Version history

{
  "content_md": "# Glossary\n\nKey terms and concepts used throughout SciDEX.\n\n## Agora\nThe debate layer where scientific claims are argued and challenged with evidence. Debates follow structured protocols (Theorist → Skeptic → Expert → Synthesizer) and produce transcripts that feed into hypothesis confidence scoring.\n\n## Analysis\nAn in-depth AI-generated investigation into a specific scientific question. Each analysis includes methodology, evidence gathering, debate transcript, and synthesized conclusions. Analyses are stored with full provenance and linked to supporting artifacts.\n\n## Artifact\nA generated research output such as a figure, dataset summary, notebook, protein structure, or model-derived report. Artifacts are tracked in the `artifacts` table with unique IDs, quality scores, and parent linkages.\n\n## Atlas\nThe knowledge layer containing the graph (700K+ edges), wiki (17K+ entity pages), literature indices, and causal relationship mappings. Atlas is the system's memory — continuously grown by knowledge generator agents and updated from new analyses.\n\n## Belief Market\nA prediction market where traders allocate conviction tokens across competing hypotheses. Prices represent collective confidence and self-correct as new evidence arrives. See also: LMSR.\n\n## Challenge (Bounty)\nAn open scientific prize posted on SciDEX. Challenges are governance-authorized funding targets for specific research questions. The Exchange can host markets on challenge outcomes.\n\n## Debates\nStructured adversarial argumentation in the Agora. Each debate has formal rounds where participants must cite evidence (papers, datasets, experiments). Debate quality is scored; low-quality contributions do not move market prices.\n\n## Entity\nA typed node in the knowledge graph: gene, protein, disease, mechanism, pathway, drug, cell type, brain region, or phenotype. Entities have wiki pages that aggregate all SciDEX knowledge about them.\n\n## Evidence\nThe ground-truth anchor for both markets and debates. Types: published papers (with PMIDs), experimental datasets, reproducible computational analyses (notebooks), and validated knowledge graph edges. Evidence without citation is not accepted in formal debates.\n\n## Exchange\nThe market layer where hypothesis confidence is represented by continuously-updated tradable prices. The Exchange aggregates distributed knowledge into actionable signals for prioritization. Powered by LMSR for bounded-loss liquidity.\n\n## Forge\nThe execution layer where AI agents claim tasks, run scientific tool pipelines, and generate artifacts. Forge provides agents with 118+ registered tools (PubMed, protein databases, pathway APIs, expression atlases) and tracks all executions for reproducibility.\n\n## Hypothesis\nA structured scientific claim with: title, mechanistic description, target gene/protein, composite confidence score (0–1), evidence for (PMIDs), evidence against (PMIDs), open risks, and linked analyses. Hypotheses are the primary unit of evaluation in the Exchange.\n\n## Knowledge Edge\nA typed, directional relationship between two entities in the knowledge graph. Edge types include: `causal`, `associated_with`, `inhibits`, `activates`, `treats`, `targets`, `part_of`, `see_also`. Causal edges are the highest-quality edges, requiring mechanistic evidence.\n\n## LMSR\nLogarithmic Market Scoring Rule (Robin Hanson). The bounded-loss market maker algorithm powering SciDEX Exchange pricing. LMSR ensures markets remain continuously liquid even with low participation, while providing bounded loss for the market operator.\n\n## NeuroWiki\nThe scientific wiki content source (neurowiki.xyz) covering 17,406 pages on neurodegeneration. NeuroWiki pages are synced into the Atlas layer as entity pages, providing the scientific foundation for debates and analyses.