{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.12408", "kind": "paper", "url": "https://arxiv.org/abs/2609.12408"}, {"id": "gh:yuxieharrison/gso-net", "kind": "repo", "url": "https://github.com/yuxieHarrison/GSO-Net"}], "authors": ["Yu Xie", "Bangshu Xiong", "Zhibo Rao", "Rui Gan", "Chongxuan Liu", "Zechu Ouyang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.12408", "source_url": "https://arxiv.org/abs/2609.12408"}, "categories": ["Logistics & Operations", "Vision & 3D", "cs.CV"], "description": {"en": "A large-scale industrial vision benchmark for standard operating procedure understanding in petrochemical unloading, built from 50,325 images across 64 stations with 321,432 bounding boxes. It links nine macroscopic procedural steps and 15 microscopic operational states across a core joint step-state detection task and a diagnostic frame-level step classification task, using a strict cross-site split."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.12408", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.12408", "title": "GSO-Net"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.12408", "modality": null, "name": "GSO-Net", "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": "false", "origin_record_id": "bm_gso-net_911a783f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e1273efd289cb7f27b4ef41782b1e26f2de1583d771ff057c229e2b9af701098", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T00:43:53.625753Z", "source_url": "https://arxiv.org/abs/2609.12408"}, "publisher": null, "released": "2026-09-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.12408", "source_url": "https://arxiv.org/abs/2609.12408"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-12408", "source": "claire_radar", "source_benchmark_id": "2609.12408", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/yuxieHarrison/GSO-Net", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.12408", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Attention is likely driven by the industrial safety domain, the large labeled dataset scale, and the presence of an official repository with public download mirrors.", "score": 42}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T10:07:09.772218Z", "inputHash": "4a8cf129c39ff1f4be26e8d0acc6f15fbb36f08c00734313981342ed4dd9028c", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "Dataset of 50K images with detailed annotations is publicly available via multiple hosts; while no benchmark tooling is provided, the dataset alone enables reuse for model evaluation.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-14T00:43:53.625753Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A large-scale industrial vision benchmark for standard operating procedure understanding in petrochemical unloading, built from 50,325 images across 64 stations with 321,432 bounding boxes. It links nine macroscopic procedural steps and 15 microscopic operational states across a core joint step-state detection task and a diagnostic frame-level step classification task, using a strict cross-site split.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present GSO-Net, a large-scale benchmark for visual understanding of standard operating procedures (SOPs) in petrochemical unloading scenarios."}, "familyId": "bmf_355a1c507787", "firstSeenAt": "2026-09-14", "heat": null, "id": "bm_gso-net_911a783f", "indexedAt": "2026-09-14T00:39:56.575498Z", "industrySectors": ["Logistics"], "links": {"code": "https://github.com/yuxieHarrison/GSO-Net", "data": null, "paper": "https://arxiv.org/abs/2609.12408", "pdf": "https://arxiv.org/pdf/2609.12408", "project": null, "report": "https://arxiv.org/abs/2609.12408"}, "metrics": [], "motivation": "Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints.", "name": "GSO-Net", "oneLine": "A large-scale industrial vision benchmark for standard operating procedure understanding in petrochemical unloading, built from 50,325 images across 64 stations with 321,432 bounding boxes. It links nine macroscopic procedural steps and 15 microscopic operational states across a core joint step-state detection task and a diagnostic frame-level step classification task, using a strict cross-site split.", "paperTitle": "GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.12408", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-14T00:39:56.575498Z"}, "publications": [], "publishers": [{"name": "Yu Xie and Bangshu Xiong", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/yuxieHarrison/GSO-Net"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.16198483906027114, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 76, "score": 31}, "method": "attention-ranking-v13", "rank": 76, "score": 31}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 249, "score": 31}, "method": "attention-ranking-v13", "rank": 249, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-11", "source": {"authors": ["Yu Xie", "Bangshu Xiong", "Zhibo Rao", "Rui Gan", "Chongxuan Liu", "and Zechu Ouyang"], "categories": ["cs.CV"], "id": "2609.12408", "title": "GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes", "type": "arxiv", "url": "https://arxiv.org/abs/2609.12408"}, "sourceUpdatedAt": "2026-09-11T04:00:41Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing industrial benchmarks emphasize anomaly detection or object presence, while procedural compliance under sparse polling requires grounding localized operational cues to procedural stages. A shared cross-site protocol and released labels allow teams to compare whether models recover procedural meaning from incomplete observations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
