Pith Number

pith:6BYZOIHV

pith:2026:6BYZOIHVWZLLXCVRAGWGAOFA7F

not attested not anchored not stored refs pending

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data

Eslam Abdelaleem, Ilya Nemenman, K. Michael Martini, Paarth Gulati

DySIB recovers the two-dimensional phase space of a pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.

arxiv:2604.24662 v2 · 2026-04-27 · physics.data-an · cs.AI · cs.IT · math.IT

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6BYZOIHVWZLLXCVRAGWGAOFA7F}

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 method, with hyperparameters of the learning architecture set self-consistently by the data, recovers a two-dimensional representation that matches the dimensionality, topology, and geometry of the pendulum phase space, with the learned coordinates aligning smoothly with the canonical angle and angular velocity.

C2weakest assumption

That maximizing predictive mutual information between past and future observation windows in latent space is sufficient to recover the true underlying dynamical state variables without additional supervision or reconstruction.

C3one line summary

DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.

Cited by

1 paper in Pith

Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning

Receipt and verification

First computed	2026-06-11T01:10:36.689383Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f0719720f5b656bb8ab101ac6038a0f9497ee77ea491cec14660b427c3de7ca6

Aliases

arxiv: 2604.24662 · arxiv_version: 2604.24662v2 · doi: 10.48550/arxiv.2604.24662 · pith_short_12: 6BYZOIHVWZLL · pith_short_16: 6BYZOIHVWZLLXCVR · pith_short_8: 6BYZOIHV

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/6BYZOIHVWZLLXCVRAGWGAOFA7F \
  | 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: f0719720f5b656bb8ab101ac6038a0f9497ee77ea491cec14660b427c3de7ca6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8383d205a8deddba83bdb939606d16a6d4deff35d3165643c8340052c8f2213d",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.IT",
      "math.IT"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "physics.data-an",
    "submitted_at": "2026-04-27T16:24:45Z",
    "title_canon_sha256": "8e83c44754c65cf3e1edfeec4779d7c919f1d685b9eee7f61522ce51b637311f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.24662",
    "kind": "arxiv",
    "version": 2
  }
}