Pith Number

pith:NHNDZ7GO

pith:2026:NHNDZ7GOL6G5MP3M7VRLDM6DTY

not attested not anchored not stored refs resolved

Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints

Shweta Mishra

A size-based filter using only file metadata cuts tokens in LLM repository contexts by 80 to 89 percent and raises task accuracy from 25 to 72 percent.

arxiv:2605.14362 v1 · 2026-05-14 · cs.SE · 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{NHNDZ7GOL6G5MP3M7VRLDM6DTY}

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

Across 10 real open-source repositories (22,046 files, 5 languages), the proposed SizeFilter at θ=1 MB achieves 79.6% (±13.2%) mean token reduction at 0.30 ms overhead; the HybridFilter achieves 89.3% (±9.0%) the lowest variance of any filter evaluated. A limited-scope evaluation (18 tasks, CodeLlama-7B-Instruct) yields 72% file-level accuracy under filtering versus 25% at baseline; hallucination frequency declines from 61% to 17%.

C2weakest assumption

That file size (or a quick token-density estimate) is a reliable proxy for task relevance and that discarding large files will not remove critical code needed for the downstream LLM task.

C3one line summary

A pre-execution size filter cuts repository tokens by 80-89% at sub-millisecond cost and raises file-level accuracy from 25% to 72% in a small CodeLlama evaluation.

References

24 extracted · 24 resolved · 4 Pith anchors

[1] Retrieval-Augmented Generation for Knowledge- Intensive NLP Tasks, 2020

[2] Language Models are Few-Shot Learners, 1901

[3] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374

[4] The Tail at Scale, 2013

[5] LLMLingua: Compressing Prompts for Accelerated Inference, 2023

Receipt and verification

First computed	2026-05-17T23:39:07.938136Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

69da3cfcce5f8dd63f6cfd62b1b3c39e2207c6e4553eff25b14fdaa3276c66b2

Aliases

arxiv: 2605.14362 · arxiv_version: 2605.14362v1 · doi: 10.48550/arxiv.2605.14362 · pith_short_12: NHNDZ7GOL6G5 · pith_short_16: NHNDZ7GOL6G5MP3M · pith_short_8: NHNDZ7GO

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/NHNDZ7GOL6G5MP3M7VRLDM6DTY \
  | 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: 69da3cfcce5f8dd63f6cfd62b1b3c39e2207c6e4553eff25b14fdaa3276c66b2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "96fafebce4393315df46d1861b122fd5f1406251292483c0d26f22d481d9709a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-14T04:37:39Z",
    "title_canon_sha256": "afe0ba635aaf9c64fa12842b8e4eaea32cdce8e44dcc83c732a2b8421ad5767e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14362",
    "kind": "arxiv",
    "version": 1
  }
}