{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.11144", "kind": "paper", "url": "https://arxiv.org/abs/2606.11144"}, {"id": "gh:span-ai-labs/oncotraj", "kind": "repo", "url": "https://github.com/span-ai-labs/oncotraj"}, {"id": "hf:span-ai-labs/oncotraj-v1", "kind": "dataset", "url": "https://huggingface.co/datasets/span-ai-labs/oncotraj-v1"}], "authors": ["Abhijoy Sarkar", "Aarchi Singh Thakur"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.11144", "source_url": "https://arxiv.org/abs/2606.11144"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.LG"], "description": {"en": "OncoTraj is a public benchmark for predicting acquired resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer. It provides a harmonized dataset of 813 patients from three real-world sources, with locked splits, an evaluation harness, and six baselines, defining three tasks: 12-month progression classification, time-to-progression regression, and resistance mechanism classification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.11144", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.11144", "title": "OncoTraj"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.11144", "modality": null, "name": "OncoTraj", "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_oncotraj_0ff8775a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0025f53fe09d4c3bc2c4638247d7d3a38cd9a5c6b2fdffaefef0f49317cab0dc", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.11144"}, "publisher": null, "released": "2026-06-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.11144", "source_url": "https://arxiv.org/abs/2606.11144"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-11144", "source": "claire_radar", "source_benchmark_id": "2606.11144", "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": "https://github.com/span-ai-labs/oncotraj", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": "span-ai-labs/oncotraj-v1", "hfDatasetDownloads": 11, "hfDatasetLikes": 1, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.11144", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-24", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-24", "state": "stale"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "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": "45e7b3d746c923009561febbf9ece9a74aebae17d8fadd6f94d4d054cf38b6ec", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OncoTraj is a public benchmark for predicting acquired resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer. It provides a harmonized dataset of 813 patients from three real-world sources, with locked splits, an evaluation harness, and six baselines, defining three tasks: 12-month progression classification, time-to-progression regression, and resistance mechanism classification.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce OncoTraj, a public benchmark of 813 EGFR-mutant NSCLC patients receiving first-line osimertinib, harmonized from three real-world clinical-genomic sources: MSK-CHORD (672 patients), AACR Project GENIE BPC NSCLC (34 patients), and the FLAURA molecular-resistance supplement (107 patients)."}, "familyId": "bmf_bdc2d0e2d2ef", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/span-ai-labs/oncotraj", "url": "https://github.com/span-ai-labs/oncotraj"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/span-ai-labs/oncotraj", "url": "https://huggingface.co/papers/2606.11144"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/span-ai-labs/oncotraj", "url": "https://arxiv.org/abs/2606.11144"}], "scope": "benchmark_repo", "url": "https://github.com/span-ai-labs/oncotraj", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_oncotraj_0ff8775a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/span-ai-labs/oncotraj", "data": "https://huggingface.co/datasets/span-ai-labs/oncotraj-v1", "hfPaper": "https://huggingface.co/papers/2606.11144", "paper": "https://arxiv.org/abs/2606.11144", "pdf": "https://arxiv.org/pdf/2606.11144", "project": null, "report": "https://arxiv.org/abs/2606.11144"}, "metrics": [], "motivation": "Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computational models on the corresponding longitudinal patient trajectories.", "name": "OncoTraj", "oneLine": "OncoTraj is a public benchmark for predicting acquired resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer. It provides a harmonized dataset of 813 patients from three real-world sources, with locked splits, an evaluation harness, and six baselines, defining three tasks: 12-month progression classification, time-to-progression regression, and resistance mechanism classification.", "paperTitle": "OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.11144", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Span AI Labs", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/span-ai-labs/oncotraj"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-09", "source": {"authors": ["Abhijoy Sarkar", "Aarchi Singh Thakur"], "categories": ["cs.LG", "q-bio.GN", "q-bio.QM", "stat.AP"], "id": "2606.11144", "title": "OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib", "type": "arxiv", "url": "https://arxiv.org/abs/2606.11144"}, "sourceUpdatedAt": "2026-06-09T17:33:24Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "OncoTraj fills the gap of a standardized, public evaluation for longitudinal resistance prediction, offering reproducible baseline results and leakage-audited splits. It provides a practical means to compare models and highlights the limitation of single-timepoint features, guiding future data collection and algorithm development."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
