36 historical antibacterial Phase 3 entrants (2004–2019) evaluated against PhaseFolio's rNPV engine. Pairwise AUC of 0.629 (up from 0.524 pre-Sprint-1) clears the conventional ≥0.60 PASS target. The +0.105 lift is entirely the single-asset-sponsor-fragility scored multiplier — the one Sprint-1 signal the cohort can validate, because it fires on three approvals as well as failures. Two other candidate signatures were deliberately demoted to non-scored risk flags after a pre-publication ablation; the full ablation is published below, not just the largest number.
Key finding: Sprint-1 (2026-05-16) partially closed the discrimination gap. Pre-Sprint-1 the engine's Phase 3-entry PoS was well-calibrated as a point estimate (mean ~91% vs observed 69.4% cohort approval rate) but did not discriminate approved from failed (AUC 0.524). One scored multiplier — single-asset sponsor fragility — moves AUC to 0.629 (PASS ≥0.60). It is the only Sprint-1 signal that scores, because it is the only one the cohort can validate: it fires on three approvals (plazomicin, eravacycline cIAI, lefamulin) as well as failures, so a skeptic can verify it does not merely track outcomes. The engine's value for antimicrobials remains substantially downstream of Phase 3-entry PoS — rNPV math, Monte Carlo distribution, sub-indication context, IRA terminal-value modeling.
Unlike the NSCLC cohort, which derives from a curated enrichment pipeline over 5,167 trials, the antimicrobial cohort is hand-built and verified by an LLM CMO-grade review — Claude Opus 4.7 acting in a chief-medical-officer reviewer role, not a human medical officer. Antibacterial Phase 3 programs over 2004–2019 are a small, well-bounded universe; the verification path emphasizes primary-source accuracy over scale.
Hand-curated, LLM CMO-verified (Claude Opus 4.7), and the test set — not the training set. The 36-drug cohort is verified by a Claude Opus 4.7 LLM CMO-grade pass (no human medical officer) against ClinicalTrials.gov, FDA approval letters, and SEC 8-K filings; the 4,102-trial antimicrobial enrichment in the platform's peer population is a separate corpus. Enrichment did not move AUC (0.531→0.524, within noise) — the scored path reads basic trial-metadata fields already at 97–100% coverage, which established the discrimination gap was structural and needed model features, not more data. That is what Sprint-1 addressed.
Why Phase-3 entry, not Phase-2 — the anchor-selection finding. RA and NSCLC are anchored at Phase 2 entry; this cohort is anchored at Phase 3. The rule is identical for all three — anchor at the earliest decision point at which the cohort's failure population is observable in public registries, so the cohort is not survivorship-truncated on the failure side. For antibacterials it is not: a reproducible scan of the platform's antimicrobial peer-population corpus — 4,102 trials across 81 distinct drugs — found 68 Phase-2 entrants, of which 61 progressed to Phase 3/4 and only 7 were Phase-2-terminal; at most 4 of those sit outside the 36-program cohort and none are registry-flagged as terminated or failed. Effectively zero clean Phase-2 antibacterial failures exist in the registry — a Phase-2-anchored antibacterial backtest would have a near-empty, survivorship-fatal failure arm. Phase 3 is the earliest anchor at which the antibacterial universe is small, bounded, and registry+FDA-complete, which is exactly why the 36-program cohort can be primary-source-complete. Oncology and RA Phase-2 failures, by contrast, are densely registered, so Phase-2 anchoring is unbiased there. Full cross-cohort treatment: backtest methodology.
Each drug is evaluated using only information available before its real-world Phase 3 start. The decision phase is Phase 3 entry, mirroring BIO/QLS 2021 anti-infective transition calibration.
Bars show the engine's predicted cumulative probability of success at Phase 3 entry, sorted within group. Top 12 of 25 approved + all 11 not-approved shown. Post-Sprint-1 the single-asset-sponsor failures separate downward; residual overlap in the ~0.88–0.93 band is the part of the gap one cohort-validatable multiplier does not close (the demoted M1/M2 signatures would tighten it but cannot be cohort-validated, so they are carried as non-scored flags).
