Paper Citation Record · LEDGER

LLM Pretraining with Continuous Concepts

As of 22 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 19 inbound Pith citation observations for arXiv:2502.08524.

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

pith.paper-citation-record.v1
2502.08524 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T04:54:39.421494Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:40:27.771507Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy5
unresolved24
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 70ce4d20-5606-489e-8464-8873fe115a0a · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

LLM Pretraining with Continuous Concepts Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.269793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6995f843-6bb6-462c-93e1-aff7e85b49e4 · outbound

This paper cites DeepSeek-V3 Technical Report.

LLM Pretraining with Continuous Concepts DeepSeek-V3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.280782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c57982a-0ba5-455f-b6df-0fdb59de392e · outbound

This paper cites The Llama 3 Herd of Models.

LLM Pretraining with Continuous Concepts The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.291932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca7a76e4-8a62-44d9-87d0-cce56ebf2776 · outbound

This paper cites AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn.

LLM Pretraining with Continuous Concepts AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.297648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb8c4dec-efd5-4ed0-b1cf-fff501116883 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

LLM Pretraining with Continuous Concepts Scaling and evaluating sparse autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.302858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 654413b9-704c-431e-849e-de4cb7ab02e5 · outbound

This paper cites MiniPLM: Knowledge Distillation for Pre-Training Language Models.

LLM Pretraining with Continuous Concepts MiniPLM: Knowledge Distillation for Pre-Training Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.307725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329e6b1f-9aaa-4b11-bf5e-19f78a067d63 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

LLM Pretraining with Continuous Concepts Training Large Language Models to Reason in a Continuous Latent Space

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.313421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f08ce55-b6f8-410c-98bf-cc948defd65b · outbound

This paper cites Distilling the Knowledge in a Neural Network.

LLM Pretraining with Continuous Concepts Distilling the Knowledge in a Neural Network

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.319043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6096342-a395-41a8-9d9f-303c102c5783 · outbound

This paper cites Large Concept Models: Language Modeling in a Sentence Representation Space.

LLM Pretraining with Continuous Concepts Large Concept Models: Language Modeling in a Sentence Representation Space

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.324272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e812e43-1633-4be2-9ae8-9156c926c1da · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

LLM Pretraining with Continuous Concepts Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.330610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2836ea7-38e3-486b-a59c-24988a3151f6 · outbound

This paper cites Decoupled Weight Decay Regularization.

LLM Pretraining with Continuous Concepts Decoupled Weight Decay Regularization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.336491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7862238f-be87-4d00-9142-f0067f09fd5b · outbound

This paper cites Code Llama: Open Foundation Models for Code.

LLM Pretraining with Continuous Concepts Code Llama: Open Foundation Models for Code

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.364183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e5c6412-4262-4403-a520-bed940c2b047 · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

LLM Pretraining with Continuous Concepts Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.369463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad03885-c99a-4063-a5b4-18148c1f35f3 · outbound

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

LLM Pretraining with Continuous Concepts Gemma 2: Improving Open Language Models at a Practical Size

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.374645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db8e37c5-f6ee-4792-a9c8-dd9307818a09 · outbound

This paper cites Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al.

LLM Pretraining with Continuous Concepts Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:54:39.969965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 52478968-0718-47e1-8060-d0e336b4f5de · outbound

This paper cites Evaluation of ChatGPT and Microsoft Bing AI Chat Performances on Physics Exams of Vietnamese National High School Graduation Examination.

LLM Pretraining with Continuous Concepts Evaluation of ChatGPT and Microsoft Bing AI Chat Performances on Physics Exams of Vietnamese National High School Graduation Examination

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-08T04:54:39.522927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 549a592e-5b9d-4877-890b-469fe03712f6 · outbound

This paper cites Distilling System 2 into System 1.

LLM Pretraining with Continuous Concepts Distilling System 2 into System 1

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.389971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a1532da-f258-47d4-8e8d-40b4e0fc68e7 · outbound

This paper cites Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors.

