{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "ferminet",
    "title": "FermiNet: learning quantum wavefunctions",
    "summary": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules.",
    "boundary": "These are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.",
    "area": "Chemistry & materials",
    "topic": "Chemistry & materials",
    "year": 2020,
    "lane": "AI",
    "result": "EMPIRICAL",
    "package_id": "ferminet",
    "target": {
      "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
      "version": 1,
      "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
    },
    "humans": [
      "David Pfau",
      "James S. Spencer",
      "Alexander G. D. G. Matthews",
      "W. M. C. Foulkes"
    ],
    "authors_complete": true,
    "human_role_note": "Full deposited paper byline or identified author of the scoped historical source. Association does not measure individual effort.",
    "agents": [
      {
        "provider": "Google DeepMind",
        "product": "FermiNet",
        "model": "Fermionic neural network",
        "role": "Variational wavefunction optimization; human-led ansatz design and numerical evaluation",
        "assurance": "SOURCE_REPORTED",
        "source": "rc3-paper-ferminet"
      }
    ],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "rc3-paper-ferminet",
        "title": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks",
        "url": "https://link.aps.org/doi/10.1103/PhysRevResearch.2.033429"
      },
      {
        "id": "rc3-metadata-ferminet",
        "title": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks — deposited bibliography",
        "url": "https://api.crossref.org/works/10.1103%2Fphysrevresearch.2.033429"
      }
    ],
    "geography": {
      "country_codes": [
        "GB"
      ],
      "location_basis": "DeepMind, London, and Department of Physics, Imperial College London; all authors’ original paper affiliations.",
      "source_url": "https://journals.aps.org/prresearch/abstract/10.1103/PhysRevResearch.2.033429",
      "target": {
        "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
        "version": 1,
        "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-12",
      "nationality_inferred": false,
      "coverage_status": "COMPLETE",
      "country_labels": {
        "GB": "United Kingdom"
      }
    },
    "points": "18000",
    "published_grade": {
      "id": "ferminet",
      "entry_id": "ferminet",
      "band": "B",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
        "version": 1,
        "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
      },
      "what_changed": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules.",
      "scope": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules. Scope limitation: These are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.",
      "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:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
        "version": 1,
        "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-12T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks",
            "url": "https://link.aps.org/doi/10.1103/PhysRevResearch.2.033429"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks — deposited bibliography",
            "url": "https://api.crossref.org/works/10.1103%2Fphysrevresearch.2.033429"
          }
        }
      ],
      "origin": "AGENT_NATIVE",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "These are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.",
        "domain": "Chemistry & materials"
      },
      "sources": [
        {
          "citation": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks",
          "url": "https://link.aps.org/doi/10.1103/PhysRevResearch.2.033429"
        },
        {
          "citation": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks — deposited bibliography",
          "url": "https://api.crossref.org/works/10.1103%2Fphysrevresearch.2.033429"
        }
      ],
      "statement": "# FermiNet: learning quantum wavefunctions\n\nOptimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules.\n\n## Scientific scope\n\nThese are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nDavid Pfau; James S. Spencer; Alexander G. D. G. Matthews; W. M. C. Foulkes\n\nFull deposited paper byline or identified author of the scoped historical source. Association does not measure individual effort.\n\nFermiNet / Google DeepMind / Fermionic neural network: Variational wavefunction optimization; human-led ansatz design and numerical evaluation (source reported).\n\n## Original sources\n\n- [Ab initio solution of the many-electron Schrödinger equation with deep neural networks](https://link.aps.org/doi/10.1103/PhysRevResearch.2.033429)\n- [Ab initio solution of the many-electron Schrödinger equation with deep neural networks — deposited bibliography](https://api.crossref.org/works/10.1103%2Fphysrevresearch.2.033429)\n",
      "summary": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules.",
      "title": "FermiNet: learning quantum wavefunctions"
    },
    "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
      "version": 1,
      "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:85a635209914057696eaea28469e7ec32e8e9b268f0d63994daf7f1b7c70b1a9"
  },
  "target": {
    "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
    "version": 1,
    "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "ferminet",
    "entry_id": "ferminet",
    "revision": 1,
    "title": "FermiNet: learning quantum wavefunctions",
    "context": "Chemistry & materials",
    "track": "Scoped scientific or research-capability contribution",
    "band": "B",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-14",
    "evidence_cutoff": "2026-09-14",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules.",
    "scope": "Optimized antisymmetric neural-network wavefunctions with variational Monte Carlo to calculate electronic energies for tested atoms and molecules. Scope limitation: These are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.",
    "evidence_summary": "Assessment uses the catalogue-linked source evidence for the stated contribution. These are approximate computational results for specified systems, not a general exact solution of the many-electron Schrödinger equation.",
    "references": [
      {
        "title": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks",
        "url": "https://link.aps.org/doi/10.1103/PhysRevResearch.2.033429",
        "locator": "Retained catalogue source evidence; Bibliographic identity and scoped source account; not a full proof audit, experiment replay or clinical validation."
      },
      {
        "title": "Ab initio solution of the many-electron Schrödinger equation with deep neural networks — deposited bibliography",
        "url": "https://api.crossref.org/works/10.1103%2Fphysrevresearch.2.033429",
        "locator": "Retained catalogue source evidence; Full deposited byline, bibliographic identity and any supplied abstract/affiliations; checksum retained locally."
      }
    ],
    "roles": [
      {
        "who": "David Pfau",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      },
      {
        "who": "James S. Spencer",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      },
      {
        "who": "Alexander G. D. G. Matthews",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      },
      {
        "who": "W. M. C. Foulkes",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      },
      {
        "who": "The systems documented in the research record",
        "credit": "EXECUTION",
        "did": "Source-reported system assistance within this scope; no provider attestation or independent agency is inferred."
      }
    ],
    "target": {
      "record_id": "urn:uuid:c3fb70c9-9423-41e4-a818-0b96f9c2ff93",
      "version": 1,
      "content_hash": "sha256:07d7c01c3b7a79e9253e02c922579ff8085fff72c4bffff455fc735d8cd1124f"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "18000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}