[{"data":1,"prerenderedAt":372},["ShallowReactive",2],{"doc-\u002Fdocs\u002Fresearch-workflows\u002Fgap-finding":3,"docs-nav":248},{"id":4,"title":5,"body":6,"description":240,"extension":241,"meta":242,"navigation":243,"path":244,"seo":245,"stem":246,"__hash__":247},"content\u002Fdocs\u002F3.research-workflows\u002F7.gap-finding.md","Gap Finding",{"type":7,"value":8,"toc":228},"minimark",[9,13,22,27,30,57,60,64,67,73,76,80,83,88,91,106,109,113,116,121,124,127,138,142,145,150,153,157,160,171,184,188,208,212],[10,11,5],"h1",{"id":12},"gap-finding",[14,15,16,17,21],"p",{},"Once you've assembled what's known, the next question is what isn't. ",[18,19,20],"strong",{},"Gap finding"," is the workflow for surfacing under-explored areas, weak claims, and open questions that the literature hasn't yet answered. It's often the most valuable output of a review — it's what turns a survey into a contribution.",[23,24,26],"h2",{"id":25},"what-counts-as-a-gap","What counts as a gap",[14,28,29],{},"Three distinct things, useful to keep separate:",[31,32,33,40,51],"ol",{},[34,35,36,39],"li",{},[18,37,38],{},"Coverage gaps"," — topics adjacent to your subject that the KB doesn't cover, even though the literature exists. Often a curation problem: add the missing papers.",[34,41,42,45,46,50],{},[18,43,44],{},"Evidence gaps"," — claims on the map that rest on too few or too weak sources. The work ",[47,48,49],"em",{},"was"," done, but not enough of it.",[34,52,53,56],{},[18,54,55],{},"Conceptual gaps"," — questions the literature hasn't yet asked, or assumptions it hasn't examined. These are the openings for new research.",[14,58,59],{},"Each kind needs a different response.",[23,61,63],{"id":62},"step-1-audit-coverage","Step 1 — Audit coverage",[14,65,66],{},"Ask the agent to compare what's on the map against what the KB contains:",[68,69,70],"blockquote",{},[14,71,72],{},"Compare the current mindmap to the KB. Are there documents in the KB whose contributions aren't reflected on the map? List them with a one-line summary of what they add.",[14,74,75],{},"Often there are — large workflows leave some sources behind. Decide per item whether to fold the missed contribution in or leave it out deliberately.",[23,77,79],{"id":78},"step-2-audit-evidence-strength","Step 2 — Audit evidence strength",[14,81,82],{},"For each major branch, ask the agent to evaluate the load each citation is carrying:",[68,84,85],{},[14,86,87],{},"Within the selected subtree, identify claims that rest on only one citation or on sources with low confidence scores. List them with their citations and a note on what would strengthen each.",[14,89,90],{},"Outputs will land in two buckets:",[92,93,94,100],"ul",{},[34,95,96,99],{},[18,97,98],{},"Add sources"," — the claim is true but undersupported. Action: find more evidence (often in your KB; sometimes new papers needed).",[34,101,102,105],{},[18,103,104],{},"Soften the claim"," — the evidence is genuinely thin. Action: rewrite the claim to match what the evidence actually shows.",[14,107,108],{},"Don't accept the agent's verdict uncritically here. A claim with one citation can still be defensible if the source is authoritative.",[23,110,112],{"id":111},"step-3-surface-conceptual-gaps","Step 3 — Surface conceptual gaps",[14,114,115],{},"This is the high-value step. A useful instruction:",[68,117,118],{},[14,119,120],{},"Looking across the current mindmap, identify questions that the literature on this topic hasn't yet directly addressed, or assumptions that authors share but don't examine. Be specific — name the assumption, name who shares it, name what would be required to test it.",[14,122,123],{},"Expect 3–8 candidates. Treat them as drafts — your job is to evaluate which are genuinely open, which are open but uninteresting, and which the agent missed (since \"the literature hasn't addressed X\" is a hard claim to make from retrieval alone).",[14,125,126],{},"For each gap you want to take seriously, create a node and develop it:",[128,129,134],"pre",{"className":130,"code":132,"language":133},[131],"language-text","Open question: Are pre-collapse warning indicators visible at non-palatial sites?