Pith Number

pith:65LENYMP

pith:2026:65LENYMP5AEO5CT7VDCCD3AU2O

not attested not anchored not stored refs resolved

CSLibPremiseBench: Structure-Guided Premise Retrieval and Label Robustness for Lean 4 Computer-Science Theorems

Junye Ji

CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.

arxiv:2605.14549 v1 · 2026-05-14 · 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{65LENYMP5AEO5CT7VDCCD3AU2O}

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

CSG-Rerank gives a modest early-rank MRR gain over lexical BM25 under the strict policy, but does not reliably outperform BM25+symbol and does not improve Recall@10.

C2weakest assumption

The source-visible proxy labels from proof references accurately stand in for the premises that would actually be needed in a realistic proof-generation or proof-repair setting.

C3one line summary

CSLibPremiseBench shows that a structure-guided reranker provides only modest MRR gains over BM25 for premise retrieval in Lean 4 CS theorems and does not improve Recall@10.

References

16 extracted · 16 resolved · 0 Pith anchors

[1] Leanexplore: A search engine for lean 4 declarations, 2025 2025

[2] Ayers, Dragomir Radev, and Jeremy Avigad 2023

[3] Cslib: The lean computer science library, 2026 2026

[4] The lean 4 theorem prover and programming language, 2021 2021

[5] Computer science as infrastructure: the spine of the lean computer science library (cslib), 2026 2026

Receipt and verification

First computed	2026-05-17T23:39:05.729714Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd

Aliases

arxiv: 2605.14549 · arxiv_version: 2605.14549v1 · doi: 10.48550/arxiv.2605.14549 · pith_short_12: 65LENYMP5AEO · pith_short_16: 65LENYMP5AEO5CT7 · pith_short_8: 65LENYMP

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/65LENYMP5AEO5CT7VDCCD3AU2O \
  | 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: f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6545c839f80bc4e63467ee1a63f48c05a841200e2089c52f8d1a5cdd0c0def5a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LO",
    "submitted_at": "2026-05-14T08:28:57Z",
    "title_canon_sha256": "98424ed4b2b79f191374b94e616f2c70afaa5f93838f0ec7f6066ce090e18c3a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14549",
    "kind": "arxiv",
    "version": 1
  }
}