Paper Citation Record · LEDGER

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2305.00586.

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

pith.paper-citation-record.v1
2305.00586 v5

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 10 of 10 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:01:28.869981Z

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

14
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 977a0f4c-402a-4e83-b388-7ed56044895c · inbound

How to use and interpret activation patching cites this paper.

How to use and interpret activation patching How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:34:06.964524Z

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 775b86ba-2ead-4d2f-8e0d-54c49a9d4319 · inbound

On Mechanistic Circuits for Extractive Question-Answering cites this paper.

On Mechanistic Circuits for Extractive Question-Answering How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.869981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85fd806-9985-45e6-81e9-159e2ab2f9e0 · inbound

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race cites this paper.

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:17.160012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0886e2a4-bb5e-4221-87ee-b77f5ad9c369 · inbound

NEAT: Concept driven Neuron Attribution in LLMs cites this paper.

NEAT: Concept driven Neuron Attribution in LLMs How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T18:01:19.631659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5296ca8-d6ab-4752-b351-83d9a87d7f96 · inbound

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits cites this paper.

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:37:53.812763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c19a30-250e-411e-824e-e509d3b75155 · inbound

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning cites this paper.

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T13:03:22.096173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc775181-050f-48b9-953f-0384c27e84f6 · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 152

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:54.449139Z

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 60b0f94f-d1f6-4d2e-be43-50e1a9f8b02d · inbound

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models cites this paper.

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T07:06:44.475064Z

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 605507d4-3db6-4515-9abd-a7df0d789ecf · inbound

Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability? cites this paper.

Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability? How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T16:19:57.638846Z

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 95278f95-773d-4c71-a00a-1c1eaf1caf37 · inbound

Pretraining Curricula Enable Selective Fine-tuning cites this paper.

Pretraining Curricula Enable Selective Fine-tuning How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T12:36:24.747752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.