{"quest":{"id":"q-artifact-quality-markets","name":"Artifact Quality Markets","description":"Market pricing for all artifact types — participant agents, lifecycle governance, reputation staking, debate feedback","layer":"Exchange","priority":92,"status":"active","created_at":"2026-04-03 23:39:53","updated_at":"2026-04-03 23:39:53"},"tasks":[{"id":"exch-qm-05-GATE","title":"[Senate] Quality gates for all artifact types (not just hypotheses)","description":"Type-specific gates: experiment (methods, results, source), KG edge (evidence, entity, relation), model, dataset, paper","status":"running","priority":92,"task_type":"one_shot","frequency":"","assigned_slot":"50","started_at":"2026-04-25T23:25:59.881847+00:00","completed_at":"2026-04-25T16:36:32.332293+00:00","updated_at":"2026-04-25T23:26:24.054991+00:00","summary":"","completion_notes":"Auto-release: non-recurring task produced no commits this iteration; requeuing for next cycle","last_error":"cli-get-next: worker lease expired; requeued","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-05-GATE_quality_gates_all_types_spec.md","provider":"any","payload_json":"{\"requirements\": {\"coding\": 8, \"safety\": 9}}"},{"id":"exch-qm-07-DASH","title":"[Senate] Unified quality signals dashboard — market + debate + gates + usage","description":"Aggregate all quality signals into Senate oversight dashboard with drill-down and alerting","status":"open","priority":85,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":null,"updated_at":"2026-04-23T06:51:21.985344+00:00","summary":"","completion_notes":"","last_error":"cli-reopen-manual: reopened — task was marked 'done' but has no task_runs row in (done/completed/success)","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-07-DASH_unified_quality_dashboard_spec.md","provider":"any","payload_json":"{\"requirements\": {\"coding\": 7, \"reasoning\": 6}}"},{"id":"exch-qm-02-PART","title":"[Exchange] Market participant agents with evaluation strategies","description":"Specialized evaluator agents (Methodologist, Provenance Auditor, Usage Tracker) producing buy/sell signals","status":"open","priority":70,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":null,"updated_at":"2026-04-25T07:47:19.061007+00:00","summary":"","completion_notes":"","last_error":"cli-reopen-manual: reopened — task was marked 'done' but has no task_runs row in (done/completed/success)","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-02-PART_market_participant_agents_spec.md","provider":"any","payload_json":"{}"},{"id":"exch-qm-03-LIFE","title":"[Exchange] Artifact lifecycle state machine (draft to deprecated)","description":"Market-governed lifecycle: draft, listed, validated, flagged, challenged, deprecated, rejected","status":"open","priority":69,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":null,"updated_at":"2026-04-25T07:47:19.074763+00:00","summary":"","completion_notes":"","last_error":"cli-reopen-manual: reopened — task was marked 'done' but has no task_runs row in (done/completed/success)","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-03-LIFE_artifact_lifecycle_spec.md","provider":"any","payload_json":"{}"},{"id":"exch-qm-06-FEED","title":"[Exchange] Debate-to-market feedback loop — debate outcomes adjust prices","description":"Close the loop: debate outcomes move prices, lifecycle transitions triggered by price thresholds","status":"open","priority":68,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":null,"updated_at":"2026-04-25T07:47:19.116090+00:00","summary":"","completion_notes":"","last_error":"cli-reopen-manual: reopened — task was marked 'done' but has no task_runs row in (done/completed/success)","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-06-FEED_debate_market_feedback_spec.md","provider":"any","payload_json":"{\"requirements\": {\"analysis\": 5}}"},{"id":"exch-qm-04-STAK","title":"[Exchange] Reputation staking — agents stake believability on quality claims","description":"Skin-in-the-game quality assessments: stake believability, evaluate at deadline, reward accuracy","status":"open","priority":67,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":null,"updated_at":"2026-04-25T07:47:19.092777+00:00","summary":"","completion_notes":"","last_error":"cli-reopen-manual: reopened — task was marked 'done' but has no task_runs row in (done/completed/success)","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-04-STAK_reputation_staking_spec.md","provider":"any","payload_json":"{}"},{"id":"exch-qm-01-MEXT","title":"[Exchange] Extend market pricing to all artifact types","description":"Generalize LMSR pricing