[{"data":1,"prerenderedAt":449},["ShallowReactive",2],{"doc-\u002Fdocs\u002Fcore-concepts\u002Fai-verification":3,"docs-nav":326},{"id":4,"title":5,"body":6,"description":318,"extension":319,"meta":320,"navigation":321,"path":322,"seo":323,"stem":324,"__hash__":325},"content\u002Fdocs\u002F2.core-concepts\u002F8.ai-verification.md","AI Verification",{"type":7,"value":8,"toc":305},"minimark",[9,13,20,27,32,35,69,72,76,88,91,99,103,106,116,123,127,130,182,185,189,194,197,200,204,210,237,240,244,247,264,267,271,277,281],[10,11,5],"h1",{"id":12},"ai-verification",[14,15,16,19],"p",{},[17,18,5],"strong",{}," lets you ask the agent to assess how well an individual mindmap node is supported by its citations — and to generate alternative ways of phrasing the same claim in four different tones. The original node is never changed. The results are added as a new subtree directly underneath the node you verified.",[14,21,22],{},[23,24],"img",{"alt":25,"src":26},"AI Verification result subtree example","\u002Fdocs\u002Fcore-concepts\u002Fai-verification-result.webp",[28,29,31],"h2",{"id":30},"what-it-does","What it does",[14,33,34],{},"Given a node and its attached citations, the verification agent:",[36,37,38,45,51,57,63],"ol",{},[39,40,41,44],"li",{},[17,42,43],{},"Reads all citations"," attached to the node — the actual passage text from your documents.",[39,46,47,50],{},[17,48,49],{},"Assesses citation backing"," — determines whether each claim in the node text is directly supported, partially supported, or unsupported by the evidence.",[39,52,53,56],{},[17,54,55],{},"Assigns a support score"," — a number from 0 to 100 reflecting overall citation alignment.",[39,58,59,62],{},[17,60,61],{},"Identifies discrepancies"," — specific claims or phrases the citations do not support.",[39,64,65,68],{},[17,66,67],{},"Generates four alternative phrasings"," of the node text — one per tone — for you to consider and optionally adopt.",[14,70,71],{},"All output is written into your mindmap as nodes, so you can navigate, copy, or build on it like any other content.",[28,73,75],{"id":74},"invoking-ai-verification","Invoking AI Verification",[14,77,78,79,82,83,87],{},"Select one or more nodes on the mindmap, then right-click to open the context menu and choose ",[17,80,81],{},"AI Verify",". You can also trigger it by pressing ",[84,85,86],"code",{},"F3"," on your keyboard.",[14,89,90],{},"To verify a single node, select it and invoke verification. To verify several nodes at once, multi-select them — the agent will process each node sequentially, one after another.",[14,92,93,94,98],{},"While verification is running, a progress overlay appears on the canvas: ",[95,96,97],"em",{},"\"AI Verifying node X of N...\"",". The mindmap remains readable but edits are paused until the batch completes.",[28,100,102],{"id":101},"the-result-tree","The result tree",[14,104,105],{},"The verification output appears as a new subtree attached as a child of the verified node:",[107,108,113],"pre",{"className":109,"code":111,"language":112},[110],"language-text","Your original node\n└── AI Verification Result          ← colour reflects the support score\n    ├── Citation Backing\n    │   ├── Score: 74\u002F100\n    │   └── Discrepancies\n    │       └── The claim about X is not directly supported by any attached citation.