LLM Pretraining with Continuous Concepts Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.394799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b578b36d-6fbb-49e3-95d7-74bec819cd32 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

LLM Pretraining with Continuous Concepts Representation Engineering: A Top-Down Approach to AI Transparency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.400356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f751cd2-f452-4a7b-b04b-c249dc62e023 · outbound

This paper cites Our method and baseline both utilize the GPT-2-based Transformer architecture and tokenizer (Radford et al., 2019), with a context length of.

LLM Pretraining with Continuous Concepts Our method and baseline both utilize the GPT-2-based Transformer architecture and tokenizer (Radford et al., 2019), with a context length of

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:54:39.952345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3fad0500-06e3-4d2d-bb8d-bbfedbd74ff9 · outbound

This paper cites Consequently, our models introduce an additional(C + Kconcept) × d activated parameters on top of the base Transformer parameters.

LLM Pretraining with Continuous Concepts Consequently, our models introduce an additional(C + Kconcept) × d activated parameters on top of the base Transformer parameters

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:54:39.915153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6daeb9f7-e9a3-49cd-a87a-8775bb20ce3e · outbound

This paper cites Latent concept modeling is a.

LLM Pretraining with Continuous Concepts Latent concept modeling is a

Reference 31

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T04:54:39.898587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fbe4797f-a9e9-4286-ab91-f0bfb5fc2ae7 · outbound

This paper cites For CoCoMix, the hidden state dimensionsd are 512, 1024, and 2028, with 8, 24, and 24 layers, respectively.

LLM Pretraining with Continuous Concepts For CoCoMix, the hidden state dimensionsd are 512, 1024, and 2028, with 8, 24, and 24 layers, respectively

Reference 1024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:54:39.933400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f7eaeea9-c1b1-47e5-a0fa-75acd4cc7612 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

LLM Pretraining with Continuous Concepts Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.342599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0813bb-bf0c-4247-af1c-f7270a4f9eae · outbound

This paper cites OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text.

LLM Pretraining with Continuous Concepts OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.353679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 551de2d2-9abc-4e3e-8fc2-a578f465e342 · outbound

This paper cites Show Your Work: Scratchpads for Intermediate Computation with Language Models.

LLM Pretraining with Continuous Concepts Show Your Work: Scratchpads for Intermediate Computation with Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.348326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f613b6-363e-4383-a17e-3d6b5a4e3cc8 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

LLM Pretraining with Continuous Concepts Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.275380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26b2ce15-01b2-4115-8fea-05981e86e29f · outbound

This paper cites A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs.

LLM Pretraining with Continuous Concepts A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.359172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67942a3d-9f06-488c-b455-241cb2094f85 · outbound

This paper cites Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.

LLM Pretraining with Continuous Concepts Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.263903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6233ff7e-b64e-48c4-853d-51ba1a4faf96 · outbound

This paper cites Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al.

LLM Pretraining with Continuous Concepts Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:54:39.987870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6c35d17c-690d-4149-b86d-164ad2a0344e · outbound

This paper cites Implicit Chain of Thought Reasoning via Knowledge Distillation.

LLM Pretraining with Continuous Concepts Implicit Chain of Thought Reasoning via Knowledge Distillation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T04:54:39.286449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4e0d9e0a-28f1-4682-a39f-c1c5e1863568 · inbound

A Survey of Scaling in Large Language Model Reasoning cites this paper.

A Survey of Scaling in Large Language Model Reasoning LLM Pretraining with Continuous Concepts

Reference 189

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:22:08.794718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ffa160b7-62b5-4451-9cee-ba8cc6e5f20b · inbound

Efficient Pretraining Length Scaling cites this paper.

Efficient Pretraining Length Scaling LLM Pretraining with Continuous Concepts

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T11:40:27.771507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f9d6edd-9263-434b-b776-3b3437af8323 · inbound

Kinetics: Rethinking Test-Time Scaling Laws cites this paper.

Kinetics: Rethinking Test-Time Scaling Laws LLM Pretraining with Continuous Concepts

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T10:30:34.382006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3959c756-5e25-421b-b86a-7fa6cc9f9be9 · inbound

A foundation model with multi-variate parallel attention to generate neuronal activity cites this paper.

