Commonsense reasoning¶

In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day.

Version: v1 · 2026-09-28 · History
Domain-specific #: 8571
Domain group: Applied Sciences & Engineering
Origin domain: Computer Science & Software Engineering
Subdomains: Artificial Intelligence, Knowledge Representation → Computer Science & Software Engineering

Core Idea¶

Commonsense reasoning is treated here as the recurring computing and information systems identity summarized by this source-grounded definition: In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day.

In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. These assumptions include judgments about the nature of physical objects, taxonomic properties, and peoples' intentions. A device that exhibits commonsense reasoning might be capable of drawing conclusions that are similar to humans' folk psychology (humans' innate ability to reason about people's behavior and intentions) and naive physics (humans' natural understanding of the physical world).

(A generic AI has difficulty discerning whether the ones alleged to be advocating violence are the councilmen or the demonstrators.) This lack of "common knowledge" means that AI often makes different mistakes than humans make, in ways that can seem incomprehensible. The commonsense knowledge problem is a current project in the sphere of artificial intelligence to create a database that contains the general knowledge most individuals are expected to have, represented in an accessible way to artificial intelligence programs that use natural language. For example, in translating the sentences "The electrician is working" and "The telephone is working" into German, the machine translates correctly "working" in the means of "laboring" in the first one and as "functioning properly" in the second one.

For Commonsense reasoning, the abstraction is narrower than the article's general subject matter: a positive case must preserve In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. Retaining only the name, a familiar example, or a downstream effect is insufficient. The specialist roles and tests remain anchored in computing and information systems, which is why this identity is domain-specific rather than prime.

How would you explain it like I'm…

Everyday Sense for Computers

You know that if you let go of a ball it falls, and that if a friend is crying they are probably sad. Nobody has to tell you each time; it's just everyday sense. Commonsense reasoning is when a computer tries to have that same everyday sense, which is surprisingly hard for it.

Teaching Computers Common Sense

People know lots of everyday things without being taught them directly: heavy things fall, a dog is a kind of animal, people who say they are hungry want food. Commonsense reasoning, in artificial intelligence, is the ability to make these everyday guesses about ordinary situations. Computers often lack it, so they make strange mistakes people would never make. For example, a computer must know that 'the electrician is working' means doing a job, while 'the telephone is working' means it isn't broken.

Machine Everyday Inference

In artificial intelligence, commonsense reasoning is the human-like ability to make presumptions about ordinary, everyday situations: what kind of situation this is and what it is about. It covers judgments about physical objects (naive physics), categories and their properties, and people's intentions (folk psychology). For example, a translation system needs common sense to know that 'working' means 'laboring' for an electrician but 'functioning' for a telephone. Because AI systems often lack this background knowledge, they make mistakes that look bizarre to people, like being unsure who is advocating violence in a sentence about councilmen and demonstrators. One research effort, the commonsense knowledge problem, aims to build databases of the general knowledge most people are expected to have, in a form AI programs can use.

In AI, commonsense reasoning is the human-like capacity to make presumptions about the type and essence of ordinary everyday situations. It covers judgments about physical objects and their behavior (naive physics), taxonomic properties of categories, and people's intentions and behavior (folk psychology). Systems lacking it fail in ways that differ from human errors and can appear incomprehensible, for example misresolving an ambiguous pronoun whose referent a human settles using background knowledge about who is likely to advocate violence. It matters in natural-language tasks such as translation, where choosing the right sense of 'working' in 'the electrician is working' versus 'the telephone is working' depends on knowing what electricians and telephones are. The related commonsense knowledge problem is the effort to assemble the general knowledge most people are expected to have into a form accessible to AI programs that use natural language. The concept is specifically this presumptive, everyday-situation capacity in computing systems, not reasoning or knowledge representation in general.

