{
  "schemaVersion": 1,
  "releaseId": "2026-07-v2",
  "title": "ResumeGet Resume Parsing Lab - July 2026",
  "publishedAt": "2026-07-26",
  "generatedAt": "2026-07-26T00:00:00.000Z",
  "canonicalUrl": "https://resume-get.com/research/resume-parsing-lab",
  "productionPipeline": "ResumeGet production PDF and DOCX text extraction pipeline",
  "methodologyVersion": 1,
  "supersedes": "2026-07-v1",
  "changes": [
    "Corrected PDF name and contact line spacing across nine affected fixture layouts.",
    "Added automated text-collision validation for every generated resume PDF."
  ],
  "sourceSha256": "2ed6af0dc2c518cb134330f3fa8d1eb07596d783e627c5dc880d71f192912d1e",
  "syntheticDataNotice": "Every person, employer, institution, URL, phone number, and achievement in this release is synthetic and reserved for testing.",
  "totals": {
    "cases": 10,
    "artifacts": 20,
    "riskPatterns": 11,
    "byStatus": {
      "preserved": 14,
      "reordered": 1,
      "content_loss": 5,
      "unreadable": 0
    }
  },
  "results": [
    {
      "id": "baseline-single-column.pdf",
      "caseId": "baseline-single-column",
      "title": "Baseline single column",
      "description": "A conventional one-column resume with contact details in the main document flow.",
      "format": "pdf",
      "riskPatterns": [
        "single-column-baseline"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/baseline-single-column.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/baseline-single-column.pdf.txt",
      "fixtureSha256": "ca052161dd962ae540ec8e47bca87911153f46824fa073f0fe91fa7db63300eb",
      "extractedTextSha256": "33e1349d679a7951e4301fbec0269326ddb611827df1d11bf007e5d961df6784",
      "bytes": 4330,
      "status": "preserved",
      "extractedCharacters": 1355,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "baseline-single-column.docx",
      "caseId": "baseline-single-column",
      "title": "Baseline single column",
      "description": "A conventional one-column resume with contact details in the main document flow.",
      "format": "docx",
      "riskPatterns": [
        "single-column-baseline"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/baseline-single-column.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/baseline-single-column.docx.txt",
      "fixtureSha256": "df23e226289b8490f46ca5fc426d18fcc3f5a6fcc4745634e9f16538c22908ed",
      "extractedTextSha256": "66479bf771b4c6a518ab89ca4fb10a883db2e50a9c7055c1ed83e17755bb7de1",
      "bytes": 9795,
      "status": "preserved",
      "extractedCharacters": 1362,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "contact-in-header.pdf",
      "caseId": "contact-in-header",
      "title": "Contact details in the header",
      "description": "Name and contact details live in the document header rather than the body.",
      "format": "pdf",
      "riskPatterns": [
        "header-content"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/contact-in-header.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/contact-in-header.pdf.txt",
      "fixtureSha256": "ca84d4d81b17e9bf7609ccdde806b05f1c8c3954861d96aec52356be93e30c83",
      "extractedTextSha256": "33e1349d679a7951e4301fbec0269326ddb611827df1d11bf007e5d961df6784",
      "bytes": 4392,
      "status": "preserved",
      "extractedCharacters": 1355,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "contact-in-header.docx",
      "caseId": "contact-in-header",
      "title": "Contact details in the header",
      "description": "Name and contact details live in the document header rather than the body.",
      "format": "docx",
      "riskPatterns": [
        "header-content"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/contact-in-header.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/contact-in-header.docx.txt",
      "fixtureSha256": "d20c85682a0d73b9a048c2a0dc17cc5a7e69bbd3d3ab3e932d3553bcc695ab82",
