CoreSR retweeted
Is JEV a new architecture? It might just be a smallish LLM with a muzzle...#jev #llm #ai
youtube.com/watch?v=UdHV216g…
CoreSR retweeted
coreSR now runs inside Claude and ChatGPT
I connected the coreSR MCP server and gave Claude one sentence: build a search on sildenafil for pulmonary arterial hypertension, run it, and screen it with TITAN at the strictest setting, randomized trials only.
Twelve minutes later, Claude had searched PubMed and Europe PMC, run TITAN across 1,022 unique records, and written a report that reads like a methods section. It also checked the screen against landmark trials. Two were missing. Claude traced the gap to the search strategy, ran a corrected supplement, and recovered both.
That division of labour is the point. Validated engines do the science. Claude does the legwork. You make the final calls.
The full demo runs under three minutes. Connect at coresr.ai/mcp.
#SystematicReview #EvidenceSynthesis #MetaAnalysis #ClaudeAI
CoreSR retweeted
Component NMA isn't just another league table. You estimate effects for treatment components and combinations — including ones no trial ran directly.
Walkthrough in CoreSR:
youtube.com/watch?v=hW73KzeX…
#ComponentNMA #NetworkMetaAnalysis #SystematicReview #EvidenceSynthesis #CoreSR
CoreSR retweeted
Intransitivity and incoherence are the two GRADE domains most NMA software ignores. Both demand structured judgment. Neither reduces to a p-value.
CoreSR implements both, and guards against the common error: a double downgrade for one problem.
youtube.com/@CoreSR
coresr.ai/
CoreSR retweeted
NMA has meant handing the analysis to whoever on the team writes R. Methodological review stays shallow. Few co-authors can check work they cannot reproduce.
CoreSR puts frequentist and Bayesian engines behind an interface a methodologist can drive.
Disclosure: co-founder, I hold equity.
youtu.be/wBh_GNqxoLE?si=Bjks…
coresr.ai/
CoreSR retweeted
Thread: when target trial emulation points the wrong way
1/ 11,073 patients said oseltamivir saves lives in hospitalised influenza. 442 randomised patients said the opposite — 98% harm probability.
How target trial emulation goes wrong, and what to check before the next one. 🧵
CoreSR retweeted
3,434 held-out Cochrane reviews. Median specificity 0.902 at 99% recall. The model runs locally: no per-abstract cost, no data leaving the machine. Method paper in press at JCE.
Screening no longer decides what a small team can attempt.
Disclosure: co-founder, I hold equity.
youtube.com/watch?v=JxQTnsBo…
coresr.ai/
CoreSR retweeted
A systematic review takes one to two years. Very little of that time goes to thinking. It goes to moving citations between disconnected tools.
We built CoreSR to strip that out and return the reviewer's time to judgment.
youtube.com/@CoreSR
coresr.ai/
CoreSR retweeted
We’ve collapsed “AI” into “chatbot.” That is like pointing at a combustion engine and calling it physics. AI is a field, not a product.
My new piece maps the territory beyond the chat window: drtylerpitre.substack.com/p/… #Ai #LLM #ML
CoreSR retweeted
Weeks of manual synthesis reduced to less than 10 minutes.
Watch how CoreSR runs a Bayesian NMA + automated GRADE assessment instantly.
Watch below 👇 #EvidenceBasedMedicine @GuyattGH @Bram_Rochwerg @DenaZera
Vist Coresr.ai