Pith Number

pith:7PFSY7BA

pith:2026:7PFSY7BACAQBGO2XYCEXPI5XBV

not attested not anchored not stored refs resolved

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited

Ashutosh Nayyar, Rahul Jain, Rishabh Agrawal

Reformulating BFM task inference as a minimax problem over dynamics perturbations yields robust policies from single-environment offline data alone.

arxiv:2605.17017 v1 · 2026-05-16 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7PFSY7BACAQBGO2XYCEXPI5XBV}

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

To the best of our knowledge, this is the first BFM-based framework that achieves robustness to dynamics shifts while relying solely on offline data from a single nominal environment.

C2weakest assumption

The minimax optimization over dynamics perturbations can be solved tractably from offline nominal data alone and produces policies that generalize to actual (not just modeled) dynamics shifts.

C3one line summary

Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.

References

68 extracted · 68 resolved · 6 Pith anchors

[1] GPT-4 Technical Report 2023 · arXiv:2303.08774

[2] Policy optimization for strictly batch imitation learning 2024

[3] Balance equation-based distributionally robust offline imitation learning.arXiv preprint arXiv:2511.07942, 2025 2025

[4] Markov balance satisfac- tion improves performance in strictly batch offline imitation learning 2025

[5] Conditional kernel imi- tation learning for continuous state environments 2025

Receipt and verification

First computed	2026-05-20T00:03:36.199052Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fbcb2c7c201020133b57c08977a3b70d7097c9773427b1da4bdbbe65063c4861

Aliases

arxiv: 2605.17017 · arxiv_version: 2605.17017v1 · doi: 10.48550/arxiv.2605.17017 · pith_short_12: 7PFSY7BACAQB · pith_short_16: 7PFSY7BACAQBGO2X · pith_short_8: 7PFSY7BA

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/7PFSY7BACAQBGO2XYCEXPI5XBV \
  | 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: fbcb2c7c201020133b57c08977a3b70d7097c9773427b1da4bdbbe65063c4861

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b34725124ea9eb3f03a4e0656afbb4469ad79ba6344c2cef591e9fcc1909e0c5",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T14:33:34Z",
    "title_canon_sha256": "51c09b3f440dc5b2f773b13f533f33af1896f6aa502fbce271410e6b3e50dcec"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17017",
    "kind": "arxiv",
    "version": 1
  }
}