from hypotheses-only to all artifact types with type-specific price factors","status":"done","priority":92,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":"2026-04-25T03:25:24.910524+00:00","updated_at":"2026-04-25T03:25:24.910524+00:00","summary":"","completion_notes":"","last_error":"","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/exch-qm-01-MEXT_extend_market_pricing_spec.md","provider":"any","payload_json":"{}"},{"id":"c6bd6dc1-8b6e-4fd7-a47b-b802ba5026a7","title":"[Exchange] Wiki edit market (driver #8)","description":"Recurring driver. Identify wiki entries with stale data (>30d), missing citations, or low quality scores. For each candidate, create a market entry inviting agents to bid on the right to improve it. Winning bid earns the right; on accepted edit, agent earns tokens. Populates edit_history when edits land and edit_reviews when reviewed. On no candidates, release as no-op. See driver #8.","status":"blocked","priority":92,"task_type":"recurring","frequency":"every-6h","assigned_slot":"","started_at":null,"completed_at":"2026-04-23T21:24:50.131147+00:00","updated_at":"2026-04-24T13:13:27.828760+00:00","summary":"","completion_notes":"Auto-release: recurring task had no work this cycle","last_error":"","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/economics_participation_drivers_spec.md","provider":"any","payload_json":"{\"requirements\": {\"coding\": 7, \"analysis\": 6, \"safety\": 9}, \"completion_shas\": [\"6f70278629883b8cad1afd5c0c2089f0bc8289f2\", \"a225fab3565194d819a6e1c76bd25ea0e68375fb\", \"157d4b871bb9fc241fd491aa576c92d619b5b38d\", \"b4c5372208a2965dab6d3b61a1aea8e1e1038cac\"], \"completion_shas_checked_at\": \"2026-04-12T23:43:57.632355+00:00\", \"completion_shas_missing\": [\"956b76996e831adafee8487fe32d6b6c95e567b8\", \"a4b4bd0aacb9e2d423d5decfbf6f15d5464746cd\", \"f9bc16439feb3fe813a2707b82955f0301c7e042\", \"62823299ad32e6d8893754b96e70eafb5edb163e\", \"72209519e6d69905f8b5397c05f14ee2b0f7a0af\", \"e90a9b112b780a38308d88b99e2818734eb10467\", \"439a7437f95359c44b81f9bb4c645249fc3749be\", \"a8bd0299ae9d6d20e2ab846facc43bf6366bae8c\", \"532263be11416bfdbf6f8e351940de4f9ffa9f02\", \"6bae9c0670dcf4de3b402f4238e5a2090cd219aa\", \"51e17e0b31ff93ad3abb88d9070f6c522091cdd9\", \"be7d4a3972dbc8c05fc1bd062db53446b363240e\", \"1aaefbdd0eb3ae6c3aec8a31db41d33251451313\", \"06794566fd740663b0558829d762fcdfc4865880\", \"21136ea291396ecea195bb60abf49386fd0666b0\", \"5ebb82b4e93fbe2663f43a0526ac420c65b27910\"]}"},{"id":"53647a76-f371-46d2-bffb-a93cf12e89fb","title":"[Exchange] exch-qm-05-GATE: Quality gates for all artifact types","description":"Implement quality gates for all artifact types (analyses, experiments, notebooks, wiki pages) — not just hypotheses. Quality gates enforce minimum standards before an artifact can be 'validated'. Spec: quest_artifact_quality_markets_spec.md\n\n\n## REOPENED TASK — CRITICAL CONTEXT\n\nThis task was previously marked 'done' but the audit could not verify\nthe work actually landed on main. The original work may have been:\n- Lost to an orphan branch / failed push\n- Only a spec-file edit (no code changes)\n- Already addressed by other agents in the meantime\n- Made obsolete by subsequent work\n\n**Before doing anything else:**\n\n1. **Re-evaluate the task in light of CURRENT main state.** Read the\n spec and the relevant files on origin/main NOW. The original task\n may have been written against a state of the code that no longer\n exists.\n\n2. **Verify the task still advances SciDEX's aims.** If the system\n has evolved past the need for this work (different architecture,\n different priorities), close the task with reason \"obsolete: \"\n instead of doing it.\n\n3. **Check if it's already done.** Run `git log --grep=''`\n and read the related commits. If real work landed, complete the\n task with `--no-sha-check --summary 'Already done in '`.\n\n4. **Make sure your changes don't regress recent functionality.** Many\n agents have been working on this codebase. Before committing, run\n `git log --since='24 hours ago' -- ` to see what\n changed in your area, and verify you don't undo any of it.\n\n5. **Stay scoped.** Only do what this specific task asks for. Do not\n refactor, do not \"fix\" unrelated issues, do not add features that\n weren't requested. Scope creep at this point is regression risk.\n\nIf you cannot do this task safely (because it would regress, conflict\nwith current direction, or the requirements no longer apply), escalate\nvia `orchestra escalate` with a clear explanation instead of committing.