Structural Signature¶

Sig role-phrases:

Defining carrier — The commonsense world consists of "time, space, physical interactions, people, and so on".
Constitutive relation — In 1961, Bar Hillel first discussed the need and significance of practical knowledge for natural language processing in the context of machine translation.
Operating condition — Some ambiguities are resolved by using simple and easy to acquire rules.
Recognition evidence — For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context.
Admissible variation — Existing computer programs carry out simple language tasks by manipulating short phrases or separate words, but they don't attempt any deeper understanding and focus on short-term results.
Characteristic consequence — Some movies contain scenes and moments that cannot be understood by simply matching memorized templates to images.
Failure boundary — Events are deterministic, meaning the world's state at the end of the event is defined by the world's state at the beginning and the specification of the event.

What It Is Not¶

Not the whole field of computing and information systems. The node requires the specific identity stated by In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day.
Not an over-broad reading. It takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes.
Not an over-broad reading. "Commonsense knowledge differs from encyclopedic knowledge in that it deals with general knowledge rather than the details of specific entities.".
Not an over-broad reading. Common sense is "broadly reusable background knowledge that's not specific to a particular subject area... knowledge that you ought to have.".
Not automatically Idea. Retrieval proximity does not establish equivalence; the two identities must be compared by carrier, operation, and failure boundary.

Scope of Application¶

Commonsense reasoning applies literally inside computing and information systems wherever the source-defined carrier and relation can be established. Its documented habitats include:

Commonsense reasoning problem. This enables even young children to easily make inferences like "If I roll this pen off a table, it will fall on the floor".
Commonsense reasoning problem. Humans also have a powerful mechanism of "folk psychology" that helps them to interpret natural-language sentences such as "The city councilmen refused the demonstrators a permit because they advocated violence".
Commonsense in intelligent tasks. For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context.
Commonsense in intelligent tasks. For example, in translating the sentences "The electrician is working" and "The telephone is working" into German, the machine translates correctly "working" in the means of "laboring" in the first one and as "functioning properly" in the second one.
Commonsense in intelligent tasks. The machine has seen and read in the body of texts that the German words for "laboring" and "electrician" are frequently used in a combination and are found close together.
Computer vision. For instance when looking at a photograph of a bathroom some items that are small and only partly seen, such as facecloths and bottles, are recognizable due to the surrounding objects (toilet, wash basin, bathtub), which suggest the purpose of the room.

Outside computing and information systems, the name should be retained only when these same operational conditions survive; otherwise the comparison belongs to the broader parent Pattern or should be marked as analogy.

Clarity¶

A clear use of Commonsense reasoning names the carrier, the operative relation, and the conditions under which the source treats the identity as present. The minimal definition is In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. The strongest recognition evidence in the frozen account is: For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context. A report should distinguish that evidence from a proxy, consequence, or common implementation. It should also state the qualification It takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes. so that a reader can reproduce the classification rather than infer it from topical resemblance.

Manages Complexity¶

Commonsense reasoning compresses multiple computing and information systems details into a stable diagnostic relation. The source shows both the central mechanism—in 1961, Bar Hillel first discussed the need and significance of practical knowledge for natural language processing in the context of machine translation.—and the practical consequence—some movies contain scenes and moments that cannot be understood by simply matching memorized templates to images. This compression makes cases comparable while leaving parameters, conventions, exceptions, and evidential quality explicit. It is lossy by design: local history and implementation details may be omitted only when they do not alter the defining relation.

Abstract Reasoning¶

Type the carrier. Identify the computing and information systems entities to which the claim applies.
State the relation. Use the source-grounded identity: In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day.
Check operation and conditions. Some ambiguities are resolved by using simple and easy to acquire rules.
Demand recognition evidence. For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context.
Test variation. Change an implementation or setting while preserving existing computer programs carry out simple language tasks by manipulating short phrases or separate words, but they don't attempt any deeper understanding and focus on short-term results.
Run the collapse test. Remove the defining operation; if the label still seems equally apt, only a topic or correlate was retained.
Reduce cautiously. When the specialist conditions cannot be carried, route the residual comparison to Pattern.

