Skip to content

zrwangems/dsh-zrwang-plugin / ars/skills/deep-research

deep-research

Flagged

学术研究前置:把模糊想法收敛成可研究的问题,并做文献综述、事实核查、系统综述(PRISMA)与三向文献扫描。Triggers: research, deep research, literature review, systematic review, meta-analysis, PRISMA, fact-check, guide my research | 研究, 文献综述, 系统性文献回顾, 事实核查, 引导我研究, 帮我确定研究问题。输出 RQ Brief、方法论蓝图、带核验的注释书目。

FileKindSize
SKILL.mdskill md51.2 KB
_shared/ARCHITECTURE.mdmarkdown51.7 KB
_shared/MODE_REGISTRY.mdmarkdown6.7 KB
_shared/agents/compliance_agent.mdmarkdown9.4 KB
_shared/artifact_reproducibility_pattern.mdmarkdown9.8 KB
_shared/benchmark_report.schema.jsonconfig2.7 KB
_shared/benchmark_report_pattern.mdmarkdown8.8 KB
_shared/bibliographic_integrity_signals.mdmarkdown8.1 KB
_shared/collaboration_depth_rubric.mdmarkdown11.5 KB
_shared/compliance_checkpoint_protocol.mdmarkdown8.9 KB
_shared/compliance_report.schema.jsonconfig8.1 KB
_shared/contracts/README.mdmarkdown54.7 KB
_shared/contracts/activity/adjudication_activity_input.schema.jsonconfig18.5 KB
_shared/contracts/activity/adjudication_activity_store.schema.jsonconfig18.7 KB
_shared/contracts/audit/audit_jsonl.schema.jsonconfig5.4 KB
_shared/contracts/audit/audit_sidecar.schema.jsonconfig8.4 KB
_shared/contracts/audit/audit_verdict.schema.jsonconfig5.4 KB
_shared/contracts/audit/cross_document_consistency_advisory.schema.jsonconfig20.4 KB
_shared/contracts/audit/cross_document_consistency_advisory_draft.schema.jsonconfig23.4 KB
_shared/contracts/audit/cross_document_source_manifest.schema.jsonconfig6.3 KB
_shared/contracts/audit/tortured_phrase_advisory.schema.jsonconfig30.9 KB
_shared/contracts/audit/tortured_phrase_snapshot.schema.jsonconfig4.9 KB
_shared/contracts/audit/tortured_phrase_snapshot_manifest.schema.jsonconfig7.3 KB
_shared/contracts/capability/stage_capability_matrix.jsonconfig23.5 KB
_shared/contracts/claim_standing/candidate_ledger.schema.jsonconfig23.1 KB
_shared/contracts/claim_standing/query_plan.schema.jsonconfig12.7 KB
_shared/contracts/claim_standing/query_plan_v1_1.schema.jsonconfig20.3 KB
_shared/contracts/claim_standing/retrieval_input.schema.jsonconfig14.4 KB
_shared/contracts/claim_standing/stance_record.schema.jsonconfig11.7 KB
_shared/contracts/claim_standing/transmission_ledger.schema.jsonconfig7.6 KB
_shared/contracts/cross_model/codex_citation_receipt.schema.jsonconfig4.7 KB
_shared/contracts/cross_model/codex_citation_request.schema.jsonconfig986 B
_shared/contracts/cross_model/promotion_bakeoff_sealed_commitment.schema.jsonconfig1.5 KB
_shared/contracts/cross_model/promotion_bakeoff_sealed_reveal.schema.jsonconfig1.5 KB
_shared/contracts/degradation_registry.jsonconfig42.5 KB
_shared/contracts/evaluator/full.jsonconfig6.3 KB
_shared/contracts/evidence/claim_registry.schema.jsonconfig2.3 KB
_shared/contracts/evidence/claim_registry_coverage_report.schema.jsonconfig4.8 KB
_shared/contracts/evidence/evidence_row.schema.jsonconfig14.3 KB
_shared/contracts/evidence/evidence_row_v1_1.schema.jsonconfig11.4 KB
_shared/contracts/evidence/evidence_row_v1_2.schema.jsonconfig21.8 KB
_shared/contracts/evidence/evidence_row_v1_3.schema.jsonconfig10.7 KB
_shared/contracts/human_subjects/authority_profile_registry.schema.jsonconfig16.7 KB
_shared/contracts/human_subjects/committee_correspondence.schema.jsonconfig9.9 KB
_shared/contracts/human_subjects/content_coverage_advisory.schema.jsonconfig19.9 KB
_shared/contracts/human_subjects/irb_context_record.schema.jsonconfig12.1 KB
_shared/contracts/human_subjects/resolved_authority_context.schema.jsonconfig11.8 KB
_shared/contracts/human_subjects/review_pathway_rule_trace.schema.jsonconfig9.5 KB
_shared/contracts/human_subjects/review_pathway_trace_request.schema.jsonconfig4.8 KB
_shared/contracts/human_subjects/submission_packet_inventory.schema.jsonconfig8.5 KB
_shared/contracts/human_subjects/submission_packet_manifest.schema.jsonconfig32.2 KB
_shared/contracts/passport/audit_artifact_entry.schema.jsonconfig10.8 KB
_shared/contracts/passport/bibliographic_integrity_signal.schema.jsonconfig48.9 KB
_shared/contracts/passport/citation_provenance.schema.jsonconfig4.8 KB
_shared/contracts/passport/citation_verification_summary.schema.jsonconfig8.2 KB
_shared/contracts/passport/claim_audit_result.schema.jsonconfig7.8 KB
_shared/contracts/passport/claim_drift.schema.jsonconfig3.8 KB
_shared/contracts/passport/claim_intent_manifest.schema.jsonconfig6.6 KB
_shared/contracts/passport/constraint_violation.schema.jsonconfig3.6 KB
_shared/contracts/passport/excluded_source_entry.schema.jsonconfig1.7 KB
_shared/contracts/passport/experiment_alignment_result.schema.jsonconfig4.8 KB
_shared/contracts/passport/experiment_provenance_entry.schema.jsonconfig10.0 KB
_shared/contracts/passport/human_read_log.schema.jsonconfig3.8 KB
_shared/contracts/passport/inquiry_ledger_ref.schema.jsonconfig881 B
_shared/contracts/passport/literature_corpus_entry.schema.jsonconfig30.3 KB
_shared/contracts/passport/preregistration_artifact.schema.jsonconfig4.3 KB
_shared/contracts/passport/rejection_log.schema.jsonconfig3.3 KB
_shared/contracts/passport/reset_ledger_entry.schema.jsonconfig7.1 KB
_shared/contracts/passport/run_ledger.schema.jsonconfig8.0 KB
_shared/contracts/passport/standing_constraint_entry.schema.jsonconfig2.6 KB
_shared/contracts/passport/temporal_audit_results.schema.jsonconfig8.8 KB
_shared/contracts/passport/terminal_policies.schema.jsonconfig8.1 KB
_shared/contracts/passport/timeline.schema.jsonconfig4.7 KB
_shared/contracts/passport/uncited_assertion.schema.jsonconfig3.3 KB
_shared/contracts/passport/uncited_audit_failure.schema.jsonconfig4.4 KB
_shared/contracts/passport/user_attested_read_resolution.schema.jsonconfig3.2 KB
_shared/contracts/passport/version_records.schema.jsonconfig4.9 KB
_shared/contracts/patch/block_manifest.schema.jsonconfig2.1 KB
_shared/contracts/patch/legacy/v1_0/revision_patch.schema.jsonconfig5.3 KB
_shared/contracts/patch/revision_patch.schema.jsonconfig8.9 KB
_shared/contracts/pdf/pdf_content_classifier_diagnostic.schema.jsonconfig1.2 KB
_shared/contracts/pdf/pdf_content_classifier_worker.schema.jsonconfig2.2 KB
_shared/contracts/pdf/pdf_read_preflight.schema.jsonconfig6.8 KB
_shared/contracts/re_review/input_manifest.schema.jsonconfig7.6 KB
_shared/contracts/re_review/legacy/v1_0/input_manifest.schema.jsonconfig6.2 KB
_shared/contracts/re_review/legacy/v1_0/precommitment.schema.jsonconfig8.9 KB
_shared/contracts/re_review/legacy/v1_0/traceability.schema.jsonconfig34.2 KB
_shared/contracts/re_review/legacy/v1_0/verdict_record.schema.jsonconfig10.5 KB
_shared/contracts/re_review/precommitment.schema.jsonconfig8.6 KB
_shared/contracts/re_review/traceability.schema.jsonconfig37.7 KB
