NorviTech builds fast, compact, self-hosted neural models and systems tools for the Linux desktop and the self-hosted stack.
1. Armiger Core Neural Models (Audited Unmutated Ground-Truth Benchmarks)
| Model Repository | Role | Footprint | Hardware-Attributed Speed | 6-Dim Composite | 11-Class Category (Unmutated Keys) | Movie vs. TV (oct15 N=1,296) |
Audio Language (oct15 N=545) |
Swarm Liveliness (AUROC) |
|---|---|---|---|---|---|---|---|---|
NorviTech/armiger-ultra |
Unified Flagship Suite (Armiger + Ultra FP32 + armiger_inference.py + All 6 Plugins Rolled In) |
32.3 MB model (+26.0 MB BLAKE2b-64 catalog) |
0.21 ms RTX GPU / 0.29 ms M4 Pro MPS (batch-64) |
96.86% Pub / 97.60% Corpus |
95.49% oct15 / 95.12% beyond / 98.47% mlang (95.42% 5-split N=10,262) |
97.30% (96.54% beyond) |
97.80% |
96.83% Corpus / 92.42% Pub (100% trap recall) |
NorviTech/armiger |
Universal Fast CPU Classifier (ONNX INT8 + armiger_inference.py) |
8.3 MB |
2.44 ms single-item / 3.07 ms batch-64 (M4 Pro CPU) |
96.85% (96.50% Raw) |
95.06% oct15 / 92.88% beyond / 97.37% mlang (93.95% 5-split N=10,262) |
96.60% |
96.88% |
86.64% Priors (92.42% w/ Adapter) |
2. Armiger Modular Plugins (6 Standalone Repos & Rolled Into Armiger Ultra)
| Plugin Repository | Bundled in Armiger Ultra? |
Footprint | Core Capability & Measured Impact (Unmutated Ground-Truth Keys) |
|---|---|---|---|
NorviTech/armiger-swarm-survival |
Yes (swarm_adapter.pt, swarm_survival.py) |
167 KB (132 KB .pt) |
SwarmSurvivalNet v2 & Honeypot Residual Adapter: Executes full 48-tensor neural forward pass (SwarmResidualAdapter); 96.83% Multi-Source Corpus AUROC (N=10,278, vs. 53.02% raw seeders), 92.42% / 93.03% Public-Tracker AUROC (N=757 / N=493, vs. 85.17% raw seeders), 100.0% fake-seeder malware trap recall, 0.00% content-category flip guarantee. |
NorviTech/armiger-swarm-priors |
Yes (swarm_priors.py) |
29.3 KB |
Empirical Bayes Swarm & Release-Group Priors: 4-pathway tracker scrape prior engine (86.64% formula AUROC), mandatory modality dropout (p=0.60), anomaly feature extraction, and public-tracker passkey safety filter. |
NorviTech/armiger-zero-cue-catalog |
Yes (zero_cue_plugin.py, validated_zero_cue_catalog.json) |
26.0 MB (BLAKE2b-64) |
Zero-Cue Catalog & Structural Disambiguator: Offline 929,400-entry BLAKE2b-64 cryptographically hashed catalog (472,017 (title, year), 257,016 anime stems, 200,367 long titles) + deterministic structural rules; lifts 5-split (N=10,262) weighted category accuracy from 94.00% (Standalone Neural) to 95.42% (Fair Blind Hybrid), beyond_confirmation (N=1,025) from 92.88% to 95.12%, and zero_cue_2000 (N=2,000) from 87.40% to 91.50% (+4.10 pp). |
NorviTech/armiger-audio-guard |
Yes (audio_language_guard.py) |
3.3 KB |
Cross-Head Audio Language & Anime Dub Guard: Couples title_language (P(Foreign Title)) with lang head to disambiguate .en. prepositions, <Foreign>.ENG.Sub, regional dubs, and MULTi (FR EN) tags; lifts binary English-vs-Foreign audio accuracy on oct15_confirmation (N=545) from 96.88% (Standalone Neural) to 97.80% (92.75% 3-class N=772). |
NorviTech/armiger-calibration-dht |
Yes (calibration.json, calibration_and_dht.py, armiger_dht_rsi.py) |
181 KB |
