VERSIONED EVIDENCE · COMPILED 16 NOVEMBER 2026
What survives
an edit?
Observed watermark recovery, with the version, input, transformation and denominator kept together. Current-release checks and historical experiments have separate tables.
Download structured results JSON ↗ · Download recovery-table CSV ↗ · Inspect embedded C2PA separately ↗
CURRENT RELEASE
Current release · 0.7.3a4
CJ-05, 15 November 2026. Linux m6a.large, 2 CPU / 4 GiB, two threads, verification scope current. Two image fixtures and seven video fixtures; repeated checks are not additional source scenes. No recompression, crop or social-platform survival rate is measured by this cohort.
| Scenario / exact transform | Image | Economy5s | Economy2s | Resilient |
|---|---|---|---|---|
| Image · Unchanged exportA separate blind verifier reads the accepted SDK output. Two procedural inputs: 1024×683 PNG and 2048×1152 JPEG; one first job + three resident repeats per input. | 8 / 8 recoveredExpected ID | Not applicable | Not applicable | Not applicable |
| Image · Metadata removedLossless PNG re-save; JPEG input becomes PNG. Decoded RGB pixels unchanged. Two procedural inputs: 1024×683 PNG and 2048×1152 JPEG; one first job + three resident repeats per input. | 8 / 8 recoveredExpected ID | Not applicable | Not applicable | Not applicable |
| Video · Unchanged exportA separate blind verifier reads the accepted SDK output. Seven procedural SDR clips, 720p/1080p, 5/10/15 s, 24/30/30000:1001 fps, including HEVC input; four checks per fixture/profile. | Not applicable | 28 / 28 recoveredExpected ID | 28 / 28 recoveredExpected ID | 28 / 28 recoveredExpected ID |
| Video · Metadata removedMP4 stream-copy remux; compressed video essence unchanged. No re-encoding. Seven procedural SDR clips, 720p/1080p, 5/10/15 s, 24/30/30000:1001 fps, including HEVC input; four checks per fixture/profile. | Not applicable | 28 / 28 recoveredExpected ID | 28 / 28 recoveredExpected ID | 28 / 28 recoveredExpected ID |
HISTORICAL · NOT RETESTED ON CURRENT RELEASE
Historical paired transforms · 0.7.1a1
Linux/m6a.large; code 35cf34d4b794f0ba65588ba6f8d0b49f9040a24c; 2 CPU / 6 GiB container. Two 720p24 stock scenes (crowd, face). Blind detector receives no expected ID, preset or schedule. Seeks use the 24 fps frame grid. These observations are not a re-test of 0.7.3a4.
| Scenario / exact transform | Economy5s | Economy2s | Resilient |
|---|---|---|---|
| Fresh 10 s exportNo later transform; 1280×720, 24 fps. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| Fresh 3 s exportThree-second rendition prepared before marking. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| H.264 CRF23 · 10 sIdentity transcode of a marked ten-second export. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| H.264 CRF23 · 3 sIdentity transcode of the marked three-second export. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| Keep seconds 1–4Three-second excerpt from a marked ten-second export. | 0 / 2 recovered2 not_found | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| Keep seconds 0.2–1.8Excerpt deliberately between Economy marking windows. | 0 / 2 recovered2 not_found | 0 / 2 recovered2 not_found | 2 / 2 recoveredExpected ID |
| Trim 0.2 s from the startLeading trim of a marked three-second export; not an intact short export. | 0 / 2 recovered2 not_found | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
HISTORICAL · NOT RETESTED ON CURRENT RELEASE
Historical codec and geometry checks · 0.7.1a0
Linux/Oregon m6a.large, 2 CPU / 6 GiB. Code 4933202. Two stock scenes; NTSC rows use two rates (four cases/profile). Portrait rows use two cases/profile. Historical runtime and decoder; not a current-release durability score.
| Scenario / exact transform | Economy5s | Economy2s | Resilient |
|---|---|---|---|
| Fresh NTSC exportSix seconds, 720p; 24000/1001 and 30000/1001 fps. | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID |
| H.264 CRF28Recompression of the marked NTSC exports. | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID |
| 90%-dimension center cropRetain 90% of width and height, then resize. This is not a 16:9-to-9:16 crop. | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID | 4 / 4 recoveredExpected ID |
| 640×360 + H.264 CRF32Combined downscale and severe compression. The written record supplies the per-mode recovery split; the summary does not split every unrecovered result into not_found versus incomplete. | 0 / 4 recoveredUnrecovered status not split | 0 / 4 recoveredUnrecovered status not split | 3 / 4 recoveredUnrecovered status not split |
| Portrait rendition prepared before markingTwo source scenes; square-pixel portrait input prepared before export. Separate from cropping a previously marked landscape file. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
| Portrait export → 540×960, CRF28Two source scenes; square-pixel portrait input prepared before export. Separate from cropping a previously marked landscape file. | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID | 2 / 2 recoveredExpected ID |
HISTORICAL · NOT RETESTED ON CURRENT RELEASE
Historical deliberate-removal checks · 0.7.1a1
Same Linux two-scene cohort. Image PSNR 45.03–49.62 dB relative to marked images. A separate video result reads crowd only through aggregate recovery. This is an adversarial scenario, not an ordinary delivery transform or an attack-proof guarantee.