_shared/contracts/re_review/verdict_record.schema.jsonconfig10.5 KB
_shared/contracts/research_workflow/inquiry_branch_ledger.schema.jsonconfig17.0 KB
_shared/contracts/research_workflow/research_workflow_profile.schema.jsonconfig7.2 KB
_shared/contracts/research_workflow/research_workflow_profile_selection_receipt.schema.jsonconfig3.9 KB
_shared/contracts/review_target/constructive_review_findings.schema.jsonconfig7.0 KB
_shared/contracts/review_target/criteria_registry.schema.jsonconfig4.0 KB
_shared/contracts/review_target/review_criteria_binding_manifest.schema.jsonconfig7.9 KB
_shared/contracts/review_target/review_criteria_source_receipt.schema.jsonconfig5.6 KB
_shared/contracts/review_target/review_target_context.schema.jsonconfig4.5 KB
_shared/contracts/review_target/review_target_declaration.schema.jsonconfig4.6 KB
_shared/contracts/reviewer/full.jsonconfig3.7 KB
_shared/contracts/reviewer/methodology_focus.jsonconfig2.2 KB
_shared/contracts/reviewer/review_panel_provenance.schema.jsonconfig7.8 KB
_shared/contracts/reviewer/review_panel_provenance_carrier.schema.jsonconfig4.1 KB
_shared/contracts/reviewer/review_panel_provenance_input.schema.jsonconfig3.5 KB
_shared/contracts/revision/author_adjudication.schema.jsonconfig7.8 KB
_shared/contracts/revision/author_adjudication_input.schema.jsonconfig1.2 KB
_shared/contracts/revision/claim_strength_drift_disposition.schema.jsonconfig3.6 KB
_shared/contracts/revision/claim_strength_drift_disposition_input.schema.jsonconfig3.1 KB
_shared/contracts/revision/claim_strength_drift_findings.schema.jsonconfig4.2 KB
_shared/contracts/revision/claim_surface_manifest.schema.jsonconfig3.3 KB
_shared/contracts/revision/integrity_correction_authorization.schema.jsonconfig4.3 KB
_shared/contracts/revision/integrity_correction_authorization_input.schema.jsonconfig1.5 KB
_shared/contracts/revision/integrity_correction_list.schema.jsonconfig1.8 KB
_shared/contracts/revision/integrity_pass_receipt.schema.jsonconfig809 B
_shared/contracts/revision/revision_evidence_bundle.schema.jsonconfig4.9 KB
_shared/contracts/revision/revision_roadmap.schema.jsonconfig11.2 KB
_shared/contracts/submission/format_profile.example.yamlconfig971 B
_shared/contracts/submission/format_profile.schema.jsonconfig4.6 KB
_shared/contracts/submission/submission_verification_report.schema.jsonconfig10.3 KB
_shared/contracts/submission/venue_profile.schema.jsonconfig4.1 KB
_shared/contracts/writer/full.jsonconfig3.6 KB
_shared/cross_model_verification.mdmarkdown83.3 KB
_shared/description-original.mdmarkdown1.3 KB
_shared/dsh-runtime.mdmarkdown1.5 KB
_shared/evals_lift_report.schema.jsonconfig5.0 KB
_shared/ground_truth_isolation_pattern.mdmarkdown16.0 KB
_shared/handoff_schemas.mdmarkdown96.9 KB
_shared/human_subjects_authority_registry.jsonconfig49.5 KB
_shared/mode_spectrum.mdmarkdown5.2 KB
_shared/model_tiering.mdmarkdown12.6 KB
_shared/output_language_pair.mdmarkdown7.7 KB
_shared/policy_data/nature_policy.mdmarkdown3.9 KB
_shared/prisma_trAIce_protocol.mdmarkdown10.2 KB
_shared/raise_framework.mdmarkdown7.5 KB
_shared/references/authority_content_coverage_advisory_protocol.mdmarkdown14.0 KB
_shared/references/claim_standing_candidate_ledger_protocol.mdmarkdown19.2 KB
_shared/references/claim_strength_ladder.mdmarkdown5.5 KB
_shared/references/cross_document_consistency_advisory_protocol.mdmarkdown13.5 KB
_shared/references/evidence_row_protocol.mdmarkdown14.4 KB
_shared/references/firm_rules.mdmarkdown11.0 KB
_shared/references/human_subjects_authority_protocol.mdmarkdown13.1 KB
_shared/references/intent_clarification_protocol.mdmarkdown11.9 KB
_shared/references/irb_terminology_glossary.mdmarkdown12.4 KB
_shared/references/per_source_method_weaknesses.mdmarkdown4.2 KB
_shared/references/protected_hedging_phrases.mdmarkdown8.9 KB
_shared/references/psychometric_terminology_glossary.mdmarkdown8.7 KB
_shared/references/review_criteria_consumer_protocol.mdmarkdown10.3 KB
_shared/references/review_form_note.mdmarkdown11.3 KB
_shared/references/review_pathway_rule_trace_protocol.mdmarkdown8.3 KB
_shared/references/routing_core.mdmarkdown5.7 KB
_shared/references/submission_packet_manifest_protocol.mdmarkdown13.6 KB
_shared/references/word_count_conventions.mdmarkdown9.0 KB
_shared/research_workflow_profiles/field_general.jsonconfig1.2 KB
_shared/review_criteria_registry.jsonconfig11.5 KB
_shared/review_criteria_sources/msr-2027-technical-papers.2026-08-24.jsonconfig2.0 KB
_shared/review_criteria_sources/sigsoft-empirical-standards.2026-08-24.jsonconfig1.4 KB
_shared/sprint_contract.schema.jsonconfig19.0 KB
_shared/style_calibration_protocol.mdmarkdown6.9 KB
_shared/templates/codex_audit_multifile_template.mdmarkdown16.7 KB
agents/bibliography_agent.mdmarkdown35.1 KB
agents/devils_advocate_agent.mdmarkdown11.6 KB
agents/editor_in_chief_agent.mdmarkdown8.5 KB
agents/ethics_review_agent.mdmarkdown22.3 KB
agents/meta_analysis_agent.mdmarkdown16.9 KB
agents/monitoring_agent.mdmarkdown9.8 KB
agents/report_compiler_agent.mdmarkdown26.7 KB
agents/research_architect_agent.mdmarkdown25.9 KB
agents/research_question_agent.mdmarkdown10.7 KB
agents/risk_of_bias_agent.mdmarkdown12.8 KB
agents/socratic_mentor_agent.mdmarkdown53.0 KB
agents/source_verification_agent.mdmarkdown10.9 KB
agents/synthesis_agent.mdmarkdown28.9 KB
agents/timeline_extraction_agent.mdmarkdown9.7 KB
examples/exploratory_research.mdmarkdown6.9 KB
examples/fact_check_mode.mdmarkdown12.9 KB
examples/handoff_to_paper.mdmarkdown12.5 KB
examples/idea_diversity_coverage_gap_advisory.mdmarkdown3.2 KB
examples/policy_analysis.mdmarkdown9.4 KB
examples/review_mode.mdmarkdown17.3 KB
examples/socratic_guided_research.mdmarkdown22.9 KB
examples/systematic_review.mdmarkdown7.7 KB
references/apa7_style_guide.mdmarkdown5.2 KB
references/argumentation_reasoning_framework.mdmarkdown4.5 KB
references/arxiv_api_protocol.mdmarkdown7.2 KB
references/changelog.mdmarkdown2.9 KB
references/chinese_literature_api_protocol.mdmarkdown35.0 KB
references/cross_agent_quality_definitions.mdmarkdown2.1 KB
references/crossref_api_protocol.mdmarkdown5.7 KB
references/equator_reporting_guidelines.mdmarkdown42.4 KB
references/ethics_checklist.mdmarkdown17.7 KB
references/failure_paths.mdmarkdown18.6 KB
references/interdisciplinary_bridges.mdmarkdown21.6 KB
references/irb_decision_tree.mdmarkdown19.7 KB
references/literature_monitoring_strategies.mdmarkdown11.2 KB
references/logical_fallacies.mdmarkdown11.0 KB
references/methodology_patterns.mdmarkdown17.6 KB
references/mode_selection_guide.mdmarkdown18.3 KB
references/openalex_api_protocol.mdmarkdown7.0 KB
references/preregistration_guide.mdmarkdown14.2 KB

