================================================================================
CONCATENATED DOCUMENT
================================================================================
Input Directory: data/d4d_individual/gpt5/CM4AI
Total Files: 4
Extensions: All
Recursive: False
================================================================================

TABLE OF CONTENTS
--------------------------------------------------------------------------------
  1. dataverse_10.18130_V3_B35XWX_d4d.yaml
  2. dataverse_10.18130_V3_F3TD5R_d4d.yaml
  3. dataverse_10.18130_V3_F3TD5R_d4d_metadata.yaml
  4. doi_row3_d4d.yaml
================================================================================

FILE: dataverse_10.18130_V3_B35XWX_d4d.yaml
PATH: data/d4d_individual/gpt5/CM4AI/dataverse_10.18130_V3_B35XWX_d4d.yaml
SIZE: 23346 bytes
--------------------------------------------------------------------------------

# D4D Metadata extracted from: dataverse_10.18130_V3_B35XWX_row13.txt
# Column: CM4AI
# Validation: Download ✅ success
# Relevance: ✅ relevant
# Generated: 2025-10-30 12:39:49

id: "doi:10.18130/V3/B35XWX"
name: Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)
title: Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)
description: >
  This dataset is the March 2025 Data Release of Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org),
  the Functional Genomics Grand Challenge in the NIH Bridge2AI program. This Beta release includes
  perturb-seq data in undifferentiated KOLF2.1J iPSCs; SEC-MS data in undifferentiated KOLF2.1J iPSCs and
  iPSC-derived NPCs, neurons, and cardiomyocytes; and IF images in MDA-MB-468 breast cancer cells in the
  presence and absence of chemotherapy (vorinostat and paclitaxel). CM4AI output data are packaged with
  provenance graphs and rich metadata as AI-ready datasets in RO-Crate format using the FAIRSCAPE framework.
  Data presented here will be augmented regularly through the end of the project. CM4AI is a collaboration
  of UCSD, UCSF, Stanford, UVA, Yale, UA Birmingham, Simon Fraser University, and the Hastings Center.
  This data is Copyright (c) 2025 The Regents of the University of California except where otherwise noted.
  Spatial proteomics raw image data is copyright (c) 2025 The Board of Trustees of the Leland Stanford
  Junior University. Dataset licensed for reuse under Creative Commons Attribution-NonCommercial-ShareAlike
  4.0 International license (https://creativecommons.org/licenses/by-nc-sa/4.0/). Attribution is required
  to the copyright holders and the authors. Any publications referencing this data or derived products
  should cite the Related Publication below, as well as directly citing this data collection (2025-03-04).
doi: "doi:10.18130/V3/B35XWX"
publisher: "https://dataverse.lib.virginia.edu"
issued: "2025-03-03"
page: "https://doi.org/10.18130/V3/B35XWX"
created_on: "2025-02-27"
license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
version: "1.4"
conforms_to: "https://w3id.org/ro/crate"
keywords:
  - AI
  - affinity purification
  - AP-MS
  - artificial intelligence
  - breast cancer
  - Bridge2AI
  - cardiomyocyte
  - CM4AI
  - CRISPR/Cas9
  - induced pluripotent stem cell
  - iPSC
  - KOLF2.1J
  - machine learning
  - mass spectroscopy
  - MDA-MB-468
  - neural progenitor cell
  - NPC
  - neuron
  - paclitaxel
  - perturb-seq
  - perturbation sequencing
  - protein-protein interaction
  - protein localization
  - single-cell RNA sequencing
  - scRNAseq
  - SEC-MS
  - size exclusion chromatography
  - subcellular imaging
  - vorinostat
created_by:
  - "Clark T (University of Virginia) - ORCID: https://orcid.org/0000-0003-4060-7360"
  - "Parker J (University of California, San Diego) - ORCID: https://orcid.org/0000-0003-4535-3486"
  - "Al Manir S (University of Virginia) - ORCID: https://orcid.org/0000-0003-4647-3877"
  - "Axelsson U (KTH Royal Institute of Technology,)"
  - "Ballllosero Navarro F (Stanford University) - ORCID: https://orcid.org/0000-0002-4180-422X"
  - "Chinn B (University of California San Diego)"
