Pith Number

pith:B7Y4EP6U

pith:2026:B7Y4EP6U5N6XG4KRKVBK24SI4Y

not attested not anchored not stored refs resolved

SADP: Subgoal-Aware Diffusion Policy for Explainable Robots Learned from Foundation Model Generated Demonstrations

Site Hu, Takato Horii

Conditioning diffusion policies on foundation-model-generated subgoals improves both task success and explainability for robot manipulation.

arxiv:2605.16871 v1 · 2026-05-16 · 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{B7Y4EP6U5N6XG4KRKVBK24SI4Y}

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

Experiments in RLBench simulations and real-world evaluations on a UR5e robot demonstrate that SADP achieves higher task success rates than strong task-conditioned diffusion baselines, while providing subgoal-level execution signals for monitoring progress and diagnosing failures.

C2weakest assumption

Foundation models can autonomously generate accurate, unbiased subgoal annotations from raw task demonstrations without introducing systematic errors that would degrade downstream policy learning or explainability.

C3one line summary

SADP trains diffusion policies on foundation-model-generated subgoal-annotated demonstrations and adds a completion predictor to give robots built-in, subgoal-level explainability alongside improved task performance.

References

40 extracted · 40 resolved · 2 Pith anchors

[1] Transparent, explainable, and accountable ai for robotics, 2017

[2] A review of robot learning for manipulation: Challenges, representations, and algorithms, 2021

[3] A survey of demonstration learning, 2024

[4] Hierarchical reinforce- ment learning: A survey and open research challenges, 2022

[5] Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction, 2024

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:03:27.458428Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0ff1c23fd4eb7d7371515542ad7248e63d8690dff728952bdc3415ac4d727019

Aliases

arxiv: 2605.16871 · arxiv_version: 2605.16871v1 · doi: 10.48550/arxiv.2605.16871 · pith_short_12: B7Y4EP6U5N6X · pith_short_16: B7Y4EP6U5N6XG4KR · pith_short_8: B7Y4EP6U

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/B7Y4EP6U5N6XG4KRKVBK24SI4Y \
  | 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: 0ff1c23fd4eb7d7371515542ad7248e63d8690dff728952bdc3415ac4d727019

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0ebcf7089c0ce3380b126e36805d9f5ecebbe9c98230d9234242f7f51b042317",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-16T08:18:47Z",
    "title_canon_sha256": "5508fc7b3e26bdf750d4adb20c32c37df7524bb7a8f5a8c567e712822b81f0ce"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16871",
    "kind": "arxiv",
    "version": 1
  }
}