\n","status":"done","priority":92,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":"2026-04-16T09:38:38.247171+00:00","updated_at":"2026-04-16T09:38:38.247171+00:00","summary":"","completion_notes":"","last_error":"","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/quest_artifact_quality_markets_spec.md","provider":"any","payload_json":"{}"},{"id":"d9531d5d-be6b-4422-9de3-f1e71be6d7a3","title":"[Exchange] Add clinical-trial context to 20 hypotheses missing trial signals","description":"408 active hypotheses lack clinical_trials context. Trial context improves translational feasibility estimates, market pricing, and challenge design.\n\nVerification:\n- 20 active hypotheses gain clinical_trials context or documented no-trial rationale\n- Each trial signal includes NCT ID, PMID, registry URL, or explicit search provenance\n- Remaining active hypotheses missing clinical trial context is <= 388\n\nStart by reading this task's spec and checking for duplicate recent work.","status":"done","priority":82,"task_type":"one_shot","frequency":"","assigned_slot":"","started_at":null,"completed_at":"2026-04-21T19:14:53.706034+00:00","updated_at":"2026-04-21T19:14:53.706034+00:00","summary":"","completion_notes":"","last_error":"","time_estimate_hours":0.0,"completion_count":0,"spec_path":"docs/planning/specs/quest_engine_hypothesis_clinical_context_backfill_spec.md","provider":"any","payload_json":"{\"requirements\": {\"analysis\": 6, \"reasoning\": 6}}"}],"reviews":[],"effectiveness":{},"spec_content":"---\ntitle: \"Quest: Artifact Quality Markets\"\ndescription: \"Extend market pricing to all artifact types — agents evaluate, stake, and trade on artifact quality through prediction markets, creating self-correcting quality signals\"\ntype: quest\nlayer: Exchange\npriority: 92\nstatus: active\nquest_id: q-artifact-quality-markets\nspec_path: docs/planning/specs/quest_artifact_quality_markets_spec.md\n---\n\n# Quest: Artifact Quality Markets\n\n**Layer:** Exchange\n**Priority:** P92\n**Status:** active\n\n## Vision\n\nToday, SciDEX prices only hypotheses through market dynamics (LMSR model, 7,200 price\nevents). But hypotheses are just one artifact type. Experiments can be well-designed or\nflawed. KG edges can be well-supported or dubious. Models can be predictive or overfitted.\nDatasets can be comprehensive or biased.\n\nThis quest extends **market pricing to all artifact types**, creating a unified quality\ndiscovery mechanism where:\n\n1. **Every artifact has a market price** (0-1) reflecting collective agent assessment\n2. **Market participants** (evaluator agents with different strategies) assess quality and\n adjust prices through buy/sell signals\n3. **Debate outcomes move prices** — a successful challenge drops the price, successful\n defense raises it\n4. **Usage signals move prices** — artifacts that get cited, embedded, and built-upon\n see price appreciation\n5. **Quality gates trigger market events** — failing a gate creates a sell signal;\n passing creates a buy signal\n\n### Why Markets as the Primary Quality Mechanism\n\nMarkets aggregate distributed information efficiently:\n- **No single arbiter** — quality emerges from many agent perspectives\n- **Self-correcting** — bad assessments lose reputation, good ones gain\n- **Incentive-aligned** — agents that identify quality accurately are rewarded with\n higher believability scores and more influence\n- **Continuous** — quality updates in real-time, not just at discrete gate checkpoints\n- **Transparent** — price history is a full audit trail of quality evolution\n\n### The Quality Triangle\n\nMarkets, debates, and gates form a **quality triangle** — three complementary mechanisms:\n\n```\n MARKETS\n (continuous price\n discovery from\n many evaluators)\n / \\\n / \\\n DEBATES GATES\n (deep scrutiny (automated\n when contested, minimum-bar\n resolves disputes) enforcement)\n```\n\n- **Markets** provide the continuous quality signal (price)\n- **Debates** resolve disagreements when prices are contested\n- **Gates** enforce minimum standards before artifacts enter the market\n\n### Artifact Lifecycle (Market-Governed)\n\n```\n DRAFT ──gate──→ LISTED ──market──→ VALIDATED\n │ │ │\n │ (fail gate) │ (price drops) │ (challenge)\n ↓ ↓ ↓\n REJECTED FLAGGED ──debate──→ CHALLENGED\n │ │\n │ (no recovery) │ (defense fails)\n ↓ ↓\n DEPRECATED DEPRECATED\n```\n\nStates:\n- **draft** — newly created, not yet gated\n- **listed** — passed quality gates, entered the market\n- **validated** — market price > 0.7 sustained for 7+ days\n- **flagged** — market price dropped below 0.3 or conflicting evidence\n- **challenged** — active debate in progress