{"record": {"aliases": ["A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images"], "artifacts": [{"id": "arxiv:2608.14075", "kind": "paper", "url": "https://arxiv.org/abs/2608.14075"}], "authors": ["Jennifer D'Souza", "Fahad Ahmed", "Cecilia Andrea Bustamante Andrade", "Lina Frolova", "Poorani Gnanasambandan", "Dilshad Hussain", "Muhammad Uzair Khan", "Nkembeng Kevin Nkengfoa", "Paul Praveen J.", "Fabio Priante", "Sjoerd Franciscus van der Werf", "Thomas Frederik Jan van Roeden"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14075", "source_url": "https://arxiv.org/abs/2608.14075"}, "categories": ["General AI", "Multimodal"], "description": {"en": "ALD/E-ImageMiner is a benchmark of 1,951 scientific figures from 205 publications, expert-annotated for classification, table extraction, summarization, and visual question answering."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14075", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14075", "title": "ALD/E-ImageMiner"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.14075", "modality": null, "name": "ALD/E-ImageMiner", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_a-pathway-to-general-purpose-scientific-ai_1bd05759", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "66112600bd45d330020f0f161cebace27a6d8329628c6317b0e6fa7705fffa5c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.14075"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14075", "source_url": "https://arxiv.org/abs/2608.14075"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14075", "source": "claire_radar", "source_benchmark_id": "2608.14075", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/sciknoworg/sci-imageminer", "githubScope": "benchmark_repo", "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2608.14075", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Association with an ICDAR 2026 competition and a named dataset suggests moderate early attention.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "df11e72b642620cd3554c13416f7b511888b3d800a4691326b7a57ce69d13120", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "The ALD/E-ImageMiner benchmark and ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching Scientific Figures provide 1,951 figures from 205 publications", "canonicalNameSource": "abstract", "decisionReason": "The abstract explicitly names the benchmark and describes its tasks and annotations, with an associated public competition.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ALD/E-ImageMiner is a benchmark of 1,951 scientific figures from 205 publications, expert-annotated for classification, table extraction, summarization, and visual question answering.", "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": "In these companion proceedings, we present a forward-looking perspective on how the benchmark can guide future scientific-image challenges."}, "familyId": "bmf_327876259ef1", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_a-pathway-to-general-purpose-scientific-ai_1bd05759", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.14075", "pdf": "https://arxiv.org/pdf/2608.14075", "project": null, "report": "https://arxiv.org/abs/2608.14075"}, "metrics": [], "motivation": "Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret.", "name": "ALD/E-ImageMiner", "oneLine": "ALD/E-ImageMiner is a benchmark of 1,951 scientific figures from 205 publications, expert-annotated for classification, table extraction, summarization, and visual question answering.", "paperTitle": "A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14075", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.31659423970600165, "value": 5}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 47}, "method": "attention-ranking-v13", "rank": null, "score": 47}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Jennifer D'Souza", "Fahad Ahmed", "Cecilia Andrea Bustamante Andrade", "Lina Frolova", "Poorani Gnanasambandan", "Dilshad Hussain", "Muhammad Uzair Khan", "Nkembeng Kevin Nkengfoa", "Paul Praveen J.", "Fabio Priante", "Sjoerd Franciscus van der Werf", "and Thomas Frederik Jan van Roeden"], "categories": ["cs.AI", "cs.CV", "cs.DL"], "id": "2608.14075", "title": "A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14075"}, "sourceUpdatedAt": "2026-08-14T08:34:33Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "It enables evaluation on scientific figure understanding, connecting a competition to broader aims in scientific visual knowledge and multimodal AI."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