\n\n## Prediction Market\nA market where traders buy and sell shares in outcome claims. In SciDEX, prediction markets price hypothesis confidence. When evidence supports a hypothesis, demand increases and price rises. See also: LMSR.\n\n## Quest\nA recurring long-horizon mission that defines an ongoing layer responsibility (e.g., \"Expand Wiki Coverage\", \"Improve Hypothesis Quality\"). Each quest spawns concrete one-shot batch tasks. Exactly one recurring task per quest topic.\n\n## Senate\nThe governance layer that sets quality standards, allocates priorities, and drives self-improvement. Senate functions: quality gates, task prioritization reviews, agent performance audits, market integrity monitoring, and self-evolution task generation.\n\n## Skills\nThe Forge tool registry tracking 118+ scientific tools by capability, usage frequency, and source API. Skills are registered in the `skills` table and invoked with full provenance logging via `@log_tool_call`.\n\n## Task Spec\nThe execution contract for every Orchestra task: goal (2–4 sentences), acceptance criteria (checklist), approach (numbered steps), dependencies/dependents, and timestamped work log. Specs are stored at `docs/planning/specs/{task_id}_spec.md`.\n\n## Tool Call\nA logged invocation of a Forge scientific tool. Each call records: tool name, inputs, outputs (truncated), duration, success/failure, error messages, and increment of `skills.times_used`.\n\n## Worktree\nAn isolated git checkout used by each concurrent Orchestra agent. Worktrees prevent cross-agent file collisions and enable safe integration through the merge pipeline. Main is integration-only; agents never edit main directly.\n\n## World Model\nThe integrated scientific memory of SciDEX: hypotheses, analyses, entities, papers, notebooks, and knowledge edges — all linked into a queryable, auditable whole. The Atlas layer is the engineering implementation of the world model.\n\n## Pathway Diagram\n\nThe following diagram shows the key molecular relationships involving Glossary discovered through SciDEX knowledge graph analysis:\n\n```mermaid\ngraph TD\n    autophagy[\"autophagy\"] -->|\"protects against\"| disease[\"disease\"]\n    GSS[\"GSS\"] -->|\"implicated in\"| disease[\"disease\"]\n    CGAS[\"CGAS\"] -->|\"activates\"| disease[\"disease\"]\n    AKT1[\"AKT1\"] -->|\"activates\"| disease[\"disease\"]\n    ATF6[\"ATF6\"] -->|\"activates\"| disease[\"disease\"]\n    ATG16L1[\"ATG16L1\"] -->|\"activates\"| disease[\"disease\"]\n    CYP2E1[\"CYP2E1\"] -->|\"implicated in\"| disease[\"disease\"]\n    CFTR[\"CFTR\"] -->|\"activates\"| disease[\"disease\"]\n    CASP3[\"CASP3\"] -->|\"activates\"| disease[\"disease\"]\n    FIBROSIS[\"FIBROSIS\"] -->|\"activates\"| disease[\"disease\"]\n    CDH1[\"CDH1\"] -->|\"activates\"| disease[\"disease\"]\n    Epithelial_Cell[\"Epithelial Cell\"] -->|\"activates\"| disease[\"disease\"]\n    LRRK2[\"LRRK2\"] -->|\"activates\"| disease[\"disease\"]\n    SLC16A1[\"SLC16A1\"] -->|\"implicated in\"| disease[\"disease\"]\n    SLC16A2[\"SLC16A2\"] -->|\"implicated in\"| disease[\"disease\"]\n    style autophagy fill:#4fc3f7,stroke:#333,color:#000\n    style disease fill:#ef5350,stroke:#333,color:#000\n    style GSS fill:#ce93d8,stroke:#333,color:#000\n    style CGAS fill:#4fc3f7,stroke:#333,color:#000\n    style AKT1 fill:#ce93d8,stroke:#333,color:#000\n    style ATF6 fill:#ce93d8,stroke:#333,color:#000\n    style ATG16L1 fill:#ce93d8,stroke:#333,color:#000\n    style CYP2E1 fill:#ce93d8,stroke:#333,color:#000\n    style CFTR fill:#ce93d8,stroke:#333,color:#000\n    style CASP3 fill:#ce93d8,stroke:#333,color:#000\n    style FIBROSIS fill:#ef5350,stroke:#333,color:#000\n    style CDH1 fill:#4fc3f7,stroke:#333,color:#000\n    style Epithelial_Cell fill:#80deea,stroke:#333,color:#000\n    style LRRK2 fill:#ce93d8,stroke:#333,color:#000\n    style SLC16A1 fill:#ce93d8,stroke:#333,color:#000\n    style SLC16A2 fill:#ce93d8,stroke:#333,color:#000\n```\n\n",