\n├─ Why this is unaddressed\n├─ What current work assumes\n├─ What evidence would resolve it\n└─ Feasibility\n","text",[135,136,132],"code",{"__ignoreMap":137},"",[23,139,141],{"id":140},"step-4-cross-check-the-gaps","Step 4 — Cross-check the gaps",[14,143,144],{},"For each candidate gap, sanity-check that it really is one:",[68,146,147],{},[14,148,149],{},"For each \"open question\" node, search the KB to verify that this question is genuinely under-addressed. If you find papers that do address it, list them and revise the gap accordingly.",[14,151,152],{},"Some \"gaps\" the agent surfaces are actually addressed in papers it didn't surface in the original review. This step closes that loop.",[23,154,156],{"id":155},"step-5-triage","Step 5 — Triage",[14,158,159],{},"Not every gap is worth pursuing. Use whatever criteria fit your work:",[92,161,162,165,168],{},[34,163,164],{},"Tractability — is there a feasible way to address it?",[34,166,167],{},"Impact — would resolving it change the picture meaningfully?",[34,169,170],{},"Fit — does it match your skills, time, and resources?",[14,172,173,174,179,180,183],{},"Tag the survivors with a ",[175,176,178],"a",{"href":177},"..\u002Fcore-concepts\u002Flabeled-items","label"," like ",[135,181,182],{},"research-agenda"," so they're easy to find later.",[23,185,187],{"id":186},"tips","Tips",[92,189,190,196,202],{},[34,191,192,195],{},[18,193,194],{},"Gap finding works best after a real review pass."," Running it on a thin mindmap mostly surfaces \"we don't have data on X\" trivialities.",[34,197,198,201],{},[18,199,200],{},"Be skeptical of \"no one has studied X\" claims."," Retrieval can miss things. Step 4 is non-negotiable.",[34,203,204,207],{},[18,205,206],{},"The most useful gaps are usually structural, not topical."," \"No one has compared A and B\" or \"everyone assumes Y\" tends to be higher-leverage than \"no study on this specific phenomenon\".",[23,209,211],{"id":210},"whats-next","What's next",[92,213,214,221],{},[34,215,216,220],{},[175,217,219],{"href":218},".\u002Fhypothesis-generation-and-testing","Hypothesis Generation & Testing"," — turn the best gaps into testable hypotheses.",[34,222,223,227],{},[175,224,226],{"href":225},".\u002Foutlining-a-paper","Outlining a Paper"," — the gaps often become your discussion or future-work section.",{"title":137,"searchDepth":229,"depth":229,"links":230},4,[231,233,234,235,236,237,238,239],{"id":25,"depth":232,"text":26},2,{"id":62,"depth":232,"text":63},{"id":78,"depth":232,"text":79},{"id":111,"depth":232,"text":112},{"id":140,"depth":232,"text":141},{"id":155,"depth":232,"text":156},{"id":186,"depth":232,"text":187},{"id":210,"depth":232,"text":211},"Once you've assembled what's known, the next question is what isn't. Gap finding is the workflow for surfacing under-explored areas, weak claims, and open questions that the literature hasn't yet answered. It's often the most valuable output of a review — it's what turns a survey into a contribution.","md",{},true,"\u002Fdocs\u002Fresearch-workflows\u002Fgap-finding",{"title":5,"description":240},"docs\u002F3.research-workflows\u002F7.gap-finding","Vx2GBuxAOXPdNOVvkkYmCyk3PJob4dTCtkwKzCfWMdI",[249,273,309,336,360],{"slug":250,"title":251,"items":252},"getting-started","Getting Started",[253,257,261,265,269],{"path":254,"title":255,"stem":256},"\u002Fdocs\u002Fgetting-started\u002Fintroduction","Introduction","docs\u002F1.getting-started\u002F1.introduction",{"path":258,"title":259,"stem":260},"\u002Fdocs\u002Fgetting-started\u002Fquickstart","Quickstart","docs\u002F1.getting-started\u002F2.quickstart",{"path":262,"title":263,"stem":264},"\u002Fdocs\u002Fgetting-started\u002Fthe-interface","The Interface","docs\u002F1.getting-started\u002F3.the-interface",{"path":266,"title":267,"stem":268},"\u002Fdocs\u002Fgetting-started\u002Fzotero-integration","Zotero Integration","docs\u002F1.getting-started\u002F4.zotero-integration",{"path":270,"title":271,"stem":272},"\u002Fdocs\u002Fgetting-started\u002Fcredits-and-billing","Credits & Billing","docs\u002F1.getting-started\u002F5.credits-and-billing",{"slug":274,"title":275,"items":276},"core-concepts","Core Concepts",[277,281,285,289,293,297,301,305],{"path":278,"title":279,"stem":280},"\u002Fdocs\u002Fcore-concepts\u002Fprojects","Projects","docs\u002F2.core-concepts\u002F1.projects",{"path":282,"title":283,"stem":284},"\u002Fdocs\u002Fcore-concepts\u002Fknowledge-bases","Knowledge Bases","docs\u002F2.core-concepts\u002F2.knowledge-bases",{"path":286,"title":287,"stem":288},"\u002Fdocs\u002Fcore-concepts\u002Frag-and-retrieval","RAG and Retrieval","docs\u002F2.core-concepts\u002F3.rag-and-retrieval",{"path":290,"title":291,"stem":292},"\u002Fdocs\u002Fcore-concepts\u002Flabeled-items","Labeled Items","docs\u002F2.core-concepts\u002F4.labeled-items",{"path":294,"title":295,"stem":296},"\u002Fdocs\u002Fcore-concepts\u002Fmindmaps-nodes-and-claims","Mindmaps, Nodes & Claims","docs\u002F2.core-concepts\u002F5.mindmaps-nodes-and-claims",{"path":298,"title":299,"stem":300},"\u002Fdocs\u002Fcore-concepts\u002Fthe-multi-agent-system","The Multi-Agent System","docs\u002F2.core-concepts\u002F6.the-multi-agent-system",{"path":302,"title":303,"stem":304},"\u002Fdocs\u002Fcore-concepts\u002Fterminology-graph-explorer","Terminology Graph Explorer","docs\u002F2.core-concepts\u002F7.terminology-graph-explorer",{"path":306,"title":307,"stem":308},"\u002Fdocs\u002Fcore-concepts\u002Fai-verification","AI Verification","docs\u002F2.core-concepts\u002F8.ai-verification",{"slug":310,"title":311,"items":312},"research-workflows","Research Workflows",[313,317,320,324,328,332,335],{"path":314,"title":315,"stem":316},"\u002Fdocs\u002Fresearch-workflows\u002Fliterature-review","Literature Review","docs\u002F3.research-workflows\u002F1.literature-review",{"path":318,"title":219,"stem":319},"\u002Fdocs\u002Fresearch-workflows\u002Fhypothesis-generation-and-testing","docs\u002F3.research-workflows\u002F2.hypothesis-generation-and-testing",{"path":321,"title":322,"stem":323},"\u002Fdocs\u002Fresearch-workflows\u002Fthematic-analysis","Thematic Analysis","docs\u002F3.research-workflows\u002F3.thematic-analysis",{"path":325,"title":326,"stem":327},"\u002Fdocs\u002Fresearch-workflows\u002Fcomparative-analysis","Comparative Analysis","docs\u002F3.research-workflows\u002F4.comparative-analysis",{"path":329,"title":330,"stem":331},"\u002Fdocs\u002Fresearch-workflows\u002Fnode-transformation","Node Transformation","docs\u002F3.research-workflows\u002F5.node-transformation",{"path":333,"title":226,"stem":334},"\u002Fdocs\u002Fresearch-workflows\u002Foutlining-a-paper","docs\u002F3.research-workflows\u002F6.outlining-a-paper",{"path":244,"title":5,"stem":246},{"slug":337,"title":338,"items":339},"working-with-the-agent","Working With The Agent",[340,344,348,352,356],{"path":341,"title":342,"stem":343},"\u002Fdocs\u002Fworking-with-the-agent\u002Fwriting-instructions","Writing Instructions","docs\u002F4.working-with-the-agent\u002F1.writing-instructions",{"path":345,"title":346,"stem":347},"\u002Fdocs\u002Fworking-with-the-agent\u002Fagent-context","Agent Context","docs\u002F4.working-with-the-agent\u002F2.agent-context",{"path":349,"title":350,"stem":351},"\u002Fdocs\u002Fworking-with-the-agent\u002Fconversational-refinement","Conversational Refinement","docs\u002F4.working-with-the-agent\u002F3.conversational-refinement",{"path":353,"title":354,"stem":355},"\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":357,"title":358,"stem":359},"\u002Fdocs\u002Fworking-with-the-agent\u002Fversion-history-and-provenance","Version History & Provenance","docs\u002F4.working-with-the-agent\u002F5.version-history-and-provenance",{"slug":361,"title":362,"items":363},"reference","Reference",[364,368],{"path":365,"title":366,"stem":367},"\u002Fdocs\u002Freference\u002Fsettings-and-api-keys","Settings & API Keys","docs\u002F5.reference\u002F1.settings-and-api-keys",{"path":369,"title":370,"stem":371},"\u002Fdocs\u002Freference\u002Ftroubleshooting-and-faq","Troubleshooting & FAQ","docs\u002F5.reference\u002F2.troubleshooting-and-faq",1780503376376]