{
  "identifier": "tag:aim-pro.eu,2026:oer/24a89d134ed6/record",
  "profile": "aimpro-oer-profile/1",
  "normaliser": "oerlib.metadata/2",
  "status": "ready",
  "normalised_at": "2026-10-09T09:54:16+00:00",
  "resource": {
    "id": "24a89d134ed6",
    "identifier": "tag:aim-pro.eu,2026:oer/24a89d134ed6",
    "uri": "https://arxiv.org/abs/2307.02796",
    "title": "VerifAI: Verified Generative AI",
    "description": "Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as inaccurate decision-making, the spread of false information, privacy violations, legal liabilities, and more. Although efforts to address these risks are underway, including explainable AI and responsible AI practices such as transparency, privacy protection, bias mitigation, and social and environmental responsibility, misinformation caused by generative AI will remain a significant challenge. We propose that verifying the outputs of generative AI from a data management perspective is an emerging issue for generative AI. This involves analyzing the underlying data from multi-modal data lakes, including text files, tables, and knowledge graphs, and assessing its quality and consistency. By doing so, we can establish a stronger foundation for evaluating the outputs of generative AI models. Such an approach can ensure the correctness of generative AI, promote transparency, and enable decision-making with greater confidence. Our vision is to promote the development of verifiable generative AI and contribute to a more trustworthy and responsible use of AI.",
    "creators": [
      "Nan Tang",
      "Chenyu Yang",
      "Ju Fan",
      "Lei Cao",
      "Yuyu Luo",
      "Alon Halevy"
    ],
    "keywords": [
      "cs.DB",
      "cs.CL",
      "cs.LG"
    ],
    "kind": "html",
    "content_language": "en",
    "declared_language": "en",
    "word_count": 5321,
    "content_hash": "c6dbe291c9b81473",
    "metadata_only": false
  },
  "licence": {
    "raw": "CC-BY-4.0",
    "spdx": "CC-BY-4.0",
    "uri": "http://creativecommons.org/licenses/by/4.0/",
    "verdict": "OPEN",
    "note": "open, permissive",
    "ingestable": true,
    "commercial_ok": true,
    "derivable": true,
    "share_alike": false,
    "evidence": {
      "scope": "this submitted version of the paper",
      "method": "arXiv OAI-PMH GetRecord (metadataPrefix=arXiv)",
      "schema": 1,
      "status": "captured",
      "location": "arXiv:arXiv/arXiv:license",
      "source_url": "https://oaipmh.arxiv.org/oai?verb=GetRecord&identifier=oai:arXiv.org:2307.02796&metadataPrefix=arXiv",
      "asserted_by": "arXiv submitter",
      "captured_at": "2026-10-09T09:54:11+00:00",
      "source_system": "arxiv",
      "observed_value": "http://creativecommons.org/licenses/by/4.0/",
      "documentation_url": "https://info.arxiv.org/help/oa/index.html",
      "responsibility_url": "https://info.arxiv.org/help/license/index.html",
      "documentation_label": "arXiv OAI-PMH metadata documentation",
      "responsibility_note": "The submitter chooses the article-version licence and certifies the right to grant it."
    }
  },
  "descriptive": {
    "contributions": [
      {
        "name": "Nan Tang",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Chenyu Yang",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Ju Fan",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Lei Cao",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Yuyu Luo",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Alon Halevy",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      }
    ],
    "identifiers": [
      {
        "scheme": "arxiv",
        "value": "2307.02796",
        "scope": "resource"
      }
    ],
    "dates": [
      {
        "meaning": "issued",
        "value": "2023-07-06",
        "scope": "resource"
      },
      {
        "meaning": "modified",
        "value": "2023-10-11",
        "scope": "resource"
      }
    ],
    "subjects": [
      {
        "value": "cs.DB",
        "scheme": "arxiv",
        "scope": "resource"
      },
      {
        "value": "cs.CL",
        "scheme": "arxiv",
        "scope": "resource"
      },
      {
        "value": "cs.LG",
        "scheme": "arxiv",
        "scope": "resource"
      }
    ],
    "relations": [],
    "educational": {
      "learning_resource_type": "",
      "intended_end_user_role": "",
      "context": "",
      "difficulty": "",
      "typical_learning_time": "",
      "description": ""
    },
    "container": {
      "kind": "",
      "uri": "",
      "title": "",
      "description": "",
      "identifier": ""
    },
    "declared_language": "en",
    "declared_type": "preprint",
    "rights_holder": "",
    "access_rights": "open",
    "publisher": "",
    "version": "v2",
    "citation": "",
    "notes": "",
    "lifecycle_status": "revised",
    "structure_role": "",
    "snapshot": {
      "resource": {
        "title": "VerifAI: Verified Generative AI",
        "authors": [
          "Nan Tang",
          "Chenyu Yang",
          "Ju Fan",
          "Lei Cao",
          "Yuyu Luo",
          "Alon Halevy"
        ],
        "summary": "Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as inaccurate decision-making, the spread of false information, privacy violations, legal liabilities, and more. Although efforts to address these risks are underway, including explainable AI and responsible AI practices such as transparency, privacy protection, bias mitigation, and social and environmental responsibility, misinformation caused by generative AI will remain a significant challenge. We propose that verifying the outputs of generative AI from a data management perspective is an emerging issue for generative AI. This involves analyzing the underlying data from multi-modal data lakes, including text files, tables, and knowledge graphs, and assessing its quality and consistency. By doing so, we can establish a stronger foundation for evaluating the outputs of generative AI models. Such an approach can ensure the correctness of generative AI, promote transparency, and enable decision-making with greater confidence. Our vision is to promote the development of verifiable generative AI and contribute to a more trustworthy and responsible use of AI.",
