摘要：Oberauer (2019) suggested that the working memory capacity in word lists only limits the binding of words to serial positions, with no limit for the words themselves. I advocate a word item limit as a broad kind of binding of each word to the current trial. I propose that the word capacity limit can be observed in Oberauer’s data when binding of a word to the trial is crucial (Experiment 2, words drawn from a small pool and often repeated across trials), though probably much less so when this kind of binding is unimportant (Experiment 1, words drawn from a large pool and rarely repeated across trials). In Oberauer’s recognition procedure for lists of 2, 4, 6, or 8 words, the number of words in the response set was varied, including both words from the list (1, 2, 4, 6, or 8 of them) and words that were not from the list (0, 1, 2, or 4 of them). There was also a serial recall procedure. In a re-analysis of the data from Experiment 2, an overlooked item capacity limit was found that affected the distribution of erroneous responses. Specifically, when the correct answer was unknown to the participant (which happened more at longer list lengths), proportionally fewer words from the list were selected as responses; selection of non-list words increased. It is an important theoretical refinement of Oberauer’s position to include evidence of a word item capacity limit when the item-to-trial binding is crucial, as in his Experiment 2.
