Topics — What a work is about. Nucleation holds whatever reading the owner files here, whether or not an Anthology of the SOTA topic could also hold it; instruction for ML practice belongs to the anthology (ADR-048). The words are seeded from the clusters the reading-time triage of 2026-09-25 found, and grow by decision.
Translation — translation and its theory — equivalence and its kinds (formal, dynamic, functional), interpretive resemblance, register and quality assessment, translation as skopos-driven action, intersemiotic translation between media, and what a translation preserves or changes (ADR-033).
5 of 371 QUESTION documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| QUESTION-074 | Can the transport structure fitted to single transformations predict what receivers recover under a composition of transformations no data were fitted on, within the conditions under which approximate transports compose? | From the interlocutor’s reading of PR #121 and its reconciliation, relayed by the owner on 2026-10-12. It names the test the reading takes to separate a structural formalism from a richer feature set. Its scope is set by CLAIM-260: approximate transports compose only under conditions. | Open |
| QUESTION-195 | Does prior-scored translation without parallel data keep an error bound that falls in the common ground and the size of the source language when the languages are not uniform or the translators are lossy? | Filed when the promotion audit (batch 044, ADR-047 v2) narrowed and promoted THEORY-270 to Goldwasser and co-authors’ common-nonsense theorem, re-derived from its appendix. The former promote_when, a bound outside the uniform, lossless models, is held here. | Open |
| QUESTION-339 | In a random sample of English-source human translations drawn without a named-entity or alignment filter, annotated by at least two annotators with agreement per category reported, how often per sentence does each language’s translation add material for the target audience, and are measurement and entity explicitations the most frequent types? | The promotion condition formerly on THEORY-1153, moved here when the status review of 2026-10-30 promoted it under ADR-065. PETra’s counts are within a filtered, mostly classifier-found pool labelled by one annotator; this asks for the base rate. | Open |
| QUESTION-345 | Does a learned translation metric trained on synthetic hallucinations and perturbations detect errors and hallucinations from real systems, in pairs and kinds its training did not synthesise, as well as its synthetic tests report? | The promotion condition formerly on THEORY-1151, moved here when the twenty-second status review promoted that reading of xCOMET’s §7 (ADR-065). The paper measured detection on synthetic perturbations and one benchmark; whether its robustness generalises past what its training synthesised is this question. | Open |
| QUESTION-355 | Measured against the agreement between two or more native raters scoring the same translations, how close does a reference-based metric such as COMET come to that ceiling in scoring the pragmatic adequacy of LLM translations of culturally loaded utterances into English, per pragmatic phenomenon, on items chosen in advance? | The promotion condition formerly on THEORY-1120, moved here when the twenty-fourth status review narrowed and promoted it (ADR-065 §3). With one rater per language, r = 0.81 has no ceiling to be read against. | Open |