Information Provenance & Multi-Source Synthesis

What You Need to Know

Information provenance is knowing where every claim comes from and how confident you should be in it. In a multi-agent research system, subagents gather findings and a synthesis agent combines them. A claim-source mapping links one finding to its source. Provenance is the difference between a research system with trustworthy outputs and a research system that produces plausible claims that nobody can trace to a source.

This lesson uses one example throughout, based on the exam guide's multi-agent research system. In this made-up case, an investment research firm uses the system to write a report on renewable energy investment. Subagents search the web and analyse documents. A synthesis agent combines their findings into the report.

Structured Claim-Source Mappings

Every finding must contain its provenance. The mapping is the structure that ensures the final output can be traced to specific sources. Each finding must include:

• Claim: The specific assertion being made
• Source URL: Where the information was found
• Document name: The title of the source document
• Relevant excerpt: The specific passage that supports the claim
• Publication date: When the source was published or data was collected

The mapping below fills in all five fields.

{
  "claim": "Global renewable energy investment reached $495 billion in 2023",
  "sourceUrl": "https://example.com/iea-report-2024",
  "documentName": "IEA World Energy Investment Report 2024",
  "relevantExcerpt": "Total investment in renewable energy technologies reached approximately $495 billion in calendar year 2023, representing a 17% increase over 2022.",
  "publicationDate": "2024-06-15"
}

Why Attribution Dies in Synthesis

Attribution is lost during summarisation. A synthesis agent that combines findings from several subagents compresses and paraphrases those findings. Without explicit instructions to keep the mappings, the source details are lost. The result reads like "Investment in renewable energy has grown significantly", with no amount, no source and no date. Nobody can check that sentence.

Downstream agents must explicitly preserve and merge claim-source mappings through synthesis. That needs three things:

1. Subagents output findings in the structured claim-source format.
2. The synthesis agent is instructed to maintain these mappings when it combines findings.
3. The final output includes inline citations or a structured reference section that traces each claim to its source.

Attribution must be kept through every step of a multi-agent pipeline:

1. Research subagent collects findings with claim-source mappings.
2. Analysis subagent evaluates findings and adds assessment, preserving original mappings.
3. Synthesis subagent combines findings from multiple agents, merging mappings.
4. Report generation produces the final output with inline citations.

Any step can lose attribution. The most common failure point is step 3, where the synthesis agent paraphrases findings without keeping the mappings. The prompt of the synthesis agent must explicitly require every claim in its output to be traceable to a specific source.

Reports should also include explicit sections separating well-established findings from contested ones, preserving original source characterisations and methodological context. A source characterisation is how the source describes its own finding, for example as an estimate. Methodological context is how the source collected its data. A finding that three independent sources support differs from a finding that is based on a single report. This is true even when the text states both findings with equal confidence. In the investment report, a figure that three sources agree on goes in a different section from a figure that one report alone gives.

Conflict Handling

Two credible sources can report different statistics for the same measure. Suppose two reports give different growth figures for the same market: 12% and 8%. The wrong approach is to arbitrarily select one value: the more recent source, the average, or the more authoritative publisher. Each of these choices destroys information and presents a false certainty.

The correct approach is to annotate the conflict with both values and full source attribution, and let the consumer, who reads the output, decide.

Market growth estimates vary by source:
- **12% growth** — IEA World Energy Report (published June 2024, using 2023 calendar year data)
- **8% growth** — Bloomberg NEF Annual Review (published March 2024, using July 2022–June 2023 data)

The difference may reflect different reporting periods and methodological approaches.

The consumer sees both values and sources and judges which value better fits their needs. Here the consumer can see that the two reports use different data periods and methods.

Temporal Awareness

Different publication dates explain different numbers. The publication dates are temporal context, and they have to be preserved. Suppose instead that the 8% report was published in 2023 and the 12% report was published in 2024. Without dates, the two numbers look contradictory. With dates, they show a trend: growth accelerated from 8% to 12%.

So require publication or data collection dates in all structured outputs. Without these dates, the synthesis agent cannot put two numbers for one measure in date order. It can misread a valid trend as a data quality issue. Then it can incorrectly flag or suppress findings that are consistent. Subagents include the dates. The synthesis agent preserves the dates when it merges findings. The final output shows the dates beside the data.

Content-Appropriate Rendering

If you put all content into one format (all tables, all prose or all lists), the content is harder to read and understand. The synthesis agent selects the format from the content type.

Financial data goes in tables. Numbers, comparisons and trends read best in a table. In prose, values are harder to compare and patterns are harder to see.

News and current events go in prose. Narrative context, cause and effect, and chronological developments read naturally as paragraphs.

Technical findings go in structured lists. Architectural patterns, API specifications and configuration options are clearest as bulleted or numbered lists with clear hierarchy.

In the investment report, the yearly totals go in the table above. News about the events behind those totals goes in prose.

Completing Analysis with Conflicts Intact

When the analysis agent finds conflicting values in a document, it completes its work with the conflicts included and explicitly annotated. The analysis agent does not resolve the conflict, because the coordinator or the consumer makes that decision. The record below shows one conflict: two revenue figures for one energy company in the report.

{
  "field": "annualRevenue",
  "conflictDetected": true,
  "values": [
    {
      "value": "$4.2M",
      "source": "Annual Report 2023",
      "context": "Audited financial statements, fiscal year ending December 2023"
    },
    {
      "value": "$3.8M",
      "source": "SEC Filing Q4 2023",
      "context": "Preliminary unaudited figures, calendar year 2023"
    }
  ],
  "possibleExplanation": "Difference may reflect audited vs preliminary figures and fiscal vs calendar year reporting periods"
}

The coordinator then decides: present both values, investigate further, or escalate to a human analyst.

In the exam

Questions test attribution through synthesis, conflicting sources, and the dates that prevent false contradictions. When a synthesis agent picks one of two credible values, the right answer annotates both with attribution and dates. The wrong options pick the most recent, the average or the most authoritative. Putting every content type into one format is also wrong.

Exam Traps

Practice Scenario

Build Exercise

Sources

• Claude Certified Architect Foundations Exam Guide — Domain 5, Task Statement 5.6 — Anthropic
• Anthropic Multi-Agent Research Patterns — Anthropic
• Claude API: Citations — Anthropic
• CCAR-F Exam Guide v1.0: Task Statement 5.6 — Anthropic