Pith. sign in

Paper Citation Record · LEDGER

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express

As of 20 August 2026, this Paper Citation Record lists 7 of 7 outbound references and 0 inbound Pith citation observations for arXiv:2605.25891.

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

pith.paper-citation-record.v1
2605.25891 v1

Coverage vector

measured 7 of 7 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:13:32.378862Z

measured 7 of 7 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 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

7 of 7 outbound references displayed

  • verified exact1
  • verified fuzzy0
  • unresolved2
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d8e4eeaf-744f-4b17-891c-14c4e4fb381c · outbound

This paper cites InAdvances in Neural Information Processing Systems (NeurIPS), pages 66044–66063.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express InAdvances in Neural Information Processing Systems (NeurIPS), pages 66044–66063

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-29T22:13:32.378862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:4a85d3279ad48dad80bc73e23ea4608e3d3d2d07b3f1d6c41850ea10fb161c0e

Observation 9da43dc0-b74f-4845-8786-1a267269f772 · outbound

This paper cites CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models

Reference 2

Resolution
metadata mismatch
local_arxiv, observed 2026-06-29T22:13:59.307409Z

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.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:d38f6faa9133861ac1ae9a2023152b72637af27dccb4049347e9fb7ea8369948

Observation 99815bc9-5498-4231-a359-5e014c213440 · outbound

This paper cites CausaLM: Causal Model Explanation Through Counterfactual Language Models.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express CausaLM: Causal Model Explanation Through Counterfactual Language Models

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-06-29T22:13:59.304753Z

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.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:cfe60f72bdbb62fdd8bc337b8ac658a7eb7aaea612d784fc027aa113c4bba547

Observation e0173868-2849-46b3-9fed-ba9a2a8aec7b · outbound

This paper cites Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Reference 4

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T22:13:59.318138Z

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.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:3a435c6ad7992915804e16affe9e7c6ab3b472f32b128f3a0e67954221927986

Observation 3fc0dc93-831d-409e-addb-a0d0c250c4db · outbound

This paper cites InThe Thirteenth International Conference on Learning Representations (ICLR).

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express InThe Thirteenth International Conference on Learning Representations (ICLR)

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-29T22:13:32.378862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:3c03c3c1235d01881b9cf061ff3fbc9c31f0e083021e02369b9fee8b6ef6be20

Observation 5d2194b0-7703-4664-9e07-b22047cdcd3e · outbound

This paper cites Qwen2.5 Technical Report.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express Qwen2.5 Technical Report

Reference 6

Resolution
metadata mismatch
local_arxiv, observed 2026-06-29T22:13:59.315393Z

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.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:6673cfa89f4b752137f492716b06af796bee8137a4afbc14f49d9bc4cd89c4dc

Observation 43cfe100-717c-4622-83d8-99d0a3cab3d6 · outbound

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

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express Representation Engineering: A Top-Down Approach to AI Transparency

Reference 7

Resolution
malformed identifier
local_arxiv, observed 2026-06-29T22:13:59.312193Z

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.

source=pdf_text observed=2026-06-29T22:13:32.378862Z digest=sha256:1b929a81b6d2b954aa88d941382ecb3b889922e281f55b3e9271c60c5c2a2236

Pith citing papers

No inbound Pith citation observations are available.