  - "Churas CP (University of California San Diego) https://orcid.org/0000-0001-9998-705X"
  - "Dailamy A (University of California, San Diego) - ORCID: https://orcid.org/0000-0002-6711-8260"
  - "Doctor Y (University of California, San Diego) - ORCID: https://orcid.org/0009-0009-0483-7506"
  - "Fall J (KTH - Royal Institute of Technology)"
  - "Forget A (University of California San Francisco) - ORCID: https://orcid.org/0000-0003-0223-0312"
  - "Gao J (University of California San Diego) - ORCID: https://orcid.org/0000-0002-6311-3526"
  - "Hansen JN (Stanford University) - ORCID: https://orcid.org/0000-0002-4650-9094"
  - "Hu M (University of California San Diego) https://orcid.org/0000-0002-1571-8029"
  - "Johannesson A (KTH - Royal Institute of Technology)"
  - "Khaliq H (University of California San Diego)"
  - "Lee YH (University of California San Diego) - ORCID: https://orcid.org/0000-0003-0917-355X"
  - "Lenkiewicz J (University of California San Diego) https://orcid.org/0000-0001-7252-8638"
  - "Levinson MA (University of Virginia) - ORCID: https://orcid.org/0000-0003-0384-8499"
  - "Marquez C (University of California San Diego) - ORCID: 0000-0003-3960-420X"
  - "Metallo C (University of California San Diego) - ORCID: https://orcid.org/0000-0003-2404-3040"
  - "Muralidharan M (University of California San Francisco)"
  - "Nourreddine S (University of California San Diego) https://orcid.org/0000-0003-3881-7588"
  - "Niestroy J (University of Virginia) - ORCID: https://orcid.org/0000-0002-1103-3882"
  - "Obernier K (University of California San Francisco) - ORCID: https://orcid.org/0000-0002-4025-1299"
  - "Pan E (University of California San Diego)"
  - "Polacco B (University of California San Francisco)"
  - "Pratt D (University of California San Diego) - ORCID: https://orcid.org/0000-0002-1471-9513"
  - "Qian G (University of California San Diego) - ORCID: https://orcid.org/0009-0005-4217-2745"
  - "Schaffer L (University of California San Diego) - ORCID: https://orcid.org/0000-0001-6339-9141"
  - "Sigaeva A (KTH Royal Institute of Technology) - ORCID: https://orcid.org/0000-0003-3361-3797"
  - "Thaker S (University of Alabama at Birmingham) - ORCID: https://orcid.org/0000-0001-6730-2773"
  - "Zhang Y (University of California San Diego)"
  - "Bélisle-Pipon JC (Simon Fraser University) - ORCID: https://orcid.org/0000-0002-8965-8153"
  - "Brandt C (Yale University) - ORCID: https://orcid.org/0000-0001-8179-1796"
  - "Chen JY (The University of Alabama at Birmingham) - ORCID: https://orcid.org/0000-0002-6112-415X"
  - "Ding Y (University of Texas at Austin) - ORCID: https://orcid.org/0000-0003-2567-2009"
  - "Fodeh S (Yale University) - ORCID: https://orcid.org/0000-0003-4664-3143"
  - "Krogan N (University of California San Francisco) - ORCID: https://orcid.org/0000-0003-4902-337X"
  - "Lundberg E (Stanford University) - ORCID: https://orcid.org/0000-0001-7034-0850"
  - "Mali P (University of California San Diego) https://orcid.org/0000-0002-3383-1287"
  - "Payne-Foster P (University of Alabama) - ORCID: https://orcid.org/0000-0002-3508-3577"
  - "Ratcliffe S (University of Virginia) - ORCID: https://orcid.org/0000-0002-6644-8284"
  - "Ravitsky V (University of Montreal) - ORCID: https://orcid.org/0000-0002-7080-8801"
  - "Sali A (University of California San Diego) - ORCID: https://orcid.org/0000-0003-0435-6197"
  - "Schulz W (Yale University) - ORCID: https://orcid.org/0000-0002-2048-4028"
  - "Ideker T (University of California San Diego) - ORCID: https://orcid.org/0000-0002-1708-8454"
resources:
  - id: "CRISPR Perturbation Cell Atlas/ro-crate-metadata.json"
    name: ro-crate-metadata.json
    title: CRISPR Perturbation Cell Atlas RO-Crate metadata
    description: >
      Expressed genome-scale CRISPRi Perturbation Cell Atlas in undifferentiated KOLF2.1J human induced
      pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739
      targeted genes. Findings validated via phenotypic, protein-interaction, and metabolic tracing assays.
