Pith Number

pith:D3AOF3LZ

pith:2026:D3AOF3LZKO63M3F7IX37ZMXWBS

not attested not anchored not stored refs resolved

Learning to Persuade a Biased Receiver

Milind Tambe, Sadie Zhao, Yiling Chen, Yuqi Pan

A sender can learn a receiver's fixed bias in belief updating through safe exploration while achieving O(log log T) regret against a full-information oracle.

arxiv:2605.15331 v1 · 2026-05-14 · cs.GT

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{D3AOF3LZKO63M3F7IX37ZMXWBS}

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 general finite state and action spaces and arbitrary bounded utilities, the safe exploration algorithm achieves O(log log T) regret relative to a full-information oracle that knows the receiver's biased updating rule, with a matching Omega(log log T) lower bound.

C2weakest assumption

The receiver's bias parameter is fixed across all rounds and the only uncertainty is this single scalar; the model assumes the sender can perfectly observe the realized action after each signal but receives no other feedback.

C3one line summary

A safe exploration algorithm learns an unknown receiver bias parameter in repeated information design and achieves O(log log T) regret with a matching lower bound.

References

47 extracted · 47 resolved · 1 Pith anchors

[1] Robert J Aumann, Michael Maschler, and Richard E Stearns.Repeated games with incomplete information. MIT press, 1995 1995

[2] Over-and underreaction to information: Belief updating with cognitive constraints 2025

[3] Markov persuasion processes: Learning to persuade from scratch.arXiv preprint arXiv:2402.03077, 2024 2024

[4] A meta-analysis of the weight of advice in decision-making.Current Psychology, 42(28): 24516–24541, 2023 2023

[5] The base-rate fallacy in probability judgments.Acta Psychologica, 44(3): 211–233, 1980 1980

Receipt and verification

First computed	2026-05-20T00:00:52.977414Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1ec0e2ed7953bdb66cbf45f7fcb2f60ca0ab0975dc4541f6da8a7a23dbc6d5a1

Aliases

arxiv: 2605.15331 · arxiv_version: 2605.15331v1 · doi: 10.48550/arxiv.2605.15331 · pith_short_12: D3AOF3LZKO63 · pith_short_16: D3AOF3LZKO63M3F7 · pith_short_8: D3AOF3LZ

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/D3AOF3LZKO63M3F7IX37ZMXWBS \
  | 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: 1ec0e2ed7953bdb66cbf45f7fcb2f60ca0ab0975dc4541f6da8a7a23dbc6d5a1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7552019ea7011ef26f2b303835fbceae25b9a711598e73713188054f8d9e6359",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.GT",
    "submitted_at": "2026-05-14T18:54:38Z",
    "title_canon_sha256": "12dfb11bd00188d03c973079b15126d34e3db6db0726ec8e04db99f0a9cf5429"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15331",
    "kind": "arxiv",
    "version": 1
  }
}