Hypothesis #35466

ocrelizumab CD20 CDAI

Drug domain: Multiple sclerosis Outcome domain: Rheumatoid arthritis Score: 0.333 Quality: high

← Back to all hypotheses

Provenance trace

Audit trail · ocrelizumab → CD20 → CDAI

14 source papers, 14 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 papers14
Filter
2Extracted claims14

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.

  • Ocrelizumabbinds_toCD20A→B
    "recombinant humanized monoclonal antibody targeting CD20-expressing B cells"confidence 1.00· extraction run #25· claim #143650
  • ocrelizumabbinds_toCD20A→B
    "not specified"confidence 0.90· extraction run #25· claim #144243
  • ocrelizumabbinds_toCD20A→B
    "for multiple sclerosis treatment"confidence 0.95· extraction run #25· claim #145144
  • ocrelizumabbinds_toCD20A→B
    "in patients with relapsing-remitting multiple sclerosis"confidence 0.90· extraction run #25· claim #147406
  • Ocrelizumabbinds_toCD20A→B
    "in multiple sclerosis treatment"confidence 0.90· extraction run #25· claim #150122
  • Ocrelizumabbinds_toCD20A→B
    "in multiple sclerosis"confidence 0.90· extraction run #25· claim #153164
  • ocrelizumabbinds_toCD20A→B
    "as a humanized CD20 monoclonal antibody"polarity: neutralconfidence 0.95· extraction run #25· claim #154850
  • ocrelizumabbinds_toCD20A→B
    "general"confidence 1.00· extraction run #25· claim #157219
  • ocrelizumabbinds_toCD20A→B
    "in vitro"confidence 0.90· extraction run #25· claim #157545
  • ocrelizumabbinds_toCD20A→B
    "in relapsing multiple sclerosis"confidence 0.95· extraction run #25· claim #158001
  • ocrelizumabbinds_toCD20A→B
    "as anti-CD20 therapy"confidence 0.95· extraction run #25· claim #159654
  • Ocrelizumabbinds_toCD20A→B
    "in multiple sclerosis treatment"confidence 0.90· extraction run #25· claim #161398
  • ocrelizumabbinds_toCD20A→B
    "humanized monoclonal antibody targeting CD20-positive B-cells"confidence 0.95· extraction run #25· claim #163848
  • CD20correlates_withCDAIB→C
    "in synovial tissue of patients with advanced stage rheumatoid arthritis"confidence 0.80· extraction run #29· claim #222259
3Bridging logicSwanson ABC
Drug
ocrelizumab
binds_to
13 papers
Mediator
CD20
correlates_with
1 paper
Outcome
CDAI
edge_support_log_ab
log(ab + 1) = 2.639
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 · 0.333
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
0.3332
outreach score
0.3332
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.

0.000.100.200.300.40051015 score evidence count May 12, 2026 · score 0.333 · 14 evidence · CT: none · Lit: novel_signalMay 12freezeMay 13, 2026 · score 0.333 · 14 evidence · CT: none · Lit: novel_signalMay 13monthly
Score (left axis) Evidence count (right axis, dashed)