{
  "schema_version": "1.0.0",
  "site_revision": 21,
  "generated_at": "2026-08-06",
  "title": "2026 Senate COVID-19 investigation records index",
  "scope_note": "Page-level and file-level metadata for publisher-current Senate HSGAC records hosted or cataloged through R21. Primary records establish what the documents, witnesses, scientists, agencies, and committee members recorded. This archive makes no independent determination about scientific causation, intent, ethics, disclosure, conflicts of interest, compliance, misconduct, or legal liability.",
  "privacy_screening": {
    "status": "completed_with_disclosed_limits",
    "method": "Non-modifying automated text-pattern screening of every extractable page plus visual review of flagged pages and image-only or low-text pages, with publisher-revision comparison where a superseded version was present.",
    "result": "The NIH moderation and intelligence-correspondence files passed the R20 publication screen unchanged. The complete Slack production contains access-bearing URLs and the current Daszak CBP file contains operational contact details, so those files are not mirrored. The selected Slack excerpts are deferred with the complete production to avoid presenting a curated slice without the fuller record. R21 found a date-of-birth identifier and operational contacts in the Gates collection, and direct contacts plus sensitive immigration, family, demographic, employment, financial, and law-enforcement records in the separate 41-page CBP package. Those bodies remain official-source-only. The superseded CBP body and its text extract remain quarantined. This site did not add, remove, or select any blackout and hosts only byte-identical publisher-current copies.",
    "limitation": "The site screen is quality control, not a redaction process, privacy certification, legal review, or ethics determination. It cannot guarantee that no sensitive information remains. Publisher-current status is necessary but not treated as a guarantee of privacy completeness; reports of sensitive information should be handled through the public correction process."
  },
  "hosted_files": [
    {
      "source_catalog_id": 106,
      "title": "The Reading Room: Investigation Records — Volume I",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/Reading-Room-FINAL.pdf",
      "hosted_path": "/primary-records/r17/senate-investigation-records-volume-1.pdf",
      "pages": 496,
      "bytes": 72002614,
      "sha256": "2336f6650bb4740f5e14e60a1b86a63ff4b8b62bdc3a899151eda1c57e0b0018",
      "extractable_text_pages": 383,
      "text_coverage_percent": 77.2,
      "duplicate_screen": {
        "method": "SHA-256 of whitespace-normalized extracted text",
        "exact_text_groups": 88,
        "pages_in_groups": 240,
        "redundant_occurrences_after_one_canonical_page_per_group": 152,
        "interpretation": "The production repeats two substantial blocks: pages 2–57 recur at 225–280, and most of pages 193–224 recur at 330–361. A large group also consists only of identical release-stamp text on otherwise image-only or separator pages. Duplicate counts are discovery aids, not grounds for deleting pages from the complete hosted record."
      },
      "page_index": "/senate-records/volume-1-page-index.json"
    },
    {
      "source_catalog_id": 107,
      "title": "Transcribed Interview of Dr. Ralph Baric — Senate source file labeled redacted",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/2026.07.23_UPDATED-FINAL-FINAL_BARIC-TI_Redacted.pdf",
      "hosted_path": "/primary-records/r17/baric-transcribed-interview-2026-redacted.pdf",
      "pages": 155,
      "bytes": 2201101,
      "sha256": "1c92d71aa0ab489da09c84a5c31f8684d8d98c2b3610519e336bb5422e647214",
      "extractable_text_pages": 155,
      "contents": "Cover and committee summary; 105-page interview transcript; committee errata; three exhibits beginning at transcript exhibit pages 45, 81, and 113."
    },
    {
      "source_catalog_id": 108,
      "title": "Fauci awards and prize correspondence — Senate source file labeled redacted",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/7.24.2026_Fauci-Awards_FINAL_REDACTED.pdf",
      "hosted_path": "/primary-records/r17/fauci-awards-records-2026-redacted.pdf",
      "pages": 136,
      "bytes": 16574007,
      "sha256": "eddf51f11901124f041236b9c1afc623a2d3fabbfb0296143cf8e6cf547333e0",
      "extractable_text_pages": 133,
      "framing": "The file documents prize and nomination correspondence. This archive makes no independent determination about compliance with ethics, disclosure, conflict-of-interest, or other legal requirements."
