Claim · 1985-06 · event · Stated in source · Supported

Pearl's 1985 report presents Bayesian networks as a formalism for the computational objectives of connectionist models of knowledge, supporting multidirectional propagation of evidence that converges to a globally consistent equilibrium.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning → discusses →

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoningdiscusses ↓

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 1985-06 · event Records dated 1985 →

Scope and limitsParaphrase of the abstract read from the page image of the June version.

The evidence 01

primary sourceSupports the claim

Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning (Technical Report CSD-850021, R-43, June 1985)

UCLA Cognitive Systems Laboratory (Pearl technical-report series) · 1985-06

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Paraphrase

The abstract says the paper reports results from the theory of Bayesian networks, which offer a viable formalism for realizing the computational objectives of connectionist models of knowledge, and that the formalism supports self-activated, multidirectional propagation of evidence converging rapidly to a globally-consistent equilibrium.

Location in source PDF p. 2, abstract (page image)

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Judea Pearl
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 f4ad363e84932966f67f85f5fe623c763c94e4da33ed8899ded0c4e86d5d2bfe). Scanned report without a text layer; title page and abstract page read from the page images. Evidence is paraphrase.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Judea Pearl, “Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning (Technical Report CSD-850021, R-43, June 1985)”, 1985-06.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Kinds of AI and technical history (research/technical-history). The paraphrase is Selekoa’s, written from the text retrieved for the candidate pack on 2026-10-29; it is not a quotation and was not machine-matched. Read from the page image. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. The concept is explicitly discussed in the document. This makes no earliest-use, invention or transmission claim.

Date. Dateline on the title page of report CSD-850021, R-43 (June 1985), whose abstract the record paraphrases; no release or publication of the report on that date was verified.

Record ID th-prob-pearl-1985-def