_shared/contracts/re_review/traceability.schema.json

View on GitHub
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/re_review/traceability.schema.json",
  "title": "Re-review Phase 2B Traceability Sidecar (machine-readable Schema 11 sidecar)",
  "description": "Phase 2B (letter-revealed) final traceability artifact of the #576 Spec B three-gate re-review contract. Every difference between a committed 2A verdict and the final matrix verdict rides a typed AdjustmentRecord (closed basis set, §3.4); the 2A new-issue set is carried FROZEN (whole-record byte-identical, §13 witness); all user-answerable states (§6 G2) resolve through typed records inside the deferral loop, each re-emission incrementing revision and superseding the prior emission by hash. scripts/check_re_review_synthesis.py recomputes every invariant and the §6 decision derivation from this sidecar plus the raw artifacts. Spec: docs/design/2026-07-27-576-spec-b-re-review-precommitment-contract-spec.md §5.3.",

  "type": "object",
  "additionalProperties": false,
  "required": [
    "contract_version",
    "round_id",
    "revision",
    "verdict_record_hash",
    "rows",
    "adjustments",
    "new_issues",
    "post_letter_observations",
    "dissent_adjudications",
    "resolution_intents",
    "cross_model_resolutions",
    "rebuttal_adjudications",
    "g2d_acceptances",
    "pending_rebuttal_upgrades",
    "escalation_approvals",
    "reapplications",
    "decision_inputs",
    "decision_state"
  ],

