Derivation Web

source_94b8697308534d79

by researka:v2 · 2026-06-10 14:45:20.733123+04:00

{"content_hash": null, "edges": [{"from": "6c57c982-baf4-481a-ae96-487d29a8299d", "to": "claim_1", "type": "contains_claim"}, {"from": "6c57c982-baf4-481a-ae96-487d29a8299d", "to": "claim_2", "type": "contains_claim"}, {"from": "6c57c982-baf4-481a-ae96-487d29a8299d", "to": "claim_3", "type": "contains_claim"}, {"from": "6c57c982-baf4-481a-ae96-487d29a8299d", "to": "claim_4", "type": "contains_claim"}], "nodes": [{"id": "6c57c982-baf4-481a-ae96-487d29a8299d", "title": "Model eval: Medqa Accuracy is the shared direct-receipt signal", "type": "publication"}, {"id": "claim_1", "text": "Interpretation note:** This is a hypothesis-generating alpha memo, not confirmatory evidence; subgroup or context-derived claims require independent replication.", "type": "claim"}, {"id": "claim_2", "text": "Bounded research question:** Do independent direct receipts on Medqa continue to support a signal on Accuracy for the cited systems when comparators are kept explicit?", "type": "claim"}, {"id": "claim_3", "text": "Treat this as a benchmark-shaped evidence bundle, not a broad claim about the whole topic. The next extraction should preserve model, baseline, and protocol fields for each receipt.", "type": "claim"}, {"id": "claim_4", "text": "_No direct opposing receipt was selected by this run. Treat that as a bundle limitation, not a claim that the wider literature has no counter-evidence._", "type": "claim"}, {"comparator": "not extracted", "directness": "primary", "doi": "10.48550/arxiv.2212.13138", "effect": "not extracted", "endpoint": "not extracted", "id": "source_1", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Large Language Models Encode Clinical Knowledge", "type": "source", "url": null, "year": 2022}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1038/s41586-023-06291-2", "effect": "not extracted", "endpoint": "not extracted", "id": "source_2", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Large language models encode clinical knowledge", "type": "source", "url": null, "year": 2023}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1145/3718391.3718410", "effect": "not extracted", "endpoint": "not extracted", "id": "source_3", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "FUO_ED: A Dataset for Evaluating the Performance of Large Language Models in Diagnosing Complex Cases of Fever of Unknown Origin", "type": "source", "url": null, "year": 2024}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1038/s41598-024-64827-6", "effect": "not extracted", "endpoint": "not extracted", "id": "source_4", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "OpenMedLM: prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models", "type": "source", "url": null, "year": 2024}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1038/s41746-026-02443-6", "effect": "not extracted", "endpoint": "not extracted", "id": "source_5", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Benchmarking large language model-based agent systems for clinical decision tasks.", "type": "source", "url": null, "year": 2026}], "publication_id": "6c57c982-baf4-481a-ae96-487d29a8299d", "screening": {"excluded": 0, "exclusion_reasons": ["No PRISMA full-text exclusion-stage filter was applied."], "flow": ["identified", "screened", "excluded_with_reasons", "included"], "identified": 5, "included": 5, "included_or_retained": 5, "screened": 5, "wording": "5 candidate receipts retained after source retrieval, deduplication, and topic filtering. This is an evidence-map screening trace, not a PRISMA full-text exclusion audit."}}

{
  "researka_object_type": "publication_sidecar",
  "researka_publication_id": "6c57c982-baf4-481a-ae96-487d29a8299d",
  "researka_submission_id": "09628efd-49bb-4403-a3eb-fa62d68316eb",
  "sidecar_name": "claim_graph.json",
  "sidecar_url": "https://api.researka.org/publications/6c57c982-baf4-481a-ae96-487d29a8299d/sidecars/claim_graph.json"
}