Paper Citation Record · LEDGER

Geometric Metrics and LLMs: What They Measure and When They Work

As of 23 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2509.25359.

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

pith.paper-citation-record.v1
2509.25359 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:47:42.935255Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T09:15:32.395442Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T09:16:19.644401Z

Reference resolution

20 of 20 outbound references displayed

verified exact3
verified fuzzy2
unresolved14
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 347e7b87-3588-41db-9f45-64bd6d1d1c46 · outbound

This paper cites Robust AI-Generated Text Detection by Restricted Embeddings.

Geometric Metrics and LLMs: What They Measure and When They Work Robust AI-Generated Text Detection by Restricted Embeddings

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.873599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e701f1-e1e4-4590-a5e7-ddadac86f02b · outbound

This paper cites Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders.

Geometric Metrics and LLMs: What They Measure and When They Work Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.878053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 058c8497-7809-493d-bb71-07f22dfaa99b · outbound

This paper cites The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models.

Geometric Metrics and LLMs: What They Measure and When They Work The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.895701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425605f3-a283-42e6-9ad6-e2337ce92ec5 · outbound

This paper cites Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs.

Geometric Metrics and LLMs: What They Measure and When They Work Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:47:43.059303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a82ba433-f763-410e-9f0e-592be8917395 · outbound

This paper cites The Geometry of Tokens in Internal Representations of Large Language Models.

Geometric Metrics and LLMs: What They Measure and When They Work The Geometry of Tokens in Internal Representations of Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.908419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c084c3a-df1d-4bb4-9e15-cef976ed7740 · outbound

This paper cites Automated Evaluation of Personalized Text Generation using Large Language Models.

Geometric Metrics and LLMs: What They Measure and When They Work Automated Evaluation of Personalized Text Generation using Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.912853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04fdde5-c4fe-417b-94fc-dbdb9222f47f · outbound

This paper cites Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation.

Geometric Metrics and LLMs: What They Measure and When They Work Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.917073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 375bece8-fdb9-4fe6-abdc-ba5593df5f5e · outbound

This paper cites BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training.

Geometric Metrics and LLMs: What They Measure and When They Work BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:47:42.998499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5b6cb0bd-73e8-4d85-8595-2dc99173262b · outbound

This paper cites Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension.

Geometric Metrics and LLMs: What They Measure and When They Work Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.925827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 225e7443-c65b-43bf-881a-3b1cb3912ae2 · outbound

This paper cites MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance.

Geometric Metrics and LLMs: What They Measure and When They Work MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.930576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6a45b61-cd2e-40ba-9e24-836c7bce597f · outbound

This paper cites an unresolved cited work.

Geometric Metrics and LLMs: What They Measure and When They Work Unresolved cited work

Reference 20

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T15:47:43.270570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dc94f30c-06d0-458f-8503-67ec9d5d0663 · outbound

This paper cites Scaling Parameter-Constrained Language Models with Quality Data.

Geometric Metrics and LLMs: What They Measure and When They Work Scaling Parameter-Constrained Language Models with Quality Data

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.851694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27713baa-fef7-4daf-9e48-6253b6aa0672 · outbound

This paper cites Anisotropy Is Inherent to Self-Attention in Transformers.

Geometric Metrics and LLMs: What They Measure and When They Work Anisotropy Is Inherent to Self-Attention in Transformers

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.860797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1906bceb-aa64-460b-b17d-08968dbc2cad · outbound

This paper cites A Survey on Large Language Model Benchmarks.

Geometric Metrics and LLMs: What They Measure and When They Work A Survey on Large Language Model Benchmarks

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.882488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62d47e6-ef60-440b-a314-c22890608ce0 · outbound

This paper cites How contextual are contextualized word representations? comparing the geom- etry of bert, elmo, and gpt-2 embeddings.

Geometric Metrics and LLMs: What They Measure and When They Work How contextual are contextualized word representations? comparing the geom- etry of bert, elmo, and gpt-2 embeddings

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:47:43.296480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 23f6d9f7-f540-4066-b162-bcd7250f2dd0 · outbound

This paper cites URLhttps://www.aclweb.org/ anthology/2020.lrec-1.202/.

Geometric Metrics and LLMs: What They Measure and When They Work URLhttps://www.aclweb.org/ anthology/2020.lrec-1.202/

Reference 2020

Resolution: verified exact; raw_fallback, observed 2026-08-15T15:47:43.233509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bebba29c-5cb4-492c-bbe6-150bbe8d023e · outbound

This paper cites Human Perception of LLM-generated Text Content in Social Media Environments.

Geometric Metrics and LLMs: What They Measure and When They Work Human Perception of LLM-generated Text Content in Social Media Environments

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.891297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0f5257-377b-4263-a021-6c67ca6dc559 · outbound

This paper cites The shape of learning: Anisotropy and intrinsic dimensions in transformer- based models.

Geometric Metrics and LLMs: What They Measure and When They Work The shape of learning: Anisotropy and intrinsic dimensions in transformer- based models

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:47:43.283534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e7e2b1c4-2f0f-4d45-be6b-cfa4ad6a3664 · outbound

This paper cites Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions.

Geometric Metrics and LLMs: What They Measure and When They Work Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.869590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f178a5-f380-4511-a27b-9fd411bcdbc0 · outbound

This paper cites Large Language Diffusion Models.

Geometric Metrics and LLMs: What They Measure and When They Work Large Language Diffusion Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:42.887025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ddef3172-311e-4922-b4de-7cf62f78c8f9 · inbound

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes cites this paper.

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes Geometric Metrics and LLMs: What They Measure and When They Work

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-11T02:08:34.461803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5b7d90ed-a98e-4947-9c50-38cac50fd68a · inbound

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes cites this paper.

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes Geometric Metrics and LLMs: What They Measure and When They Work

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-11T02:08:34.461803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.