Pith Number

pith:MXQTO4WX

pith:2025:MXQTO4WXWZ5WU5MTATLMBHZZYD

not attested not anchored not stored refs pending

Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors

Michael Witbrock, Qiming Bao, Xiaoxuan Fu

A four-stage training pipeline makes LLMs check rules for contradictions before reasoning, fixing their tendency to follow inconsistent premises.

arxiv:2512.06393 v7 · 2025-12-06 · cs.AI · cs.CL · cs.LG · cs.LO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MXQTO4WXWZ5WU5MTATLMBHZZYD}

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

The pipeline saturates all four primary stress tests for both 1.5B and 8B backbones. We further validate a Phase 2 extension that replaces the propositional oracle with a Lean 4 kernel, attaining 99.0% kernel agreement on the 105 classically-derivable (T) questions within a stratified 187-question Lean-translated sample (overall 71.7% across both polarities).

C2weakest assumption

That the four stress tests capture the relevant forms of logical inconsistency that arise in real-world LLM use, and that the symbolic forward-chaining engine (or Lean kernel) supplies rewards that do not embed their own unexamined biases or coverage gaps into the learned policy.

C3one line summary

Conflict-Aware Fusion mitigates Logic Inertia in LLMs through a four-stage pipeline of SFT, DPO, logical invariance regularization, and reinforcement learning from a symbolic oracle, saturating four stress tests on rule contradictions.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-26T01:03:19.406900Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

65e13772d7b67b6a759304d6c09f39c0e1459711a404ca9300d750fdfcea6856

Aliases

arxiv: 2512.06393 · arxiv_version: 2512.06393v7 · doi: 10.48550/arxiv.2512.06393 · pith_short_12: MXQTO4WXWZ5W · pith_short_16: MXQTO4WXWZ5WU5MT · pith_short_8: MXQTO4WX

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/MXQTO4WXWZ5WU5MTATLMBHZZYD \
  | 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: 65e13772d7b67b6a759304d6c09f39c0e1459711a404ca9300d750fdfcea6856

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "10e7d04bf3e837bbb599f565529c91c66acdd6a96e9a88ef4d9d3ec71cea9221",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG",
      "cs.LO"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-12-06T10:49:50Z",
    "title_canon_sha256": "174223e13832395cc26d800e70f119f22c2332f40073368839b4628477570eff"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.06393",
    "kind": "arxiv",
    "version": 7
  }
}