Pith Number

pith:5AVENWBW

pith:2025:5AVENWBWJLVIO7D3FG4E7TLYE2

not attested not anchored not stored refs pending

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

George Karypis, Huzefa Rangwala, Mingyi Hong, Rasool Fakoor, Siliang Zeng, Yao Liu

arxiv:2503.13538 v1 · 2025-03-15 · 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{5AVENWBWJLVIO7D3FG4E7TLYE2}

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.

Cited by

1 paper in Pith

rePIRL: Learn PRM with Inverse RL for LLM Reasoning

Receipt and verification

First computed	2026-07-05T10:33:12.334427Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e82a46d8364aea877c7b29b84fcd78269f8dc10845fc72c7ca40cb691429eafa

Aliases

arxiv: 2503.13538 · arxiv_version: 2503.13538v1 · doi: 10.48550/arxiv.2503.13538 · pith_short_12: 5AVENWBWJLVI · pith_short_16: 5AVENWBWJLVIO7D3 · pith_short_8: 5AVENWBW

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/5AVENWBWJLVIO7D3FG4E7TLYE2 \
  | 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: e82a46d8364aea877c7b29b84fcd78269f8dc10845fc72c7ca40cb691429eafa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ded4a35c4e72373f69c5746c3446f19866d664c06d8c08f485005753545fb995",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-03-15T20:53:46Z",
    "title_canon_sha256": "6e81d88aebd138c2bc16a0612cd1f2d497fdd9dca322a77e05cedbe11dac0331"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.13538",
    "kind": "arxiv",
    "version": 1
  }
}