Claim LD06-SL-C23 (v1.0)
In their joint pre-deployment test of OpenAI’s o1, the US and UK AI Safety Institutes stated that their findings were preliminary and partial, that they tested an early version without the full mitigations after a limited period of access and after fixing tool-use problems with their own scaffolding, and that the results should not be read as showing whether the model was safe or appropriate for release.
Research opportunities this claim motivates
What this claim leaves open for research. Each is a hypothesis about a gap, not a finding.
- How is external evaluation under the EU AI Code of Practice carried out?US and UK state evaluators described their own pre-deployment test as preliminary, partial and limited by access.
Provenance and status
- Claim type
- FACT (as printed: “FACT”)
- Publication status
- ELIGIBLE (QUALIFIED) (as printed: “ELIGIBLE WITH QUALIFIER”)
- Verification state
- CONTENT_VERIFIED_PRIMARY (as printed: “CONTENT VERIFIED”; verified by: UNKNOWN)
- Does not license
- Conclusions about the released model
- Source (field 6, as printed)
- US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024
- Source type (field 7)
- GOVERNMENT_AUDIT_OR_EVALUATION (as printed: “Government evaluation report”)
- Institutional position
- Government AI safety institutes (US and UK)
- Maturity (claim evidence / publication maturity)
- EMERGING (as printed: “EMERGING”)
- Recorded date
- 2026-10-15
- Currentness / correction
- This is the current version. No correction or concern relation is recorded on its Sources.
Version
Current version v1.0, resolved through the explicit current pointer CLAIM--LD06-SL-C23.
Pinned Sources (field 6, version-specific)
- “US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024” → SRC-SL-US-UK-AISI-O1-PREDEPLOYMENT-EVALUATION-2024-12--v1.0 — US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024; class GOVERNMENT_AUDIT_OR_EVALUATION (explicit public provenance pin)
All 25 canonical Claim fields (raw values and normalized values)
| # | Canonical field | Canonical value (verbatim) | Normalized (Claim Value Vocabulary v1.0.2) |
|---|---|---|---|
| 1 | CLAIM ID | LD06-SL-C23 | — |
| 2 | PUBLIC-FACING CLAIM | In their joint pre-deployment test of OpenAI’s o1, the US and UK AI Safety Institutes stated that their findings were preliminary and partial, that they tested an early version without the full mitigations after a limited period of access and after fixing tool-use problems with their own scaffolding, and that the results should not be read as showing whether the model was safe or appropriate for release. | — |
| 3 | CLAIM TYPE | FACT | base_types: FACT |
| 4 | RESEARCH STRAND | C — Evaluation in governance, audits and red-teaming | — |
| 5 | MATURITY | EMERGING | states: EMERGING |
| 6 | SOURCE | US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024 | source_ids: SRC-SL-US-UK-AISI-O1-PREDEPLOYMENT-EVALUATION-2024-12 |
| 7 | SOURCE TYPE | Government evaluation report | classes: GOVERNMENT_AUDIT_OR_EVALUATION |
| 8 | INSTITUTIONAL POSITION | Government AI safety institutes (US and UK) | — |
| 9 | SCOPE | Cyber, biological and software-development capabilities of an early o1 version | — |
| 10 | DESIGN | Pre-deployment capability evaluation by two state institutes | — |
| 11 | SAMPLE / DATASET | Public and private benchmark tasks (for example 40 Cybench challenges and 47 UK AISI cyber challenges) | — |
| 12 | MODEL / TOOL / VERSION | An early version of OpenAI o1 | — |
| 13 | COMPARATOR | Reference models | — |