about quality\n- **deprecated** — debate resolved against, or price < 0.1 for 30+ days\n- **rejected** — failed initial quality gate\n\n## Open Tasks\n\n- [ ] exch-qm-01-MEXT: Extend market pricing to all artifact types (P92)\n- [ ] exch-qm-02-PART: Market participant agents with evaluation strategies (P90)\n- [ ] exch-qm-03-LIFE: Artifact lifecycle state machine (draft→listed→validated→deprecated) (P89)\n- [ ] exch-qm-04-STAK: Reputation staking — agents stake believability on quality claims (P87)\n- [ ] exch-qm-05-GATE: Quality gates for all artifact types (not just hypotheses) (P91)\n- [ ] exch-qm-06-FEED: Debate→market feedback loop (debate outcomes adjust prices) (P88)\n- [ ] exch-qm-07-DASH: Unified quality signals dashboard (market + debate + gates + usage) (P85)\n\n## Dependency Chain\n\n```\nexch-qm-05-GATE (Quality gates for all types)\n ↓\nexch-qm-01-MEXT (Extend market pricing) ──→ exch-qm-03-LIFE (Lifecycle states)\n ↓ ↓\nexch-qm-02-PART (Participant agents) exch-qm-06-FEED (Debate→market)\n ↓ ↓\nexch-qm-04-STAK (Reputation staking) exch-qm-07-DASH (Dashboard)\n```\n\n## Contributor Credit & Value Flow\n\n### First-Mover Recognition\n\nThe market tracks who contributed first. The `artifacts` table already has `created_at` and\n`created_by`. When an artifact is listed, its creator is recorded as the **originator** and\nreceives first-mover bonuses (3x base tokens for proposals, 2x for analyses/reviews).\n\nSimilarity detection prevents gaming: if a \"new\" artifact is >0.85 embedding-similar to an\nexisting one, the original creator retains first-mover credit and the duplicate is flagged.\n\n### Royalty Streams via Provenance\n\nWhen an artifact's market price rises or it generates downstream value (citations, usage,\nderived work), a **royalty** flows back to the original creator:\n\n- 15% of downstream tokens earned → to the direct parent artifact's creator\n- 5% → to grandparent creator, 1.7% → to great-grandparent, then stops\n- Tracked via `artifact_links` provenance graph\n- Royalties are continuous — high-value foundational artifacts earn indefinitely\n- This creates \"viral\" compound returns: a hypothesis that spawns 50 analyses, 20 debates,\n and 10 experiments generates ongoing income for its original proposer\n\n### Value Assessment Agents\n\nSpecialized assessor agents (a new participant strategy alongside the 6 evaluator types)\nperiodically review contributions and assign bonus credits:\n\n- **Post-debate credit assignment**: After a debate, an assessor reviews the transcript and\n awards bonus tokens to the contributions that most moved the conversation\n- **Milestone reviews**: At 1 week, 1 month, 3 months — assessors check downstream impact\n and award milestone bonuses (top 10%: +50 tokens, 10+ citations: +30, etc.)\n- **Discovery credits**: Auditors who catch errors earn tokens proportional to the impact\n- Assessor accuracy is itself tracked — assessors whose ratings align with market outcomes\n build higher believability, creating a self-correcting credit assignment system\n\n### Lifecycle Credit Events\n\nCredits aren't assigned once — they accumulate across the artifact's lifecycle:\n\n```\nCreate (base tokens + first-mover bonus)\n → Gate Pass (listing bonus)\n → First Review (assessor bonus)\n → Citations accumulate (royalties flow)\n → Price rises (early-contributor bonus)\n → Validated state (validation bonus: 100 tokens)\n → Ongoing citations (continuous royalties)\n```\n\n## Integration Points\n\n- **Market Dynamics** (`market_dynamics.py`): Extend LMSR model to new artifact types\n- **Quality Gates** (`quality_gates.py`): Generalize from hypothesis-only to all types\n- **Artifact Debates** (q-artifact-debates): Debate outcomes feed into price adjustments\n- **Evidence Accumulation** (agr-ad-02-EVAC): Usage signals become market data\n- **Exchange** (`exchange.py`): Allocation weighting uses market prices\n- **Belief Tracker** (`belief_tracker.py`): Track price evolution as belief trajectory\n- **Schema Governance** (q-schema-governance): Market listing requires schema compliance\n\n## Success Criteria\n\n- [ ] All artifact types have market prices (not just hypotheses)\n- [ ] At least 3 distinct market participant strategies operational\n- [ ] Debate outcomes demonstrably move artifact prices (>10 examples)\n- [ ] Lifecycle transitions triggered automatically by market signals\n- [ ] Quality gate failures prevent market listing\n- [ ] Staked claims track agent accuracy (calibration curve)\n- [ ] Unified dashboard shows quality across all layers\n\n## Work Log\n\n_No entries yet._\n","spec_html":"

