Viridian, it is inherent in the playback of vinyl through the recovery of the signal from the grove, because of the 90 degree difference where the L and R signals are picked up. In a recording, some of the left signal is captured in the right channel and vice versa. That "bleed" is slightly out of phase with the opposite channels. If this is not permitted (highly isolated L & R channels), then reproduction of this by CD will not add this effect. If this same "poor" recording is, however, retrieved through vinyl, the inherent phasing effect of the cartridge puts some phase difference in the L & R signals, giving a more "real" sound.
Remember that one of the reasons that we can locate sounds in space is due to phase clues due to the slight arrival time differences in the left and right ears.
It is this phase difference and reverberation clues that enable us to get a feel for the size of the room in which a recording is made.
Vinyl playback of digital recordings in the late 70s, for the most part sounded very poor (DG's especially), but some were quite good after a while of learning how to do them properly. A well recorded CD (with the appropriate microphone set-up which allows some phase difference information in each channel) sound just as good as vinyl.
I am not surprised that you haven't heard of this explanation, since we just don't pay enough attention to recording process as a way of understanding the listening process.
BTW, it is exactly this hidden information in the L & R channels that is retrieved by the Hafler circuits for rear channels. On poor sounding CD's one does not retrieve as much signal for the rear channels as the same recording played back through vinyl, even though the source signals are the same - vinyl creates some of it to be retrieved. Trust me I have done the experiment to confirm this.
