# What the Receiver Rebuilds
# Book: Language
# Chapter URL: https://programmer.ie/books/language/02-chapter/
# Prose fingerprint (sha256, normalized): f912c08c58cb548e260d9687f0d67ce0b7f17c9cc5c98c1b2446a3045a963a42
# Snapshot generated at build time by Hugo. This is the complete rendered prose
# of the chapter; it is not a transcript of the source file.

Imagine two registrars receiving the same handover note about bed seven: keep an eye on him. The first has worked on the ward for a week. She knows that this patient’s observations can drift before he deteriorates, that he under-reports pain, and that this colleague usually means check within the hour when she says those words. She reads the note and forms a plan. The second is new to the ward. She reads the same words and infers only that the patient needs some vigilance, with no particular deadline. Both have read the words accurately. But the first has inferred a specific action and the second has not. The note alone cannot establish whether either reconstruction matches the outgoing registrar’s intent or the patient’s needs.
The representation was identical. The reconstructions were not. One reader drew on experience with this patient; the other did not. Both also had to guess what the sender expected them to do. So the chapter’s question is not only why interpretations differ. It is which parts of each interpretation came from the message, which came from prior knowledge, and which remain unverified. Its claim is simple to state and harder to accept:
Receiving a representation is not the same as receiving its meaning. The receiver builds the meaning, and what they can build depends on what they bring.
representation ≠ meaning sent ≠ understood Everything the book later asks of a generated representation (a diagram, a brief, a timeline, an agent’s message) will be judged against this distinction. A representation can be accurate to its source and still leave a receiver unable to act. It can also look fluent and helpful while prompting the wrong inference. The question is therefore not only whether an output looks right. We also need to ask what a particular receiver can recover from it, what evidence supports that recovery, and whether it serves the stated purpose.
The pipe, and why it fails A common picture sits underneath everyday talk about messages. A sender puts meaning into words, the words travel, and the receiver takes the meaning out. Claude Shannon’s mathematical theory of communication (1948) formalised a different and narrower problem: how reliably information chosen at one point can be reproduced at another, despite the limits of the channel and the presence of noise. Shannon explicitly set semantic meaning aside, because his engineering problem did not require it. The theory is therefore not a failed account of understanding, since it was never trying to give one. A signal can arrive without error while the receiver still draws an inference the sender did not intend.
Warren Weaver, introducing the book version of the theory in 1949, separated three levels of problem. How accurately can the symbols be transmitted? How precisely do they convey the desired meaning? How effectively does the received meaning affect conduct in the desired way? Shannon offers a mathematical treatment of the technical problem, not a general solution to the other two. All three levels can fail. This book concentrates on the second and third, and it refuses to infer semantic success from technically successful delivery.
The trouble starts when the pipe is mistaken for a theory of understanding. If meaning travels inside words, then understanding is just decoding, and a clearer message is simply one with less noise. But the words alone do not always determine the action a speaker intends. Someone who says “it’s cold in here” might be reporting a temperature, asking for the window to be closed, or complaining about a colleague. The philosopher Paul Grice drew attention to this gap between what is said and what is meant. He also showed how listeners cross it, by reasoning about the speaker: why would they say this, now, in this way? Dan Sperber and Deirdre Wilson developed the idea in Relevance (1986). On their account, a speaker does not hand over a thought. A speaker provides evidence of what they intend, and the listener infers the most relevant interpretation consistent with that evidence, given everything else they know and expect.
On this view, understanding involves inference by the receiver. That is what the first registrar did with four words. The inference can be reasonable and still wrong. Human conversation has a partial remedy that a one-way handover note lacks. The receiver can ask, “Do you mean check him within the hour?” and the sender can confirm, correct or qualify the point. Feedback is part of communication. It is not evidence that the first representation succeeded.
Conceptual comparison. Perfect transmission of words does not establish that the receiver reconstructed what the sender intended. Open full-size diagram. What a receiver brings It helps to separate the things a receiver brings, because each calls for a different response. Some can be supplied by the receiver as part of the task. Some are established through conversation. Some may simply be unknown. An AI mediator needs ways to handle these differences. It should not infer a private profile of the person from whatever traces happen to be available.
Prior knowledge. The first registrar knew the patient. The second knew medicine in general but not this patient. Knowledge supplies candidate connections that a short representation leaves unstated. It can also supply the wrong connection: an earlier pattern may no longer apply, or a remembered convention may not be what this sender meant. Filling a gap is one achievement. Filling it correctly is another.
Shared context. Herbert Clark’s notion of common ground concerns what participants can reasonably treat as shared for the purposes of their exchange. This includes earlier utterances, the visible situation and expectations they have jointly established. “The usual place” may work between friends and fail between strangers. Even friends, however, can wrongly assume they have the same place in mind. Common ground is maintained and repaired through interaction. It is not identical to everything one participant knows, and a system should not silently treat private or inferred knowledge as shared.
Purpose. People read for something: to decide, to check, to learn or to act. An engineer reviewing an outage needs to judge whether the proposed fix is justified. A student reading the same report may need to explain the failure mechanism. Their questions, acceptable omissions and useful formats differ. Purpose supplies the success criterion. It does not authorise the mediator to change the underlying facts to make the task easier.