Knowledge Transfer¶

Within the home domain. Knowledge about Commonsense reasoning transfers literally when a new case preserves the same carrier type, relation, and recognition test. This enables even young children to easily make inferences like "If I roll this pen off a table, it will fall on the floor". Humans also have a powerful mechanism of "folk psychology" that helps them to interpret natural-language sentences such as "The city councilmen refused the demonstrators a permit because they advocated violence".

Beyond the home domain. No canonical parent is asserted for Commonsense reasoning. An outside case receives the specialist name only when the same typed roles and rejection conditions can be filled literally; otherwise the comparison remains an analogy pending later graph densification.

Examples¶

Canonical¶

"Commonsense knowledge includes the basic facts about events (including actions) and their effects, facts about knowledge and how it is obtained, facts about beliefs and desires. This case is canonical because it supplies a concrete carrier and lets the defining relation be checked rather than merely named.

Mapped back: carrier → the entities in the documented case; operation → In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day; recognition evidence → For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context

Applied / In Practice¶

NYU professor Ernest Davis characterizes commonsense knowledge as "what a typical seven year old knows about the world", including physical objects, substances, plants, animals, and human society. The applied case shows how the identity is used under a second setting or qualification while keeping the same operative relation.

Mapped back: changed setting → Definitions and characterizations; invariant → In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day; boundary → the case exits the class when it takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes

Structural Tensions¶

T1 — Stable identity versus admissible variation. It takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Which changes preserve the defining relation, and which replace it?

T2 — Recognition versus proxy. "Commonsense knowledge differs from encyclopedic knowledge in that it deals with general knowledge rather than the details of specific entities.". The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Does the cited evidence establish the identity or only a correlated sign?

T3 — Definition versus implementation. Common sense is "broadly reusable background knowledge that's not specific to a particular subject area... knowledge that you ought to have.". The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Is the observed implementation constitutive, optional, or merely common?

T4 — Scope versus overextension. For example, knowing how to play cards is specialized knowledge, not "commonsense knowledge"; but knowing that people play cards for fun does count as "commonsense knowledge". The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Can every claimed application fill the same typed roles without metaphor?

T5 — Transfer versus domain accent. The commonsense world consists of "time, space, physical interactions, people, and so on". The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Does the receiving case instantiate Commonsense reasoning literally, co-instantiate Pattern, or only resemble it?

T6 — Autonomy versus reduction. In 1961, Bar Hillel first discussed the need and significance of practical knowledge for natural language processing in the context of machine translation. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: What does Commonsense reasoning distinguish that the broader parent Pattern leaves together?

Structural–Framed Character¶

Commonsense reasoning is mixed or framed-leaning. Its structural side is the repeatable organization summarized by In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. Its framed side is the computing and information systems vocabulary that fixes the carrier, evidence, exceptions, and admissible transformations.

Evaluative weight: the identity can be stated descriptively even when applications carry practical stakes. Human-practice dependence: the source-grounded carrier determines whether the relation exists independently or is constituted by a practice. Institutional origin: disciplinary conventions stabilize the name and test. Vocabulary portability: Some ambiguities are resolved by using simple and easy to acquire rules. Import versus recognition: literal transfer requires the same mechanism; shape alone is analogy.

Its portable skeleton is Pattern. Its character: a recurring specialist identity whose thin organization can be abstracted, while its operational meaning remains domain-bound.

Structural Core vs. Domain Accent¶

What is skeletal. In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. The stable skeleton is the typed relation expressed in that definition and the entry's recognition and collapse tests. The source identifies these operative conditions: The commonsense world consists of "time, space, physical interactions, people, and so on". In 1961, Bar Hillel first discussed the need and significance of practical knowledge for natural language processing in the context of machine translation. It further constrains recognition and variation through: Some ambiguities are resolved by using simple and easy to acquire rules. For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context.

What is domain-bound. computing and information systems supplies the operative entities, technical vocabulary, warrants, and exceptions that make Commonsense reasoning literal. Its documented scope includes the condition that This enables even young children to easily make inferences like "If I roll this pen off a table, it will fall on the floor". Another bounded application condition is that Humans also have a powerful mechanism of "folk psychology" that helps them to interpret natural-language sentences such as "The city councilmen refused the demonstrators a permit because they advocated violence". These are not decorative examples; they determine which carrier and evidence can fill the abstraction's roles.