\n    └── Alternative Phrasing\n        ├── Formal\n        │   └── [formal rephrasing]\n        ├── Concise\n        │   └── [concise rephrasing]\n        ├── Accessible\n        │   └── [accessible rephrasing]\n        └── Assertive\n            └── [assertive rephrasing]\n","text",[84,114,111],{"__ignoreMap":115},"",[14,117,118,119,122],{},"The ",[17,120,121],{},"AI Verification Result"," root node is colour-coded on a red→yellow→green scale matching the support score, so you can see at a glance whether the evidence is strong or weak before drilling in.",[28,124,126],{"id":125},"understanding-the-support-score","Understanding the support score",[14,128,129],{},"The score is a 0–100 integer:",[131,132,133,146],"table",{},[134,135,136],"thead",{},[137,138,139,143],"tr",{},[140,141,142],"th",{},"Score",[140,144,145],{},"Meaning",[147,148,149,158,166,174],"tbody",{},[137,150,151,155],{},[152,153,154],"td",{},"80–100",[152,156,157],{},"Every claim is well-supported by the attached citations",[137,159,160,163],{},[152,161,162],{},"50–79",[152,164,165],{},"Mostly supported, with minor gaps or hedged claims",[137,167,168,171],{},[152,169,170],{},"30–49",[152,172,173],{},"Partially supported — notable claims lack direct citation backing",[137,175,176,179],{},[152,177,178],{},"0–29",[152,180,181],{},"Poorly supported, or citations are only tangentially related",[14,183,184],{},"A high score does not mean the claims are objectively true — it means they are consistent with the passages your citations contain. The quality of verification is bounded by the quality of your citations.",[28,186,188],{"id":187},"discrepancies","Discrepancies",[14,190,118,191,193],{},[17,192,188],{}," node lists specific problems the agent found — claims that are stated more broadly than the evidence supports, conclusions not present in any attached citation, or wording that mischaracterises the source. Each discrepancy is a single child node with a short description (under 300 characters).",[14,195,196],{},"If the node is fully supported, the Discrepancies node will have no children.",[14,198,199],{},"Discrepancies are grounded in the citation content provided. The agent does not flag stylistic issues or speculate about what citations say; it only flags what it can directly observe from the text.",[28,201,203],{"id":202},"alternative-phrasings","Alternative phrasings",[14,205,118,206,209],{},[17,207,208],{},"Alternative Phrasing"," branch always contains exactly four rephrasings of your original node text:",[211,212,213,219,225,231],"ul",{},[39,214,215,218],{},[17,216,217],{},"Formal"," — precise, scholarly register suitable for an academic paper; uses technical vocabulary and complex sentence structure.",[39,220,221,224],{},[17,222,223],{},"Concise"," — maximum information density, minimum words; removes all redundancy while preserving every claim.",[39,226,227,230],{},[17,228,229],{},"Accessible"," — plain language for a general educated audience; avoids jargon and uses concrete expressions.",[39,232,233,236],{},[17,234,235],{},"Assertive"," — confident, direct voice; states findings and conclusions strongly without hedging.",[14,238,239],{},"Each phrasing is a leaf node in the tree. To adopt one, you can move it in place of the original node, or use it as a starting point for manual editing. The original node is never touched by the agent.",[28,241,243],{"id":242},"when-a-node-has-no-citations","When a node has no citations",[14,245,246],{},"If the node you verify has no citations attached, the verification still runs but the result reflects the absence of evidence:",[211,248,249,255,261],{},[39,250,251,252],{},"Support score: ",[17,253,254],{},"0\u002F100",[39,256,257,258],{},"A single discrepancy: ",[95,259,260],{},"\"No citations are attached to this node — citation support cannot be verified.