  "properties": {
    "contract_version": { "const": "1.1" },
    "round_id": { "type": "string", "minLength": 1 },
    "revision": {
      "type": "integer",
      "minimum": 1,
      "description": "Starts at 1; each §6 deferral-loop re-emission increments it."
    },
    "supersedes_hash": {
      "$ref": "#/$defs/sha256",
      "description": "sha256 (JSON Canonical Form) of the superseded emission. Present iff revision >= 2."
    },
    "verdict_record_hash": {
      "$ref": "#/$defs/sha256",
      "description": "sha256 hex over the Phase 2A artifact's JSON Canonical Form. NEVER changes across re-emissions — the 2A artifact is immutable (§6 loop step 3). Third link of the §11 hash chain; the checker recomputes it."
    },
    "rows": {
      "type": "array",
      "items": { "$ref": "#/$defs/matrix_row" },
      "description": "EVERY Schema 7 roadmap item, all priorities, has exactly one row (Schema 11 completeness rule; checker-enforced)."
    },
    "adjustments": {
      "type": "array",
      "items": { "$ref": "#/$defs/adjustment_record" }
    },
    "new_issues": {
      "type": "array",
      "items": { "$ref": "#/$defs/new_issue_record" },
      "description": "The FROZEN 2A set, copied verbatim — WHOLE-RECORD byte-identical to §5.2, every field including found_by (§13 witness)."
    },
    "post_letter_observations": {
      "type": "array",
      "items": { "type": "string", "minLength": 1 },
      "description": "Free-form advisory entries noticed only after letter reveal; decision-inert; next-round seed (§3.3)."
    },
    "dissent_adjudications": {
      "type": "array",
      "items": { "$ref": "#/$defs/dissent_adjudication" }
    },
    "resolution_intents": {
      "type": "array",
      "items": { "$ref": "#/$defs/resolution_intent" }
    },
    "cross_model_resolutions": {
      "type": "array",
      "items": { "$ref": "#/$defs/cross_model_resolution" }
    },
    "rebuttal_adjudications": {
      "type": "array",
      "items": { "$ref": "#/$defs/rebuttal_adjudication" }
    },
    "g2d_acceptances": {
      "type": "array",
      "items": { "$ref": "#/$defs/g2d_acceptance" }
    },
    "pending_rebuttal_upgrades": {
      "type": "array",
      "items": { "$ref": "#/$defs/pending_rebuttal_upgrade" }
    },
    "escalation_approvals": {
      "type": "array",
      "items": { "$ref": "#/$defs/escalation_approval" }
    },
    "reapplications": {
      "type": "array",
      "items": { "$ref": "#/$defs/reapplication_record" }
    },
    "decision_inputs": { "$ref": "#/$defs/decision_inputs" },
    "decision_state": {
      "enum": ["Accept", "Minor Revision", "Major Revision", "user_review_required", "aborted"],
      "description": "The emitted outcome §13 compares against. Reject is NOT a Stage 3' decision (§6) — B1/B2 set DecisionInputs.reject_recommended instead."
    },
    "abort_reason": {
      "enum": [
        "phase1_lint_failed",
        "phase2a_lint_failed",
        "phase2b_lint_failed",
        "manifest_incomplete",
        "manifest_hash_mismatch",
        "criteria_drift",
        "synthesis_mismatch"
      ],
      "description": "§3.5 closed abort taxonomy. Required iff decision_state = aborted."
    }
  },

  "allOf": [
    {
      "if": {
        "required": ["revision"],
        "properties": { "revision": { "const": 1 } }
      },
      "then": { "not": { "required": ["supersedes_hash"] } },
      "else": { "required": ["supersedes_hash"] }
    },
    {
      "if": {
        "required": ["decision_state"],
        "properties": { "decision_state": { "const": "aborted" } }
      },
      "then": { "required": ["abort_reason"] },
      "else": { "not": { "required": ["abort_reason"] } }
    }
  ],

  "$defs": {
    "sha256": { "type": "string", "pattern": "^[0-9a-f]{64}$" },
    "item_id": { "type": "string", "pattern": "^REV-[A-Za-z0-9-]+$" },
    "nonempty_string": { "type": "string", "minLength": 1 },
    "verdict": {
      "enum": ["FULLY_ADDRESSED", "PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"]
    },
    "judge_verdict": {
      "enum": ["FULLY_ADDRESSED", "PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE"],
      "description": "The #539 judge's closed verdict set (no CANNOT_VERIFY)."
    },
    "verifier_seat": { "enum": ["EIC", "R1", "R2", "R3"] },
    "severity": { "enum": ["critical", "major", "minor"] },
    "typed_anchor": {
      "type": "string",
      "pattern": "^(text|table|figure|equation|dataset|absence): .+$"
    },
    "tagged_anchor": {
      "type": "object",
      "additionalProperties": false,
      "required": ["anchor", "anchor_artifact"],
      "properties": {
        "anchor": { "$ref": "#/$defs/typed_anchor" },
        "anchor_artifact": {
          "enum": ["manuscript", "letter"],
          "description": "Basis-enforced (§5.3): author_pointer_located_evidence and scope_correction anchors must be manuscript; valid_rebuttal may use either; cross_model_adjudication anchors are mechanically copied, tags included, from the referenced ReapplicationRecord."
        }
      }
    },
    "residual_gap": {
      "type": "object",
      "additionalProperties": false,
      "required": ["text", "residual_obligation_class"],
      "properties": {
        "text": { "$ref": "#/$defs/nonempty_string" },
        "residual_obligation_class": { "enum": ["must_fix", "should_fix", "consider"] }
      }
    },
    "verdict_count_map": {
      "type": "object",
      "additionalProperties": false,
      "required": ["FULLY_ADDRESSED", "PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"],
      "properties": {
        "FULLY_ADDRESSED": { "type": "integer", "minimum": 0 },
        "PARTIALLY_ADDRESSED": { "type": "integer", "minimum": 0 },
        "NOT_ADDRESSED": { "type": "integer", "minimum": 0 },
        "MADE_WORSE": { "type": "integer", "minimum": 0 },
        "CANNOT_VERIFY": { "type": "integer", "minimum": 0 }
      }
    },
    "residual_obligation_class_count_map": {
      "type": "object",
      "additionalProperties": false,
      "required": ["must_fix", "should_fix", "consider"],
      "properties": {
        "must_fix": { "type": "integer", "minimum": 0 },
        "should_fix": { "type": "integer", "minimum": 0 },
        "consider": { "type": "integer", "minimum": 0 }
      }
    },
    "author_target_scope": {
      "type": "object",
      "additionalProperties": false,
      "required": ["block_id", "allowed_operations"],
      "properties": {
        "block_id": { "type": "string", "pattern": "^(?:B[0-9]{4,}|DOC-BODY-START)$" },
        "allowed_operations": {
          "type": "array",
          "minItems": 1,
          "uniqueItems": true,
          "items": { "enum": ["replace_block", "insert_after", "delete_block"] }
        }
      }
    },
    "claim_strength_authorization": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "authorization_id", "author_event_id", "surface_id", "scoped_manifest_id",
        "claim_id", "block_id", "original_text_sha256", "replacement_text",
        "replacement_text_sha256", "from_rung", "to_rung", "direction", "reason"
      ],
      "properties": {
        "authorization_id": { "type": "string", "pattern": "^CLAIM-AUTH-[A-Za-z0-9._-]+$" },
        "author_event_id": { "type": "string", "pattern": "^AUTHOR-EVENT-[A-Za-z0-9._-]+$" },
        "surface_id": { "type": "string", "pattern": "^CLAIM-SURFACE-[A-Za-z0-9._-]+$" },
        "scoped_manifest_id": { "type": "string", "pattern": "^M-[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z-[0-9a-f]{4}$" },
        "claim_id": { "type": "string", "pattern": "^C-[0-9]{3,}$" },
        "block_id": { "type": "string", "pattern": "^B[0-9]{4,}$" },
        "original_text_sha256": { "$ref": "#/$defs/sha256" },
        "replacement_text": { "type": "string", "maxLength": 4000 },
        "replacement_text_sha256": { "$ref": "#/$defs/sha256" },
        "from_rung": { "$ref": "#/$defs/nonempty_string" },
        "to_rung": { "$ref": "#/$defs/nonempty_string" },
        "direction": { "enum": ["strengthen", "weaken"] },
        "reason": { "$ref": "#/$defs/nonempty_string" }
      }
    },