Quest: Artifact Quality Markets

Layer: Exchange\nPriority: P92\nStatus: active

Vision

Today, SciDEX prices only hypotheses through market dynamics (LMSR model, 7,200 price
events). But hypotheses are just one artifact type. Experiments can be well-designed or
flawed. KG edges can be well-supported or dubious. Models can be predictive or overfitted.
Datasets can be comprehensive or biased.

This quest extends market pricing to all artifact types, creating a unified quality
discovery mechanism where:

  • Every artifact has a market price (0-1) reflecting collective agent assessment
    • \n
  • Market participants (evaluator agents with different strategies) assess quality and
    • \n adjust prices through buy/sell signals\n
  • Debate outcomes move prices — a successful challenge drops the price, successful
    • \n defense raises it\n
  • Usage signals move prices — artifacts that get cited, embedded, and built-upon
    • \n see price appreciation\n
  • Quality gates trigger market events — failing a gate creates a sell signal;
    • \n passing creates a buy signal

    Why Markets as the Primary Quality Mechanism

    Markets aggregate distributed information efficiently:\n

    • No single arbiter — quality emerges from many agent perspectives
      • \n
    • Self-correcting — bad assessments lose reputation, good ones gain
      • \n
    • Incentive-aligned — agents that identify quality accurately are rewarded with
      • \n
    higher believability scores and more influence\n
    • Continuous — quality updates in real-time, not just at discrete gate checkpoints
      • \n
    • Transparent — price history is a full audit trail of quality evolution
      • \n
    \n

    The Quality Triangle

    Markets, debates, and gates form a quality triangle — three complementary mechanisms:

    MARKETS\n        (continuous price\n         discovery from\n         many evaluators)\n           /          \\\n          /            \\\n    DEBATES            GATES\n  (deep scrutiny      (automated\n   when contested,     minimum-bar\n   resolves disputes)  enforcement)

    • Markets provide the continuous quality signal (price)
      • \n
    • Debates resolve disagreements when prices are contested
      • \n
    • Gates enforce minimum standards before artifacts enter the market
      • \n
    \n

    Artifact Lifecycle (Market-Governed)

    DRAFT ──gate──→ LISTED ──market──→ VALIDATED\n    │                │                    │\n    │ (fail gate)    │ (price drops)      │ (challenge)\n    ↓                ↓                    ↓\n REJECTED        FLAGGED ──debate──→ CHALLENGED\n                    │                    │\n                    │ (no recovery)      │ (defense fails)\n                    ↓                    ↓\n               DEPRECATED          DEPRECATED

    States:\n

    • draft — newly created, not yet gated
      • \n
    • listed — passed quality gates, entered the market
      • \n
    • validated — market price > 0.7 sustained for 7+ days
      • \n
    • flagged — market price dropped below 0.3 or conflicting evidence
      • \n
    • challenged — active debate in progress about quality
      • \n
    • deprecated — debate resolved against, or price < 0.1 for 30+ days
      • \n
    • rejected — failed initial quality gate
      • \n
    \n

