Pith Number

pith:WDGDTGCO

pith:2026:WDGDTGCOTTJX46EC2GFEBW7GAY

not attested not anchored not stored refs resolved

MedASR: An Open-Source Model for High-Accuracy Medical Dictation

Ehsan Variani, Ke Wu, Rory Pilgrim, Shashir Reddy, Tom Bagby

MedASR is a 105M-parameter open-source model that achieves a 58% relative WER reduction on medical dictation versus Whisper Large-v3.

arxiv:2605.16555 v1 · 2026-05-15 · eess.AS

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WDGDTGCOTTJX46EC2GFEBW7GAY}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our evaluation shows that MedASR achieves a 58% relative WER reduction on Eye Gaze compared to Whisper Large-v3.

C2weakest assumption

The Eye Gaze dataset and evaluation protocol provide a fair and representative measure of real-world medical dictation performance that generalizes beyond the test conditions.

C3one line summary

MedASR is an open-source 105M-parameter ASR model achieving 58% relative WER reduction versus Whisper Large-v3 on medical dictation.

References

36 extracted · 36 resolved · 5 Pith anchors

[1] Introduction The administrative burden of clinical documentation is a pri- mary driver of physician burnout, creating an urgent need for robust Automated Speech Recognition (ASR) systems [1, 2]. While

[2] The MedASR Foundation MedASR is built on a 105M-parameter Conformer architecture

[3] MedASR: An Open-Source Model for High-Accuracy Medical Dictation 2026 · arXiv:2605.16555

[4] • Conformer Encoder: 17 layers, 512 activations, and 8 at- tention heads

[5] Bootstrapping: A seed model was trained exclusively on a subset of the data containing naturally occurring short sequences (up to 36s)

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

MedASR: An Open-Source Model for High-Accuracy Medical Dictation

Receipt and verification

First computed	2026-05-20T00:02:28.937186Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b0cc39984e9cd37e7882d18a40dbe60632177144db00fd307ad896272010cfc9

Aliases

arxiv: 2605.16555 · arxiv_version: 2605.16555v1 · doi: 10.48550/arxiv.2605.16555 · pith_short_12: WDGDTGCOTTJX · pith_short_16: WDGDTGCOTTJX46EC · pith_short_8: WDGDTGCO

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/WDGDTGCOTTJX46EC2GFEBW7GAY \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b0cc39984e9cd37e7882d18a40dbe60632177144db00fd307ad896272010cfc9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "aae8a86478dc9f231e6f9cc83865942fe6ceb19311ba39daa7a5e58d921e6a33",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-05-15T18:57:48Z",
    "title_canon_sha256": "475b8365ba21426537de5e60dd42c1b45e1adb0da98737c44900c5b9f86ad613"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16555",
    "kind": "arxiv",
    "version": 1
  }
}