Pith Number

pith:LN7L4IB5

pith:2026:LN7L4IB5ZV6LZKQIQG62G2YSDT

not attested not anchored not stored refs resolved

Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems

Arkady Gonoskov

Twincher learns bijective representations of outputs aligned with parameters to enable robust inversion of continuous systems under noise.

arxiv:2605.13470 v1 · 2026-05-13 · 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{LN7L4IB5ZV6LZKQIQG62G2YSDT}

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

Twincher enables robust and efficient iterative inverse inference by learning bijective representations of y that are aligned with p while remaining insensitive to perturbations in y caused by noise or model mismatch, exhibiting improved data efficiency and robustness compared to a baseline inverse-modeling approach.

C2weakest assumption

That stacks of structured diffeomorphic transformations combined with adversarial training will produce representations that remain bijectively aligned and perturbation-insensitive when applied to real-world continuous systems beyond the synthetic examples shown.

C3one line summary

Twincher learns bijective representations of observations aligned with continuous system parameters to enable robust iterative inversion, showing better data efficiency and noise tolerance than standard inverse modeling on synthetic systems.

References

51 extracted · 51 resolved · 0 Pith anchors

[1] Scaling laws for neural language models 2020

[2] Gradient-based learning applied to document recognition.Proc 1998

[3] Gomez, Lukasz Kaiser, and Illia Polosukhin 2017

[4] On the inductive bias of neural tangent kernels, 2019 2019

[5] Challenging common assumptions in the unsupervised learning of disentangled representations 2018

Receipt and verification

First computed	2026-05-18T02:44:41.553752Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48

Aliases

arxiv: 2605.13470 · arxiv_version: 2605.13470v1 · doi: 10.48550/arxiv.2605.13470 · pith_short_12: LN7L4IB5ZV6L · pith_short_16: LN7L4IB5ZV6LZKQI · pith_short_8: LN7L4IB5

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/LN7L4IB5ZV6LZKQIQG62G2YSDT \
  | 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: 5b7ebe203dcd7cbcaa0881bda36b121ce22d2d72d626255d7d177f885502bd48

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c70ea4baf94dba8269c1915a0e5e48e8f1a5652d59506b4e9a7859b62170d1e2",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T12:57:17Z",
    "title_canon_sha256": "646ff408ca698a7375cd8290c1bc287c1cbdc5728dd427d7a238b649fc0ed620"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13470",
    "kind": "arxiv",
    "version": 1
  }
}