Pith Number

pith:LIBMPMSV

pith:2026:LIBMPMSVHWZ7S2JEAMK33JBK7W

not attested not anchored not stored refs resolved

Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space

Alon Bebchuk, Nir Shavit

Winning tickets correspond to precursor locations in feature space already near the final codes at initialization.

arxiv:2605.17704 v1 · 2026-05-18 · 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{LIBMPMSVHWZ7S2JEAMK33JBK7W}

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

winning tickets in weight space correspond to precursor locations in feature space that are already near, at initialization, to the final feature-channel codes. A winning ticket is thus a family of compatible code locations that jointly balance proximity to final codes with low inter-feature interference.

C2weakest assumption

The combinatorial, clause-structured toy setting admits an interpretable feature-space representation with well-defined combinatorial distances between features that capture the relevant dynamics of real neural networks under superposition.

C3one line summary

In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.

References

91 extracted · 91 resolved · 6 Pith anchors

[1] International Conference on Learning Representations , year=

[2] International Conference on Learning Representations , year=

[3] International Conference on Machine Learning , year=

[4] International Conference on Learning Representations , year=

[5] Advances in Neural Information Processing Systems , year=

Receipt and verification

First computed	2026-05-20T00:04:53.654081Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5a02c7b2553db3f969240315bda42afda356f1757290cf1ed95606f081b2849d

Aliases

arxiv: 2605.17704 · arxiv_version: 2605.17704v1 · doi: 10.48550/arxiv.2605.17704 · pith_short_12: LIBMPMSVHWZ7 · pith_short_16: LIBMPMSVHWZ7S2JE · pith_short_8: LIBMPMSV

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/LIBMPMSVHWZ7S2JEAMK33JBK7W \
  | 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: 5a02c7b2553db3f969240315bda42afda356f1757290cf1ed95606f081b2849d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2c7c7580093599767840203442bafa64edbea7e5b6d34a4aec80260d4624a973",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-18T00:00:53Z",
    "title_canon_sha256": "384a9d1492db2241b97e02283d40c69b245f325342cb96960b2289adac4318f4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17704",
    "kind": "arxiv",
    "version": 1
  }
}