Returns sources active within the last 36 days with >100 articles analyzed, sorted by
avg_social_shares descending. The response also includes total, offset, limit, has_more,
and one shared bias_score_methodology block.

Each entry contains:
- source_name, slug_name, page_url
- articles_analyzed: total articles analyzed for this source
- avg_social_shares: average social shares per article (proxy for reach/influence)
- emotionality_score (0-10): average emotional intensity of the writing
- prescriptiveness_score (0-10): how much the source tells readers what to think/do
- bias_values: dict mapping classifier key → integer source weighted display score
  (-50 to +50 for bipolar, 0 to +50 for unipolar). Keys use the same canonical
  names as get_bias_from_url where a source aggregate is available, but article scores use
  -10 to +10 or 0 to 10. Compare direction directly; normalize before comparing magnitude.

  Political / ideological (bipolar: neg=left pole, pos=right pole):
    'liberal conservative bias'      neg=liberal, pos=conservative
    'populist elitist bias'           neg=populist, pos=elitist
    'libertarian authoritarian bias' neg=libertarian, pos=authoritarian
    'dovish hawkish bias'            neg=dovish, pos=hawkish
    'establishment bias'             neg=anti-establishment, pos=pro-establishment

  Credibility / quality (bipolar):
    'overall credibility'            neg=low credibility, pos=high credibility
    'integrity bias'                 neg=low integrity, pos=high integrity
    'article intelligence'           neg=low intelligence, pos=high intelligence
    'delusion bias'                  neg=truth-seeking, pos=delusional
    'objective subjective bias'      neg=objective, pos=subjective
    'objective sensational bias'     neg=objective, pos=sensational
    'descriptive prescriptive bias'  neg=descriptive, pos=prescriptive
    'bearish bullish bias'           neg=bearish, pos=bullish
    'optimistic pessimistic bias'    neg=pessimistic, pos=optimistic
    'interesting'                    neg=boring, pos=interesting
    'emotional bias'                 neg=negative tone, pos=positive tone
    'rational irrational bias'       neg=rational, pos=irrational
    'corporate bias'                 neg=anti-corporate, pos=pro-corporate
    'science superstition bias'      neg=scientific, pos=superstitious
    'individualist collectivist bias' neg=individualist, pos=collectivist

  Unipolar bias dimensions (higher = more of that trait):
    'opinion bias'                   opinion vs informative
    'political bias'                 political content
    'fearful bias'                   fear-based framing
    'overconfidence bias'            overconfidence
    'gossip bias'                    gossip
    'manipulation bias'              manipulative framing
    'ideological bias'               ideological rigidity
    'conspiracy bias'                conspiracy content
    'double standard bias'           double standards
    'virtue signal bias'             virtue signaling
    'oversimplification bias'        oversimplification
    'appeal to authority bias'       appeal to authority
    'begging the question bias'      question-begging
    'victimization bias'             victimization framing
    'terrorism bias'                 terrorism content
    'fraud bias'                     fraud-promoting framing
    'marxism bias'                   Marxist framing
    'islamist bias'                  Islamist framing
    'anti-semitism bias'             anti-Jewish framing
    'anti-lgbt bias'                 anti-LGBT framing
    'racism bias'                    racist framing
    'anti-enlightenment bias'        regressive, anti-liberal content
    'scapegoat bias'                 scapegoating
    'hypocrisy bias'                 hypocrisy
    'suicidal empathy bias'          suicidal-empathy framing
    'cruelty bias'                   cruelty
    'woke bias'                      woke framing
    'written by AI'                  AI-written likelihood
    'immature bias'                  immaturity
    'circular reasoning bias'        circular reasoning
    'covering the response bias'     covering-the-response tactic
    'spam bias'                      spam-like content
    'advertising bias'               advertorial or promotional content
    'speculation bias'               speculation or forecasting
    'big pharma bias'                reflexive trust in medical/pharma authority

Tip: use get_source_bias for full narrative descriptions and recent articles on a specific source.
Tip: bias_values use shared canonical names where available. Source and article score scales
differ, so normalize magnitudes.
get_source_bias exposes the same canonical keys in bias_values and retains emoji-prefixed
bias_scores only for backward compatibility.

Args:
    limit: Sources to return (1-1000, default 200).
    offset: Number of sources to skip for pagination (default 0).