← Back to command center

CARL MALMSTEN. SOFFA, "VISNINGSÖ", EK.

Carl Malmsten · Paintings · Crafoord Auktioner Lund

Open auction lot
54
research

Acquisition position

Current all in cost

900.0 SEK
Current bid or estimate900.0 SEK
Modelled discount59.6%
Liquidity score82%

Potential market value

Specialist value interval

400 to 6100 SEK
Value confidence74%
Comparable sales30

Evidence strength

38%
Identity confidence27%
Visual match0%
External references0

Market anomaly

68%
Information gap60%
Potential undervaluation59.6%

Risk profile

8%
Authenticity risk8%
Condition risk6%

Investigation rationale

Why this may be worth considering

  • maker or artist identity supplied
  • auction estimate is materially below the specialist model
  • all in acquisition cost is at least 55 percent below modelled value
  • Large gap to recent market history
  • Estimate materially below specialist value

Decision guardrails

What must be verified

  • missing medium
  • missing dimensions
  • missing signature

Visual laboratory

Add and compare research imagery

Object record

Known facts and missing information

ArtistCarl Malmsten
MakerMissing
MediumMissing
MaterialsMissing
Dimensions? × ? × ? cm
WeightMissing g
YearMissing
EditionMissing
MarksMissing
ConditionStötmärken, repor, fläckar. Klädsel med slitage och fläckar.
ProvenanceMissing
Modelpainting_specialist 2.0.0

Med lösa plymåer klädda i blått ylletyg. Rygghöjd 78 cm, sitthöjd ca 39 cm, längd ca 200 cm, djup 73 cm. Has resale rights.

Identity resolution

Artist and maker hypotheses

Ranked from independent evidence. Confirmation or rejection becomes controlled training data.

0 candidates
Research pending

No identity hypotheses yet

Run global research after adding the clearest available front, back, marks and label images.

Closed deal feedback

Teach the valuation model

Enter the verified hammer price after the auction closes. Only verified outcomes become calibration data.

Learning guardrail

Truth before training

  • Unverified AI output is stored as a hypothesis only.
  • One-source matches are confidence capped.
  • Rejected matches improve source and feature calibration.
  • At least five verified closed sales are required per category.

Global research evidence

Reference material found elsewhere

0 references
Research pending

No external references stored

Run global research to search museum and authority collections.

Comparable logic

Specialist model explanation

Comparable IDMatchPriceReasons
1648276%12600.0 SEKidentity 100%, material 45%, size 62%, title 75%
1663375%11000.0 SEKidentity 100%, material 45%, size 62%, title 67%
1885074%2602.0 SEKidentity 100%, material 45%, size 62%, title 59%
2010574%350.0 SEKidentity 100%, material 45%, size 62%, title 58%
1896274%1500.0 SEKidentity 100%, material 45%, size 62%, title 58%
1889374%23000.0 SEKidentity 100%, material 45%, size 62%, title 58%
1659974%6100.0 SEKidentity 100%, material 45%, size 62%, title 58%
1802163%1700.0 SEKidentity 77%, material 45%, size 62%, title 47%

Automatic signature module

Every artwork image is checked for signatures and marks

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.

Candidate regions0
Signature regions0
AI enrichmentLocal only
PipelineNot run

No automatic mark result yet

The module runs during normal analysis when a local image is available.

Marks laboratory

Isolate and identify signatures, hallmarks and maker marks

110 independent methods generate cleanup variants, stroke and symbol descriptors, library matches, trust controls and conflict warnings.

Open mark library

Match an unknown mark

Upload the tightest available crop. Include a little surrounding surface so the system can separate paint, engraving, glare and background.

Add a known reference

Signature forensics

Check consistency with known genuine variation

This does not declare a signature genuine. It measures fit against a multi-source reference set, confusing signers and natural variation.

No forensic check yet

Run mark matching first, then compare the questioned signature against a sufficiently broad trusted reference set.

Open command centerDashboard Open specialist model labModels Show extreme candidatesFilter Show priority reviewsFilter