Unverified50% confidenceConceptExact time
Orthographic perturbation refers to applying controlled variations to the surface written form of input text during training, such as randomly removing, replacing or inserting Ruby annotations, so that the model sees multiple representations and does not over-rely on a single input format.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMetalinguistic prompting requires the model to switch from a text-generating mode to a text-evaluating mode, a mode shift that is not directly covered by the pretraining objective.72% similarUnverifiedProsodic event textualization encodes prosodic events such as pauses and word lengthening as explicit tokens, and uses a duration-aware bounded repetition mechanism to represent event intensity.70% similarUnverifiedEmbedding models are trained to bring texts with similar meaning close together, so they smooth out character sequences that carry no semantics, such as random product IDs, making it hard for semantic search to match such queries exactly.70% similarUnverifiedTextGrain forms patterns recognizable by detection tools through fine-tuning word choices, but editing, translation, or the use of very short excerpts may weaken the signal.70% similarUnverifiedThe draft sources of SuffixDecoding and prompt-lookup decoding are static or semi-static text and are unaware of changes in the policy distribution during training.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138201API
curl https://kongchang.com/api/v1/knowledge/claims/1138201MCP
get_claim(id=1138201)