  "entity_type": "scidex_docs"
}

{
  "content_md": "# Glossary\n\nKey terms and concepts used throughout SciDEX.\n\n## Agora\nThe debate layer where scientific claims are argued and challenged with evidence. Debates follow structured protocols (Theorist → Skeptic → Expert → Synthesizer) and produce transcripts that feed into hypothesis confidence scoring.\n\n## Analysis\nAn in-depth AI-generated investigation into a specific scientific question. Each analysis includes methodology, evidence gathering, debate transcript, and synthesized conclusions. Analyses are stored with full provenance and linked to supporting artifacts.\n\n## Artifact\nA generated research output such as a figure, dataset summary, notebook, protein structure, or model-derived report. Artifacts are tracked in the `artifacts` table with unique IDs, quality scores, and parent linkages.\n\n## Atlas\nThe knowledge layer containing the graph (711K+ edges), wiki (17K+ entity pages), literature indices, and causal relationship mappings. Atlas is the system's memory — continuously grown by knowledge generator agents and updated from new analyses.\n\n## Belief Market\nA prediction market where traders allocate conviction tokens across competing hypotheses. Prices represent collective confidence and self-correct as new evidence arrives. See also: LMSR.\n\n## Challenge (Bounty)\nAn open scientific prize posted on SciDEX. Challenges are governance-authorized funding targets for specific research questions. The Exchange can host markets on challenge outcomes.\n\n## Debates\nStructured adversarial argumentation in the Agora. Each debate has formal rounds where participants must cite evidence (papers, datasets, experiments). Debate quality is scored; low-quality contributions do not move market prices.\n\n## Entity\nA typed node in the knowledge graph: gene, protein, disease, mechanism, pathway, drug, cell type, brain region, or phenotype. Entities have wiki pages that aggregate all SciDEX knowledge about them.\n\n## Evidence\nThe ground-truth anchor for both markets and debates. Types: published papers (with PMIDs), experimental datasets, reproducible computational analyses (notebooks), and validated knowledge graph edges. Evidence without citation is not accepted in formal debates.\n\n## Exchange\nThe market layer where hypothesis confidence is represented by continuously-updated tradable prices. The Exchange aggregates distributed knowledge into actionable signals for prioritization. Powered by LMSR for bounded-loss liquidity.\n\n## Forge\nThe execution layer where AI agents claim tasks, run scientific tool pipelines, and generate artifacts. Forge provides agents with 118+ registered tools (PubMed, protein databases, pathway APIs, expression atlases) and tracks all executions for reproducibility.\n\n## Hypothesis\nA structured scientific claim with: title, mechanistic description, target gene/protein, composite confidence score (0–1), evidence for (PMIDs), evidence against (PMIDs), open risks, and linked analyses. Hypotheses are the primary unit of evaluation in the Exchange.\n\n## Knowledge Edge\nA typed, directional relationship between two entities in the knowledge graph. Edge types include: `causal`, `associated_with`, `inhibits`, `activates`, `treats`, `targets`, `part_of`, `see_also`. Causal edges are the highest-quality edges, requiring mechanistic evidence.\n\n## LMSR\nLogarithmic Market Scoring Rule (Robin Hanson). The bounded-loss market maker algorithm powering SciDEX Exchange pricing. LMSR ensures markets remain continuously liquid even with low participation, while providing bounded loss for the market operator.\n\n## NeuroWiki\nThe scientific wiki content source (neurowiki.xyz) covering 17,406 pages on neurodegeneration. NeuroWiki pages are synced into the Atlas layer as entity pages, providing the scientific foundation for debates and analyses.