      "extractedTextSha256": "c8c7fa8061b0d9502b807e5108ca3ae2628d443b5b8db068363501809f856eb0",
      "bytes": 10678,
      "status": "content_loss",
      "extractedCharacters": 1238,
      "foundMarkers": [
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test"
      ],
      "outOfOrderMarkers": []
    },
    {
      "id": "contact-in-footer.pdf",
      "caseId": "contact-in-footer",
      "title": "Contact details in the footer",
      "description": "Contact details live in the document footer, a common source of extraction loss or reordering.",
      "format": "pdf",
      "riskPatterns": [
        "footer-content"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/contact-in-footer.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/contact-in-footer.pdf.txt",
      "fixtureSha256": "8bf2bdcef64315d24677667962588176ae4a967e8f78adc5c56d6f6e8349dd33",
      "extractedTextSha256": "33e1349d679a7951e4301fbec0269326ddb611827df1d11bf007e5d961df6784",
      "bytes": 4420,
      "status": "preserved",
      "extractedCharacters": 1355,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "contact-in-footer.docx",
      "caseId": "contact-in-footer",
      "title": "Contact details in the footer",
      "description": "Contact details live in the document footer, a common source of extraction loss or reordering.",
      "format": "docx",
      "riskPatterns": [
        "footer-content"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/contact-in-footer.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/contact-in-footer.docx.txt",
      "fixtureSha256": "939324f6a1a7a1f6fabf2b0c38fd774f3e35e047ba69d330891d7bbd58d328a6",
      "extractedTextSha256": "c8c7fa8061b0d9502b807e5108ca3ae2628d443b5b8db068363501809f856eb0",
      "bytes": 10583,
      "status": "content_loss",
      "extractedCharacters": 1238,
      "foundMarkers": [
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test"
      ],
      "outOfOrderMarkers": []
    },
    {
      "id": "two-column-sidebar.pdf",
      "caseId": "two-column-sidebar",
      "title": "Two-column sidebar",
      "description": "Contact, skills, and education appear in a narrow sidebar beside the main experience column.",
      "format": "pdf",
      "riskPatterns": [
        "two-column-reading-order"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/two-column-sidebar.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/two-column-sidebar.pdf.txt",
      "fixtureSha256": "3286a4d933ad0f4fbcc257cfcdaddb88d16ae09ee4c80d21704a00caa6462600",
      "extractedTextSha256": "fb2815547b954de2c2ecfd1dda34e89ebeaf1160925ce0e9af6948fcd3e147d7",
      "bytes": 4781,
      "status": "content_loss",
      "extractedCharacters": 1363,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [
        "Lakeview State University"
      ],
      "outOfOrderMarkers": []
    },
    {
      "id": "two-column-sidebar.docx",
      "caseId": "two-column-sidebar",
      "title": "Two-column sidebar",
      "description": "Contact, skills, and education appear in a narrow sidebar beside the main experience column.",
      "format": "docx",
      "riskPatterns": [
        "two-column-reading-order"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/two-column-sidebar.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/two-column-sidebar.docx.txt",
      "fixtureSha256": "ca217012e1bd4f763027bcc063f1420d2617643138cd9936192887f9d2f2f5a8",
      "extractedTextSha256": "481462ee71693442f94d53cbb150701983c2ef42c8b203c2d143479bb31be654",
      "bytes": 9984,
      "status": "reordered",
      "extractedCharacters": 1362,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": [
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ]
    },
    {
      "id": "table-based-layout.pdf",
      "caseId": "table-based-layout",
      "title": "Table-based layout",
      "description": "A borderless table controls alignment and may alter reading order in extracted text.",