A foundation model with multi-variate parallel attention to generate neuronal activity LLM Pretraining with Continuous Concepts

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T22:55:46.262459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f46559-0637-4498-a104-7320a4abcc83 · inbound

Towards Distributed Neural Architectures cites this paper.

Towards Distributed Neural Architectures LLM Pretraining with Continuous Concepts

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-06T22:14:19.808871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3281b352-bf5a-4ab0-83ec-ce80173c72f3 · inbound

Implicit Reasoning in Large Language Models: A Comprehensive Survey cites this paper.

Implicit Reasoning in Large Language Models: A Comprehensive Survey LLM Pretraining with Continuous Concepts

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:36.759475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c4a3242-f36c-4ba6-b8b7-61579dc05215 · inbound

LaRe: Latent Refocusing for Multimodal Reasoning cites this paper.

LaRe: Latent Refocusing for Multimodal Reasoning LLM Pretraining with Continuous Concepts

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T00:15:16.513242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49da501c-ea80-4c50-9e14-3297463d8dc9 · inbound

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook cites this paper.

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook LLM Pretraining with Continuous Concepts

Reference 196

Resolution: unresolved; no resolver link, observed 2026-07-13T14:03:01.974171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 563aa1fc-bd0a-4c8b-ae3c-2846ce007c50 · inbound

LEPO: Latent Reasoning Policy Optimization for Large Language Models cites this paper.

LEPO: Latent Reasoning Policy Optimization for Large Language Models LLM Pretraining with Continuous Concepts

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:46:09.869259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 73909bf1-8873-46a6-ad32-f7ba0130d606 · inbound

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering cites this paper.

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering LLM Pretraining with Continuous Concepts

Reference 95

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T23:54:45.137827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 31659c60-6c27-4512-8158-429d649dbce5 · inbound

LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG cites this paper.

LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG LLM Pretraining with Continuous Concepts

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:01:12.073029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3812236f-747b-44f0-a585-107309943a5e · inbound

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning cites this paper.

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning LLM Pretraining with Continuous Concepts

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:28:04.793043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dfdefbf8-0b3f-4d05-a234-543fdc0ceff0 · inbound

NITP: Next Implicit Token Prediction for LLM Pre-training cites this paper.

NITP: Next Implicit Token Prediction for LLM Pre-training LLM Pretraining with Continuous Concepts

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-06-30T12:24:39.194388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 720668a7-825d-4c95-a79b-b749c11ce05c · inbound

NITP: Next Implicit Token Prediction for LLM Pre-training cites this paper.

NITP: Next Implicit Token Prediction for LLM Pre-training LLM Pretraining with Continuous Concepts

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:16.257287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 80db826e-7060-4cb0-b06e-9e99428f908b · inbound

NITP: Next Implicit Token Prediction for LLM Pre-training cites this paper.

NITP: Next Implicit Token Prediction for LLM Pre-training LLM Pretraining with Continuous Concepts

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T18:45:28.635910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb8e52f-601f-4ac6-b2e2-de24ce4ad896 · inbound

Learn from your own latents and not from tokens: A sample-complexity theory cites this paper.

Learn from your own latents and not from tokens: A sample-complexity theory LLM Pretraining with Continuous Concepts

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:23:50.223099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b58f78ff-db56-47d7-b67e-f93805d42449 · inbound

Unlocking the Working Memory of Large Language Models for Latent Reasoning cites this paper.

Unlocking the Working Memory of Large Language Models for Latent Reasoning LLM Pretraining with Continuous Concepts

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:03:13.922213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 857c626d-7c49-4ea9-917c-847b4a225a69 · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers LLM Pretraining with Continuous Concepts

Reference 127

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T23:32:46.627650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ddf34b57-8542-4937-8107-2ec9681cd422 · inbound

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories cites this paper.

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories LLM Pretraining with Continuous Concepts

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-11T00:37:43.265957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.