data.sample.public.json

{
  "generatedAt": "2026-08-10T09:00:00",
  "papers": [
    {
      "id": "S001",
      "title": "A Fake Paper With No Stage Set Yet",
      "abstract": "An early-stage look at how community health workers describe unmet needs in their own words, and whether that language differs systematically from what standard intake forms capture.",
      "tags": [
        "health equity",
        "qualitative research",
        "community health"
      ],
      "skillsNeeded": [
        "interview skills",
        "writing"
      ],
      "stage": "Getting started",
      "openToNewMembers": true,
      "contact": {
        "name": "Test",
        "email": "test-owner-a@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S002",
      "title": "A Fake Paper That Is Mid-Draft",
      "abstract": "A machine learning approach to flagging which public health policy interventions are most likely to widen, rather than close, outcome gaps between neighborhoods — trained on a decade of city-level program data.",
      "tags": [
        "machine learning",
        "public health policy",
        "urban health"
      ],
      "skillsNeeded": [
        "Python",
        "policy analysis"
      ],
      "stage": "In progress (drafting)",
      "openToNewMembers": true,
      "contact": {
        "name": "Test",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S005",
      "title": "A Fake Paper Currently Out for Review",
      "abstract": "A biostatistics-heavy re-analysis of a published clinical trial's subgroup effects, testing whether the original result holds under a pre-registered alternative model.",
      "tags": [
        "clinical trials",
        "biostatistics"
      ],
      "skillsNeeded": [
        "R",
        "statistics"
      ],
      "stage": "Submitted, under review",
      "openToNewMembers": true,
      "contact": {
        "name": "Test",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S009",
      "title": "Mapping Algorithmic Bias in Emergency Triage Models",
      "abstract": "An audit of algorithmic bias in ML-based emergency-department triage scoring tools, focused on whether risk scores systematically under-triage patients from historically under-resourced neighborhoods.",
      "tags": [
        "machine learning",
        "algorithmic bias",
        "emergency medicine",
        "health equity"
      ],
      "skillsNeeded": [
        "Python",
        "fairness metrics"
      ],
      "stage": "In progress (drafting)",
      "openToNewMembers": true,
      "contact": {
        "name": "Priya",
        "email": "priya.raman@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S010",
      "title": "The Ethics of Consent in Passive Sensor Data Collection",
      "abstract": "Examining what 'informed consent' should mean when wearable and ambient sensors passively collect health-relevant data outside a clinical encounter, and drafting a practical consent framework labs can adopt.",
      "tags": [
        "research ethics",
        "data governance",
        "informed consent"
      ],
      "skillsNeeded": [
        "writing",
        "policy analysis"
      ],
      "stage": "Early stage / idea",
      "openToNewMembers": true,
      "contact": {
        "name": "Marcus",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S011",
      "title": "Federated Learning for Multi-Hospital Sepsis Prediction",
      "abstract": "A federated learning approach to sepsis onset prediction that trains across five hospital systems without centralizing patient data, addressing the generalizability failures that sank an earlier single-site model.",
      "tags": [
        "machine learning",
        "federated learning",
        "sepsis",
        "clinical data"
      ],
      "skillsNeeded": [
        "Python",
        "distributed systems"
      ],
      "stage": "Submitted, under review",
      "openToNewMembers": true,
      "contact": {
        "name": "Wei",
        "email": "wei.zhang@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S012",
      "title": "Should AI Clinicians Disclose Uncertainty? A Survey of Patient Preferences",
      "abstract": "A patient-preference survey testing whether people want AI clinical-decision-support tools to explicitly disclose their confidence level, and how disclosure changes trust and follow-through on recommendations.",
      "tags": [
        "healthcare AI",
        "patient preferences",
        "survey research"
      ],
      "skillsNeeded": [
        "survey design",
        "writing"
      ],
      "stage": "In progress (drafting)",
      "openToNewMembers": true,
      "contact": {
        "name": "Sofia",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S013",
      "title": "Cleaning Ten Years of Messy EHR Timestamps: A Reproducible Pipeline",
      "abstract": "A fully reproducible, open-source pipeline for reconciling inconsistent EHR timestamp formats across a decade of merged hospital systems, released alongside the accepted manuscript.",
      "tags": [
        "EHR data",
        "data engineering",
        "reproducibility"
      ],
      "skillsNeeded": [
        "Python",
        "SQL"
      ],
      "stage": "Submitted, under review",
      "openToNewMembers": true,
      "contact": {
        "name": "Priya",
