Pith Number

pith:3V2FUOVG

pith:2022:3V2FUOVGLKAJUJ42Z5XLFPFSYU

not attested not anchored not stored refs pending

Models of human preference for learning reward functions

Alessandro Allievi, Peter Stone, Scott Niekum, Serena Booth, Stephane Hatgis-Kessell, W. Bradley Knox

arxiv:2206.02231 v3 · 2022-06-05 · cs.LG · cs.AI · cs.SY · eess.SY

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{3V2FUOVGLKAJUJ42Z5XLFPFSYU}

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

5 papers in Pith

From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation

Implicit Safety Alignment from Crowd Preferences

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

Mitigating Cognitive Bias in RLHF by Altering Rationality

Receipt and verification

First computed	2026-07-05T06:48:22.608965Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dd745a3aa65a809a279acf6eb2bcb2c52256d8db190c38cf1a1eb000c3dc4f8d

Aliases

arxiv: 2206.02231 · arxiv_version: 2206.02231v3 · doi: 10.48550/arxiv.2206.02231 · pith_short_12: 3V2FUOVGLKAJ · pith_short_16: 3V2FUOVGLKAJUJ42 · pith_short_8: 3V2FUOVG

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/3V2FUOVGLKAJUJ42Z5XLFPFSYU \
  | 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: dd745a3aa65a809a279acf6eb2bcb2c52256d8db190c38cf1a1eb000c3dc4f8d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fdb2a99e088a783203be25b87a1227d696195f30168f4dfcf3429c355272874b",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.SY",
      "eess.SY"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-06-05T17:58:02Z",
    "title_canon_sha256": "d82b36090e1b884c71f2701820d7024483dc079f2399abba4172f6175fa0021c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2206.02231",
    "kind": "arxiv",
    "version": 3
  }
}