    "matrix_row": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "item_id",
        "concern_id",
        "obligation_class",
        "original_comment",
        "authors_claim",
        "revision_location",
        "verified",
        "status",
        "quality_assessment",
        "final_verdict",
        "phase2a_verdict",
        "verified_by",
        "author_triage",
        "authorized_targets",
        "claim_strength_authorizations"
      ],
      "properties": {
        "item_id": {
          "$ref": "#/$defs/item_id",
          "description": "The Schema 7 roadmap id — the JOIN KEY every §13 invariant uses; concern_id stays Schema 11's human numbering and is never used for joins."
        },
        "concern_id": { "type": "string", "pattern": "^[RSN][1-9][0-9]*$" },
        "obligation_class": {
          "enum": ["MUST_FIX", "SHOULD_FIX", "CONSIDER"],
          "description": "Schema 11 casing; the checker maps it mechanically onto the roadmap item's must_fix/should_fix/consider."
        },
        "original_comment": { "$ref": "#/$defs/nonempty_string" },
        "authors_claim": {
          "$ref": "#/$defs/nonempty_string",
          "description": "Under a letter-absent manifest, the §11 \"—\" fill is the recorded value (the must_fix non-empty requirement stands; contract mode derives verified from final_verdict)."
        },
        "revision_location": { "$ref": "#/$defs/nonempty_string" },
        "verified": {
          "enum": ["YES", "PARTIAL", "NO", "CANNOT_VERIFY"],
          "description": "Mechanical 5->4 map from final_verdict (§5.3): FULLY->YES, PARTIALLY->PARTIAL, NOT_ADDRESSED->NO, MADE_WORSE->NO, CANNOT_VERIFY->CANNOT_VERIFY. Checker-enforced."
        },
        "status": {
          "$ref": "#/$defs/verdict",
          "description": "Mechanical 1:1 map from final_verdict (Schema 11 status enum + the §16 CANNOT_VERIFY extension). Checker-enforced."
        },
        "quality_assessment": { "$ref": "#/$defs/nonempty_string" },
        "final_verdict": { "$ref": "#/$defs/verdict" },
        "phase2a_verdict": { "$ref": "#/$defs/verdict" },
        "verified_by": {
          "$ref": "#/$defs/verifier_seat",
          "description": "Copied from the item's §5.2 verdict record (checker-enforced equality)."
        },
        "author_triage": {
          "enum": ["will_address", "wont_address", "not_on_point"],
          "description": "Exact copy from the hash-bound #670 author-adjudication sidecar."
        },
        "author_reason": { "$ref": "#/$defs/nonempty_string" },
        "authorized_targets": {
          "type": "array",
          "uniqueItems": true,
          "items": { "$ref": "#/$defs/author_target_scope" },
          "description": "Exact full copy of the author-owned work scope; declined rows carry an empty array."
        },
        "claim_strength_authorizations": {
          "type": "array",
          "items": { "$ref": "#/$defs/claim_strength_authorization" },
          "description": "Exact full copy of the author-owned scoped claim authorizations; declined rows carry an empty array."
        },
        "adjustment_id": {
          "type": "string",
          "pattern": "^ADJ-[1-9][0-9]*$",
          "description": "Names the LATEST record of the item's adjustment chain. Present iff a chain exists (§5.3 row invariant)."
        },
        "addressed_by_rebuttal": {
          "const": true,
          "description": "Marker for a valid_rebuttal chain-tail upgrade to FULLY_ADDRESSED (§3.4)."
        },
        "cross_model_status": {
          "enum": ["agree", "diverges", "unavailable", "not_configured"],
          "description": "DERIVED PER EMISSION on the rows the #539 pass EVALUATED (those carrying cross_model_verdict): agree <=> cross_model_verdict = final_verdict, else diverges; unavailable/not_configured rows keep their recorded status. MUST_FIX rows always carry it; SHOULD_FIX/CONSIDER rows carry neither field."
        },
        "cross_model_verdict": {
          "$ref": "#/$defs/judge_verdict",
          "description": "The #539 judge's recorded verdict — immutable once the pass ran; present exactly on evaluated (agree/diverges) rows."
        }
      },
      "allOf": [
        {
          "if": {
            "required": ["author_triage"],
            "properties": {
              "author_triage": { "enum": ["wont_address", "not_on_point"] }
            }
          },
          "then": {
            "required": ["author_reason"],
            "properties": {
              "authorized_targets": { "maxItems": 0 },
              "claim_strength_authorizations": { "maxItems": 0 }
            }
          },
          "else": { "not": { "required": ["author_reason"] } }
        },
        {
          "if": {
            "required": ["obligation_class"],
            "properties": { "obligation_class": { "const": "MUST_FIX" } }
          },
          "then": { "required": ["cross_model_status"] },
          "else": {
            "not": {
              "anyOf": [
                { "required": ["cross_model_status"] },
                { "required": ["cross_model_verdict"] }
              ]
            }
          }
        },
        {
          "if": {
            "required": ["cross_model_status"],
            "properties": { "cross_model_status": { "enum": ["agree", "diverges"] } }
          },
          "then": { "required": ["cross_model_verdict"] },
          "else": { "not": { "required": ["cross_model_verdict"] } }
        }
      ]
    },

