Pith Number

pith:UPB5KTAE

pith:2026:UPB5KTAER4VCIYWRAQ3O2GBPVN

not attested not anchored not stored refs resolved

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning

Ana S. Carreon-Rascon, Feiyang Cai, Feng Luo, Huayu Li, Jingjing Wang, Wenhui Zhu, Xiwen Chen, Xuanzhao Dong, ZhengXiao He

LaMR decomposes code relevance into separate semantic and dependency models to prune agent context without losing performance.

arxiv:2605.15315 v1 · 2026-05-14 · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UPB5KTAER4VCIYWRAQ3O2GBPVN}

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

LaMR wins 12 of 16 head-to-head multi-turn comparisons, saves up to 31% more tokens on multi-turn agent tasks, and improves Exact Match by up to +3.5 on single-turn tasks while frequently matching or outperforming unpruned full-context baselines.

C2weakest assumption

That labels derived via AST-based program analysis can reliably supervise the two separate rubrics and denoise the original binary teacher labels without introducing systematic biases or missing key relevance patterns.

C3one line summary

LaMR decomposes code context pruning into two rubrics using dedicated CRFs, a mixture-of-experts gate, and AST-derived labels to filter noise and often match or beat full-context baselines on coding benchmarks.

References

37 extracted · 37 resolved · 6 Pith anchors

[1] SWE-agent: Agent-computer interfaces enable automated soft- ware engineering 2024

[2] Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H 2024

[3] Agentless: Demystifying LLM-based Software Engineering Agents 2024

[4] Swe-pruner: Self-adaptive context pruning for coding agents, 2026 2026

[5] Lost in the Middle: How Language Models Use Long Contexts 2023 · arXiv:2307.03172

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:52.292856Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a3c3d54c048f2a2462d10436ed182fab5d0ba1860084bf571833cf1504279fb4

Aliases

arxiv: 2605.15315 · arxiv_version: 2605.15315v1 · doi: 10.48550/arxiv.2605.15315 · pith_short_12: UPB5KTAER4VC · pith_short_16: UPB5KTAER4VCIYWR · pith_short_8: UPB5KTAE

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/UPB5KTAER4VCIYWRAQ3O2GBPVN \
  | 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: a3c3d54c048f2a2462d10436ed182fab5d0ba1860084bf571833cf1504279fb4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a2b2a224be799d2bce02a990856247766c134d23d041406a3e05abd7def736bf",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T18:30:10Z",
    "title_canon_sha256": "dc1cd9acdd686b8d6baf0493ac9b4e3410154f5cdcb68409f3a2a67753ed7832"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15315",
    "kind": "arxiv",
    "version": 1
  }
}