Hypothesis #35500

niraparib IL-17A rheumatoid arthritis

Drug domain: Multiple sclerosis Outcome domain: Rheumatoid arthritis Score: 0.208 Quality: mid

← Back to all hypotheses

Provenance trace

Audit trail · niraparib → IL-17A → rheumatoid arthritis

4 source papers, 4 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 papers4
2Extracted claims4

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.

  • NiraparibinhibitsIL-17AA→B
    "in vitro reporter assay and molecular docking"confidence 0.90· extraction run #25· claim #159409
  • IL-17Aassociated_withrheumatoid arthritisB→C
    "in female RA patients"confidence 0.95· extraction run #29· claim #219762
  • IL-17Aassociated_withrheumatoid arthritisB→C
    "in patients with RA compared to healthy controls"confidence 0.90· extraction run #29· claim #240998
  • IL-17Aincreasesrheumatoid arthritisB→C
    "in two-sample Mendelian randomization analysis"confidence 0.90· extraction run #29· claim #247306
3Bridging logicSwanson ABC
Drug
niraparib
inhibits
1 paper
Mediator
IL-17A
associated_with
3 papers
Outcome
rheumatoid arthritis
edge_support_log_ab
log(ab + 1) = 0.693
edge_support_log_bc
log(bc + 1) = 1.386
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 · 0.208
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
0.2079
outreach score
0.2079
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.

0.000.100.200.3001234 score evidence count May 12, 2026 · score 0.208 · 4 evidence · CT: none · Lit: novel_signalMay 12freezeMay 13, 2026 · score 0.208 · 4 evidence · CT: none · Lit: novel_signalMay 13monthly
Score (left axis) Evidence count (right axis, dashed)