← Files Xperiments ValidaciónARCHIVED FILE
SOURCE-PROVENANCE.json
1.82 KB · Nov 9, 2026 · 01:17 UTC
[
{
"source": "La empresa experimental.pdf",
"pages": 370,
"sha256": "2072fdbdbfe83aed92eb08a469df179db5298f59dbfe1bebc4c31a7977284b94",
"extraction": "Tesseract 5.4 spa+eng, 150 dpi, rotation 90 clockwise",
"low_text_pages": [
17,
18,
19,
21,
67,
93,
95,
117,
151,
195,
217,
219,
257,
273,
287,
307,
361
],
"characters": 610555
},
{
"source": "GTM-espanol.pdf",
"pages": 291,
"sha256": "92a91c133af1707ca2a2c4478d81159af9d2b21b22f8609d8732c2de6db16ba0",
"extraction": "PyMuPDF text extraction",
"low_text_pages": [],
"characters": 675379
},
{
"source": "The mom test.pdf",
"title": "El Mom Test",
"author": "Rob Fitzpatrick",
"translator": "Verónica Torras",
"pages": 105,
"sha256": "8c02efd74aea8ca965dd610c1d4cfb8a79ab91c769c5e8b0a0bca094261da3a9",
"source_bytes": 32293719,
"extraction": "Tesseract 5.4.0 spa+eng psm3; embedded JPEG screenshots enlarged 2x; TSV coordinate-based column ordering; targeted visual corrections logged.",
"characters": 239287,
"characters_excluding_repetitions": 218233,
"low_text_pages": [
1,
2
],
"duplicate_pages": [
95,
96,
97,
98,
99,
100,
101,
102,
103,
104,
105
],
"duplicate_of_pdf_page": 94,
"source_pdf_preserved_at": "skills/customer-discovery/references/source/the-mom-test-original.pdf",
"full_text_at": "skills/customer-discovery/references/full-text.md",
"audit_at": "skills/customer-discovery/references/ocr-pages.json",
"coverage": "All 105 pages of supplied PDF processed; no claim of completeness against an external edition or character-perfect OCR.",
"integrated_on": "2026-10-15"
}
]
SHA-256: 92376fd68cc619b8d96bbce5b3ad1d2c55c13a3ce2231b81848ac9cf11b3f622