Risk Pathway

NIKOLAI editorial proposal (unsourced): a risk-pathway record is a specific causal route from model behaviour or misuse to harm, finer-grained than a threat model, capturing the concrete steps or stages by which a threat model's harm could actually occur. This is element B2 of the source crosswalk.

This is CASRAI's own proposed definition, not a definition any named organisation has agreed to. See what NIKOLAI is and is not.

Source of record

Where this definition comes from

Anthropic Risk Report, August 2026, §2.2.1, §2.13
“Eight "priority risk pathways": "diffuse sandbagging on safety R&D; targeted undermining of safety R&D; code backdoors; training-data poisoning; self-exfiltration; persistent rogue internal deployment; undermining R&D at other developers; undermining decisions within major governments" (§2.2.1). "We aren't able to defend the choice of these pathways rigorously" (§2.13).”
https://www-cdn.anthropic.com/f61d49fa5596956a5dec75fea0e973bf6a6a8378/Redacted%20Risk%20Report%20August%202026%20.pdf
Google DeepMind Frontier Safety Framework v3.1, s.1.2
“CCLs are "determined by identifying and analyzing the main foreseeable paths through which a model could cause severe harm" (FSF s.1.2).”
https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/strengthening-our-frontier-safety-framework/frontier-safety-framework_3-1.pdf

Crosswalk

How named organisations use this concept

Every row below is a shadow mapping. It is CASRAI's own reading of a published document. No lab, evaluator or regulator named here has declared, endorsed, or been consulted on this mapping. That will change only when an organisation files its own Mapping Declaration — see the non-endorsement policy.

Organisation	Their term, as published	Match	Source
Anthropic Anthropic Risk Report, August 2026	“Eight "priority risk pathways": "diffuse sandbagging on safety R&D; targeted undermining of safety R&D; code backdoors; training-data poisoning; self-exfiltration; persistent rogue internal deployment; undermining R&D at other developers; undermining decisions within major governments" (§2.2.1). "We aren't able to defend the choice of these pathways rigorously" (§2.13).”	exact confidence: high	Anthropic Risk Report, August 2026
OpenAI Preparedness Framework v2 / Path to Astra	“Safeguards Report contents: "Identified ways a risk of severe harm can be realized for the given deployment, each mapped to the associated security controls and safeguards" (PF §4.2). Astra: "Risk pathways (cyber)": "(1) a malicious actor using Astra to develop novel exploits ... or (2) the model itself causing cyber harm when taking an unauthorized (or misaligned) action." (s.10.2)”	close confidence: high	OpenAI Preparedness Framework v2
Google DeepMind Gemini 3.7 Flash FSF report / FSF v3.1	“CCLs are "determined by identifying and analyzing the main foreseeable paths through which a model could cause severe harm" (report p.2; FSF s.1.2).”	close confidence: high	Google DeepMind Frontier Safety Framework v3.1
xAI xAI Frontier AI Framework (30 Jun 2026)	“"These risk domains describe principal pathways through which severe or systemic harm may arise." (s.2.1). Here "pathway" names the risk domain itself, not a finer-grained causal route beneath it.” PDF metadata /Title reads "Privileged/Confidential DRAFT working FRAMEWORK DOC"; no xAI statement disambiguating draft vs. final was found. This row is also confirmed by the source document's own false-friends register ("pathway": Anthropic's eight fine-grained misalignment routes vs. xAI's risk domains themselves vs. SB 53's three incident mechanisms).	none confidence: high	xAI Frontier AI Framework (30 Jun 2026, draft-marked)
Meta Meta Advanced AI Scaling Framework v2	“Threat modeling "identifies the potential causal pathways for realizing the catastrophic outcome" (Appendix I).”	close confidence: high	Meta Advanced AI Scaling Framework v2
California SB 53 California SB 53	“Catastrophic risk arises from "a single incident involving a frontier model doing any of the following: (A) ... (B) ... (C) ..." (22757.11(c)) — a broader, outcome-defined construct than a specific causal pathway.”	broad confidence: medium	California SB 53
Frontier Model Forum FMF Risk Taxonomy and Thresholds	“Threat modeling includes "mapping the potential pathways to those outcomes"; "Credibility: There is a credible pathway to extreme harm." (s1.3, s2.1)”	close confidence: high	FMF Risk Taxonomy and Thresholds

Divergence

Where sources materially disagree

xAI's Frontier AI Framework uses "pathway" as a synonym for its risk domains themselves (s.2.1), not as a finer-grained causal route beneath a domain/threat-model as in Anthropic's eight priority risk pathways, OpenAI's Astra risk pathways, or Meta's causal pathways — a false-friend label collision, confirmed by the source document's own false-friends register ("pathway": Anthropic eight fine-grained misalignment routes vs. xAI's risk domains themselves vs. SB53's three incident mechanisms). {RR} {FAIF26} {SB53}