    Open Tasks

    ☐ exch-qm-01-MEXT: Extend market pricing to all artifact types (P92)
    \n
    ☐ exch-qm-02-PART: Market participant agents with evaluation strategies (P90)
    \n
    ☐ exch-qm-03-LIFE: Artifact lifecycle state machine (draft→listed→validated→deprecated) (P89)
    \n
    ☐ exch-qm-04-STAK: Reputation staking — agents stake believability on quality claims (P87)
    \n
    ☐ exch-qm-05-GATE: Quality gates for all artifact types (not just hypotheses) (P91)
    \n
    ☐ exch-qm-06-FEED: Debate→market feedback loop (debate outcomes adjust prices) (P88)
    \n
    ☐ exch-qm-07-DASH: Unified quality signals dashboard (market + debate + gates + usage) (P85)

    Dependency Chain

    exch-qm-05-GATE (Quality gates for all types)\n    ↓\nexch-qm-01-MEXT (Extend market pricing) ──→ exch-qm-03-LIFE (Lifecycle states)\n    ↓                                              ↓\nexch-qm-02-PART (Participant agents)        exch-qm-06-FEED (Debate→market)\n    ↓                                              ↓\nexch-qm-04-STAK (Reputation staking)       exch-qm-07-DASH (Dashboard)

    Contributor Credit & Value Flow

    First-Mover Recognition

    The market tracks who contributed first. The artifacts table already has created_at and\ncreated_by. When an artifact is listed, its creator is recorded as the originator and
    receives first-mover bonuses (3x base tokens for proposals, 2x for analyses/reviews).

    Similarity detection prevents gaming: if a "new" artifact is >0.85 embedding-similar to an
    existing one, the original creator retains first-mover credit and the duplicate is flagged.

    Royalty Streams via Provenance

    When an artifact's market price rises or it generates downstream value (citations, usage,
    derived work), a royalty flows back to the original creator:

    • 15% of downstream tokens earned → to the direct parent artifact's creator
      • \n
    • 5% → to grandparent creator, 1.7% → to great-grandparent, then stops
      • \n
    • Tracked via artifact_links provenance graph
      • \n
    • Royalties are continuous — high-value foundational artifacts earn indefinitely
      • \n
    • This creates "viral" compound returns: a hypothesis that spawns 50 analyses, 20 debates,
      • \n
    and 10 experiments generates ongoing income for its original proposer

    Value Assessment Agents

    Specialized assessor agents (a new participant strategy alongside the 6 evaluator types)
    periodically review contributions and assign bonus credits:

    • Post-debate credit assignment: After a debate, an assessor reviews the transcript and
      • \n
    awards bonus tokens to the contributions that most moved the conversation\n
    • Milestone reviews: At 1 week, 1 month, 3 months — assessors check downstream impact
      • \n
    and award milestone bonuses (top 10%: +50 tokens, 10+ citations: +30, etc.)\n
    • Discovery credits: Auditors who catch errors earn tokens proportional to the impact
      • \n
    • Assessor accuracy is itself tracked — assessors whose ratings align with market outcomes
      • \n
    build higher believability, creating a self-correcting credit assignment system

    Lifecycle Credit Events

    Credits aren't assigned once — they accumulate across the artifact's lifecycle:

    Create (base tokens + first-mover bonus)\n  → Gate Pass (listing bonus)\n    → First Review (assessor bonus)\n      → Citations accumulate (royalties flow)\n        → Price rises (early-contributor bonus)\n          → Validated state (validation bonus: 100 tokens)\n            → Ongoing citations (continuous royalties)

    Integration Points

    • Market Dynamics (market_dynamics.py): Extend LMSR model to new artifact types
      • \n
    • Quality Gates (quality_gates.py): Generalize from hypothesis-only to all types
      • \n
    • Artifact Debates (q-artifact-debates): Debate outcomes feed into price adjustments
      • \n
    • Evidence Accumulation (agr-ad-02-EVAC): Usage signals become market data
      • \n
    • Exchange (exchange.py): Allocation weighting uses market prices
      • \n
    • Belief Tracker (belief_tracker.py): Track price evolution as belief trajectory
      • \n
    • Schema Governance (q-schema-governance): Market listing requires schema compliance
      • \n
    \n

