Pith. sign in

Paper Citation Record · LEDGER

Transformers Learn Latent Mixture Models In-Context via Mirror Descent

As of 16 August 2026, this Paper Citation Record lists 5 of 5 outbound references and 0 inbound Pith citation observations for arXiv:2604.10848.

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

pith.paper-citation-record.v1
2604.10848 v1

Coverage vector

measured 5 of 5 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T15:22:21.955640Z

measured 5 of 5 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 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

5 of 5 outbound references displayed

  • verified exact0
  • verified fuzzy4
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe242d53-4e3a-4b84-98e4-bc8ac54c0e9a · outbound

This paper cites Transformers on Markov Data: Constant Depth Suffices.

Transformers Learn Latent Mixture Models In-Context via Mirror Descent Transformers on Markov Data: Constant Depth Suffices

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T10:41:05.038608Z

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=2026-05-10T15:22:21.955640Z digest=sha256:0a048de2885d944252940ed14a7634c963722a296e1f3c424e8c61b0224d8ed5

Observation 212bbb76-5681-4c23-a220-48789a0d8d77 · outbound

This paper cites It represents the theoretical performance limit for inference under the MTD model assumptions, providing a gold-standard benchmark against which other estimators can be compared.

Transformers Learn Latent Mixture Models In-Context via Mirror Descent It represents the theoretical performance limit for inference under the MTD model assumptions, providing a gold-standard benchmark against which other estimators can be compared

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T02:40:41.893072Z

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=2026-05-10T15:22:21.955640Z digest=sha256:35f41e39d9023608e317a6f72c0d2d3d77e93505f757cf0d7461de693d04a917

Observation 449fe2f6-50c6-4cef-9bd1-ac964298f925 · outbound

This paper cites no evidence.

Transformers Learn Latent Mixture Models In-Context via Mirror Descent no evidence

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T02:40:41.889593Z

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=2026-05-10T15:22:21.955640Z digest=sha256:69a79c3cf2adc7f5aae29fcf699f24b6de96452fb46251c2a3cd04f52962ad49

Observation d30ed26a-c687-4074-abbf-9cf3569d7c1d · outbound

This paper cites Using equation 43 we get the upper bound∥c t∥2 2 ≤m·1 2 =mfor everyt.

Transformers Learn Latent Mixture Models In-Context via Mirror Descent Using equation 43 we get the upper bound∥c t∥2 2 ≤m·1 2 =mfor everyt

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T02:40:41.896390Z

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=2026-05-10T15:22:21.955640Z digest=sha256:b0d451b60668f57882c6c540f15db28e1ec1d2ef869786972fc5946fa2f0fe85

Observation b752d62d-d8ee-4a70-9892-056bfa49f1f3 · outbound

This paper cites Using this inequality we obtain, for everyt, m2 S2 t ∥ct∥2 2 ≤ m2 S2 t S2 t =m 2.

Transformers Learn Latent Mixture Models In-Context via Mirror Descent Using this inequality we obtain, for everyt, m2 S2 t ∥ct∥2 2 ≤ m2 S2 t S2 t =m 2

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T02:40:41.900041Z

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=2026-05-10T15:22:21.955640Z digest=sha256:8d65cda1413ffd777bcc2af8c94329a44354c51daab1bc9adc5bf77445552519

Pith citing papers

No inbound Pith citation observations are available.