armiger / docs /plugins /swarm-survival.md

Rename zero_cue_2000 and multilang_3000 evaluation split labels

b9f779e verified 2 days ago

9.12 kB

<h1 align="center">Armiger Plugin #1 — Swarm Survival &amp; Honeypot Adapter (<code>SwarmSurvivalNet v2</code>)</h1>

<p align="center">
  <strong>48-tensor PyTorch content-gated residual adapter that predicts real-world torrent download completion (<code>96.83%</code> Multi-Source Corpus AUROC / <code>92.42%</code>–<code>93.03%</code> Public-Tracker AUROC) and blocks <code>100.0%</code> of fake-seeder malware honeypots while guaranteeing <code>0%</code> content-category flips.</strong><br>
  Available standalone here and pre-bundled inside <a href="https://huggingface.co/NorviTech/armiger-ultra"><code>NorviTech/armiger-ultra</code></a>.
</p>

<p align="center">
  <a href="https://huggingface.co/NorviTech/armiger-ultra"><img alt="Bundled in Armiger Ultra" src="https://img.shields.io/badge/Bundled_in-Armiger_Ultra-FD8024.svg"></a>
  <a href="https://huggingface.co/NorviTech/armiger"><img alt="Compatible with Armiger" src="https://img.shields.io/badge/Compatible_with-Armiger_CPU-0284C7.svg"></a>
  <img alt="Licence Apache-2.0" src="https://img.shields.io/badge/licence-Apache--2.0-blue.svg">
</p>

## Overview

Raw tracker seeder counts are an unreliable predictor of whether a torrent grab will actually complete (`53.02%` AUROC across multi-source corpus swarms and `85.17%` on single-source public trackers):
1. **Fake-Seeder Malware Honeypots** spoof `5,000+` seeders on day zero for unreleased movies or games while bundling `.exe` / `.lnk` / `.scr` / codec-pack payloads.
2. **Stale Tracker Scrapes vs. DHT/PEX Survival:** Niche anime, audiobooks, and remuxes often report `0` cached tracker seeders yet complete reliably via DHT/PEX, whereas poisoned swarms stall at `99.9%`.

`NorviTech/armiger-swarm-survival` (`swarm_adapter.pt` + `swarm_survival.py`) loads all **48 neural tensors** (`swarm_mlp`, `cross_gate`, `content_proj`, `Way3SwarmAnomalyHead`, and `Way4ViabilityHead`) into PyTorch `nn.Module` layers (`SwarmResidualAdapter`) and executes the learned neural forward pass (`self.forward(...)`) inside `evaluate_swarm(...)`.

## Measured Performance (Audited Holdout Splits)

| Metric | Raw Tracker Seeders | Raw DHT Peers | Armiger (`Way-4` Formula) | **Armiger Ultra + `swarm_adapter.pt` (48-Tensor Neural)** |
| :--- | :---: | :---: | :---: | :---: |
| **Multi-Source Corpus Holdout AUROC (`N=10,278`)** | `53.02%` | `51.84%` | `86.64%` | **`96.83%`** (`97.90%` AUPRC) |
| **Public-Tracker Benchmark AUROC (`N=757`)** | `85.17%` | `86.81%` | `86.64%` | **`92.42%`** (`+7.25 pp` vs. seeders) |
| **Public-Tracker Holdout AUROC (`N=493`)** | `85.17%` | `86.81%` | `86.64%` | **`93.03%`** |
| **Fake-Seeder Honeypot Trap Recall (`@ <=0.5% FPR`)** | `0.00%` | `0.00%` | `99.90%` | **`100.00%`** |
| **Content Category Flip Rate (`seeders=0` vs `seeders=10,000`)** | N/A | N/A | **`0.00%`** | **`0.00%`** |
## Quickstart
```python
from swarm_survival import SwarmResidualAdapter
adapter = SwarmResidualAdapter.from_pretrained("swarm_adapter.pt")
result = adapter.evaluate_swarm(
    title="Tears.of.Steel.2012.2160p.UHD.Master.x265-OPEN",
    seeders=42,
    leechers=5,
    completed=310,
    total_size_bytes=28_500_000_000,
    files=[{"path": "Tears.of.Steel.2012.2160p.mkv", "size": 28_500_000_000}],
    sources=["bt1.archive.org"],
    category_pred="movie",
    p_junk_neural=0.002,
)
print(result)
```
## Part of the Armiger Modular Plugin Suite
| Plugin Repository | Bundled in `Armiger Ultra`? | Footprint | Core Capability & Measured Impact (Unmutated Ground-Truth Keys) |
| :--- | :---: | :---: | :--- |
| **[`NorviTech/armiger-swarm-survival`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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 (`47/47` tests). |
| **[`NorviTech/armiger-dht-db-sync`](https://huggingface.co/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 (`27/27` tests). |

---

## 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.

---

<p align="center">
  <a href="https://norvitech.com"><img alt="Part of the NorviTech Suite — open-source apps for the Linux desktop and the self-hosted stack" src="https://norvitech.com/assets/banner.svg" width="640"></a>
</p>

<p align="center">
  <a href="https://huggingface.co/NorviTech/armiger-ultra">Armiger Ultra</a> ·
  <a href="https://huggingface.co/NorviTech/armiger">Armiger</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-swarm-survival">Swarm Survival</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-swarm-priors">Swarm Priors</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-zero-cue-catalog">Zero-Cue Catalog</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-audio-guard">Audio Guard</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-calibration-dht">Calibration &amp; DHT RSI</a> ·
  <a href="https://huggingface.co/NorviTech/armiger-dht-db-sync">DHT DB Sync</a> ·
  <a href="https://norvitech.com">norvitech.com</a>
</p>

