SOTA: epistemic ancestry tracking so more agents do not count as more evidence
Los mantenedores suelen responder en 1 día
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 5/5
- Tiempo estimado
- Más de una semana
- Aptitud para principiantes
- 25/100
Línea de trabajo
Empieza reproduciendo el benchmark público de ESB sin integrar RuVector, utilizando sus salidas congeladas, pruebas, benchmark independiente, dependencias fijadas, semillas fijas y una ruta sin red. Después compara los cuatro enfoques de agregación enumerados y define el adaptador de RuVector y los casos específicos de RuV. Se considera terminado cuando la calibración con datos reservados mejora materialmente, la corroboración falsa disminuye al menos un 50 %, la utilidad de la tarea no baja más de 2 puntos, el recorrido sigue estando acotado y no se producen regresiones entre ámbitos ni de autoridad.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Finding
Epistemic Sybil Resistance (arXiv:2609.01873, submitted 2026-09-01) formalizes a failure mode that directly affects distributed RuV intelligence: another agent report is not another independent observation.
The originating team reports more than 20,000 controlled LLM report and extraction calls. Holding one evidence root fixed while report multiplicity grows from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263. Increasing true evidence-root multiplicity closes the gap. They also measure correlated extraction error among repeated agent calls and show that report-space deduplication tracks surface similarity much more strongly than actual evidential ancestry.
The public reproducibility repository is MIT licensed for code and includes frozen outputs, tests, a standalone benchmark, pinned dependencies, fixed seeds, and a no-network reproduction path.
RuV implication
RuVector, Ruflo, Autogenous, LatentMesh, Core Memory, and MetaHarness should reason over evidence roots and dependence, not agent count, report count, vote count, or embedding similarity.
This complements earlier correlation-aware memory work but gives a sharper invariant:
N reports from one evidence root never become N independent observations.
At the same time, common ancestry does not imply complete redundancy because independent extraction passes can still add bounded information. The model must track both ancestry and extraction dependence.
Proposed primitive
Add an experimental EvidenceAncestry graph above normal RuVector retrieval.
Each evidence-bearing artifact should be able to carry:
- immutable evidence root identifiers
- parent artifact identifiers
- observation or source class
- extractor or model family identity
- extraction attempt identity
- known shared context roots
- tenant and resource scope
- confidence and calibration metadata
- explicit
authority: none
Aggregation should estimate effective independent evidence from roots plus dependence, while retaining raw report multiplicity as descriptive telemetry only.
Benchmark
First reproduce the public ESB benchmark without integrating RuVector. Then implement a RuVector adapter and compare:
- naive report voting
- embedding or lexical deduplication
- evidence-root clustering only
- evidence-root clustering plus extraction-dependence correction
Add RuV-specific cases using multiple agents reading the same document, different documents with similar wording, the same source through multiple retrieval paths, and independent sensors producing superficially similar observations.
Metrics
Calibration coverage, Brier score, log loss, effective evidence count, false corroboration rate, missed corroboration rate, aggregation latency, index bytes, provenance traversal cost, and task utility.
Falsification
Reject the extra graph machinery if simple source-root counting performs within variance, if ancestry metadata is unavailable often enough that estimates become mostly unknown, or if dependence estimation is too unstable to improve held-out calibration.
Security and governance
Evidence ancestry is not identity authority and not execution authority. A signed agent cannot turn a duplicated source into independent evidence merely by signing it. A trusted source can still be wrong. RVM remains the privileged action boundary.
Test forged ancestry, omitted parents, cross-tenant roots, cyclic ancestry, source aliasing, identical reports from independent roots, distinct reports from one root, and correlation shifts across model upgrades.
Acceptance
Advance only if held-out calibration error improves materially over both naive voting and similarity deduplication, false corroboration falls by at least 50%, task utility does not regress by more than 2 absolute points, provenance traversal remains bounded, and zero cross-scope or authority regressions occur.
Coordinate independent reproduction through MetaHarness and record promotion state in Core Memory federation. No autonomous merge.
- Lenguaje dominante
- Rust
- Estrellas
- 4.5k
- Forks
- 603
- Merge medio
- 1 d 11 h
- PR fusionados (30 d)
- 56
Preparar el entorno
Aún no hemos revisado los archivos de configuración de este proyecto. Empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de ruvnet/RuVector
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 83/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 74/100
Los mantenedores suelen responder en 1 día
Todos los issues de ruvnet/RuVector
Issues similares
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 88/100
aws-samples/sample-pacer#76 ·
Los mantenedores suelen responder en 1 día
-
mime-type element is mandatoryAbierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 86/100
axodotdev/cargo-dist#2523 ·
Los mantenedores suelen responder en 2 días