{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.24045", "kind": "paper", "url": "https://arxiv.org/abs/2605.24045"}], "authors": ["Zhaohan Meng", "Zhen Bai", "Ke Yuan", "Iadh Ounis", "Zaiqiao Meng", "Hao Xu", "Joseph Loscalzo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.24045", "source_url": "https://arxiv.org/abs/2605.24045"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.LG"], "description": {"en": "InteractBind provides a large-scale dataset of ~100k protein-ligand pairs with fine-grained binding-site localization tasks and interaction maps for six non-covalent interaction types, plus affinity and similarity-controlled splits."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.24045", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.24045", "title": "A Large-Scale Dataset and Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Life Science Institute", "Cancer Research UK Scotland Institute", "University of Glasgow", "Harvard University", "Brigham and Women's Hospital", "Broad Institute"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.24045", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.24045", "source_url": "https://openalex.org/W7162433276"}, "key": "claire-radar:2605.24045", "modality": null, "name": "A Large-Scale Dataset and Benchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_a-large-scale-dataset-and-benchmark_80e45544", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "29d4f6be091c9480f1ee965027358ab8aa8d439211bce79f104bb6a674fedc89", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.24045"}, "publisher": null, "released": "2026-05-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.24045", "source_url": "https://arxiv.org/abs/2605.24045"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-24045", "source": "claire_radar", "source_benchmark_id": "2605.24045", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2605.24045", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d9fc988423d4f52a06e3da234630e597ddf74eca1f6a54f647a6ba78aa296eb2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "InteractBind provides a large-scale dataset of ~100k protein-ligand pairs with fine-grained binding-site localization tasks and interaction maps for six non-covalent interaction types, plus affinity and similarity-controlled splits.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce InteractBind, a large-scale protein-ligand dataset comprising approximately 100k protein-ligand pairs, together with a benchmark for fine-grained evaluation."}, "familyId": "bmf_06e6d8e2fe19", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_a-large-scale-dataset-and-benchmark_80e45544", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.24045", "paper": "https://arxiv.org/abs/2605.24045", "pdf": "https://arxiv.org/pdf/2605.24045", "project": null, "report": "https://arxiv.org/abs/2605.24045"}, "metrics": [], "motivation": "Protein-ligand modeling underpins computational drug discovery and molecular design.", "name": "A Large-Scale Dataset and Benchmark", "oneLine": "InteractBind provides a large-scale dataset of ~100k protein-ligand pairs with fine-grained binding-site localization tasks and interaction maps for six non-covalent interaction types, plus affinity and similarity-controlled splits.", "paperTitle": "A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.24045", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-21", "source": {"authors": ["Zhaohan Meng", "Zhen Bai", "Ke Yuan", "Iadh Ounis", "Zaiqiao Meng", "Hao Xu", "Joseph Loscalzo"], "categories": ["cs.LG", "cs.AI"], "id": "2605.24045", "title": "A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?", "type": "arxiv", "url": "https://arxiv.org/abs/2605.24045"}, "sourceUpdatedAt": "2026-05-21T20:50:03Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Challenges existing protein-ligand benchmarks by focusing on localization and interaction interpretability, which is critical for drug discovery."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
