Pith Number

pith:HMXUOUHU

pith:2026:HMXUOUHUPLWEP543W4VGTWY6OX

not attested not anchored not stored refs resolved

Differentiable Learning of Lifted Action Schemas for Classical Planning

Hector Geffner, Jakob Elias Gebler, Jonas Reiter

A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes.

arxiv:2605.13282 v1 · 2026-05-13 · cs.AI · 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{HMXUOUHUPLWEP543W4VGTWY6OX}

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

Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure.

C2weakest assumption

The assumption that states are fully observed as sets of atoms and that action arguments can be uniquely recovered from observed state changes without additional supervision or ambiguity.

C3one line summary

A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.

References

300 extracted · 300 resolved · 2 Pith anchors

[1] doi:10.1016/j.artint.2019.05.003 , langid = 2019 · doi:10.1016/j.artint.2019.05.003

[2] Asai, Masataro and Fukunaga, Alex , date =. Classical

[3] Michael , date = 2024 · doi:10.24963/kr.2024/76

[4] and Monet, Mikael and Pérez, Jorge and Reutter, Juan and Silva, Juan Pablo , date =

[5] Going Beyond Accuracy: Interpretability Metrics for CNN Representations of Physiological Signals , shorttitle = 2022 · doi:10.1109/icpr56361.2022.9956203

Receipt and verification

First computed	2026-05-18T02:44:49.186519Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8

Aliases

arxiv: 2605.13282 · arxiv_version: 2605.13282v1 · doi: 10.48550/arxiv.2605.13282 · pith_short_12: HMXUOUHUPLWE · pith_short_16: HMXUOUHUPLWEP543 · pith_short_8: HMXUOUHU

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/HMXUOUHUPLWEP543W4VGTWY6OX \
  | 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: 3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "67bee74cca35e230c624dc64a60ac3ecc01d7b2d81d14a9f828837beef478ebe",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T09:59:49Z",
    "title_canon_sha256": "5b4754684cfd0aa5dccfe9699372d0df6d6d27c9a246cd57e9c1b91fd3a8ddad"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13282",
    "kind": "arxiv",
    "version": 1
  }
}