Skip to content

K-Dense-AI/scientific-agent-skills / skills/hypothesis-generation

hypothesis-generation

Verified

Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.

assets/hypothesis_record_template.json

View on GitHub
{
  "schema_version": "2.0",
  "project_id": "HG-SYN-001",
  "status": "draft",
  "updated_on": "2026-07-23",
  "human_owner": "Accountable human investigator",
  "observation": {
    "statement": "In a synthetic demonstration dataset, units measured after condition X had a different mean value of outcome Y than units measured after the comparator condition.",
    "provenance": "Synthetic demonstration only; no human, animal, clinical, proprietary, or security-sensitive data.",
    "source_ids": [
      "SRC-SYN-001"
    ],
    "uncertainties": [
      "The synthetic pattern could reflect the generating process, selection, measurement, or random variation."
    ]
  },
  "research_question": {
    "statement": "In the synthetic target system, what is the effect of assigning condition X rather than the comparator on outcome Y after one measurement interval?",
    "framework": "PICO",
    "question_type": "causal",
    "population_or_system": "Synthetic independent units meeting the declared eligibility rule",
    "intervention_or_exposure": "Assignment to synthetic condition X",
    "comparator": "Assignment to the synthetic comparator condition",
    "outcome": "Validated synthetic outcome Y",
    "timeframe": "One prespecified measurement interval"
  },
  "hypotheses": [
    {
      "hypothesis_id": "H1",
      "statement": "Condition X changes outcome Y through the proposed synthetic process M.",
      "mechanism": "Condition X changes intermediate M before outcome Y is measured.",
      "status": "candidate",
      "source_ids": [
        "SRC-SYN-001"
      ],
      "assumptions": [
        "The synthetic assignment and measurement procedures operate as declared."
      ],
      "boundary_conditions": [
        "The candidate is limited to the declared synthetic units and one-interval horizon."
      ],
      "uncertainties": [
        "The intermediate may be a marker rather than a mediator."
      ],
      "prediction_ids": [
        "P1"
      ],
      "rival_hypothesis_ids": [
        "H2"
      ]
    },
    {
      "hypothesis_id": "H2",
      "statement": "The observed difference in outcome Y is produced by a synthetic measurement drift rather than process M.",
      "mechanism": "A time-linked offset changes the recorded outcome without changing the target construct.",
      "status": "candidate",
      "source_ids": [
        "SRC-SYN-001"
      ],
      "assumptions": [
        "The synthetic measurement offset is not removed by calibration."
      ],
      "boundary_conditions": [
        "The candidate applies only to measurements from the affected synthetic acquisition period."
      ],
      "uncertainties": [
        "The size and stability of any offset are unknown."
      ],
      "prediction_ids": [
        "P2"
      ],
      "rival_hypothesis_ids": [
        "H1"
      ]
    }
  ],
  "causal_estimands": [
    {
      "estimand_id": "E1",
      "linked_hypothesis_ids": [
        "H1"
      ],
      "population": "Synthetic eligible units",
      "intervention_or_exposure": "Assignment to condition X",
      "comparator": "Assignment to comparator",
      "outcome": "Outcome Y measured with method M-OUTCOME",
      "time_horizon": "One measurement interval",
      "population_summary": "Difference in population mean outcome Y",
      "intercurrent_event_strategy": "Not applicable in the synthetic demonstration",
      "identification_assumptions": [
        "Random assignment, no interference, consistent treatment versions, and valid outcome measurement."
      ]
    }
  ],
  "predictions": [
    {
      "prediction_id": "P1",
      "hypothesis_id": "H1",
      "statement": "Under matched acquisition conditions, assignment to X will precede a change in intermediate M and then outcome Y.",
      "observable": "Ordered changes in intermediate M and outcome Y",
      "conditions": "Synthetic units are randomly assigned and measured with calibrated instruments.",
      "expected_pattern": "Intermediate M changes before outcome Y in X but not comparator units.",
      "falsifier": "Outcome Y changes without the prespecified change in intermediate M under a successful manipulation and valid measurements.",
      "rival_hypothesis_ids": [
        "H2"
      ],
      "measurement_ids": [
        "M-INTERMEDIATE",
        "M-OUTCOME"
      ],
      "analysis_ids": [
        "A1"
      ]
    },
    {
      "prediction_id": "P2",
      "hypothesis_id": "H2",
      "statement": "A reference quantity measured in the same acquisition period will show a similar offset even though process M cannot affect it.",
      "observable": "Offset in the negative-control reference quantity",
      "conditions": "The same acquisition and calibration workflow is used.",
      "expected_pattern": "The reference quantity and outcome Y shift together by acquisition period.",
      "falsifier": "The reference quantity remains stable while outcome Y changes reproducibly across independently calibrated periods.",
      "rival_hypothesis_ids": [
        "H1"
      ],
      "measurement_ids": [
        "M-NEGATIVE-CONTROL",
        "M-OUTCOME"
      ],
      "analysis_ids": [
        "A2"
      ]
    }
  ],
  "alternative_explanations": [
    {
      "alternative_id": "ALT1",
      "statement": "Synthetic selection into the analyzed set creates the observed difference.",
      "linked_hypothesis_ids": [
        "H1",
        "H2"
      ],
      "risk_types": [
        "selection_bias"
      ],
      "discriminating_prediction_ids": [
        "P1",
        "P2"
      ]
    }
  ],
  "null_hypotheses": [
    {
      "null_id": "N1",
      "statement": "The population mean of outcome Y is equal under assignment to X and comparator at the prespecified horizon.",
      "linked_prediction_ids": [
        "P1"
      ],
      "rejection_or_compatibility_rule": "Use the prespecified interval estimate and decision rule in analysis A1; do not equate failure to reject with equivalence."
    },
    {
      "null_id": "N2",
      "statement": "The synthetic negative-control reference mean is equal across acquisition periods.",
      "linked_prediction_ids": [
        "P2"
      ],
      "rejection_or_compatibility_rule": "Use analysis A2 as a bias diagnostic; failure to reject does not prove absence of drift when precision or reference sensitivity is insufficient."
    }
  ],
  "negative_controls": [
    {
      "control_id": "NC1",
      "control_type": "negative_outcome",
      "rationale": "The reference quantity cannot be changed by process M but shares the synthetic acquisition workflow.",
      "expected_result": "No difference by assigned condition after accounting for acquisition period.",
      "failure_implication": "A non-null control result raises concern about acquisition, selection, or analysis bias.",
      "linked_prediction_ids": [
        "P2"
      ]
    }
  ],
  "operationalizations": [
    {
      "measurement_id": "M-INTERMEDIATE",
      "construct": "Synthetic intermediate M",
      "variable": "m_value",
      "role": "mediator",
      "operational_definition": "Calibrated continuous synthetic measurement at the prespecified early time.",
      "instrument_or_method": "Deterministic synthetic measurement procedure",
      "unit": "synthetic units",
      "timing": "Early prespecified time",
      "population_or_system": "Synthetic eligible units",
      "validity_evidence_source_ids": [
        "SRC-SYN-001"
      ],
      "reliability_plan": "Repeat the deterministic check on an independent synthetic batch.",
      "missingness_plan": "Report missingness by assignment and use the prespecified sensitivity analysis.",
      "blinding_or_masking": "Synthetic analyst label is masked until validation completes.",
      "threshold_rationale": "No threshold; analyze the continuous measurement."
    },
    {
      "measurement_id": "M-OUTCOME",
      "construct": "Synthetic outcome Y",
      "variable": "y_value",
      "role": "outcome",
      "operational_definition": "Calibrated continuous synthetic outcome at one interval.",
      "instrument_or_method": "Deterministic synthetic measurement procedure",
      "unit": "synthetic units",
      "timing": "One prespecified measurement interval",
      "population_or_system": "Synthetic eligible units",
      "validity_evidence_source_ids": [
        "SRC-SYN-001"
      ],
      "reliability_plan": "Verify calibration and repeatability before unmasking assignment.",
      "missingness_plan": "Report reasons and analyze under the prespecified primary and sensitivity assumptions.",
      "blinding_or_masking": "Outcome acquisition and validation are masked to assignment.",
      "threshold_rationale": "No threshold; estimate the continuous mean contrast."
    },
    {
      "measurement_id": "M-NEGATIVE-CONTROL",
      "construct": "Synthetic reference quantity",
      "variable": "reference_value",
      "role": "negative_control",
      "operational_definition": "Stable synthetic reference measured in the same acquisition workflow.",
      "instrument_or_method": "Deterministic synthetic reference procedure",