Conformal Calibration, BEP-44 DHT Updater & Distributed RSI Engine: Per-head temperature scaling ($T_h$), Mondrian safety gates (100.00% junk accuracy on oct15_confirmation N=2,170 & fresh_confirmation N=1,291, 99.90% on beyond_confirmation N=977), Hybrid Ed25519+WOTS+-SHAKE256 signed BEP-44/BEP-46 DHT hot-reload, Hybrid X25519+ML-KEM-768+ChaCha20-Poly1305 AEAD, distinct-ASN quorum, and 500-canary regression gate (61/61 unit tests, 4/4 multi-instance transfer tests, 45/45 red-team exploit probes blocked). |
NorviTech/armiger-dht-db-sync |
Yes (csam_guard.py, armiger_dht_db_sync.py) |
155 KB |
Modular, CSAM-Protected, Encrypted BEP-44/BEP-46 DHT Database Sync: Multi-stage CSAM & abuse pre-ingest blocker, Hybrid PQ-signed blinded SHA-256 tombstone purge engine, 10-category $\times$ 14-language $\times$ 7-quality sharded subscriptions with strict default-off xxx isolation, X25519+ML-KEM-768+ChaCha20-Poly1305 AEAD, binary Merkle proofs, and $K$-of-$N$ distinct-ASN Sybil quorum (37/37 unit + 12-node localhost UDP Kademlia BEP-44/46 wire tests, 45/45 red-team exploit probes blocked). |
3. Ecosystem Integrations (DH-Waypoint, Bitmagnet & Torznab / Webhook Clients)
Both NorviTech/armiger-ultra and spencernorton/armiger include turnkey Docker Compose stacks and HTTP adapters under examples/ and docs/INTEGRATION_GUIDE.md for:
spencernorton/DH-Waypoint: Nativedh-waypoint.processor.v1classification,dh-waypoint.processors.admission.v1cohort admission gate, and 4-tierdh-waypoint.processors.feedback.v1closed-loop telemetry (examples/dh-waypoint/).Bitmagnet: Pre-ingest / post-crawl batch classifier, GraphQLtorrent.deletemalware/honeypot pruner, and Torznab proxy (examples/bitmagnet/).- Torznab Index Consumers (
Prowlarr,Sonarr,Radarr,Lidarr,Readarr) &qBittorrent: Pre-grab Torznab XML filtering proxy (armiger_torznab_proxy.py) and post-import webhook +ffprobeground-truth receiver (armiger_arr_webhook_receiver.py->SeriesWebhookAdapter,MovieWebhookAdapter,AudioWebhookAdapter,PublicationWebhookAdapter,QBittorrentAdapter,PhysicalGroundTruthVerifier).
Canonical Statistical Chart Audit & Cryptographic Provenance (v2.1.0)
All benchmark charts and headline metrics across the Armiger v2.1.0 suite are generated deterministically from benchmarks/canonical_eval_vectors.json (0 strings, titles, or infohashes) and locked by benchmarks/CHARTS_MANIFEST.json under four machine-enforced invariants (pytest benchmarks/test_chart_integrity.py):
- Identical Denominator Lock (
assert_identical_denominator): Every model compared on a benchmark bar shares the exact same item count $N$ and item mask (oct15_confirmation$N=2,835$;beyond_confirmation$N=1,025$; Movie-vs-TV $N=1,296$; Audio $N=545$; Anime $N=507$; Junk $N=2,170$). - Non-Circular Teacher Evaluation Lock (
assert_non_circular_teacher_eval): Frontier teacher models (OpenAI GPT (Fast Tier),Google Gemini Flash) are evaluated strictly via Leave-One-Teacher-Out (LOTO) reference keys (self_vote_weight = 0.0), removing $+1.47\text{ pp}$ and $+1.81\text{ pp}$ of circular self-vote inflation. - Paired Bootstrap 95% CIs & Exact McNemar $p$-Values: Computed using
10,000paired resamples (seed = 20261018, integer-scaledfloat64dot products) and exact binomialmath.combMcNemar tests (p = 1.42e-11vs.Google Gemini FlashLOTO;p = 3.88e-24vs.Anthropic Claude Haiku 4.5). - Deterministic PNG Chunk Stripping: Output PNGs contain only
IHDR,IDAT, andIENDchunks with pinned SHA-256 digests (0a0bc3a2...,7344ba71...,51e1f229...,1a77a643...).
