{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "ai-oct-sindy",
    "title": "SINDy sparse identification of nonlinear dynamics",
    "summary": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models.",
    "boundary": "Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.",
    "area": "Scientific machine learning",
    "topic": "Artificial intelligence",
    "year": 2015,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "ai-oct-sindy",
    "target": {
      "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
      "version": 1,
      "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
    },
    "humans": [
      "Steven L. Brunton",
      "Joshua L. Proctor",
      "J. Nathan Kutz"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "src-ai-oct-1509-03580v1-primary",
        "title": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
        "url": "https://arxiv.org/pdf/1509.03580v1"
      }
    ],
    "points": "270000",
    "published_grade": {
      "id": "ai-oct-sindy",
      "entry_id": "ai-oct-sindy",
      "band": "S",
      "modifier": "-",
      "target": {
        "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
        "version": 1,
        "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
      },
      "what_changed": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models.",
      "scope": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models. Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
        "version": 1,
        "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Steven L. Brunton",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
            "url": "https://arxiv.org/pdf/1509.03580v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Joshua L. Proctor",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
            "url": "https://arxiv.org/pdf/1509.03580v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "J. Nathan Kutz",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
            "url": "https://arxiv.org/pdf/1509.03580v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
            "url": "https://arxiv.org/pdf/1509.03580v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.",
        "domain": "Scientific machine learning"
      },
      "sources": [
        {
          "citation": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
          "url": "https://arxiv.org/pdf/1509.03580v1"
        }
      ],
      "statement": "# SINDy sparse identification of nonlinear dynamics\n\n## The question\n\nImagine watching a system move and wanting an understandable equation for its motion. A flexible neural predictor might fit the observations without giving a short law. SINDy starts with a different hope: in suitable coordinates, the dynamics may use only a few terms from a larger library of possible functions. The task is to identify which terms are needed.\n\n## The idea\n\nThe method combines measured states, estimates of their time derivatives and a table of candidate functions. Sparse regression favors an equation using relatively few library terms while fitting the derivative data. Sparsity means few nonzero coefficients, not necessarily a universally simple truth. The answer depends on the chosen library, coordinates, measurements and treatment of noise.\n\n## Why it matters\n\nThe field-enabling value is a practical connection between data and interpretable candidate dynamical models. It does not invent sparse regression or guarantee automatic discovery of arbitrary governing laws. Several different equations can agree on a limited trajectory. Good identification therefore needs conditions that distinguish candidates, plus validation on observations not used to select the expression.\n\n## A teaching example\n\nFor an original classroom example, suppose synthetic measurements were generated by dx/dt = -0.5x. Offer a library containing a constant, x and x squared. A successful procedure should favor the linear term in this controlled setting. Now add measurement noise before estimating derivatives: small differences between nearby measurements can amplify noise. The resulting difficulty is about the measurement-and-identification pipeline, not a mysterious failure of algebra.\n\n## Scope and a useful next step\n\nReproduce a small synthetic system while keeping the true equation hidden from the selection code. Vary noise and sampling rate, then test predictions from new initial conditions. Record which library was allowed and which incorrect terms appeared. A concise but wrong equation is still wrong; a useful contribution explains the conditions under which the recovered expression remains reliable. Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.\n\n## Scientific scope\n\nSparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.\n\n## Sources for this explanation\n\n- [Discovering governing equations from data: Sparse identification of nonlinear dynamical systems](https://arxiv.org/pdf/1509.03580v1): Pinned original contribution and its stated method, assumptions and limits. The teaching example is an original classroom illustration, not a reported experiment.\n",
      "summary": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models.",
      "title": "SINDy sparse identification of nonlinear dynamics"
    },
    "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
      "version": 1,
      "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:2e7034aa1c9c323b581a46ae7df98547f0a93da077e08d7f10c1179360f44c8c"
  },
  "target": {
    "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
    "version": 1,
    "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "ai-oct-sindy",
    "entry_id": "ai-oct-sindy",
    "revision": 1,
    "title": "SINDy sparse identification of nonlinear dynamics",
    "context": "Scientific machine learning",
    "track": "Human-designed research method or resource",
    "band": "S",
    "modifier": "-",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models.",
    "scope": "Regresses measured state derivatives onto a candidate nonlinear-function library using sparsity, including sequential thresholded least squares, to identify compact dynamical models. Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.",
    "evidence_summary": "The linked original sources describe this contribution and its evidence limits. WRS has not independently reconstructed the full scientific claims. Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness.",
    "references": [
      {
        "title": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
        "url": "https://arxiv.org/pdf/1509.03580v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
      "version": 1,
      "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "270000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": {
    "id": "ai-oct-sindy",
    "target": {
      "record_id": "urn:uuid:6ebfdcba-ab65-4b23-a81c-9e36789d2075",
      "version": 1,
      "content_hash": "sha256:04aefc35c702c5dbb2db0f654d0fcf4ddbaff843bc09615b9130fe50944830dd"
    },
    "sections": [
      {
        "title": "The question",
        "text": "Imagine watching a system move and wanting an understandable equation for its motion. A flexible neural predictor might fit the observations without giving a short law. SINDy starts with a different hope: in suitable coordinates, the dynamics may use only a few terms from a larger library of possible functions. The task is to identify which terms are needed."
      },
      {
        "title": "The idea",
        "text": "The method combines measured states, estimates of their time derivatives and a table of candidate functions. Sparse regression favors an equation using relatively few library terms while fitting the derivative data. Sparsity means few nonzero coefficients, not necessarily a universally simple truth. The answer depends on the chosen library, coordinates, measurements and treatment of noise."
      },
      {
        "title": "Why it matters",
        "text": "The field-enabling value is a practical connection between data and interpretable candidate dynamical models. It does not invent sparse regression or guarantee automatic discovery of arbitrary governing laws. Several different equations can agree on a limited trajectory. Good identification therefore needs conditions that distinguish candidates, plus validation on observations not used to select the expression."
      },
      {
        "title": "A teaching example",
        "text": "For an original classroom example, suppose synthetic measurements were generated by dx/dt = -0.5x. Offer a library containing a constant, x and x squared. A successful procedure should favor the linear term in this controlled setting. Now add measurement noise before estimating derivatives: small differences between nearby measurements can amplify noise. The resulting difficulty is about the measurement-and-identification pipeline, not a mysterious failure of algebra."
      },
      {
        "title": "Scope and a useful next step",
        "text": "Reproduce a small synthetic system while keeping the true equation hidden from the selection code. Vary noise and sampling rate, then test predictions from new initial conditions. Record which library was allowed and which incorrect terms appeared. A concise but wrong equation is still wrong; a useful contribution explains the conditions under which the recovered expression remains reliable. Sparsity is relative to chosen library/coordinates; adequate measurements, derivative quality and identifiability matter. No recovery of arbitrary governing laws, invention of LASSO or universal noise robustness."
      }
    ],
    "references": [
      {
        "title": "Discovering governing equations from data: Sparse identification of nonlinear dynamical systems",
        "url": "https://arxiv.org/pdf/1509.03580v1",
        "locator": "Pinned original contribution and its stated method, assumptions and limits. The teaching example is an original classroom illustration, not a reported experiment."
      }
    ]
  },
  "reading_status": "EXPLANATORY_GUIDE"
}