| Scenario / exact transform | Image | Economy5s | Economy2s | Resilient |
|---|---|---|---|---|
| Image · identity controlRGB PNG with C2PA stripped; two source frames × two IDs. | 4 / 4 recoveredExpected ID | Not applicable | Not applicable | Not applicable |
| Image · public TrustMark removerSame paired images; C2PA stripped in both control and treatment. Four trials from two scenes, not four independent images. | 0 / 4 recoveredUnrecovered status not split | Not applicable | Not applicable | Not applicable |
| Resilient video · identity controlTwo ten-second 720p24 scenes; matched codec/color path. | Not applicable | Not evaluated here | Not evaluated here | 2 / 2 recoveredExpected ID |
| Resilient video · public remover240 remover calls per scene. Crowd recovered by aggregation after full scan; face returned not_found. Economy video not tested in this paired remover trial. | Not applicable | Not evaluated here | Not evaluated here | 1 / 2 recovered1 not_found |
CURRENT RELEASE · 0.7.3a4
A negative and an unfinished scan differ.
Same CJ-05 procedural inputs, first job plus three resident repeats. The separate 60-second control has one cold and one resident run. No supported ID in a completed current-scope scan is not proof of human creation or a population false-positive estimate.
| Inputs / scope | Completed result | Unfinished checks |
|---|---|---|
| ImageTwo procedural images, four checks/input. | 8 / 8 completed negatives | 0 incomplete |
| VideoSeven procedural clips, four checks/input. The 1080p/15 s NTSC negative exhausts its budget. | 24 / 28 completed negatives | 4 incomplete |
| 60 s video · separate budget control | 0 / 2 completed negatives | 2 incomplete |
RESEARCH ONLY · HISTORICAL 0.7.1a0
Letterbox recovery is a separate research result.
Two landscape stock scenes × three profiles, placed inside 720×1280 letterbox frames with a 720×406 active picture. A bounded FFmpeg cropdetect probe restored the active region before a separate decode. This ROI path is not enabled in the qualified public verifier.
| Decoder input | Observed ID recovery |
|---|---|
| Full letterboxed frame | 0 / 6 recovered |
| FFmpeg cropdetect ROI | 6 / 6 recovered |
These are six correlated cases, not six independent sources or evidence that deleted pixels can be restored. A native portrait export and a landscape-to-portrait crop are different operations. Source record ↗
NOT ESTABLISHED BY THIS EVIDENCE
Keep the remaining scope visible.
- Matched current-release delivery series. The indexed current 0.7.3a4 series covers intact output and metadata loss. It does not retest every historical recompression, resize, crop, trim or remover result on representative content.
- Named social platforms. No Instagram, TikTok or YouTube Shorts round-trip result is published here.
- Population calibration. A held-out false-positive rate and general detection probability are not established by the small/repeated fixtures.
- Your production pipeline. Public CA/TSA trust, visual quality, actual app/CDN delivery and workload capacity need their own qualification.
Known crop/remover and window-free-excerpt limits remain relevant. Their historical counts are not silently relabelled as current-version measurements. No profile, including Resilient, is described as attack-proof.
Methods, versions and retained records
Current 0.7.3a4: CJ-05 methods and full measurements; two procedural images and seven silent SDR fixtures. Whole-file watermark checks and metadata recovery are separate from proof of asset authenticity. 341 installed-media tests are release qualification, not 341 durability attacks.
Historical 0.7.1a1: Complete paired-media protocol · Machine-readable observations. Two 1280×720/24 fps stock scenes, prepared 3 s renditions, development credentials and offline Linux testing.
Historical 0.7.1a0: Codec/geometry protocol · Machine-readable observations · Spatial research and limitations.
Historical source files are retained at SDK documentation commit f90a59917b850c3aee36bfc1ac6a506bed17b571. Source paths and SHA-256 manifest ↗. The tables are generated from these records and the current CSV; no new media experiment was run to produce this page.
Why the tables use this structure
Each cohort keeps one runtime/corpus definition, named transformations and raw counts, with machine-readable data beside the human summary. This follows the reproducible per-augmentation reporting approach of VideoSeal evaluation. Captions and explicit row/column headers follow W3C table guidance. Vendor scores are not imported into Ariadne results.