Condition. Time, attention and fatigue can change what a reader notices and remembers. A person reading under severe time pressure may overlook a qualification they would catch in a careful review. That is a risk to test. It is not a fact a mediator can safely deduce about this person from the time of day or the device they are using.
These differences are not defects in the receiver. They are the conditions under which reconstruction happens. But different reconstructions are not automatically equally adequate. Where a distinction matters, the system needs a way to check it against the source, against the sender’s clarified intent, or against an independently specified task criterion. Sometimes the right enhancement is not another representation but a question.
Conceptual model. The receiver’s contribution is not noise around a message; it is part of how the message becomes usable. Open full-size diagram. A model, not a copy What a receiver constructs is not necessarily a copy of the words. Research on discourse comprehension distinguishes the wording of a text from a reader’s model of the situation the text describes. Walter Kintsch’s construction–integration account (1988) describes comprehension as information from the text interacting with prior knowledge. Zwaan and Radvansky (1998) reviewed research on situation models, in which readers represent events, participants, goals and causal relations, not only the sentences used to describe them. We cannot inspect that representation directly. We can test aspects of it by asking a person to explain a cause, notice a contradiction, make a decision or transfer an idea to a new case. Each task supplies evidence about comprehension, but none is an unmediated readout of a mind.
A finding from this tradition makes the role of prior knowledge concrete. McNamara, Kintsch and colleagues (1996) studied versions of science texts that differed in how explicitly they connected ideas. Readers with less background knowledge generally benefited from greater coherence. On some measures of deeper understanding, knowledgeable readers benefited from text that left more of the inferential work to them. The authors interpreted this as readers using their knowledge to supply connections. This is not evidence that obscure writing is better for experts, and it does not show that a person’s knowledge level can be inferred from a clickstream. Within those studies and measures, it shows that a text’s effectiveness can depend on how its form interacts with the reader’s knowledge. The design question is therefore which representation helps this receiver perform this task? That question has to be tested. It cannot be answered by a universal readability score.
Why confidence is not a comprehension test Two familiar errors make this process harder to see from the inside.
Receivers can feel they have understood more than they can explain. Rozenblit and Keil (2002) asked people to rate their understanding of familiar mechanisms, such as zippers and flush toilets, and then to attempt an explanation. Their self-assessments often fell after the attempt: confidence had exceeded explanatory ability. The study does not establish a general effect of polished AI formatting on comprehension. It does explain why a satisfaction rating or a confident “I get it” cannot stand in for a task that probes what the reader can actually explain or use.
Senders, for their part, tend to overestimate how much of their intent has got across. Keysar and Henly (2002) found that speakers believed their ambiguous statements had been understood more often than they were. The speaker’s own knowledge of what they meant fills the ambiguity automatically. A well-known demonstration comes from a doctoral study by Elizabeth Newton (1990). Participants tapped out the rhythm of a famous song for a listener to identify. The tappers expected listeners to identify roughly half the tunes. The dissertation’s results section and Table 1 report just three correct identifications in 120 attempts (2.5%). The dissertation is internally inconsistent about the precise count, however: its abstract reports two in 150, and its later discussion reports three in 150. For the tapper, the song plays in their head. For the listener there is only knocking. The tapper has access to a richer experienced whole than the tapping carries. Speakers are in a similar position. They may begin with an image, a relation, a direction or a partly formed thought rather than a finished inner sentence, and the words they choose carry only some of it. The gap between what the sender has and what the representation carries is part of what the receiver has to rebuild. No general theory of wordless thought is needed to see that.
Put these two findings together and a design lesson emerges for both human and machine communication. The sender’s confidence and the receiver’s self-report are observations, but neither establishes that the intended distinctions survived. Better evidence comes from testing a consequence. Can the receiver explain the critical relation, identify an exception, or choose the action the task requires? Such tests need their own criteria, and they can also be imperfect. A successful answer is evidence about performance on that check. It is not proof of a complete mental reconstruction.
A target for everything that follows This gives the book a measurement target it can carry to the last chapter. First, declare what the communication is meant to accomplish and which source-grounded distinctions must survive: a deadline, a causal direction, a qualification, an uncertainty, a prohibition. Then assess both the generated representation and the receiver’s observable response. Four questions apply. They should not be collapsed into a single score:
SOURCE → REPRESENTATION → RECEIVER'S RECONSTRUCTION ├─ what survived? ├─ what changed? ├─ what was added? └─ what became easier? The first three questions concern preservation, distortion and addition. The fourth concerns what the receiver can now do. These questions are related but not interchangeable. A diagram might preserve every source claim and still confuse its reader. A shorter brief might make an important decision easier while quietly dropping a condition that would reverse the decision in another case. Gain therefore needs an outcome measure, such as accuracy on a declared question, detection of an exception, or time and effort under a quality constraint. It also needs a source-level check of what survived. A gain in usability is not permission to change the facts.