    "adjustment_record": {
      "type": "object",
      "additionalProperties": false,
      "required": ["adjustment_id", "item_id", "from_verdict", "to_verdict", "basis", "rationale"],
      "properties": {
        "adjustment_id": { "type": "string", "pattern": "^ADJ-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "from_verdict": { "$ref": "#/$defs/verdict" },
        "to_verdict": { "$ref": "#/$defs/verdict" },
        "basis": {
          "enum": [
            "author_pointer_located_evidence",
            "valid_rebuttal",
            "scope_correction",
            "user_accepted_fail_closed",
            "cross_model_adjudication"
          ]
        },
        "evidence_anchor": {
          "type": "array",
          "minItems": 1,
          "items": { "$ref": "#/$defs/tagged_anchor" }
        },
        "cannot_verify_reason": { "$ref": "#/$defs/nonempty_string" },
        "residual_gap": { "$ref": "#/$defs/residual_gap" },
        "critical_rebuttal_check": {
          "anyOf": [
            { "type": "string", "pattern": "^adjudicated:RADJ-[1-9][0-9]*$" },
            { "const": "single_family_disclosed" },
            { "const": "pass_unavailable_disclosed" }
          ],
          "description": "§3.4 closed union — present exactly on critical valid_rebuttal adjustments (checker-enforced against the roadmap's driving severity). single_family_disclosed is invalid on a run whose cross-model configuration was active."
        },
        "rationale": { "$ref": "#/$defs/nonempty_string" },
        "source_ref": {
          "type": "string",
          "pattern": "^(reapplication:RAP-[1-9][0-9]*|acceptance:ACC-[1-9][0-9]*)$",
          "description": "Basis-DISCRIMINATED: required reapplication:<id> iff basis = cross_model_adjudication; required acceptance:<id> iff basis = user_accepted_fail_closed; FORBIDDEN on every other basis."
        },
        "supersedes_adjustment_id": {
          "type": "string",
          "pattern": "^ADJ-[1-9][0-9]*$",
          "description": "Ordered-chain link: the prior latest record on the same item (§5.3 chain grammar)."
        }
      },
      "allOf": [
        {
          "if": {
            "required": ["to_verdict"],
            "properties": { "to_verdict": { "const": "CANNOT_VERIFY" } }
          },
          "then": {
            "required": ["cannot_verify_reason"],
            "properties": { "basis": { "const": "user_accepted_fail_closed" } },
            "not": { "required": ["evidence_anchor"] }
          },
          "else": {
            "required": ["evidence_anchor"],
            "not": { "required": ["cannot_verify_reason"] }
          }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": { "basis": { "const": "user_accepted_fail_closed" } }
          },
          "then": {
            "properties": {
              "to_verdict": { "const": "CANNOT_VERIFY" },
              "source_ref": { "pattern": "^acceptance:ACC-[1-9][0-9]*$" }
            },
            "required": ["source_ref"]
          }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": { "basis": { "const": "cross_model_adjudication" } }
          },
          "then": {
            "properties": {
              "source_ref": { "pattern": "^reapplication:RAP-[1-9][0-9]*$" }
            },
            "required": ["source_ref"]
          }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": {
              "basis": {
                "enum": ["author_pointer_located_evidence", "valid_rebuttal", "scope_correction"]
              }
            }
          },
          "then": { "not": { "required": ["source_ref"] } }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": {
              "basis": { "enum": ["author_pointer_located_evidence", "scope_correction"] }
            }
          },
          "then": {
            "properties": {
              "evidence_anchor": {
                "items": {
                  "properties": { "anchor_artifact": { "const": "manuscript" } }
                }
              }
            }
          }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": { "basis": { "const": "valid_rebuttal" } }
          },
          "then": {
            "properties": {
              "to_verdict": { "const": "FULLY_ADDRESSED" },
              "from_verdict": {
                "enum": ["PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"]
              }
            },
            "description": "§3.4 Direction column: valid_rebuttal is 'upgrade to FULLY_ADDRESSED' — the only basis allowing letter-side anchors must land on the fully-addressed verdict, or the persuasion channel §1 closes reopens."
          }
        },
        {
          "if": {
            "required": ["basis"],
            "properties": { "basis": { "const": "author_pointer_located_evidence" } }
          },
          "then": {
            "oneOf": [
              {
                "properties": {
                  "to_verdict": { "const": "FULLY_ADDRESSED" },
                  "from_verdict": {
                    "enum": ["PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"]
                  }
                }
              },
              {
                "properties": {
                  "to_verdict": { "const": "PARTIALLY_ADDRESSED" },
                  "from_verdict": {
                    "enum": ["NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"]
                  }
                }
              }
            ],
            "description": "§3.4 Direction column: author_pointer_located_evidence is an UPGRADE — located evidence satisfies the Phase-1 operationalization (fully or partially), so the target is PARTIALLY/FULLY and strictly better than the source (MADE_WORSE/CANNOT_VERIFY rank lowest)."
          }
        },
        {
          "if": {
            "required": ["to_verdict"],
            "properties": { "to_verdict": { "const": "PARTIALLY_ADDRESSED" } }
          },
          "then": { "required": ["residual_gap"] },
          "else": { "not": { "required": ["residual_gap"] } }
        },
        {
          "if": { "required": ["critical_rebuttal_check"] },
          "then": {
            "properties": { "basis": { "const": "valid_rebuttal" } }
          }
        }
      ]
    },

    "new_issue_record": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "new_issue_id",
        "description",
        "location_anchor",
        "severity",
        "found_by",
        "confidence",
        "competence_basis",
        "attribution",
        "attribution_evidence",
        "nearest_roadmap_item",
        "non_match_rationale"
      ],
      "properties": {
        "new_issue_id": { "type": "string", "pattern": "^NEW-[1-9][0-9]*$" },
        "description": { "$ref": "#/$defs/nonempty_string" },
        "location_anchor": { "$ref": "#/$defs/typed_anchor" },
        "severity": { "$ref": "#/$defs/severity" },
        "found_by": { "$ref": "#/$defs/verifier_seat" },
        "confidence": { "type": "integer", "minimum": 1, "maximum": 5 },
        "competence_basis": { "$ref": "#/$defs/nonempty_string" },
        "attribution": { "enum": ["regression", "previously_missed", "indeterminate"] },
        "attribution_evidence": { "$ref": "#/$defs/nonempty_string" },
        "nearest_roadmap_item": {
          "anyOf": [
            { "$ref": "#/$defs/item_id" },
            { "type": "null" }
          ]
        },
        "non_match_rationale": { "$ref": "#/$defs/nonempty_string" }
      }
    },

    "dissent_adjudication": {
      "type": "object",
      "additionalProperties": false,
      "required": ["dissent_id", "adjudicator", "outcome", "rationale"],
      "properties": {
        "dissent_id": { "type": "string", "pattern": "^DIS-[1-9][0-9]*$" },
        "adjudicator": { "enum": ["cross_model", "user"] },
        "outcome": { "enum": ["replacement_approved", "original_upheld"] },
        "rationale": { "$ref": "#/$defs/nonempty_string" }
      }
    },

    "resolution_intent": {
      "type": "object",
      "additionalProperties": false,
      "required": ["intent_id", "item_id", "answered_by"],
      "properties": {
        "intent_id": { "type": "string", "pattern": "^INT-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "answered_by": {
          "enum": ["system", "user"],
          "description": "system intents are emitted at Phase 2B completion for every must_fix diverges row; user intents exist only on the §6 fallback paths."
        },
        "guidance_note": { "$ref": "#/$defs/nonempty_string" }
      },
      "allOf": [
        {
          "if": {
            "required": ["answered_by"],
            "properties": { "answered_by": { "const": "system" } }
          },
          "then": { "not": { "required": ["guidance_note"] } }
        }
      ]
    },