      "format": "pdf",
      "riskPatterns": [
        "table-reading-order"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/table-based-layout.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/table-based-layout.pdf.txt",
      "fixtureSha256": "e5d214130821dcdcdd0d621fed87ea192af5758dba012f61ade1a44a56782631",
      "extractedTextSha256": "7dda050278662261f9a7132b548dc6884a26a044202891cbc940f95256604534",
      "bytes": 4530,
      "status": "preserved",
      "extractedCharacters": 1363,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "table-based-layout.docx",
      "caseId": "table-based-layout",
      "title": "Table-based layout",
      "description": "A borderless table controls alignment and may alter reading order in extracted text.",
      "format": "docx",
      "riskPatterns": [
        "table-reading-order"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/table-based-layout.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/table-based-layout.docx.txt",
      "fixtureSha256": "fad4ffce14e1e971fab03469bdb8b15fde89accc8f9cd2787b014554a5aebfe7",
      "extractedTextSha256": "7de0c1c88d5c3cdf1cafa7c7022ffa63a9ab772f5144e53a093e9ba798e28b8a",
      "bytes": 9974,
      "status": "preserved",
      "extractedCharacters": 1373,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "icon-contact-labels.pdf",
      "caseId": "icon-contact-labels",
      "title": "Icon-like contact labels",
      "description": "Short symbol-like labels precede contact values without relying on embedded images.",
      "format": "pdf",
      "riskPatterns": [
        "symbol-and-icon-labels"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/icon-contact-labels.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/icon-contact-labels.pdf.txt",
      "fixtureSha256": "7c2068a6f9fb594a1e7a1b5e9b9c08b0dd2f9d186b1b8ea3a48bf0e7b64716fa",
      "extractedTextSha256": "ab495bb61c659a1fdcb3cf0a4d51334d05218e67d8a51dae1cb200ca31845c67",
      "bytes": 4354,
      "status": "preserved",
      "extractedCharacters": 1357,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "icon-contact-labels.docx",
      "caseId": "icon-contact-labels",
      "title": "Icon-like contact labels",
      "description": "Short symbol-like labels precede contact values without relying on embedded images.",
      "format": "docx",
      "riskPatterns": [
        "symbol-and-icon-labels"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/icon-contact-labels.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/icon-contact-labels.docx.txt",
      "fixtureSha256": "cb51271ac8c97fbdf190a9b03cc5e99d932aa422bc65c2191cc56faee392b0bb",
      "extractedTextSha256": "67926183fff6963cfdc84b6bf2d65bfc7277ba61a37a531c4cd7ea95efdc3bc7",
      "bytes": 9811,
      "status": "preserved",
      "extractedCharacters": 1370,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "section-page-breaks.pdf",
      "caseId": "section-page-breaks",
      "title": "Section page breaks",
      "description": "Experience and education are split across deliberate page boundaries.",
      "format": "pdf",
      "riskPatterns": [
        "multi-page-section-breaks"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/section-page-breaks.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/section-page-breaks.pdf.txt",
      "fixtureSha256": "9e35401891a324bd9c833e8124bb64f9ef6167438c349140484611c23b968168",
      "extractedTextSha256": "33e1349d679a7951e4301fbec0269326ddb611827df1d11bf007e5d961df6784",
      "bytes": 5186,
      "status": "preserved",
      "extractedCharacters": 1355,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "section-page-breaks.docx",
      "caseId": "section-page-breaks",
      "title": "Section page breaks",
      "description": "Experience and education are split across deliberate page boundaries.",
      "format": "docx",