    format: JSON
    media_type: application/json
    md5: cbdb263b1c099396d75e16f00a79a818
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "AI-ready functional genomics data release for CM4AI to support machine learning research."
    tasks:
      - response: "Single-cell perturb-seq analysis and model development."
      - response: "Gene function and fitness phenotype modeling."
    instances:
      - representation: "CRISPR perturbation atlas metadata (RO-Crate)."
        data_type: "JSON metadata conforming to RO-Crate; describes sample, assay, and provenance."
    acquisition_methods:
      - description: "CRISPR interference (CRISPRi) with perturb-seq in KOLF2.1J hiPSCs."
    collection_timeframes:
      - description: "Data creation date: 2025-02-27; Published: 2025-03-03."
    data_collectors:
      - description: "CM4AI consortium; work conducted at UC San Diego and collaborating institutions."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    existing_uses:
      - description: "Related publication: Cell Maps for Artificial Intelligence (bioRxiv 2024.05.21.589311)."
      - description: "Related publication: A PERTURBATION CELL ATLAS OF HUMAN iPSCs (bioRxiv 2024.11.03.621734)."
    distribution_formats:
      - description: "RO-Crate (JSON metadata)."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required to copyright holders and authors; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
    conforms_to: "https://w3id.org/ro/crate"
    distribution:
      - description: "Public access via Dataverse; dataset may be too large for bulk download—select files individually."
  - id: "CRISPR Perturbation RNA Sequences - Raw Sequences/ro-crate-metadata.json"
    name: ro-crate-metadata.json
    title: CRISPR Perturbation RNA Sequences (Raw) RO-Crate metadata
    description: >
      Raw sequence data from an expressed genome-scale CRISPRi Perturbation Cell Atlas in KOLF2.1J hiPSCs
      mapping transcriptional and fitness phenotypes associated with 11,739 targeted genes.
    format: JSON
    media_type: application/json
    md5: 1cafefa32a897998e3e2ba0a29a3ef5c
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "Provide raw RNA sequence data for AI/ML-ready perturb-seq analyses within CM4AI."
    tasks:
      - response: "Single-cell RNA sequencing analysis of CRISPR perturbations."
    instances:
      - representation: "Raw RNA sequence dataset metadata (RO-Crate)."
        data_type: "JSON metadata describing raw sequence files and provenance."
    acquisition_methods:
      - description: "CRISPRi with perturb-seq in KOLF2.1J hiPSCs; raw RNA sequences."
    collection_timeframes:
      - description: "Data creation date: 2025-02-27; Published: 2025-03-03."
    data_collectors:
      - description: "CM4AI consortium; work conducted at UC San Diego and collaborating institutions."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    existing_uses:
      - description: "Related publication: A PERTURBATION CELL ATLAS OF HUMAN iPSCs (bioRxiv 2024.11.03.621734)."
    distribution_formats:
      - description: "RO-Crate (JSON metadata)."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
    conforms_to: "https://w3id.org/ro/crate"
  - id: "Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-untreated.zip"
    name: cm4ai-v0.6-beta-if-images-untreated.zip
    title: Protein Localization Subcellular Images - Untreated (MDA-MB-468)
    description: >
      Spatial localization of 563 proteins of interest in untreated cells of the breast cancer cell line
      MDA-MB-468, imaged by immunofluorescence-based staining (ICC-IF) and confocal microscopy in the
      Lundberg Lab at Stanford University. Nuclei were stained with DAPI (blue); endoplasmic reticulum with
      calreticulin antibody (yellow); microtubules with tubulin antibody (red); protein of interest antibody
      (green).
    compression: ZIP
    media_type: application/zip
    md5: 0b4d129f5fbc3bb7f7ea564cd032cef7
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "AI-ready subcellular imaging for protein localization analysis and ML benchmarking."
