Paper Citation Record · LEDGER

When Mean CE Fails: Median CE Can Better Track Language Model Quality

As of 12 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2605.24667.

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

pith.paper-citation-record.v1
2605.24667 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T13:23:55.114628Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

13 of 13 outbound references displayed

verified exact11
verified fuzzy1
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5dd350d3-ded2-45d1-9f8b-f0ff8599591e · outbound

This paper cites Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.967032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 08efea3f-7c10-49d2-b791-c5b0130c9f66 · outbound

This paper cites TinyStories: How Small Can Language Models Be and Still Speak Coherent English?.

When Mean CE Fails: Median CE Can Better Track Language Model Quality TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.950539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8d46e23f-9dff-4889-bf50-fb293cab2fbd · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

When Mean CE Fails: Median CE Can Better Track Language Model Quality MiniLLM: On-Policy Distillation of Large Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.971420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4ddf8e2c-bd92-43df-8662-8385a14a450e · outbound

This paper cites Distilling the Knowledge in a Neural Network.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Distilling the Knowledge in a Neural Network

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.953012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4582d3fa-d37a-48e4-8a69-d02152f30f1f · outbound

This paper cites TinyBERT: Distilling BERT for Natural Language Understanding.

When Mean CE Fails: Median CE Can Better Track Language Model Quality TinyBERT: Distilling BERT for Natural Language Understanding

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:24:39.948088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dcff0ee8-55f5-490f-b00c-e509c786d58b · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

When Mean CE Fails: Median CE Can Better Track Language Model Quality The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.966451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d72e7980-5f28-434e-b71f-1ae3d651c4f3 · outbound

This paper cites Observational Scaling Laws and the Predictability of Language Model Performance.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Observational Scaling Laws and the Predictability of Language Model Performance

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:24:39.964653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5f617ea4-428a-4893-875e-c6a49a081e6f · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

When Mean CE Fails: Median CE Can Better Track Language Model Quality DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.961897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b5427515-d49a-42e9-980f-3f2799e3eb94 · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Retentive Network: A Successor to Transformer for Large Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.969088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 50be2b67-81f4-4c61-a01a-4ed1c52d5940 · outbound

This paper cites Qwen2.5 Technical Report.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Qwen2.5 Technical Report

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:24:39.958038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 73242296-a5cc-4025-8218-df897c01fdea · outbound

This paper cites ?”. Examples include“Complete: Above Nimbusglade floats ___.

When Mean CE Fails: Median CE Can Better Track Language Model Quality ?”. Examples include“Complete: Above Nimbusglade floats ___

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:24:39.960958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 13209490-057f-40ac-9fec-9b2df9b6a257 · outbound

This paper cites Large”; 4-layer, 256-dim, 4 heads,∼8M params for “Small.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Large”; 4-layer, 256-dim, 4 heads,∼8M params for “Small

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T02:15:55.293452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 504c4165-0fed-412a-b482-d6819d6adb7d · outbound

This paper cites an unresolved cited work.

When Mean CE Fails: Median CE Can Better Track Language Model Quality Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-07-09T02:15:55.291672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

No inbound Pith citation observations are available.