Chief Scientist Perspective | 2026-09-13 Industry Review
We first put the core claims of the public paper ActiveUMI (2025) under the microscope: combining active ego perception with wrist cameras to fill in the blind spots where contact is invisible. This does not mean that TOBI owns or operates this public dataset; what this article discusses is how to translate specifications of this kind into purchasable, auditable data-capture hardware and delivery language.
Against the public ActiveUMI specifications, organize visibility, hardware synchronization, and failed-sample retention for household tidying tasks. Explain how E2 turns paper fields into auditable capture forms, without implying that TOBI owns this dataset. Aimed at teams planning Ego datasets, VLA training, and robot transfer around 2026, emphasizing auditable delivery, versioned calibration, and hardware synchronization quality checks, while avoiding misreading public benchmarks as any single vendor's exclusive capability.
What the Paper Timeline Tells Us
Around 2025, ActiveUMI pushed community discussion toward a clear question: active Ego perception combined with wrist cameras, filling in contact-invisible blind spots. The timeline tells us that the value of a public benchmark lies in defining "what counts as a qualified first-person/embodied sample," not in implying that any hardware vendor automatically possesses data assets of equivalent scale. TOBI cites this paper for specification comparison and procurement language translation only.
If ActiveUMI is included in the 2026-09-13 procurement review, three layers should be distinguished: the timing of the paper's release and open-source links, the timing of community reproduction and secondary annotation, and the timing when enterprise-built/procured data actually enters the database. Method iterations between 2025 and 2026 often occur across these three layers; what hardware teams should track is field/schema changes, not chasing paper titles.
For scene-type tasks (slug in this paper: news-seo-079-scene-e2-home-s007), the paper's timeline also indicates when "failure cases and long-tail scenarios" were incorporated into the benchmark protocol. Constraints introduced later often affect VLA training more than early-stage scale figures; device selection should reserve the ability to retain pre- and post-contact time windows.
Dataset Boundary Statement
The ActiveUMI referenced in this article and its link https://arxiv.org/abs/2510.01607 are both in a public research context; TOBI does not claim ownership, hosting, or exclusive distribution of this dataset.
Chief Scientist's Perspective: Turning Paper Claims into Verifiable Metrics
Starting from ActiveUMI (2025), active Ego perception combined with a wrist camera fills in contact-invisible blind spots. Scientific readers should require suppliers to provide a reproducible experiment package: fixed firmware, calibration version, recording scripts, and a sync report. TOBI does not own public benchmarks; the E2 evaluation only verifies whether the hardware fields can support task designs of this kind.
When comparing against third-party specifications such as JoyEgoCam (a third-party capture device described in the EgoLive paper, not a TOBI product), device ownership and licensing boundaries should be listed separately to avoid misinterpreting the paper's capture pipeline as TOBI's factory default configuration.

Acceptable requirements for capture hardware
Translating ActiveUMI's one-line claim into procurement language starts with defining "acceptable fields" rather than restating that active egocentric sensing combined with wrist-mounted cameras fills contact-invisible blind spots. Hardware acceptance must be independently reproducible by third parties: given fixed firmware, a fixed calibration package, and a fixed recording script, anyone can export the same timeline semantics.
- Hard synchronization: whether each camera/IMU/gesture stream shares an acceptable clock domain (target jitter and measured distribution are recorded in the data card).
- Calibration: intrinsic and extrinsic parameters, along with model versions such as Kannala-Brandt, are frozen with the firmware; changing the camera, ring, or wrist unit requires regression testing.
- Container: frame timestamp units and dropped-frame markers in dual-stream HEVC/fMP4 or MCAP and similar formats must not be lost during transcoding.
- Sharding: shard duration for long-horizon dex/collaborative tasks, ~5 GB upload limits, and DatasetServer health checks.
- Failure samples: whether contact-invisible, occluded, and desynced segments are retained and labeled rather than silently deleted.
- Compliance: operator authorization, site permissions, and de-identification policies are included as delivery attachments; unrelated to the licensing of publicly released academic datasets.
The following sequence is suitable for a scientist team to write into an SOP (2026-09-13 version), bound to the E2 evaluation prototype:
- Freeze the E2 firmware and SDK versions, and provide the minimal script set to reproduce the ActiveUMI comparison experiment.
- Bench sync testing: measure cross-path offset using LED / mechanical triggers to produce a baseline report.
- Worn-state spot check: sample 50 contact-frame segments for multi-view consistency across scenarios tagged E2, ActiveUMI, household tidying, scenario.
- Ingestion QC: outputs sync_health, drop_frame, and calib_version fields.
- Training feedback: compare contact success rates using the hard-sync subset versus the soft-alignment subset, and record the results in the procurement review.

Mapped to TOBI E2 Product Capabilities
The TOBI E2 uses a binocular global-shutter stereo solution, designed for offline reconstruction and lightweight Ego front-station capture; it provides access to the IMU stream, dual-channel HEVC/fMP4 recording, and Device SDK documentation, making it suitable for turning paper-level stereo/IMU metrics into verifiable deliverable fields.