    tasks:
      - response: "Subcellular localization classification and feature learning from IF images."
    instances:
      - representation: "Immunofluorescence confocal microscopy images (untreated MDA-MB-468)."
        data_type: "Multichannel TIFF/imagery within ZIP archive."
    acquisition_methods:
      - description: "ICC-IF staining and confocal microscopy; channels: DAPI (nuclei), calreticulin (ER), tubulin (microtubules), protein-of-interest."
    collection_timeframes:
      - description: "Published: 2025-03-03."
    data_collectors:
      - description: "Lundberg Lab, Stanford University."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    distribution_formats:
      - description: "ZIP archive of imaging data."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Spatial proteomics raw image data copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University."
        - "Other data copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
  - id: "Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-paclitaxel.zip"
    name: cm4ai-v0.6-beta-if-images-paclitaxel.zip
    title: Protein Localization Subcellular Images - Paclitaxel-treated (MDA-MB-468)
    description: >
      Spatial localization of 563 proteins of interest in MDA-MB-468 cells treated with paclitaxel, imaged
      by ICC-IF and confocal microscopy in the Lundberg Lab at Stanford University. Channels: DAPI (blue),
      calreticulin (ER, yellow), tubulin (red), protein-of-interest (green).
    compression: ZIP
    media_type: application/zip
    md5: 9422486c80bc9e1d35b2fbbc72a5f043
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "Support ML studies on chemotherapy-induced subcellular localization changes."
    tasks:
      - response: "Image-based ML for drug response phenotyping."
    instances:
      - representation: "Immunofluorescence confocal microscopy images (paclitaxel-treated MDA-MB-468)."
        data_type: "Multichannel microscopy images in ZIP archive."
    acquisition_methods:
      - description: "ICC-IF staining and confocal microscopy under paclitaxel treatment."
    collection_timeframes:
      - description: "Published: 2025-03-03."
    data_collectors:
      - description: "Lundberg Lab, Stanford University."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    distribution_formats:
      - description: "ZIP archive of imaging data."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Spatial proteomics raw image data copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University."
        - "Other data copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
  - id: "Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-vorinostat.zip"
    name: cm4ai-v0.6-beta-if-images-vorinostat.zip
    title: Protein Localization Subcellular Images - Vorinostat-treated (MDA-MB-468)
    description: >
      Spatial localization of 563 proteins of interest in MDA-MB-468 cells treated with vorinostat, imaged
      by ICC-IF and confocal microscopy in the Lundberg Lab at Stanford University. Channels: DAPI (blue),
      calreticulin (ER, yellow), tubulin (red), protein-of-interest (green).
    compression: ZIP
    media_type: application/zip
    md5: ac577109a41a9806978461157b777d52
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "Enable ML analyses of HDAC inhibitor effects on protein localization."
    tasks:
      - response: "Subcellular imaging analysis under vorinostat treatment."
    instances:
      - representation: "Immunofluorescence confocal microscopy images (vorinostat-treated MDA-MB-468)."
        data_type: "Multichannel microscopy images in ZIP archive."
    acquisition_methods:
      - description: "ICC-IF staining and confocal microscopy under vorinostat treatment."
    collection_timeframes:
      - description: "Published: 2025-03-03."
    data_collectors:
      - description: "Lundberg Lab, Stanford University."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    distribution_formats:
