AI-Assisted Semantic Search for Scientific Documents
Research & Development
What it collects
- PDF libraries of scientific and grey literature. These documents are used to build a searchable content library; no personal information is involved.
- Run by
- Fisheries and Oceans Canada (DFO)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization
- Your copy
- You cannot see the data it holds about you. What you can do
What it is for
This tool helps Government of Canada employees search through large libraries of scientific and grey-literature PDFs using AI-powered semantic search, so they can find relevant passages without having to read every document manually. It extracts text from PDF files and uses a Small Language Model to match queries to contextually related content. The system does not process personal information. Users are informed that AI is in use.
What it collects and what happens to it
Data taken in
- PDF libraries of scientific and grey literature. These documents are used to build a searchable content library; no personal information is involved.
Processing
- Small Language Models are used to implement semantic search, enabling users to retrieve contextually relevant passages from within PDF documents more effectively than traditional keyword-based methods.
What it does
- The system uses semantic search to retrieve contextually relevant passages from PDF documents in response to user queries. Users review and decide which retrieved passages are useful for their work.
Outputs
- Contextually relevant passages retrieved from scientific and grey-literature PDFs in response to user search queries. These are advisory results — users determine which passages to act upon.
Run by
- Fisheries and Oceans Canada is the federal department that deploys and operates the Factoid Finder Tool to support its employees in searching scientific document libraries.
Built by
- The Government of Canada developed the Factoid Finder Tool in-house, acting as both developer and technology provider for this system.
Kept for
Not stated by the Helpful Places.
Shared with
- The Factoid Finder Tool is available only to GC employees; it is not accessible to members of the general public. No personal information is collected, so individual data access requests do not apply.
- Search outputs and retrieved document passages are available to GC employees using the tool within Fisheries and Oceans Canada.
Stored
Not stated by the Helpful Places.
How to read the colours
Can it identify you?
- Anonymized data
- Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
- Pseudonymous data
- Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
- Identifiable data
- The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.
Who completes the loop?
- Human decides
- This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
- Human executes
- This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
- Autonomous
- This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.
Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.
- AI registerGovernment of Canada Algorithmic Impact Assessment Register — Factoid Finder Tool (2526-DFO-MPO-011)Fisheries and Oceans Canada, AI Register ID 2526-DFO-MPO-011.
- AI registerGovernment of Canada AI Register — Factoid Finder Tool
- AI registerGovernment of Canada AI Register — Factoid Finder Tool
- Register entryPublished by the Helpful Places. Reference 4306cb7e. This disclosure was drafted with AI assistance.Schema: ai@2026-05-06-beta
What you can do
Ask about this system
Questions go to the Helpful Places, not the vendor.
Your rights
- Right to Be Informed of AI UseUsers are informed that AI is in use when interacting with the Factoid Finder Tool. The AI Register entry confirms that AI use is disclosed to users.
- Right to Algorithmic TransparencyThe Government of Canada has published information about this system in the public AI Register, describing how the tool uses Small Language Models and semantic search to retrieve relevant document passages.
Risks and safeguards
No risks or safeguards have been published for this system yet.