START WITH THE PRODUCT STEPS Read START-HERE.txt first. It states the actual source acquisition, access/privacy limits, manual field mapping and exact next prompt. The original file templates and synthetic examples below are supporting review aids. Some paths need separately supplied documents or source text; a blank worksheet is not a native export or completed integration. S14: Map exact duplicate documents without deleting evidence Starter kit Status: Proposed / not tested PURPOSE New production receipt or document-review preparation → group administrator-generated exact whole-file hashes while preserving provenance → read-only duplicate-group map, unique-file index and explicitly unresolved page-level/near-duplicate questions. PREREQUISITES 1. Approved local IT-generated manifest: immutable file ID, source batch, original path/name, size, SHA-256, custodian, family/attachment ID and receipt timestamp. Excel/Power Query groups exact hashes; an assistant explains exceptions. No document-content uploads are required. 2. Synthetic files first. Real use requires firm-approved access, privacy, processing terms, retention controls, export coverage and a named reviewer. 3. Prepare any required original files or rendered evidence separately. This kit does not configure accounts, connectors or live actions. FILES AND FORMATS file-manifest.csv: file_id, source_batch, original_path, original_name, size_bytes, sha256, custodian_alias, family_id, received_at scope.txt: approved repository, export coverage, hash method and unresolved page-level duplicates Files without .example are blank input worksheets; CSV templates contain headers only. .example files contain invented records for the dry run. Text input .txt files contain blank labeled fields. Use the original base filename when supplying an example to the prompt, or explicitly map the example filename to that input. CSV files are UTF-8 with comma delimiters, quoted fields where needed, and CRLF row endings. Preserve identifiers as text when importing into Excel. Blank means missing or unresolved, never a zero or a pass. Multi-value fields use a pipe only where the fixture scope says so. SETUP AND DRY RUN 1. Copy this kit to an approved working folder. Keep examples separate from any real exports. Do not upload client, privileged, personal, credential or financial-account data to an unapproved service. 2. Read the .example text policy/scope files and all .example.csv inputs together. They define this fixture only. For a real pilot, fill the blank templates from approved exports without changing headers and obtain approved policy values. 3. Use native read-only exports, exact joins and arithmetic for deterministic checks. This kit includes an advanced local snapshot helper. It requires authorized IT review and a synthetic validation before use; it was statically reviewed but not runtime-tested. Follow START-HERE.txt for its fixed-drive, stable-snapshot and secret-exclusion limits. 4. Give only the approved prepared inputs to a firm-approved text assistant and use the recipe prompt below. Keep source IDs, source row numbers and unresolved evidence visible. 5. Compare the proposed result with expected-fixture-result.txt. Verify every listed issue and that the prompt invents no missing evidence. The expected file describes assertions, not a performed workflow run. 6. Have the named reviewer check source evidence and record remaining questions before any separately authorized action. RECIPE PROMPT Group this sanitized manifest by exact SHA-256 value and file size. Retain every file ID, source batch, custodian and family relationship. Output exact whole-file duplicate groups and an inventory of files not grouped. Flag missing hashes and inconsistent sizes. Do not infer that repeated pages are duplicates, that identical copies are dispensable, or that any file should be withheld, deleted or excluded from production. Produce a review map only. INPUTS file-manifest.csv: file_id, source_batch, original_path, original_name, size_bytes, sha256, custodian_alias, family_id, received_at scope.txt: approved repository, export coverage, hash method and unresolved page-level duplicates OUTPUT duplicate-map.csv: group_id, file_id, source_batch, sha256, size_bytes, original_path, custodian_alias, family_id, evidence_conflict, review_note. Preserve every file and report missing or inconsistent hashes. Use only these synthetic or firm-approved inputs and preserve source row/page IDs. Keep missing or conflicting evidence unresolved. Return a draft for the named reviewer. Do not send messages, connect accounts, change records or permissions, move money, or make legal decisions. Keep source files unchanged. List missing prerequisites before continuing. REVIEW CHECKLIST [ ] Headers match the exact input schema and the export covers the stated scope [ ] Synthetic example files were used alone for the first dry run [ ] Every output finding retains its original source ID/row/page reference [ ] Missing keys, contradictions, unavailable originals and ambiguous dates remain unresolved [ ] Every expected fixture finding is present; no live action or unsupported result is claimed [ ] Responsible reviewer checks the original records before a real deployment RECIPE-SPECIFIC REVIEW Litigation staff verifies samples and all provenance. Test two differently named identical files, two PDFs differing by one page and identical content in different families. This assists navigation, not discovery decisions. Local research batch discovery-inventory evidence can strengthen this entry rather than become a separate duplicate-detection entry. VALIDATION Exact CSV header order, field counts, serialized round-trip values and fixture semantics were checked during kit preparation. This does not test OCR, a vendor integration, a model response or end-to-end reliability. All data and identifiers are synthetic. Dates are fixed fixture dates, not current monitoring results.