Generalization dynamics are strongly correlated across paraphrases of the same dataset, much more than between SST-2 and IMDB. Original versus paraphrase correlations are 0.96 for SST-2 and 0.97 for IMDB; within-dataset paraphrase pairs are printed as 1.00.

Generalization dynamics are strongly correlated across paraphrases of the same dataset, much more than between SST-2 and IMDB. Original versus paraphrase correlations are 0.96 for SST-2 and 0.97 for IMDB; within-dataset paraphrase pairs are printed as 1.00. · CiteArk

Measurement results

0/15 assessed

0 supported0 disputed or conflicting15 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
dataset1: flipped-sst2 · dataset2: sst2-paraphrase-1	0.96 dimensionless	—	Not assessed
dataset1: flipped-sst2 · dataset2: sst2-paraphrase-2	0.96 dimensionless	—	Not assessed
dataset1: flipped-sst2 · dataset2: flipped-imdb	0.43 dimensionless	—	Not assessed
dataset1: flipped-sst2 · dataset2: imdb-paraphrase-1	0.35 dimensionless	—	Not assessed
dataset1: flipped-sst2 · dataset2: imdb-paraphrase-2	0.35 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-1 · dataset2: sst2-paraphrase-2	1 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-1 · dataset2: flipped-imdb	0.34 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-1 · dataset2: imdb-paraphrase-1	0.37 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-1 · dataset2: imdb-paraphrase-2	0.37 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-2 · dataset2: flipped-imdb	0.36 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-2 · dataset2: imdb-paraphrase-1	0.37 dimensionless	—	Not assessed
dataset1: sst2-paraphrase-2 · dataset2: imdb-paraphrase-2	0.37 dimensionless	—	Not assessed

Generalization dynamics are strongly correlated across paraphrases of the same dataset, much more than between SST-2 and IMDB. Original versus paraphrase correlations are 0.96 for SST-2 and 0.97 for IMDB; within-dataset paraphrase pairs are printed as 1.00.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results