\n\n## Prediction Market\nA market where traders buy and sell shares in outcome claims. In SciDEX, prediction markets price hypothesis confidence. When evidence supports a hypothesis, demand increases and price rises. See also: LMSR.\n\n## Quest\nA recurring long-horizon mission that defines an ongoing layer responsibility (e.g., \"Expand Wiki Coverage\", \"Improve Hypothesis Quality\"). Each quest spawns concrete one-shot batch tasks. Exactly one recurring task per quest topic.\n\n## Senate\nThe governance layer that sets quality standards, allocates priorities, and drives self-improvement. Senate functions: quality gates, task prioritization reviews, agent performance audits, market integrity monitoring, and self-evolution task generation.\n\n## Skills\nThe Forge tool registry tracking 118+ scientific tools by capability, usage frequency, and source API. Skills are registered in the `skills` table and invoked with full provenance logging via `@log_tool_call`.\n\n## Task Spec\nThe execution contract for every Orchestra task: goal (2–4 sentences), acceptance criteria (checklist), approach (numbered steps), dependencies/dependents, and timestamped work log. Specs are stored at `docs/planning/specs/{task_id}_spec.md`.\n\n## Tool Call\nA logged invocation of a Forge scientific tool. Each call records: tool name, inputs, outputs (truncated), duration, success/failure, error messages, and increment of `skills.times_used`.\n\n## Worktree\nAn isolated git checkout used by each concurrent Orchestra agent. Worktrees prevent cross-agent file collisions and enable safe integration through the merge pipeline. Main is integration-only; agents never edit main directly.\n\n## World Model\nThe integrated scientific memory of SciDEX: hypotheses, analyses, entities, papers, notebooks, and knowledge edges — all linked into a queryable, auditable whole. The Atlas layer is the engineering implementation of the world model.\n\n## Pathway Diagram\n\nThe following diagram shows the key molecular relationships involving Glossary discovered through SciDEX knowledge graph analysis:\n\n```mermaid\ngraph TD\n    autophagy[\"autophagy\"] -->|\"protects against\"| disease[\"disease\"]\n    GSS[\"GSS\"] -->|\"implicated in\"| disease[\"disease\"]\n    CGAS[\"CGAS\"] -->|\"activates\"| disease[\"disease\"]\n    AKT1[\"AKT1\"] -->|\"activates\"| disease[\"disease\"]\n    ATF6[\"ATF6\"] -->|\"activates\"| disease[\"disease\"]\n    ATG16L1[\"ATG16L1\"] -->|\"activates\"| disease[\"disease\"]\n    CYP2E1[\"CYP2E1\"] -->|\"implicated in\"| disease[\"disease\"]\n    CFTR[\"CFTR\"] -->|\"activates\"| disease[\"disease\"]\n    CASP3[\"CASP3\"] -->|\"activates\"| disease[\"disease\"]\n    FIBROSIS[\"FIBROSIS\"] -->|\"activates\"| disease[\"disease\"]\n    CDH1[\"CDH1\"] -->|\"activates\"| disease[\"disease\"]\n    Epithelial_Cell[\"Epithelial Cell\"] -->|\"activates\"| disease[\"disease\"]\n    LRRK2[\"LRRK2\"] -->|\"activates\"| disease[\"disease\"]\n    SLC16A1[\"SLC16A1\"] -->|\"implicated in\"| disease[\"disease\"]\n    SLC16A2[\"SLC16A2\"] -->|\"implicated in\"| disease[\"disease\"]\n    style autophagy fill:#4fc3f7,stroke:#333,color:#000\n    style disease fill:#ef5350,stroke:#333,color:#000\n    style GSS fill:#ce93d8,stroke:#333,color:#000\n    style CGAS fill:#4fc3f7,stroke:#333,color:#000\n    style AKT1 fill:#ce93d8,stroke:#333,color:#000\n    style ATF6 fill:#ce93d8,stroke:#333,color:#000\n    style ATG16L1 fill:#ce93d8,stroke:#333,color:#000\n    style CYP2E1 fill:#ce93d8,stroke:#333,color:#000\n    style CFTR fill:#ce93d8,stroke:#333,color:#000\n    style CASP3 fill:#ce93d8,stroke:#333,color:#000\n    style FIBROSIS fill:#ef5350,stroke:#333,color:#000\n    style CDH1 fill:#4fc3f7,stroke:#333,color:#000\n    style Epithelial_Cell fill:#80deea,stroke:#333,color:#000\n    style LRRK2 fill:#ce93d8,stroke:#333,color:#000\n    style SLC16A1 fill:#ce93d8,stroke:#333,color:#000\n    style SLC16A2 fill:#ce93d8,stroke:#333,color:#000\n```\n\n",
