Pith Number

pith:IIT7QJGP

pith:2026:IIT7QJGPKSXS76MOLSVRA2DQRB

not attested not anchored not stored refs pending

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

A. Ali Heydari, Ahmed A. Metwally, Alan Karthikesalingam, Annalisa Pawlosky, Chunjong Park, Cynthia Breazeal, Daniel McDuff, Dongjae Lee, Elahe Vedadi, Hae Won Park, Hamid Palangi, Hanseul Cho, Hong Yu, Hyeonhoon Lee, Hyewon Jeong, Ivor Rendulic, Juraj Gottweis, Kyungho Lim, Mark Malhotra, Maxwell A. Xu, Mingyu Lu, Nicolas Stroppa, Petar Sirkovic, Pushmeet Kohli, Salman Rahman, Samir Tulebaev, Samuel Schmidgall, Shwetak Patel, Theodora Pappa, Tim Althoff, Vivek Natarajan, Xin Liu, Xuhai Xu, Yubin Kim, Yuzhe Yang, Zhihan Zhang

A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts.

arxiv:2604.14615 v2 · 2026-04-16 · 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{IIT7QJGPKSXS76MOLSVRA2DQRB}

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 three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes... Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated ΔR² increases of 0.040 for depression and 0.021 for insulin resistance.

C2weakest assumption

The multi-agent AI system with adversarial validation and human oversight can generate and prioritize hypotheses that are both novel and clinically meaningful without introducing systematic bias or over-fitting to the specific datasets used.

C3one line summary

CoDaS, a multi-agent AI co-data-scientist, identifies 41 mental health and 25 metabolic digital biomarkers from 9,279 wearable observations, replicates some circadian features across cohorts, and yields modest predictive gains when added to demographic models.

Receipt and verification

First computed	2026-06-23T01:12:07.184388Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89

Aliases

arxiv: 2604.14615 · arxiv_version: 2604.14615v2 · doi: 10.48550/arxiv.2604.14615 · pith_short_12: IIT7QJGPKSXS · pith_short_16: IIT7QJGPKSXS76MO · pith_short_8: IIT7QJGP

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/IIT7QJGPKSXS76MOLSVRA2DQRB \
  | 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: 4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "780c99402f9ebad50dd0274b51f7241b4c4198f4b6e9943459db77b1ff90b7e6",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-16T04:47:55Z",
    "title_canon_sha256": "ccba6313644bedd099c3e6ffc030a5bb85fe6acaa41b9211c65d2c7663754ea3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.14615",
    "kind": "arxiv",
    "version": 2
  }
}