Published June 13, 2026 | Version 2.0.0

RUNA-2: a directional typed biosemiotic knowledge-graph embedding for European ecology (v2.0.0)

Authors/Creators

  • 1. AGNT ECO

Description

RUNA-2 is a directional revision of RUNA-1, a typed biosemiotic knowledge-graph embedding (BoxE, PyKEEN) of European ecological interactions.

What changed (v1.4 → v2.0): RUNA-1 was direction-blind on its most important relations — it scored reversed trophic triples higher than correct ones (overall directionality 0.53, barely above chance; preysOn 0.26, eats 0.45, pollinates 0.24). The root cause, verified from the shipped model, was training with create_inverse_triples=True, which symmetrizes the per-relation boxes and destroys direction. Retraining with create_inverse_triples=False restores directionality to 0.98 (preysOn 0.96, eats 0.99, pollinates 1.00) with no hard negatives and no architecture change, and with no regression on already-correct symmetric relations.

Provenance: the retrain, the leak-free MRR benchmark, the per-relation directionality figures and the architecture sweep were produced by the model-training session (RTX 5090) and are documented in RUNA_v2_recommendation.md in the bundle; they are reported as-measured by that session. The directionality battery in RUNA_v2_verification_and_generation.md was independently run against the live v2.0 endpoint.

Ranking is unchanged. On an honest leak-free split (split by unordered entity-pair), v1.4 scores MRR 0.114 and v2.0 scores 0.118 — the same ranker. v1.4's originally-reported ~0.30 MRR was measured on a leaky random split that both inflated MRR and hid the direction flaw. An architecture sweep (RotatE, PairRE) confirms the ~0.12 MRR is a data ceiling, not an architecture limit.

Use: v2.0 fixes direction, not ranking — score_interaction is now directionally trustworthy, but RUNA remains a candidate seeder, not an arbiter. A confident forward>reverse margin means the model is sure which way the arrow points, not that the edge is real; candidates must still be gated by external evidence. This deposit includes the retrained model, the full retrain/diagnosis writeup, an independent verification battery against the live endpoint, and a directed candidate-generation report.

Notes

v1.4.0 adds the navigatesBy relation (senses->navigation: magnetic/sun/star/olfaction), ingests literature-confirmed magnetoreception facts, removes a 15-edge ash-dieback contamination cluster (Hymenoscyphus fraxineus now resolves ash correctly), and anchors sparse endemics (Saimaa seal, aspen bracket, stag beetle). 53,099 entities / 33 relations / 421,952 edges. Validation: MRR 0.301 held; temperature rho 0.576, pH 0.316 - within seed variance of v1.3 (same-data control under seed 43: 0.569 / 0.298). New VERSION of concept 10.5281/zenodo.20630499. Novelty is the relation schema + frozen triples + derivation/verification code, hashed in MANIFEST.sha256.

Files

RUNA_v2_directed_candidates.csv

Files (52.9 MB)

Name Size Download all
md5:a68209861de3a1bab1e8b2ba6c4a5562
52.9 MB Download
md5:3c7f4afb9ddcf145f1717adb529f8563
22.2 kB Preview Download
md5:f7f22400882a627b0c680f2cb817659b
4.5 kB Preview Download
md5:d9ce9e2a456a2853415b5ca85e9fb526
5.0 kB Preview Download

Additional details