\"",[39,262,263],{},"All four alternative phrasings are still generated (based on improving clarity and grammar of the original text, without introducing any new claims).",[14,265,266],{},"This is useful as a reminder to go back and add supporting citations, and still gives you the four rephrasing options even without citation backing.",[28,268,270],{"id":269},"credits","Credits",[14,272,273,274,276],{},"Each AI Verification call uses credits, but it is optimized to minimize usage, usually consuming around one credit per node. The charge appears in your credits history as ",[17,275,5],{},". When verifying multiple nodes in a batch, each node is charged separately.",[28,278,280],{"id":279},"see-also","See also",[211,282,283,291,298],{},[39,284,285,290],{},[286,287,289],"a",{"href":288},".\u002Fmindmaps-nodes-and-claims","Mindmaps, Nodes & Claims"," — how nodes, citations, and the mindmap structure work.",[39,292,293,297],{},[286,294,296],{"href":295},".\u002Fterminology-graph-explorer","Terminology Graph Explorer"," — exploring your corpus from a concept perspective.",[39,299,300,304],{},[286,301,303],{"href":302},"..\u002Fgetting-started\u002Fcredits-and-billing","Credits & Billing"," — understanding credit usage.",{"title":115,"searchDepth":306,"depth":306,"links":307},4,[308,310,311,312,313,314,315,316,317],{"id":30,"depth":309,"text":31},2,{"id":74,"depth":309,"text":75},{"id":101,"depth":309,"text":102},{"id":125,"depth":309,"text":126},{"id":187,"depth":309,"text":188},{"id":202,"depth":309,"text":203},{"id":242,"depth":309,"text":243},{"id":269,"depth":309,"text":270},{"id":279,"depth":309,"text":280},"AI Verification lets you ask the agent to assess how well an individual mindmap node is supported by its citations — and to generate alternative ways of phrasing the same claim in four different tones. The original node is never changed. The results are added as a new subtree directly underneath the node you verified.","md",{},true,"\u002Fdocs\u002Fcore-concepts\u002Fai-verification",{"title":5,"description":318},"docs\u002F2.core-concepts\u002F8.ai-verification","nXMRTr7LpSwhyMFW0_nrP4PmWR8eBPXuWx88ntdlUFw",[327,350,381,413,437],{"slug":328,"title":329,"items":330},"getting-started","Getting Started",[331,335,339,343,347],{"path":332,"title":333,"stem":334},"\u002Fdocs\u002Fgetting-started\u002Fintroduction","Introduction","docs\u002F1.getting-started\u002F1.introduction",{"path":336,"title":337,"stem":338},"\u002Fdocs\u002Fgetting-started\u002Fquickstart","Quickstart","docs\u002F1.getting-started\u002F2.quickstart",{"path":340,"title":341,"stem":342},"\u002Fdocs\u002Fgetting-started\u002Fthe-interface","The Interface","docs\u002F1.getting-started\u002F3.the-interface",{"path":344,"title":345,"stem":346},"\u002Fdocs\u002Fgetting-started\u002Fzotero-integration","Zotero Integration","docs\u002F1.getting-started\u002F4.zotero-integration",{"path":348,"title":303,"stem":349},"\u002Fdocs\u002Fgetting-started\u002Fcredits-and-billing","docs\u002F1.getting-started\u002F5.credits-and-billing",{"slug":351,"title":352,"items":353},"core-concepts","Core Concepts",[354,358,362,366,370,373,377,380],{"path":355,"title":356,"stem":357},"\u002Fdocs\u002Fcore-concepts\u002Fprojects","Projects","docs\u002F2.core-concepts\u002F1.projects",{"path":359,"title":360,"stem":361},"\u002Fdocs\u002Fcore-concepts\u002Fknowledge-bases","Knowledge Bases","docs\u002F2.core-concepts\u002F2.knowledge-bases",{"path":363,"title":364,"stem":365},"\u002Fdocs\u002Fcore-concepts\u002Frag-and-retrieval","RAG and