pith:R4XXJIEG
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Rank-Surprisal Ratio identifies reasoning trajectories that best improve student model performance
arxiv:2601.14249 v5 · 2026-01-20 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{R4XXJIEGPTYVIT32QY6VPKRYLS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Across five student models and reasoning trajectories from 11 diverse teachers, RSR strongly correlates with post-training reasoning performance (average Spearman 0.86), consistently outperforming existing metrics.
That the balance of low absolute probability and high relative rank under the student model genuinely indicates informativeness rather than an artifact of the tested models, tasks, or trajectory generation methods, and that this correlation will generalize beyond the five students and eleven teachers examined.
Rank-Surprisal Ratio (RSR) correlates strongly (average Spearman 0.86) with post-distillation reasoning gains across five student models and trajectories from eleven teachers, outperforming existing selection metrics.
Receipt and verification
| First computed | 2026-05-26T02:04:03.266205Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
8f2f74a0867cf1544f7a863d57aa385c93404a161d9db04452c1e317dd1afcea
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/R4XXJIEGPTYVIT32QY6VPKRYLS \
| 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: 8f2f74a0867cf1544f7a863d57aa385c93404a161d9db04452c1e317dd1afcea
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "8908ccfe791646148cc75285abf1995b752c95d5f7e41352ab6c0dd37f76b4a3",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-01-20T18:58:10Z",
"title_canon_sha256": "b2637a3595c01475d3b4d5444fa2709ba1fd3a4e9e743a9a7a1e2f24391efed0"
},
"schema_version": "1.0",
"source": {
"id": "2601.14249",
"kind": "arxiv",
"version": 5
}
}