Compared with ActiveUMI: active egocentric perception combined with a wrist camera to fill the blind spot of invisible contact. On the device side, this should be translated into clickable product fields—for example frame rate / exposure / IMU frequency, offline trajectory reconstruction on the computer side (E2 reconstructs offline by default, not on-device SLAM), and whether gestures / ring / wrist share the same time domain. Readers should go to /product-e2.html and /docs.html#device-sdk to verify the README and delivery package, rather than assuming that the paper configuration equals the factory default.
When pillar=scene and E2 is the primary recommendation, it is recommended to split "paper metrics" into Must (not purchased if absent) and Stretch (co-development with R&D). Must typically covers hard synchronization, calibration version, and recording container time semantics; Stretch may cover motion capture bridging, ten-channel expansion, or cross-laboratory matrix deployment.
- E2 specification: binocular global shutter, offline reconstruction on the computer side (not on-device SLAM), lightweight human demo pre-station (when this article primarily recommends E2, it can still serve as a secondary path for networked setups).
- E6 specification: six channels + on-board SLAM + gesture recognition; host time-stamping and sharded upload are the primary solutions for dex/collaborative Ego.
- E8 specification: ten-channel sensor density + TOF + motion capture (R&D-phase target, subject to written confirmation). An R&D target suitable for high-density sensing and VIO comparison experiments; commercial confirmation of mass-production boundaries is required.
- Wrist: PPS + UART, in the same domain as the head-mounted unit, serving contact blind spots for ActiveUMI-type use cases.
- Light ring / finger ring: supplementary tool-side geometry for HaMeR / MANO-friendly annotation.

Engineering deep dive: turning paper metrics into gates by scenario
(Deep Dive · 79-1) For ActiveUMI and E2: laboratory matrix-style capture must define a three-level primary key of operator_id, session_id, and shard_id to avoid filename collisions. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Home Tidying: TOB…".
(Deep Dive · 79-2) For ActiveUMI and E2: when comparing against public benchmarks, only borrow task definitions and metrics, not data licensing boundaries. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Household Tidying: TOB...".
(Deep Dive · 79-3) For ActiveUMI and E2: Ego-to-robot transfer should include a separate coordinate-frame appendix: the transform chain for head, wrist, world, and robot_base. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Household Tidying: TOB...".
(Deep Dive · 79-4) For ActiveUMI and E2: if HEVC transcoding rewrites timestamps, the original_pts field must be preserved in metadata. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Home Tidying: TOB…".
(Deep dive \u00b7 79-5) For ActiveUMI and E2: ring-based point completion suits sparse geometric constraints and should not replace high-resolution hand pixel supervision. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Home Tidying: TOB..."
(Deep dive · 79-6) For ActiveUMI and E2: if the device supports offline reconstruction (non-onboard SLAM) (as E6 does), the trajectory can serve as a prior and should be disableable on the training side; E2 defaults to offline reconstruction, and offline reconstruction (non-onboard SLAM) must not be written as an out-of-the-box E2 capability. Under the scene pillar, this directly relates to the delivery risk of "ActiveUMI × Home Organization: TOB…".
(Deep Dive · 79-7) For ActiveUMI and E2: collaborative ego scenarios must declare the speech/instruction synchronization strategy to avoid causal misalignment between audio and visual streams. Under the scene pillar, this is directly related to the delivery risk of "ActiveUMI × Home Tidying: TOB…"
(Deep Dive · 79-8) For ActiveUMI and E2: QA spot checks should re-run the same script on a Linux host to ensure delivery is auditable. Under the scene pillar, this is directly related to the delivery risk of "ActiveUMI × Home Tidying: TOB…"
(Extension · 79-B1) 2026-09-13 retrospective: there may be a gap between the E8 ten-channel and TOF channels in R&D integration and mass-production specifications; the contract should specify the delivery tier clearly. If your team tags=E2,ActiveUMI,Home Tidying,Scene, we recommend adding this to the project risk register.
(Extension · 79-B2) 2026-09-13 retrospective: motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. If your team tags=E2,ActiveUMI,Home Tidying,Scene, we recommend adding this to the project risk register.
(Extension · 79-B3) 2026-09-13 retrospective: global shutter reduces geometric distortion compared with rolling shutter in fast lateral-motion scenarios, benefiting stereo matching. If your team tags=E2,ActiveUMI,Home Tidying,Scene, we recommend adding this to the project risk register.
(Extended · 79-B4) 2026-09-13 retrospective: the choice of 65mm-level baseline affects depth accuracy and wearing volume, and should be consistent across the product page and the data card. If your team tags=E2,ActiveUMI,home tidying,scene, it is recommended to write this into the project risk register.
(Extension · 79-B5) 2026-09-13 retrospective: fMP4 segments are convenient for browser preview, but the training side requires a raw or lossless backup strategy. If your team tags=E2,ActiveUMI,Home Tidying,Scene, we recommend adding this to the project risk register.
Frequently Asked Questions (FAQ)
Q: Does TOBI provide the ActiveUMI dataset? Not provided. ActiveUMI is a public research/community resource; TOBI only discusses specification comparison and capture hardware capabilities.
