repro-language-generation-with-replay-a-learning-theoretic-view-of-model-collapse / official_claims.json
| [ | |
| "Theorem 3.1 proves that a hypothesis class is uniformly generatable with replay if and only if it is uniformly generatable in the standard no-replay setting, with identical sample complexity, showing replay is benign for the strongest notion of generation (Theorem 3.1).", | |
| "Theorem 4.1 exhibits a countable hypothesis class that is non-uniformly generatable without replay but not non-uniformly generatable with replay, establishing a strict separation caused by replay (Theorem 4.1).", | |
| "Theorem 5.1 shows a computable algorithm using only membership queries can generate in the limit any countable hypothesis class even under replay conditions (Theorem 5.1).", | |
| "Theorem 5.6 constructs an uncountable hypothesis class that is generatable in the limit without replay but becomes non-generatable in the limit once replay is permitted (Theorem 5.6).", | |
| "Theorem 6.1 proves no deterministic generator using only membership queries can properly generate in the limit for all countable hypothesis classes (Theorem 6.1).", | |
| "Theorem 6.3 shows that even some finite hypothesis classes that are properly generatable in the limit without replay become impossible to properly generate once replay is introduced (Theorem 6.3)." | |
| ] | |