    },
    {
      "source_catalog_id": 110,
      "title": "Opening Statement of Chairman Rand Paul — July 29, 2026",
      "official_source_url": "https://www.hsgac.senate.gov/library/files/opening-statement-peters-2026-07-29/opening-statement-paul-2026-07-29/",
      "hosted_path": "/primary-records/r17/paul-opening-statement-fauci-hearing-2026.pdf",
      "pages": 5,
      "bytes": 106761,
      "sha256": "1801631de41b5c10f460815b9563a94a31c58da79276307b1da7f636a51bb533",
      "extractable_text_pages": 5
    },
    {
      "source_catalog_id": 111,
      "title": "Opening Statement of Ranking Member Gary Peters — July 29, 2026",
      "official_source_url": "https://www.hsgac.senate.gov/library/files/opening-statement-peters-2026-07-29/opening-statement-peters-2026-07-29/",
      "hosted_path": "/primary-records/r17/peters-opening-statement-fauci-hearing-2026.pdf",
      "pages": 3,
      "bytes": 120244,
      "sha256": "587886cf3602f22504ba6f058122131877bfcc28df5ff7c61e42f214e66461ad",
      "extractable_text_pages": 3
    },
    {
      "source_catalog_id": 115,
      "title": "NIH public-comment moderation and litigation records",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/2026.07.17_NIH-Hid-Public-Comments-Package.pdf",
      "hosted_path": "/primary-records/r20/nih-public-comment-moderation-records-2026.pdf",
      "pages": 128,
      "bytes": 10208940,
      "sha256": "e606fcff44bc5caac3d274a7aafd665fe721b80d6758e50bd4c3e21b2037932d",
      "extractable_text_pages": 106,
      "framing": "The records document keyword filters, manual hiding, off-topic moderation, and litigation advice. They do not by themselves adjudicate the constitutionality or legality of any moderation decision."
    },
    {
      "source_catalog_id": 116,
      "title": "Fauci and intelligence-community correspondence",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/Fauci-Intel-Release-2026.06.11.pdf",
      "hosted_path": "/primary-records/r20/fauci-intelligence-community-correspondence-2026.pdf",
      "pages": 88,
      "bytes": 10333452,
      "sha256": "b84b698b1c8a8a69de0bbfad98d24b205826e510f44f5d185fe203d1984b7ee6",
      "extractable_text_pages": 61,
      "framing": "The correspondence documents contacts, briefings, and requests for scientific review. Contact with intelligence agencies does not by itself establish concealment, improper coordination, or a conclusion about origin."
    }
  ],
  "privacy_deferred_records": [
    {
      "source_catalog_id": 113,
      "title": "Proximal Origin authors' Slack messages — committee-selected key messages",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/slack-drop-AM.pdf",
      "pages": 15,
      "bytes": 1875918,
      "sha256": "d19363233e3659550dd2037f5b86e48ce0e86b7d5047a28fece6f0a986edeb48",
      "status": "cataloged_not_hosted",
      "reason": "The excerpt passed screening but is deferred with the complete production so a committee-curated slice is not mirrored without the fuller record."
    },
    {
      "source_catalog_id": 114,
      "title": "Proximal Origin authors' Slack messages — complete Senate production",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/slack-drop-pm.pdf",
      "pages": 1123,
      "bytes": 14177833,
      "sha256": "c7717f016c4385e25de3fd1bdc2989c5f8f3ab6d496f346d3a74953729c2c89b",
      "page_index": "/senate-records/slack-page-index.json",
      "status": "cataloged_not_hosted",
      "reason": "The production contains access-bearing URLs on two reviewed pages. The site does not reproduce those values and does not alter publisher PDFs."
