Pith Number

pith:HB4I3UAL

pith:2026:HB4I3UALQBOZ3ZS7IIR3XBQZNP

not attested not anchored not stored refs resolved

Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL

Hwiyoung Kim, Hyun Do Jung, Jungwon Choi, Soojung Choi, Yujin Oh

FOCI reveals that compact rationales for frozen WSI-MIL predictions depend on the choice of backbone aggregator.

arxiv:2605.12575 v1 · 2026-05-12 · eess.IV · cs.AI · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{HB4I3UALQBOZ3ZS7IIR3XBQZNP}

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

Across three WSI benchmarks and seven MIL backbones, FOCI reveals that compact rationales are selection-headroom dependent: transformer and multi-branch attention aggregators can admit compact rationales, near-minimal attention-pooling baselines enter a selection-saturation regime, and hard-selection backbones can conflict with an external readout. For TransMIL, relative to its documented CLS-proxy ranking, FOCI reduces the Minimum Sufficient K (MSK) tile count by 32-56% across benchmarks, while ACMIL+FOCI attains the highest mean SHI (+0.465).

C2weakest assumption

That the sufficiency and exclusion objectives used to train FOCI produce tile subsets that are genuinely model-sufficient and free of readout-induced artifacts, and that the Sequential Reveal Protocol accurately isolates selection headroom without confounding effects from the specific keep/drop training procedure.

C3one line summary

FOCI adds a post-hoc readout to frozen WSI-MIL models to find compact output-consistent tile subsets and measures selection headroom with SHI, showing transformer-based models allow smaller rationales than attention-pooling baselines.

References

41 extracted · 41 resolved · 0 Pith anchors

[1] Hanna, Luke Geneslaw, Allen Miraflor, Vitor Werneck Krauss Silva, Klaus J 2019

[2] Attention-based deep multiple instance learning 2018

[3] Data-efficient and weakly supervised computational pathology on whole-slide images.Nature biomedical engineering, 5(6):555–570 2021

[4] Towards a general-purpose foundation model for computational pathology.Nature medicine, 30(3):850–862 2024

[5] Deep learning for whole slide image analysis: an overview.Frontiers in medicine, 6:264, 2019 2019

Receipt and verification

First computed	2026-05-18T03:10:01.648828Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

38788dd00b805d9de65f4223bb86196be2dd3c452bdb550061b9411405d22132

Aliases

arxiv: 2605.12575 · arxiv_version: 2605.12575v1 · doi: 10.48550/arxiv.2605.12575 · pith_short_12: HB4I3UALQBOZ · pith_short_16: HB4I3UALQBOZ3ZS7 · pith_short_8: HB4I3UAL

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/HB4I3UALQBOZ3ZS7IIR3XBQZNP \
  | 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: 38788dd00b805d9de65f4223bb86196be2dd3c452bdb550061b9411405d22132

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0b9a6b2ddb14a5553b9f297063d56b467b5afa596ab3f582a4f4dba2f0101d7b",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.IV",
    "submitted_at": "2026-05-12T12:15:41Z",
    "title_canon_sha256": "4bebf2b53ff5d0b3b0a0a21b74c1bae8ab81291330f12c75ddaa146124f373b4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12575",
    "kind": "arxiv",
    "version": 1
  }
}