Privacy & Anonymous Opt-In-By-Default DHT Sharing (opt_in_sharing=False)
Distributed DHT intelligence sharing (NorviTech/armiger-calibration-dht and NorviTech/armiger-dht-db-sync) is strictly opt-in by default and enforced by the 5-layer AnonymityGuard wire firewall when enabled (see docs/ANONYMOUS_OPT_IN_DHT.md and benchmarks/anonymous_opt_in_proof_report.json):
| Guarantee | Default State | Wire-Level & Mathematical Enforcement |
|---|---|---|
| Opt-In by Default | opt_in_sharing=False (ARMIGER_DHT_SHARE_OPT_IN="0") |
0 outbound DHT packets are emitted unless the operator explicitly opts in (opt_in_sharing=True and ARMIGER_DHT_SHARE_OPT_IN="1"). |
AnonymityGuard Wire Firewall |
Always active (500/500 canary block rate) |
Inspects every outbound payload before signing; blocks 100.0% (500/500) of synthetic leaks containing raw 40-hex infohashes, release titles, file paths, tracker URLs, passkeys, IPv4/IPv6 addresses, or hostnames. |
Ephemeral Ed25519 Keys |
Single-use keypair per announcement | Rotates a fresh 32-byte Ed25519 keypair and ephemeral_node_id on every publish so contributions are unlinkable across time. |
| Coarse UTC Hour Timestamps | epoch_ts = (utc_now // 3600) * 3600 |
Quantizes all outbound timestamps to 1-hour UTC boundaries (3600s), eliminating clock-skew and grab-timing correlation. |
| DP-Clipped Weight Deltas | clip_norm = 1.0, noise_multiplier = 0.05 |
Clips calibration/adapter update vectors in $L_2$ norm (<= 1.0) and adds calibrated Gaussian noise ($\sigma = 0.05$) before hybrid X25519 + ML-KEM-768 + ChaCha20-Poly1305 encryption. |
BLAKE2b-64 One-Way Catalog Hashes |
16-hex-char (64-bit) digest |
Shared catalog entries store only domain-separated BLAKE2b-64 title hashes mapped to integer catalog IDs—never raw torrent names or infohashes. |
Intended Use & Legal Compliance
Armiger, Armiger Ultra, and all bundled plugins are open-source machine learning and cryptographic metadata-classification utilities designed strictly for lawful use cases, including:
- Organizing and indexing licensed, public-domain, Creative Commons, and open-source digital media, software distributions (e.g., Linux ISOs, open-source games), and educational archives (e.g., OpenCourseWare, LibriVox, Project Gutenberg).
- Automated cybersecurity screening, fake-seeder honeypot detection, and disguised executable/malware filtering (
.mkv.exe,.scr,.vbs) in peer-to-peer and decentralized storage research. - Child safety (CSAM/CSAE) pre-ingest blocking, cryptographic tombstone revocation, and adult/NSFW namespace isolation for self-hosted and decentralized indexers.
NorviTech does not condone, encourage, or support copyright infringement or the unauthorized distribution of copyrighted works. Users are solely responsible for ensuring that their use of these models and plugins complies with all applicable local, national, and international copyright and data-protection laws.
Armiger Ultra · Armiger · Swarm Survival · Swarm Priors · Zero-Cue Catalog · Audio Guard · Calibration & DHT RSI · DHT DB Sync · norvitech.com