        "updated": "2023-10-11T03:16:23Z",
        "version": 2,
        "arxiv_id": "2307.02796",
        "published": "2023-07-06T06:11:51Z",
        "categories": [
          "cs.DB",
          "cs.CL",
          "cs.LG"
        ],
        "affiliations": [
          "",
          "",
          "",
          "",
          "",
          ""
        ],
        "primary_category": "cs.DB"
      }
    }
  },
  "representations": [
    {
      "role": "extracted",
      "media_type": "text/markdown",
      "size_bytes": 35315,
      "filename": "",
      "location": "",
      "source_format": "latexml-html",
      "converter": "arxiv-html"
    }
  ],
  "observed": {
    "language": {
      "method": "declared",
      "reason": "declared English",
      "accepted": true,
      "declared": "en",
      "detected": "en",
      "confidence": null,
      "review_required": false
    }
  },
  "collection": {
    "source": "arxiv",
    "source_label": "arXiv",
    "collected_at": "2026-10-09T09:54:16.160411+00:00",
    "query": "(all:\"artificial intelligence\" OR all:\"machine learning\" OR all:\"generative AI\" OR all:\"deep learning\" OR all:\"reinforcement learning\" OR all:\"large language model\") AND (all:\"AI concepts\" OR all:\"types of AI\" OR all:\"AI fundamentals\" OR all:\"recognizing AI\" OR all:\"recognising AI\" OR all:\"general versus narrow AI\" OR all:\"narrow AI\" OR all:\"general AI\" OR all:\"machine intelligence\" OR all:\"AI strengths and weaknesses\" OR all:\"traditional software\" OR all:\"rule-based systems\" OR all:\"introduction to AI\" OR all:\"introduction to artificial intelligence\" OR all:\"artificial intelligence introduction\" OR all:\"AI primer\" OR all:\"foundations of artificial intelligence\" OR all:\"overview of AI\" OR all:\"understanding AI\" OR all:\"history of AI\" OR all:\"AI essentials\" OR all:\"AI terminology\" OR all:\"metaphors for AI\" OR all:\"AI fundamental concepts\" OR all:\"AI key concepts\" OR all:\"philosophy of AI\" OR all:\"critical AI literacy\")",
    "note": "where this was collected from. Not a claim that the provider published or authored it"
  },
  "provenance": [
    {
      "field": "resource_id",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/resource_id"
    },
    {
      "field": "query",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/query"
    },
    {
      "field": "collected_from",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/source"
    },
    {
      "field": "title",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/title"
    },
    {
      "field": "description",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/summary"
    },
    {
      "field": "version",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "lifecycle_status",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "subjects",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/categories/0"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/0"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/1"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/2"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/3"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/4"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/5"
    },
    {
      "field": "dates",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/arxiv_id"
    },
    {
      "field": "content_language",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/language/declared"
    },
    {
      "field": "declared_language",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "licence",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/licence/evidence"
    },
    {
      "field": "access_rights",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "representations",
      "scope": "resource",
      "method": "conversion",
      "evidence_ref": "conversion#/latexml-html"
    },
    {
      "field": "declared_type",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "educational",
      "scope": "resource",
      "method": "declared_type_mapping",
      "evidence_ref": "profile#/learning_resource_type/preprint"
    }
  ],
  "incidents": [
    {
      "code": "absent",
      "field": "rights_holder",
      "detail": "no rights holder is named at source; the licence is recorded without one rather than attributed to the platform that served it"
    },
    {
      "code": "absent",
      "field": "publisher",
      "detail": "the source named no publisher of the work; where it was collected from is recorded as collection provenance instead, which is a different claim"
    },
    {
      "code": "absent",
      "field": "educational",
      "detail": "the source declared no educational metadata — no resource type, audience, context, difficulty or learning time. Nothing here estimates them"
    }
  ],
  "inferred": [
    {
      "rule": "purpose.declared_type",
      "field": "purpose",
      "value": "reference",
      "method": "inferred",
      "evidence": {
        "declared_type": "preprint"
      },
      "rule_version": "purpose/1"
    },
    {
      "field": "references",
      "value": "https://arxiv.org/abs/1909.02164",
      "label": "arXiv:1909.02164",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 265,
            "basis": "reference",
            "literal": "arXiv:1909.02164"
          }
        ],
        "kind": "citation"
      }
    }
  ]
}