Pith Number

pith:7GCNP5QP

pith:2026:7GCNP5QP72FF3U54YXHRRZORJ7

not attested not anchored not stored refs resolved

interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification

Amit Sharma, Ashmit Khandelwal, Maitreyi Swaroop, Nagarajan Natarajan, Prateek Chanda, Subbarao Kambhampati, Vijval Ekbote, Vineeth N. Balasubramanian, Vishak K Bhat

Interwhen monitors reasoning traces in real time and steers models by verifying intermediate states against synthesized policy rules.

arxiv:2602.11202 v3 · 2026-02-05 · cs.LO · 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{7GCNP5QP72FF3U54YXHRRZORJ7}

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

On reasoning benchmarks where policies encode mathematical or logical constraints, interwhen achieves near-perfect accuracy for reasoning models using a fraction of the tokens of baselines. On agentic benchmarks with policy-based verifier generation, it enables improvements in task quality for SLMs without any finetuning, e.g., task completion rate of Qwen3-30B jumps from 32% to 87% on the telecom domain in tau2-bench.

C2weakest assumption

That the monitoring system can reliably poll and fork inference to recover accurate intermediate states from any reasoning trace, and that automatic synthesis from natural-language policies produces verifiers that are both correct and sufficiently complete to catch relevant violations.

C3one line summary

interwhen is a single-trajectory test-time verification system that polls reasoning traces, forks inference for intermediate states, synthesizes verifiers from policies including in Lean and z3, and steers models to near-perfect accuracy and higher task completion on benchmarks.

References

25 extracted · 25 resolved · 0 Pith anchors

[1] Early stopping chain-of-thoughts in large language models.ArXiv, abs/2509.14004 2025

[2] - A set of features (e.g., color, name, pet, book genre)

[6] Use any feedback to guide your reasoning until a complete solution is reached

[7] Do not stop responding until you’ve assigned each and every variable. # Final Answer Reporting Format ‘‘‘json { "House 1": { "feature1": "value1", "feature2": "value2", ... }, "House 2": { "feature1":

[8] - A set of features (e.g., color, name, pet, book genre)

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:45:05.313031Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f984d7f60ffe8a5dd3bcc5cf18e5d14ff0433282228ef2e479f7d5b5314e194e

Aliases

arxiv: 2602.11202 · arxiv_version: 2602.11202v3 · doi: 10.48550/arxiv.2602.11202 · pith_short_12: 7GCNP5QP72FF · pith_short_16: 7GCNP5QP72FF3U54 · pith_short_8: 7GCNP5QP

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/7GCNP5QP72FF3U54YXHRRZORJ7 \
  | 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: f984d7f60ffe8a5dd3bcc5cf18e5d14ff0433282228ef2e479f7d5b5314e194e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9076f40e44ed1a7dcce7ae6da57701989e6497de5d209beca364a609cc3e529b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LO",
    "submitted_at": "2026-02-05T08:35:01Z",
    "title_canon_sha256": "75016f1e0a7d0c1baf16a53aac6d508421057089eae60d44d8b5c67c7dd4701e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.11202",
    "kind": "arxiv",
    "version": 3
  }
}