How the compass works

Depolaris shows how outlets across the Indian political spectrum frame the same story — framing meaning the way a story is told: what is emphasised, what is left out, who gets quoted, and what the reader is nudged to feel. This page explains exactly how placements are made — because a rating you can't interrogate is just another opinion.

Why not left–right

A single left–right axis fails in India: parties and outlets mix cultural, economic, and federal positions freely. We use four independent axes, and show only the axes a story genuinely engages. A story that engages none gets no compass at all.

The four axes

• Cultural — Majoritarian ↔ Pluralist: how the piece frames the relationship between the religious-cultural majority and minorities. In plain words: does the telling put the majority community's interests first, or treat India as many communities with equal claims?
• Economic — Statist ↔ Market: framing of the state's role in the economy: welfare, regulation, privatisation. In plain words: should the government lead the economy, or should private business?
• Structural — Centralising ↔ Federalist: framing of Union–state relations and where power should sit. In plain words: more power in Delhi, or more power with the states?
• Institutional — Populist ↔ Institutionalist: framing of mediating institutions — courts, Election Commission, RBI — versus direct popular mandate. In plain words: should elected leaders act directly on the people's vote, or should umpire bodies like courts hold them to rules along the way?

Neither end of any axis is the "bad" end. Scores run −3 to +3 between the two named poles; 0 means the piece takes no discernible position or balances positions.

What we score — and what we never score

We score framing choices in the text: which stakeholders are quoted and which are absent; what the headline foregrounds (puts first); loaded vocabulary (words that carry a verdict rather than a description — every camp has its own: "jumla" or "godi media" thrown from one direction, "anti-national" or "urban naxal" from the other; the compass treats both alike); what is treated as cause and consequence; editorialising markers (places where opinion leaks into reporting). We never score an outlet's ownership, an author's identity, a story's subject (covering a party's event is not endorsing it), or whether conclusions favour any party. Truth of claims is a separate matter from framing and is not what the compass measures.

How a placement is made — and checked

1. Articles covering one story are clustered (grouped automatically) together.
2. The relevant axes for the story are selected (and can be: none — a story that engages no axis carries no compass).
3. Each article with readable full text is scored per axis, with a written rationale and verbatim evidence recorded internally.
4. An adversarial pass — a deliberate second reading that argues for the opposite placement — tests each score. Unstable placements are flagged, as are all extreme scores and a random sample.
5. Flagged placements face two independent checks: every cited evidence span is machine-verified to exist verbatim in the article (fabricated evidence can never pass), and a second AI model from a different provider blind-rescores the axis — "blind" meaning it never sees the first score, so it cannot simply copy it. If the two independent models agree within one point and the evidence verifies, the flag resolves as machine consensus, recorded as such. If they disagree, a human editor arbitrates.
6. A placement still awaiting resolution may appear publicly, but always marked contested (our own checks disagreed about it), with a notice explaining that our own review read the framing differently and the position is provisional. We would rather show you our uncertainty than hide it.

How stories are selected

Each edition includes up to ten deeply analysed stories. We read 55+ sources daily, but the edition is deliberately lean: quality over quantity. Courts, parliament, policy, economy, diplomacy, disasters, and exam-relevant news are prioritised; entertainment and score-line sport are demoted unless a policy hook (court, regulation, parliament, etc.) is present. Procedural and statistical items — releases, indices, weather statistics — remain eligible and appear under The record when they engage no compass axis. On thin news days we publish fewer stories rather than pad with soft news.

How the edition is ordered

Each story's divergence index is a number measuring how far apart outlets' placements sit on its axes — in plain words, how differently the same story was told across the press. It is a documented spread, not an editorial vibe. The edition leads with India stories whose framing diverges most, because that is where seeing multiple lenses matters most. Stories where the spectrum substantially agrees are given their own section — agreement is news too, and a depolarisation platform should say so as loudly as it documents division. World stories appear with a stated India stake; procedural and statistical stories appear under "The record".

Tone indicators

Separately from the compass, articles are checked for heightened language: sensationalism (making news feel bigger or scarier than the facts), inflammatory phrasing (words likely to anger one community against another), loaded vocabulary (verdict-carrying words), and emotive appeals (asking you to feel before you think), each with a severity from 1 to 3. Tone flags describe how something is said, never whether it is true and never which side it favours — measured prose about a divisive topic earns no flag, and calm-sounding misinformation earns no pass. Hover any tone chip to read the specific reason it was raised.

Beyond the press

Coverage also lists video reporting and commentary from a spectrum-spanning set of YouTube channels. In the current phase, video items are listed for completeness and linked, but not compass-scored — scoring requires text we can verify, and transcript analysis is planned. Video can join a story's coverage but never determines whether something counts as a story, and never supplies a story's title.

Mainstream vs indie — a coverage taxonomy

In The coverage, some outlets carry a small badge:Mainstream or Indie / specialist. This is not a compass label and not a quality grade. It is an editorial taxonomy so we can compare how high-volume nationals and legacy TV/digital outlets tend to frame a story versus digital-native, pole-representing, regional, and legal-specialist press. Mainstream here means the volume backbone (nationals, business press, centre-leaning legacy digital); indie means outlets we roster chiefly for spectrum depth, federalist lens, or legal-institutional expertise. The story-level "Mainstream vs indie framing" note synthesises the pattern for that day's roster only.

Outlets get distributions, not labels

We never assign an outlet a fixed label. Over time we show the distribution of an outlet's article scores per axis — the whole spread of its scores, not one summary stamp — with sample sizes (how many articles the spread is based on). Outlets drift; distributions capture that.

Limits, honestly stated

• Some outlets block automated reading of their full text; their articles are listed for coverage but not scored. We disclose this per-article.
• Scoring uses AI assistance with layered checks: adversarial review, machine evidence-verification, cross-model consensus, and human arbitration of disagreements. Some flags are resolved by machine consensus rather than a human, and are recorded as such. Errors will still occur; the corrections log is public and placements are versioned.
• This methodology is versioned (currently v0.1) and will change; changes are logged.

Plain words — a short glossary

• Compass / placement: where an article's framing sits on an axis, from −3 to +3. A dot on a line, nothing more.
• Brief: a one-line story note in "The record" — listed, not analysed.
• The backdrop: the context you'd need if you're meeting the story for the first time.
• Bridge points: the specific facts or framings that outlets across the spectrum agree on.
• Lens note ("Through this lens"): a short comparative read on what a particular outlet's telling emphasises relative to the others on the same story.
• Reading the roster: a story-level synthesis of how the listed outlets collectively tell the event — who leads with what angle, what gets foregrounded.
• Mainstream vs indie framing: how high-volume nationals and legacy outlets tend to tell a story differently from digital-native and specialist press. This is an editorial taxonomy for analysis, not a quality judgment — we disclose which outlets sit in which bucket on the methodology page roster.
• For exam prep: concrete UPSC (GS paper/topic) and CLAT (constitutional/legal) hooks plus Mains-style answer prompts — syllabus links, not coaching marketing.
• Missing from the coverage: voices or angles no outlet we read included.
• Provisional: published, but still under review — shown in amber.

Disagree with a placement?

Any outlet or reader can challenge any score via the grievance page. Appeals receive a reasoned response, and outcomes are logged publicly.