{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "malkov-yashunin-hnsw-2016",
    "title": "Malkov and Yashunin: hierarchical navigable proximity-graph search",
    "summary": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics.",
    "boundary": "Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.",
    "area": "Approximate nearest-neighbor indexing",
    "topic": "Artificial intelligence",
    "year": 2016,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "malkov-yashunin-hnsw-2016",
    "target": {
      "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
      "version": 1,
      "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
    },
    "humans": [
      "Yu. A. Malkov",
      "D. A. Yashunin"
    ],
    "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": "cur20261015-arxiv-1603-09320v1",
        "title": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
        "url": "https://arxiv.org/abs/1603.09320v1"
      }
    ],
    "points": "280000",
    "published_grade": {
      "id": "malkov-yashunin-hnsw-2016",
      "entry_id": "malkov-yashunin-hnsw-2016",
      "band": "S",
      "modifier": "-",
      "target": {
        "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
        "version": 1,
        "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
      },
      "what_changed": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics.",
      "scope": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics. Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.",
      "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:33c94569-e714-45fc-a4d5-5b8d365505c8",
        "version": 1,
        "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
      },
      "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": "Yu. A. Malkov",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
            "url": "https://arxiv.org/abs/1603.09320v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "D. A. Yashunin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
            "url": "https://arxiv.org/abs/1603.09320v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
            "url": "https://arxiv.org/abs/1603.09320v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.",
        "domain": "Approximate nearest-neighbor indexing"
      },
      "sources": [
        {
          "citation": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
          "url": "https://arxiv.org/abs/1603.09320v1"
        }
      ],
      "statement": "# Malkov and Yashunin: hierarchical navigable proximity-graph search\n\n## The question\n\nSuppose you want to find a photograph that looks like one on your phone. A computer can turn each image into a list of numbers called an embedding, then look for nearby lists. Comparing your query with every stored image becomes expensive as the collection grows. The challenge is to search less while still finding useful neighbors.\n\n## The idea\n\nHNSW builds a network whose links connect nearby items, then organizes that network into layers. The sparse upper layers help the search move across large distances. Lower layers provide finer local connections. A query follows promising links, much as you might first choose a district on a map and then inspect its streets. The layers guide the search; they do not make every answer exact.\n\n## Why it matters\n\nThe important contribution is a reusable indexing design. An index is an extra structure built to answer repeated queries efficiently. Building and storing it has a cost, so the complete tradeoff includes construction time, memory, query time and missed neighbors. This is different from claiming that a single clever comparison makes every possible search fast.\n\n## A teaching example\n\nFor a classroom example, imagine cards placed along a corridor. A few express links jump between distant sections; ordinary links connect nearby cards. Starting at the wrong end, express links can get you close quickly, after which local inspection helps. Now arrange the cards in several confusing clusters. The example suggests why graph connectivity and the search budget matter, rather than proving a universal speed guarantee.\n\n## Scope and a useful next step\n\nChoose a small public set of embeddings and compare exact search with graph search. Keep the query set fixed. Report how often the graph search retrieves the exact nearest items, along with the actual memory and timing setup. A useful result can identify where accuracy drops; an unsuccessful setting is still reusable evidence. Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.\n\n## Scientific scope\n\nNavigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.\n\n## Sources for this explanation\n\n- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://arxiv.org/abs/1603.09320v1): Pinned original contribution and its stated method, assumptions and limits. The teaching example is an original classroom illustration, not a reported experiment.\n",
      "summary": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics.",
      "title": "Malkov and Yashunin: hierarchical navigable proximity-graph search"
    },
    "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
      "version": 1,
      "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:47031888e16c4850fa36c7ac0305daa12192a87033f77cdda1ae4e54bc75c6a3"
  },
  "target": {
    "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
    "version": 1,
    "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "malkov-yashunin-hnsw-2016",
    "entry_id": "malkov-yashunin-hnsw-2016",
    "revision": 1,
    "title": "Malkov and Yashunin: hierarchical navigable proximity-graph search",
    "context": "Approximate nearest-neighbor indexing",
    "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": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics.",
    "scope": "Built nested proximity-graph layers with randomized maximum levels and searched from coarse upper layers toward the base, combining distance-scale separation and neighbor-selection heuristics. Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.",
    "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. Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution.",
    "references": [
      {
        "title": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
        "url": "https://arxiv.org/abs/1603.09320v1",
        "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:33c94569-e714-45fc-a4d5-5b8d365505c8",
      "version": 1,
      "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "280000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": {
    "id": "malkov-yashunin-hnsw-2016",
    "target": {
      "record_id": "urn:uuid:33c94569-e714-45fc-a4d5-5b8d365505c8",
      "version": 1,
      "content_hash": "sha256:c13c513ade9eeb2f775a50cfaee4e359a97945199a66e0aeadf8639023bf82a0"
    },
    "sections": [
      {
        "title": "The question",
        "text": "Suppose you want to find a photograph that looks like one on your phone. A computer can turn each image into a list of numbers called an embedding, then look for nearby lists. Comparing your query with every stored image becomes expensive as the collection grows. The challenge is to search less while still finding useful neighbors."
      },
      {
        "title": "The idea",
        "text": "HNSW builds a network whose links connect nearby items, then organizes that network into layers. The sparse upper layers help the search move across large distances. Lower layers provide finer local connections. A query follows promising links, much as you might first choose a district on a map and then inspect its streets. The layers guide the search; they do not make every answer exact."
      },
      {
        "title": "Why it matters",
        "text": "The important contribution is a reusable indexing design. An index is an extra structure built to answer repeated queries efficiently. Building and storing it has a cost, so the complete tradeoff includes construction time, memory, query time and missed neighbors. This is different from claiming that a single clever comparison makes every possible search fast."
      },
      {
        "title": "A teaching example",
        "text": "For a classroom example, imagine cards placed along a corridor. A few express links jump between distant sections; ordinary links connect nearby cards. Starting at the wrong end, express links can get you close quickly, after which local inspection helps. Now arrange the cards in several confusing clusters. The example suggests why graph connectivity and the search budget matter, rather than proving a universal speed guarantee."
      },
      {
        "title": "Scope and a useful next step",
        "text": "Choose a small public set of embeddings and compare exact search with graph search. Keep the query set fixed. Report how often the graph search retrieves the exact nearest items, along with the actual memory and timing setup. A useful result can identify where accuracy drops; an unsuccessful setting is still reusable evidence. Navigable small-world graphs and skip-list-like hierarchies are inherited. Search is approximate; observed near-logarithmic scaling is not a worst-case exact-search guarantee for every metric/data distribution."
      }
    ],
    "references": [
      {
        "title": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
        "url": "https://arxiv.org/abs/1603.09320v1",
        "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"
}