Paper Citation Record · LEDGER

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures

As of 17 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.27617.

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

pith.paper-citation-record.v1
2607.27617 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T04:38:50.463405Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 525dd4db-f4ba-4980-b028-38ae4d601580 · outbound

This paper cites What is in R1? What value is stored in R1? Return the value of R1.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures What is in R1? What value is stored in R1? Return the value of R1

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.862323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb0d65d-5647-4180-9069-ef12bb217580 · outbound

This paper cites Coordination Among Neural Modules Through a Shared Global Workspace.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Coordination Among Neural Modules Through a Shared Global Workspace

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.695120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7e363d1-8075-43ea-8538-d5336d2af231 · outbound

This paper cites The Llama 3 Herd of Models.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.848813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae59fc80-2cd8-41a8-9f87-112fcf225a01 · outbound

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

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Verbalizable Representations Form a Global Workspace in Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.969437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b25919b-5a48-4033-a316-5cdd3fb9bfbd · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.315072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 742dbb2d-fc81-4d2a-990b-bbabf32eb826 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.558628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de55a49-4185-4bdf-9369-cdbf6b1a54f2 · outbound

This paper cites The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.704646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d3824c-817b-4d15-b155-2161929e66cf · outbound

This paper cites Proofwriter: Generating implications, proofs, and abductive statements over natural language.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Proofwriter: Generating implications, proofs, and abductive statements over natural language

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.828512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db2a2871-d1f4-45a8-9eac-10434247e324 · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet—transformer-circuits.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet—transformer-circuits

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.948363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bad18a71-8f05-4d9c-b017-d71e07bc5762 · outbound

This paper cites Steering Language Models With Activation Engineering.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Steering Language Models With Activation Engineering

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.093668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5024ea-41ee-48c5-9aa3-63bcf72d1120 · outbound

This paper cites Model Organisms for Emergent Misalignment.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Model Organisms for Emergent Misalignment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.192379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f4d5b9-bccc-47af-b6b1-ba755438641c · outbound

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

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Representation Engineering: A Top-Down Approach to AI Transparency

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.368600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7e78b9-69c5-462b-b27a-88fbde0c9751 · outbound

This paper cites an unresolved cited work.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.540080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b47e0d-33d1-4cee-8454-08085ee51064 · outbound

This paper cites Supplementary Fig.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Supplementary Fig

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:50.222566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25489f4d-d239-4a18-82de-b8dda0157f29 · outbound

This paper cites Density and hub overlap differ from matched null graphs at p <0.001.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Density and hub overlap differ from matched null graphs at p <0.001

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:50.338846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e5789e-5aef-4026-8a5e-90195245000f · outbound

This paper cites The Shared architecture is favored under the tested operation bank and coding contract.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures The Shared architecture is favored under the tested operation bank and coding contract

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:50.463405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65aa6cfa-f1d5-48b8-9337-ddbe5745b855 · outbound

This paper cites an unresolved cited work.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Unresolved cited work

Reference 300

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:49.697066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24dcb9b-1607-4e90-916b-cfd26b790e70 · outbound

This paper cites always Shared.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures always Shared

Reference 512

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:50.022110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 958832b7-ea95-46ec-8014-a855eebab417 · outbound

This paper cites Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives

Reference 1993

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:46.959081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652f6c59-9509-4d69-8400-22a9019ddd27 · outbound

This paper cites Principal component analysis.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Principal component analysis

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.448397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81145fc9-2271-4a90-a257-8aa95e6d5e06 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Scaling and evaluating sparse autoencoders

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.319921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 185a0d8f-3d6a-4c1d-9262-4358f8ad36a4 · outbound

This paper cites The Consciousness Prior.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures The Consciousness Prior

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.098855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c4911a3-76a3-4c47-a933-f075ac900c0b · outbound

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

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.201686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54dea94e-c682-4258-8e7a-fe02286e01dc · outbound

This paper cites Localizing Model Behavior with Path Patching.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Localizing Model Behavior with Path Patching

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.572549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 040dc338-e7f4-40cf-a6d5-09e949d9ebf7 · outbound

This paper cites Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.440173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047b2678-4406-449c-a449-06bd6f84fa9b · outbound

This paper cites In-context learning creates task vectors.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures In-context learning creates task vectors

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:48.144072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.