d-9bff-2c472a3fbf90 · outbound

This paper cites Matching methods for causal inference: A review and a look forward.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Matching methods for causal inference: A review and a look forward

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:12.811869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:07.185664Z digest=sha256:57c784780d1e8a0acf34e4e3368ff1a3cbbbf5c60106a0a2815247dba44d028d

Observation a36f9775-fad5-4d4c-8e26-65fa47f22c1d · outbound

This paper cites Multitask prompted training enables zero-shot task generalization.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Multitask prompted training enables zero-shot task generalization

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:12.582736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:07.300084Z digest=sha256:8af3d21b4b3d76c93b8d7f8884b221cb587b5c1f3e84c480670f6ce3d55a1278

Observation 15e875bb-d667-44a3-bec2-c9254e3f50d1 · outbound

This paper cites How to grow a mind: Statistics, structure, and abstraction.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning How to grow a mind: Statistics, structure, and abstraction

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:12.236470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:07.438379Z digest=sha256:6592198b87c89462f7d4aabd573b35830714f04c148fc4ebffcf2ea649375bff

Observation 66a6f830-b240-4aa7-9e91-150b1b1525c0 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Gemma 2: Improving Open Language Models at a Practical Size

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:07.609846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:07.609846Z digest=sha256:cd0473e0a6114257512b63811c4de8f1239ec081c5e6df4ece544823085cc073

Observation 452ada49-09c1-4ce3-b06b-6cce064e17b0 · outbound

This paper cites Reliable and Efficient Amortized Model-based Evaluation.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Reliable and Efficient Amortized Model-based Evaluation

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:07.776135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:07.776135Z digest=sha256:0bc15da6c955f58b2c308d05a9c527f1bda4ab97a051d058dfec0e33972cb01a

Observation 41453dd2-3a78-490f-9438-c4781d8369bc · outbound

This paper cites u gelgen, Michel Besserve, Liang Wendong, Luigi Gresele, Armin Keki \'c , Elias Bareinboim, David Blei, and Bernhard Sch \.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning u gelgen, Michel Besserve, Liang Wendong, Luigi Gresele, Armin Keki \'c , Elias Bareinboim, David Blei, and Bernhard Sch \

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:11.977760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:07.990648Z digest=sha256:e0bf66ca55a351417435e7128c1495821b74415e533562a1eda1874f7e986153

Observation ba62fe5e-c8d8-42d4-a336-c7fd2d071bec · outbound

This paper cites an unresolved cited work.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Unresolved cited work

Reference 70

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:39:11.736778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:08.126619Z digest=sha256:840f0bb244f4cb36001918eabcdb3dcf8644f733601eeb1eb73907afc968be7f

Observation 5f73c6e8-86c4-4284-861f-1fc363db16fd · outbound

This paper cites Emergent Abilities of Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Emergent Abilities of Large Language Models

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:08.295838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:08.295838Z digest=sha256:0132c0b7af3f1a30716dad734664d38df7992db618f7d8068e12e986a92d8716

Observation 2ca6bb1b-f90a-44ac-a0a6-4acc444e8649 · outbound

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

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:08.432069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:08.432069Z digest=sha256:b8dcdaf4eb6ee7c0907d5765df055861f80d24c6675092d302369747730f056e

Observation 4f700dc1-78d5-40f7-88eb-c72c490540eb · outbound

This paper cites Qwen2.5 Technical Report.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Qwen2.5 Technical Report

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:08.522540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:08.522540Z digest=sha256:4f3bc7648e752ae06faf55828d145d290693c00e7062ce3ab07af8b3b2304d1e

Observation 3b99727a-a679-4969-a46c-9ba35f4e0e31 · outbound

This paper cites Unveiling the impact of coding data instruction fine-tuning on large language models reasoning.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Unveiling the impact of coding data instruction fine-tuning on large language models reasoning

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:11.451018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:08.626556Z digest=sha256:f19827cafc5bf5e52100536580d96fe0276f55aed2799046dc9118781e9b2c57

Observation a238c3eb-9b06-4095-973b-b8ec36056841 · outbound

This paper cites Identifiability guarantees for causal disentanglement from soft interventions.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Identifiability guarantees for causal disentanglement from soft interventions

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:11.181960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:08.739725Z digest=sha256:e64ac5dde1a3d8072f2eb7b4d8626b39b5af5e8d40a69704dbec718e51e20bb5

Observation d8d350f2-3699-4bd4-bfc3-42f09638ad17 · outbound

This paper cites When scaling meets llm finetuning: The effect of data, model and finetuning method.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning When scaling meets llm finetuning: The effect of data, model and finetuning method

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:10.917752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:08.867178Z digest=sha256:ca0d8cfcb9eb06e0d444dc98a82e3cda60a2a29547149d86ddfd1a43a56e17f4

Observation 77f34f5e-32a2-486f-a497-2323514f9ea2 · outbound

This paper cites Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:08.980643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:08.980643Z digest=sha256:5dadfecbd70faa1463c1af237f34ec1eee7b638c5f1c0bc0979e43740d7c7bcb

Observation 1eb0872c-5acd-485a-87f7-9bb5fa1505fd · outbound

This paper cites Investigating the Catastrophic Forgetting in Multimodal Large Language Models.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Investigating the Catastrophic Forgetting in Multimodal Large Language Models

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-07T04:39:09.135335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:39:09.135335Z digest=sha256:17ef4385048d5a0e0a56132e0974bb0d36f3f5a2e317d70888ec98e7add30045

Observation d0606cbd-59fc-4474-a7f6-d801b108c258 · outbound

This paper cites Causal representation learning from multiple distributions: A general setting.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Causal representation learning from multiple distributions: A general setting

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:39:10.609813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T04:39:09.218815Z digest=sha256:745bf608471434d527ef0fe3178c2da6ddbb55db839e21c9da877629799f650e

Pith citing papers

Observation b0f1d4cb-6768-449a-b1fc-34542ff1c298 · inbound

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities cites this paper.

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T22:58:13.488639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T22:58:13.488639Z digest=sha256:6100c4302c451a4f3e4bde8c5006454d7119930e74bbef6f72cc917882b11dd1

Observation 65d6faf7-e7b7-4b4d-abb7-fedcd5281eae · inbound

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling cites this paper.

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-06-29T13:03:26.401147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-29T12:57:31.313438Z digest=sha256:225f47dd68cd473ffe1e3a534128f6f969de844d8ab9c32c5dce32fa7ff54b97

Observation b300a453-5410-4831-a99e-864932b4d533 · inbound

Domain-Aware Scaling Laws Uncover Data Synergy cites this paper.

Domain-Aware Scaling Laws Uncover Data Synergy Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-14T07:24:27.255815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T07:24:27.255815Z digest=sha256:dc00052ac83c8f94e916497d8c73ba582a76220adb1605398d0bf2b4e6539105