Pith Number

pith:EEWA4TLP

pith:2026:EEWA4TLPS6LSPCF7U2XFHKMMRM

not attested not anchored not stored refs resolved

Ergodic Imitation for Adaptive Exploration around Demonstrations

Cem Bilaloglu, Sylvain Calinon, Yiming Li, Ziyi Xu

Robots adapt imitation by building target distributions from demonstration geometry to generate trajectories that balance tracking and exploration.

arxiv:2605.13996 v1 · 2026-05-13 · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EEWA4TLPS6LSPCF7U2XFHKMMRM}

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

we propose an adaptive ergodic imitation approach that constructs a target distribution from the geometry of the retrieved demonstrations and uses it to generate trajectories that adaptively interpolate between tracking and exploration. Our method extends ergodic control beyond its traditional role in area-coverage and search by incorporating demonstrations into a retrieval-based receding-horizon framework for adaptive imitation.

C2weakest assumption

That a target distribution constructed from the geometry of retrieved demonstrations can be used within ergodic control to produce trajectories that effectively adaptively interpolate between tracking and exploration while remaining grounded in the demonstrations.

C3one line summary

An adaptive ergodic imitation method constructs a target distribution from demonstration geometry to generate trajectories that interpolate between tracking and exploration in imitation learning.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] S., Sartoretti, G., and Schwager, M 2025

[2] Y . Li, N. Darwiche, A. Razmjoo, S. Liu, Y . Du, A. Ijspeert, and S. Calinon, “Geometry-aware policy imitation,” inProc. Intl Conf. on Learning Representations (ICLR), 2026 2026

[3] Ccdp: Composition of conditional diffusion policies with guided sampling, 2025

[4] Sime: Enhanc- ing policy self-improvement with modal-level exploration, 2025

[5] Spectral Multiscale Coverage: A uniform coverage algorithm for mobile sensor networks, 2009

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.199344Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

212c0e4d6f97972788bfa6ae53a98c8b0f49fa2580f2d09ec09df49b0698662f

Aliases

arxiv: 2605.13996 · arxiv_version: 2605.13996v1 · doi: 10.48550/arxiv.2605.13996 · pith_short_12: EEWA4TLPS6LS · pith_short_16: EEWA4TLPS6LSPCF7 · pith_short_8: EEWA4TLP

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/EEWA4TLPS6LSPCF7U2XFHKMMRM \
  | 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: 212c0e4d6f97972788bfa6ae53a98c8b0f49fa2580f2d09ec09df49b0698662f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "418e3e8526675639054e97c6c8188b3389c5596d484a7add49bceb8d06260eb5",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T18:06:46Z",
    "title_canon_sha256": "98525d724c106eb02f2d6eb6dfbf1e767e6893485d3eed899499c1aa26ce48b8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13996",
    "kind": "arxiv",
    "version": 1
  }
}