    "cross_model_resolution": {
      "type": "object",
      "additionalProperties": false,
      "required": ["resolution_id", "item_id", "intent_id", "reapplication_id", "state", "resolved_by", "rationale"],
      "properties": {
        "resolution_id": { "type": "string", "pattern": "^RES-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "intent_id": { "type": "string", "pattern": "^INT-[1-9][0-9]*$" },
        "reapplication_id": { "type": "string", "pattern": "^RAP-[1-9][0-9]*$" },
        "state": { "enum": ["primary_upheld", "primary_revised"] },
        "resolved_by": {
          "enum": ["system", "user"],
          "description": "system: created mechanically when the reapplication derives a state (reapplied_verdict != CANNOT_VERIFY). user: the acceptance form — the user accepts primary_upheld on a CANNOT_VERIFY reapplication; the user never hand-sets a verdict."
        },
        "rationale": { "$ref": "#/$defs/nonempty_string" }
      },
      "allOf": [
        {
          "if": {
            "required": ["resolved_by"],
            "properties": { "resolved_by": { "const": "user" } }
          },
          "then": {
            "properties": { "state": { "const": "primary_upheld" } }
          }
        }
      ]
    },

    "rebuttal_adjudication": {
      "type": "object",
      "additionalProperties": false,
      "required": ["rebuttal_adjudication_id", "item_id", "verdict", "rationale"],
      "properties": {
        "rebuttal_adjudication_id": { "type": "string", "pattern": "^RADJ-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "verdict": {
          "enum": ["upheld", "challenged"],
          "description": "§3.4 critical-rebuttal pass: upheld books the drafted AdjustmentRecord; challenged means it is NEVER booked."
        },
        "rationale": { "$ref": "#/$defs/nonempty_string" }
      }
    },

    "g2d_acceptance": {
      "type": "object",
      "additionalProperties": false,
      "required": ["acceptance_id", "item_id", "reapplication_id", "accepted_by"],
      "properties": {
        "acceptance_id": { "type": "string", "pattern": "^ACC-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "reapplication_id": {
          "type": "string",
          "pattern": "^RAP-[1-9][0-9]*$",
          "description": "Must resolve to a CANNOT_VERIFY ReapplicationRecord on the same item (checker-enforced)."
        },
        "accepted_by": { "const": "user" }
      }
    },

    "pending_rebuttal_upgrade": {
      "type": "object",
      "additionalProperties": false,
      "required": ["proposal_id", "item_id", "drafted_adjustment", "disposition"],
      "properties": {
        "proposal_id": { "type": "string", "pattern": "^PRB-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "drafted_adjustment": {
          "type": "object",
          "additionalProperties": false,
          "required": ["item_id", "from_verdict", "to_verdict", "basis", "evidence_anchor", "rationale"],
          "properties": {
            "item_id": { "$ref": "#/$defs/item_id" },
            "from_verdict": {
              "enum": ["PARTIALLY_ADDRESSED", "NOT_ADDRESSED", "MADE_WORSE", "CANNOT_VERIFY"],
              "description": "§3.4 Direction: a rebuttal upgrade starts below FULLY_ADDRESSED."
            },
            "to_verdict": {
              "const": "FULLY_ADDRESSED",
              "description": "§3.4 Direction: valid_rebuttal upgrades to FULLY_ADDRESSED only."
            },
            "basis": { "const": "valid_rebuttal" },
            "evidence_anchor": {
              "type": "array",
              "minItems": 1,
              "items": { "$ref": "#/$defs/tagged_anchor" }
            },
            "residual_gap": { "$ref": "#/$defs/residual_gap" },
            "rationale": { "$ref": "#/$defs/nonempty_string" }
          },
          "description": "The full would-be AdjustmentRecord body. Content-equality with the booked record is checker-enforced field-for-field, excluding EXACTLY {adjustment_id, supersedes_adjustment_id, critical_rebuttal_check} (assigned at booking / by the dispatching layer); item_id is draft-time-known and NEVER excluded (§5.3)."
        },
        "disposition": {
          "anyOf": [
            { "type": "string", "pattern": "^booked:ADJ-[1-9][0-9]*$" },
            { "type": "string", "pattern": "^challenged:RADJ-[1-9][0-9]*$" },
            { "type": "string", "pattern": "^booked_disclosed:ADJ-[1-9][0-9]*$" },
            { "type": "string", "pattern": "^booked_single_family:ADJ-[1-9][0-9]*$" }
          ],
          "description": "booked: upheld by the §3.4 pass; challenged: never booked; booked_disclosed: active cross-model, pass unavailable (adjustment carries pass_unavailable_disclosed); booked_single_family: cross-model not configured (adjustment carries single_family_disclosed)."
        }
      }
    },

    "escalation_approval": {
      "type": "object",
      "additionalProperties": false,
      "required": ["exception_id", "approval_state", "approved_by"],
      "properties": {
        "exception_id": { "type": "string", "pattern": "^ESC-[1-9][0-9]*$" },
        "approval_state": { "enum": ["approved", "rejected"] },
        "approved_by": { "const": "user" }
      }
    },

