Pith Number

pith:FUHSEB34

pith:2026:FUHSEB34TNMYFH4KTQBJYN6VME

not attested not anchored not stored refs resolved

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

Andreas Hellander, Ekta Vats, Li Ju, Mayank Nautiyal, Prashant Singh

A single masked velocity field on paired hyperspherical embeddings yields valid joint and conditional Riemannian flows for uncertainty in frozen vision-language models.

arxiv:2605.13352 v1 · 2026-05-13 · cs.LG

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

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

A consistency result shows that, in the population limit, the trained network exposes the joint flow and both cross-modal conditional flows as valid Riemannian flow-matching velocity fields on their respective domains.

C2weakest assumption

That a single masked velocity field trained via Riemannian flow matching on paired hyperspherical embeddings will yield practically useful conditional and marginal distributions whose derived entropy and typicality scores remain calibrated on real benchmarks.

C3one line summary

GeoFlowVLM learns joint distributions of l2-normalized VLM embeddings on the product hypersphere via Riemannian flow matching to expose both aleatoric and epistemic uncertainty through derived entropy and typicality scores.

References

44 extracted · 44 resolved · 2 Pith anchors

[1] Learning transferable visual models from natural language supervision 2021

[2] Sigmoid loss for lan- guage image pre-training 2023

[3] Probabilistic embeddings for cross-modal retrieval 2021

[4] Prob- vlm: Probabilistic adapter for frozen vison-language models 1910

[5] Probabilistic embeddings for frozen vision-language models: uncertainty quantiﬁcation with gaussian process latent vari- able models 2025

Receipt and verification

First computed	2026-05-18T02:44:48.266387Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2d0f22077c9b59829f8a9c029c37d5612fe184ad1d5ea145f666e68df71c4a82

Aliases

arxiv: 2605.13352 · arxiv_version: 2605.13352v1 · doi: 10.48550/arxiv.2605.13352 · pith_short_12: FUHSEB34TNMY · pith_short_16: FUHSEB34TNMYFH4K · pith_short_8: FUHSEB34

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/FUHSEB34TNMYFH4KTQBJYN6VME \
  | 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: 2d0f22077c9b59829f8a9c029c37d5612fe184ad1d5ea145f666e68df71c4a82

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1dc5e46486dc9073ce16198c2b1dbf438a29c623bd04a8d46910e37a9513a65a",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:12:18Z",
    "title_canon_sha256": "f866756120ed58ea131a2ddfb1ab96090afdb6c30a9b2de4d148d69d29d76ed4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13352",
    "kind": "arxiv",
    "version": 1
  }
}