      - description: "ZIP archive of imaging data."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Spatial proteomics raw image data copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University."
        - "Other data copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
  - id: "Protein-protein Interaction SEC-MS/ro-crate-metadata.json"
    name: ro-crate-metadata.json
    title: Protein-Protein Interaction SEC-MS RO-Crate metadata
    description: >
      Size exclusion chromatography-mass spectroscopy (SEC-MS) on undifferentiated KOLF2.1J human induced
      pluripotent stem cells (hiPSCs), generated in the Nevan Krogan laboratory at UCSF as part of CM4AI
      (NIH Bridge2AI program). The data will be uploaded to PRIDE when available.
    format: JSON
    media_type: application/json
    md5: cb67e7749b15ce87b9042a9feba9d032
    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
    purposes:
      - response: "Provide AI-ready proteomics interaction data for modeling protein complexes."
    tasks:
      - response: "Protein complex inference and PPI network analysis from SEC-MS profiles."
    instances:
      - representation: "SEC-MS assay metadata (RO-Crate)."
        data_type: "JSON metadata describing SEC-MS experiments and provenance."
    acquisition_methods:
      - description: "Size exclusion chromatography followed by mass spectrometry (SEC-MS) in KOLF2.1J hiPSCs."
    collection_timeframes:
      - description: "Data creation date: 2025-02-27; Published: 2025-03-03."
    data_collectors:
      - description: "Nevan Krogan Laboratory, University of California San Francisco."
    funders:
      - grantor:
          id: "https://reporter.nih.gov/"
          name: National Institutes of Health
        grant:
          name: "Bridge2AI CM4AI"
          grant_number: "1OT2OD032742-01"
    external_resources:
      - external_resources: "PRIDE repository (planned upload when available)."
    distribution_formats:
      - description: "RO-Crate (JSON metadata)."
    distribution_dates:
      - description: "2025-03-03"
    license_and_use_terms:
      description:
        - "Attribution required; cite related publication and this data collection."
        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International."
    ip_restrictions:
      description:
        - "Copyright (c) 2025 The Regents of the University of California."
    maintainers:
      - description:
          - "Hosted by University of Virginia Dataverse; contact via dataset page."
          - "Point of Contact: Trey Ideker (University of California San Diego)."
existing_uses:
  - description: "Clark T, et al. Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. 2024. doi: http://doi.org/10.1101/2024.05.21.589311"
  - description: "Nourreddine S, et al. A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS. bioRxiv. 2024 Nov 4; 2024.11.03.621734. PMCID: PMC11580897 doi: https://doi.org/10.1101/2024.11.03.621734"
distribution_formats:
  - description: "RO-Crate packages (JSON metadata) and ZIP archives for imaging data."
distribution_dates:
  - description: "2025-03-03"
license_and_use_terms:
  description:
    - "Dataset is licensed under CC BY-NC-SA 4.0; attribution required to copyright holders and authors."
    - "Cite the related publication(s) and this data collection."
IP_restrictions:
  description:
    - "Copyright (c) 2025 The Regents of the University of California except where otherwise noted."
    - "Spatial proteomics raw image data: Copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University."
maintainers:
  - description:
      - "Hosted/maintained by University of Virginia Dataverse (LibraData)."
      - "Point of Contact listed: Trey Ideker (University of California San Diego); contact via dataset page."
updates:
  description:
    - "Data will be augmented regularly through the end of the project."
use_repository:
  - description: "Dataset available via University of Virginia Dataverse (public files; large dataset guidance provided)."