    "reapplication_record": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "reapplication_id",
        "item_id",
        "answer_refs",
        "pre_reapplication_verdict",
        "reapplied_verdict",
        "rationale",
        "criterion_ref"
      ],
      "properties": {
        "reapplication_id": { "type": "string", "pattern": "^RAP-[1-9][0-9]*$" },
        "item_id": { "$ref": "#/$defs/item_id" },
        "answer_refs": {
          "type": "array",
          "minItems": 1,
          "uniqueItems": true,
          "items": {
            "type": "string",
            "pattern": "^(adjudication:DIS-[1-9][0-9]*|intent:INT-[1-9][0-9]*)$"
          },
          "description": "Tagged refs to the answers this re-application discharges. A G2(b)/G2(d) retry's refs are CUMULATIVE: the original mandating answer PLUS every retry ResolutionIntent to date (§6)."
        },
        "supersedes_reapplication_id": {
          "type": "string",
          "pattern": "^RAP-[1-9][0-9]*$",
          "description": "A retry names the failed attempt it supersedes; the failed record is preserved. Per mandating answer exactly ONE reapplication is CURRENT (non-superseded)."
        },
        "pre_reapplication_verdict": {
          "$ref": "#/$defs/verdict",
          "description": "The row's verdict at dispatch — the chain tail before this loop iteration, or phase2a_verdict when no chain. The TIME ANCHOR every §9 comparison binds to."
        },
        "reapplied_verdict": { "$ref": "#/$defs/verdict" },
        "evidence_anchor": {
          "type": "array",
          "minItems": 1,
          "items": { "$ref": "#/$defs/tagged_anchor" }
        },
        "cannot_verify_reason": {
          "$ref": "#/$defs/nonempty_string",
          "description": "Required iff reapplied_verdict = CANNOT_VERIFY. An undispatchable/crashed 2B' call is recorded by the ORCHESTRATOR with reason \"dispatch_failed: <why>\" — a transport fact, not a verification judgment (§6)."
        },
        "residual_gap": { "$ref": "#/$defs/residual_gap" },
        "rationale": { "$ref": "#/$defs/nonempty_string" },
        "criterion_ref": {
          "type": "string",
          "pattern": "^(phase1:REV-[A-Za-z0-9-]+|dissent:DIS-[1-9][0-9]*)$",
          "description": "EFFECTIVE-criterion rule (§6): adjudication-mandated -> phase1 (re-applying the ORIGINAL is its definition); divergence-only -> dissent:<id> when a replacement_approved adjudication exists for the item, else phase1."
        }
      },
      "allOf": [
        {
          "if": {
            "required": ["reapplied_verdict"],
            "properties": { "reapplied_verdict": { "const": "CANNOT_VERIFY" } }
          },
          "then": {
            "required": ["cannot_verify_reason"],
            "not": { "required": ["evidence_anchor"] }
          },
          "else": {
            "required": ["evidence_anchor"],
            "not": { "required": ["cannot_verify_reason"] }
          }
        },
        {
          "if": {
            "required": ["reapplied_verdict"],
            "properties": { "reapplied_verdict": { "const": "PARTIALLY_ADDRESSED" } }
          },
          "then": { "required": ["residual_gap"] },
          "else": { "not": { "required": ["residual_gap"] } }
        }
      ]
    },

    "decision_inputs": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "per_item",
        "verdict_counts",
        "residual_obligation_class_counts",
        "should_fix_addressed_rate",
        "regressions",
        "non_regression_new_issue_ids",
        "escalations",
        "apply_chain_witness"
      ],
      "properties": {
        "per_item": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "required": ["item_id", "final_verdict", "driving_severity"],
            "properties": {
              "item_id": { "$ref": "#/$defs/item_id" },
              "final_verdict": { "$ref": "#/$defs/verdict" },
              "driving_severity": {
                "anyOf": [
                  { "$ref": "#/$defs/severity" },
                  { "type": "null" }
                ],
                "description": "null for source_kind items and legacy roadmaps whose Schema 7 severity is legitimately absent — B1 treats null as NOT critical, never fabricating a severity."
              },
              "residual_obligation_class": {
                "enum": ["must_fix", "should_fix", "consider"],
                "description": "The magnitude on the record that set the item's FINAL verdict (chain-tail adjustment or its reapplication when adjusted; else the 2A verdict record)."
              }
            }
          },
          "description": "Per-must_fix-item operands for §6 Steps 2-3."
        },
        "verdict_counts": {
          "type": "object",
          "additionalProperties": false,
          "required": ["must_fix", "should_fix", "consider"],
          "properties": {
            "must_fix": { "$ref": "#/$defs/verdict_count_map" },
            "should_fix": { "$ref": "#/$defs/verdict_count_map" },
            "consider": { "$ref": "#/$defs/verdict_count_map" }
          }
        },
        "residual_obligation_class_counts": {
          "type": "object",
          "additionalProperties": false,
          "required": ["must_fix", "should_fix", "consider"],
          "properties": {
            "must_fix": { "$ref": "#/$defs/residual_obligation_class_count_map" },
            "should_fix": { "$ref": "#/$defs/residual_obligation_class_count_map" },
            "consider": { "$ref": "#/$defs/residual_obligation_class_count_map" }
          },
          "description": "Per-obligation_class residual_obligation_class counts over PARTIALLY_ADDRESSED rows (final verdicts)."
        },
        "should_fix_addressed_rate": {
          "type": "object",
          "additionalProperties": false,
          "required": ["numerator", "denominator"],
          "properties": {
            "numerator": { "type": "integer", "minimum": 0 },
            "denominator": { "type": "integer", "minimum": 0 }
          },
          "description": "§6 definition: numerator = should_fix items with final_verdict in {FULLY_ADDRESSED, PARTIALLY_ADDRESSED}; denominator = all should_fix items; zero should_fix items -> vacuously 100%. Computed over final post-2B verdicts."
        },
        "regressions": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "required": ["new_issue_id", "severity"],
            "properties": {
              "new_issue_id": { "type": "string", "pattern": "^NEW-[1-9][0-9]*$" },
              "severity": { "$ref": "#/$defs/severity" }
            }
          }
        },
        "non_regression_new_issue_ids": {
          "type": "array",
          "items": { "type": "string", "pattern": "^NEW-[1-9][0-9]*$" },
          "description": "Frozen previously_missed + indeterminate ids — never in the decision path (§6 goalpost guard)."
        },
        "escalations": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "required": ["exception_id", "effective_approval_state", "escalation_class", "mechanical_decision_impact"],
            "properties": {
              "exception_id": { "type": "string", "pattern": "^ESC-[1-9][0-9]*$" },
              "effective_approval_state": {
                "enum": ["pending", "approved", "rejected"],
                "description": "JOINED from the EscalationApproval via exception_id (pending when none exists); the EscalationExceptionRecord's own field is the literal emission constant and is never copied here."
              },
              "escalation_class": {
                "enum": ["research_integrity", "ethics", "safety", "legal_compliance", "fatal_validity"]
              },
              "mechanical_decision_impact": { "enum": ["Minor Revision", "Major Revision"] }
            }
          }
        },
        "reject_recommended": {
          "type": "boolean",
          "description": "PRESENT iff the emission is non-gated (§6 Steps 2-3 ran) — on a gated emission the field is ABSENT, never a fabricated false (checker-enforced presence biconditional). True on B1/B2 or an approved research_integrity-class exception."
        },
        "apply_chain_witness": {
          "enum": ["pass", "fail", "not_run_no_reports"],
          "description": "§11 current closed composite with declared TOTAL PRECEDENCE fail > not_run_no_reports > pass. Original manuscript is hard-required in 1.1; first_link_not_run remains archived in 1.0 only. Compared on every emission kind (§13)."
        }
      }
    }
  }
}
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall