{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.10356", "kind": "paper", "url": "https://arxiv.org/abs/2609.10356"}], "authors": ["Benedetta Liberatori", "Nermin Samet", "Paolo Rota", "Matthieu Cord", "Elisa Ricci", "Andrei Bursuc", "Monika Wysoczańska"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.10356", "source_url": "https://arxiv.org/abs/2609.10356"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "A human-verified benchmark for grounded image difference captioning of long-term changes, with captions and spatial masks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.10356", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.10356", "title": "SPOT-THE-SHIFT"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.10356", "modality": null, "name": "SPOT-THE-SHIFT", "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_spot-the-shift_1b43b422", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1cdc69bee223779b84aca24630cfffd58efe8f6f544e50bc4628e53ae37fbd0f", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-11T00:52:53.785364Z", "source_url": "https://arxiv.org/abs/2609.10356"}, "publisher": null, "released": "2026-09-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.10356", "source_url": "https://arxiv.org/abs/2609.10356"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-10356", "source": "claire_radar", "source_benchmark_id": "2609.10356", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2609.10356", "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", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The task has practical applications but the absence of released artifacts limits immediate adoption.", "score": 48}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:52:53.785364Z", "inputHash": "38c051fcbcaf9daf37637ba288d80381b1b9e424412504370912bfe3f54f0066", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No public dataset or evaluation protocol link is provided in the supplied evidence.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-11T00:52:53.785364Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A human-verified benchmark for grounded image difference captioning of long-term changes, with captions and spatial masks.", "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"], "snippet": "We introduce SPOT-THE-SHIFT, a human-verified benchmark for grounded image difference captioning of long-term changes in real-world driving scenes."}, "familyId": "bmf_5cc64df998b4", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_spot-the-shift_1b43b422", "indexedAt": "2026-09-10T06:16:58.931316Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.10356", "pdf": "https://arxiv.org/pdf/2609.10356", "project": null, "report": "https://arxiv.org/abs/2609.10356"}, "metrics": [], "motivation": "Long-term change understanding from images of the same place revisited over time is a challenging task with applications in map maintenance and urban infrastructure monitoring.", "name": "SPOT-THE-SHIFT", "oneLine": "A human-verified benchmark for grounded image difference captioning of long-term changes, with captions and spatial masks.", "paperTitle": "Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.10356", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-10T06:16:58.931316Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-09", "source": {"authors": ["Benedetta Liberatori", "Nermin Samet", "Paolo Rota", "Matthieu Cord", "Elisa Ricci", "Andrei Bursuc", "Monika Wysocza\\'nska"], "categories": ["cs.CV"], "id": "2609.10356", "title": "Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes", "type": "arxiv", "url": "https://arxiv.org/abs/2609.10356"}, "sourceUpdatedAt": "2026-09-09T15:52:04Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Addresses a valuable task in map maintenance and infrastructure monitoring, but no artifact link is available to verify reusability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