| Drug | Sponsor | Mechanism | Outcome |
|---|---|---|---|
| imipenem_relebactam | Merck & Co. (relebactam in-house) | Carbapenem+BLI | Approved |
| cefiderocol | Shionogi & Co., Ltd. (Japan) | Siderophore cephalosporin | Approved |
| gepotidacin | GSK plc | Triazaacenaphthylene | Approved |
| cefepime_enmetazobactam | Allecra Therapeutics | Cephalosporin+BLI | Approved |
| sulbactam_durlobactam | Entasis Therapeutics (Innoviva subsidiary) | Sulbactam+BLI | Approved |
| dalbavancin | Durata Therapeutics (acquired Vicuron rights 2009 post-Vicuron-CRL-2007; acquired by Actavis/Allergan Nov 2014, now AbbVie) | Lipoglycopeptide | Approved |
| oritavancin | The Medicines Company (acquired from Targanta Feb 2009 post-Targanta-CRL-2008; acquired by Melinta Aug 2017) | Lipoglycopeptide | Approved |
| zoliflodacin | Innoviva Specialty Therapeutics / Entasis (in partnership with GARDP) | Spiropyrimidinetrione | Approved |
| bezlotoxumab | Merck (via Medarex → BMS + MBL co-development) | Anti-toxin B mAb | Approved |
| ceftazidime_avibactam | AstraZeneca + Forest (avibactam from Novexel acq Forest 2010; sold to Pfizer 2016) | Cephalosporin+BLI | Approved |
| meropenem_vaborbactam | The Medicines Company (acquired Rempex Dec 2013; Vabomere transferred to Melinta Jan 2018 post-approval) | Carbapenem+BLI | Approved |
| ceftolozane_tazobactam | Cubist Pharmaceuticals (acquired Calixa Dec 2009; Cubist acquired by Merck Jan 2015 post-approval) | Cephalosporin+BLI | Approved |
| omadacycline | Paratek Pharmaceuticals (acq Gurnet Point Capital/Novo 2023) | Tetracycline (aminomethyl) | Approved |
| pretomanid | TB Alliance (first not-for-profit to register a drug with FDA) | Nitroimidazole | Approved |
| telavancin | Theravance (now Cumberland for US Vibativ post-2018) | Lipoglycopeptide | Approved |
| ceftaroline | Forest Laboratories (acquired Cerexa Jan 2007; now AbbVie via Actavis-Allergan) | 5th-gen cephalosporin | Approved |
| fidaxomicin | Optimer Pharmaceuticals (acquired by Cubist 2013, now Merck) | Macrocyclic | Approved |
| ceftobiprole | Basilea Pharmaceutica (originally J&J/Cilag, 2008 CRL on data-integrity grounds) | Anti-MRSA cephalosporin | Approved |
| lefamulin | Nabriva Therapeutics (US rights divested 2022; Nabriva wound down 2023) | Pleuromutilin | Approved |
| doripenem | Shionogi (originator) / Johnson & Johnson Pharmaceutical R&D (US Ph3) | Carbapenem | Approved |
| tedizolid | Trius Therapeutics (originator; acquired by Cubist July 2013 mid-Ph3; now Merck) | Oxazolidinone | Approved |
| eravacycline_cIAI | Tetraphase Pharmaceuticals (acq La Jolla 2020 → Innoviva 2022) | Fluorocycline | Approved |
| rifamycin_sv_mmx | Cosmo Pharmaceuticals (US co-promote: RedHill → Aries Pharmaceuticals) | Rifamycin | Approved |
| delafloxacin | Melinta Therapeutics (formerly Rib-X Pharmaceuticals) | Fluoroquinolone | Approved |
| plazomicin | Achaogen (BANKRUPT 2019-04-15; assets to Cipla USA) | Aminoglycoside | Approved |
| cadazolid | Actelion (acq J&J Jun 2017; J&J discontinued April 2018) | Quinox-oxazolidinone | Failed (Ph 3) |
| sulopenem | Iterum Therapeutics | Penem | Failed (CRL/Reg) |
| cefepime_taniborbactam | Venatorx Pharmaceuticals (US partner Melinta) | Cephalosporin+boronic-BLI | Failed (CRL/Reg) |
| tebipenem | Spero Therapeutics | Penem (oral) | Failed (CRL/Reg) |
| ridinilazole | Summit Therapeutics Inc. (still active; pivoted to oncology with ivonescimab post-failure) | Bis-benzimidazole | Failed (Ph 3) |
| murepavadin | Polyphor Ltd. | LptD inhibitor (OMP-targeting peptide) | Failed (Ph 3) |
| iclaprim_motif | Motif Bio plc (defunct 2020-2021) | DHFR inhibitor | Failed (CRL/Reg) |
| eravacycline_cUTI | Tetraphase Pharmaceuticals | Fluorocycline | Failed (Ph 3) |
| surotomycin | Cubist Pharmaceuticals (acq Merck Jan 2015; development discontinued post-Trial 2) | Lipopeptide | Failed (Ph 3) |
| iclaprim_arpida | Arpida AG (acquired by Evolva 2010 post-failure) | DHFR inhibitor | Failed (CRL/Reg) |
| solithromycin | Cempra Pharmaceuticals (merged into Melinta Nov 2017; asset abandoned post-CRL) | Fluoroketolide | Failed (CRL/Reg) |
Discrimination is real but modest, and rank-only. Post-Sprint-1 pairwise AUC is 0.629 (was 0.524) with a separation gap of only 0.7pp — the engine ranks approved above failed better than chance but does not separate them with confident probabilities; point-estimate calibration (mean ~91% vs observed 69.4%) is intact. Only one of three failure signatures legitimately scores: M1/M2 are deliberately non-scored flags because they fire only on this cohort's failures with no approved counterexample, so the cohort cannot validate them. The residual gap is the deliberate cost of that honesty; closing it defensibly needs an external validation set, not a bigger in-cohort multiplier. Per-point detail, the full ablation, and the per-drug ledger are in the backtest methodology.
Engine version: PhaseFolio rNPV engine v1 · substrate methodology version: methodology@2026-05-21 · cohort verified via a 5-agent Claude Opus 4.7 LLM CMO-grade audit (no human medical officer) against primary sources (ClinicalTrials.gov, FDA approval letters, SEC 8-K filings).