Jake
26c7307607
Phase 9 of the rebrand cascade. Sweep covers everything the Phase 8
frontend pass deliberately skipped: docs/, root markdown, scripts,
Cargo.toml descriptions, code comments that survived earlier
word-boundary sed, plus a handful of identifiers caught on the final
verify pass.
transcription-app changes:
- README.md, HANDOVER.md, KNOWN-ISSUES.md, run.sh — magnotia/Magnotia
-> lumotia/Lumotia.
- docs/ — sweep across all subdirs except docs/handovers/ (preserved
as immutable audit trail). Includes architecture-map references
to magnotia_core::*, magnotia_storage::*, etc. now pointing at
lumotia_*; dev-setup.md tracing output examples (lumotia_startup
target); brief/ + superpowers/ + issues/ + whisper-ecosystem/ +
audit/.
- Cargo.toml descriptions on 9 crates (core, audio, cloud-providers,
hotkey, llm, mcp, plus referenced others).
- crates/core/src/{error,hardware,recommendation,paths}.rs +
crates/audio/src/wav.rs + crates/llm/src/model_manager.rs +
crates/cloud-providers/src/keystore.rs + crates/mcp/src/lib.rs —
doc comments and a model-manager user-agent string.
- Caught on final pass: BroadcastChannel("magnotia_task_sync") -> ...
("lumotia_task_sync"); magnotia_locale i18n localStorage key
renamed + migration shim added; CSS keyframe names
magnotiaPulse / magnotiaBar / magnotiaFade renamed in the design-
system kit; magnotia_viewer_item / magnotia_viewer_mode handoff
keys renamed in HistoryPage + viewer/+page.svelte; src/assets/
wordmark.svg text.
- src-tauri/src/lib.rs comment cleanup ("magnotia era" was sed'd
to "lumotia era" earlier — restored).
Preserved (intentional):
- crates/core/src/paths.rs — keeps "magnotia" / "Magnotia" / ".magnotia"
legacy detection strings in legacy_and_target_paths() so the
migration shim can still find user data from the magnotia era.
- src/lib/stores/{page,focusTimer}.svelte.ts + src/lib/i18n/index.ts
— migration call sites reference the legacy magnotia keys
deliberately.
- docs/handovers/ — historical audit trail.
cargo build --workspace passes. npm run check: 0 errors / 0 warnings
(3958 files). cargo test --workspace: 339 pass / 0 fail.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3.2 KiB
3.2 KiB
A2. AI Body Doubling — Controlled Studies
Core finding: AI-driven body doubles are statistically indistinguishable from human body doubles for task efficiency and sustained attention (p = 1.000), whilst eliminating the social anxiety that many neurodivergent users experience with human co-presence.
Primary evidence:
- Ara et al. 2025 (arXiv:2509.12153): 12 adults with ADHD in a VR bricklaying task across three conditions — alone (C1), human body double (C2), AI body double (C3). Repeated-measures ANOVA: F(2,22) = 6.51, p = 0.006. Both human and AI body doubles improved task efficiency by 27–30% over working alone (8.49 vs 10.82 and 11.06 bricks per minute). No significant difference between human and AI (p = 1.000). Some participants preferred AI specifically because it reduced social anxiety and performance pressure.
- Eagle, Baltaxe-Admony & Ringland 2024 (ACM TACCESS): Survey of 193 neurodivergent participants establishing that body doubling operates on a continuum of space/time and mutuality. Non-human presence — animated characters, "Study With Me" videos, even ambient audio — can function as a body double, grounded in parasocial relationship theory.
- O'Connell et al. 2024 (ACM/IEEE HRI '24): Socially assistive robot (Blossom) as body double for 11 ADHD university students over three weeks. 91% voluntarily continued using the robot. System Usability Scale score: 83.86 (above "good" threshold). Non-judgmental passive presence was the most-valued attribute.
- Lalwani, Saleh & Salam 2025 (HRI '25): Robot companions providing active micro-scaffolding (goal reminders, encouragement) outperformed mere passive presence. 80% of 15 ADHD participants expressed interest in continued use — suggesting the ideal design combines ambient presence with context-aware nudges.
- Cuber et al. 2024 (ACM CHI '24): VR study environment for 27 ADHD university students across up to 12 sessions. Significant increases in concentration, motivation, and effort during VR sessions vs. baseline.
- Schuenke, Dickenson & Moore 2025 (ACM ASSETS '25): First study to use EEG for objective neurophysiological markers of attentional state during body doubling — moving beyond self-report.
- Papadopoulos 2025 (SAGE): AI chatbot use among autistic individuals provides "qualitatively different and more profound" support through judgment-free, on-demand interaction.
Theoretical basis: Barkley's (1997) model of ADHD as a disorder of behavioural inhibition prescribes externalisation of executive functions — moving regulatory demands from impaired internal systems into the environment. Body doubling is precisely this: an external source of temporal anchoring, accountability, and arousal regulation.
Implication for Lumotia: The low-fi "Focus Room" (section 4) is strongly validated. Combine ambient AI presence with context-aware nudges for maximum effect. The AI option specifically reduces barriers for autistic users whilst maintaining comparable efficacy. Design should include: simulated progress indicators, rhythmic work pacing cues, and subtle ambient motion for divided attention support.