      "riskPatterns": [
        "multi-page-section-breaks"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/section-page-breaks.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/section-page-breaks.docx.txt",
      "fixtureSha256": "cf6c0a9c5f6ddf8af4050ba9dc94c4b38dfe8de789aa3183480e705468e8f68a",
      "extractedTextSha256": "f3bb63874b3bcea0f3fab7ea6f7e0d52b0ccfab58737fbf06fea1af40088e6ae",
      "bytes": 9804,
      "status": "preserved",
      "extractedCharacters": 1364,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "decorative-letter-spacing.pdf",
      "caseId": "decorative-letter-spacing",
      "title": "Decorative letter spacing",
      "description": "Display headings use expanded letter spacing while substantive content remains conventional.",
      "format": "pdf",
      "riskPatterns": [
        "decorative-letter-spacing"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/decorative-letter-spacing.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/decorative-letter-spacing.pdf.txt",
      "fixtureSha256": "fe7c1d818555dc69ba86b7e88330cb4bec0991e40821085afe0580a7ee8b54a4",
      "extractedTextSha256": "57e1c953df95fb9791db3d4cfe7093a520b6e467cb98235e93d57b3a3d6fe616",
      "bytes": 4425,
      "status": "content_loss",
      "extractedCharacters": 1402,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "Lakeview State University",
        "Spanish"
      ],
      "missingMarkers": [
        "EDUCATION",
        "SKILLS"
      ],
      "outOfOrderMarkers": []
    },
    {
      "id": "decorative-letter-spacing.docx",
      "caseId": "decorative-letter-spacing",
      "title": "Decorative letter spacing",
      "description": "Display headings use expanded letter spacing while substantive content remains conventional.",
      "format": "docx",
      "riskPatterns": [
        "decorative-letter-spacing"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/decorative-letter-spacing.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/decorative-letter-spacing.docx.txt",
      "fixtureSha256": "f4bbdc6b7188dacb96e8448cd29b182bcc8a2d92a4ffe07a817d16bc9a589d4f",
      "extractedTextSha256": "66479bf771b4c6a518ab89ca4fb10a883db2e50a9c7055c1ed83e17755bb7de1",
      "bytes": 9809,
      "status": "preserved",
      "extractedCharacters": 1362,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "mixed-language-headings.pdf",
      "caseId": "mixed-language-headings",
      "title": "Mixed-language headings",
      "description": "Section labels mix English and Spanish while the resume body remains English.",
      "format": "pdf",
      "riskPatterns": [
        "mixed-language-sections"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/mixed-language-headings.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/mixed-language-headings.pdf.txt",
      "fixtureSha256": "6ce739d5a523b4079d07f462f9b5d68cb8fa87706c86cc2453344f97f9ab42cb",
      "extractedTextSha256": "eb53782e5f5fec0d6b66a1e6e8f0fe28dba88dc84fbbca382dbb39b66f2b0680",
      "bytes": 4365,
      "status": "preserved",
      "extractedCharacters": 1395,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "mixed-language-headings.docx",
      "caseId": "mixed-language-headings",
      "title": "Mixed-language headings",
      "description": "Section labels mix English and Spanish while the resume body remains English.",
      "format": "docx",
      "riskPatterns": [
        "mixed-language-sections"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/mixed-language-headings.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/mixed-language-headings.docx.txt",
      "fixtureSha256": "fad17c24b886c83e0fde6b0e2b1ff3298b9f3f1446f52e627a6c88ce926c6711",
      "extractedTextSha256": "9d7939f5cfb3d57048be45b1e9d65eac19b0ab48c8972b70a00fdb758e803b29",
      "bytes": 9822,
      "status": "preserved",