Q: Can the E2 alone reproduce all of the paper's results? No, it cannot be automatically guaranteed. The papers also involve task design, annotation toolchains, and training code; the hardware is responsible for making the timeline and sensor fields verifiable and acceptable.
Q: What does the demo animation demo-eval.webp represent? An illustrative animated image showing the E2 in actual recording and wearing configuration. Not official ActiveUMI release material.
Q: What attachments should I prepare when requesting a quote? Recommended attachments: https://arxiv.org/abs/2510.01607, a target hours/scenario table, a Must-field checklist, and whether wrist/ring/matrix networking is required.
Next step: specification comparison and evaluation prototype
If you are planning an E2,ActiveUMI,Home Tidying,Scene scenario against ActiveUMI, please contact TOBI with your Must-field checklist to apply for an E2 evaluation unit or a joint dataset delivery plan.
Read E2 Product Page, Developer Documentation · Device SDK, or Submit Quote Request and Technical Evaluation.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 1) Inconsistent versions of the wrist-mounted and head-mounted extrinsic calibration cause a systematic shift in MANO supervision. Run regression tests when the wearer changes. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 2) Semantic gestures can serve as weak supervision, rather than independent labels, only when the OpenXR gesture stream and video frames share the same time base. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 3) DatasetServer shard limits and disk flush strategy affect whether the "last frame" is lost. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 4) Matrix-style data capture in the lab should define a three-level primary key of operator_id, session_id, and shard_id to avoid filename collisions. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 5) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 6) Ego-to-robot transfer should include a separate coordinate frame attachment: the transformation chain for head, wrist, world, and robot_base. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 7) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 8) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 9) If the device has on-board SLAM (e.g., E6), the trajectory can serve as a prior and must be disableable on the training side; E2 defaults to offline reconstruction, and offline reconstruction (not on-board SLAM) must not be written as an E2 factory capability. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 10) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 11) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 12) Illumination variation in kitchen and home long-tail scenarios requires exposure strategy to be written into the SOP: fixed, manual, and adaptive modes must be consistent. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 13) When 60fps stereo capture is combined with a 30fps auxiliary stream, clearly specify the downsampling and phase rules. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 14) When aligning 200Hz IMU with video frames, it must be declared whether interpolation or nearest-neighbor is used, along with boundary frame handling. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 15) ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; Ego devices should align to equivalent semantics. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 16) Open X-Embodiment emphasizes cross-platform action distributions; the Ego field schema should reserve an embodiment_id field. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 17) DROID-class robot data lacks human priors; E2's lightweight Ego is suitable as a pre-stage for human demonstration. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 18) The HaMeR lineage is sensitive to occlusion; ring + multi-path redundancy reduces the proportion of invisible frames. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 19) ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted plus head-mounted streams is the procurement-grade answer. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 20) World model training relies more on long-duration consistent timelines; random cropping of short clips destroys state continuity. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 21) Diffusion policies are sensitive to contact phase; the data card should annotate the start and end frames of contact_phase. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 22) The Sim2Real pipeline should not use different timestamp units in sim and real. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 23) Enterprise content funnel: paper page → spec page → prototype → small-batch data → scaled procurement, with exit criteria at each step. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 24) This article focuses on engineering acceptance field descriptions, so that procurement and algorithm teams can copy them directly into RFQ attachments. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 25) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 26) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 27) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 28) There may be a gap between the E8 ten-channel and TOF channels in R&D integration versus mass-production specifications; the contract should specify the delivery level clearly. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 29) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 30) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 31) The choice of 65mm-level baseline affects depth accuracy and wearing volume, and should be consistent across the product page and data card. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 32) fMP4 segments facilitate browser preview, but the training side requires a raw or lossless backup strategy. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 33) MCAP is well-suited to the ROS2 ecosystem; field naming should follow the team's schema registry. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 34) Scripts like linux_run_time_sync.sh should be versioned and cross-referenced with the firmware README. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 35) The open-source e2-sdk/e6-sdk only helps you get started; mass-production procurement still follows the commercial delivery package. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 36) When multiple capture operators work in parallel, mixing NTP and hardware time sources will prevent shards from being merged; a unified time source must be used. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 37) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 38) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 39) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 40) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 41) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 42) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 43) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 44) The algorithm team should document the observation–action causal window in the data card, including whether frames from multiple streams are retained for 120ms before contact and 200ms after contact. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 45) During procurement review, require the supplier to provide P50/P95 curves of sync jitter, not single-point marketing figures. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 46) In long-duration dex capture, thermal drift and bandwidth contention amplify soft alignment errors; hardware triggering is superior to pure software timestamping. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 47) Failed samples must include a timeline health score; otherwise, VLA will treat interpolated frames after repair as real contact. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 48) Cross-day capture requires declaring the time source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-079-scene-e2-家庭-s007 · 49) Inconsistent versions of the wrist-mounted and head-mounted extrinsic calibration cause a systematic shift in MANO supervision. Run regression tests when the wearer changes. When assessing E2 against ActiveUMI (2025), archive this together with the acceptance checklist dated 2026-09-13.