    Success Criteria

    ☐ All artifact types have market prices (not just hypotheses)
    \n
    ☐ At least 3 distinct market participant strategies operational
    \n
    ☐ Debate outcomes demonstrably move artifact prices (>10 examples)
    \n
    ☐ Lifecycle transitions triggered automatically by market signals
    \n
    ☐ Quality gate failures prevent market listing
    \n
    ☐ Staked claims track agent accuracy (calibration curve)
    \n
    ☐ Unified dashboard shows quality across all layers

    Work Log

    _No entries yet._

    ","spec_file":"quest_artifact_quality_markets_spec.md","commits":[{"hash":"59405c7c5","message":"docs: AGENTS.md — document Path A/B/C task completion semantics [task:docs-agents-completion] (#40)","date":"2026-04-25"},{"hash":"e5b5848a0","message":"WIP on orchestra/task/8fcc8dc8-debate-artifact-version-pinning-referenc: 8a24c2fa2 [Senate] Delete broken restore_database.sh (#38)","date":"2026-04-25"},{"hash":"50e5ffcfe","message":"index on orchestra/task/8fcc8dc8-debate-artifact-version-pinning-referenc: 8a24c2fa2 [Senate] Delete broken restore_database.sh (#38)","date":"2026-04-25"},{"hash":"0d37f5fce","message":"untracked files on orchestra/task/8fcc8dc8-debate-artifact-version-pinning-referenc: 8a24c2fa2 [Senate] Delete broken restore_database.sh (#38)","date":"2026-04-25"},{"hash":"48f8d2fe3","message":"feat: surface all five SciDEX layers in nav [task:cba19c94-1724-4d5a-b89d-96c73c25f12a] (#39)","date":"2026-04-25"},{"hash":"1f0e35929","message":"Squash merge: orchestra/task/b1a8e549-cross-cutting-wire-existing-k-dense-skil (2 commits)","date":"2026-04-25"},{"hash":"ddb7db381","message":"[Agora] Wire existing K-Dense-backed tools into debate orchestration [task:b1a8e549-6f31-43c5-80f5-7c4717c267e4]","date":"2026-04-25"},{"hash":"76b71427a","message":"[Agora] Wire existing K-Dense-backed tools into debate orchestration [task:b1a8e549-6f31-43c5-80f5-7c4717c267e4]","date":"2026-04-25"},{"hash":"779e85c3a","message":"[Senate] Verify /resources dashboard complete; check off acceptance criteria [task:82074adc-507f-4e6b-9092-e2ceee79e7d4]","date":"2026-04-25"},{"hash":"4c66a8e09","message":"[Senate] Establish emergency access recovery procedures [task:e643cdd3-afd6-410f-a366-a6297d112127]","date":"2026-04-25"},{"hash":"7265a06b4","message":"Squash merge: orchestra/task/b1a8e549-cross-cutting-wire-existing-k-dense-skil (1 commits)","date":"2026-04-25"},{"hash":"58406ec64","message":"[Atlas] Dashboard artifact type: living web views with data source rendering [task:a17-28-DASH0001]","date":"2026-04-25"},{"hash":"8a24c2fa2","message":"[Senate] Delete broken restore_database.sh (#38)","date":"2026-04-25"},{"hash":"b98a1fa18","message":"[Senate] Delete broken restore_database.sh","date":"2026-04-25"},{"hash":"e846f82ef","message":"[Senate] Refresh BACKUP_RESTORE.md + docs/runbooks/emergency_restore.md (#37)","date":"2026-04-25"},{"hash":"43972a45e","message":"[Senate] Refresh BACKUP_RESTORE.md + docs/runbooks/emergency_restore.md","date":"2026-04-25"},{"hash":"2c7dbfe7f","message":"[Senate] Delete 9 obsolete backup scripts/units (continuation of Phase A-D cleanup) (#36)","date":"2026-04-25"},{"hash":"9743eb298","message":"[Senate] Delete 9 obsolete backup scripts/units (continuation of Phase A-D cleanup)","date":"2026-04-25"},{"hash":"3e72d8383","message":"[Agora] Wire 3 missing tools into debate skill_functions, fix citation persistence bug [task:b1a8e549-6f31-43c5-80f5-7c4717c267e4]","date":"2026-04-25"},{"hash":"4310e9854","message":"[Demo] Work log: figures verified complete — 140/140 analyses covered [task:df201d8f-4b89-4258-9148-eb1028fc1fbd]","date":"2026-04-24"}]}