Find and contextualize candidates in an existing archive
See the requirement-level assessment and its sources.
SCIENCE UNDER AUTOMATION
AI in Historical & archaeological research: capabilities and evidence
Evidence about the past comes from objects, texts and their physical and cultural contexts.
Autonomy · up to 4.4 / 10
Model interval: 2.1–4.4. Assessed 21 October 2026.
Two equally weighted workflow families: a bounded operational task and an investigation or deployment beyond that task. Inherited subfields use this parent scenario.
Calculation and work mix
Each requirement uses the operational scale from 0 (independent execution unestablished) to 4 (reliable independent execution in the stated setting). A workflow takes its lowest requirement level. The two workflows receive equal weight; the headline is 1 + 9 × weighted level / 4.
These levels are source-linked model assignments, not measurements reported by the papers. “Up to” is the upper model bound, not a probability or a forecast date.
Find and contextualize candidates in an existing archive: 1–2 / 4.
Establish and verify a new historical interpretation: 0–1 / 4.
Upper bound with 75:25 workflow weights: 4.9. With 25:75 weights: 3.8.
What has AI demonstrated?
AI-assisted image screening and six months of human fieldwork led to 303 newly identified figurative geoglyphs.
- Test
- Peer-reviewed image analysis plus physical survey
- Comparison
- Comparators vary by study; see the linked sources.
- System and version
- AI-accelerated Nazca survey · 2024-09
- Evidence checked
- 2026-10-21
303 is a discovery count, not an accuracy score. Field confirmation was performed by researchers.
What does the field require?
Find and contextualize candidates in an existing archive
- Detect candidates in images or texts
Autonomy level: 2–3 / 4.
Image screening and inscription retrieval provide useful candidates from existing material.
AI-accelerated Nazca survey · Contextualizing ancient texts with generative neural networks - Compare and attribute candidate evidence
Autonomy level: 1–2 / 4.
Aeneas improves expert workflows, with human–AI collaboration outperforming either alone on key tasks.
Contextualizing ancient texts with generative neural networks - Check whether a candidate is historically meaningful
Autonomy level: 1–2 / 4.
Historians assess contextual parallels and researchers confirm geoglyph candidates in the field.
Contextualizing ancient texts with generative neural networks · AI-accelerated Nazca survey
Establish and verify a new historical interpretation
- Acquire and document physical evidence
Autonomy level: 0–1 / 4.
The geoglyph discoveries required six months of human fieldwork following AI-assisted screening.
AI-accelerated Nazca survey - Interpret provenance and cultural context
Autonomy level: 1–2 / 4.
Contextualization is evaluated with historians; autonomous historical adjudication is not established.
Contextualizing ancient texts with generative neural networks - Resolve competing explanations with independent evidence
Autonomy level: 0–1 / 4.
Physical confirmation and historical judgement remain researcher responsibilities in the demonstrated workflows.
AI-accelerated Nazca survey · Contextualizing ancient texts with generative neural networks
Research tasks
Establish and verify a new historical interpretation
See the requirement-level assessment and its sources.
Can AI replace the whole workflow?
The results above measure specific tasks. The field assessment also requires completion of the connected workflow, including the requirements listed here. A field-wide replacement percentage has not been established.
Read the assessment method