Changelog

Last updated: September 19, 2026

Unreleased | Media Lens preview (not deployed)

• Added an experimental, unreleased Media Lens mode for public articles, ads, speeches, and campaign material, evaluated separately from Clarity as evidence-linked Language, Claims, Coverage, and Source context, with no overall score.
• Media Lens runs behind a local worker process that you or an operator run; the default and only continuous-integration-tested mode uses local example fixtures with no network calls.
• Clarity's files, scoring, safety logic, and privacy behavior are unchanged; Media Lens code is isolated from Clarity and is excluded from this site's deployment.
• Privacy, Limitations, and Acceptable Use now describe a possible future Media Lens live URL path as disabled, not deployed, and not available on the public site, without enabling it. Live pasted-text analysis remains prohibited. Clarity on-device analysis is unchanged.

September 3, 2026 | Clarity brand overhaul

• Reframed the public experience around Clarity, a private communication literacy product by Manipulation Score.
• Replaced the previous landing-page composition with the pause-field brand system and a clearer route into Learn and Analyze.
• Updated the wordmark, icon, manifest, metadata, and shared page shell without changing screening logic, safety behavior, or privacy architecture.
• Service worker cache: clarity-v37.

September 3, 2026 | Visual refresh

• Recomposed the public landing page around a calm private-screening workspace with clearer visual hierarchy and a more legible analysis preview.
• Added visible pattern tags and local-context cues to the illustrative hero card without changing screening logic, scoring, or methodology.
• Refined the Learn/Analyze entry cards and preserved keyboard focus and reduced-motion behavior.
• Service worker cache: clarity-v36.

August 17, 2026 | Public screening v0.3.3

• Platform site: Home, Learn (twelve functions), and Analyze as separate doors.
• Labeled gold harness for benign, autonomy, coercive, and safety slices. Regression count only, not a published accuracy study.
• Clause-aware scoring exclusions; class-based fiction/training and requested-logistics safety filters.
• Thread results name the highest band and how many messages sit in High/Moderate.
• Pause, boundary, and clarify responses all shown.
• Image upload remains disabled. Trust-strip wording is “Free, on your device.”
• Service worker cache: clarity-v35.

August 3, 2026 | Controlled Beta candidate v0.3.2

• History writes require the visible checkbox in the submitting tab; cross-tab storage sync added.
• Results clear when message text changes before re-analysis.
• Unicode normalization, message-boundary safety detection, and expanded negation/word boundaries.
• English-only abstention for unsupported languages; image upload disabled for this candidate.
• Pilot UI shows pattern bands without a 0-100 number; score explainer details fixed.
• Methodology updated for thread aggregation and v0.3.2.
• Expanded and locked the declared 40-case critical and 40-case benign safety corpus.
• Removed the remaining illustrative number, hid the disabled OCR control, and aligned Contact with v0.3.2.
• Service worker cache: clarity-v34.

August 3, 2026 | Controlled Beta v0.3.1

• Fixed Clear so the history opt-in checkbox stays synchronized with saved state.
• Thread screening no longer shows a numeric score when every message abstains.
• Smart apostrophes and extra whitespace no longer erase pattern matches.
• Safety attribution fixes: first-person threats after comma-and are detected; quoted training examples stay excluded.
• Regex word-boundary fixes reduce false violence evidence on words like “your.”
• Consistent Controlled Beta labeling across hero, results, and methodology.
• Service worker cache: clarity-v32.

August 3, 2026 | Controlled Beta v0.3.0

• Evidence-based score calibration: high, medium, and low specificity tiers; single broad matches no longer auto-escalate to Moderate.
• Expanded safety patterns for confinement, violence, stalking, and conditional self-harm variants.
• Benign safety-context handling for quotations, rehearsals, idioms, and protective instructions.
• Working email contact routes: feedback@ and security@manipulationscore.com.
• Mobile menu focus management improved.
• Service worker cache: clarity-v31.

Controlled Beta is an experimental testing stage. It does not imply validation, clinical accuracy, or safety-performance guarantees.

August 3, 2026 | Screening v0.2.8

• Fixed supportive-context false positives where autonomy phrases such as “whatever time you need to think” triggered Assigned obligation.
• Added instructional and procedural exclusions for training “nobody is required” and policy language.
• Added Round 11 regression and benign adversarial test suites.
• Skip link now moves focus to the main content region.
• Service worker cache: clarity-v30.

August 3, 2026 | Site trust pages

• Published Methodology, Contact and Corrections, Acceptable Use, Accessibility, and Changelog pages.
• Updated footer navigation, sitemap, and service worker shell for new pages.
• Screening logic remains v0.2.7 (no scoring or safety rule changes in this build).

August 2, 2026 | Screening v0.2.7

• Split explicit-future and continuous-adverb first-person stalking escalation.
• Require menace for single continuous-adverb stalking behaviors.
• Fixed benign false positives on requested pickups, rides, walks, and agreed meetings.
• Service worker cache: clarity-v28.

August 2, 2026 | Screening v0.2.6

• Extended demonstration phrasing for instructional attribution.
• Added refusal menace phrases (told/asked me to leave, go away, stop).
• Fixed news quotation plus real refusal-violating conduct false negative.

August 2, 2026 | Screening v0.2.5

• Filtered attributed behaviors before multi-behavior stalking counts.
• Fixed instructor and fictional two-behavior stalking quotation false positives.

August 2, 2026 | Screening v0.2.4

• Two-stage contextual stalking model (behavior plus menace).
• Removed generic unless you conditional-access scoring.
• Fixed coercive arrival false negative and invitation false positives.

Earlier alpha releases

• v0.2.3-v0.2.2: Expanded stalking patterns, clause-scoped negation, training attribution.
• v0.2.1: Per-sentence safety with local negation and attribution.
• v0.2-alpha: History opt-in (v2), abstention below 15 words, safety override, exclusion rules.

Known limitations

See Methodology for evaluation status, regression scope, and foreseeable failure modes. Clarity has not completed a representative validation study on natural messages.