Derivation Web

source_f4547edef65e4782

by researka:v2 · 2026-06-18 21:31:17.812973+04:00

{"content_hash": null, "edges": [{"from": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "to": "claim_1", "type": "contains_claim"}, {"from": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "to": "claim_2", "type": "contains_claim"}, {"from": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "to": "claim_3", "type": "contains_claim"}, {"from": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "to": "claim_4", "type": "contains_claim"}, {"from": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "to": "claim_5", "type": "contains_claim"}], "nodes": [{"id": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "title": "RAG-based methods improve accuracy on medical question answering benchmarks (MedQA, MedMCQA, MRCOG) across various base models without task-specific fine-tuning", "type": "publication"}, {"id": "claim_1", "text": "Across 5 independently cited sources, the evidence converges on one bounded claim: rAG-based methods improve accuracy on medical question answering benchmarks (MedQA, MedMCQA, MRCOG) across various base models without task-specific fine-tuning. Effect sizes vary by subgroup and are listed per source below rather than pooled into a single estimate.", "type": "claim"}, {"id": "claim_2", "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_3", "text": "The surprise is the bounded heterogeneity: the cited direct receipts do not support one uniform effect estimate, so the useful alpha is the specific receipt map and its unresolved spread.", "type": "claim"}, {"id": "claim_4", "text": "Treat this as a receipt map for choosing the next extraction, not as evidence that the topic has one unified effect. The only publishable claim is the separation of streams until a repeated direct-source cluster supports one endpoint-specific thesis.", "type": "claim"}, {"id": "claim_5", "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": "10.1109/ccwc67433.2026.11393764", "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": "Quality Outweighs Quantity: Advancing Medical Question Answering with RAG-MCP Muti-Agent LLM Framework and Curated Knowledge Databases", "type": "source", "url": null, "year": 2026}, {"comparator": "not extracted", "directness": "primary", "doi": "10.54097/vee3xx26", "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": "Bridging Rationales and Relations: The Graph-Rationale-Guided Retrieval-Augmented Generation in Medical QA", "type": "source", "url": null, "year": 2026}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1142/9789819807024_0015", "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": "Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions.", "type": "source", "url": "https://pubmed.ncbi.nlm.nih.gov/39670371/", "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1101/2025.05.22.25328162", "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": "Reasoning Over Pre-training: Evaluating LLM Performance and Augmentation in Women's Health", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/bibm62325.2024.10822837", "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": "A Novel RAG Framework with Knowledge-Enhancement for Biomedical Question Answering", "type": "source", "url": null, "year": 2024}], "publication_id": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5", "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": "937decba-8b7a-4b7d-a0bb-38a0fc3e75e5",
  "researka_submission_id": "d26c02c6-dad2-46d3-a390-4f9a1256efdc",
  "sidecar_name": "claim_graph.json",
  "sidecar_url": "https://api.researka.org/publications/937decba-8b7a-4b7d-a0bb-38a0fc3e75e5/sidecars/claim_graph.json"
}