| 14 | MAIN RESULT | “A version of o1 that was better optimized for tool use might exhibit better performance”; the model comparison “cannot provide a reliable comparison of capabilities”; UK AISI could not assess the ceiling of o1’s cyber capabilities | — |
| 15 | INFERENTIAL TARGET | What a state pre-deployment evaluation can and cannot establish | — |
| 16 | DOES NOT LICENSE | Conclusions about the released model | — |
| 17 | VERIFICATION STATE | CONTENT VERIFIED | state: CONTENT_VERIFIED_PRIMARY · verified_by: UNKNOWN |
| 18 | LIMITATIONS | One report on one model; later institute reports were not read | — |
| 19 | CONTRADICTORY / SUPPORTING SOURCES | Compare the evaluator access and timing set out in LD06-SL-C24 | — |
| 20 | GEOGRAPHY / LANGUAGE | US / UK / English | — |
| 21 | DISTRIBUTIONAL LEDGER | Not analysed in this claim | — |
| 22 | R01 / FIELD-MAP LINKS | LD-06, D4b | — |
| 23 | WHAT WOULD CHANGE THIS CLAIM? | Later reports with longer access and full elicitation | — |
| 24 | PUBLICATION STATUS | ELIGIBLE WITH QUALIFIER | state: ELIGIBLE · qualifiers: QUALIFIED |
| 25 | RECORDED DATE | 2026-10-15 | — |
Field 22 references resolved against Field Map v0.2: LD-06 (LIVING_DEBATE); D4b (SUB_AREA)
Cited by Living Debate versions
Research-of-record provenance
Materialized by sociolens-materializer 0.6.0 at 2026-09-28T20:00:00.000Z; normalization contract SocioLens — Claim Value Vocabulary v1.0.2 — Pre-Spike Materialization Contract (v1.0.2). Content seal SHA-256 36d054a66cb544f975a682bf6db8a44555567b391259ae8c2e0771637881b61b.
Repository-authored inputs (not Drive exports)
- SocioLens claim — LD06-SL-C23 v1.0 (v1.0) — written in the SocioLens repository by Project Lead (Claude, AI) on 2026-10-15; no Drive identity exists. Authority: AGENTS.md "Authority" (the Project Lead decides research content within the research-integrity rules) and the Owner's choice in the SocioLens project chat on 15 October 2026 to build the LD-06 debate; a new Claim, first version, written from the project's LD-06 source notes, checked against full texts or official abstracts. Block “ENTRY 23 — LD06-SL-C23” SHA-256
58aeabceb7b6f28b48b7f5c98f753886b40efadf4b0200c3565fbfd0ef31fdb0; fixturefixtures/authored/claims/LD06-SL-C23--v1.0.
Builder decisions (not Drive data)
- VERSION = v1.0 — basis: Claim version taken from the repository-authored claim fixture version (SocioLens claim — LD06-SL-C23 v1.0); the first version of a new Claim of the LD-06 debate
- CURRENT_POINTER = true — basis: repository-authored claim "SocioLens claim — LD06-SL-C23 v1.0" (Project Lead (Claude, AI), 2026-10-15); basis: AGENTS.md "Authority" (the Project Lead decides research content within the research-integrity rules) and the Owner's choice in the SocioLens project chat on 15 October 2026 to build the LD-06 debate; a new Claim, first version, written from the project's LD-06 source notes, checked against full texts or official abstracts
- FIELD_6_SOURCE_REFERENCE = SRC-SL-US-UK-AISI-O1-PREDEPLOYMENT-EVALUATION-2024-12--v1.0 — basis: field 6 of ENTRY 23 — LD06-SL-C23 cites "US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024"; the only field-6 segment of this ClaimVersion's repository-authored ledger block.
- SOURCE_PROVENANCE_PIN = SRC-SL-US-UK-AISI-O1-PREDEPLOYMENT-EVALUATION-2024-12--v1.0 — basis: explicit version-pinned public provenance of this ClaimVersion (Amendment v1.2 §6): the pinned field-6 Source record "US AI Safety Institute & UK AI Safety Institute, “US AISI and UK AISI Joint Pre-Deployment Test: OpenAI o1,” December 2024".