      "extractedCharacters": 1402,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "dense-three-page.pdf",
      "caseId": "dense-three-page",
      "title": "Dense three-page resume",
      "description": "A dense three-page document repeats page furniture and long project notes.",
      "format": "pdf",
      "riskPatterns": [
        "dense-multi-page-content",
        "repeated-page-furniture"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/dense-three-page.pdf",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/dense-three-page.pdf.txt",
      "fixtureSha256": "5ba264ee62cff1f4bfa0a069e16371f82d20e69881f993dcd61a8638bbb2c9d3",
      "extractedTextSha256": "6db86094c41d6507478d364a72ef1b375efdc2dca24de4aeedd0bf00682bf391",
      "bytes": 8317,
      "status": "preserved",
      "extractedCharacters": 5586,
      "foundMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test",
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [],
      "outOfOrderMarkers": []
    },
    {
      "id": "dense-three-page.docx",
      "caseId": "dense-three-page",
      "title": "Dense three-page resume",
      "description": "A dense three-page document repeats page furniture and long project notes.",
      "format": "docx",
      "riskPatterns": [
        "dense-multi-page-content",
        "repeated-page-furniture"
      ],
      "fixturePath": "/research/resume-parsing-lab/2026-07-v2/fixtures/dense-three-page.docx",
      "extractedTextPath": "/research/resume-parsing-lab/2026-07-v2/results/extracted/dense-three-page.docx.txt",
      "fixtureSha256": "7ad3f3f9892142c7826f7585a28e77c6b129e48cdc2c1e565a6d675dc52e89d9",
      "extractedTextSha256": "19ab38d723edd263d91d962c572c830d7ef4ce6dfc2d3071795a7443625fc8c3",
      "bytes": 11684,
      "status": "content_loss",
      "extractedCharacters": 5082,
      "foundMarkers": [
        "PRODUCT OPERATIONS SPECIALIST",
        "Northstar Works",
        "42%",
        "18 hours",
        "EDUCATION",
        "Lakeview State University",
        "SKILLS",
        "Spanish"
      ],
      "missingMarkers": [
        "Jordan Avery",
        "jordan.avery@example.test"
      ],
      "outOfOrderMarkers": []
    }
  ],
  "files": [
    {
      "path": "fixtures/baseline-single-column.pdf",
      "mediaType": "application/pdf",
      "bytes": 4330,
      "sha256": "ca052161dd962ae540ec8e47bca87911153f46824fa073f0fe91fa7db63300eb"
    },
    {
      "path": "results/extracted/baseline-single-column.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1356,
      "sha256": "bf1c043a7393103b20489aa09a86b63c5fb74ffb532ee22305f29ef856da7db6"
    },
    {
      "path": "fixtures/baseline-single-column.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9795,
      "sha256": "df23e226289b8490f46ca5fc426d18fcc3f5a6fcc4745634e9f16538c22908ed"
    },
    {
      "path": "results/extracted/baseline-single-column.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1363,
      "sha256": "a4911223838d1453823c979938ebaf28fa76987700ff9fe94af92041b1f91b8d"
    },
    {
      "path": "fixtures/contact-in-header.pdf",
      "mediaType": "application/pdf",
      "bytes": 4392,
      "sha256": "ca84d4d81b17e9bf7609ccdde806b05f1c8c3954861d96aec52356be93e30c83"
    },
    {
      "path": "results/extracted/contact-in-header.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1356,
      "sha256": "bf1c043a7393103b20489aa09a86b63c5fb74ffb532ee22305f29ef856da7db6"
    },
    {
      "path": "fixtures/contact-in-header.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 10678,
      "sha256": "d20c85682a0d73b9a048c2a0dc17cc5a7e69bbd3d3ab3e932d3553bcc695ab82"
    },
    {
      "path": "results/extracted/contact-in-header.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1239,
      "sha256": "fee8219d989a5099cec5aa00341c7bd887578ba49b18be6fa9fe43f089ede8ed"
    },
    {
      "path": "fixtures/contact-in-footer.pdf",
      "mediaType": "application/pdf",
