Acquisition position
Carl Malmsten · Paintings · Stockholms Auktionsverk Sickla
Acquisition position
Potential market value
Evidence strength
Market anomaly
Risk profile
Investigation rationale
Decision guardrails
Visual laboratory
Object record
Rygghöjd 84 cm, sitthöjd 44 cm.
Identity resolution
Ranked from independent evidence. Confirmation or rejection becomes controlled training data.
Run global research after adding the clearest available front, back, marks and label images.
Closed deal feedback
Enter the verified hammer price after the auction closes. Only verified outcomes become calibration data.
Learning guardrail
Global research evidence
Run global research to search museum and authority collections.
Comparable logic
| Comparable ID | Match | Price | Reasons |
|---|---|---|---|
| 1851 | 79% | 2200.0 SEK | identity 100%, material 45%, size 62%, title 100% |
| 3441 | 78% | 2655.0 SEK | identity 100%, material 45%, size 62%, title 90% |
| 2270 | 76% | 3450.0 SEK | identity 100%, material 45%, size 62%, title 77% |
| 971 | 76% | 7000.0 SEK | identity 100%, material 45%, size 62%, title 75% |
| 3913 | 76% | 5600.0 SEK | identity 100%, material 45%, size 62%, title 74% |
| 258 | 76% | 5555.0 SEK | identity 100%, material 45%, size 62%, title 73% |
| 1636 | 75% | 650.0 SEK | identity 100%, material 45%, size 62%, title 67% |
| 1284 | 74% | 10600.0 SEK | identity 100%, material 45%, size 62%, title 63% |
Automatic signature module
The local engine detects and isolates candidate regions, searches the trusted mark library and runs conservative signature forensics. Optional AI interprets unreadable regions and creates research queries without changing the forensic verdict.
The module runs during normal analysis when a local image is available.
Marks laboratory
110 independent methods generate cleanup variants, stroke and symbol descriptors, library matches, trust controls and conflict warnings.
Signature forensics
This does not declare a signature genuine. It measures fit against a multi-source reference set, confusing signers and natural variation.
Run mark matching first, then compare the questioned signature against a sufficiently broad trusted reference set.