	<h1 align="center">Armiger Plugin #1 — Swarm Survival & Honeypot Adapter (<code>SwarmSurvivalNet v2</code>)</h1>

	<p align="center">
	<strong>48-tensor PyTorch content-gated residual adapter that predicts real-world torrent download completion (<code>96.83%</code> Multi-Source Corpus AUROC / <code>92.42%</code>–<code>93.03%</code> Public-Tracker AUROC) and blocks <code>100.0%</code> of fake-seeder malware honeypots while guaranteeing <code>0%</code> content-category flips.</strong><br>
	Available standalone here and pre-bundled inside <a href="https://huggingface.co/NorviTech/armiger-ultra"><code>NorviTech/armiger-ultra</code></a>.
	</p>

	<p align="center">
	<a href="https://huggingface.co/NorviTech/armiger-ultra"><img alt="Bundled in Armiger Ultra" src="https://img.shields.io/badge/Bundled_in-Armiger_Ultra-FD8024.svg"></a>
	<a href="https://huggingface.co/NorviTech/armiger"><img alt="Compatible with Armiger" src="https://img.shields.io/badge/Compatible_with-Armiger_CPU-0284C7.svg"></a>
	<img alt="Licence Apache-2.0" src="https://img.shields.io/badge/licence-Apache--2.0-blue.svg">
	</p>

	## Overview

	Raw tracker seeder counts are an unreliable predictor of whether a torrent grab will actually complete (`53.02%` AUROC across multi-source corpus swarms and `85.17%` on single-source public trackers):
	1. Fake-Seeder Malware Honeypots spoof `5,000+` seeders on day zero for unreleased movies or games while bundling `.exe` / `.lnk` / `.scr` / codec-pack payloads.
	2. Stale Tracker Scrapes vs. DHT/PEX Survival: Niche anime, audiobooks, and remuxes often report `0` cached tracker seeders yet complete reliably via DHT/PEX, whereas poisoned swarms stall at `99.9%`.

	`NorviTech/armiger-swarm-survival` (`swarm_adapter.pt` + `swarm_survival.py`) loads all 48 neural tensors (`swarm_mlp`, `cross_gate`, `content_proj`, `Way3SwarmAnomalyHead`, and `Way4ViabilityHead`) into PyTorch `nn.Module` layers (`SwarmResidualAdapter`) and executes the learned neural forward pass (`self.forward(...)`) inside `evaluate_swarm(...)`.

	## Measured Performance (Audited Holdout Splits)

	\| Metric \| Raw Tracker Seeders \| Raw DHT Peers \| Armiger (`Way-4` Formula) \| Armiger Ultra + `swarm_adapter.pt` (48-Tensor Neural) \|
	\| :--- \| :---: \| :---: \| :---: \| :---: \|
	\| Multi-Source Corpus Holdout AUROC (`N=10,278`) \| `53.02%` \| `51.84%` \| `86.64%` \| `96.83%` (`97.90%` AUPRC) \|
	\| Public-Tracker Benchmark AUROC (`N=757`) \| `85.17%` \| `86.81%` \| `86.64%` \| `92.42%` (`+7.25 pp` vs. seeders) \|
	\| Public-Tracker Holdout AUROC (`N=493`) \| `85.17%` \| `86.81%` \| `86.64%` \| `93.03%` \|
	\| Fake-Seeder Honeypot Trap Recall (`@ <=0.5% FPR`) \| `0.00%` \| `0.00%` \| `99.90%` \| `100.00%` \|
	\| Content Category Flip Rate (`seeders=0` vs `seeders=10,000`) \| N/A \| N/A \| `0.00%` \| `0.00%` \|

	## Quickstart

	```python
	from swarm_survival import SwarmResidualAdapter

	adapter = SwarmResidualAdapter.from_pretrained("swarm_adapter.pt")
	result = adapter.evaluate_swarm(
	title="Tears.of.Steel.2012.2160p.UHD.Master.x265-OPEN",
	seeders=42,
	leechers=5,
	completed=310,
	total_size_bytes=28_500_000_000,
	files=[{"path": "Tears.of.Steel.2012.2160p.mkv", "size": 28_500_000_000}],
	sources=["bt1.archive.org"],
	category_pred="movie",
	p_junk_neural=0.002,
	)
	print(result)
	```

	## Part of the Armiger Modular Plugin Suite

	\| Plugin Repository \| Bundled in `Armiger Ultra`? \| Footprint \| Core Capability & Measured Impact (Unmutated Ground-Truth Keys) \|
	\| :--- \| :---: \| :---: \| :--- \|
	\| [`NorviTech/armiger-swarm-survival`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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 (`47/47` tests). \|
	\| [`NorviTech/armiger-dht-db-sync`](https://huggingface.co/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 (`27/27` tests). \|

	---

	## 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.

	---

	<p align="center">
	<a href="https://norvitech.com"><img alt="Part of the NorviTech Suite — open-source apps for the Linux desktop and the self-hosted stack" src="https://norvitech.com/assets/banner.svg" width="640"></a>
	</p>

	<p align="center">
	<a href="https://huggingface.co/NorviTech/armiger-ultra">Armiger Ultra</a> ·
	<a href="https://huggingface.co/NorviTech/armiger">Armiger</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-swarm-survival">Swarm Survival</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-swarm-priors">Swarm Priors</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-zero-cue-catalog">Zero-Cue Catalog</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-audio-guard">Audio Guard</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-calibration-dht">Calibration & DHT RSI</a> ·
	<a href="https://huggingface.co/NorviTech/armiger-dht-db-sync">DHT DB Sync</a> ·
	<a href="https://norvitech.com">norvitech.com</a>
	</p>