Pith Number

pith:YV5QITBX

pith:2026:YV5QITBXBG55UA6OWTKU5HEN62

not attested not anchored not stored refs resolved

An Agentic LLM-Based Framework for Population-Scale Mental Health Screening

Donald Cowan, Giuliano Lorenzoni, Paulo Alencar

An agentic LLM framework builds stable pipelines for population-scale mental health screening by locking validated stages after proxy evaluation.

arxiv:2605.13046 v1 · 2026-05-13 · 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{YV5QITBXBG55UA6OWTKU5HEN62}

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

The proposed framework evolves from feature-level exploration, through proxy-based tuning and freeze/rollback mechanisms, to full orchestration by an Orchestrator Agent that coordinates preprocessing, retrieval, selection, diversity, threshold optimization, and decoding. A proof-of-concept in transcript-based depression detection demonstrates that the framework converges to stable configurations, such as cosine similarity, dynamic Top-k, and threshold 0.75, while controlling evaluation costs and avoiding regressions.

C2weakest assumption

That proxy-guided evaluation metrics reliably predict actual clinical performance and that locking validated stages will prevent regressions without blocking necessary future adaptations to new patient data or clinical contexts.

C3one line summary

An agentic framework orchestrates LLM agents for transcript-based depression detection and converges on stable configurations including cosine similarity, dynamic Top-k, and a 0.75 threshold.

References

31 extracted · 31 resolved · 0 Pith anchors

[1] A survey on RAG meeting LLMs: Towards retrieval-augmented large language models, 2024

[2] A survey on RAG with LLMs, 2024

[3] Efficiency- driven custom chatbot development: Unleashing LangChain, RAG, and performance-optimized LLM fusion, 2024

[4] Dynamic configuration for distributed sys- tems, 1985

[5] Dynamic configuration of resource-aware services, 2004

Receipt and verification

First computed	2026-05-18T03:08:59.414332Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c57b044c3709bbda03ceb4d54e9c8df6bed0f4cf176114cb7a535405c5ce60f5

Aliases

arxiv: 2605.13046 · arxiv_version: 2605.13046v1 · doi: 10.48550/arxiv.2605.13046 · pith_short_12: YV5QITBXBG55 · pith_short_16: YV5QITBXBG55UA6O · pith_short_8: YV5QITBX

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/YV5QITBXBG55UA6OWTKU5HEN62 \
  | 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: c57b044c3709bbda03ceb4d54e9c8df6bed0f4cf176114cb7a535405c5ce60f5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c0215198f194539c4938bd55156d2b40aa840f9abd6d1a31fdfbb4d8e5cfa30c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T06:08:43Z",
    "title_canon_sha256": "078d3840b323f6ad6c4d2587c621ad5794ec02972710409dfd7dbf8816042444"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13046",
    "kind": "arxiv",
    "version": 1
  }
}