Pith Number

pith:FESXYA4Q

pith:2026:FESXYA4QM6IE3GOFDREMGRAOER

not attested not anchored not stored refs resolved

Teaching and Learning under Deductive Errors

Brigt H{\aa}vardstun, Jan Arne Telle, Jose Hernandez-Orallo

Teachers can find small example sets that still guide learners making deductive errors to approximately correct hypotheses with high probability.

arxiv:2605.13384 v1 · 2026-05-13 · 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{FESXYA4QM6IE3GOFDREMGRAOER}

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

For some estimated error level, the teacher must find a PAC teaching set that with high probability will lead the learner to guess a hypothesis that is approximately correct.

C2weakest assumption

That the learner's deductive error rate can be estimated in advance and remains consistent enough for the PAC guarantee to apply across different hypotheses.

C3one line summary

Extends PAC machine teaching to handle deductive errors by requiring teachers to select sets that lead to approximately correct hypotheses with high probability despite learner mistakes, with complexity results and LLM experiments.

References

300 extracted · 300 resolved · 8 Pith anchors

[1] Machine Learning , volume= 2026

[2] Probably approximately correct: nature's algorithms for learning and prospering in a complex world , author=. 2013 , publisher= 2013

[3] International Workshop on Parameterized and Exact Computation , pages= 2009

[4] On Problems as Hard as 2016 · doi:10.1145/2925416

[5] Journal of Machine Learning Research , volume =

Receipt and verification

First computed	2026-05-18T02:44:47.803790Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

29257c039067904d99c51c48c3440e245fd393df9d3dfec535681b71058018ae

Aliases

arxiv: 2605.13384 · arxiv_version: 2605.13384v1 · doi: 10.48550/arxiv.2605.13384 · pith_short_12: FESXYA4QM6IE · pith_short_16: FESXYA4QM6IE3GOF · pith_short_8: FESXYA4Q

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/FESXYA4QM6IE3GOFDREMGRAOER \
  | 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: 29257c039067904d99c51c48c3440e245fd393df9d3dfec535681b71058018ae

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b1f6db7ff2c71291579c899958fb36facb6480efcd3f2057251b114e082b67da",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:43:01Z",
    "title_canon_sha256": "234adc6af69cb2d9ad0d5ba7fb2ad3b43b35dd382eb005fb02bfc80511188651"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13384",
    "kind": "arxiv",
    "version": 1
  }
}