Paper Citation Record · LEDGER

Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 29 inbound Pith citation observations for arXiv:2309.13638.

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

pith.paper-citation-record.v1
2309.13638 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 29 of 29 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 29 of 29 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:32:42.615052Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

35
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 6c2a71e8-a51f-4e81-bf34-285360f87fe4 · inbound

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites this paper.

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:45:35.367808Z

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.

Observation c0d3b194-9b40-42cf-8b55-2a109a09bf9e · inbound

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models cites this paper.

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:42:12.042691Z

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.

Observation 8b9710ee-d728-4c16-9ff2-c4c8e2fd9c48 · inbound

Code Simulation as a Proxy for High-order Tasks in Large Language Models cites this paper.

Code Simulation as a Proxy for High-order Tasks in Large Language Models Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T04:32:42.615052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a7728d-c64b-4e0f-b73e-d18dfa7cce69 · inbound

Thinking beyond the anthropomorphic paradigm benefits LLM research cites this paper.

Thinking beyond the anthropomorphic paradigm benefits LLM research Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T22:21:52.626878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a8ba7a-7a57-4d54-89b2-c2bb637460d9 · inbound

Benchmarking and Rethinking Knowledge Editing for Large Language Models cites this paper.

Benchmarking and Rethinking Knowledge Editing for Large Language Models Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:46.768635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82410dd6-9c7d-4113-bfaa-bd89f85eacd2 · inbound

Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? cites this paper.

Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T22:36:23.410934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31a102b7-4e87-4c4c-9295-f303e1f2bcf8 · inbound

Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs cites this paper.

Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:47:07.237936Z

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.

Observation 51c9e342-52d9-4a2a-8e7d-48d5f35d2ecc · inbound

Transformers Don't In-Context Learn Least Squares Regression cites this paper.

Transformers Don't In-Context Learn Least Squares Regression Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:03:14.956649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b356d2d-d71a-4936-b246-4607be5c5755 · inbound

Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize? cites this paper.

Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize? Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:12:11.347497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d509bba-f692-4382-bef0-2b9effbbfdb1 · inbound

Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models cites this paper.

Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:49.265422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258441ab-7d9b-49af-8e50-a1c207a64b6f · inbound

Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead cites this paper.

Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-19T02:12:55.698013Z

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.

Observation b29fc0df-0378-4ed7-9310-c33a7ef201f9 · inbound

Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test cites this paper.

Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T17:28:41.999957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac61b992-31eb-42cb-8f07-9b25bab39f80 · inbound

Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations cites this paper.

Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T10:50:28.986221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3fe2c25-97f7-4ad1-85dd-c30545ef9abb · inbound

How Do Language Models Compose Functions? cites this paper.

How Do Language Models Compose Functions? Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T11:06:17.651651Z

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.

Observation de87f7ae-b17f-4c8e-b5c7-f46700c0d710 · inbound

When Verification Fails: How Compositionally Infeasible Claims Escape Rejection cites this paper.

When Verification Fails: How Compositionally Infeasible Claims Escape Rejection Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T08:30:58.770152Z

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.

Observation 947c7cc0-196f-4708-a8f1-8387d027c792 · inbound

Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance cites this paper.

Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 88

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:56:47.943215Z

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.

Observation dc976031-228b-4769-96a8-b29cf482fbba · inbound

Gradient-Based Program Synthesis with Neurally Interpreted Languages cites this paper.

Gradient-Based Program Synthesis with Neurally Interpreted Languages Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 61

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:56:09.255758Z

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.

Observation e70fcc8a-dbd2-4f05-b2ca-e38f1f1a54a4 · inbound

How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem cites this paper.

How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T01:45:51.993772Z

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.

Observation 2acf4377-0d7f-42fc-931e-74d32a2ecbd3 · inbound

Is She Even Relevant? When BERT Ignores Explicit Gender Cues cites this paper.

Is She Even Relevant? When BERT Ignores Explicit Gender Cues Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:50:55.449012Z

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.

Observation 6c5f7b40-fa2d-4e16-9b66-0e7e849cee6b · inbound

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition cites this paper.

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:52:08.678449Z

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.

Observation 785d8acd-f290-4b37-babb-04535f49d2b4 · inbound

Investigating Concept Alignment Using Implausible Category Members cites this paper.

Investigating Concept Alignment Using Implausible Category Members Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T09:14:45.623827Z

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.

Observation a3cabf13-e2b2-4265-a4c8-6bcfdcc13468 · inbound

Brain-LLM Alignment Tracks Training Data, Not Typology cites this paper.

Brain-LLM Alignment Tracks Training Data, Not Typology Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:45:23.017738Z

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.

Observation 580e03a0-ccf0-4e8f-934b-9be3c200f5d0 · inbound

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation cites this paper.

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T08:53:15.649920Z

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.

Observation f27f6629-3f00-4d02-83fa-6fdff3123352 · inbound

Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence cites this paper.

Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:32:35.403391Z

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.

Observation 579d769b-c004-4936-938a-cf55ac190bf6 · inbound

Consistency Training while Mitigating Obfuscation via Rate Matching cites this paper.

Consistency Training while Mitigating Obfuscation via Rate Matching Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-28T14:32:18.142375Z

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.

Observation 87def45e-f137-4ad6-826a-da0afb83e0f7 · inbound

Empirical Study for Structured Output Control in LLMs for Software Engineering cites this paper.

Empirical Study for Structured Output Control in LLMs for Software Engineering Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T02:47:37.524525Z

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.

Observation 0059e049-6af2-4e99-a592-67c177993321 · inbound

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models cites this paper.

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T18:53:51.912792Z

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.

Observation 762acea0-c741-4cdb-9c08-67514e58de16 · inbound

Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning cites this paper.

Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T15:08:32.713343Z

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.

Observation 725cebcd-b851-4ec2-9c94-9cdd7fd0ec2c · inbound

Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives cites this paper.

Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-01T15:26:58.293344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.