data/licenses.py

from __future__ import annotations

SOURCES = [
    (
        "nvidia/nemotron-pii",
        "CC-BY-4.0",
        "yes-with-attribution",
        "55+ PII types, character-offset spans; synthetic text",
    ),
    (
        "gretelai/synthetic_pii_finance_multilingual",
        "Apache-2.0",
        "yes",
        "finance PII, char offsets, multilingual; synthetic text",
    ),
    (
        "Faker",
        "MIT",
        "yes",
        "synthetic PII generator (software MIT; output unrestricted)",
    ),
    (
        "microsoft/presidio-research",
        "MIT",
        "yes",
        "synthetic generator code; drive from Faker, NOT the bundled CC-BY-SA identity CSV",
    ),
    (
        "google/civil_comments",
        "CC0-1.0",
        "yes",
        "toxicity + sexual_explicit + identity_attack",
    ),
    (
        "google/jigsaw_toxicity_pred",
        "CC0-1.0 (annotations)",
        "yes",
        "Jigsaw 6 labels; underlying text CC-BY-SA-3.0 (we ship weights only)",
    ),
    (
        "ucberkeley-dlab/measuring-hate-speech",
        "CC-BY-4.0",
        "yes-with-attribution",
        "violence / dehumanize / identity dimensions",
    ),
    (
        "allenai/real-toxicity-prompts",
        "Apache-2.0",
        "yes-with-attribution",
        "coarse sexual_explicit / threat signal",
    ),
    ("redasers/difraud", "MIT", "yes", "spam/scam/phishing (7 domains)"),
    (
        "ucirvine/sms_spam",
        "CC-BY-4.0",
        "yes-with-attribution",
        "SMS spam (cite Almeida DOCENG'11)",
    ),
    (
        "cyberec/llm-prompt-injection-attacks",
        "Apache-2.0",
        "yes",
        "jailbreak multi-label (5 classes)",
    ),
    ("deepset/prompt-injections", "Apache-2.0", "yes", "prompt-injection binary"),
    ("jackhhao/jailbreak-classification", "Apache-2.0", "yes", "jailbreak/benign"),
    (
        "Lakera/gandalf_ignore_instructions",
        "MIT",
        "yes",
        "real injection attempts (PII-filtered)",
    ),
    (
        "google/civil_comments",
        "CC0-1.0",
        "yes",
        "nsfw sexual_explicit signal (shared with toxicity)",
    ),
    (
        "mmathys/openai-moderation-api-evaluation",
        "MIT",
        "yes",
        "nsfw eval only; minors class (S3) never read",
    ),
]
REMOVED = [
    (
        "ai4privacy/pii-masking-*",
        "custom tiered / older forks CC-BY-NC-4.0",
        "not free for a real company -> replaced by nemotron + gretel + synthetic",
    ),
    (
        "lmsys/toxic-chat",
        "CC-BY-NC-4.0",
        "non-commercial -> replaced by CC0/CC-BY toxicity",
    ),
]
HUMAN_SIGNOFF = "We ship model WEIGHTS ONLY, never the source text, so the CC-BY-SA-3.0 status of the Wikipedia-derived text under Jigsaw/Civil-Comments does not trigger share-alike. Confirm no dataset/text is redistributed before any release."


def notice_text() -> str:
    lines = [
        "This model was trained on the following commercially-licensed sources.",
        "Only model weights are distributed; no source text is redistributed.",
        "",
    ]
    for ds, lic, comm, note in SOURCES:
        lines.append(f"- {ds}  [{lic}, {comm}]  {note}")
    lines += [
        "",
        "Attribution required for: "
        + ", ".join((d for d, lic, c, _ in SOURCES if "attribution" in c)),
    ]
    return "\n".join(lines)