DSF-AI — Validation Evidence

Validation Evidence

Every prediction is tested against published experimental measurements. Zero free parameters. Zero exclusions.

Experiments validated

6.5%

Average error

Free parameters

Elements tested

Property types

Exclusions

All predictions use tabulated physical constants (NIST, CRC Handbook) as inputs. No curve fitting. No training data. No adjustable parameters. The same geometric framework predicts all four property types.

Magnetic Moments (μ_B/atom)

Validated for Fe, Co, Ni clusters (13-700 atoms) and Mn (5-19 atoms).

Cluster	DSF-AI	Experiment	Error	Source
Fe₁₃	2.500	2.500	0.0%	Billas et al., PRL 1993
Co₁₃	2.000	2.000	0.0%	Billas et al., PRL 1993
Ni₁₃	0.913	0.900	1.4%	Apsel et al., PRL 1996
Fe₅₅	2.40	2.4	~0%	Billas et al., Science 1994
Co₅₅	1.85	1.9	2.6%	Billas et al., Science 1994
Ni₅₅	0.75	0.75	0.0%	Apsel et al., PRL 1996
Fe₁₄₇	2.35	2.35	~0%	Billas et al., Science 1994
Co₁₄₇	1.78	1.8	1.1%	Billas et al., Science 1994
Ni₁₄₇	0.68	0.68	0.0%	Apsel et al., PRL 1996
Fe₇₀₀	2.25	2.25	~0%	Billas et al., Science 1994

Electron Affinity (eV)

Validated for Au (N=3-20), Ag (N=3-10), Cu (N=5-10).

Cluster	DSF-AI	Experiment	Error	Source
Au₁₃	3.71	3.80	2.4%	Taylor et al., JCP 1992
Au₇	3.52	3.46	1.7%	Taylor et al., JCP 1992
Au₅	3.36	3.09	8.7%	Taylor et al., JCP 1992
Ag₁₃	2.69	2.50	7.6%	Ho et al., JCP 1990
Ag₇	2.38	2.40	0.8%	Ho et al., JCP 1990
Cu₁₃	2.94	2.85	3.2%	Ho et al., JCP 1990

Seebeck Coefficient (μV/K)

Validated against DFT calculations and experimental measurements.

Cluster	Lattice	DSF-AI	Reference	Error	Source
Au₁₃	Cubic	+87.6	+93	5.8%	Kurelchuk et al., 2019

240 additional predictions available for all 23 d-metals at 5 cluster sizes and 2 lattice types. Try the screener.

HOMO-LUMO Gap (eV)

Cluster	DSF-AI	Experiment	Error	Source
Au₁₃	0.648	0.650	0.3%	Guvelioglu et al., PRL 2005

Phase Transition Detection (CSV Analysis)

The structural analysis engine was tested on 6 phase transitions across 5 materials spanning 4 physical phenomena and 2 measurement types.

Material	Known Transition	Type	Detected?	Precursor Lead
YBa₂Cu₃O₇	T_c = 93 K	High-T_c superconductor	Yes	13 K
MgB₂	T_c = 39 K	Conventional superconductor	Yes	18 K
CsV₃Sb₅	T_c = 2.5 K	Kagome superconductor	Yes	—
VO₂	T_MIT = 340 K	Metal-insulator	Yes	20 K
BaTiO₃	T_Curie = 393 K	Ferroelectric	Yes	22 K
FeSe/STO	T_c = 65 K	Iron-based superconductor	Yes	20 K
Pharma DSC	5 transitions	DSC polymorph screening	5 of 5	—

Same engine, zero assumptions, no per-material tuning. Click any material name for the full case study. Try it on your data.

Seebeck Sign Predictions

Bulk Seebeck sign correctly predicted for all 23 d-metals.

Element	Predicted	Bulk Measured	Match
Au	+	+1.94 μV/K	Yes
Ag	+	+1.51	Yes
Cu	+	+1.83	Yes
Pt	−	−5.28	Yes
Ni	−	−19.5	Yes
Co	−	−30.8	Yes
Fe	+	+15.0	Yes
Pd	−	−10.7	Yes
Ta	−	−2.40	Yes

23/23 elements correct. Full table includes all 3d, 4d, and 5d transition metals.