Pith. sign in
Pith Number

pith:NJBT33RY

pith:2026:NJBT33RYEYDFFIOH2GAHGKD4Y2
not attested not anchored not stored refs pending

Prosocial Persuasion at Scale? Large Language Models Outperform Humans in Donation Appeals Across Levels of Personalization

Bennett Kleinberg, John Caffier, Olga Stavrova

LLM-generated donation appeals produced more donations, higher engagement, and stronger persuasiveness ratings than human-written ones in two experiments.

arxiv:2604.03202 v2 · 2026-04-03 · cs.CY

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NJBT33RYEYDFFIOH2GAHGKD4Y2}

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

In both experiments, LLM-generated content yielded more donations, resulted in higher engagement, and was rated as more persuasive than human-authored content.

C2weakest assumption

That distributing a small bonus in an online experiment accurately measures real-world charitable donation behavior and that human and LLM content were produced under equivalent effort and quality constraints.

C3one line summary

LLM-generated donation appeals outperform human-written ones in driving donations, engagement, and perceived persuasiveness across generic, personalized, and falsely personalized conditions.

Receipt and verification
First computed 2026-07-21T01:20:47.303067Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

6a433dee38260652a1c7d18073287cc68a541937d95e094898471b5117bccd04

Aliases

arxiv: 2604.03202 · arxiv_version: 2604.03202v2 · doi: 10.48550/arxiv.2604.03202 · pith_short_12: NJBT33RYEYDF · pith_short_16: NJBT33RYEYDFFIOH · pith_short_8: NJBT33RY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NJBT33RYEYDFFIOH2GAHGKD4Y2 \
  | 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: 6a433dee38260652a1c7d18073287cc68a541937d95e094898471b5117bccd04
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "e2f3467c589572ab9c0e1da92264b85ce2a38876a0d8deffcd806e641870fdeb",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CY",
    "submitted_at": "2026-04-03T17:25:07Z",
    "title_canon_sha256": "09f7ff805259aa96a97f1f330ad611b8f01bffd1d9f48f80e9d2d434748a8d8c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.03202",
    "kind": "arxiv",
    "version": 2
  }
}