      "unit": "synthetic reference units",
      "timing": "Concurrent with outcome Y",
      "population_or_system": "Synthetic acquisition batches",
      "validity_evidence_source_ids": [
        "SRC-SYN-001"
      ],
      "reliability_plan": "Check repeatability across synthetic batches.",
      "missingness_plan": "Treat a missing reference as an acquisition-quality failure.",
      "blinding_or_masking": "Reference processing is independent of assignment labels.",
      "threshold_rationale": "Use the prespecified calibration tolerance."
    }
  ],
  "analysis_plan": {
    "analyses": [
      {
        "analysis_id": "A1",
        "prediction_ids": [
          "P1"
        ],
        "estimand_ids": [
          "E1"
        ],
        "analysis_population": "All randomized synthetic eligible units under the declared estimand strategy",
        "method": "Estimate the prespecified mean contrast with its uncertainty interval.",
        "effect_or_summary_measure": "Difference in population means",
        "uncertainty_method": "Prespecified interval estimate under the declared independent-unit assumptions",
        "missing_data_plan": "Primary declared assumption plus a bounded sensitivity analysis",
        "multiplicity_plan": "A1 is the sole confirmatory contrast; all additional contrasts are exploratory.",
        "sensitivity_analyses": [
          "Repeat under the prespecified alternative missingness assumption."
        ],
        "decision_rule": "Interpret compatibility with predicted patterns and rivals; do not select a hypothesis automatically.",
        "exploratory_or_confirmatory": "confirmatory"
      },
      {
        "analysis_id": "A2",
        "prediction_ids": [
          "P2"
        ],
        "estimand_ids": [],
        "analysis_population": "All synthetic acquisition batches with valid reference measurements",
        "method": "Estimate reference shifts by acquisition period and assigned condition.",
        "effect_or_summary_measure": "Difference in reference means",
        "uncertainty_method": "Prespecified interval estimate",
        "missing_data_plan": "Report and exclude acquisition failures according to the locked quality rule.",
        "multiplicity_plan": "Negative-control analysis is interpreted as a bias diagnostic, not a candidate-selection score.",
        "sensitivity_analyses": [
          "Repeat after excluding the prespecified failed-calibration batch category."
        ],
        "decision_rule": "A non-null reference shift triggers investigation and limits causal interpretation.",
        "exploratory_or_confirmatory": "confirmatory"
      }
    ],
    "harking_control": "Freeze this record before viewing the target synthetic outcomes and label later candidates or analyses exploratory.",
    "deviation_reporting": "Preserve the original plan and log each deviation with date, rationale, decision owner, result-awareness status, and interpretive impact."
  },
  "evidence": {
    "ledger_path": "local-evidence-ledger.csv",
    "source_ids": [
      "SRC-SYN-001"
    ],
    "search_boundary_id": "SEARCH-SYN-001",
    "evidence_limitations": [
      "The bundled row is synthetic and demonstrates structure only."
    ]
  },
  "risk_register": {
    "confounding": [
      "Synthetic assignment failure or implementation differences could act as common causes."
    ],
    "selection_bias": [
      "Post-assignment exclusion could make analyzed groups non-comparable."
    ],
    "collider_bias": [
      "Restricting analysis to a jointly caused quality indicator could open bias."
    ],
    "reverse_causation": [
      "Temporal ordering is built into the synthetic design but must be verified."
    ],
    "measurement_bias": [
      "Acquisition-period drift could change recorded outcome Y."
    ],
    "other": [
      "Random variation and model misspecification remain possible."
    ]
  },
  "ethics_and_feasibility": {
    "human_subjects_gate": "not_applicable",
    "animal_research_gate": "not_applicable",
    "biosafety_gate": "not_applicable",
    "dual_use_gate": "not_applicable",
    "regulatory_gate": "not_applicable",
    "data_governance_gate": "approved",
    "feasibility_status": "feasible_for_planning",
    "required_reviews": [],
    "unresolved_blocks": []
  },
  "ai_use": {
    "used": false,
    "sensitive_or_unpublished_data_sent_externally": false,
    "local_policy_checked": true,
    "citation_verification_required": true,
    "human_accountable": true,
    "diversity_mitigation": "Generate independent rivals before any authorized AI-assisted expansion and retain human-origin candidates."
  }
}
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