Проверка источников и цитирование

Почему проверка источников важна

Правило двух источников

from urllib.parse import urlparse

def extract_domain(url: str) -> str:
    return urlparse(url).netloc.replace('www.', '')

def is_verified(fact: str, all_facts: list[dict]) -> bool:
    matching_domains = set()
    for f in all_facts:
        if fact.lower() in f['fact'].lower() or f['fact'].lower() in fact.lower():
            matching_domains.add(extract_domain(f['source']))
    return len(matching_domains) >= 2

# Example
facts = [
    {'fact': 'Inflation peaked at 9.1% in June 2022', 'source': 'https://bls.gov/cpi'},
    {'fact': 'US inflation hit 9.1% peak in mid-2022',  'source': 'https://reuters.com/article/a'}
]
print(is_verified('inflation peaked at 9.1%', facts))  # True

Семантическое сопоставление на основе LLM

import openai, json

client = openai.OpenAI(api_key='YOUR_OPENAI_KEY')

def claims_are_equivalent(claim_a: str, claim_b: str) -> bool:
    prompt = (
        f'Are these two statements making the same factual claim?\n'
        f'A: "{claim_a}"\n'
        f'B: "{claim_b}"\n'
        f'Answer JSON: {{"equivalent": true/false}}'
    )
    resp = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': prompt}],
        response_format={'type': 'json_object'}
    )
    return json.loads(resp.choices[0].message.content).get('equivalent', False)

print(claims_are_equivalent(
    'CPI hit 9.1% in June 2022',
    'US consumer prices rose 9.1 percent year-over-year in June 2022'
))  # True

Оценка качества источников

from datetime import datetime, timezone

HIGH_AUTHORITY_DOMAINS = [
    'gov', 'edu', 'nature.com', 'science.org', 'pubmed.ncbi.nlm.nih.gov',
    'reuters.com', 'bbc.com', 'apnews.com', 'who.int'
]

def score_source(url: str, publication_date: str | None) -> float:
    score = 0.5   # baseline
    domain = extract_domain(url)
    tld = domain.split('.')[-1]

    # Domain authority
    if any(ha in domain for ha in HIGH_AUTHORITY_DOMAINS):
        score += 0.3
    elif tld in ('gov', 'edu', 'org'):
        score += 0.1

    # Recency
    if publication_date:
        try:
            pub = datetime.fromisoformat(publication_date)
            days_old = (datetime.now(timezone.utc) - pub.replace(tzinfo=timezone.utc)).days
            if days_old < 365:
                score += 0.1
            elif days_old > 1825:  # 5 years
                score -= 0.1
        except ValueError:
            pass

    return min(1.0, max(0.0, score))

Сопоставление утверждений с источниками

def cross_reference(claim: str, all_facts: list[dict]) -> list[dict]:
    supporting = []
    seen_domains = set()

    for fact in all_facts:
        if claims_are_equivalent(claim, fact['fact']):
            domain = extract_domain(fact['source'])
            if domain not in seen_domains:  # only one per domain
                seen_domains.add(domain)
                supporting.append({
                    'source': fact['source'],
                    'domain': domain,
                    'fact':   fact['fact'],
                    'score':  score_source(fact['source'], fact.get('publication_date'))
                })

    return sorted(supporting, key=lambda x: x['score'], reverse=True)

Проверка квалификации авторов

def assess_authorship(url: str, page_text: str) -> dict:
    prompt = (
        f'From this webpage text, extract:\n'
        f'1. Author name(s) (or null)\n'
        f'2. Author affiliation/credentials (or null)\n'
        f'3. Publication name (or null)\n'
        f'Return JSON: {{"authors": [], "affiliation": null, "publication": null}}\n\n'
        f'TEXT:\n{page_text[:2000]}'
    )
    resp = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': prompt}],
        response_format={'type': 'json_object'}
    )
    return json.loads(resp.choices[0].message.content)

Пометка непроверенных утверждений

def classify_claims(claims: list[str], all_facts: list[dict]) -> list[dict]:
    classified = []
    for claim in claims:
        support = cross_reference(claim, all_facts)
        classified.append({
            'claim':       claim,
            'verified':    len(support) >= 2,
            'sources':     support[:3],  # top 3 supporting sources
            'confidence':  'high' if len(support) >= 3 else
                           'medium' if len(support) == 2 else
                           'low'
        })
    return classified

Формат цитирования: встроенные ссылки и список источников

def format_citations(classified_claims: list[dict]) -> tuple[list[str], list[str]]:
    ref_list = []
    ref_map = {}   # url -> citation number
    inline_claims = []

    for item in classified_claims:
        nums = []
        for src in item['sources']:
            url = src['source']
            if url not in ref_map:
                ref_map[url] = len(ref_list) + 1
                ref_list.append(f'[{ref_map[url]}] {url}')
            nums.append(f'[{ref_map[url]}]')

        citation_str = ''.join(nums)
        prefix = '' if item['verified'] else '[UNVERIFIED] '
        inline_claims.append(f'{prefix}{item["claim"]} {citation_str}')

    return inline_claims, ref_list

if __name__ == '__main__':
    demo_claims = [
        {'claim': 'Revenue grew 12% year over year', 'verified': True, 'sources': [{'source': 'https://example.com/report'}]},
        {'claim': 'The CEO plans to step down', 'verified': False, 'sources': [{'source': 'https://example.com/rumor'}]},
    ]
    inline, refs = format_citations(demo_claims)
    for line in inline:
        print(line)
    print('References:')
    for r in refs:
        print(' ', r)

Выявление противоречий между источниками

def find_contradictions(claim: str, all_facts: list[dict]) -> list[dict]:
    contradictions = []
    for fact in all_facts:
        if extract_domain(fact['source']) == extract_domain(claim):
            continue
        prompt = (
            f'Does fact B contradict fact A?\n'
            f'A: "{claim}"\nB: "{fact["fact"]}"\n'
            f'JSON: {{"contradicts": true/false}}'
        )
        resp = client.chat.completions.create(
            model='gpt-4o-mini',
            messages=[{'role': 'user', 'content': prompt}],
            response_format={'type': 'json_object'}
        )
        result = json.loads(resp.choices[0].message.content)
        if result.get('contradicts'):
            contradictions.append(fact)
    return contradictions

Отчет о результатах проверки

def verification_report_card(classified: list[dict]) -> dict:
    total     = len(classified)
    verified  = sum(1 for c in classified if c['verified'])
    all_sources = [
        src for c in classified for src in c['sources']
    ]
    top_domains = sorted(
        set(s['domain'] for s in all_sources),
        key=lambda d: max(s['score'] for s in all_sources if s['domain'] == d),
        reverse=True
    )[:5]
    return {
        'total_claims':    total,
        'verified':        verified,
        'unverified':      total - verified,
        'verification_rate': f'{verified/max(total,1)*100:.0f}%',
        'top_sources':     top_domains
    }

if __name__ == '__main__':
    demo_classified = [
        {'verified': True, 'sources': [{'domain': 'docs.python.org', 'score': 1.3}]},
        {'verified': False, 'sources': [{'domain': 'quora.com', 'score': 0.5}]},
    ]
    card = verification_report_card(demo_classified)
    for k, v in card.items():
        print(f'{k}: {v}')

Результат с порогом достоверности

MIN_VERIFICATION_RATE = 0.70

def should_run_more_research(classified: list[dict]) -> list[str]:
    unverified = [c for c in classified if not c['verified']]
    total = len(classified)
    if total == 0:
        return []
    rate = (total - len(unverified)) / total
    if rate >= MIN_VERIFICATION_RATE:
        return []  # Sufficient confidence — stop
    # Return search queries to verify remaining claims
    return [f'verify: {c["claim"]}' for c in unverified[:3]]

if __name__ == '__main__':
    demo_classified = [
        {'claim': 'A', 'verified': True},
        {'claim': 'B', 'verified': False},
        {'claim': 'C', 'verified': False},
    ]
    followups = should_run_more_research(demo_classified)
    print('Follow-up queries needed:', followups)

Что означает «независимые» источники в правиле проверки по двум источникам

Итоги проверки источников