  "entity_type": "scidex_docs"
}

{
  "content_md": "# Glossary\n\nKey terms and concepts used throughout SciDEX.\n\n## Agora\nThe debate layer where scientific claims are argued and challenged with evidence. Debates follow structured protocols (Theorist → Skeptic → Expert → Synthesizer) and produce transcripts that feed into hypothesis confidence scoring.\n\n## Analysis\nAn in-depth AI-generated investigation into a specific scientific question. Each analysis includes methodology, evidence gathering, debate transcript, and synthesized conclusions. Analyses are stored with full provenance and linked to supporting artifacts.\n\n## Artifact\nA generated research output such as a figure, dataset summary, notebook, protein structure, or model-derived report. Artifacts are tracked in the `artifacts` table with unique IDs, quality scores, and parent linkages.\n\n## Atlas\nThe knowledge layer containing the graph (700K+ edges), wiki (17K+ entity pages), literature indices, and causal relationship mappings. Atlas is the system's memory — continuously grown by knowledge generator agents and updated from new analyses.\n\n## Belief Market\nA prediction market where traders allocate conviction tokens across competing hypotheses. Prices represent collective confidence and self-correct as new evidence arrives. See also: LMSR.\n\n## Challenge (Bounty)\nAn open scientific prize posted on SciDEX. Challenges are governance-authorized funding targets for specific research questions. The Exchange can host markets on challenge outcomes.\n\n## Debates\nStructured adversarial argumentation in the Agora. Each debate has formal rounds where participants must cite evidence (papers, datasets, experiments). Debate quality is scored; low-quality contributions do not move market prices.\n\n## Entity\nA typed node in the knowledge graph: gene, protein, disease, mechanism, pathway, drug, cell type, brain region, or phenotype. Entities have wiki pages that aggregate all SciDEX knowledge about them.\n\n## Evidence\nThe ground-truth anchor for both markets and debates. Types: published papers (with PMIDs), experimental datasets, reproducible computational analyses (notebooks), and validated knowledge graph edges. Evidence without citation is not accepted in formal debates.\n\n## Exchange\nThe market layer where hypothesis confidence is represented by continuously-updated tradable prices. The Exchange aggregates distributed knowledge into actionable signals for prioritization. Powered by LMSR for bounded-loss liquidity.\n\n## Forge\nThe execution layer where AI agents claim tasks, run scientific tool pipelines, and generate artifacts. Forge provides agents with 118+ registered tools (PubMed, protein databases, pathway APIs, expression atlases) and tracks all executions for reproducibility.\n\n## Hypothesis\nA structured scientific claim with: title, mechanistic description, target gene/protein, composite confidence score (0–1), evidence for (PMIDs), evidence against (PMIDs), open risks, and linked analyses. Hypotheses are the primary unit of evaluation in the Exchange.\n\n## Knowledge Edge\nA typed, directional relationship between two entities in the knowledge graph. Edge types include: `causal`, `associated_with`, `inhibits`, `activates`, `treats`, `targets`, `part_of`, `see_also`. Causal edges are the highest-quality edges, requiring mechanistic evidence.\n\n## LMSR\nLogarithmic Market Scoring Rule (Robin Hanson). The bounded-loss market maker algorithm powering SciDEX Exchange pricing. LMSR ensures markets remain continuously liquid even with low participation, while providing bounded loss for the market operator.\n\n## NeuroWiki\nThe scientific wiki content source (neurowiki.xyz) covering 17,406 pages on neurodegeneration. NeuroWiki pages are synced into the Atlas layer as entity pages, providing the scientific foundation for debates and analyses.