================================================================================

FILE: dataverse_10.18130_V3_F3TD5R_d4d.yaml
PATH: data/d4d_individual/gpt5/CM4AI/dataverse_10.18130_V3_F3TD5R_d4d.yaml
SIZE: 1254 bytes
--------------------------------------------------------------------------------

# D4D Metadata extracted from: dataverse_10.18130_V3_F3TD5R_row16.txt
# Column: CM4AI
# Validation: Download ✅ success
# Relevance: ✅ relevant
# Generated: 2025-09-16 18:09:00

id: dataverse_10.18130_V3_F3TD5R_row16
title: University of Virginia Dataverse Login Page
description: This record captures the University of Virginia Dataverse login page content. It provides institutional login options, contact information for University of Virginia Dataverse Support, and a maintenance notice. No dataset-specific metadata is present in this source.
language: en
keywords:
  - CM4AI
  - Dataverse
  - University of Virginia
  - Login
path: dataverse_10.18130_V3_F3TD5R_row16.txt
media_type: text/plain
distribution_formats:
  - description:
      - Hosted and accessed via the University of Virginia Dataverse web portal (login required).
    used_software:
      - name: Dataverse
        version: 6.6 build 1829-192cdc4
maintainers:
  - description:
      - University of Virginia Dataverse Support
license_and_use_terms:
  description:
    - The site references Terms of Use and a Privacy Policy; no specific dataset license information is present in the source.
external_resources:
  - external_resources:
      - Terms of Use
      - Privacy Policy

================================================================================

FILE: dataverse_10.18130_V3_F3TD5R_d4d_metadata.yaml
PATH: data/d4d_individual/gpt5/CM4AI/dataverse_10.18130_V3_F3TD5R_d4d_metadata.yaml
SIZE: 1688 bytes
--------------------------------------------------------------------------------

extraction_metadata:
  timestamp: '2025-09-17T01:09:00.686820Z'
  extraction_id: 91825473ce2a
input_document:
  filename: dataverse_10.18130_V3_F3TD5R_row16.txt
  relative_path: dataverse_10.18130_V3_F3TD5R_row16.txt
  format: txt
  size_bytes: 1339
  sha256_hash: 17a0deabef43d1de4ced7a18a9a37df0e89bd9f1ab1df3fdace0d2a089baf764
  project_column: CM4AI
output_document:
  filename: dataverse_10.18130_V3_F3TD5R_d4d.yaml
  relative_path: dataverse_10.18130_V3_F3TD5R_d4d.yaml
  format: yaml
datasheets_schema:
  version: 1.0.0
  url: https://raw.githubusercontent.com/monarch-initiative/ontogpt/main/src/ontogpt/templates/data_sheets_schema.yaml
  retrieved_at: '2025-09-17T01:09:00.687201Z'
d4d_agent:
  version: 1.0.0
  implementation: pydantic_ai
  wrapper: validated_d4d_wrapper.py
  wrapper_version: 2.0.0
llm_model:
  provider: openai
  model_name: openai:gpt-5
  model_version: gpt-5
  temperature: null
  max_tokens: null
validation_results:
  download_validation:
    success: true
    file_size: 1339
    content_type: .txt
  relevance_validation:
    success: true
    score: 6
    keywords_found:
    - dataverse
    project_indicators:
    - virginia
processing_environment:
  platform: Darwin
  python_version: 3.13.4
  processor_architecture: arm64
reproducibility:
  command: python validated_d4d_wrapper.py -i ../downloads_by_column -o ../data/extracted_by_column
  environment_variables:
    OPENAI_API_KEY: required
    ANTHROPIC_API_KEY: not_set
  random_seed: null
provenance:
  extraction_performed_by: validated_d4d_wrapper
  extraction_requested_at: '2025-09-17T01:09:00.687245Z'
  git_commit: null
  notes: D4D extraction using GPT-5 model with validation checks


================================================================================

FILE: doi_row3_d4d.yaml
PATH: data/d4d_individual/gpt5/CM4AI/doi_row3_d4d.yaml
SIZE: 343 bytes
--------------------------------------------------------------------------------

# D4D Metadata extracted from: doi_row3.json
# Column: CM4AI
# Validation: Download ✅ success
# Relevance: ⚠️  limited relevance
# Generated: 2025-10-30 19:48:45

id: "doi:10.1101/2024.05.21.589311"
name: 10.1101/2024.05.21.589311
doi: "doi:10.1101/2024.05.21.589311"
page: "https://doi.org/10.1101/2024.05.21.589311"
keywords:
  - CM4AI