    },
    {
      "source_catalog_id": 117,
      "title": "Peter Daszak CBP records — publisher-current version",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/2026.07.17_Daszak-CBP-Package_-1.pdf",
      "pages": 23,
      "bytes": 2977578,
      "sha256": "41ddf4f797298e4d426cf498822f061af6b479755db8a396390dab38a24bdb21",
      "status": "cataloged_not_hosted",
      "reason": "The publisher-current file contains an operational phone number and work email the site will not mirror.",
      "withdrawn_predecessor": {
        "bytes": 5070880,
        "sha256": "b007c77119233c89017c3c41fcec50b05100f8304c9ec74e447d60eece2a284e",
        "status": "quarantined_not_hosted_or_linked",
        "reason": "The prior source URL now returns 404 and the retired body exposed identifiers that are blacked out in the publisher-current file. Its text derivative is also quarantined."
      }
    },
    {
      "source_catalog_id": 118,
      "title": "CBP traveler and researcher records release package",
      "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/FINAL-CBP-Release-Package.pdf",
      "pages": 41,
      "bytes": 5754806,
      "sha256": "b1a4e3bf9f93405ca410f173dd39f73d93d406b02bc98807e3c03b1a63e750cf",
      "status": "cataloged_not_hosted",
      "reason": "The production contains direct contacts and sensitive immigration, family, demographic, employment, financial, and law-enforcement records. The site does not reproduce those values or alter the publisher PDF.",
      "review": {
        "method": "Every page was visually reviewed; the four text-rich pages also received pattern screening.",
        "result": "Publisher blackouts appeared burned into page images. No hidden text, layers, attachments, JavaScript, annotations, or populated form fields were detected.",
        "limitation": "Publication and privacy quality control, not a legal review or a determination that the publisher's handling satisfies every policy.",
        "markings_note": "FOUO, LES, and USPER are originating CBP handling markings. They do not by themselves establish that Senate publication was lawful or unlawful."
      },
      "framing": "Attribute report assessments and committee characterizations. The record does not independently establish scientific causation, intent, wrongdoing, ethics violations, or legal liability."
    }
  ],
  "hearing_record": {
    "source_catalog_id": 109,
    "title": "Testimony of Anthony Fauci — July 29, 2026",
    "hearing_page": "https://www.hsgac.senate.gov/hearings/testimony-of-anthony-fauci/",
    "official_full_video": "https://www.senate.gov/isvp/?comm=govtaff&type=live&stt=930&filename=govtaff072926&auto_play=false",
    "available_official_files": ["Chairman Paul opening statement", "Ranking Member Peters opening statement"],
    "not_located_as_of_2026_08_06": ["official stenographic transcript", "downloadable Fauci witness statement"]
  },
  "deferred_collection": {
    "source_catalog_id": 112,
    "title": "NIH, Fauci, and Gates Foundation records collection",
    "official_source_url": "https://www.paul.senate.gov/wp-content/uploads/2026/07/2026.07.31Gates.pdf",
    "pages": 1375,
    "bytes": 136929291,
    "sha256": "7531a11492ec1654e7044b4e402a1e2a202d99f091534a7b6c7f361c71819acd",
    "page_index": "/senate-records/gates-page-index.json",
    "status": "indexed_official_source_only",
    "reason": "The collection now has a public-safe page/topic and duplicate index, but the publisher-current PDF contains a date-of-birth identifier and operational contact details. The site does not reproduce those values or alter the publisher PDF."
  },
  "publisher_revision_check": {
    "checked_at": "2026-08-06",
    "result": "The official Slack excerpt, complete Slack production, and current Daszak CBP bodies remain byte-identical to the R20-reviewed copies. No later Reading Room volume, official July 29 hearing transcript, Fauci witness statement, or committee contempt record was located."
  },
  "monitored_future_records": [
    "Reading Room Investigation Records — Volume II or later volumes",
    "official July 29, 2026 hearing transcript or Fauci witness statement",
    "official committee contempt resolution, report, or referral materials"
  ]
}