Paper Citation Record · LEDGER

Slot Machines: How LLMs Keep Track of Multiple Entities

As of 5 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2604.21139.

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

pith.paper-citation-record.v1
2604.21139 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-09T23:48:36.019590Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T23:15:18.699660Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact11
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f5288b2e-0484-4307-aa07-07342f645c7a · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Slot Machines: How LLMs Keep Track of Multiple Entities Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:01:04.059381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 466d200c-636a-4154-8f06-58bbb44007e6 · outbound

This paper cites Burke, Tristan Hume, Shan Carter, Tom Henighan, and Christopher Olah.

Slot Machines: How LLMs Keep Track of Multiple Entities Burke, Tristan Hume, Shan Carter, Tom Henighan, and Christopher Olah

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T12:25:39.894710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 43171d1e-7c69-4c3f-b85e-79efb3d43d4b · outbound

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

Slot Machines: How LLMs Keep Track of Multiple Entities Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:01:04.072173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a058615d-a715-4440-950a-88349cd92929 · outbound

This paper cites Representational Analysis of Binding in Language Models.

Slot Machines: How LLMs Keep Track of Multiple Entities Representational Analysis of Binding in Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:01:03.962542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dd3de2ae-4022-44e0-8c28-6a86074cc888 · outbound

This paper cites Measuring the persuasiveness of language models.https://www.anthropic.com/research/ measuring-model-persuasiveness.

Slot Machines: How LLMs Keep Track of Multiple Entities Measuring the persuasiveness of language models.https://www.anthropic.com/research/ measuring-model-persuasiveness

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T12:25:39.898190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 92c1948e-7da8-463f-813c-6c4e664f19ac · outbound

This paper cites How do Language Models Bind Entities in Context?.

Slot Machines: How LLMs Keep Track of Multiple Entities How do Language Models Bind Entities in Context?

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:01:04.033376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e75ba7d8-cbb3-4acf-a5a1-0c79dcb76b16 · outbound

This paper cites Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context.

Slot Machines: How LLMs Keep Track of Multiple Entities Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-29T02:04:57.235642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d06bf59d-2d11-4382-ac51-f55497cd0304 · outbound

This paper cites Representational similarity analysis – connecting the branches of systems neuroscience.Frontiers in Systems Neuroscience, 2:4.

Slot Machines: How LLMs Keep Track of Multiple Entities Representational similarity analysis – connecting the branches of systems neuroscience.Frontiers in Systems Neuroscience, 2:4

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T12:25:39.901605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2dd6379c-38d9-41c1-9176-663da8aaf276 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Slot Machines: How LLMs Keep Track of Multiple Entities Locating and Editing Factual Associations in GPT

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:58:57.694057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6747b243-3128-4945-afb4-8b0ddce9227e · outbound

This paper cites In-context Learning and Induction Heads.

Slot Machines: How LLMs Keep Track of Multiple Entities In-context Learning and Induction Heads

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:01:04.006350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cdd2fa72-0248-4394-a7df-180d8b9c69ab · outbound

This paper cites AI Deception: A Survey of Examples, Risks, and Potential Solutions.

Slot Machines: How LLMs Keep Track of Multiple Entities AI Deception: A Survey of Examples, Risks, and Potential Solutions

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:01:04.046214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50ef22f3-fff3-4990-aa32-7d87f41117fe · outbound

This paper cites Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking.

Slot Machines: How LLMs Keep Track of Multiple Entities Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:01:04.079136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 546b1e0a-dfe7-4c00-b66f-924928d37f89 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Slot Machines: How LLMs Keep Track of Multiple Entities Steering Llama 2 via Contrastive Activation Addition

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:37:21.847050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a82001df-96a8-489f-8d12-01f8207c9fbb · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Slot Machines: How LLMs Keep Track of Multiple Entities Towards Understanding Sycophancy in Language Models

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T14:01:04.052487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc88c2e0-6b7f-44ba-9353-769e3c9c8af2 · outbound

This paper cites Tensor product variable binding and the representation of symbolic structures in connectionist systems.Artificial Intelligence, 46(1–2):159–216.

Slot Machines: How LLMs Keep Track of Multiple Entities Tensor product variable binding and the representation of symbolic structures in connectionist systems.Artificial Intelligence, 46(1–2):159–216

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T12:25:39.887782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ccfc4aaf-fa7a-40bd-ad39-8d7a84df5d7b · outbound

This paper cites Treisman and Garry Gelade.

Slot Machines: How LLMs Keep Track of Multiple Entities Treisman and Garry Gelade

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T12:25:39.891027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c5707b0e-d2eb-4ebf-bbb0-6962fda2427d · outbound

This paper cites Steering Language Models With Activation Engineering.

Slot Machines: How LLMs Keep Track of Multiple Entities Steering Language Models With Activation Engineering

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:01:04.023514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 84589b15-46d6-4cab-b686-5432bf43894a · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Slot Machines: How LLMs Keep Track of Multiple Entities Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:01:04.014750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 93cceac6-59c2-4b7b-b3a7-b1c64741ea6e · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Slot Machines: How LLMs Keep Track of Multiple Entities

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.699660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.