Hypothesis #35656

Dimethyl fumarate Nrf2 type 1 diabetes

Drug domain: Multiple sclerosis Outcome domain: Type 2 diabetes Score: 0.369 Quality: high

← Back to all hypotheses

Provenance trace

Audit trail · Dimethyl fumarate → Nrf2 → type 1 diabetes

20 source papers, 20 extracted claims, scored by Swanson ABC chain.

Backfilled

Backfilled retroactively from DB state on 2026-05-13. The pipeline_run this row references was created by the backfill script, not by the actual generation orchestrator. Source papers, claims, scoring, and embedding config are recovered; generation-time metadata (exact git commit at gen time, host, exact command) is not recoverable.

1Source papers20
Filter
2Extracted claims20

Each row is one structured triple extracted by deepseek-v4-flash (prompt v1_2026_05_07, source: configured). Confidence is the LLM's self-rating.

  • dimethyl fumarateactivatesNrf2A→B
    "in relapsing-remitting multiple sclerosis"confidence 0.80· extraction run #25· claim #140676
  • dimethyl fumarateactivatesNrf2A→B
    "in a rat model of osteoarthritis"confidence 0.95· extraction run #25· claim #143502
  • dimethyl fumarateupregulatesNRF2A→B
    "in liver cells"confidence 0.95· extraction run #25· claim #145010
  • Dimethyl fumarateactivatesNRF2A→B
    "in diabetic and non-diabetic mice"confidence 0.90· extraction run #25· claim #145635
  • Dimethyl fumarateactivatesNRF2A→B
    "in non-tumorigenic cells"confidence 0.90· extraction run #25· claim #145713
  • dimethyl fumarateupregulatesNrf2A→B
    "in apo-E-deficient mouse model with STZ-induced hyperglycemia"confidence 0.90· extraction run #25· claim #146123
  • dimethyl fumarateupregulatesNrf2A→B
    "in MCAO/R rat model"confidence 0.95· extraction run #25· claim #148795
  • Dimethyl fumarateactivatesNRF2A→B
    "general"confidence 0.90· extraction run #25· claim #150499
  • dimethyl fumarateupregulatesNrf2A→B
    "in VSMCs and in mice"confidence 0.90· extraction run #25· claim #152967
  • dimethyl fumarateactivatesNrf2A→B
    "in H9c2 cells subjected to myocardial ischemia/reperfusion"confidence 0.80· extraction run #25· claim #153293
  • dimethyl fumarateactivatesNRF2A→B
    "as an NRF2-activating drug"confidence 0.90· extraction run #25· claim #153291
  • Dimethyl fumarateactivatesNrf2A→B
    "in rats"confidence 0.90· extraction run #25· claim #153586
  • dimethyl fumarateactivatesNrf2A→B
    "in NOD mice"confidence 0.70· extraction run #25· claim #154816
  • Dimethyl fumarateactivatesNRF2A→B
    "in RAW 264.7 cells"confidence 0.80· extraction run #25· claim #155264
  • dimethyl fumarateactivatesNrf2A→B
    "in SH-SY5Y cells"confidence 0.80· extraction run #25· claim #159037
  • dimethyl fumarateactivatesNrf2A→B
    "in patients with SSc-PAH"confidence 0.95· extraction run #25· claim #160871
  • Dimethyl fumaratedownregulatesNrf2A→B
    "in multiple sclerosis treatment"confidence 0.80· extraction run #25· claim #162857
  • Dimethyl fumarateactivatesNrf2A→B
    "in multiple sclerosis patients"confidence 0.90· extraction run #25· claim #163681
  • dimethyl fumarateactivatesNrf2A→B
    "FDA-approved therapeutic for multiple sclerosis"confidence 0.80· extraction run #25· claim #163943
  • Nrf2preventstype 1 diabetesB→C
    "in NOD mice"confidence 0.95· extraction run #27· claim #192796
3Bridging logicSwanson ABC
Drug
Dimethyl fumarate
activates
19 papers
Mediator
Nrf2
prevents
1 paper
Outcome
type 1 diabetes
edge_support_log_ab
log(ab + 1) = 2.996
edge_support_log_bc
log(bc + 1) = 0.693
novelty_factor
1.000 (no direct drug→outcome evidence — full novelty)
direct_a_to_c_count
0
4Embedding modelbge-m3

Embeddings are used at the L1 filtering stage to prune off-topic abstracts before claim extraction. They do not directly score the hypothesis.

model
bge-m3
dim
1024
max_length
8192 tokens
similarity_scores
No per-hypothesis cosine scores stored.
5Final scoringhigh · 0.369
method
swanson_abc_log_evidence_with_novelty_penalty
formula
score = min((log(ab+1) + log(bc+1)) * novelty / 10, 1.0); novelty = 1.0 if direct==0 else 0.7 / (direct+1)
raw score
0.3689
outreach score
0.3689
quality tier
high
Pipeline version
9996ffa
Pipeline run
id 4 · uuid eb8b7730…
Pipeline command
scripts/backfill_provenance_v2.py:v2_2026_05_12
Pipeline status
completed
Generated
2026-05-12 21:43:40 UTC
Schema version
1.0
Download full provenance JSON
Score trajectory

How this hypothesis evolved

First captured May 12, 2026, latest May 13, 2026. 2 snapshots.

0.000.100.200.300.400.5005101520 score evidence count May 12, 2026 · score 0.369 · 20 evidence · CT: active · Lit: reproduces_knownMay 12freezeMay 13, 2026 · score 0.369 · 20 evidence · CT: active · Lit: reproduces_knownMay 13monthly
Score (left axis) Evidence count (right axis, dashed)