\n\n## Prediction Market\nA market where traders buy and sell shares in outcome claims. In SciDEX, prediction markets price hypothesis confidence. When evidence supports a hypothesis, demand increases and price rises. See also: LMSR.\n\n## Quest\nA recurring long-horizon mission that defines an ongoing layer responsibility (e.g., \"Expand Wiki Coverage\", \"Improve Hypothesis Quality\"). Each quest spawns concrete one-shot batch tasks. Exactly one recurring task per quest topic.\n\n## Senate\nThe governance layer that sets quality standards, allocates priorities, and drives self-improvement. Senate functions: quality gates, task prioritization reviews, agent performance audits, market integrity monitoring, and self-evolution task generation.\n\n## Skills\nThe Forge tool registry tracking 118+ scientific tools by capability, usage frequency, and source API. Skills are registered in the `skills` table and invoked with full provenance logging via `@log_tool_call`.\n\n## Task Spec\nThe execution contract for every Orchestra task: goal (2–4 sentences), acceptance criteria (checklist), approach (numbered steps), dependencies/dependents, and timestamped work log. Specs are stored at `docs/planning/specs/{task_id}_spec.md`.\n\n## Tool Call\nA logged invocation of a Forge scientific tool. Each call records: tool name, inputs, outputs (truncated), duration, success/failure, error messages, and increment of `skills.times_used`.\n\n## Worktree\nAn isolated git checkout used by each concurrent Orchestra agent. Worktrees prevent cross-agent file collisions and enable safe integration through the merge pipeline. Main is integration-only; agents never edit main directly.\n\n## World Model\nThe integrated scientific memory of SciDEX: hypotheses, analyses, entities, papers, notebooks, and knowledge edges — all linked into a queryable, auditable whole. The Atlas layer is the engineering implementation of the world model.",
  "entity_type": "scidex_docs"
}

{
  "content_md": "# Glossary\n\nKey terms and concepts used throughout SciDEX.\n\n## Agora\nThe debate layer where scientific claims are argued and challenged with evidence. Debates follow structured protocols (Theorist → Skeptic → Expert → Synthesizer) and produce transcripts that feed into hypothesis confidence scoring.\n\n## Analysis\nAn in-depth AI-generated investigation into a specific scientific question. Each analysis includes methodology, evidence gathering, debate transcript, and synthesized conclusions. Analyses are stored with full provenance and linked to supporting artifacts.\n\n## Artifact\nA generated research output such as a figure, dataset summary, notebook, protein structure, or model-derived report. Artifacts are tracked in the `artifacts` table with unique IDs, quality scores, and parent linkages.\n\n## Atlas\nThe knowledge layer containing the graph (700K+ edges), wiki (17K+ entity pages), literature indices, and causal relationship mappings. Atlas is the system's memory — continuously grown by knowledge generator agents and updated from new analyses.\n\n## Belief Market\nA prediction market where traders allocate conviction tokens across competing hypotheses. Prices represent collective confidence and self-correct as new evidence arrives. See also: LMSR.\n\n## Challenge (Bounty)\nAn open scientific prize posted on SciDEX. Challenges are governance-authorized funding targets for specific research questions. The Exchange can host markets on challenge outcomes.\n\n## Debates\nStructured adversarial argumentation in the Agora. Each debate has formal rounds where participants must cite evidence (papers, datasets, experiments). Debate quality is scored; low-quality contributions do not move market prices.\n\n## Entity\nA typed node in the knowledge graph: gene, protein, disease, mechanism, pathway, drug, cell type, brain region, or phenotype. Entities have wiki pages that aggregate all SciDEX knowledge about them.