      "bytes": 4420,
      "sha256": "8bf2bdcef64315d24677667962588176ae4a967e8f78adc5c56d6f6e8349dd33"
    },
    {
      "path": "results/extracted/contact-in-footer.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1356,
      "sha256": "bf1c043a7393103b20489aa09a86b63c5fb74ffb532ee22305f29ef856da7db6"
    },
    {
      "path": "fixtures/contact-in-footer.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 10583,
      "sha256": "939324f6a1a7a1f6fabf2b0c38fd774f3e35e047ba69d330891d7bbd58d328a6"
    },
    {
      "path": "results/extracted/contact-in-footer.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1239,
      "sha256": "fee8219d989a5099cec5aa00341c7bd887578ba49b18be6fa9fe43f089ede8ed"
    },
    {
      "path": "fixtures/two-column-sidebar.pdf",
      "mediaType": "application/pdf",
      "bytes": 4781,
      "sha256": "3286a4d933ad0f4fbcc257cfcdaddb88d16ae09ee4c80d21704a00caa6462600"
    },
    {
      "path": "results/extracted/two-column-sidebar.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1364,
      "sha256": "837963ff6d675c7afc98f1e1a6fd729cf23b5371398fd9aca2dde7ebe5855ae1"
    },
    {
      "path": "fixtures/two-column-sidebar.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9984,
      "sha256": "ca217012e1bd4f763027bcc063f1420d2617643138cd9936192887f9d2f2f5a8"
    },
    {
      "path": "results/extracted/two-column-sidebar.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1363,
      "sha256": "5f98578482b323f37e4d222fe65f1ae07b69101999d39f149b69eeeaa0958589"
    },
    {
      "path": "fixtures/table-based-layout.pdf",
      "mediaType": "application/pdf",
      "bytes": 4530,
      "sha256": "e5d214130821dcdcdd0d621fed87ea192af5758dba012f61ade1a44a56782631"
    },
    {
      "path": "results/extracted/table-based-layout.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1364,
      "sha256": "b8048a4031941da13268a5761a9285a48c6688ecee50c140c8300a4c0be639af"
    },
    {
      "path": "fixtures/table-based-layout.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9974,
      "sha256": "fad4ffce14e1e971fab03469bdb8b15fde89accc8f9cd2787b014554a5aebfe7"
    },
    {
      "path": "results/extracted/table-based-layout.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1374,
      "sha256": "30ac3cfcd17361f45a5c939b1d2c711ba11b982bc8d97b10ac4da13b518b79e0"
    },
    {
      "path": "fixtures/icon-contact-labels.pdf",
      "mediaType": "application/pdf",
      "bytes": 4354,
      "sha256": "7c2068a6f9fb594a1e7a1b5e9b9c08b0dd2f9d186b1b8ea3a48bf0e7b64716fa"
    },
    {
      "path": "results/extracted/icon-contact-labels.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1358,
      "sha256": "5c6c9b0824e5db90ad748ac84ce090c799f7ae25e1e8688260daf75f4835454a"
    },
    {
      "path": "fixtures/icon-contact-labels.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9811,
      "sha256": "cb51271ac8c97fbdf190a9b03cc5e99d932aa422bc65c2191cc56faee392b0bb"
    },
    {
      "path": "results/extracted/icon-contact-labels.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1371,
      "sha256": "3c06eb9f8fe41c8b8ab49a24b25eb18fa8bf0b13fab696075e71642cf37e40b6"
    },
    {
      "path": "fixtures/section-page-breaks.pdf",
      "mediaType": "application/pdf",
      "bytes": 5186,
      "sha256": "9e35401891a324bd9c833e8124bb64f9ef6167438c349140484611c23b968168"
    },
    {
      "path": "results/extracted/section-page-breaks.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1356,
      "sha256": "bf1c043a7393103b20489aa09a86b63c5fb74ffb532ee22305f29ef856da7db6"
    },
    {
      "path": "fixtures/section-page-breaks.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9804,
      "sha256": "cf6c0a9c5f6ddf8af4050ba9dc94c4b38dfe8de789aa3183480e705468e8f68a"
    },
    {
      "path": "results/extracted/section-page-breaks.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1365,
