Pith Number

pith:BCH2K7KM

pith:2026:BCH2K7KMHJNAOIWTD6CUQX3XDC

not attested not anchored not stored refs resolved

Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning

Danyang Liu, Kan Li

A length-regularized self-distillation method lets student rerankers match teacher effectiveness while cutting reasoning tokens by 34-37%.

arxiv:2605.14450 v1 · 2026-05-14 · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BCH2K7KMHJNAOIWTD6CUQX3XDC}

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 on TREC Deep Learning and NeuCLIR benchmarks demonstrate that our method maintains the teacher's effectiveness while reducing inference token consumption by 34%-37% across different retrieval settings.

C2weakest assumption

The Pareto-inspired filter reliably selects reasoning traces that preserve ranking quality when transferred to the student model; this transfer is assumed to work without additional validation on held-out data or different model scales.

C3one line summary

Length-regularized self-distillation trains rerankers to use concise reasoning traces that match teacher performance at 34-37 percent lower token cost.

References

2 extracted · 2 resolved · 0 Pith anchors

[1] R. Nogueira and K. Cho, ‘Passage Re-ranking with BERT’, ArXiv Prepr. ArXiv190104085, 2019. [19] S. Hongjin et al., ‘BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval’, in 2019

[2] Chen et al., ‘TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy’, ArXiv Prepr 2024

Receipt and verification

First computed	2026-05-17T23:39:06.903989Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

088fa57d4c3a5a0722d31f85485f77188f737d506d91a1d299441eef348bade5

Aliases

arxiv: 2605.14450 · arxiv_version: 2605.14450v1 · doi: 10.48550/arxiv.2605.14450 · pith_short_12: BCH2K7KMHJNA · pith_short_16: BCH2K7KMHJNAOIWT · pith_short_8: BCH2K7KM

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/BCH2K7KMHJNAOIWTD6CUQX3XDC \
  | 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: 088fa57d4c3a5a0722d31f85485f77188f737d506d91a1d299441eef348bade5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3afc3a2b06b55bde658dbbb1ad674fb8dab59005cf3fb93b0bc4e3012a779675",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-14T06:44:44Z",
    "title_canon_sha256": "b53e38cb866b72e67cfe38c48de8f5ef5a38a1dcca3eb48ef192e272bca964cc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14450",
    "kind": "arxiv",
    "version": 1
  }
}