pith. sign in
Pith Number

pith:EYDHFGU7

pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB
not attested not anchored not stored refs pending

Aligning Deep Implicit Preferences by Learning to Reason Defensively

Peiming Li, Shiyu Li, Xi Chen, Yang Tang, Zhiyuan Hu

CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.

arxiv:2510.11194 v3 · 2025-10-13 · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{EYDHFGU7MCNEAPBZ7OSMLKHOWB}

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

Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.

C2weakest assumption

The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation.

C3one line summary

CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.

Receipt and verification
First computed 2026-06-04T01:08:33.599423Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de

Aliases

arxiv: 2510.11194 · arxiv_version: 2510.11194v3 · doi: 10.48550/arxiv.2510.11194 · pith_short_12: EYDHFGU7MCNE · pith_short_16: EYDHFGU7MCNEAPBZ · pith_short_8: EYDHFGU7
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB \
  | 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: 2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-10-13T09:26:47Z",
    "title_canon_sha256": "42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.11194",
    "kind": "arxiv",
    "version": 3
  }
}