Claim · 2018-11-19 · publication · Stated in source · Supported

Leike et al. (2018) state that they build on taxonomies and problem definitions from earlier authors, citing Amodei et al. (2016) among several works.

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

Scalable agent alignment via reward modeling: a research direction → attributes to → Concrete Problems in AI Safety

Where it appears

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

Claim and evidence

Scalable agent alignment via reward modeling: a research directionattributes to ↓Concrete Problems in AI Safety

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2018-11-19 · publication Records dated 2018 →
Kind of attribution: Builds on the work

Scope and limitsA shared statement covering several cited works; it does not single out Concrete Problems in AI Safety or show which definitions came from it.

The evidence 01

primary sourceSupports the claim

Scalable agent alignment via reward modeling: a research direction

arXiv · 2018-11-19

Cite the original source

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

Source excerpt

“We build on taxonomies and problem definitions from many authors before us, highlighting tractable and neglected problems in the field of AI safety (Russell et al., 2015; Soares, 2015; Amodei et al., 2016;”

Location in source PDF p. 1, §1 Introduction

Machine-checked · 2026-10-31

Source details and check notes

Authors: Jan Leike; David Krueger; Tom Everitt; Miljan Martic; Vishal Maini; Shane Legg
Version: arXiv:1811.07871v1; first-submission date from version history. Later revisions are not substituted.
Version date: 2018-11-19
Canonical address: Open the canonical source ↗
Accessed: 2026-09-25
Language: English (en)
Attribution: Jan Leike; David Krueger; Tom Everitt; Miljan Martic; Vishal Maini; Shane Legg, Scalable agent alignment via reward modeling: a research direction.
Reuse: No open redistribution licence asserted. Bibliographic metadata and brief attributed paraphrases only; source publications and personal contact details are not redistributed.
Check notes: Candidate pack passage, key papers (research/key-papers). The quotation (33 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. A cross-family machine check (2026-10-30, item B020) found the attribution at its locator and in the citing text’s reference entry. 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. A document expressly attributes an argument, concept, term, finding or approach to another work, in its own words; the kind of attribution is recorded. The record is the citing document’s claim. It is not evidence that the cited work originated the idea, that the attribution is accurate, or of influence beyond the passage. Citation alone is recorded as a citation.

Date. Date of the citing text as the dataset records it (19 November 2018).

Record ID kp-shaping-reward-modeling-concrete-problems