Hypothesis #39406

saxagliptin SOD1 familial amyotrophic lateral sclerosis

Drug domain: Type 2 diabetes Outcome domain: ALS Score: 0.248 Quality: mid

← Back to all hypotheses

Provenance trace

Audit trail · saxagliptin → SOD1 → familial amyotrophic lateral sclerosis

6 source papers, 6 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 papers6
2Extracted claims6

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.

  • saxagliptinupregulatesSOD1A→B
    "in CD34+ cells from early type 2 diabetes patients treated with metformin"confidence 0.90· extraction run #27· claim #193190
  • SOD1associated_withfamilial amyotrophic lateral sclerosisB→C
    "in Norwegian ALS patients"confidence 0.75· extraction run #15· claim #32940
  • SOD1causesfamilial amyotrophic lateral sclerosisB→C
    "in humans"confidence 0.90· extraction run #15· claim #33305
  • SOD1associated_withfamilial amyotrophic lateral sclerosisB→C
    "North Indian family"confidence 0.95· extraction run #21· claim #97967
  • SOD1associated_withfamilial amyotrophic lateral sclerosisB→C
    "in silico analysis of A4F and A4V variants"confidence 0.90· extraction run #21· claim #98773
  • SOD1causesfamilial amyotrophic lateral sclerosisB→C
    "Chinese pedigree with autosomal dominant inheritance and reduced penetrance"confidence 0.95· extraction run #21· claim #101174
3Bridging logicSwanson ABC
Drug
saxagliptin
upregulates
1 paper
Mediator
SOD1
associated_with
5 papers
Outcome
familial amyotrophic lateral sclerosis
edge_support_log_ab
log(ab + 1) = 0.693
edge_support_log_bc
log(bc + 1) = 1.792
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 scoringmid · 0.248
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
0.2485
outreach score
0.2485
quality tier
mid
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.

0.000.100.200.300246 score evidence count May 12, 2026 · score 0.248 · 6 evidence · CT: none · Lit: novel_signalMay 12freezeMay 13, 2026 · score 0.248 · 6 evidence · CT: none · Lit: novel_signalMay 13monthly
Score (left axis) Evidence count (right axis, dashed)