{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "ai-oct-deepdream",
    "title": "Inceptionism / DeepDream: iterative amplification of learned image features",
    "summary": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns.",
    "boundary": "Original 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.",
    "area": "AI representation visualization",
    "topic": "Artificial intelligence",
    "year": 2015,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "ai-oct-deepdream",
    "target": {
      "record_id": "urn:uuid:935e89ce-eda4-4299-a1f1-1eb587d37d35",
      "version": 1,
      "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
    },
    "humans": [
      "Alexander Mordvintsev",
      "Christopher Olah",
      "Mike Tyka"
    ],
    "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-deepdream",
        "title": "Inceptionism: Going Deeper into Neural Networks",
        "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
      }
    ],
    "points": "120000",
    "published_grade": {
      "id": "ai-oct-deepdream",
      "entry_id": "ai-oct-deepdream",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:935e89ce-eda4-4299-a1f1-1eb587d37d35",
        "version": 1,
        "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
      },
      "what_changed": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns.",
      "scope": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns. Original 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.",
      "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:935e89ce-eda4-4299-a1f1-1eb587d37d35",
        "version": 1,
        "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
      },
      "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": "Alexander Mordvintsev",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Inceptionism: Going Deeper into Neural Networks",
            "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Christopher Olah",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Inceptionism: Going Deeper into Neural Networks",
            "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Mike Tyka",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Inceptionism: Going Deeper into Neural Networks",
            "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Inceptionism: Going Deeper into Neural Networks",
            "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Original 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.",
        "domain": "AI representation visualization"
      },
      "sources": [
        {
          "citation": "Inceptionism: Going Deeper into Neural Networks",
          "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/"
        }
      ],
      "statement": "# Inceptionism / DeepDream: iterative amplification of learned image features\n\nAmplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns.\n\n## Scientific scope\n\nOriginal 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.\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\nAlexander Mordvintsev; Christopher Olah; Mike Tyka\n\nSource-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.\n\n\n\n## Original sources\n\n- [Inceptionism: Going Deeper into Neural Networks](https://research.google/blog/inceptionism-going-deeper-into-neural-networks/)\n",
      "summary": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns.",
      "title": "Inceptionism / DeepDream: iterative amplification of learned image features"
    },
    "record_id": "urn:uuid:935e89ce-eda4-4299-a1f1-1eb587d37d35",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:935e89ce-eda4-4299-a1f1-1eb587d37d35",
      "version": 1,
      "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:546a1110962f0d953566193bd15105bf02aac166afd04286fe520c7c59ff278d"
  },
  "target": {
    "record_id": "urn:uuid:935e89ce-eda4-4299-a1f1-1eb587d37d35",
    "version": 1,
    "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "ai-oct-deepdream",
    "entry_id": "ai-oct-deepdream",
    "revision": 1,
    "title": "Inceptionism / DeepDream: iterative amplification of learned image features",
    "context": "AI representation visualization",
    "track": "Human-designed research method or resource",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns.",
    "scope": "Amplifies features selected from a trained visual network, feeding transformed outputs back with zooming to generate and inspect recurring learned patterns. Original 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original 2015 technical account, not invention of activation maximization generally. Results depend on trained network and priors, with no guarantee of faithful semantic explanations or general creative intelligence.",
    "references": [
      {
        "title": "Inceptionism: Going Deeper into Neural Networks",
        "url": "https://research.google/blog/inceptionism-going-deeper-into-neural-networks/",
        "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:935e89ce-eda4-4299-a1f1-1eb587d37d35",
      "version": 1,
      "content_hash": "sha256:96a35476c483e2f62a25e6b38fb19d81650ad910fb53de6b3cce498dde6c9de9"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "120000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}