Een modelfamilie die leren compileert tot één artefact: byte-identiek op elke architectuur, zonder seeds, en overal herafspeelbaar.
Samenvatting: Adaptive Binary Memory Networks (ABMN) ask a narrow question: can a learned model be fully and truly deterministic on every architecture, with no seeding involved, and does that property survive a change of task? The family answers with a contract rather than a tolerance. ABMNs do not compress or quantize a trained network, they compile it. One build produces the artifact, that artifact is byte identical wherever it is built, and it replays the same decisions on every host that opens it. What is deployed is the model itself, not a floating point checkpoint identified within a numerical error bound. This paper states the contract, the evidence a build has to carry and the limits of what it covers, then holds it across sequence labelling, classification, retrieval reranking and lexical retrieval, and carries it to a structurally different logical learner.
Deterministische named entity recognition, gecompileerd in plaats van gecomprimeerd, en byte-identiek op elke architectuur.
Samenvatting: ABMN-NER asks whether the ABMN build contract holds for sequence labelling, where every decision depends on the tokens around it and a small difference propagates along the sentence. The terms are the ones the family paper sets out. Nothing is compressed or quantized: learning is compiled into one deployed artifact, that artifact is byte identical on every architecture with no seeding involved, and decoding is exact rather than approximate, so the same text replays the same labelled sequence on any host that opens it. Figures are reported per dataset and per host. On CoNLL-2003, on an Intel i9, the artifact reaches 91.24% F1 and tags 606,000 tokens per second. Further datasets and benchmarks are reported in the paper itself.
Gesuperviseerde tekstclassificatie gecompileerd tot één artefact: byte-identiek op ARM en x86, zonder seeds en zonder kwantisatie.
Samenvatting: ABMN-Classification asks what the build contract costs on ordinary supervised text classification, and whether it survives a change of instruction set. Learning is compiled rather than compressed or quantized: the deployed artifact is the model, one build produces it with no seeding involved, and it replays the same predictions wherever it is opened. Independent builds of all eleven tasks produced byte identical artifacts and identical prediction streams across ARM and x86. Measurements are per dataset and per host. On DBpedia-14, on an Intel i9, the artifact reaches 98.89% accuracy and 98.89% macro F1; on IMDb, on the same host, it sustains 90.75 million tokens per second at 1.38 microjoules per token. The full set of datasets and benchmarks appears in the paper.
Onderwerpen: Tekstclassificatie, MASSIVE, DBpedia-14, Reproduceerbaarheid tussen architecturen, Energie per token
Deterministische herrangschikking van kandidaten, gecompileerd tot één artefact, zonder dicht model in het uitvoeringspad en met dezelfde volgorde op elke host.
Samenvatting: ABMN-Ranking asks whether the build contract reaches a stage that is normally served by a dense model: reranking a candidate list. It does not compress or quantize such a model, it replaces the stage with a compiled artifact, so no dense vector or transformer inference runs in the hot path and scoring is exact integer work. One build produces the artifact, no seeding is involved, and the same query returns the same ordering on every architecture that opens it. Figures are per dataset and per host. On SciFact, on an Intel i9, the artifact reaches 0.809 nDCG@10 at 14,059 queries per second, which is 593 microseconds per query. Additional datasets and benchmarks are set out in the paper.
Onderwerpen: Herrangschikking bij zoeken, Zoekrelevantie, SciFact, Latentie per query, Deterministische rangschikking
Corpusadaptieve lexicale retrieval, gecompileerd tot één artefact, deterministisch en identiek op elke architectuur zonder seeds.
Samenvatting: ABMN-Relevance asks whether the build contract reaches the retrieval stage itself, where the corpus rather than a training run decides what the deployed model contains. The index is compiled into one artifact rather than compressed or quantized, and retrieval over it is deterministic: no seeding is involved, and the same artifact replays the same ranking on every host and every architecture it is opened on. Against a tantivy BM25 baseline over the same collection it returns better ranked results and serves them faster, from a smaller index and a lower resident memory footprint. The measured numbers are held back until the paper publishes. What is claimed here is the contract, and that a lexical retrieval index can be held to it.
Onderwerpen: Lexicale retrieval, Zoekindexering, MS MARCO, Indexomvang, Herafspeelbare retrieval
Reproduceerbare binaire modelcompilatie doorgetrokken voorbij associatieve classificatie naar een structureel ander logisch leermodel.
Samenvatting: ABMN-Tsetlin asks whether the build contract is a property of one model family or of the approach behind it. It takes a structurally different logical learner, trained by a different rule, and holds it to the same terms. The trained Tsetlin machine is compiled into one deployed artifact rather than compressed or quantized. Across five image and text tasks that artifact came out byte identical on every architecture, with no seeding involved, and replays the same decisions wherever it is opened. Results are recorded per dataset and per host. On MNIST, on an Intel i9, it reaches 97.61% accuracy from a 40.4 KiB artifact. The paper carries the remaining datasets and benchmark tables.
Onderwerpen: Tsetlin-machines, Logisch leren, MNIST, Beeldclassificatie, Bewijs per host
Dit zijn werkende concepten. De repository toont geen tijdschrift-, conferentie- of peer-review-uitkomst.
Kies de doelgroep die bij je vraag past
De pagina bevat drie selecteerbare lezingen van hetzelfde onderwerp.
Voor consumenten
Working papers met gemeten resultaten en leesbare samenvattingen; elk concept geven we op aanvraag vrij. Elk getal blijft gekoppeld aan taak, dataset, configuratie en omgeving.
Voor bedrijven
Alle zes vermeldingen zijn working papers uit juli 2026. De repository legt de bron en de claimgrenzen vast; hij toont geen indiening, peerreview of publicatie aan.
Voor engineers
Papers die beschrijven hoe de stack is gebouwd, niet alleen wat hij bereikt. Lees ze om te begrijpen waarom een subsysteem zo is ontworpen. Elke vermelding blijft gelabeld als working paper.