What is recorded here?
Measured FID variability on a two-axis panel of training and generation seeds for hundreds of SiT image models and introduced per-cell guidance tuning and multi-training-seed reporting recommendations.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Empirical findings concern the studied ImageNet256 SiT settings. The reported approximately1.3percent coefficient of variation is not a universal significance threshold or noise floor. Guidance optimization adds evaluation cost; this does not invent FID.
Read the original work
- The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
- Kyutai scientific publications index
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Nicolas Dufour; Alexei A. Efros; Patrick Pérez
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
FID Lottery: training-seed and sampling-seed evaluation
Measured FID variability on a two-axis panel of training and generation seeds for hundreds of SiT image models and introduced per-cell guidance tuning and multi-training-seed reporting recommendations.
Scientific scope
Empirical findings concern the studied ImageNet256 SiT settings. The reported approximately1.3percent coefficient of variation is not a universal significance threshold or noise floor. Guidance optimization adds evaluation cost; this does not invent FID.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Nicolas Dufour; Alexei A. Efros; Patrick Pérez
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.