{"record": {"aliases": ["Evaluation of Pipelines for Data Integration into Knowledge Graphs"], "artifacts": [{"id": "arxiv:2605.22304", "kind": "paper", "url": "https://arxiv.org/abs/2605.22304"}], "authors": ["Marvin Hofer", "Erhard Rahm"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.22304", "source_url": "https://arxiv.org/abs/2605.22304"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "KGI-Bench evaluates pipelines that integrate multiple input-data formats into an existing knowledge graph."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.22304", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.22304", "title": "KGI-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Leipzig University of Applied Sciences", "Center for Scalable Data Analytics and Artificial Intelligence", "Leipzig University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.22304", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.22304", "source_url": "https://openalex.org/W7162070388"}, "key": "claire-radar:2605.22304", "modality": null, "name": "KGI-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_evaluation-of-pipelines-for-data-integrati_fc4b3dcf", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "db205bf1d7caf5c72d3e40e587ffb979da560136ed830d6ec90698e9d92f64c0", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T17:55:22.111267Z", "source_url": "https://arxiv.org/abs/2605.22304"}, "publisher": null, "released": "2026-05-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.22304", "source_url": "https://arxiv.org/abs/2605.22304"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-22304", "source": "claire_radar", "source_benchmark_id": "2605.22304", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Evaluation of Pipelines for Data Integration into Knowledge Graphs"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark addresses a practical but specialized knowledge-graph integration problem.", "score": 32}, "capabilities": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T17:55:22.111267Z", "inputHash": "98262e16409cc649bb5bf508e4c9569f2c0c1f30e130610439f0eb6b70714784", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "a new benchmark KGI-Bench", "canonicalNameSource": "abstract", "decisionReason": "The supplied abstract names the benchmark, defines its task and three scoring metrics, and states that the required benchmark datasets and ground truth are provided.", "evaluationEvidence": {"reuse": "We also provide benchmark datasets (seed KG, overlapping input data of three formats, reference KG as a ground truth)", "scoring": "the three complementary quality metrics coverage, correctness and consistency", "task": "evaluate integration pipelines that ingest different kinds of input data into an existing KG"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T17:55:22.111267Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "KGI-Bench evaluates pipelines that integrate multiple input-data formats into an existing knowledge graph.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We therefore propose a new benchmark KGI-Bench to evaluate integration pipelines that ingest different kinds of input data into an existing KG."}, "familyId": "bmf_ab74856aace4", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_evaluation-of-pipelines-for-data-integrati_fc4b3dcf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2605.22304", "pdf": "https://arxiv.org/pdf/2605.22304", "project": null, "report": "https://arxiv.org/abs/2605.22304"}, "metrics": [], "motivation": "Integrating new data into knowledge graphs (KG) typically involves different tasks that are executed within workflows or pipelines There are many possible pipelines for a specific integration problem but there is not yet a general approach to evaluate the overall quality and performance of such pipelines to be able to determine the best choices.", "name": "KGI-Bench", "oneLine": "KGI-Bench evaluates pipelines that integrate multiple input-data formats into an existing knowledge graph.", "paperTitle": "Evaluation of Pipelines for Data Integration into Knowledge Graphs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.22304", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-05-21", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Marvin Hofer", "Erhard Rahm"], "categories": ["cs.AI", "cs.DB", "cs.LG"], "id": "2605.22304", "title": "Evaluation of Pipelines for Data Integration into Knowledge Graphs", "type": "arxiv", "url": "https://arxiv.org/abs/2605.22304"}, "sourceUpdatedAt": "2026-05-21T10:52:48Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It supplies comparable quality measures and reusable movie-domain benchmark data for evaluating complete integration pipelines."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
