Pith Number

pith:7DCMFFRQ

pith:2026:7DCMFFRQOFPEX754FINWCOOPRV

not attested not anchored not stored refs resolved

Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2

Brinnae Bent, Stuart Bladon

Feature visualization via gradient ascent on a brain encoder recovers the known progression of selectivity from V1 to V4 and distinctive patterns for MT, FFA and PPA.

arxiv:2605.13904 v1 · 2026-05-13 · q-bio.NC · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7DCMFFRQOFPEX754FINWCOOPRV}

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

The probe recovers a visible progression of increasing spatial scale and feature complexity across V1 to V4, matching the ventral-stream hierarchy. It also produces three distinctive downstream regimes: radial frozen-motion streaks for MT, face-like features for FFA, and consistent rectilinear line patterns for PPA. Optimized FFA stimuli drive the predicted region ~4x as much as a natural face photograph.

C2weakest assumption

That gradient-ascent optimization on the encoder's output for a target ROI reveals the functional organization the model has internalized, rather than being dominated by optimization artifacts or adversarial effects unrelated to biological selectivity.

C3one line summary

Feature visualization on TRIBE v2 brain encoders recovers the known ventral visual hierarchy from V1 to V4 and produces distinctive patterns for MT, FFA, and PPA, with optimized stimuli driving ~4x higher activation than natural images.

References

20 extracted · 20 resolved · 4 Pith anchors

[1] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning · arXiv:2506.09985

[2] Preprint at bioRxiv 461525 · doi:10.1126/science.aav9436

[3] doi: 10.1146/annurev.neuro.26.041002. 131052. d’Ascoli, S., Rapin, J., Benchetrit, Y ., Banville, H., and King, J.-R. TRIBE: TRImodal brain encoder for whole- brain fMRI response prediction.arXiv prep · doi:10.1146/annurev.neuro.26.041002

[4] arXiv preprint arXiv:2507.22229 , year= 2025 · doi:10.48550/arxiv.2507.22229

[5] Erhan, D., Bengio, Y ., Courville, A., and Vincent, P · doi:10.1038/33402

Receipt and verification

First computed	2026-05-17T23:39:18.906801Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f8c4c29630715e4bffbc2a1b6139cf8d63b079af205884cdcfe1b92619bcd64b

Aliases

arxiv: 2605.13904 · arxiv_version: 2605.13904v1 · doi: 10.48550/arxiv.2605.13904 · pith_short_12: 7DCMFFRQOFPE · pith_short_16: 7DCMFFRQOFPEX754 · pith_short_8: 7DCMFFRQ

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/7DCMFFRQOFPEX754FINWCOOPRV \
  | 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: f8c4c29630715e4bffbc2a1b6139cf8d63b079af205884cdcfe1b92619bcd64b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "25cf1bd8fab9d3678d5336d7ea5d0ad10cbd6dc804ffefea5ec87f0eed424c6f",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "q-bio.NC",
    "submitted_at": "2026-05-13T00:55:45Z",
    "title_canon_sha256": "5973fed065e3d730ca7c72bbcb608abde9c84fa8ec31bfc316f1c200254e904e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13904",
    "kind": "arxiv",
    "version": 1
  }
}