Retrieval","docs\u002F2.core-concepts\u002F3.rag-and-retrieval",{"path":367,"title":368,"stem":369},"\u002Fdocs\u002Fcore-concepts\u002Flabeled-items","Labeled Items","docs\u002F2.core-concepts\u002F4.labeled-items",{"path":371,"title":289,"stem":372},"\u002Fdocs\u002Fcore-concepts\u002Fmindmaps-nodes-and-claims","docs\u002F2.core-concepts\u002F5.mindmaps-nodes-and-claims",{"path":374,"title":375,"stem":376},"\u002Fdocs\u002Fcore-concepts\u002Fthe-multi-agent-system","The Multi-Agent System","docs\u002F2.core-concepts\u002F6.the-multi-agent-system",{"path":378,"title":296,"stem":379},"\u002Fdocs\u002Fcore-concepts\u002Fterminology-graph-explorer","docs\u002F2.core-concepts\u002F7.terminology-graph-explorer",{"path":322,"title":5,"stem":324},{"slug":382,"title":383,"items":384},"research-workflows","Research Workflows",[385,389,393,397,401,405,409],{"path":386,"title":387,"stem":388},"\u002Fdocs\u002Fresearch-workflows\u002Fliterature-review","Literature Review","docs\u002F3.research-workflows\u002F1.literature-review",{"path":390,"title":391,"stem":392},"\u002Fdocs\u002Fresearch-workflows\u002Fhypothesis-generation-and-testing","Hypothesis Generation & Testing","docs\u002F3.research-workflows\u002F2.hypothesis-generation-and-testing",{"path":394,"title":395,"stem":396},"\u002Fdocs\u002Fresearch-workflows\u002Fthematic-analysis","Thematic Analysis","docs\u002F3.research-workflows\u002F3.thematic-analysis",{"path":398,"title":399,"stem":400},"\u002Fdocs\u002Fresearch-workflows\u002Fcomparative-analysis","Comparative Analysis","docs\u002F3.research-workflows\u002F4.comparative-analysis",{"path":402,"title":403,"stem":404},"\u002Fdocs\u002Fresearch-workflows\u002Fnode-transformation","Node Transformation","docs\u002F3.research-workflows\u002F5.node-transformation",{"path":406,"title":407,"stem":408},"\u002Fdocs\u002Fresearch-workflows\u002Foutlining-a-paper","Outlining a Paper","docs\u002F3.research-workflows\u002F6.outlining-a-paper",{"path":410,"title":411,"stem":412},"\u002Fdocs\u002Fresearch-workflows\u002Fgap-finding","Gap Finding","docs\u002F3.research-workflows\u002F7.gap-finding",{"slug":414,"title":415,"items":416},"working-with-the-agent","Working With The Agent",[417,421,425,429,433],{"path":418,"title":419,"stem":420},"\u002Fdocs\u002Fworking-with-the-agent\u002Fwriting-instructions","Writing Instructions","docs\u002F4.working-with-the-agent\u002F1.writing-instructions",{"path":422,"title":423,"stem":424},"\u002Fdocs\u002Fworking-with-the-agent\u002Fagent-context","Agent Context","docs\u002F4.working-with-the-agent\u002F2.agent-context",{"path":426,"title":427,"stem":428},"\u002Fdocs\u002Fworking-with-the-agent\u002Fconversational-refinement","Conversational Refinement","docs\u002F4.working-with-the-agent\u002F3.conversational-refinement",{"path":430,"title":431,"stem":432},"\u002Fdocs\u002Fworking-with-the-agent\u002Fconfidence-gaps-and-iteration-limits","Confidence, Gaps & Iteration Limits","docs\u002F4.working-with-the-agent\u002F4.confidence-gaps-and-iteration-limits",{"path":434,"title":435,"stem":436},"\u002Fdocs\u002Fworking-with-the-agent\u002Fversion-history-and-provenance","Version History & Provenance","docs\u002F4.working-with-the-agent\u002F5.version-history-and-provenance",{"slug":438,"title":439,"items":440},"reference","Reference",[441,445],{"path":442,"title":443,"stem":444},"\u002Fdocs\u002Freference\u002Fsettings-and-api-keys","Settings & API Keys","docs\u002F5.reference\u002F1.settings-and-api-keys",{"path":446,"title":447,"stem":448},"\u002Fdocs\u002Freference\u002Ftroubleshooting-and-faq","Troubleshooting & FAQ","docs\u002F5.reference\u002F2.troubleshooting-and-faq",1780503376376]