GAIN ≠ ADDITION A diagram that invents a causal link the source does not justify has added something unsupported, however persuasive its layout. A diagram that helps a reader identify a cycle the source already supports may deliver a genuine gain. A mediator can sometimes add outside explanations or examples, but these are augmentations, not preservation. Their provenance, standing and permission must be explicit, and their correctness must be checked separately.
This changes what counts as a good representation. It cannot be judged from the artifact alone, because the same diagram may help one receiver and mislead another. The unit of evaluation is a representation for a task and a receiver, under declared preservation and authority constraints. This does not require a secret psychological profile. The mediator can begin with the user’s stated purpose, an explicit choice of level of detail, and a request for clarification when the necessary knowledge is missing. Any further inference about the person has to remain distinguishable from what they declared, open to correction, and within the permissions the system actually has. The later Parts ask whether more adaptation earns its cost and risk. They do not assume that more personal data means better communication.
Inspecting a response Re-analysing the delivered text asks what that representation appears to communicate. Analysing a recipient’s answer asks what the answer reveals about applying it. These are different observations. A concise, correct answer may apply the two distinctions a question needs without repeating the other five in a source inventory. Its omissions are not automatically a failure of reconstruction. The task determines what evidence the answer must supply.
The Understanding Compiler proposes separate inventories of the source, the delivered representation and the observable response. Even matching inventories would not settle fidelity. Two interpreters can attach the same wrong scope to an exception, or share a mistaken assumption. Independent comparison with the original source, distinguishing questions and opportunities for clarification all remain necessary. The response is evidence to be assessed. It is not a window into the receiver’s complete understanding.
What can and cannot be claimed A note on limits, because this territory invites overreach. Reconstruction is not directly observable. What we can observe are its products: answers, decisions, errors, time taken, and what a person can later do with the material. The book’s vocabulary of source, representation and reconstruction is a working model for engineering and experiment. It is not a theory of how minds encode meaning. The cited research comes from psycholinguistics, the philosophy of language and the psychology of comprehension. Findings from those studied settings do not automatically transfer to AI-generated interfaces.
A bounded experiment would begin with one frozen source and a small set of independently specified questions about it. It would declare which claims, exceptions and relations must survive. It would then compare a source-faithful baseline with a generated representation on the same tasks. Source-level preservation should be measured separately from the receiver’s answers, error types, response times and optional later recall. Self-rated understanding can be recorded as another variable, but it is not the success criterion. The experiment would vary the representation while keeping the task fixed, and it would examine whether prior knowledge changes the result rather than presuming the direction of the effect. This chapter does not report any such experiment. It sets out a design for what later evidence would need to establish.
Where this leaves us A representation does not deliver a ready-made mental model. It supplies evidence from which a receiver draws inferences, using prior knowledge, context, purpose and present condition. Those inferences may be helpful, mistaken or simply uncertain. A useful mediator therefore has two separate obligations. It must preserve the source-grounded distinctions that matter, and it must test whether the chosen form improves an observable outcome for the intended receiver and task. Confidence on either side cannot discharge those obligations by itself. Clarification, an unchanged view of the source and an honest unknown must remain available alternatives to fluent transformation.
If the receiver rebuilds meaning from whatever channels are available, then the channels matter. A timetable, a subway map and a spoken warning give a receiver very different things to build from. The next question is what different kinds of representation make possible.
References Shannon, C.E. (1948). A Mathematical Theory of Communication. Bell System Technical Journal, 27, 379–423, 623–656. Shannon, C.E. & Weaver, W. (1949). The Mathematical Theory of Communication. Urbana: University of Illinois Press. (Weaver’s introductory essay distinguishes the technical, semantic and effectiveness problems.) Grice, H.P. (1975). Logic and Conversation. In P. Cole & J. Morgan (eds.), Syntax and Semantics 3: Speech Acts. New York: Academic Press, pp. 41–58. Sperber, D. & Wilson, D. (1986). Relevance: Communication and Cognition. Oxford: Blackwell. (2nd ed. 1995.) Clark, H.H. (1996). Using Language. Cambridge: Cambridge University Press. Kintsch, W. (1988). The role of knowledge in discourse comprehension: A construction-integration model. Psychological Review, 95(2), 163–182. Zwaan, R.A. & Radvansky, G.A. (1998). Situation models in language comprehension and memory. Psychological Bulletin, 123(2), 162–185. McNamara, D.S., Kintsch, E., Songer, N.B. & Kintsch, W. (1996). Are good texts always better? Interactions of text coherence, background knowledge, and levels of understanding in learning from text. Cognition and Instruction, 14(1), 1–43. Rozenblit, L. & Keil, F. (2002). The misunderstood limits of folk science: an illusion of explanatory depth. Cognitive Science, 26(5), 521–562. Keysar, B. & Henly, A.S. (2002). Speakers’ overestimation of their effectiveness. Psychological Science, 13(3), 207–212. Newton, E. L. (1990). The Rocky Road from Actions to Intentions. Doctoral dissertation, Stanford University. The results section and Table 1 (pp. 40–41) report 3/120; the abstract (p. ix) reports 2/150, and the later discussion (p. 44) reports 3/150. The source contains inconsistent counts.