      "sha256": "4f8a587d5d29889a037a705e41ee66a455a5cafab95fec929bd7cf54c0a58b1e"
    },
    {
      "path": "fixtures/decorative-letter-spacing.pdf",
      "mediaType": "application/pdf",
      "bytes": 4425,
      "sha256": "fe7c1d818555dc69ba86b7e88330cb4bec0991e40821085afe0580a7ee8b54a4"
    },
    {
      "path": "results/extracted/decorative-letter-spacing.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1403,
      "sha256": "3c03820cd81809134544d5625310c52bb6278c8c507b1fd48ca3953cd3a3eeca"
    },
    {
      "path": "fixtures/decorative-letter-spacing.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9809,
      "sha256": "f4bbdc6b7188dacb96e8448cd29b182bcc8a2d92a4ffe07a817d16bc9a589d4f"
    },
    {
      "path": "results/extracted/decorative-letter-spacing.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1363,
      "sha256": "a4911223838d1453823c979938ebaf28fa76987700ff9fe94af92041b1f91b8d"
    },
    {
      "path": "fixtures/mixed-language-headings.pdf",
      "mediaType": "application/pdf",
      "bytes": 4365,
      "sha256": "6ce739d5a523b4079d07f462f9b5d68cb8fa87706c86cc2453344f97f9ab42cb"
    },
    {
      "path": "results/extracted/mixed-language-headings.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1396,
      "sha256": "ef33fcb8a8e480e5de49eb568ba927d6aeff07dc7848ae466db6477aff5c48ef"
    },
    {
      "path": "fixtures/mixed-language-headings.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 9822,
      "sha256": "fad17c24b886c83e0fde6b0e2b1ff3298b9f3f1446f52e627a6c88ce926c6711"
    },
    {
      "path": "results/extracted/mixed-language-headings.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 1403,
      "sha256": "5f30bf8933077d1c5eaf28f0a05656703bc535f46c946c457351cc51456587bf"
    },
    {
      "path": "fixtures/dense-three-page.pdf",
      "mediaType": "application/pdf",
      "bytes": 8317,
      "sha256": "5ba264ee62cff1f4bfa0a069e16371f82d20e69881f993dcd61a8638bbb2c9d3"
    },
    {
      "path": "results/extracted/dense-three-page.pdf.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 5587,
      "sha256": "1274e55dd90855a7308ed051f11879fd91abdd9da27ea4ddbcacd51d060c8148"
    },
    {
      "path": "fixtures/dense-three-page.docx",
      "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
      "bytes": 11684,
      "sha256": "7ad3f3f9892142c7826f7585a28e77c6b129e48cdc2c1e565a6d675dc52e89d9"
    },
    {
      "path": "results/extracted/dense-three-page.docx.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 5083,
      "sha256": "9a92f59456188ffa2d1ab989e88e26d8d3e483a725bba2cc06b05499fad8e440"
    },
    {
      "path": "results/results.json",
      "mediaType": "application/json",
      "bytes": 22292,
      "sha256": "76024ff82686a938680d96c5d8bcb70acd4e82bbe5dda7b25ad6a9a676ac210d"
    },
    {
      "path": "results/results.csv",
      "mediaType": "text/csv; charset=utf-8",
      "bytes": 12504,
      "sha256": "d83f5e5b7fd579434b39ff817486980a517ca82429f0a9fc2e3100d62499848b"
    },
    {
      "path": "methodology.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 2313,
      "sha256": "85188df40b2d6e2016231e6ac2619af68a6589ee1843d20aa89c8927fbc0e53b"
    },
    {
      "path": "README.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 733,
      "sha256": "6211e1b404067d3597502d5db05c2a46b00b91587d64f705effd4ac73584673e"
    },
    {
      "path": "REUSE.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 593,
      "sha256": "4cedaafcecf07a8a2a1aca78daedb14e2eb74cdd95e23a6f852d6cab301505d4"
    },
    {
      "path": "workshop/workshop-slides.pdf",
      "mediaType": "application/pdf",
      "bytes": 18451,
      "sha256": "0a3a84314c30803d42c8cad023f35f1ec5247584a3552feefda3073fe378d6a0"
    },
    {
      "path": "workshop/facilitator-guide.pdf",
      "mediaType": "application/pdf",
      "bytes": 11206,
      "sha256": "880be20abf48b4ff1c60e307d2f469842f00920484830b2fa57d680ca2c2675f"
