{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.07062", "kind": "paper", "url": "https://arxiv.org/abs/2608.07062"}, {"id": "gh:bahumanyarg11/tta-explanation-stability-pipeline", "kind": "repo", "url": "https://github.com/bahumanyarg11/tta-explanation-stability-pipeline"}], "authors": ["R. G. Bahumanya", "Harshith V. M.", "Shreyank N. Gowda", "Anala M. R"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07062", "source_url": "https://arxiv.org/abs/2608.07062"}, "categories": ["Biology & Drug Discovery", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates explanation stability of test-time adaptation methods across histopathology datasets and architectures, measuring drift in attribution maps along with accuracy and calibration."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07062", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07062", "title": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Nottingham"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.07062", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.07062", "source_url": "https://openalex.org/W7202125609"}, "key": "claire-radar:2608.07062", "modality": null, "name": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark", "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_explanation-stability-of-test-time-adaptat_4ac1ea1b", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "9a52b9b98556be79e05d899807f9c7f5a8f3a0ef9b9dca06b6fed4c212422f7c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-05T08:27:33.339760Z", "source_url": "https://arxiv.org/abs/2608.07062"}, "publisher": null, "released": "2026-08-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07062", "source_url": "https://arxiv.org/abs/2608.07062"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07062", "source": "claire_radar", "source_benchmark_id": "2608.07062", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/bahumanyarg11/tta-explanation-stability-pipeline", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.07062", "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": "Targets a niche but important clinical AI evaluation gap with a comprehensive released pipeline, though explanation stability may attract moderate interest from pathology and TTA researchers.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-05T08:27:33.339760Z", "inputHash": "dd7461bed7ff5bf3859ef80e21f2600bf1581de66568f8e0ec63c7fcccb6f7db", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark", "canonicalNameSource": "paper_title", "decisionReason": "Formally named benchmark with reproducible code, defined metrics, and full protocol released, enabling direct comparison and reuse.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-05T08:27:33.339760Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates explanation stability of test-time adaptation methods across histopathology datasets and architectures, measuring drift in attribution maps along with accuracy and calibration.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We release the metric, protocol, and full benchmark to support future work on adaptation methods that are not only accurate, but also stable and clinically auditable."}, "familyId": "bmf_6a39818274b9", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_explanation-stability-of-test-time-adaptat_4ac1ea1b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/bahumanyarg11/tta-explanation-stability-pipeline", "data": null, "paper": "https://arxiv.org/abs/2608.07062", "pdf": "https://arxiv.org/pdf/2608.07062", "project": null, "report": "https://arxiv.org/abs/2608.07062"}, "metrics": [], "motivation": "Test-time adaptation (TTA) has become a practical way to adapt deployed models to unlabeled target data, a setting that is especially relevant in computational pathology where staining, scanner, and cohort shifts are routine.", "name": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark", "oneLine": "Evaluates explanation stability of test-time adaptation methods across histopathology datasets and architectures, measuring drift in attribution maps along with accuracy and calibration.", "paperTitle": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.07062", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 530, "score": 23}, "method": "attention-ranking-v13", "rank": 530, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-08-07", "source": {"authors": ["R. G. Bahumanya", "Harshith V. M.", "Shreyank N. Gowda", "Anala M. R"], "categories": ["cs.CV"], "id": "2608.07062", "title": "Explanation Stability of Test-Time Adaptation in Computational Pathology: A Large-Scale Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07062"}, "sourceUpdatedAt": "2026-08-07T10:13:02Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Provides a missing reliability axis for TTA in clinical pathology, distinguishing methods that silently fail by degrading calibration or accuracy while preserving explanations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
