Paper Citation Record · LEDGER

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability

As of 20 August 2026, this Paper Citation Record lists 7 of 7 outbound references and 1 inbound Pith citation observation for arXiv:2605.26343.

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

pith.paper-citation-record.v1
2605.26343 v2

Coverage vector

measured 7 of 7 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T11:28:29.391851Z

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:37:21.478819Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T04:37:21.891300Z

Reference resolution

7 of 7 outbound references displayed

verified exact0
verified fuzzy7
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a81839fe-1001-439f-81fe-7b50e35ca24c · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability Towards automated circuit discovery for mechanistic interpretability

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.243217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eb619642-b9fe-4722-b99e-16b8fcfd1744 · outbound

This paper cites A mathematical framework for transformer circuits.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability A mathematical framework for transformer circuits

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.232951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e03b03cb-7cbe-443c-958e-725828609baa · outbound

This paper cites A circuit for Python docstrings in a 4-layer attention-only transformer.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability A circuit for Python docstrings in a 4-layer attention-only transformer

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.239188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8aa17024-6a27-440c-911b-797ca109fe40 · outbound

This paper cites Attribution patching: Activation patching at industrial scale.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability Attribution patching: Activation patching at industrial scale

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.235220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 901c0840-bf4e-4c0e-8c81-bcbaee0f659c · outbound

This paper cites In-context learning and induction heads.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability In-context learning and induction heads

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.245140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3d52c52b-48e9-4083-9b3b-5a14e9587b85 · outbound

This paper cites Proximal policy optimization algorithms.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability Proximal policy optimization algorithms

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.241270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 526dfb5d-95a5-43cc-8518-096149de8dbc · outbound

This paper cites Interpretability in the wild: A circuit for indirect object identification in GPT -2 small.

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability Interpretability in the wild: A circuit for indirect object identification in GPT -2 small

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:10.237327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation aedab491-bb82-450f-9745-760b271543e4 · inbound

Can Graph Learning Learn Circuits? cites this paper.

Can Graph Learning Learn Circuits? MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:37:21.896236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.