    },
    {
      "path": "workshop/workshop-source.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 5524,
      "sha256": "8fa9782fe2b9bf2f62ce7af71de06dcd80ddef048e823d3da28e3d3cce79f321"
    },
    {
      "path": "workshop/slide-text.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 2793,
      "sha256": "f370ee3e241674bed5216c9683cfb913d293e64eaef3c96da838c40f501a3f3a"
    },
    {
      "path": "workshop/paired-fixture-exercise.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 1109,
      "sha256": "18c05a62b8a9d74a02deeacc6ffa7ab9406a4fdc4dd8de21df0b2e0c3b0e4a06"
    },
    {
      "path": "workshop/qr-resume-parsing-lab.png",
      "mediaType": "image/png",
      "bytes": 4851,
      "sha256": "f85b427b3d0a445bd38fec8d1b4c2adb7a08f69989e65590913a15aeb99d6bc0"
    },
    {
      "path": "workshop/qr-destination.txt",
      "mediaType": "text/plain; charset=utf-8",
      "bytes": 115,
      "sha256": "7eb8c9a962ee2a8b307d20e46ce0ecf5cefb7388ac306dc1e6bca61ca269eec5"
    },
    {
      "path": "workshop/REUSE.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 593,
      "sha256": "4cedaafcecf07a8a2a1aca78daedb14e2eb74cdd95e23a6f852d6cab301505d4"
    },
    {
      "path": "downloads/resume-parsing-lab-corpus-2026-07-v2.zip",
      "mediaType": "application/zip",
      "bytes": 151752,
      "sha256": "e34c0af2f4c079df46c0a5933486775ee6a5f0e25f9aca8c69cc6fe63348cf5f"
    },
    {
      "path": "downloads/resume-parsing-workshop-kit-2026-07-v2.zip",
      "mediaType": "application/zip",
      "bytes": 88653,
      "sha256": "ab9ae9da1ed89ac265c08b7645c022a0c7b3c07e491d98f040a0d79fc47768b6"
    }
  ],
  "downloads": [
    {
      "id": "corpus",
      "label": "Complete synthetic corpus",
      "path": "/research/resume-parsing-lab/2026-07-v2/downloads/resume-parsing-lab-corpus-2026-07-v2.zip",
      "mediaType": "application/zip",
      "bytes": 151752,
      "sha256": "e34c0af2f4c079df46c0a5933486775ee6a5f0e25f9aca8c69cc6fe63348cf5f"
    },
    {
      "id": "results_csv",
      "label": "Observed results (CSV)",
      "path": "/research/resume-parsing-lab/2026-07-v2/results/results.csv",
      "mediaType": "text/csv; charset=utf-8",
      "bytes": 12504,
      "sha256": "d83f5e5b7fd579434b39ff817486980a517ca82429f0a9fc2e3100d62499848b"
    },
    {
      "id": "methodology",
      "label": "Methodology and limitations",
      "path": "/research/resume-parsing-lab/2026-07-v2/methodology.md",
      "mediaType": "text/markdown; charset=utf-8",
      "bytes": 2313,
      "sha256": "85188df40b2d6e2016231e6ac2619af68a6589ee1843d20aa89c8927fbc0e53b"
    },
    {
      "id": "workshop_slides",
      "label": "Workshop slide deck",
      "path": "/research/resume-parsing-lab/2026-07-v2/workshop/workshop-slides.pdf",
      "mediaType": "application/pdf",
      "bytes": 18451,
      "sha256": "0a3a84314c30803d42c8cad023f35f1ec5247584a3552feefda3073fe378d6a0"
    },
    {
      "id": "facilitator_guide",
      "label": "Facilitator guide",
      "path": "/research/resume-parsing-lab/2026-07-v2/workshop/facilitator-guide.pdf",
      "mediaType": "application/pdf",
      "bytes": 11206,
      "sha256": "880be20abf48b4ff1c60e307d2f469842f00920484830b2fa57d680ca2c2675f"
    },
    {
      "id": "workshop_bundle",
      "label": "Complete workshop bundle",
      "path": "/research/resume-parsing-lab/2026-07-v2/downloads/resume-parsing-workshop-kit-2026-07-v2.zip",
      "mediaType": "application/zip",
      "bytes": 88653,
      "sha256": "ab9ae9da1ed89ac265c08b7645c022a0c7b3c07e491d98f040a0d79fc47768b6"
    },
    {
      "id": "workshop_qr",
      "label": "Workshop QR code",
      "path": "/research/resume-parsing-lab/2026-07-v2/workshop/qr-resume-parsing-lab.png",
      "mediaType": "image/png",
      "bytes": 4851,
      "sha256": "f85b427b3d0a445bd38fec8d1b4c2adb7a08f69989e65590913a15aeb99d6bc0"
    }
  ]
}