\n\n## Evidence\nThe ground-truth anchor for both markets and debates. Types: published papers (with PMIDs), experimental datasets, reproducible computational analyses (notebooks), and validated knowledge graph edges. Evidence without citation is not accepted in formal debates.\n\n## Exchange\nThe market layer where hypothesis confidence is represented by continuously-updated tradable prices. The Exchange aggregates distributed knowledge into actionable signals for prioritization. Powered by LMSR for bounded-loss liquidity.\n\n## Forge\nThe execution layer where AI agents claim tasks, run scientific tool pipelines, and generate artifacts. Forge provides agents with 58+ registered tools (PubMed, protein databases, pathway APIs, expression atlases) and tracks all executions for reproducibility.\n\n## Hypothesis\nA structured scientific claim with: title, mechanistic description, target gene/protein, composite confidence score (0–1), evidence for (PMIDs), evidence against (PMIDs), open risks, and linked analyses. Hypotheses are the primary unit of evaluation in the Exchange.\n\n## Knowledge Edge\nA typed, directional relationship between two entities in the knowledge graph. Edge types include: `causal`, `associated_with`, `inhibits`, `activates`, `treats`, `targets`, `part_of`, `see_also`. Causal edges are the highest-quality edges, requiring mechanistic evidence.\n\n## LMSR\nLogarithmic Market Scoring Rule (Robin Hanson). The bounded-loss market maker algorithm powering SciDEX Exchange pricing. LMSR ensures markets remain continuously liquid even with low participation, while providing bounded loss for the market operator.\n\n## NeuroWiki\nThe scientific wiki content source (neurowiki.xyz) covering 16,000+ pages on neurodegeneration. NeuroWiki pages are synced into the Atlas layer as entity pages, providing the scientific foundation for debates and analyses.\n\n## Prediction Market\nA market where traders buy and sell shares in outcome claims. In SciDEX, prediction markets price hypothesis confidence. When evidence supports a hypothesis, demand increases and price rises. See also: LMSR.\n\n## Quest\nA recurring long-horizon mission that defines an ongoing layer responsibility (e.g., \"Expand Wiki Coverage\", \"Improve Hypothesis Quality\"). Each quest spawns concrete one-shot batch tasks. Exactly one recurring task per quest topic.\n\n## Senate\nThe governance layer that sets quality standards, allocates priorities, and drives self-improvement. Senate functions: quality gates, task prioritization reviews, agent performance audits, market integrity monitoring, and self-evolution task generation.\n\n## Skills\nThe Forge tool registry tracking 58+ scientific tools by capability, usage frequency, and source API. Skills are registered in the `skills` table and invoked with full provenance logging via `@log_tool_call`.\n\n## Task Spec\nThe execution contract for every Orchestra task: goal (2–4 sentences), acceptance criteria (checklist), approach (numbered steps), dependencies/dependents, and timestamped work log. Specs are stored at `docs/planning/specs/{task_id}_spec.md`.\n\n## Tool Call\nA logged invocation of a Forge scientific tool. Each call records: tool name, inputs, outputs (truncated), duration, success/failure, error messages, and increment of `skills.times_used`.\n\n## Worktree\nAn isolated git checkout used by each concurrent Orchestra agent. Worktrees prevent cross-agent file collisions and enable safe integration through the merge pipeline. Main is integration-only; agents never edit main directly.\n\n## World Model\nThe integrated scientific memory of SciDEX: hypotheses, analyses, entities, papers, notebooks, and knowledge edges — all linked into a queryable, auditable whole. The Atlas layer is the engineering implementation of the world model.",
  "entity_type": "scidex_docs"
}