Pith. sign in

Paper Citation Record · LEDGER

Benchmarking and Understanding Compositional Relational Reasoning of LLMs

As of 15 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2412.12841.

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

pith.paper-citation-record.v1
2412.12841 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T13:46:27.679324Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T04:30:42.215749Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T04:30:49.091477Z

Reference resolution

13 of 13 outbound references displayed

  • verified exact0
  • verified fuzzy8
  • unresolved4
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 513ffc2f-05b3-47c4-bf87-5e27631667f2 · outbound

This paper cites an unresolved cited work.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-11T13:46:27.848653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.649801Z digest=sha256:d5d4aa5a9493ce2b961e9e28bc87b5dedf4b94806a58316dbe3707f70291b91a

Observation c4d79150-d5f9-4943-8908-c0b24b483e82 · outbound

This paper cites an unresolved cited work.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-11T13:46:27.833801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.654302Z digest=sha256:63126fb09c2a5bc374a82c6257d93a84776e327be6cd173735abe66c0939214b

Observation 5e0da18e-023e-4a87-8470-b06ad3e73e1c · outbound

This paper cites vehicle.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs vehicle

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.817687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.658924Z digest=sha256:28ee1f3d6ddb72546502b7ca4ecb6a1b9f3fe90eb1f551b0a1b826b722240fa7

Observation b7e3d495-4d6e-445a-b37c-e72cc035341f · outbound

This paper cites affirmative generation) have the same overall structure.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs affirmative generation) have the same overall structure

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.801845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.664680Z digest=sha256:c7a779b44beefbdd1828040c95a36e114ef597076de077c095d93044d0a60e4b

Observation d98e33f1-4942-4036-9a1e-583ba0d4be24 · outbound

This paper cites 18.13 PPred.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs 18.13 PPred

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.785854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.669036Z digest=sha256:bba3dadd7310750f353954bb275794e5ba10d60d6e0bc44569bb9719773c2c15

Observation 4d621e95-61a6-4f02-a468-95a04fe9d129 · outbound

This paper cites heads vary with different rretrieve, because they retrieve different attributes according to the semantic re- lation.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs heads vary with different rretrieve, because they retrieve different attributes according to the semantic re- lation

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.770402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.673961Z digest=sha256:58638f544fef3ca93a26549e2aaf88546f3735c42b3a338005b7b6e88882ee83

Observation cbfb198f-3a6f-427b-b75c-96c63349b9c0 · outbound

This paper cites Premise: {premise}. Please answer with Yes or No. Can it be inferred from the premise that {hypothesis}? Answer:→{label}.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs Premise: {premise}. Please answer with Yes or No. Can it be inferred from the premise that {hypothesis}? Answer:→{label}

Reference 13

Resolution
malformed identifier
raw_fallback, observed 2026-08-11T13:46:27.754408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.679324Z digest=sha256:e87489763fb586712997620cc38b785ab1063f263396cd2ed1e2f44f2fd87ee8

Observation d50d27c9-7099-40c4-acdf-57357d3f56e8 · outbound

This paper cites In Proceedings of the 2015 Conference on Empir- ical Methods in Natural Language Processing (EMNLP).

Benchmarking and Understanding Compositional Relational Reasoning of LLMs In Proceedings of the 2015 Conference on Empir- ical Methods in Natural Language Processing (EMNLP)

Reference 2015

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.912589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.617421Z digest=sha256:fbdbb603842d6d1fb14a9dc11fc36e274d9357b8a96327d809622cee44dde537

Observation 4c13c7dc-a374-4afd-9010-aa3f8a0507ba · outbound

This paper cites Transformer Circuits Thread, 1(1): 12.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs Transformer Circuits Thread, 1(1): 12

Reference 2021

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.878930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.628024Z digest=sha256:b0caf4fa7486a7c067d9a7f0ac963b1e2fb7c173f70a14f06fd79cf4cbc12eb2

Observation b2772f64-865c-403c-9d77-92f3862d6589 · outbound

This paper cites In-context Learning and Induction Heads.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs In-context Learning and Induction Heads

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-11T13:46:27.643661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:46:27.643661Z digest=sha256:8c2e500765b2f66b3fb82f7a1471fad15133d245d737ebac8749bdfc95819a50

Observation a2852e28-5d65-460f-9ff7-49f36ef4f50e · outbound

This paper cites In Conference on Empirical Methods in Natural Language Processing (EMNLP).

Benchmarking and Understanding Compositional Relational Reasoning of LLMs In Conference on Empirical Methods in Natural Language Processing (EMNLP)

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.863491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.632925Z digest=sha256:e8fb8bad99a339dd56f7c86e03bf8a1d8479b1c888c7446cd1abd0e5d75b0605

Observation fde9c21e-bda1-4612-81ed-30fe522c16fe · outbound

This paper cites In Advances in Neural Information Processing Systems (NeurIPS), volume 36.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs In Advances in Neural Information Processing Systems (NeurIPS), volume 36

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:46:27.896109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T13:46:27.622942Z digest=sha256:8e8c238fdcd7169245286d9b405fdca0c271ffb2846399f68ee22bd108c829d8

Observation 125a6361-79da-4adf-8678-fcfaf5742bf9 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Benchmarking and Understanding Compositional Relational Reasoning of LLMs The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 2882

Resolution
unresolved
no resolver link, observed 2026-08-11T13:46:27.638083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:46:27.638083Z digest=sha256:eab890ad5b860737667cbb94c1e5f70f5587797ec51e632969a4873b4eeb108a

Pith citing papers

Observation a0bb827e-e8e3-4fb8-9109-87a6f223097e · inbound

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning cites this paper.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning Benchmarking and Understanding Compositional Relational Reasoning of LLMs

Reference 35

Resolution
verified exact
local_arxiv, observed 2026-08-06T04:30:49.095104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-06T04:30:42.215749Z digest=sha256:6781029ea3db54ff3e2bd84b81b7f3d536d37990c85a943e40d3f8dd121e883a