Pith Number

pith:ONX4DNPT

pith:2026:ONX4DNPTATBEI5SXLZ2KCDTT7Y

not attested not anchored not stored refs resolved

From Generalist to Specialist Representation

Fan Feng, Kevin Murphy, Kun Zhang, Shaoan Xie, Yujia Zheng, Yuke Li

Task structure and relevant latents are identifiable in nonparametric settings without supervision or constraints.

arxiv:2605.12733 v1 · 2026-05-12 · cs.LG · cs.AI · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ONX4DNPTATBEI5SXLZ2KCDTT7Y}

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

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

We first prove that the structure between time steps and tasks is identifiable in a fully unsupervised manner, even when sequences lack strict temporal dependence and may exhibit disconnections, and task assignments can follow arbitrarily complex and interleaving structures. We then prove that, within each time step, the task-relevant latent representation can be disentangled from the irrelevant part under a simple sparsity regularization, without any additional information or parametric constraints.

C2weakest assumption

The setting is completely nonparametric without relying on interventions, parametric forms, or structural constraints, and that a simple sparsity regularization is sufficient to disentangle task-relevant from irrelevant latents within each time step.

C3one line summary

Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.

References

16 extracted · 16 resolved · 2 Pith anchors

[1] Function classes for identifiable non- linear independent component analysis.arXiv preprint arXiv:2208.06406

[2] World Models · arXiv:1803.10122

[3] Jin, J. and Syrgkanis, V . Learning causal representations from general environments: Identifiability and intrinsic ambiguity.arXiv preprint arXiv:2311.12267,

[4] Condi- tional mutual information neural estimator 2020

[5] Nanda, N., Lee, A., and Wattenberg, M

Receipt and verification

First computed	2026-05-18T03:09:49.216720Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

736fc1b5f304c24476575e74a10e73fe2092659af4f351541292354c2ec04ad9

Aliases

arxiv: 2605.12733 · arxiv_version: 2605.12733v1 · doi: 10.48550/arxiv.2605.12733 · pith_short_12: ONX4DNPTATBE · pith_short_16: ONX4DNPTATBEI5SX · pith_short_8: ONX4DNPT

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/ONX4DNPTATBEI5SXLZ2KCDTT7Y \
  | 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: 736fc1b5f304c24476575e74a10e73fe2092659af4f351541292354c2ec04ad9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "95f9fd4c9324971c0f1d5dea220a72399ff42b26d09afb1d5e39934462ce9185",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T20:34:53Z",
    "title_canon_sha256": "db3632f546a5fe3ba79ec51bdce840dfc55303c299edf67c23bdc0674f34a7e6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12733",
    "kind": "arxiv",
    "version": 1
  }
}