Why no parent is asserted. Removing those specialist details does not currently yield one live catalog node that is a necessary genus for every instance. The entry is therefore approved as unparented rather than attached by topical resemblance. Its collapse evidence remains specific—Existing computer programs carry out simple language tasks by manipulating short phrases or separate words, but they don't attempt any deeper understanding and focus on short-term results.—and future graph densification may discover a defensible relation only if it preserves that boundary.

Approved unparented node. No current live node supplies a defensible necessary genus or structural prerequisite for Commonsense reasoning. The reviewed identity is: In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. The accelerated suggestion was declined because topical or lexical similarity does not establish hierarchy; the node is admitted without a parent pending later graph densification.
Related reasoning operations. Evidence, representation, comparison, classification, transformation, or evaluation may participate in particular cases, but participation does not make any one of them a necessary parent of every instance.

Neighborhood in Abstraction Space¶

Commonsense reasoning sits in a sparse region of the domain-specific corpus (72^nd percentile for distinctiveness): few abstractions share its structure, so a faithful description tends to retrieve it precisely.

Family — Unclustered & Miscellaneous (2551 abstractions)

Nearest neighbors

Natural-Language Programming — 0.84
Verbal Reasoning — 0.83
Declarative knowledge — 0.83
Naturalization of intentionality — 0.83
Denotational semantics of the Actor model — 0.83

Computed from structural-signature embeddings · 2026-10-08

Not to Be Confused With¶

Pattern. The parent omits the specialist differentia. Tell: Can the case establish In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day?
Idea. A mentally or symbolically entertainable content that presents a possible form, object, relation, action or state of affairs for thought and communication. Tell: Which entry's carrier, operation, and failure condition are satisfied?
Knowledge representation and reasoning. The AI discipline of encoding knowledge in formal structures whose semantics and inference procedures support machine reasoning about a domain. Tell: Which entry's carrier, operation, and failure condition are satisfied?
Deductive Reasoning. General to specific conclusions. Tell: Which entry's carrier, operation, and failure condition are satisfied?
A measurement, proxy, or consequence. Those may provide evidence without being the identity. Tell: Would Commonsense reasoning remain present if the detector or downstream effect changed?
A metaphorical analogue. A similar shape outside computing and information systems lacks the specialist mechanism. Tell: Do the native roles transfer literally, or only the parent Pattern?

References¶

Frozen Wikipedia discovery revision: https://en.wikipedia.org/wiki/Commonsense_reasoning (revision 1368965728).
Preserved source candidate: http://cacm.acm.org/magazines/2015/9/191169-commonsense-reasoning-and-commonsense-knowledge-in-artificial-intelligence/fulltext
Preserved source candidate: https://www.wired.com/story/how-to-teach-artificial-intelligence-common-sense/
Preserved source candidate: http://discovermagazine.com/2017/april-2017/cultivating-common-sense
Preserved source candidate: https://web.archive.org/web/20180325045222/http://discovermagazine.com/2017/april-2017/cultivating-common-sense
Preserved source candidate: http://autoweek.com/article/technology/fully-autonomous-vehicles-are-more-decade-down-road
Preserved source candidate: https://web.archive.org/web/20180325052230/http://autoweek.com/article/technology/fully-autonomous-vehicles-are-more-decade-down-road
Preserved source candidate: https://www.technologyreview.com/s/608871/finally-a-driverless-car-with-some-common-sense/
Preserved source candidate: https://web.archive.org/web/20200822201548/https://www.technologyreview.com/2017/09/20/149046/finally-a-driverless-car-with-some-common-sense/

The frozen Wikipedia revision is discovery provenance. The retained source set was reviewed for identity, formal or operational relation, and scope. The encyclopedia's structural synthesis is bounded to those claims; a thin authority surface is recorded as a nonblocking source-strengthening repair rather than concealed.