        "email": "priya.raman@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S014",
      "title": "Public Health Policy Simulation for Pandemic Resource Allocation",
      "abstract": "An agent-based simulation comparing pandemic-era resource-allocation policies (bed triage, vaccine rollout order, supply-chain prioritization) across different equity-weighting schemes.",
      "tags": [
        "public health policy",
        "simulation",
        "resource allocation"
      ],
      "skillsNeeded": [
        "policy analysis",
        "R"
      ],
      "stage": "In progress (internal review)",
      "openToNewMembers": true,
      "contact": {
        "name": "Marcus",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S015",
      "title": "A Narrative Review of AI Hype Cycles in Medicine (1980-2026)",
      "abstract": "A historical narrative review tracing five decades of 'AI will transform medicine' predictions against what actually shipped, looking for a pattern in why certain claims recur every hype cycle.",
      "tags": [
        "writing",
        "history of science",
        "healthcare AI"
      ],
      "skillsNeeded": [
        "writing",
        "literature review"
      ],
      "stage": "In progress (drafting)",
      "openToNewMembers": true,
      "contact": {
        "name": "Sofia",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S017",
      "title": "Who Gets Left Out? Auditing Consent Forms for Health Literacy",
      "abstract": "An audit of hospital consent forms' reading-level and comprehensibility across a diverse literacy sample, finding that most forms require college-level reading fluency to understand basic risks.",
      "tags": [
        "health equity",
        "research ethics",
        "health literacy"
      ],
      "skillsNeeded": [
        "qualitative research",
        "writing"
      ],
      "stage": "Submitted, under review",
      "openToNewMembers": true,
      "contact": {
        "name": "Priya",
        "email": "priya.raman@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S019",
      "title": "Which Combination Therapies Actually Get Tried First? A Claims-Data Audit",
      "abstract": "A claims-data audit of real-world combination-therapy sequencing for a common chronic condition, benchmarked against clinical-guideline recommended sequences.",
      "tags": [
        "machine learning",
        "clinical data",
        "claims data"
      ],
      "skillsNeeded": [
        "Python",
        "causal inference"
      ],
      "stage": "Submitted, under review",
      "openToNewMembers": true,
      "contact": {
        "name": "Wei",
        "email": "wei.zhang@example.org"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S020",
      "title": "Explaining Statistics to Journalists: A Field Guide From Five Years of Media Requests",
      "abstract": "A practical field guide, drawn from five years of fielding journalist questions about the lab's statistical results, on how to explain p-values, confidence intervals, and effect sizes without either dumbing them down or getting misquoted.",
      "tags": [
        "writing",
        "science communication",
        "public engagement"
      ],
      "skillsNeeded": [
        "writing",
        "editing"
      ],
      "stage": "Published",
      "openToNewMembers": true,
      "contact": {
        "name": "Sofia",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": null,
      "teamMembers": []
    },
    {
      "id": "S021",
      "title": "AI-Assisted Post-Surgical Recovery Check-Ins via Chat",
      "abstract": "A lightweight conversational check-in tool that messages patients on WhatsApp after surgery to catch early warning signs before their next appointment, designed with nursing staff rather than for them.",
      "tags": [
        "patient engagement",
        "healthcare AI",
        "conversational AI"
      ],
      "skillsNeeded": [
        "Python",
        "clinical workflows"
      ],
      "stage": "In progress (drafting)",
      "openToNewMembers": true,
      "contact": {
        "name": "Dana",
        "email": "criticaldata-lab@mit.edu"
      },
      "whatsapp": "https://wa.me/15551234567",
      "teamMembers": [
        {
          "name": "Dana Okafor",
          "linkedin": "https://linkedin.com/in/fake-dana-okafor"
        },
        {
          "name": "Théo Laurent",
          "linkedin": "https://linkedin.com/in/fake-theo-laurent"
        }
      ]
    },
    {
      "id": "S022",
      "title": "Community Data Co-ops for Rare Disease Research",
      "abstract": "Exploring a community-governed data co-op model where rare-disease patient communities collectively decide how their pooled health data gets used for research, instead of a single institution holding all the keys.",
      "tags": [
        "data governance",
        "rare disease",
        "community health"
      ],
      "skillsNeeded": [
        "policy analysis",
        "community organizing"
      ],
      "stage": "Early stage / idea",
      "openToNewMembers": true,
      "contact": {
        "name": "Priya",
        "email": "priya.raman@example.org"
      },
      "whatsapp": "https://wa.me/15559876543",
      "teamMembers": [
        {
          "name": "Priya Raman",
          "linkedin": "https://linkedin.com/in/fake-priya-raman"
        }
      ]
    }
  ]
}